Search results for: convolutional architectures

Authors: Reuben Newell, Edward Archer, Alistair McIlhagger, Calvin Ralph

Abstract:

Modern industry has developed a need for innovative 3D composite materials due to their attractive material properties. Composite materials are composed of a fibre reinforcement encased in a polymer matrix. The fibre reinforcement consists of warp, weft and binder yarns or tows woven together into a preform. The mechanical performance of composite material is largely controlled by the properties of the preform. As a result, the bulk of recent textile research has been focused on the design of high-strength preform architectures. Studies looking at optimisation of the weaving process have largely been neglected. It has been reported that yarns experience varying levels of damage during weaving, resulting in filament breakage and ultimately compromised composite mechanical performance. The weaving parameters involved in causing this yarn damage are not fully understood. Recent studies indicate that poor yarn tension control may be an influencing factor. As tension is increased, the yarn-to-yarn and yarn-to-weaving-equipment interactions are heightened, maximising damage. The correlation between yarn tension variation and weaving damage severity has never been adequately researched or quantified. A novel study is needed which accesses the influence of tension variation on the mechanical properties of woven yarns. This study has looked to quantify the variation of yarn tension throughout weaving and sought to link the impact of tension to weaving damage. Multiple yarns were randomly selected, and their tension was measured across the creel and shedding stages of weaving, using a hand-held tension meter. Sections of the same yarn were subsequently cut from the loom machine and tensile tested. A comparison study was made between the tensile strength of pristine and tensioned yarns to determine the induced weaving damage. Yarns from bobbins at the rear of the creel were under the least amount of tension (0.5-2.0N) compared to yarns positioned at the front of the creel (1.5-3.5N). This increase in tension has been linked to the sharp turn in the yarn path between bobbins at the front of the creel and creel I-board. Creel yarns under the lower tension suffered a 3% loss of tensile strength, compared to 7% for the greater tensioned yarns. During shedding, the tension on the yarns was higher than in the creel. The upper shed yarns were exposed to a decreased tension (3.0-4.5N) compared to the lower shed yarns (4.0-5.5N). Shed yarns under the lower tension suffered a 10% loss of tensile strength, compared to 14% for the greater tensioned yarns. Interestingly, the most severely damaged yarn was exposed to both the largest creel and shedding tensions. This study confirms for the first time that yarns under a greater level of tension suffer an increased amount of weaving damage. Significant variation of yarn tension has been identified across the creel and shedding stages of weaving. This leads to a variance of mechanical properties across the woven preform and ultimately the final composite part. The outcome from this study highlights the need for optimised yarn tension control during preform manufacture to minimize yarn-induced weaving damage.

Keywords: optimisation of preform manufacture, tensile testing of damaged tows, variation of yarn weaving tension, weaving damage

Procedia PDF Downloads 202

Authors: M. Ciminello, I. Dimino, S. Ameduri, A. Concilio

Abstract:

Improving aircraft's efficiency is one of the key elements of Aeronautics. Modern aircraft possess many advanced functions, such as good transportation capability, high Mach number, high flight altitude, and increasing rate of climb. However, no aircraft has a possibility to reach all of this optimized performance in a single airframe configuration. The aircraft aerodynamic efficiency varies considerably depending on the specific mission and on environmental conditions within which the aircraft must operate. Structures that morph their shape in response to their surroundings may at first seem like the stuff of science fiction, but take a look at nature and lots of examples of plants and animals that adapt to their environment would arise. In order to ensure both the controllable and the static robustness of such complex structural systems, a monitoring network is aimed at verifying the effectiveness of the given control commands together with the elastic response. In order to achieve this kind of information, the use of FBG sensors network is, in this project, proposed. The sensor network is able to measure morphing structures shape which may show large, global displacements due to non-standard architectures and materials adopted. Chord -wise variations may allow setting and chasing the best layout as a function of the particular and transforming reference state, always targeting best aerodynamic performance. The reason why an optical sensor solution has been selected is that while keeping a few of the contraindication of the classical systems (like cabling, continuous deployment, and so on), fibre optic sensors may lead to a dramatic reduction of the wires mass and weight thanks to an extreme multiplexing capability. Furthermore, the use of the ‘light’ as ‘information carrier’, permits dealing with nimbler, non-shielded wires, and avoids any kind of interference with the on-board instrumentation. The FBG-based transducers, herein presented, aim at monitoring the actual shape of adaptive trailing edge. Compared to conventional systems, these transducers allow more fail-safe measurements, by taking advantage of a supporting structure, hosting FBG, whose properties may be tailored depending on the architectural requirements and structural constraints, acting as strain modulator. The direct strain may, in fact, be difficult because of the large deformations occurring in morphing elements. A modulation transducer is then necessary to keep the measured strain inside the allowed range. In this application, chord-wise transducer device is a cantilevered beam sliding trough the spars and copying the camber line of the ATE ribs. FBG sensors array position are dimensioned and integrated along the path. A theoretical model describing the system behavior is implemented. To validate the design, experiments are then carried out with the purpose of estimating the functions between rib rotation and measured strain.

Keywords: fiber optic sensor, morphing structures, strain sensor, shape reconstruction

Procedia PDF Downloads 298

Authors: Irene Capecchi, Tommaso Borghini, Iacopo Bernetti

Abstract:

An important tool for the enhancement of cultural sites is serious games (SG), i.e., games designed for educational purposes; SG is applied in cultural sites through trivia, puzzles, and mini-games for participation in interactive exhibitions, mobile applications, and simulations of past events. The combination of Augmented Reality (AR) and digital cultural content has also produced examples of cultural heritage recovery and revitalization around the world. Through AR, the user perceives the information of the visited place in a more real and interactive way. Another interesting technological development for the revitalization of cultural sites is the combination of AR and Global Positioning System (GPS), which integrated have the ability to enhance the user's perception of reality by providing historical and architectural information linked to specific locations organized on a route. To the author’s best knowledge, there are currently no applications that combine GPS AR and SG for cultural heritage revitalization. The present research focused on the development of an SG based on GPS and AR. The study area is the village of Caldana in Tuscany, Italy. Caldana is a fortified Renaissance village; the most important architectures are the walls, the church of San Biagio, the rectory, and the marquis' palace. The historical information is derived from extensive research by the Department of Architecture at the University of Florence. The storyboard of the SG is based on the history of the three characters who built the village: marquis Marcello Agostini, who was commissioned by Cosimo I de Medici, Grand Duke of Tuscany, to build the village, his son Ippolito and his architect Lorenzo Pomarelli. The three historical characters were modeled in 3D using the freeware MakeHuman and imported into Blender and Mixamo to associate a skeleton and blend shapes to have gestural animations and reproduce lip movement during speech. The Unity Rhubarb Lip Syncer plugin was used for the lip sync animation. The historical costumes were created by Marvelous Designer. The application was developed using the Unity 3D graphics and game engine. The AR+GPS Location plugin was used to position the 3D historical characters based on GPS coordinates. The ARFoundation library was used to display AR content. The SG is available in two versions: for children and adults. the children's version consists of finding a digital treasure consisting of valuable items and historical rarities. Players must find 9 village locations where 3D AR models of historical figures explaining the history of the village provide clues. To stimulate players, there are 3 levels of rewards for every 3 clues discovered. The rewards consist of AR masks for archaeologist, professor, and explorer. At the adult level, the SG consists of finding the 16 historical landmarks in the village, and learning historical and architectural information interactively and engagingly. The application is being tested on a sample of adults and children. Test subjects will be surveyed on a Likert scale to find out their perceptions of using the app and the learning experience between the guided tour and interaction with the app.

Keywords: augmented reality, cultural heritage, GPS, serious game

Procedia PDF Downloads 61

Authors: Gaurav Kumar Sinha

Abstract:

In an era defined by the proliferation of data and the utilization of cloud computing environments, the efficient transfer and processing of big data workloads across multi-cloud platforms have emerged as critical challenges. This research paper embarks on a comprehensive exploration of the complexities associated with managing and optimizing big data in a multi-cloud ecosystem.The foundation of this study is rooted in the recognition that modern enterprises increasingly rely on multiple cloud providers to meet diverse business needs, enhance redundancy, and reduce vendor lock-in. As a consequence, managing data across these heterogeneous cloud environments has become intricate, necessitating innovative approaches to ensure data integrity, security, and performance.The primary objective of this research is to investigate strategies and techniques for enhancing the efficiency of data transfer and processing in multi-cloud scenarios. It recognizes that big data workloads are characterized by their sheer volume, variety, velocity, and complexity, making traditional data management solutions insufficient for harnessing the full potential of multi-cloud architectures.The study commences by elucidating the challenges posed by multi-cloud environments in the context of big data. These challenges encompass data fragmentation, latency, security concerns, and cost optimization. To address these challenges, the research explores a range of methodologies and solutions. One of the key areas of focus is data transfer optimization. The paper delves into techniques for minimizing data movement latency, optimizing bandwidth utilization, and ensuring secure data transmission between different cloud providers. It evaluates the applicability of dedicated data transfer protocols, intelligent data routing algorithms, and edge computing approaches in reducing transfer times.Furthermore, the study examines strategies for efficient data processing across multi-cloud environments. It acknowledges that big data processing requires distributed and parallel computing capabilities that span across cloud boundaries. The research investigates containerization and orchestration technologies, serverless computing models, and interoperability standards that facilitate seamless data processing workflows.Security and data governance are paramount concerns in multi-cloud environments. The paper explores methods for ensuring data security, access control, and compliance with regulatory frameworks. It considers encryption techniques, identity and access management, and auditing mechanisms as essential components of a robust multi-cloud data security strategy.The research also evaluates cost optimization strategies, recognizing that the dynamic nature of multi-cloud pricing models can impact the overall cost of data transfer and processing. It examines approaches for workload placement, resource allocation, and predictive cost modeling to minimize operational expenses while maximizing performance.Moreover, this study provides insights into real-world case studies and best practices adopted by organizations that have successfully navigated the challenges of multi-cloud big data management. It presents a comparative analysis of various multi-cloud management platforms and tools available in the market.

