Search results for: multi-class AdaBoost classifier

Authors: Monica Gonzalez Machorro

Abstract:

Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.

Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment

Procedia PDF Downloads 126

Authors: Lily Ingsrisawang, Tasanee Nacharoen

Abstract:

Introduction: The problems of unbalanced data sets generally appear in real world applications. Due to unequal class distribution, many research papers found that the performance of existing classifier tends to be biased towards the majority class. The k -nearest neighbors’ nonparametric discriminant analysis is one method that was proposed for classifying unbalanced classes with good performance. Hence, the methods of discriminant analysis are of interest to us in investigating misclassification error rates for class-imbalanced data of three diabetes risk groups. Objective: The purpose of this study was to compare the classification performance between parametric discriminant analysis and nonparametric discriminant analysis in a three-class classification application of class-imbalanced data of diabetes risk groups. Methods: Data from a healthy project for 599 staffs in a government hospital in Bangkok were obtained for the classification problem. The staffs were diagnosed into one of three diabetes risk groups: non-risk (90%), risk (5%), and diabetic (5%). The original data along with the variables; diabetes risk group, age, gender, cholesterol, and BMI was analyzed and bootstrapped up to 50 and 100 samples, 599 observations per sample, for additional estimation of misclassification error rate. Each data set was explored for the departure of multivariate normality and the equality of covariance matrices of the three risk groups. Both the original data and the bootstrap samples show non-normality and unequal covariance matrices. The parametric linear discriminant function, quadratic discriminant function, and the nonparametric k-nearest neighbors’ discriminant function were performed over 50 and 100 bootstrap samples and applied to the original data. In finding the optimal classification rule, the choices of prior probabilities were set up for both equal proportions (0.33: 0.33: 0.33) and unequal proportions with three choices of (0.90:0.05:0.05), (0.80: 0.10: 0.10) or (0.70, 0.15, 0.15). Results: The results from 50 and 100 bootstrap samples indicated that the k-nearest neighbors approach when k = 3 or k = 4 and the prior probabilities of {non-risk:risk:diabetic} as {0.90:0.05:0.05} or {0.80:0.10:0.10} gave the smallest error rate of misclassification. Conclusion: The k-nearest neighbors approach would be suggested for classifying a three-class-imbalanced data of diabetes risk groups.

Keywords: error rate, bootstrap, diabetes risk groups, k-nearest neighbors

Procedia PDF Downloads 433

Authors: Mohammed Al Sulaimani, Hamad Al Manhi

Abstract:

With the development of Remote Sensing technology, the resolution of optical Remote Sensing images has greatly improved, and images have become largely available. Numerous detectors have been developed for detecting different types of objects. In the past few years, Remote Sensing has benefited a lot from deep learning, particularly Deep Convolution Neural Networks (CNNs). Deep learning holds great promise to fulfill the challenging needs of Remote Sensing and solving various problems within different fields and applications. The use of Unmanned Aerial Systems in acquiring Aerial Photos has become highly used and preferred by most organizations to support their activities because of their high resolution and accuracy, which make the identification and detection of very small features much easier than Satellite Images. And this has opened an extreme era of Deep Learning in different applications not only in feature extraction and prediction but also in analysis. This work addresses the capacity of Machine Learning and Deep Learning in detecting and extracting Oil Leaks from Flowlines (Onshore) using High-Resolution Aerial Photos which have been acquired by UAS fixed with RGB Sensor to support early detection of these leaks and prevent the company from the leak’s losses and the most important thing environmental damage. Here, there are two different approaches and different methods of DL have been demonstrated. The first approach focuses on detecting the Oil Leaks from the RAW Aerial Photos (not processed) using a Deep Learning called Single Shoot Detector (SSD). The model draws bounding boxes around the leaks, and the results were extremely good. The second approach focuses on detecting the Oil Leaks from the Ortho-mosaiced Images (Georeferenced Images) by developing three Deep Learning Models using (MaskRCNN, U-Net and PSP-Net Classifier). Then, post-processing is performed to combine the results of these three Deep Learning Models to achieve a better detection result and improved accuracy. Although there is a relatively small amount of datasets available for training purposes, the Trained DL Models have shown good results in extracting the extent of the Oil Leaks and obtaining excellent and accurate detection.

