Search results for: atrous convolutional

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 85

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 148

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 196

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 131

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 132

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 198

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 226

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 94

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 184

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 149

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 136

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 76

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 73

Authors: David J. Foran, Nhan Do, Samuel Ajjarapu, Wenjin Chen, Tahsin Kurc, Joel H. Saltz

Abstract:

The large-scale data and computational requirements of investigators throughout the clinical and research communities demand an informatics infrastructure that supports both existing and new investigative and translational projects in a robust, secure environment. In some subspecialties of medicine and research, the capacity to generate data has outpaced the methods and technology used to aggregate, organize, access, and reliably retrieve this information. Leading health care centers now recognize the utility of establishing an enterprise-wide, clinical data warehouse. The primary benefits that can be realized through such efforts include cost savings, efficient tracking of outcomes, advanced clinical decision support, improved prognostic accuracy, and more reliable clinical trials matching. The overarching objective of the work presented here is the development and implementation of a flexible Intelligent Retrieval and Interrogation System (IRIS) that exploits the combined use of computational imaging, genomics, and data-mining capabilities to facilitate clinical assessments and translational research in oncology. The proposed System includes a multi-modal, Clinical & Research Data Warehouse (CRDW) that is tightly integrated with a suite of computational and machine-learning tools to provide insight into the underlying tumor characteristics that are not be apparent by human inspection alone. A key distinguishing feature of the System is a configurable Extract, Transform and Load (ETL) interface that enables it to adapt to different clinical and research data environments. This project is motivated by the growing emphasis on establishing Learning Health Systems in which cyclical hypothesis generation and evidence evaluation become integral to improving the quality of patient care. To facilitate iterative prototyping and optimization of the algorithms and workflows for the System, the team has already implemented a fully functional Warehouse that can reliably aggregate information originating from multiple data sources including EHR’s, Clinical Trial Management Systems, Tumor Registries, Biospecimen Repositories, Radiology PAC systems, Digital Pathology archives, Unstructured Clinical Documents, and Next Generation Sequencing services. The System enables physicians to systematically mine and review the molecular, genomic, image-based, and correlated clinical information about patient tumors individually or as part of large cohorts to identify patterns that may influence treatment decisions and outcomes. The CRDW core system has facilitated peer-reviewed publications and funded projects, including an NIH-sponsored collaboration to enhance the cancer registries in Georgia, Kentucky, New Jersey, and New York, with machine-learning based classifications and quantitative pathomics, feature sets. The CRDW has also resulted in a collaboration with the Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC) at the U.S. Department of Veterans Affairs to develop algorithms and workflows to automate the analysis of lung adenocarcinoma. Those studies showed that combining computational nuclear signatures with traditional WHO criteria through the use of deep convolutional neural networks (CNNs) led to improved discrimination among tumor growth patterns. The team has also leveraged the Warehouse to support studies to investigate the potential of utilizing a combination of genomic and computational imaging signatures to characterize prostate cancer. The results of those studies show that integrating image biomarkers with genomic pathway scores is more strongly correlated with disease recurrence than using standard clinical markers.

Keywords: clinical data warehouse, decision support, data-mining, intelligent databases, machine-learning.

Procedia PDF Downloads 126