Keywords: multi-cloud environments, big data workloads, data transfer optimization, data processing strategies

Procedia PDF Downloads 38

Authors: Aleksandra Jonas, Aleksandra Gronowska, Maciej Ścigacz, Szymon Jadczak

Abstract:

Exact Data is a smart tool which helps with meaningful marketing content creation. It helps marketers achieve this by analyzing the text of an advertisement before and after its publication on social media sites like Facebook or Instagram. In our research we focus on four areas of natural language processing (NLP): grammar correction, sentiment analysis, irony detection and advertisement interpretation. Our research has identified a considerable lack of NLP tools for the Polish language, which specifically aid online marketers. In light of this, our research team has set out to create a robust and versatile NLP tool for the Polish language. The primary objective of our research is to develop a tool that can perform a range of language processing tasks in this language, such as sentiment analysis, text classification, text correction and text interpretation. Our team has been working diligently to create a tool that is accurate, reliable, and adaptable to the specific linguistic features of Polish, and that can provide valuable insights for a wide range of marketers needs. In addition to the Polish language version, we are also developing an English version of the tool, which will enable us to expand the reach and impact of our research to a wider audience. Another area of focus in our research involves tackling the challenge of the limited availability of linguistically diverse corpora for non-English languages, which presents a significant barrier in the development of NLP applications. One approach we have been pursuing is the translation of existing English corpora, which would enable us to use the wealth of linguistic resources available in English for other languages. Furthermore, we are looking into other methods, such as gathering language samples from social media platforms. By analyzing the language used in social media posts, we can collect a wide range of data that reflects the unique linguistic characteristics of specific regions and communities, which can then be used to enhance the accuracy and performance of NLP algorithms for non-English languages. In doing so, we hope to broaden the scope and capabilities of NLP applications. Our research focuses on several key NLP techniques including sentiment analysis, text classification, text interpretation and text correction. To ensure that we can achieve the best possible performance for these techniques, we are evaluating and comparing different approaches and strategies for implementing them. We are exploring a range of different methods, including transformers and convolutional neural networks (CNNs), to determine which ones are most effective for different types of NLP tasks. By analyzing the strengths and weaknesses of each approach, we can identify the most effective techniques for specific use cases, and further enhance the performance of our tool. Our research aims to create a tool, which can provide a comprehensive analysis of advertising effectiveness, allowing marketers to identify areas for improvement and optimize their advertising strategies. The results of this study suggest that a smart tool for advertisement analysis can provide valuable insights for businesses seeking to create effective advertising campaigns.

Keywords: NLP, AI, IT, language, marketing, analysis

Procedia PDF Downloads 52

Authors: G. M. Vlasceanu, H. Iovu, E. Vasile, M. Ionita

Abstract:

Herein, the synthesis and characterization of chitosan-gelatin highly porous scaffold reinforced with graphene oxide, and hydroxyapatite (HAp), crosslinked with genipin was targeted. In tissue engineering, chitosan and gelatin are two of the most robust biopolymers with wide applicability due to intrinsic biocompatibility, biodegradability, low antigenicity properties, affordability, and ease of processing. HAp, per its exceptional activity in tuning cell-matrix interactions, is acknowledged for its capability of sustaining cellular proliferation by promoting bone-like native micro-media for cell adjustment. Genipin is regarded as a top class cross-linker, while graphene oxide (GO) is viewed as one of the most performant and versatile fillers. The composites with natural bone HAp/biopolymer ratio were obtained by cascading sonochemical treatments, followed by uncomplicated casting methods and by freeze-drying. Their structure was characterized by Fourier Transform Infrared Spectroscopy and X-ray Diffraction, while overall morphology was investigated by Scanning Electron Microscopy (SEM) and micro-Computer Tomography (µ-CT). Ensuing that, in vitro enzyme degradation was performed to detect the most promising compositions for the development of in vivo assays. Suitable GO dispersion was ascertained within the biopolymer mix as nanolayers specific signals lack in both FTIR and XRD spectra, and the specific spectral features of the polymers persisted with GO load enhancement. Overall, correlations between the GO induced material structuration, crystallinity variations, and chemical interaction of the compounds can be correlated with the physical features and bioactivity of each composite formulation. Moreover, the HAp distribution within follows an auspicious density gradient tuned for hybrid osseous/cartilage matter architectures, which were mirrored in the mice model tests. Hence, the synthesis route of a natural polymer blend/hydroxyapatite-graphene oxide composite material is anticipated to emerge as influential formulation in bone tissue engineering. Acknowledgement: This work was supported by the project 'Work-based learning systems using entrepreneurship grants for doctoral and post-doctoral students' (Sisteme de invatare bazate pe munca prin burse antreprenor pentru doctoranzi si postdoctoranzi) - SIMBA, SMIS code 124705 and by a grant of the National Authority for Scientific Research and Innovation, Operational Program Competitiveness Axis 1 - Section E, Program co-financed from European Regional Development Fund 'Investments for your future' under the project number 154/25.11.2016, P_37_221/2015. The nano-CT experiments were possible due to European Regional Development Fund through Competitiveness Operational Program 2014-2020, Priority axis 1, ID P_36_611, MySMIS code 107066, INOVABIOMED.

Keywords: biopolymer blend, ectopic osteoinduction, graphene oxide composite, hydroxyapatite

Procedia PDF Downloads 83

Authors: Dhanuj M. Gandikota

Abstract:

Sensor-derived three-dimensional (3D) point clouds of trees are invaluable in remote sensing analysis for the accurate measurement of key structural metrics, bio-inventory values, spatial planning/visualization, and ecological modeling. Machine learning (ML) holds the potential in addressing the restrictive tradeoffs in cost, spatial coverage, resolution, and information gain that exist in current point cloud sensing methods. Terrestrial laser scanning (TLS) remains the highest fidelity source of both canopy and below-canopy structural features, but usage is limited in both coverage and cost, requiring manual deployment to map out large, forested areas. While aerial laser scanning (ALS) remains a reliable avenue of LIDAR active remote sensing, ALS is also cost-restrictive in deployment methods. Space-borne photogrammetry from high-resolution satellite constellations is an avenue of passive remote sensing with promising viability in research for the accurate construction of vegetation 3-D point clouds. It provides both the lowest comparative cost and the largest spatial coverage across remote sensing methods. However, both space-borne photogrammetry and ALS demonstrate technical limitations in the capture of valuable below-canopy point cloud data. Looking to minimize these tradeoffs, we explored a class of powerful ML algorithms called Deep Learning (DL) that show promise in recent research on 3-D point cloud reconstruction and interpolation. Our research details the efficacy of applying these DL techniques to reconstruct accurate below-canopy point clouds from space-borne and aerial remote sensing through learned patterns of tree species fractal symmetry properties and the supplementation of locally sourced bio-inventory metrics. From our dataset, consisting of tree point clouds obtained from TLS, we deconstructed the point clouds of each tree into those that would be obtained through ALS and satellite photogrammetry of varying resolutions. We fed this ALS/satellite point cloud dataset, along with the simulated local bio-inventory metrics, into the DL point cloud reconstruction architectures to generate the full 3-D tree point clouds (the truth values are denoted by the full TLS tree point clouds containing the below-canopy information). Point cloud reconstruction accuracy was validated both through the measurement of error from the original TLS point clouds as well as the error of extraction of key structural metrics, such as crown base height, diameter above root crown, and leaf/wood volume. The results of this research additionally demonstrate the supplemental performance gain of using minimum locally sourced bio-inventory metric information as an input in ML systems to reach specified accuracy thresholds of tree point cloud reconstruction. This research provides insight into methods for the rapid, cost-effective, and accurate construction of below-canopy tree 3-D point clouds, as well as the supported potential of ML and DL to learn complex, unmodeled patterns of fractal tree growth symmetry.

