Search results for: multi-phase induction machine

Authors: James Rigor Camacho, Wansu Lim

Abstract:

Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.

Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors

Procedia PDF Downloads 105

Authors: M. Maier, I. Dedigama, J. Majasan, Y. Wu, Q. Meyer, L. Castanheira, G. Hinds, P. R. Shearing, D. J. L. Brett

Abstract:

Increasing the efficiency of electrolyser technology is commonly seen as one of the main challenges on the way to the Hydrogen Economy. There is a significant lack of understanding of the different states of operation of polymer electrolyte membrane water electrolysers (PEMWE) and how these influence the overall efficiency. This in particular means the two-phase flow through the membrane, gas diffusion layers (GDL) and flow channels. In order to increase the efficiency of PEMWE and facilitate their spread as commercial hydrogen production technology, new analytic approaches have to be found. Acoustic emission (AE) offers the possibility to analyse the processes within a PEMWE in a non-destructive, fast and cheap in-situ way. This work describes the generation and analysis of AE data coming from a PEM water electrolyser, for, to the best of our knowledge, the first time in literature. Different experiments are carried out. Each experiment is designed so that only specific physical processes occur and AE solely related to one process can be measured. Therefore, a range of experimental conditions is used to induce different flow regimes within flow channels and GDL. The resulting AE data is first separated into different events, which are defined by exceeding the noise threshold. Each acoustic event consists of a number of consequent peaks and ends when the wave diminishes under the noise threshold. For all these acoustic events the following key attributes are extracted: maximum peak amplitude, duration, number of peaks, peaks before the maximum, average intensity of a peak and time till the maximum is reached. Each event is then expressed as a vector containing the normalized values for all criteria. Principal Component Analysis is performed on the resulting data, which orders the criteria by the eigenvalues of their covariance matrix. This can be used as an easy way of determining which criteria convey the most information on the acoustic data. In the following, the data is ordered in the two- or three-dimensional space formed by the most relevant criteria axes. By finding spaces in the two- or three-dimensional space only occupied by acoustic events originating from one of the three experiments it is possible to relate physical processes to certain acoustic patterns. Due to the complex nature of the AE data modern machine learning techniques are needed to recognize these patterns in-situ. Using the AE data produced before allows to train a self-learning algorithm and develop an analytical tool to diagnose different operational states in a PEMWE. Combining this technique with the measurement of polarization curves and electrochemical impedance spectroscopy allows for in-situ optimization and recognition of suboptimal states of operation.

Keywords: acoustic emission, gas diffusion layers, in-situ diagnosis, PEM water electrolyser

Procedia PDF Downloads 155

Authors: Shayla He

Abstract:

Background and Purpose: According to Chamie (2017), it’s estimated that no less than 150 million people, or about 2 percent of the world’s population, are homeless. The homeless population in the United States has grown rapidly in the past four decades. In New York City, the sheltered homeless population has increased from 12,830 in 1983 to 62,679 in 2020. Knowing the trend on the homeless population is crucial at helping the states and the cities make affordable housing plans, and other community service plans ahead of time to better prepare for the situation. This study utilized the data from New York City, examined the key factors associated with the homelessness, and developed systematic modeling to predict homeless populations of the future. Using the best model developed, named HP-RNN, an analysis on the homeless population change during the months of 2020 and 2021, which were impacted by the COVID-19 pandemic, was conducted. Moreover, HP-RNN was tested on the data from Seattle. Methods: The methodology involves four phases in developing robust prediction methods. Phase 1 gathered and analyzed raw data of homeless population and demographic conditions from five urban centers. Phase 2 identified the key factors that contribute to the rate of homelessness. In Phase 3, three models were built using Linear Regression, Random Forest, and Recurrent Neural Network (RNN), respectively, to predict the future trend of society's homeless population. Each model was trained and tuned based on the dataset from New York City for its accuracy measured by Mean Squared Error (MSE). In Phase 4, the final phase, the best model from Phase 3 was evaluated using the data from Seattle that was not part of the model training and tuning process in Phase 3. Results: Compared to the Linear Regression based model used by HUD et al (2019), HP-RNN significantly improved the prediction metrics of Coefficient of Determination (R2) from -11.73 to 0.88 and MSE by 99%. HP-RNN was then validated on the data from Seattle, WA, which showed a peak %error of 14.5% between the actual and the predicted count. Finally, the modeling results were collected to predict the trend during the COVID-19 pandemic. It shows a good correlation between the actual and the predicted homeless population, with the peak %error less than 8.6%. Conclusions and Implications: This work is the first work to apply RNN to model the time series of the homeless related data. The Model shows a close correlation between the actual and the predicted homeless population. There are two major implications of this result. First, the model can be used to predict the homeless population for the next several years, and the prediction can help the states and the cities plan ahead on affordable housing allocation and other community service to better prepare for the future. Moreover, this prediction can serve as a reference to policy makers and legislators as they seek to make changes that may impact the factors closely associated with the future homeless population trend.

Keywords: homeless, prediction, model, RNN

Procedia PDF Downloads 120

Authors: Anwesha Pathak

Abstract:

With the increasing number of satellites and space debris, space traffic management (STM) becomes crucial. AI can aid in STM by predicting and preventing potential collisions, optimizing satellite trajectories, and managing orbital slots. Governance frameworks need to address the integration of AI algorithms in STM to ensure safe and sustainable satellite activities. AI and governance play significant roles in the context of satellite activities in space. Artificial intelligence (AI) technologies, such as machine learning and computer vision, can be utilized to process vast amounts of data received from satellites. AI algorithms can analyse satellite imagery, detect patterns, and extract valuable information for applications like weather forecasting, urban planning, agriculture, disaster management, and environmental monitoring. AI can assist in automating and optimizing satellite operations. Autonomous decision-making systems can be developed using AI to handle routine tasks like orbit control, collision avoidance, and antenna pointing. These systems can improve efficiency, reduce human error, and enable real-time responsiveness in satellite operations. AI technologies can be leveraged to enhance the security of satellite systems. AI algorithms can analyze satellite telemetry data to detect anomalies, identify potential cyber threats, and mitigate vulnerabilities. Governance frameworks should encompass regulations and standards for securing satellite systems against cyberattacks and ensuring data privacy. AI can optimize resource allocation and utilization in satellite constellations. By analyzing user demands, traffic patterns, and satellite performance data, AI algorithms can dynamically adjust the deployment and routing of satellites to maximize coverage and minimize latency. Governance frameworks need to address fair and efficient resource allocation among satellite operators to avoid monopolistic practices. Satellite activities involve multiple countries and organizations. Governance frameworks should encourage international cooperation, information sharing, and standardization to address common challenges, ensure interoperability, and prevent conflicts. AI can facilitate cross-border collaborations by providing data analytics and decision support tools for shared satellite missions and data sharing initiatives. AI and governance are critical aspects of satellite activities in space. They enable efficient and secure operations, ensure responsible and ethical use of AI technologies, and promote international cooperation for the benefit of all stakeholders involved in the satellite industry.

Keywords: satellite, space debris, traffic, threats, cyber security.

Procedia PDF Downloads 76

Authors: Varun Agarwal

Abstract:

Introduction: With the advent of personalized medicine, histopathological review of whole slide images (WSIs) for cancer diagnosis presents an exceedingly time-consuming, complex task. Specifically, detecting metastatic regions in WSIs of sentinel lymph node biopsies necessitates a full-scanned, holistic evaluation of the image. Thus, digital pathology, low-level image manipulation algorithms, and machine learning provide significant advancements in improving the efficiency and accuracy of WSI analysis. Using Camelyon16 data, this paper proposes a deep learning pipeline to automate and ameliorate breast cancer metastasis localization and WSI classification. Methodology: The model broadly follows five stages -region of interest detection, WSI partitioning into image tiles, convolutional neural network (CNN) image-segment classifications, probabilistic mapping of tumor localizations, and further processing for whole WSI classification. Transfer learning is applied to the task, with the implementation of Inception-ResNetV2 - an effective CNN classifier that uses residual connections to enhance feature representation, adding convolved outputs in the inception unit to the proceeding input data. Moreover, in order to augment the performance of the transfer learning CNN, a stack of convolutional denoising autoencoders (CDAE) is applied to produce embeddings that enrich image representation. Through a saliency-detection algorithm, visual training segments are generated, which are then processed through a denoising autoencoder -primarily consisting of convolutional, leaky rectified linear unit, and batch normalization layers- and subsequently a contrast-normalization function. A spatial pyramid pooling algorithm extracts the key features from the processed image, creating a viable feature map for the CNN that minimizes spatial resolution and noise. Results and Conclusion: The simplified and effective architecture of the fine-tuned transfer learning Inception-ResNetV2 network enhanced with the CDAE stack yields state of the art performance in WSI classification and tumor localization, achieving AUC scores of 0.947 and 0.753, respectively. The convolutional feature retention and compilation with the residual connections to inception units synergized with the input denoising algorithm enable the pipeline to serve as an effective, efficient tool in the histopathological review of WSIs.