Keywords: deep learning, machine learning, satellite, photogrammetry, aerial laser scanning, terrestrial laser scanning, point cloud, fractal symmetry

Procedia PDF Downloads 61

Authors: Hilal T. Sasmazel, Seda Surucu

Abstract:

Skin tissue engineering is a promising field for the treatment of skin defects using scaffolds. This approach involves the use of living cells and biomaterials to restore, maintain, or regenerate tissues and organs in the body by providing; (i) larger surface area for cell attachment, (ii) proper porosity for cell colonization and cell to cell interaction, and (iii) 3-dimensionality at macroscopic scale. Recent studies on this area mainly focus on fabrication of scaffolds that can closely mimic the natural extracellular matrix (ECM) for creation of tissue specific niche-like environment at the subcellular scale. Scaffolds designed as ECM-like architectures incorporating into the host with minimal scarring/pain and facilitate angiogenesis. This study is related to combining of synthetic PCL and natural chitosan polymers to form 3D PCL/Chitosan core-shell structures for skin tissue engineering applications. Amongst the polymers used in tissue engineering, natural polymer chitosan and synthetic polymer poly(ε-caprolactone) (PCL) are widely preferred in the literature. Chitosan has been among researchers for a very long time because of its superior biocompatibility and structural resemblance to the glycosaminoglycan of bone tissue. However, the low mechanical flexibility and limited biodegradability properties reveals the necessity of using this polymer in a composite structure. On the other hand, PCL is a versatile polymer due to its low melting point (60°C), ease of processability, degradability with non-enzymatic processes (hydrolysis) and good mechanical properties. Nevertheless, there are also several disadvantages of PCL such as its hydrophobic structure, limited bio-interaction and susceptibility to bacterial biodegradation. Therefore, it became crucial to use both of these polymers together as a hybrid material in order to overcome the disadvantages of both polymers and combine advantages of those. The scaffolds here were fabricated by using electrospinning technique and the characterizations of the samples were done by contact angle (CA) measurements, scanning electron microscopy (SEM), transmission electron microscopy (TEM) and X-Ray Photoelectron spectroscopy (XPS). Additionally, gas permeability test, mechanical test, thickness measurement and PBS absorption and shrinkage tests were performed for all type of scaffolds (PCL, chitosan and PCL/chitosan core-shell). By using ImageJ launcher software program (USA) from SEM photographs the average inter-fiber diameter values were calculated as 0.717±0.198 µm for PCL, 0.660±0.070 µm for chitosan and 0.412±0.339 µm for PCL/chitosan core-shell structures. Additionally, the average inter-fiber pore size values exhibited decrease of 66.91% and 61.90% for the PCL and chitosan structures respectively, compare to PCL/chitosan core-shell structures. TEM images proved that homogenous and continuous bead free core-shell fibers were obtained. XPS analysis of the PCL/chitosan core-shell structures exhibited the characteristic peaks of PCL and chitosan polymers. Measured average gas permeability value of produced PCL/chitosan core-shell structure was determined 2315±3.4 g.m-2.day-1. In the future, cell-material interactions of those developed PCL/chitosan core-shell structures will be carried out with L929 ATCC CCL-1 mouse fibroblast cell line. Standard MTT assay and microscopic imaging methods will be used for the investigation of the cell attachment, proliferation and growth capacities of the developed materials.

Keywords: chitosan, coaxial electrospinning, core-shell, PCL, tissue scaffold

Procedia PDF Downloads 457

Authors: Piotr A. Kowalski, Kasper Sapala, Wiktor Warchalowski

Abstract:

PM10 is a suspended dust that primarily has a negative effect on the respiratory system. PM10 is responsible for attacks of coughing and wheezing, asthma or acute, violent bronchitis. Indirectly, PM10 also negatively affects the rest of the body, including increasing the risk of heart attack and stroke. Unfortunately, Poland is a country that cannot boast of good air quality, in particular, due to large PM concentration levels. Therefore, based on the dense network of Airly sensors, it was decided to deal with the problem of prediction of suspended particulate matter concentration. Due to the very complicated nature of this issue, the Machine Learning approach was used. For this purpose, Convolution Neural Network (CNN) neural networks have been adopted, these currently being the leading information processing methods in the field of computational intelligence. The aim of this research is to show the influence of particular CNN network parameters on the quality of the obtained forecast. The forecast itself is made on the basis of parameters measured by Airly sensors and is carried out for the subsequent day, hour after hour. The evaluation of learning process for the investigated models was mostly based upon the mean square error criterion; however, during the model validation, a number of other methods of quantitative evaluation were taken into account. The presented model of pollution prediction has been verified by way of real weather and air pollution data taken from the Airly sensor network. The dense and distributed network of Airly measurement devices enables access to current and archival data on air pollution, temperature, suspended particulate matter PM1.0, PM2.5, and PM10, CAQI levels, as well as atmospheric pressure and air humidity. In this investigation, PM2.5, and PM10, temperature and wind information, as well as external forecasts of temperature and wind for next 24h served as inputted data. Due to the specificity of the CNN type network, this data is transformed into tensors and then processed. This network consists of an input layer, an output layer, and many hidden layers. In the hidden layers, convolutional and pooling operations are performed. The output of this system is a vector containing 24 elements that contain prediction of PM10 concentration for the upcoming 24 hour period. Over 1000 models based on CNN methodology were tested during the study. During the research, several were selected out that give the best results, and then a comparison was made with the other models based on linear regression. The numerical tests carried out fully confirmed the positive properties of the presented method. These were carried out using real ‘big’ data. Models based on the CNN technique allow prediction of PM10 dust concentration with a much smaller mean square error than currently used methods based on linear regression. What's more, the use of neural networks increased Pearson's correlation coefficient (R²) by about 5 percent compared to the linear model. During the simulation, the R² coefficient was 0.92, 0.76, 0.75, 0.73, and 0.73 for 1st, 6th, 12th, 18th, and 24th hour of prediction respectively.

Keywords: air pollution prediction (forecasting), machine learning, regression task, convolution neural networks

Procedia PDF Downloads 98

Authors: Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, Xavier Roca

Abstract:

Image sharing in social networks has increased exponentially in the past years. Officially, there are 600 million Instagrammers uploading around 100 million photos and videos per day. Consequently, there is a need for developing new tools to understand the content expressed in shared images, which will greatly benefit social media communication and will enable broad and promising applications in education, advertisement, entertainment, and also psychology. Following these trends, our work aims to take advantage of the existing relationship between text and personality, already demonstrated by multiple researchers, so that we can prove that there exists a relationship between images and personality as well. To achieve this goal, we consider that images posted on social networks are typically conditioned on specific words, or hashtags, therefore any relationship between text and personality can also be observed with those posted images. Our proposal makes use of the most recent image understanding models based on neural networks to process the vast amount of data generated by social users to determine those images most correlated with personality traits. The final aim is to train a weakly-supervised image-based model for personality assessment that can be used even when textual data is not available, which is an increasing trend. The procedure is described next: we explore the images directly publicly shared by users based on those accompanying texts or hashtags most strongly related to personality traits as described by the OCEAN model. These images will be used for personality prediction since they have the potential to convey more complex ideas, concepts, and emotions. As a result, the use of images in personality questionnaires will provide a deeper understanding of respondents than through words alone. In other words, from the images posted with specific tags, we train a deep learning model based on neural networks, that learns to extract a personality representation from a picture and use it to automatically find the personality that best explains such a picture. Subsequently, a deep neural network model is learned from thousands of images associated with hashtags correlated to OCEAN traits. We then analyze the network activations to identify those pictures that maximally activate the neurons: the most characteristic visual features per personality trait will thus emerge since the filters of the convolutional layers of the neural model are learned to be optimally activated depending on each personality trait. For example, among the pictures that maximally activate the high Openness trait, we can see pictures of books, the moon, and the sky. For high Conscientiousness, most of the images are photographs of food, especially healthy food. The high Extraversion output is mostly activated by pictures of a lot of people. In high Agreeableness images, we mostly see flower pictures. Lastly, in the Neuroticism trait, we observe that the high score is maximally activated by animal pets like cats or dogs. In summary, despite the huge intra-class and inter-class variabilities of the images associated to each OCEAN traits, we found that there are consistencies between visual patterns of those images whose hashtags are most correlated to each trait.

Keywords: emotions and effects of mood, social impact theory in social psychology, social influence, social structure and social networks

Procedia PDF Downloads 163

Authors: Yashas Bedre Raghavendra, Pim Vullers

Abstract:

This study presents the design and implementation of an abstract cryptographic coprocessor, leveraging AMBA(Advanced Microcontroller Bus Architecture) protocols - APB (Advanced Peripheral Bus) and AHB (Advanced High-performance Bus), to enable seamless integration with the main CPU(Central processing unit) and enhance the coprocessor’s algorithm flexibility. The primary objective is to create a versatile coprocessor that can execute various cryptographic algorithms, including ECC(Elliptic-curve cryptography), RSA(Rivest–Shamir–Adleman), and AES (Advanced Encryption Standard) while providing a robust and secure solution for modern secure embedded systems. To achieve this goal, the coprocessor is equipped with a tightly coupled memory (TCM) for rapid data access during cryptographic operations. The TCM is placed within the coprocessor, ensuring quick retrieval of critical data and optimizing overall performance. Additionally, the program memory is positioned outside the coprocessor, allowing for easy updates and reconfiguration, which enhances adaptability to future algorithm implementations. Direct links are employed instead of DMA(Direct memory access) for data transfer, ensuring faster communication and reducing complexity. The AMBA-based communication architecture facilitates seamless interaction between the coprocessor and the main CPU, streamlining data flow and ensuring efficient utilization of system resources. The abstract nature of the coprocessor allows for easy integration of new cryptographic algorithms in the future. As the security landscape continues to evolve, the coprocessor can adapt and incorporate emerging algorithms, making it a future-proof solution for cryptographic processing. Furthermore, this study explores the addition of custom instructions into RISC-V ISE (Instruction Set Extension) to enhance cryptographic operations. By incorporating custom instructions specifically tailored for cryptographic algorithms, the coprocessor achieves higher efficiency and reduced cycles per instruction (CPI) compared to traditional instruction sets. The adoption of RISC-V 128-bit architecture significantly reduces the total number of instructions required for complex cryptographic tasks, leading to faster execution times and improved overall performance. Comparisons are made with 32-bit and 64-bit architectures, highlighting the advantages of the 128-bit architecture in terms of reduced instruction count and CPI. In conclusion, the abstract cryptographic coprocessor presented in this study offers significant advantages in terms of algorithm flexibility, security, and integration with the main CPU. By leveraging AMBA protocols and employing direct links for data transfer, the coprocessor achieves high-performance cryptographic operations without compromising system efficiency. With its TCM and external program memory, the coprocessor is capable of securely executing a wide range of cryptographic algorithms. This versatility and adaptability, coupled with the benefits of custom instructions and the 128-bit architecture, make it an invaluable asset for secure embedded systems, meeting the demands of modern cryptographic applications.