Keywords: breast cancer, convolutional neural networks, metastasis mapping, whole slide images

Procedia PDF Downloads 130

Authors: M. Kozłowski, M. Kadela

Abstract:

Foamed concrete is known for its low self-weight and excellent thermal and acoustic properties. For many years, it has been used worldwide for insulation to foundations and roof tiles, as backfill to retaining walls, sound insulation, etc. However, in the last years it has become a promising material also for structural purposes e.g. for stabilization of weak soils. Due to favorable properties of foamed concrete, many interests and studies were involved to analyze its strength, mechanical, thermal and acoustic properties. However, these studies do not cover the investigation of fracture energy which is the core factor governing the damage and fracture mechanisms. Only limited number of publications can be found in literature. The paper presents the results of experimental investigation and numerical campaign of foamed concrete based on three-point bending test of beams with initial notch. First part of the paper presents the results of a series of static loading tests performed to investigate the fracture properties of foamed concrete of varying density. Beam specimens with dimensions of 100×100×840 mm with a central notch were tested in three-point bending. Subsequently, remaining halves of the specimens with dimensions of 100×100×420 mm were tested again as un-notched beams in the same set-up with reduced distance between supports. The tests were performed in a hydraulic displacement controlled testing machine with a load capacity of 5 kN. Apart from measuring the loading and mid-span displacement, a crack mouth opening displacement (CMOD) was monitored. Based on the load – displacement curves of notched beams the values of fracture energy and tensile stress at failure were calculated. The flexural tensile strength was obtained on un-notched beams with dimensions of 100×100×420 mm. Moreover, cube specimens 150×150×150 mm were tested in compression to determine the compressive strength. Second part of the paper deals with numerical investigation of the fracture behavior of beams with initial notch presented in the first part of the paper. Extended Finite Element Method (XFEM) was used to simulate and analyze the damage and fracture process. The influence of meshing and variation of mechanical properties on results was investigated. Numerical models simulate correctly the behavior of beams observed during three-point bending. The numerical results show that XFEM can be used to simulate different fracture toughness of foamed concrete and fracture types. Using the XFEM and computer simulation technology allow for reliable approximation of load–bearing capacity and damage mechanisms of beams made of foamed concrete, which provides some foundations for realistic structural applications.

Keywords: foamed concrete, fracture energy, three-point bending, XFEM

Procedia PDF Downloads 300

Authors: Ahmed Hossam ElMolla, Mohamed Hatem Saleh, Hamza Mostafa, Lara Mamdouh, Yassin Wael

Abstract:

Artificial intelligence (AI) is reshaping industries, and its potential to revolutionize renewable energy and data center operations is immense. By harnessing AI's capabilities, we can optimize energy consumption, predict fluctuations in renewable energy generation, and improve the efficiency of data center infrastructure. This convergence of technologies promises a future where energy is managed more intelligently, sustainably, and cost-effectively. The integration of AI into renewable energy systems unlocks a wealth of opportunities. Machine learning algorithms can analyze vast amounts of data to forecast weather patterns, solar irradiance, and wind speeds, enabling more accurate energy production planning. AI-powered systems can optimize energy storage and grid management, ensuring a stable power supply even during intermittent renewable generation. Moreover, AI can identify maintenance needs for renewable energy infrastructure, preventing costly breakdowns and maximizing system lifespan. Data centers, which consume substantial amounts of energy, are prime candidates for AI-driven optimization. AI can analyze energy consumption patterns, identify inefficiencies, and recommend adjustments to cooling systems, server utilization, and power distribution. Predictive maintenance using AI can prevent equipment failures, reducing energy waste and downtime. Additionally, AI can optimize data placement and retrieval, minimizing energy consumption associated with data transfer. As AI transforms renewable energy and data center operations, modified Key Performance Indicators (KPIs) will emerge. Traditional metrics like energy efficiency and cost-per-megawatt-hour will continue to be relevant, but additional KPIs focused on AI's impact will be essential. These might include AI-driven cost savings, predictive accuracy of energy generation and consumption, and the reduction of carbon emissions attributed to AI-optimized operations. By tracking these KPIs, organizations can measure the success of their AI initiatives and identify areas for improvement. Ultimately, the synergy between AI, renewable energy, and data centers holds the potential to create a more sustainable and resilient future. By embracing these technologies, we can build smarter, greener, and more efficient systems that benefit both the environment and the economy.

Keywords: data center, artificial intelligence, renewable energy, energy efficiency, sustainability, optimization, predictive analytics, energy consumption, energy storage, grid management, data center optimization, key performance indicators, carbon emissions, resiliency

Procedia PDF Downloads 33

Authors: Mladen Milicevic

Abstract:

This presentation will address how the statistical analysis of digitized popular music influences the music creation and emotionally manipulates consumers.Furthermore, it will deal with semiological aspect of uniformization of musical taste in order to predict the potential revenues generated by popular music sales. In the USA, we live in an age where most of the popular music (i.e. music that generates substantial revenue) has been digitized. It is safe to say that almost everything that was produced in last 10 years is already digitized (either available on iTunes, Spotify, YouTube, or some other platform). Depending on marketing viability and its potential to generate additional revenue most of the “older” music is still being digitized. Once the music gets turned into a digital audio file,it can be computer-analyzed in all kinds of respects, and the similar goes for the lyrics because they also exist as a digital text file, to which any kin of N Capture-kind of analysis may be applied. So, by employing statistical examination of different popular music metrics such as tempo, form, pronouns, introduction length, song length, archetypes, subject matter,and repetition of title, the commercial result may be predicted. Polyphonic HMI (Human Media Interface) introduced the concept of the hit song science computer program in 2003.The company asserted that machine learning could create a music profile to predict hit songs from its audio features Thus,it has been established that a successful pop song must include: 100 bpm or more;an 8 second intro;use the pronoun 'you' within 20 seconds of the start of the song; hit the bridge middle 8 between 2 minutes and 2 minutes 30 seconds; average 7 repetitions of the title; create some expectations and fill that expectation in the title. For the country song: 100 bpm or less for a male artist; 14-second intro; uses the pronoun 'you' within the first 20 seconds of the intro; has a bridge middle 8 between 2 minutes and 2 minutes 30 seconds; has 7 repetitions of title; creates an expectation,fulfills it in 60 seconds.This approach to commercial popular music minimizes the human influence when it comes to which “artist” a record label is going to sign and market. Twenty years ago,music experts in the A&R (Artists and Repertoire) departments of the record labels were making personal aesthetic judgments based on their extensive experience in the music industry. Now, the computer music analyzing programs, are replacing them in an attempt to minimize investment risk of the panicking record labels, in an environment where nobody can predict the future of the recording industry.The impact on the consumers taste through the narrow bottleneck of the above mentioned music selection by the record labels,created some very peculiar effects not only on the taste of popular music consumers, but also the creative chops of the music artists as well. What is the meaning of this semiological shift is the main focus of this research and paper presentation.