Keywords: abstract cryptographic coprocessor, AMBA protocols, ECC, RSA, AES, tightly coupled memory, secure embedded systems, RISC-V ISE, custom instructions, instruction count, cycles per instruction

Procedia PDF Downloads 41

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 102

Authors: Lizeth Fuentes-Mera, Vanessa Perez-Silos, Nidia K. Moncada-Saucedo, Alejandro Garcia-Ruiz, Alberto Camacho, Jorge Lara-Arias, Ivan Marino-Martinez, Victor Romero-Diaz, Adolfo Soto-Dominguez, Humberto Rodriguez-Rocha, Hang Lin, Victor Pena-Martinez

Abstract:

Biphasic scaffolds in cartilage tissue engineering have been designed to influence not only the recapitulation of the osteochondral architecture but also to take advantage of the healing ability of bone to promote the implant integration with the surrounding tissue and then bone restoration and cartilage regeneration. This study reports the development and characterization of a biphasic scaffold based on the assembly of a cartilage phase constituted by fibroin biofunctionalized with bovine cartilage matrix; cellularized with differentiated pre-chondrocytes from adipose tissue stem cells (autologous) and well attached to a bone phase (bone bovine decellularized) to mimic the structure of the nature of native tissue and to promote the cartilage regeneration in a model of joint damage in pigs. Biphasic scaffolds were assembled by fibroin crystallization with methanol. The histological and ultrastructural architectures were evaluated by optical and scanning electron microscopy respectively. Mechanical tests were conducted to evaluate Young's modulus of the implant. For the biological evaluation, pre-chondrocytes were loaded onto the scaffolds and cellular adhesion, proliferation, and gene expression analysis of cartilage extracellular matrix components was performed. The scaffolds that were cellularized and matured for 10 days were implanted into critical 3 mm in diameter and 9-mm in depth osteochondral defects in a porcine model (n=4). Three treatments were applied per knee: Group 1: monophasic cellular scaffold (MS) (single chondral phase), group 2: biphasic scaffold, cellularized only in the chondral phase (BS1), group 3: BS cellularized in both bone and chondral phases (BS2). Simultaneously, a control without treatment was evaluated. After 4 weeks of surgery, integration and regeneration tissues were analyzed by x-rays, histology and immunohistochemistry evaluation. The mechanical assessment showed that the acellular biphasic composites exhibited Young's modulus of 805.01 kPa similar to native cartilage (400-800 kPa). In vitro biological studies revealed the chondroinductive ability of the biphasic implant, evidenced by an increase in sulfated glycosaminoglycan (GAGs) and type II collagen, both secreted by the chondrocytes cultured on the scaffold during 28 days. No evidence of adverse or inflammatory reactions was observed in the in vivo trial; however, In group 1, the defects were not reconstructed. In group 2 and 3 a good integration of the implant with the surrounding tissue was observed. Defects in group 2 were fulfilled by hyaline cartilage and normal bone. Group 3 defects showed fibrous repair tissue. In conclusion; our findings demonstrated the efficacy of biphasic and bioactive scaffold based on silk fibroin, which entwined chondroinductive features and biomechanical capability with appropriate integration with the surrounding tissue, representing a promising alternative for osteochondral tissue-engineering applications.

Keywords: biphasic scaffold, extracellular cartilage matrix, silk fibroin, osteochondral tissue engineering

Procedia PDF Downloads 123

Authors: Rohit T. P., Sahil Athrij, Sasi Gopalan

Abstract:

Currently, the content entertainment industry is dominated by mobile devices. As the trends slowly shift towards Augmented/Virtual Reality applications the computational demands on these devices are increasing exponentially and we are already reaching the limits of hardware optimizations. This paper proposes a software solution to this problem. By leveraging the capabilities of cloud computing we can offload the work from mobile devices to dedicated rendering servers that are way more powerful. But this introduces the problem of latency. This paper introduces a protocol that can achieve high-performance low latency Augmented/Virtual Reality experience. There are two parts to the protocol, 1) In-flight compression The main cause of latency in the system is the time required to transmit the camera frame from client to server. The round trip time is directly proportional to the amount of data transmitted. This can therefore be reduced by compressing the frames before sending. Using some standard compression algorithms like JPEG can result in minor size reduction only. Since the images to be compressed are consecutive camera frames there won't be a lot of changes between two consecutive images. So inter-frame compression is preferred. Inter-frame compression can be implemented efficiently using WebGL but the implementation of WebGL limits the precision of floating point numbers to 16bit in most devices. This can introduce noise to the image due to rounding errors, which will add up eventually. This can be solved using an improved interframe compression algorithm. The algorithm detects changes between frames and reuses unchanged pixels from the previous frame. This eliminates the need for floating point subtraction thereby cutting down on noise. The change detection is also improved drastically by taking the weighted average difference of pixels instead of the absolute difference. The kernel weights for this comparison can be fine-tuned to match the type of image to be compressed. 2) Dynamic Load distribution Conventional cloud computing architectures work by offloading as much work as possible to the servers, but this approach can cause a hit on bandwidth and server costs. The most optimal solution is obtained when the device utilizes 100% of its resources and the rest is done by the server. The protocol balances the load between the server and the client by doing a fraction of the computing on the device depending on the power of the device and network conditions. The protocol will be responsible for dynamically partitioning the tasks. Special flags will be used to communicate the workload fraction between the client and the server and will be updated in a constant interval of time ( or frames ). The whole of the protocol is designed so that it can be client agnostic. Flags are available to the client for resetting the frame, indicating latency, switching mode, etc. The server can react to client-side changes on the fly and adapt accordingly by switching to different pipelines. The server is designed to effectively spread the load and thereby scale horizontally. This is achieved by isolating client connections into different processes.

Keywords: 2D kernelling, augmented reality, cloud computing, dynamic load distribution, immersive experience, mobile computing, motion tracking, protocols, real-time systems, web-based augmented reality application

Procedia PDF Downloads 48

Authors: Kaustav Mukherjee

Abstract:

In this paper we propose a Neural Style Transfer solution whereby we have created a Lightweight Separable Convolution Kernel Based GAN Architecture (SC-GAN) which will very useful for designing filter for Mobile Phone Cameras and also Edge Devices which will convert any image to its 2D ANIMATED COMIC STYLE Movies like HEMAN, SUPERMAN, JUNGLE-BOOK. This will help the 2D animation artist by relieving to create new characters from real life person's images without having to go for endless hours of manual labour drawing each and every pose of a cartoon. It can even be used to create scenes from real life images.This will reduce a huge amount of turn around time to make 2D animated movies and decrease cost in terms of manpower and time. In addition to that being extreme light-weight it can be used as camera filters capable of taking Comic Style Shots using mobile phone camera or edge device cameras like Raspberry Pi 4,NVIDIA Jetson NANO etc. Existing Methods like CartoonGAN with the model size close to 170 MB is too heavy weight for mobile phones and edge devices due to their scarcity in resources. Compared to the current state of the art our proposed method which has a total model size of 31 MB which clearly makes it ideal and ultra-efficient for designing of camera filters on low resource devices like mobile phones, tablets and edge devices running OS or RTOS. .Owing to use of high resolution input and usage of bigger convolution kernel size it produces richer resolution Comic-Style Pictures implementation with 6 times lesser number of parameters and with just 25 extra epoch trained on a dataset of less than 1000 which breaks the myth that all GAN need mammoth amount of data. Our network reduces the density of the Gan architecture by using Depthwise Separable Convolution which does the convolution operation on each of the RGB channels separately then we use a Point-Wise Convolution to bring back the network into required channel number using 1 by 1 kernel.This reduces the number of parameters substantially and makes it extreme light-weight and suitable for mobile phones and edge devices. The architecture mentioned in the present paper make use of Parameterised Batch Normalization Goodfellow etc al. (Deep Learning OPTIMIZATION FOR TRAINING DEEP MODELS page 320) which makes the network to use the advantage of Batch Norm for easier training while maintaining the non-linear feature capture by inducing the learnable parameters

Keywords: comic stylisation from camera image using GAN, creating 2D animated movie style custom stickers from images, depth-wise separable convolutional neural network for light-weight GAN architecture for EDGE devices, GAN architecture for 2D animated cartoonizing neural style, neural style transfer for edge, model distilation, perceptual loss

Procedia PDF Downloads 96

Authors: Jonathan Nii Laryea Ashong, Samuel Opare

Abstract:

Current sustainable cities debate focuses on the formidable problems for the Ghana’s largest urban and rural agglomerations, the majority of all urban dwellers continue to reside in far smaller urban settlements. It is estimated that by year 2030, almost all the Ghana’s population growth will likely be intense in urban areas including Nkawkaw in the Kwahu West Municipality of Ghana. Nkawkaw is situated on the road and former railway between Accra and Kumasi, and lies about halfway between these cities. It is also connected by road to Koforidua and Konongo. According to the 2013 census, Nkawkaw has a settlement population of 61,785. Many international agencies, government and private architectures’ are been asked to adequately recognize the naming of streets and property addressing system among the 170 districts across Ghana. The naming of streets and numbering of properties is to assist Metropolitan, Municipal and District Assemblies to manage the processes for establishing coherent address system nationally. Street addressing in the Nkawkaw in the Kwahu West Municipality which makes it possible to identify the location of a parcel of land, public places or dwellings on the ground based on system of names and numbers, yet agreement on how to progress towards it remains elusive. Therefore, reliable and effective development control for proper street naming and property addressing systems are required. The Intelligent Addressing (IA) technology from the UK is being used to name streets and properties in Ghana. The intelligent addressing employs the technique of unique property Reference Number and the unique street reference number which would transform national security and other service providers’ ability to respond rapidly to distress calls. Where name change is warranted following the review of existing streets names, the Physical Planning Department (PPDs) shall, in consultation with the relevant traditional authorities and community leadership (or relevant major stakeholders), select a street name in accordance with the provisions of the policy and the processes outlined for street name change for new development. In the case of existing streets with no names, the respective PPDs shall, in consultation with the relevant traditional authorities and community leadership (or relevant major stakeholders), select a street name in accordance with the requirements set out in municipality. Naming of access ways proposed for new developments shall be done at the time of developing sector layouts (subdivision maps) for the designated areas. In the case of private gated developments, the developer shall submit the names of the access ways as part of the plan and other documentation forwarded to the Municipal District Assembly for approval. The names shall be reviewed first by the PPD to avoid duplication and to ensure conformity to the required standards before submission to the Assembly’s Statutory Planning Committee for approval. The Kwahu West Municipality is supposed to be self-sustaining, providing basic services to inhabitants as a result of proper planning layouts, street naming and property addressing system that prevail in the area. The implications of these future projections are discussed.

Keywords: Nkawkaw, Kwahu west municipality, street naming, property, addressing system

Procedia PDF Downloads 469

Authors: Mahsa Mousavi, Hamid Reza Pourshaghaghi, Mohammad Tahghighi, Henk Corporaal

Abstract:

Recently, Statistic Random-Access Memory-based (SRAM-based) Field-Programmable Gate Arrays (FPGAs) are widely used in aeronautics and space systems where high dependability is demanded and considered as a mandatory requirement. Since design’s circuit is stored in configuration memory in SRAM-based FPGAs; they are very sensitive to Single Event Upsets (SEUs). In addition, the adverse effects of SEUs on the electronics used in space are much higher than in the Earth. Thus, developing fault tolerant techniques play crucial roles for the use of SRAM-based FPGAs in space. However, fault tolerance techniques introduce additional penalties in system parameters, e.g., area, power, performance and design time. In this paper, an accurate estimation of configuration memory vulnerability to SEUs is proposed for approximate-tolerant applications. This vulnerability estimation is highly required for compromising between the overhead introduced by fault tolerance techniques and system robustness. In this paper, we study applications in which the exact final output value is not necessarily always a concern meaning that some of the SEU-induced changes in output values are negligible. We therefore define and propose Approximate-based Configuration Memory Vulnerability Factor (ACMVF) estimation to avoid overestimating configuration memory vulnerability to SEUs. In this paper, we assess the vulnerability of configuration memory by injecting SEUs in configuration memory bits and comparing the output values of a given circuit in presence of SEUs with expected correct output. In spite of conventional vulnerability factor calculation methods, which accounts any deviations from the expected value as failures, in our proposed method a threshold margin is considered depending on user-case applications. Given the proposed threshold margin in our model, a failure occurs only when the difference between the erroneous output value and the expected output value is more than this margin. The ACMVF is subsequently calculated by acquiring the ratio of failures with respect to the total number of SEU injections. In our paper, a test-bench for emulating SEUs and calculating ACMVF is implemented on Zynq-7000 FPGA platform. This system makes use of the Single Event Mitigation (SEM) IP core to inject SEUs into configuration memory bits of the target design implemented in Zynq-7000 FPGA. Experimental results for 32-bit adder show that, when 1% to 10% deviation from correct output is considered, the counted failures number is reduced 41% to 59% compared with the failures number counted by conventional vulnerability factor calculation. It means that estimation accuracy of the configuration memory vulnerability to SEUs is improved up to 58% in the case that 10% deviation is acceptable in output results. Note that less than 10% deviation in addition result is reasonably tolerable for many applications in approximate computing domain such as Convolutional Neural Network (CNN).

Keywords: fault tolerance, FPGA, single event upset, approximate computing

Procedia PDF Downloads 157

Authors: Banu Pradheepa Kamarajan, Muthusamy Ananthasubramanian

Abstract:

Biofilm forming Pseudomonads occupy the top third position in causing hospital acquired infections. P. aeruginosa is notoriously known for its tendency to develop drug resistance. Major classes of drug such as β-lactams, aminoglycosides, quinolones, and polymyxins are found ineffective against multi-drug resistance Pseudomonas. To combat the infections, rather than administration of a single antibiotic, use of combinations (tobramycin and essential oils from plants and/or silver nanoparticles, chitosan, nitric oxide, cis-2-decenoic acid) in single formulation are suggested to control P. aeruginosa biofilms. Conventional techniques to prevent hospital-acquired implant infections such as coatings with antibiotics, controlled release of antibiotics from the implant material, contact-killing surfaces, coating the implants with functional DNase I and, coating with glycoside hydrolase are being followed. Coatings with bioactive components besides having limited shelf-life, require cold-chain and, are likely to fail when bacteria develop resistance. Recently identified nano-scale physical architectures on the insect wings are expected to have potential bactericidal property. Nanopillars are bactericidal to Staphylococcus aureus, Bacillus subtilis, K. pnuemoniae and few species of Pseudomonas. Our study aims to investigate the survival rate of biofilm forming Pseudomonas aeruginosa strain over non-biofilm forming strain on the nanopillar architecture of dragonfly (Pantala flavescens) wing. Dragonflies were collected near house-hold areas and, insect identification was carried out by the Department of Entomology, Tamilnadu Agricultural University, Coimbatore, India. Two strains of P. aeruginosa such as PAO1 (potent biofilm former) and MTCC 1688 (non-weak biofilm former) were tested against the glass coverslip (control) and wings of dragonfly (test) for 48 h. The wings/glass coverslips were incubated with bacterial suspension in 48-well plate. The plates were incubated at 37 °C under static condition. Bacterial attachment on the nanopillar architecture of the wing surface was visualized using FESEM. The survival rate of P. aeruginosa was tested using colony counting technique and flow cytometry at 0.5 h, 1 h, 2 h, 7 h, 24 h, and 48 h post-incubation. Cell death was analyzed using propidium iodide staining and DNA quantification. The results indicated that the survival rate of non-biofilm forming P. aeruginosa is 0.2 %, whilst that of biofilm former is 45 % on the dragonfly wings at the end of 48 h. The reduction in the survival rate of biofilm and non-biofilm forming P. aeruginosa was 20% and 40% respectively on the wings compared to the glass coverslip. In addition, Fourier Transformed Infrared Radiation was used to study the modification in the surface chemical composition of the wing during bacterial attachment and, post-sonication. This result indicated that the chemical moieties are not involved in the bactericidal property of nanopillars by the conserved characteristic peaks of chitin pre and post-sonication. The nanopillar architecture of the dragonfly wing efficiently deters the survival of non-biofilm forming P. aeruginosa, but not the biofilm forming strain. The study highlights the ability of biofilm formers to survive on wing architecture. Understanding this survival strategy will help in designing the architecture that combats the colonization of biofilm forming pathogens.

Keywords: biofilm, nanopillars, Pseudomonas aeruginosa, survival rate

Procedia PDF Downloads 152

Authors: Shanaka Gunasekara, Maleen Jayasuriya, Nalin Harischandra, Lilantha Samaranayake, Gamini Dissanayake

Abstract:

One serious facet of the worsening Human-Elephant conflict (HEC) in nations such as Sri Lanka involves elephant-train collisions. Endangered Asian elephants are maimed or killed during such accidents, which also often result in orphaned or disabled elephants, contributing to the phenomenon of lone elephants. These lone elephants are found to be more likely to attack villages and showcase aggressive behaviour, which further exacerbates the overall HEC. Furthermore, Railway Services incur significant financial losses and disruptions to services annually due to such accidents. Most elephant-train collisions occur due to a lack of adequate reaction time. This is due to the significant stopping distance requirements of trains, as the full braking force needs to be avoided to minimise the risk of derailment. Thus, poor driver visibility at sharp turns, nighttime operation, and poor weather conditions are often contributing factors to this problem. Initial investigations also indicate that most collisions occur in localised “hotspots” where elephant pathways/corridors intersect with railway tracks that border grazing land and watering holes. Taking these factors into consideration, this work proposes the leveraging of recent developments in Convolutional Neural Network (CNN) technology to detect elephants using an RGB/infrared capable camera around known hotspots along the railway track. The CNN was trained using a curated dataset of elephants collected on field visits to elephant sanctuaries and wildlife parks in Sri Lanka. With this vision-based detection system at its core, a prototype unit of an early warning system was designed and tested. This weatherised and waterproofed unit consists of a Reolink security camera which provides a wide field of view and range, an Nvidia Jetson Xavier computing unit, a rechargeable battery, and a solar panel for self-sufficient functioning. The prototype unit was designed to be a low-cost, low-power and small footprint device that can be mounted on infrastructures such as poles or trees. If an elephant is detected, an early warning message is communicated to the train driver using the GSM network. A mobile app for this purpose was also designed to ensure that the warning is clearly communicated. A centralized control station manages and communicates all information through the train station network to ensure coordination among important stakeholders. Initial results indicate that detection accuracy is sufficient under varying lighting situations, provided comprehensive training datasets that represent a wide range of challenging conditions are available. The overall hardware prototype was shown to be robust and reliable. We envision a network of such units may help contribute to reducing the problem of elephant-train collisions and has the potential to act as an important surveillance mechanism in dealing with the broader issue of human-elephant conflicts.