Keywords: music, semiology, commercial, taste

Procedia PDF Downloads 393

Authors: John Dimopoulos

Abstract:

This proposal attempts a refabrication of Heidegger’s classic thing-being and object-being analysis in order to provide better ontological tools for understanding contemporary culture, technology, and society. In his work, Heidegger sought to understand and comment on the problem of technology in an era of rampant innovation and increased perils for society and the planet. Today we seem to be at another crossroads in this course, coming after postmodernity, during which dreams and dangers of modernity augmented with critical speculations of the post-war era take shape. The new era which we are now living in, referred to as hypermodernity by researchers in various fields such as architecture and cultural theory, is defined by the horizontal implementation of digital technologies, cybernetic networks, and mixed reality. Technology today is rapidly approaching a turning point, namely the point of no return for humanity’s supervision over its creations. The techno-scientific civilization of the 21st century creates a series of problems, progressively more difficult and complex to solve and impossible to ignore, climate change, data safety, cyber depression, and digital stress being some of the most prevalent. Humans often have no other option than to address technology-induced problems with even more technology, as in the case of neuron networks, machine learning, and AI, thus widening the gap between creating technological artifacts and understanding their broad impact and possible future development. As all technical disciplines and particularly design, become enmeshed in a matrix of digital hyper-objects, a conceptual toolbox that allows us to handle the new reality becomes more and more necessary. Weaponized design, prevalent in many fields, such as social and traditional media, urban planning, industrial design, advertising, and the internet in general, hints towards an increase in conflicts. These conflicts between tech companies, stakeholders, and users with implications in politics, work, education, and production as apparent in the cases of Amazon workers’ strikes, Donald Trump’s 2016 campaign, Facebook and Microsoft data scandals, and more are often non-transparent to the wide public’s eye, thus consolidating new elites and technocratic classes and making the public scene less and less democratic. The new category proposed, weapon-being, is outlined in respect to the basic function of reducing complexity, subtracting materials, actants, and parameters, not strictly in favor of a humanistic re-orientation but in a more inclusive ontology of objects and subjects. Utilizing insights of Object-Oriented Ontology (OOO) and its schematization of technological objects, an outline for a radical ontology of technology is approached.

Keywords: design, hypermodernity, object-oriented ontology, weapon-being

Procedia PDF Downloads 152

Authors: Raphael Palucci Rosa, Giuseppe Rosace

Abstract:

Stereolithography (SLA) is one of the 3D-printing technologies that has been steadily growing in popularity for both industrial and personal applications due to its versatility, high accuracy, and low cost. Its printing process consists of using a light emitter to solidify photosensitive liquid resins layer-by-layer to produce solid objects. However, the majority of the resins used in SLA are derived from petroleum and characterized by toxicity, stability, and recalcitrance to degradation in natural environments. Aiming to develop an eco-friendly resin, in this work, different combinations of a standard commercial SLA resin (Peopoly UV professional) with a vegetable-based resin were investigated. To reach this goal, different mass concentrations (varying from 10 to 50 wt%) of acrylated epoxidized soybean oil (AESO), a vegetable resin produced from soyabean oil, were mixed with a commercial acrylate-based resin. 1.0 wt% of Diphenyl(2,4,6-trimethylbenzoyl) phosphine oxide (TPO) was used as photo-initiator, and the samples were printed using a Peopoly moai 130. The machine was set to operate at standard configurations when printing commercial resins. After the print was finished, the excess resin was drained off, and the samples were washed in isopropanol and water to remove any non-reacted resin. Finally, the samples were post-cured for 30 min in a UV chamber. FT-IR analysis was used to confirm the UV polymerization of the formulated resin with different AESO/Peopoly ratios. The signals from 1643.7 to 1616, which corresponds to the C=C stretching of the AESO acrylic acids and Peopoly acrylic groups, significantly decreases after the reaction. The signal decrease indicates the consumption of the double bonds during the radical polymerization. Furthermore, the slight change of the C-O-C signal from 1186.1 to 1159.9 decrease of the signals at 809.5 and 983.1, which corresponds to unsaturated double bonds, are both proofs of the successful polymerization. Mechanical analyses showed a decrease of 50.44% on tensile strength when adding 10 wt% of AESO, but it was still in the same range as other commercial resins. The elongation of break increased by 24% with 10 wt% of AESO and swelling analysis showed that samples with a higher concentration of AESO mixed absorbed less water than their counterparts. Furthermore, high-resolution prototypes were printed using both resins, and visual analysis did not show any significant difference between both products. In conclusion, the AESO resin was successful incorporated into a commercial resin without affecting its printability. The bio-based resin showed lower tensile strength than the Peopoly resin due to network loosening, but it was still in the range of other commercial resins. The hybrid resin also showed better flexibility and water resistance than Peopoly resin without affecting its resolution. Finally, the development of new types of SLA resins is essential to provide new sustainable alternatives to the commercial petroleum-based ones.

Keywords: 3D-printing, bio-based, resin, soybean, stereolithography

Procedia PDF Downloads 128

Authors: Ali A Alshraifeen, Josie Evans, Kathleen Stoddart

Abstract:

End-stage renal disease (ESRD) introduces physical, psychological, social, emotional and spiritual challenges into patients’ lives. Spirituality has been found to contribute to improved health outcomes, mainly in the areas of quality of life (QOL) and well-being. No studies exist to explore the influence of spirituality on the health outcomes and general well-being in patients with end-stage renal disease receiving hemodialysis (HD) treatment in Scotland. This study was conducted to explore spirituality in the daily lives of among these patients and how it may influence their QOL and general well-being. The study employed a qualitative method. Data were collected using semi-structured interviews with a sample of 21 patients. A thematic approach using Framework Analysis informed the qualitative data analysis. Participants were recruited from 11 dialysis units across four Health Boards in Scotland. The participants were regular patients attending the dialysis units three times per week. Four main themes emerged from the qualitative interviews: ‘Emotional and Psychological Turmoil’, ‘Life is Restricted’, ‘Spirituality’ and ‘Other Coping Strategies’. The findings suggest that patients’ QOL might be affected because of the physical challenges such as unremitting fatigue, disease unpredictability and being tied down to a dialysis machine, or the emotional and psychological challenges imposed by the disease into their lives such as wholesale changes, dialysis as a forced choice and having a sense of indebtedness. The findings also revealed that spirituality was an important coping strategy for the majority of participants who took part in the qualitative component (n=16). Different meanings of spirituality were identified including connection with God or Supernatural Being, connection with the self, others and nature/environment. Spirituality encouraged participants to accept their disease and offered them a sense of protection, instilled hope in them and helped them to maintain a positive attitude to carry on with their daily lives, which may have had a positive influence on their health outcomes and general well-being. The findings also revealed that humor was another coping strategy that helped to diffuse stress and anxiety for some participants and encouraged them to carry on with their lives. The findings from this study provide a significant contribution to a very limited body of work. The study contributes to our understanding of spirituality and how people receiving dialysis treatment use it to manage their daily lives. Spirituality is of particular interest due to its connection with health outcomes in patients with chronic illnesses. The link between spirituality and many chronic illnesses has gained some recognition, yet the identification of its influence on the health outcomes and well-being in patients with ESRD is still evolving. There is a need to understand patients’ experiences and examine the factors that influence their QOL and well-being to ensure that the services available are adequately tailored to them. Hence, further research is required to obtain a better understanding of the influence of spirituality on the health outcomes and general well-being of patients with ESRD.

Keywords: end-stage renal disease, general well-being, quality of life, spirituality

Procedia PDF Downloads 226

Authors: Ciro Moreno-Ramirez, Maria Tomas-Rodriguez, Simos A. Evangelou

Abstract:

A motorcycle's front end links the front wheel to the motorcycle's chassis and has two main functions: the front wheel suspension and the vehicle steering. Up to this date, several suspension systems have been developed in order to achieve the best possible front end behavior, being the telescopic fork the most common one and already subjected to several years of study in terms of its kinematics, dynamics, stability and control. A motorcycle telescopic fork suspension model consists of a couple of outer tubes which contain the suspension components (coil springs and dampers) internally and two inner tubes which slide into the outer ones allowing the suspension travel. The outer tubes are attached to the frame through two triple trees which connect the front end to the main frame through the steering bearings and allow the front wheel to turn about the steering axis. This system keeps the front wheel's displacement in a straight line parallel to the steering axis. However, there exist alternative suspension designs that allow different trajectories of the front wheel with the suspension travel. In this contribution, the authors investigate an alternative front suspension system (Hossack suspension) and its influence on the motorcycle nonlinear dynamics to identify and reduce stability risks that a new suspension systems may introduce in the motorcycle dynamics. Based on an existing high-fidelity motorcycle mathematical model, the front end geometry is modified to accommodate a Hossack suspension system. It is characterized by a double wishbone design that varies the front end geometry on certain maneuverings and, consequently, the machine's behavior/response. It consists of a double wishbone structure directly attached to the chassis. In here, the kinematics of this system and its impact on the motorcycle performance/stability are analyzed and compared to the well known telescopic fork suspension system. The framework of this research is the mathematical modelling and numerical simulation. Full stability analyses are performed in order to understand how the motorcycle dynamics may be affected by the newly introduced front end design. This study is carried out by a combination of nonlinear dynamical simulation and root-loci methods. A modal analysis is performed in order to get a deeper understanding of the different modes of oscillation and how the Hossack suspension system affects them. The results show that different kinematic designs of a double wishbone suspension systems do not modify the general motorcycle's stability. The normal modes properties remain unaffected by the new geometrical configurations. However, these normal modes differ from one suspension system to the other. It is seen that the normal modes behaviour depends on various important dynamic parameters, such as the front frame flexibility, the steering damping coefficient and the centre of mass location.