Keywords: computer vision, deep learning, human-elephant conflict, wildlife early warning technology

Procedia PDF Downloads 191

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 56

Authors: Delphine Ribes Lemay, Valentine Bernasconi, André Andrade, Lara DéFayes, Mathieu Salzmann, FréDéRic Kaplan, Nicolas Henchoz

Abstract:

Digitization and preservation of large heritage induce high maintenance costs to keep up with the technical standards and ensure sustainable access. Creating impactful usage is instrumental to justify the resources for long-term preservation. The Museum für Gestaltung of Zurich holds one of the biggest poster collections of the world from which 52’000 were digitised. In the process of building a digital installation to valorize the collection, one objective was to develop an algorithm capable of predicting the next poster to show according to the ones already displayed. The work presented here describes the steps to build an algorithm able to automatically create sequences of posters reflecting associations performed by curator and professional designers. The exposed challenge finds similarities with the domain of song playlist algorithms. Recently, artificial intelligence techniques and more specifically, deep-learning algorithms have been used to facilitate their generations. Promising results were found thanks to Recurrent Neural Networks (RNN) trained on manually generated playlist and paired with clusters of extracted features from songs. We used the same principles to create the proposed algorithm but applied to a challenging medium, posters. First, a convolutional autoencoder was trained to extract features of the posters. The 52’000 digital posters were used as a training set. Poster features were then clustered. Next, an RNN learned to predict the next cluster according to the previous ones. RNN training set was composed of poster sequences extracted from a collection of books from the Gestaltung Museum of Zurich dedicated to displaying posters. Finally, within the predicted cluster, the poster with the best proximity compared to the previous poster is selected. The mean square distance between features of posters was used to compute the proximity. To validate the predictive model, we compared sequences of 15 posters produced by our model to randomly and manually generated sequences. Manual sequences were created by a professional graphic designer. We asked 21 participants working as professional graphic designers to sort the sequences from the one with the strongest graphic line to the one with the weakest and to motivate their answer with a short description. The sequences produced by the designer were ranked first 60%, second 25% and third 15% of the time. The sequences produced by our predictive model were ranked first 25%, second 45% and third 30% of the time. The sequences produced randomly were ranked first 15%, second 29%, and third 55% of the time. Compared to designer sequences, and as reported by participants, model and random sequences lacked thematic continuity. According to the results, the proposed model is able to generate better poster sequencing compared to random sampling. Eventually, our algorithm is sometimes able to outperform a professional designer. As a next step, the proposed algorithm should include a possibility to create sequences according to a selected theme. To conclude, this work shows the potentiality of artificial intelligence techniques to learn from existing content and provide a tool to curate large sets of data, with a permanent renewal of the presented content.

Keywords: Artificial Intelligence, Digital Humanities, serendipity, design research

Procedia PDF Downloads 149

Authors: Alessandra Swiny, Michalis Georgiou, Yiorgos Hadjichristou

Abstract:

This paper focuses on the questions raised through the work of Unit 5: ‘In/Out of crisis, emergent and adaptive’; an architectural research-based studio at the University of Nicosia. It focusses on sustainable architectural and urban explorations tackling with the ever growing crises in its various types, phases and locations. ‘Great crisis situations’ are seen as ‘great chances’ that trigger investigations for further development and evolution of the built environment in an ultimate sustainable approach. The crisis is taken as an opportunity to rethink the urban and architectural directions as new forces for inventions leading to emergent and adaptive built environments. The Unit 5’s identity and environment facilitates the students to respond optimistically, alternatively and creatively towards the global current crisis. Mark Wigley’s notion that “crises are ultimately productive” and “They force invention” intrigued and defined the premises of the Unit. ‘Weather and nature are coauthors of the built environment’ Jonathan Hill states in his ‘weather architecture’ discourse. The weather is constantly changing and new environments, the subnatures are created which derived from the human activities David Gissen explains. The above set of premises triggered innovative responses by the Unit’s students. They thoroughly investigated the various kinds of crisis and their causes in relation to their various types of Terrains. The tools used for the research and investigation were chosen in contradictive pairs to generate further crisis situations: The re-used/salvaged competed with the new, the handmade rivalling with the fabrication, the analogue juxtaposed with digital. Students were asked to delve into state of art technologies in order to propose sustainable emergent and adaptive architectures and Urbanities, having though always in mind that the human and the social aspects of the community should be the core of the investigation. The resulting unprecedented spatial conditions and atmospheres of the emergent new ways of living are deemed to be the ultimate aim of the investigation. Students explored a variety of sites and crisis conditions such as: The vague terrain of the Green Line in Nicosia, the lost footprints of the sinking Venice, the endangered Australian coral reefs, the earthquake torn town of Crevalcore, and the decaying concrete urbanscape of Athens. Among other projects, ‘the plume project’ proposes a cloud-like, floating and almost dream-like living environment with unprecedented spatial conditions to the inhabitants of the coal mine of Centralia, USA, not just to enable them to survive but even to prosper in this unbearable environment due to the process of the captured plumes of smoke and heat. Existing water wells inspire inversed vertical structures creating a new living underground network, protecting the nomads from catastrophic sand storms in the Araoune of Mali. “Inverted utopia: Lost things in the sand”, weaves a series of tea-houses and a library holding lost artifacts and transcripts into a complex underground labyrinth by the utilization of the sand solidification technology. Within this methodology, crisis is seen as a mechanism for allowing an emergence of new and fascinating ultimate sustainable future cultures and cities.

Keywords: adaptive built environments, crisis as opportunity, emergent urbanities, forces for inventions

Procedia PDF Downloads 408

Authors: Mazaher Yarmohamadi-Vasel, Ali Reza Modarresi-Alama, Sahar Shabzendedara

Abstract:

Purpose/Objectives: The first purpose was synthesize Poly(N-(sulfophenyl)aniline) nanoflowers (PSANFLs) and Poly(N-(sulfophenyl)aniline) nanofibers/titanium dioxide nanoparticles ((PSANFs/TiO2NPs) by a solid-state mechano-chemical reaction and template-free method and use them in hybrid solar cell. Also, our second aim was to increase the solubility and the processability of conjugated nanomaterials in water through polar functionalized materials. poly[N-(4-sulfophenyl)aniline] is easily soluble in water because of the presence of polar groups of sulfonic acid in the polymer chain. Materials/Methods: Iron (III) chloride hexahydrate (FeCl3∙6H2O) were bought from Merck Millipore Company. Titanium oxide nanoparticles (TiO2, <20 nm, anatase) and Sodium diphenylamine-4-sulfonate (99%) were bought from Sigma-Aldrich Company. Titanium dioxide nanoparticles paste (PST-20T) was prepared from Sharifsolar Co. Conductive glasses coated with indium tin oxide (ITO) were bought from Xinyan Technology Co (China). For the first time we used the solid-state mechano-chemical reaction and template-free method to synthesize Poly(N-(sulfophenyl)aniline) nanoflowers. Moreover, for the first time we used the same technique to synthesize nanocomposite of Poly(N-(sulfophenyl)aniline) nanofibers and titanium dioxide nanoparticles (PSANFs/TiO2NPs) also for the first time this nanocomposite was synthesized. Examining the results of electrochemical calculations energy gap obtained by CV curves and UV–vis spectra demonstrate that PSANFs/TiO2NPs nanocomposite is a p-n type material that can be used in photovoltaic cells. Doctor blade method was used to creat films for three kinds of hybrid solar cells in terms of different patterns like ITO│TiO2NPs│Semiconductor sample│Al. In the following, hybrid photovoltaic cells in bilayer and bulk heterojunction structures were fabricated as ITO│TiO2NPs│PSANFLs│Al and ITO│TiO2NPs│PSANFs /TiO2NPs│Al, respectively. Fourier-transform infrared spectra, field emission scanning electron microscopy (FE-SEM), ultraviolet-visible spectra, cyclic voltammetry (CV) and electrical conductivity were the analysis that used to characterize the synthesized samples. Results and Conclusions: FE-SEM images clearly demonstrate that the morphology of the synthesized samples are nanostructured (nanoflowers and nanofibers). Electrochemical calculations of band gap from CV curves demonstrated that the forbidden band gap of the PSANFLs and PSANFs/TiO2NPs nanocomposite are 2.95 and 2.23 eV, respectively. I–V characteristics of hybrid solar cells and their power conversion efficiency (PCE) under 100 mWcm−2 irradiation (AM 1.5 global conditions) were measured that The PCE of the samples were 0.30 and 0.62%, respectively. At the end, all the results of solar cell analysis were discussed. To sum up, PSANFLs and PSANFLs/TiO2NPs were successfully synthesized by an affordable and straightforward mechanochemical reaction in solid-state under the green condition. The solubility and processability of the synthesized compounds have been improved compared to the previous work. We successfully fabricated hybrid photovoltaic cells of synthesized semiconductor nanostructured polymers and TiO2NPs as different architectures. We believe that the synthesized compounds can open inventive pathways for the development of other Poly(N-(sulfophenyl)aniline based hybrid materials (nanocomposites) proper for preparing new generation solar cells.