Keywords: nonlinear mechanical systems, motorcycle dynamics, suspension systems, stability

Procedia PDF Downloads 222

Authors: Karolina Rutkowska, Hubert Pausch, Jolanta Oprzadek, Krzysztof Flisikowski

Abstract:

The placenta is one of the most important organs that plays a crucial role in the fetal growth and development. Placenta dysfunction is one of the primary cause of the intrauterine growth restriction (IUGR). Cattle have the cotyledonary placenta which consists of two anatomical parts: fetal and maternal. In the case of cattle during the first months of pregnancy, it is very easy to separate maternal caruncle from fetal cotyledon tissue, easier in fact than removing an ordinary glove from one's hand. Which in fact make easier to conduct tissue-specific molecular studies. Typically, animal models for the study of IUGR are created using surgical methods and malnutrition of the pregnant mother or in the case of mice by genetic modifications. However, proposed cattle model with MIMT1Del/WT deletion is unique because it was created without any surgical methods what significantly distinguish it from the other animal models. The primary objective of the study was to identify differential expression of selected miRNAs in the placenta from normal and intrauterine growth restricted fetuses. There was examined the expression of miRNA in the fetal and maternal part of the placenta from 24 fetuses (12 samples from the fetal part of the placenta and 12 samples from maternal part of the placenta). In the study, there was done miRNAs sequencing in the placenta of MIMT1Del/WT fetuses and MIMT1WT/WT fetuses. Then, there were selected miRNAs that are involved in fetal growth and development. Analysis of miRNAs expression was conducted on ABI7500 machine. miRNAs expression was analyzed by reverse-transcription polymerase chain reaction (RT-PCR). As the reference gene was used SNORD47. The results were expressed as 2ΔΔCt: ΔΔCt = (Ctij − CtSNORD47j) − (Cti1 − CtSNORD471). Where Ctij and CtSNORD47j are the Ct values for gene i and for SNORD47 in a sample (named j); Cti1 and CtSNORD471 are the Ct values in sample 1. Differences between groups were evaluated with analysis of variance by using One-Way ANOVA. Bonferroni’s tests were used for interpretation of the data. All normalised miRNA expression values are expressed on a value of natural logarithm. The data were expressed as least squares mean with standard errors. Significance was declared when P < 0.05. The study shows that miRNAs expression depends on the part of the placenta where they origin (fetal or maternal) and on the genotype of the animal. miRNAs offer a particularly new approach to study IUGR. Corresponding tissue samples were collected according to the standard veterinary protocols according to the European Union Normative for Care and Use of Experimental Animals. All animal experiments were approved by the Animal Ethics Committee of the State Provincial Office of Southern Finland (ESAVI-2010-08583/YM-23).

Keywords: placenta, intrauterine growth restriction, miRNA, cattle

Procedia PDF Downloads 314

Authors: Halimat M. Ajose-Adeogun, Zaynab A. Bello

Abstract:

Artificial Intelligence (AI) and Natural Language Processing (NLP) have transformed computer language comprehension, allowing computers to comprehend spoken and written language with human-like cognition. NLP, a multidisciplinary area that combines rule-based linguistics, machine learning, and deep learning, enables computers to analyze and comprehend human language. NLP applications in medicine range from tackling issues in electronic health records (EHR) and psychiatry to improving diagnostic precision in orthopedic surgery and optimizing clinical procedures with novel technologies like chatbots. The technology shows promise in a variety of medical sectors, including quicker access to medical records, faster decision-making for healthcare personnel, diagnosing dysplasia in Barrett's esophagus, boosting radiology report quality, and so on. However, successful adoption requires training for healthcare workers, fostering a deep understanding of NLP components, and highlighting the significance of validation before actual application. Despite prevailing challenges, continuous multidisciplinary research and collaboration are critical for overcoming restrictions and paving the way for the revolutionary integration of NLP into medical practice. This integration has the potential to improve patient care, research outcomes, and administrative efficiency. The research methodology includes using NLP techniques for Sentiment Analysis and Emotion Recognition, such as evaluating text or audio data to determine the sentiment and emotional nuances communicated by users, which is essential for designing a responsive and sympathetic chatbot. Furthermore, the project includes the adoption of a Personalized Intervention strategy, in which chatbots are designed to personalize responses by merging NLP algorithms with specific user profiles, treatment history, and emotional states. The synergy between NLP and personalized medicine principles is critical for tailoring chatbot interactions to each user's demands and conditions, hence increasing the efficacy of mental health care. A detailed survey corroborated this synergy, revealing a remarkable 20% increase in patient satisfaction levels and a 30% reduction in workloads for healthcare practitioners. The poll, which focused on health outcomes and was administered to both patients and healthcare professionals, highlights the improved efficiency and favorable influence on the broader healthcare ecosystem.

Keywords: natural language processing, artificial intelligence, healthcare communication, electronic health records, patient care

Procedia PDF Downloads 76

Authors: C. M. Sapkota, B. P. Sapkota

Abstract:

Background: Continuous developments in science and technology are increasing the availability of thousands of medical devices – all of which should be of good quality and used appropriately to address global health challenges. It is obvious that bio medical devices are becoming ever more indispensable in health service delivery and among the key workforce responsible for their design, development, regulation, evaluation and training in their use: biomedical technician (BMET) is the crucial. As a pivotal member of health workforce, biomedical technicians are an essential component of the quality health service delivery mechanism supporting the attainment of the Sustainable Development Goals. Methods: The study was based on cross sectional descriptive design. Indicators measuring the quality of health services were assessed in Mechi Zonal Hospital (MZH) and Sagarmatha Zonal Hospital (SZH). Indicators were calculated based on the data about hospital utilization and performance of 2018 available in Medical record section of both hospitals. MZH had employed the BMET during 2018 but SZH had no BMET in 2018.Focus Group Discussion with health workers in both hospitals was conducted to validate the hospital records. Client exit interview was conducted to assess the level of client satisfaction in both the hospitals. Results: In MZH there was round the clock availability and utilization of Radio diagnostics equipment, Laboratory equipment. Operation Theater was functional throughout the year. Bed Occupancy rate in MZH was 97% but in SZH it was only 63%.In SZH, OT was functional only 54% of the days in 2018. CT scan machine was just installed but not functional. Computerized X-Ray in SZH was functional only in 72% of the days. Level of client satisfaction was 87% in MZH but was just 43% in SZH. MZH performed all (256) the Caesarean Sections but SZH performed only 36% of 210 Caesarean Sections in 2018. In annual performance ranking of Government Hospitals, MZH was placed in 1st rank while as SZH was placed in 19th rank out of 32 referral hospitals nationwide in 2018. Conclusion: Biomedical technicians are the crucial member of the human resource for health team with the pivotal role. Trained and qualified BMET professionals are required within health-care systems in order to design, evaluate, regulate, acquire, maintain, manage and train on safe medical technologies. Applying knowledge of engineering and technology to health-care systems to ensure availability, affordability, accessibility, acceptability and utilization of the safer, higher quality, effective, appropriate and socially acceptable bio medical technology to populations for preventive, promotive, curative, rehabilitative and palliative care across all levels of the health service delivery.

Keywords: biomedical equipment technicians, BMET, human resources for health, HRH, quality health service, rural hospitals

Procedia PDF Downloads 126

Authors: Beatrice Arthur

Abstract:

The rapid development of artificial intelligence (AI) has transformed various industries, enabling faster and more accurate decision-making processes. However, with these advancements come increased risks, including data privacy issues, systemic biases, and challenges related to transparency and accountability. As AI technologies become more integrated into business processes, there is a growing need for comprehensive auditing and assurance frameworks to manage these risks and ensure ethical use. This paper provides a literature review on AI auditing and assurance programs, highlighting the importance of adapting traditional audit methodologies to the complexities of AI-driven systems. Objective: The objective of this review is to explore current AI audit practices and their role in mitigating risks, ensuring accountability, and fostering trust in AI systems. The study aims to provide a structured framework for developing audit programs tailored to AI technologies while also investigating how AI impacts governance, risk management, and regulatory compliance in various sectors. Methodology: This research synthesizes findings from academic publications and industry reports from 2014 to 2024, focusing on the intersection of AI technologies and IT assurance practices. The study employs a qualitative review of existing audit methodologies and frameworks, particularly the COBIT 2019 framework, to understand how audit processes can be aligned with AI governance and compliance standards. The review also considers real-time auditing as an emerging necessity for influencing AI system design during early development stages. Outcomes: Preliminary findings indicate that while AI auditing is still in its infancy, it is rapidly gaining traction as both a risk management strategy and a potential driver of business innovation. Auditors are increasingly being called upon to develop controls that address the ethical and operational risks posed by AI systems. The study highlights the need for continuous monitoring and adaptable audit techniques to handle the dynamic nature of AI technologies. Future Directions: Future research will explore the development of AI-specific audit tools and real-time auditing capabilities that can keep pace with evolving technologies. There is also a need for cross-industry collaboration to establish universal standards for AI auditing, particularly in high-risk sectors like healthcare and finance. Further work will involve engaging with industry practitioners and policymakers to refine the proposed governance and audit frameworks. Funding/Support Acknowledgements: This research is supported by the Information Systems Assurance Management Program at Concordia University of Edmonton.

Keywords: AI auditing, assurance, risk management, governance, COBIT 2019, transparency, accountability, machine learning, compliance

Procedia PDF Downloads 23

Authors: Roberto Feltrero, Sara Osuna-Acedo

Abstract:

Responsible Research and Innovation have to accomplish one fundamental aim: everybody has to participate in the benefits of innovation, but also innovation has to be democratic; that is to say, everybody may have the possibility to participate in the decisions in the innovation process. Particularly, a democratic and inclusive model of social participation and innovation includes persons with disabilities and people at risk of discrimination. Innovations on Artificial Intelligence for social development have to accomplish the same dual goal: improving equality for accessing fields of public interest like education, training and public services, as well as improving civic and democratic participation in the process of developing such innovations for all. This research aims to develop innovations, policies and policy recommendations to apply and disseminate such artificial intelligence and social model for making educational and administrative processes more accessible. First, designing a citizen participation process to engage citizens in the designing and use of artificial intelligence tools for public services. This will result in improving trust in democratic institutions contributing to enhancing the transparency, effectiveness, accountability and legitimacy of public policy-making and allowing people to participate in the development of ethical standards for the use of such technologies. Second, improving educational tools for lifelong learning with AI models to improve accountability and educational data management. Dissemination, education and social participation will be integrated, measured and evaluated in innovative educational processes to make accessible all the educational technologies and content developed on AI about responsible and social innovation. A particular case will be presented regarding access for all to educational tools and public services. This accessibility requires cognitive adaptability because, many times, legal or administrative language is very complex. Not only for people with cognitive disabilities but also for old people or citizens at risk of educational or social discrimination. Artificial Intelligence natural language processing technologies can provide tools to translate legal, administrative, or educational texts to a more simple language that can be accessible to everybody. Despite technological advances in language processing and machine learning, this becomes a huge project if we really want to respect ethical and legal consequences because that kinds of consequences can only be achieved with civil and democratic engagement in two realms: 1) to democratically select texts that need and can be translated and 2) to involved citizens, experts and nonexperts, to produce and validate real examples of legal texts with cognitive adaptations to feed artificial intelligence algorithms for learning how to translate those texts to a more simple and accessible language, adapted to any kind of population.

Keywords: responsible research and innovation, AI social innovations, cognitive accessibility, public participation

Procedia PDF Downloads 88

Authors: Marcela De Oliveira, Marina P. Da Silva, Fernando C. G. Da Rocha, Jorge M. Santos, Jaime S. Cardoso, Paulo N. Lisboa-Filho

Abstract:

Multiple Sclerosis (MS) is an immune-mediated disease of the central nervous system characterized by neurodegeneration, inflammation, demyelination, and axonal loss. Magnetic resonance imaging (MRI), due to the richness in the information details provided, is the gold standard exam for diagnosis and follow-up of neurodegenerative diseases, such as MS. Brain atrophy, the gradual loss of brain volume, is quite extensive in multiple sclerosis, nearly 0.5-1.35% per year, far off the limits of normal aging. Thus, the brain volume quantification becomes an essential task for future analysis of the occurrence atrophy. The analysis of MRI has become a tedious and complex task for clinicians, who have to manually extract important information. This manual analysis is prone to errors and is time consuming due to various intra- and inter-operator variability. Nowadays, computerized methods for MRI segmentation have been extensively used to assist doctors in quantitative analyzes for disease diagnosis and monitoring. Thus, the purpose of this work was to evaluate the brain volume in MRI of MS patients. We used MRI scans with 30 slices of the five patients diagnosed with multiple sclerosis according to the McDonald criteria. The computational methods for the analysis of images were carried out in two steps: segmentation of the brain and brain volume quantification. The first image processing step was to perform brain extraction by skull stripping from the original image. In the skull stripper for MRI images of the brain, the algorithm registers a grayscale atlas image to the grayscale patient image. The associated brain mask is propagated using the registration transformation. Then this mask is eroded and used for a refined brain extraction based on level-sets (edge of the brain-skull border with dedicated expansion, curvature, and advection terms). In the second step, the brain volume quantification was performed by counting the voxels belonging to the segmentation mask and converted in cc. We observed an average brain volume of 1469.5 cc. We concluded that the automatic method applied in this work can be used for the brain extraction process and brain volume quantification in MRI. The development and use of computer programs can contribute to assist health professionals in the diagnosis and monitoring of patients with neurodegenerative diseases. In future works, we expect to implement more automated methods for the assessment of cerebral atrophy and brain lesions quantification, including machine-learning approaches. Acknowledgements: This work was supported by a grant from Brazilian agency Fundação de Amparo à Pesquisa do Estado de São Paulo (number 2019/16362-5).

Keywords: brain volume, magnetic resonance imaging, multiple sclerosis, skull stripper

Procedia PDF Downloads 146

Authors: Nir Nissim, Ran Yahalom, Tomer Lancewiki, Yuval Elovici, Boaz Lerner

Abstract:

Background: Attackers increasingly take advantage of innocent users who tend to use USB devices casually, assuming these devices benign when in fact they may carry an embedded malicious behavior or hidden malware. USB devices have many properties and capabilities that have become the subject of malicious operations. Many of the recent attacks targeting individuals, and especially organizations, utilize popular and widely used USB devices, such as mice, keyboards, flash drives, printers, and smartphones. However, current detection tools, techniques, and solutions generally fail to detect both the known and unknown attacks launched via USB devices. Significance: We propose USBWARE, a project that focuses on the vulnerabilities of USB devices and centers on the development of a comprehensive detection framework that relies upon a crucial attack repository. USBWARE will allow researchers and companies to better understand the vulnerabilities and attacks associated with USB devices as well as providing a comprehensive platform for developing detection solutions. Methodology: The framework of USBWARE is aimed at accurate detection of both known and unknown USB-based attacks by a process that efficiently enhances the framework's detection capabilities over time. The framework will integrate two main security approaches in order to enhance the detection of USB-based attacks associated with a variety of USB devices. The first approach is aimed at the detection of known attacks and their variants, whereas the second approach focuses on the detection of unknown attacks. USBWARE will consist of six independent but complimentary detection modules, each detecting attacks based on a different approach or discipline. These modules include novel ideas and algorithms inspired from or already developed within our team's domains of expertise, including cyber security, electrical and signal processing, machine learning, and computational biology. The establishment and maintenance of the USBWARE’s dynamic and up-to-date attack repository will strengthen the capabilities of the USBWARE detection framework. The attack repository’s infrastructure will enable researchers to record, document, create, and simulate existing and new USB-based attacks. This data will be used to maintain the detection framework’s updatability by incorporating knowledge regarding new attacks. Based on our experience in the cyber security domain, we aim to design the USBWARE framework so that it will have several characteristics that are crucial for this type of cyber-security detection solution. Specifically, the USBWARE framework should be: Novel, Multidisciplinary, Trusted, Lightweight, Extendable, Modular and Updatable and Adaptable. Major Findings: Based on our initial survey, we have already found more than 23 types of USB-based attacks, divided into six major categories. Our preliminary evaluation and proof of concepts showed that our detection modules can be used for efficient detection of several basic known USB attacks. Further research, development, and enhancements are required so that USBWARE will be capable to cover all of the major known USB attacks and to detect unknown attacks. Conclusion: USBWARE is a crucial detection framework that must be further enhanced and developed.