Keywords: mechanochemical synthesis, PSANFLs, PSANFs/TiO2NPs, solar cell

Procedia PDF Downloads 39

Authors: Nikola Toshikj, Michel Ramonda, Sylvain Catrouillet, Jean-Jacques Robin, Sebastien Blanquer

Abstract:

Biodegradable and biocompatible block copolymers have risen as the golden materials in both medical and environmental applications. Moreover, if their architecture is of controlled manner, higher applications can be foreseen. In the meantime, organocatalytic ROP has been promoted as more rapid and immaculate route, compared to the traditional organometallic catalysis, towards efficient synthesis of block copolymer architectures. Therefore, herein we report novel organocatalytic pathway with guanidine molecules (TBD) for supported synthesis of trimethylene carbonate initiated by poly(caprolactone) as pre-polymer. Pristine PTMC-b-PCL-b-PTMC block copolymer structure, without any residual products and clear desired block proportions, was achieved under 1.5 hours at room temperature and verified by NMR spectroscopies and size-exclusion chromatography. Besides, when elaborating block copolymer films, further stability and amelioration of mechanical properties can be achieved via additional reticulation step of precedently methacrylated block copolymers. Subsequently, stimulated by the insufficient studies on the phase-separation/crystallinity relationship in these semi-crystalline block copolymer systems, their intrinsic thermal and morphology properties were investigated by differential scanning calorimetry and atomic force microscopy. Firstly, by DSC measurements, the block copolymers with χABN values superior to 20 presented two distinct glass transition temperatures, close to the ones of the respecting homopolymers, demonstrating an initial indication of a phase-separated system. In the interim, the existence of the crystalline phase was supported by the presence of melting temperature. As expected, the crystallinity driven phase-separated morphology predominated in the AFM analysis of the block copolymers. Neither crosslinking at melted state, hence creation of a dense polymer network, disturbed the crystallinity phenomena. However, the later revealed as sensible to rapid liquid nitrogen quenching directly from the melted state. Therefore, AFM analysis of liquid nitrogen quenched and crosslinked block copolymer films demonstrated a thermodynamically driven phase-separation clearly predominating over the originally crystalline one. These AFM films remained stable with their morphology unchanged even after 4 months at room temperature. However, as demonstrated by DSC analysis once rising the temperature above the melting temperature of the PCL block, neither the crosslinking nor the liquid nitrogen quenching shattered the semi-crystalline network, while the access to thermodynamical phase-separated structures was possible for temperatures under the poly (caprolactone) melting point. Precisely this coexistence of dual crosslinked/crystalline networks in the same copolymer structure allowed us to establish, for the first time, the shape-memory properties in such materials, as verified by thermomechanical analysis. Moreover, the response temperature to the material original shape depended on the block copolymer emplacement, hence PTMC or PCL as end-block. Therefore, it has been possible to reach a block copolymer with transition temperature around 40°C thus opening potential real-life medical applications. In conclusion, the initial study of phase-separation/crystallinity relationship in PTMC-b-PCL-b-PTMC block copolymers lead to the discovery of novel shape memory materials with superior properties, widely demanded in modern-life applications.

Keywords: biodegradable block copolymers, organocatalytic ROP, self-assembly, shape-memory

Procedia PDF Downloads 103

Authors: I. Stathopoulos, V. Syrgiamiotis, E. Karavasilis, A. Ploussi, I. Nikas, C. Hatzigiorgi, K. Platoni, E. P. Efstathopoulos

Abstract:

Introduction: Brain and central nervous system (CNS) tumors form the second most common group of cancer in children, accounting for 30% of all childhood cancers. MRI is the key imaging technique used for the visualization and management of pediatric brain tumors. Initial characterization of tumors from MRI scans is usually performed via a radiologist’s visual assessment. However, different brain tumor types do not always demonstrate clear differences in visual appearance. Using only conventional MRI to provide a definite diagnosis could potentially lead to inaccurate results, and so histopathological examination of biopsy samples is currently considered to be the gold standard for obtaining definite diagnoses. Machine learning is defined as the study of computational algorithms that can use, complex or not, mathematical relationships and patterns from empirical and scientific data to make reliable decisions. Concerning the above, machine learning techniques could provide effective and accurate ways to automate and speed up the analysis and diagnosis for medical images. Machine learning applications in radiology are or could potentially be useful in practice for medical image segmentation and registration, computer-aided detection and diagnosis systems for CT, MR or radiography images and functional MR (fMRI) images for brain activity analysis and neurological disease diagnosis. Purpose: The objective of this study is to provide an automated tool, which may assist in the imaging evaluation and classification of brain neoplasms in pediatric patients by determining the glioma type, grade and differentiating between different brain tissue types. Moreover, a future purpose is to present an alternative way of quick and accurate diagnosis in order to save time and resources in the daily medical workflow. Materials and Methods: A cohort, of 80 pediatric patients with a diagnosis of posterior fossa tumor, was used: 20 ependymomas, 20 astrocytomas, 20 medulloblastomas and 20 healthy children. The MR sequences used, for every single patient, were the following: axial T1-weighted (T1), axial T2-weighted (T2), FluidAttenuated Inversion Recovery (FLAIR), axial diffusion weighted images (DWI), axial contrast-enhanced T1-weighted (T1ce). From every sequence only a principal slice was used that manually traced by two expert radiologists. Image acquisition was carried out on a GE HDxt 1.5-T scanner. The images were preprocessed following a number of steps including noise reduction, bias-field correction, thresholding, coregistration of all sequences (T1, T2, T1ce, FLAIR, DWI), skull stripping, and histogram matching. A large number of features for investigation were chosen, which included age, tumor shape characteristics, image intensity characteristics and texture features. After selecting the features for achieving the highest accuracy using the least number of variables, four machine learning classification algorithms were used: k-Nearest Neighbour, Support-Vector Machines, C4.5 Decision Tree and Convolutional Neural Network. The machine learning schemes and the image analysis are implemented in the WEKA platform and MatLab platform respectively. Results-Conclusions: The results and the accuracy of images classification for each type of glioma by the four different algorithms are still on process.

Keywords: image classification, machine learning algorithms, pediatric MRI, pediatric oncology

Procedia PDF Downloads 121

Authors: Utkarsh A. Mishra, Ankit Bansal

Abstract:

At high temperature, radiative heat transfer is the dominant mode of heat transfer. It is governed by various phenomena such as photon emission, absorption, and scattering. The solution of the governing integrodifferential equation of radiative transfer is a complex process, more when the effect of participating medium and wavelength properties are taken into consideration. Although a generic formulation of such radiative transport problem can be modeled for a wide variety of problems with non-gray, non-diffusive surfaces, there is always a trade-off between simplicity and accuracy of the problem. Recently, solutions of complicated mathematical problems with statistical methods based on randomization of naturally occurring phenomena have gained significant importance. Photon bundles with discrete energy can be replicated with random numbers describing the emission, absorption, and scattering processes. Photon Monte Carlo (PMC) is a simple, yet powerful technique, to solve radiative transfer problems in complicated geometries with arbitrary participating medium. The method, on the one hand, increases the accuracy of estimation, and on the other hand, increases the computational cost. The participating media -generally a gas, such as CO₂, CO, and H₂O- present complex emission and absorption spectra. To model the emission/absorption accurately with random numbers requires a weighted sampling as different sections of the spectrum carries different importance. Importance sampling (IS) was implemented to sample random photon of arbitrary wavelength, and the sampled data provided unbiased training of MC estimators for better results. A better replacement to uniform random numbers is using deterministic, quasi-random sequences. Halton, Sobol, and Faure Low-Discrepancy Sequences are used in this study. They possess better space-filling performance than the uniform random number generator and gives rise to a low variance, stable Quasi-Monte Carlo (QMC) estimators with faster convergence. An optimal supervised learning scheme was further considered to reduce the computation costs of the PMC simulation. A one-dimensional plane-parallel slab problem with participating media was formulated. The history of some randomly sampled photon bundles is recorded to train an Artificial Neural Network (ANN), back-propagation model. The flux was calculated using the standard quasi PMC and was considered to be the training target. Results obtained with the proposed model for the one-dimensional problem are compared with the exact analytical and PMC model with the Line by Line (LBL) spectral model. The approximate variance obtained was around 3.14%. Results were analyzed with respect to time and the total flux in both cases. A significant reduction in variance as well a faster rate of convergence was observed in the case of the QMC method over the standard PMC method. However, the results obtained with the ANN method resulted in greater variance (around 25-28%) as compared to the other cases. There is a great scope of machine learning models to help in further reduction of computation cost once trained successfully. Multiple ways of selecting the input data as well as various architectures will be tried such that the concerned environment can be fully addressed to the ANN model. Better results can be achieved in this unexplored domain.

Keywords: radiative heat transfer, Monte Carlo Method, pseudo-random numbers, low discrepancy sequences, artificial neural networks

Procedia PDF Downloads 184

Authors: Joseph M. Rich, Vinay A. Duddalwar, Assad A. Oberai

Abstract:

Prostate adenocarcinoma is the most common cancer in males, with osseous metastases as the commonest site of metastatic prostate carcinoma (mPC). Treatment monitoring is based on the evaluation and characterization of lesions on multiple imaging studies, including Computed Tomography (CT). Monitoring of the osseous disease burden, including follow-up of lesions and identification and characterization of new lesions, is a laborious task for radiologists. Deep learning algorithms are increasingly used to perform tasks such as identification and segmentation for osseous metastatic disease and provide accurate information regarding metastatic burden. Here, nnUNet was used to produce a model which can segment CT scan images of prostate adenocarcinoma vertebral bone metastatic lesions. nnUNet is an open-source Python package that adds optimizations to deep learning-based UNet architecture but has not been extensively combined with transfer learning techniques due to the absence of a readily available functionality of this method. The IRB-approved study data set includes imaging studies from patients with mPC who were enrolled in clinical trials at the University of Southern California (USC) Health Science Campus and Los Angeles County (LAC)/USC medical center. Manual segmentation of metastatic lesions was completed by an expert radiologist Dr. Vinay Duddalwar (20+ years in radiology and oncologic imaging), to serve as ground truths for the automated segmentation. Despite nnUNet’s success on some medical segmentation tasks, it only produced an average Dice Similarity Coefficient (DSC) of 0.31 on the USC dataset. DSC results fell in a bimodal distribution, with most scores falling either over 0.66 (reasonably accurate) or at 0 (no lesion detected). Applying more aggressive data augmentation techniques dropped the DSC to 0.15, and reducing the number of epochs reduced the DSC to below 0.1. Datasets have been identified for transfer learning, which involve balancing between size and similarity of the dataset. Identified datasets include the Pancreas data from the Medical Segmentation Decathlon, Pelvic Reference Data, and CT volumes with multiple organ segmentations (CT-ORG). Some of the challenges of producing an accurate model from the USC dataset include small dataset size (115 images), 2D data (as nnUNet generally performs better on 3D data), and the limited amount of public data capturing annotated CT images of bone lesions. Optimizations and improvements will be made by applying transfer learning and generative methods, including incorporating generative adversarial networks and diffusion models in order to augment the dataset. Performance with different libraries, including MONAI and custom architectures with Pytorch, will be compared. In the future, molecular correlations will be tracked with radiologic features for the purpose of multimodal composite biomarker identification. Once validated, these models will be incorporated into evaluation workflows to optimize radiologist evaluation. Our work demonstrates the challenges of applying automated image segmentation to small medical datasets and lays a foundation for techniques to improve performance. As machine learning models become increasingly incorporated into the workflow of radiologists, these findings will help improve the speed and accuracy of vertebral metastatic lesions detection.