Keywords: USB, device, cyber security, attack, detection

Procedia PDF Downloads 397

Authors: Ahmad S. Darwish, Tarek Lemaoui, Hanifa Taher, Inas M. AlNashef, Fawzi Banat

Abstract:

This research reports a systematic top-down approach for designing neoteric hydrophobic solvents –particularly, deep eutectic solvents (DES) and ionic liquids (IL)– as furfural extractants from aqueous media for the application of sustainable biomass conversion. The first stage of the framework entailed screening 32 neoteric solvents to determine their efficacy against toluene as the application’s conventional benchmark for comparison. The selection criteria for the best solvents encompassed not only their efficiency in extracting furfural but also low viscosity and minimal toxicity levels. Additionally, for the DESs, their natural origins, availability, and biodegradability were also taken into account. From the screening pool, two neoteric solvents were selected: thymol:decanoic acid 1:1 (Thy:DecA) and trihexyltetradecyl phosphonium bis(trifluoromethylsulfonyl) imide [P₁₄,₆,₆,₆][NTf₂]. These solvents outperformed the toluene benchmark, achieving efficiencies of 94.1% and 97.1% respectively, compared to toluene’s 81.2%, while also possessing the desired properties. These solvents were then characterized thoroughly in terms of their physical properties, thermal properties, critical properties, and cross-contamination solubilities. The selected neoteric solvents were then extensively tested under various operating conditions, and an exceptional stable performance was exhibited, maintaining high efficiency across a broad range of temperatures (15–100 °C), pH levels (1–13), and furfural concentrations (0.1–2.0 wt%) with a remarkable equilibrium time of only 2 minutes, and most notably, demonstrated high efficiencies even at low solvent-to-feed ratios. The durability of the neoteric solvents was also validated to be stable over multiple extraction-regeneration cycles, with limited leachability to the aqueous phase (≈0.1%). Moreover, the extraction performance of the solvents was then modeled through machine learning, specifically multiple non-linear regression (MNLR) and artificial neural networks (ANN). The models demonstrated high accuracy, indicated by their low absolute average relative deviations with values of 2.74% and 2.28% for Thy:DecA and [P₁₄,₆,₆,₆][NTf₂], respectively, using MNLR, and 0.10% for Thy:DecA and 0.41% for [P₁₄,₆,₆,₆][NTf₂] using ANN, highlighting the significantly enhanced predictive accuracy of the ANN. The neoteric solvents presented herein offer noteworthy advantages over traditional organic solvents, including their high efficiency in both extraction and regeneration processes, their stability and minimal leachability, making them particularly suitable for applications involving aqueous media. Moreover, these solvents are more environmentally friendly, incorporating renewable and sustainable components like thymol and decanoic acid. This exceptional efficacy of the newly developed neoteric solvents signifies a significant advancement, providing a green and sustainable alternative for furfural production from biowaste.

Keywords: sustainable biomass conversion, furfural extraction, ionic liquids, deep eutectic solvents

Procedia PDF Downloads 69

Authors: Skyler Kim

Abstract:

An early diagnosis of leukemia has always been a challenge to doctors and hematologists. On a worldwide basis, it was reported that there were approximately 350,000 new cases in 2012, and diagnosing leukemia was time-consuming and inefficient because of an endemic shortage of flow cytometry equipment in current clinical practice. As the number of medical diagnosis tools increased and a large volume of high-quality data was produced, there was an urgent need for more advanced data analysis methods. One of these methods was the AI approach. This approach has become a major trend in recent years, and several research groups have been working on developing these diagnostic models. However, designing and implementing a leukemia diagnostic system in real clinical environments based on a deep learning approach with larger sets remains complex. Leukemia is a major hematological malignancy that results in mortality and morbidity throughout different ages. We decided to select acute lymphocytic leukemia to develop our diagnostic system since acute lymphocytic leukemia is the most common type of leukemia, accounting for 74% of all children diagnosed with leukemia. The results from this development work can be applied to all other types of leukemia. To develop our model, the Kaggle dataset was used, which consists of 15135 total images, 8491 of these are images of abnormal cells, and 5398 images are normal. In this paper, we design and implement a leukemia diagnostic system in a real clinical environment based on deep learning approaches with larger sets. The proposed diagnostic system has the function of detecting and classifying leukemia. Different from other AI approaches, we explore hybrid architectures to improve the current performance. First, we developed two independent convolutional neural network models: VGG19 and ResNet50. Then, using both VGG19 and ResNet50, we developed a hybrid deep learning architecture employing transfer learning techniques to extract features from each input image. In our approach, fusing the features from specific abstraction layers can be deemed as auxiliary features and lead to further improvement of the classification accuracy. In this approach, features extracted from the lower levels are combined into higher dimension feature maps to help improve the discriminative capability of intermediate features and also overcome the problem of network gradient vanishing or exploding. By comparing VGG19 and ResNet50 and the proposed hybrid model, we concluded that the hybrid model had a significant advantage in accuracy. The detailed results of each model’s performance and their pros and cons will be presented in the conference.

Keywords: acute lymphoblastic leukemia, hybrid model, leukemia diagnostic system, machine learning

Procedia PDF Downloads 187

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 105

Authors: Haley Gershon

Abstract:

The transition from using fossil fuel-based building material to formulating eco-friendly and biobased building materials plays a key role in sustainable building. The growing demand on a global level for biobased materials in the building and construction industries heightens the importance of carbon-14 testing, an analytical method used to determine the percentage of biobased content that comprises a material’s ingredients. This presentation will focus on the use of carbon-14 analysis within the building materials sector. Carbon-14, also known as radiocarbon, is a weakly radioactive isotope present in all living organisms. Any fossil material older than 50,000 years will not contain any carbon-14 content. The radiocarbon method is thus used to determine the amount of carbon-14 content present in a given sample. Carbon-14 testing is performed according to ASTM D6866, a standard test method developed specifically for biobased content determination of material in solid, liquid, or gaseous form, which requires radiocarbon dating. Samples are combusted and converted into a solid graphite form and then pressed onto a metal disc and mounted onto a wheel of an accelerator mass spectrometer (AMS) machine for the analysis. The AMS instrument is used in order to count the amount of carbon-14 present. By submitting samples for carbon-14 analysis, manufacturers of building materials can confirm the biobased content of ingredients used. Biobased testing through carbon-14 analysis reports results as percent biobased content, indicating the percentage of ingredients coming from biomass sourced carbon versus fossil carbon. The analysis is performed according to standardized methods such as ASTM D6866, ISO 16620, and EN 16640. Products 100% sourced from plants, animals, or microbiological material are therefore 100% biobased, while products sourced only from fossil fuel material are 0% biobased. Any result in between 0% and 100% biobased indicates that there is a mixture of both biomass-derived and fossil fuel-derived sources. Furthermore, biobased testing for building materials allows manufacturers to submit eligible material for certification and eco-label programs such as the United States Department of Agriculture (USDA) BioPreferred Program. This program includes a voluntary labeling initiative for biobased products, in which companies may apply to receive and display the USDA Certified Biobased Product label, stating third-party verification and displaying a product’s percentage of biobased content. The USDA program includes a specific category for Building Materials. In order to qualify for the biobased certification under this product category, examples of product criteria that must be met include minimum 62% biobased content for wall coverings, minimum 25% biobased content for lumber, and a minimum 91% biobased content for floor coverings (non-carpet). As a result, consumers can easily identify plant-based products in the marketplace.

Keywords: carbon-14 testing, biobased, biobased content, radiocarbon dating, accelerator mass spectrometry, AMS, materials

Procedia PDF Downloads 158

Authors: Éva Pintér, Péter Bagó, Nikolett Deutsch, Miklós Hetényi

Abstract:

The process of digital transformation has a profound influence on all sectors of the worldwide economy and the business environment. The influence of blockchain technology can be observed in the digital economy and e-government, rendering it an essential element of a nation's growth strategy. The banking industry is experiencing significant expansion and development of financial technology firms. Utilizing developing technologies such as artificial intelligence (AI), machine learning (ML), and big data (BD), these entrants are offering more streamlined financial solutions, promptly addressing client demands, and presenting a challenge to incumbent institutions. The advantages of digital transformation are evident in the corporate realm, and firms that resist its adoption put their survival at risk. The advent of digital technologies has revolutionized the business environment, streamlining processes and creating opportunities for enhanced communication and collaboration. Thanks to the aid of digital technologies, businesses can now swiftly and effortlessly retrieve vast quantities of information, all the while accelerating the process of creating new and improved products and services. Big data analytics is generally recognized as a transformative force in business, considered the fourth paradigm of science, and seen as the next frontier for innovation, competition, and productivity. Big data, an emerging technology that is shaping the future of the banking sector, offers numerous advantages to banks. It enables them to effectively track consumer behavior and make informed decisions, thereby enhancing their operational efficiency. Banks may embrace big data technologies to promptly and efficiently identify fraud, as well as gain insights into client preferences, which can then be leveraged to create better-tailored products and services. Moreover, the utilization of big data technology empowers banks to develop more intelligent and streamlined models for accurately recognizing and focusing on the suitable clientele with pertinent offers. There is a scarcity of research on big data analytics in the banking industry, with the majority of existing studies only examining the advantages and prospects associated with big data. Although big data technologies are crucial, there is a dearth of empirical evidence about the role of big data analytics (BDA) capabilities in bank performance. This research addresses a gap in the existing literature by introducing a model that combines the resource-based view (RBV), the technical organization environment framework (TOE), and dynamic capability theory (DC). This study investigates the influence of Big Data Analytics (BDA) utilization on the performance of market and risk management. This is supported by a comparative examination of Hungarian mobile banking services.

Keywords: big data, digital transformation, dynamic capabilities, mobile banking

Procedia PDF Downloads 64

Authors: Emre Kara, Şura Karakuzu, Ahmet Fatih Geylan, Metehan Demir, Kadir Koç, Halil Aykul

Abstract:

The material selection in the design of the sandwich structures is very crucial aspect because of the positive or negative influences of the base materials to the mechanical properties of the entire panel. In the literature, it was presented that the selection of the skin and core materials plays very important role on the behavior of the sandwich. Beside this, the use of the correct adhesive can make the whole structure to show better mechanical results and behavior. By this way, the sandwich structures realized in the study were obtained with the combination of aluminum foam core and three different glass fiber reinforced polymer (GFRP) skins using two different commercial adhesives which are based on flexible polyurethane and toughened epoxy. The static and dynamic tests were already applied on the sandwiches with different types of adhesives. In the present work, the static three-point bending tests were performed on the sandwiches having an aluminum foam core with the thickness of 15 mm, the skins with three different types of fabrics ([0°/90°] cross ply E-Glass Biaxial stitched, [0°/90°] cross ply E-Glass Woven and [0°/90°] cross ply S-Glass Woven which have same thickness value of 1.75 mm) and two different commercial adhesives (flexible polyurethane and toughened epoxy based) at different values of support span distances (L= 55, 70, 80, 125 mm) by aiming the analyses of their flexural performance. The skins used in the study were produced via Vacuum Assisted Resin Transfer Molding (VARTM) technique and were easily bonded onto the aluminum foam core with flexible and toughened adhesives under a very low pressure using press machine with the alignment tabs having the total thickness of the whole panel. The main results of the flexural loading are: force-displacement curves obtained after the bending tests, peak force values, absorbed energy, collapse mechanisms, adhesion quality and the effect of the support span length and adhesive type. The experimental results presented that the sandwiches with epoxy based toughened adhesive and the skins made of S-Glass Woven fabrics indicated the best adhesion quality and mechanical properties. The sandwiches with toughened adhesive exhibited higher peak force and energy absorption values compared to the sandwiches with flexible adhesive. The core shear mode occurred in the sandwiches with flexible polyurethane based adhesive through the thickness of the core while the same mode took place in the sandwiches with toughened epoxy based adhesive along the length of the core. The use of these sandwich structures can lead to a weight reduction of the transport vehicles, providing an adequate structural strength under operating conditions.

Keywords: adhesive and adhesion, aluminum foam, bending, collapse mechanisms

Procedia PDF Downloads 328

Authors: Alberto Sanchidrián, José A. Parra, Jesús Alonso, Julián Pecharromán, Antonia Pacios, Consuelo Huerta

Abstract:

Glass is a commonly used material in building; there is not a unique design solution as plates with a different number of layers and interlayers may be used. In most façades, a security glazing have to be used according to its performance in the impact pendulum. The European Standard EN 12600 establishes an impact test procedure for classification under the point of view of the human security, of flat plates with different thickness, using a pendulum of two tires and 50 kg mass that impacts against the plate from different heights. However, this test does not replicate the actual dimensions and border conditions used in building configurations and so the real stress distribution is not determined with this test. The influence of different boundary conditions, as the ones employed in construction sites, is not well taking into account when testing the behaviour of safety glazing and there is not a detailed procedure and criteria to determinate the glass resistance against human impact. To reproduce the actual boundary conditions on site, when needed, the pendulum test is arranged to be used "in situ", with no account for load control, stiffness, and without a standard procedure. Fracture stress of small and large glass plates fit a Weibull distribution with quite a big dispersion so conservative values are adopted for admissible fracture stress under static loads. In fact, test performed for human impact gives a fracture strength two or three times higher, and many times without a total fracture of the glass plate. Newest standards, as for example DIN 18008-4, states for an admissible fracture stress 2.5 times higher than the ones used for static and wing loads. Now two working areas are open: a) to define a standard for the ‘in situ’ test; b) to prepare a laboratory procedure that allows testing with more real stress distribution. To work on both research lines a laboratory that allows to test medium size specimens with different border conditions, has been developed. A special steel frame allows reproducing the stiffness of the glass support substructure, including a rigid condition used as reference. The dynamic behaviour of the glass plate and its support substructure have been characterized with finite elements models updated with modal tests results. In addition, a new portable impact machine is being used to get enough force and direction control during the impact test. Impact based on 100 J is used. To avoid problems with broken glass plates, the test have been done using an aluminium plate of 1000 mm x 700 mm size and 10 mm thickness supported on four sides; three different substructure stiffness conditions are used. A detailed control of the dynamic stiffness and the behaviour of the plate is done with modal tests. Repeatability of the test and reproducibility of results prove that procedure to control both, stiffness of the plate and the impact level, is necessary.

Keywords: glass plates, human impact test, modal test, plate boundary conditions

Procedia PDF Downloads 307

Authors: Pardis Moslemzadeh Tehrani

Abstract:

Due to the emergence of blockchain technology and the benefits of cryptocurrencies, intelligent or smart contracts are gaining traction. Artificial intelligence (AI) is transforming our lives, and it is being embraced by a wide range of sectors. Smart contracts, which are at the heart of blockchains, incorporate AI characteristics. Such contracts are referred to as "smart" contracts because of the underlying technology that allows contracting parties to agree on terms expressed in computer code that defines machine-readable instructions for computers to follow under specific situations. The transmission happens automatically if the conditions are met. Initially utilised for financial transactions, blockchain applications have since expanded to include the financial, insurance, and medical sectors, as well as supply networks. Raw material acquisition by suppliers, design, and fabrication by manufacturers, delivery of final products to consumers, and even post-sales logistics assistance are all part of supply chains. Many issues are linked with managing supply chains from the planning and coordination stages, which can be implemented in a smart contract in a blockchain due to their complexity. Manufacturing delays and limited third-party amounts of product components have raised concerns about the integrity and accountability of supply chains for food and pharmaceutical items. Other concerns include regulatory compliance in multiple jurisdictions and transportation circumstances (for instance, many products must be kept in temperature-controlled environments to ensure their effectiveness). Products are handled by several providers before reaching customers in modern economic systems. Information is sent between suppliers, shippers, distributors, and retailers at every stage of the production and distribution process. Information travels more effectively when individuals are eliminated from the equation. The usage of blockchain technology could be a viable solution to these coordination issues. In blockchains, smart contracts allow for the rapid transmission of production data, logistical data, inventory levels, and sales data. This research investigates the legal and technical advantages and disadvantages of AI-blockchain technology in the supply chain business. It aims to uncover the applicable legal problems and barriers to the use of AI-blockchain technology to supply chains, particularly in the food industry. It also discusses the essential legal and technological issues and impediments to supply chain implementation for stakeholders, as well as methods for overcoming them before releasing the technology to clients. Because there has been little research done on this topic, it is difficult for industrial stakeholders to grasp how blockchain technology could be used in their respective operations. As a result, the focus of this research will be on building advanced and complex contractual terms in supply chain smart contracts on blockchains to cover all unforeseen supply chain challenges.