Keywords: deep learning, image segmentation, medicine, nnUNet, prostate carcinoma, radiomics

Procedia PDF Downloads 67

Authors: Gabrielle Robertson, Matthew Downs, Joseph Dagher

Abstract:

Iron deposition in the brain has been linked with a host of neurological disorders such as Alzheimer’s, Parkinson’s, and Multiple Sclerosis. While some treatment options exist, there are no objective measurement tools that allow for the monitoring of iron levels in the brain in vivo. An emerging Magnetic Resonance Imaging (MRI) method has been recently proposed to deduce iron concentration through quantitative measurement of magnetic susceptibility. This is a multi-step process that involves repeated modeling of physical processes via approximate numerical solutions. For example, the last two steps of this Quantitative Susceptibility Mapping (QSM) method involve I) mapping magnetic field into magnetic susceptibility and II) mapping magnetic susceptibility into iron concentration. Process I involves solving an ill-posed inverse problem by using regularization via injection of prior belief. The end result from Process II highly depends on the model used to describe the molecular content of each voxel (type of iron, water fraction, etc.) Due to these factors, the accuracy and repeatability of QSM have been an active area of research in the MRI and medical imaging community. This work aims to estimate iron concentration in the brain via a single step. A synthetic numerical model of the human head was created by automatically and manually segmenting the human head on a high-resolution grid (640x640x640, 0.4mm³) yielding detailed structures such as microvasculature and subcortical regions as well as bone, soft tissue, Cerebral Spinal Fluid, sinuses, arteries, and eyes. Each segmented region was then assigned tissue properties such as relaxation rates, proton density, electromagnetic tissue properties and iron concentration. These tissue property values were randomly selected from a Probability Distribution Function derived from a thorough literature review. In addition to having unique tissue property values, different synthetic head realizations also possess unique structural geometry created by morphing the boundary regions of different areas within normal physical constraints. This model of the human brain is then used to create synthetic MRI measurements. This is repeated thousands of times, for different head shapes, volume, tissue properties and noise realizations. Collectively, this constitutes a training-set that is similar to in vivo data, but larger than datasets available from clinical measurements. This 3D convolutional U-Net neural network architecture was used to train data-driven Deep Learning models to solve for iron concentrations from raw MRI measurements. The performance was then tested on both synthetic data not used in training as well as real in vivo data. Results showed that the model trained on synthetic MRI measurements is able to directly learn iron concentrations in areas of interest more effectively than other existing QSM reconstruction methods. For comparison, models trained on random geometric shapes (as proposed in the Deep QSM method) are less effective than models trained on realistic synthetic head models. Such an accurate method for the quantitative measurement of iron deposits in the brain would be of important value in clinical studies aiming to understand the role of iron in neurological disease.

Keywords: magnetic resonance imaging, MRI, iron deposition, machine learning, quantitative susceptibility mapping

Procedia PDF Downloads 93

Authors: Stefan K. Behfar

Abstract:

The rapid growth of the Ethereum network has brought forth the urgent need for scalable analysis methods to handle the increasing volume of blockchain data. In this research, we propose efficient methodologies for making Ethereum network analysis scalable. Our approach leverages a combination of graph-based data representation, probabilistic sampling, and parallel processing techniques to achieve unprecedented scalability while preserving critical network insights. Data Representation: We develop a graph-based data representation that captures the underlying structure of the Ethereum network. Each block transaction is represented as a node in the graph, while the edges signify temporal relationships. This representation ensures efficient querying and traversal of the blockchain data. Probabilistic Sampling: To cope with the vastness of the Ethereum blockchain, we introduce a probabilistic sampling technique. This method strategically selects a representative subset of transactions and blocks, allowing for concise yet statistically significant analysis. The sampling approach maintains the integrity of the network properties while significantly reducing the computational burden. Graph Convolutional Networks (GCNs): We incorporate GCNs to process the graph-based data representation efficiently. The GCN architecture enables the extraction of complex spatial and temporal patterns from the sampled data. This combination of graph representation and GCNs facilitates parallel processing and scalable analysis. Distributed Computing: To further enhance scalability, we adopt distributed computing frameworks such as Apache Hadoop and Apache Spark. By distributing computation across multiple nodes, we achieve a significant reduction in processing time and enhanced memory utilization. Our methodology harnesses the power of parallelism, making it well-suited for large-scale Ethereum network analysis. Evaluation and Results: We extensively evaluate our methodology on real-world Ethereum datasets covering diverse time periods and transaction volumes. The results demonstrate its superior scalability, outperforming traditional analysis methods. Our approach successfully handles the ever-growing Ethereum data, empowering researchers and developers with actionable insights from the blockchain. Case Studies: We apply our methodology to real-world Ethereum use cases, including detecting transaction patterns, analyzing smart contract interactions, and predicting network congestion. The results showcase the accuracy and efficiency of our approach, emphasizing its practical applicability in real-world scenarios. Security and Robustness: To ensure the reliability of our methodology, we conduct thorough security and robustness evaluations. Our approach demonstrates high resilience against adversarial attacks and perturbations, reaffirming its suitability for security-critical blockchain applications. Conclusion: By integrating graph-based data representation, GCNs, probabilistic sampling, and distributed computing, we achieve network scalability without compromising analytical precision. This approach addresses the pressing challenges posed by the expanding Ethereum network, opening new avenues for research and enabling real-time insights into decentralized ecosystems. Our work contributes to the development of scalable blockchain analytics, laying the foundation for sustainable growth and advancement in the domain of blockchain research and application.

Keywords: Ethereum, scalable network, GCN, probabilistic sampling, distributed computing

Procedia PDF Downloads 39

Authors: Chandu Rathnayake, Isuri Anuradha

Abstract:

Early detection and accurate diagnosis of lung diseases play a crucial role in improving patient prognosis. However, conventional diagnostic methods heavily rely on subjective symptom assessments and medical imaging, often causing delays in diagnosis and treatment. To overcome this challenge, we propose a novel lung disease prediction system that integrates patient symptoms and X-ray images to provide a comprehensive and reliable diagnosis.In this project, develop a mobile application specifically designed for detecting lung diseases. Our application leverages both patient symptoms and X-ray images to facilitate diagnosis. By combining these two sources of information, our application delivers a more accurate and comprehensive assessment of the patient's condition, minimizing the risk of misdiagnosis. Our primary aim is to create a user-friendly and accessible tool, particularly important given the current circumstances where many patients face limitations in visiting healthcare facilities. To achieve this, we employ several state-of-the-art algorithms. Firstly, the Decision Tree algorithm is utilized for efficient symptom-based classification. It analyzes patient symptoms and creates a tree-like model to predict the presence of specific lung diseases. Secondly, we employ the Random Forest algorithm, which enhances predictive power by aggregating multiple decision trees. This ensemble technique improves the accuracy and robustness of the diagnosis. Furthermore, we incorporate a deep learning model using Convolutional Neural Network (CNN) with the RestNet50 pre-trained model. CNNs are well-suited for image analysis and feature extraction. By training CNN on a large dataset of X-ray images, it learns to identify patterns and features indicative of lung diseases. The RestNet50 architecture, known for its excellent performance in image recognition tasks, enhances the efficiency and accuracy of our deep learning model. By combining the outputs of the decision tree-based algorithms and the deep learning model, our mobile application generates a comprehensive lung disease prediction. The application provides users with an intuitive interface to input their symptoms and upload X-ray images for analysis. The prediction generated by the system offers valuable insights into the likelihood of various lung diseases, enabling individuals to take appropriate actions and seek timely medical attention. Our proposed mobile application has significant potential to address the rising prevalence of lung diseases, particularly among young individuals with smoking addictions. By providing a quick and user-friendly approach to assessing lung health, our application empowers individuals to monitor their well-being conveniently. This solution also offers immense value in the context of limited access to healthcare facilities, enabling timely detection and intervention. In conclusion, our research presents a comprehensive lung disease prediction system that combines patient symptoms and X-ray images using advanced algorithms. By developing a mobile application, we provide an accessible tool for individuals to assess their lung health conveniently. This solution has the potential to make a significant impact on the early detection and management of lung diseases, benefiting both patients and healthcare providers.

Keywords: CNN, random forest, decision tree, machine learning, deep learning

Procedia PDF Downloads 49