Keywords: blockchain, supply chain, IoT, smart contract

Procedia PDF Downloads 126

Authors: Nguyen J. M., Lucas G., Ruan S., Digonnet H., Antonioli D.

Abstract:

Introduction: Deep Learning (DL) is a very powerful tool for analyzing image data. But for tabular data, it cannot compete with machine learning methods like XGBoost. The research question becomes: can tabular data be transformed into images that can be analyzed by simple CNNs (Convolutional Neuron Networks)? Will DL be the absolute tool for data classification? All current solutions consist in repositioning the variables in a 2x2 matrix using their correlation proximity. In doing so, it obtains an image whose pixels are the variables. We implement a technology, DeepNIC, that offers the possibility of obtaining an image for each variable, which can be analyzed by simple CNNs. Material and method: The 'ROP' (Regression OPtimized) model is a binary and atypical decision tree whose nodes are managed by a new artificial neuron, the Neurop. By positioning an artificial neuron in each node of the decision trees, it is possible to make an adjustment on a theoretically infinite number of variables at each node. From this new decision tree whose nodes are artificial neurons, we created the concept of a 'Random Forest of Perfect Trees' (RFPT), which disobeys Breiman's concepts by assembling very large numbers of small trees with no classification errors. From the results of the RFPT, we developed a family of 10 statistical information criteria, Nguyen Information Criterion (NICs), which evaluates in 3 dimensions the predictive quality of a variable: Performance, Complexity and Multiplicity of solution. A NIC is a probability that can be transformed into a grey level. The value of a NIC depends essentially on 2 super parameters used in Neurops. By varying these 2 super parameters, we obtain a 2x2 matrix of probabilities for each NIC. We can combine these 10 NICs with the functions AND, OR, and XOR. The total number of combinations is greater than 100,000. In total, we obtain for each variable an image of at least 1166x1167 pixels. The intensity of the pixels is proportional to the probability of the associated NIC. The color depends on the associated NIC. This image actually contains considerable information about the ability of the variable to make the prediction of Y, depending on the presence or absence of other variables. A basic CNNs model was trained for supervised classification. Results: The first results are impressive. Using the GSE22513 public data (Omic data set of markers of Taxane Sensitivity in Breast Cancer), DEEPNic outperformed other statistical methods, including XGBoost. We still need to generalize the comparison on several databases. Conclusion: The ability to transform any tabular variable into an image offers the possibility of merging image and tabular information in the same format. This opens up great perspectives in the analysis of metadata.

Keywords: tabular data, CNNs, NICs, DeepNICs, random forest of perfect trees, classification

Procedia PDF Downloads 125

Authors: Nkechi V. Osuji

Abstract:

The use of blockchain to address the issue of climate change is increasingly a discourse among countries, industries, and stakeholders. For a long time, the European Union (EU) has been combating the issue of climate action in industries through sustainability programs. One of such programs is the EU monitoring reporting and verification (MRV) program of the EU ETS. However, the system has some key challenges and areas for improvement, which makes it inefficient. The main objective of the research is to look at how blockchain can be used to improve the inefficiency of the EU ETS program for the Danish energy industry with a focus on its monitoring and reporting framework. Applying empirical data from 13 semi-structured expert interviews, three case studies, and literature reviews, three outcomes are presented in the study. The first is on the current conditions and challenges of monitoring and reporting CO₂ emission trading. The second is putting into consideration if blockchain is the right fit to solve these challenges and how. The third stage looks at the factors that might affect the implementation of such a system and provides recommendations to mitigate these challenges. The first stage of the findings reveals that the monitoring and reporting of CO₂ emissions is a mandatory requirement by law for all energy operators under the EU ETS program. However, most energy operators are non-compliant with the program in reality, which creates a gap and causes challenges in the monitoring and reporting of CO₂ emission trading. Other challenges the study found out are the lack of transparency, lack of standardization in CO₂ accounting, and the issue of double-counting in the current system. The second stage of the research was guided by three case studies and requirement engineering (RE) to explore these identified challenges and if blockchain is the right fit to address them. This stage of the research addressed the main research question: how can blockchain be used for monitoring and reporting CO₂ emission trading in the energy industry. Through analysis of the study data, the researcher developed a conceptual private permissioned Hyperledger blockchain and elucidated on how it can address the identified challenges. Particularly, the smart contract of blockchain was highlighted as a key feature. This is because of its ability to automate, be immutable, and digitally enforce negotiations without a middleman. These characteristics are unique in solving the issue of compliance, transparency, standardization, and double counting identified. The third stage of the research presents technological constraints and a high level of stakeholder collaboration as major factors that might affect the implementation of the proposed system. The proposed conceptual model requires high-level integration with other technologies such as the Internet of Things (IoT) and machine learning. Therefore, the study encourages future research in these areas. This is because blockchain is continually evolving its technology capabilities. As such, it remains a topic of interest in research and development for addressing climate change. Such a study is a good contribution to creating sustainable practices to solve the global climate issue.

Keywords: blockchain, carbon emission trading, European Union emission trading system, monitoring and reporting

Procedia PDF Downloads 128

Authors: Robert Wimmer, Soeren Eikemeier, Michael Berger, Anita Preisler

Abstract:

A relatively large percentage of energy and resource consumption occurs in the building sector. This concerns the production of building materials, the construction of buildings and also the energy consumption during the use phase. Therefore, the overall objective of this EU LIFE project “LIFE Cycle Habitation” (LIFE13 ENV/AT/000741) is to demonstrate innovative building concepts that significantly reduce CO₂emissions, mitigate climate change and contain a minimum of grey energy over their entire life cycle. The project is being realised with the contribution of the LIFE financial instrument of the European Union. The ultimate goal is to design and build prototypes for carbon-neutral and “LIFE cycle”-oriented residential buildings and make energy-efficient settlements the standard of tomorrow in line with the EU 2020 objectives. To this end, a resource and energy-efficient building compound is being built in Böheimkirchen, Lower Austria, which includes 6 living units and a community area as well as 2 single family houses with a total usable floor surface of approximately 740 m². Different innovative straw bale construction types (load bearing and pre-fabricated non loadbearing modules) together with a highly innovative energy-supply system, which is based on the maximum use of thermal energy for thermal energy services, are going to be implemented. Therefore only renewable resources and alternative energies are used to generate thermal as well as electrical energy. This includes the use of solar energy for space heating, hot water and household appliances like dishwasher or washing machine, but also a cooking place for the community area operated with thermal oil as heat transfer medium on a higher temperature level. Solar collectors in combination with a biomass cogeneration unit and photovoltaic panels are used to provide thermal and electric energy for the living units according to the seasonal demand. The building concepts are optimised by support of dynamic simulations. A particular focus is on the production and use of modular prefabricated components and building parts made of regionally available, highly energy-efficient, CO₂-storing renewable materials like straw bales. The building components will be produced in collaboration by local SMEs that are organised in an efficient way. The whole building process and results are monitored and prepared for knowledge transfer and dissemination including a trial living in the residential units to test and monitor the energy supply system and to involve stakeholders into evaluation and dissemination of the applied technologies and building concepts. The realised building concepts should then be used as templates for a further modular extension of the settlement in a second phase.

Keywords: energy-efficiency, green architecture, renewable resources, sustainable building

Procedia PDF Downloads 149