Keywords: GIS, remote sensing, oil leak detection, machine learning, aerial photos, unmanned aerial systems

Procedia PDF Downloads 31

Authors: Rosa Figueroa, Christopher Flores

Abstract:

Text categorization is the problem of assigning a new document to a set of predetermined categories, on the basis of a training set of free-text data that contains documents whose category membership is known. To train a classification model, it is necessary to extract characteristics in the form of tokens that facilitate the learning and classification process. In text categorization, the feature extraction process involves the use of word sequences also known as N-grams. In general, it is expected that documents belonging to the same category share similar features. The Smith-Waterman (SW) algorithm is a dynamic programming algorithm that performs a local sequence alignment in order to determine similar regions between two strings or protein sequences. This work explores the use of SW algorithm as an alternative to feature extraction in text categorization. The dataset used for this purpose, contains 2,610 annotated documents with the classes Obese/Non-Obese. This dataset was represented in a matrix form using the Bag of Word approach. The score selected to represent the occurrence of the tokens in each document was the term frequency-inverse document frequency (TF-IDF). In order to extract features for classification, four experiments were conducted: the first experiment used SW to extract features, the second one used unigrams (single word), the third one used bigrams (two word sequence) and the last experiment used a combination of unigrams and bigrams to extract features for classification. To test the effectiveness of the extracted feature set for the four experiments, a Support Vector Machine (SVM) classifier was tuned using 20% of the dataset. The remaining 80% of the dataset together with 5-Fold Cross Validation were used to evaluate and compare the performance of the four experiments of feature extraction. Results from the tuning process suggest that SW performs better than the N-gram based feature extraction. These results were confirmed by using the remaining 80% of the dataset, where SW performed the best (accuracy = 97.10%, weighted average F-measure = 97.07%). The second best was obtained by the combination of unigrams-bigrams (accuracy = 96.04, weighted average F-measure = 95.97) closely followed by the bigrams (accuracy = 94.56%, weighted average F-measure = 94.46%) and finally unigrams (accuracy = 92.96%, weighted average F-measure = 92.90%).

Keywords: comorbidities, machine learning, obesity, Smith-Waterman algorithm

Procedia PDF Downloads 296

Authors: Mohammad Tarek Al Muallim, Ozhan Duzenli, Ceyhun Ilguy

Abstract:

Harbor protection systems are so important. The need for automatic protection systems has increased over the last years. Diver detection active sonar has great significance. It used to detect underwater threats such as divers and autonomous underwater vehicle. To automatically detect such threats the sonar image is processed by algorithms. These algorithms used to detect, track and classify of underwater objects. In this work, divers tracking and classification algorithm is improved be proposing a robust wake detection method. To detect objects the sonar images is normalized then segmented based on fixed threshold. Next, the centroids of the segments are found and clustered based on distance metric. Then to track the objects linear Kalman filter is applied. To reduce effect of noise and creation of false tracks, the Kalman tracker is fine tuned. The tuning is done based on our active sonar specifications. After the tracks are initialed and updated they are subjected to a filtering stage to eliminate the noisy and unstable tracks. Also to eliminate object with a speed out of the diver speed range such as buoys and fast boats. Afterwards the result tracks are subjected to a classification stage to deiced the type of the object been tracked. Here the classification stage is to deice wither if the tracked object is an open circuit diver or a close circuit diver. At the classification stage, a small area around the object is extracted and a novel wake detection method is applied. The morphological features of the object with his wake is extracted. We used support vector machine to find the best classifier. The sonar training images and the test images are collected by ARMELSAN Defense Technologies Company using the portable diver detection sonar ARAS-2023. After applying the algorithm to the test sonar data, we get fine and stable tracks of the divers. The total classification accuracy achieved with the diver type is 97%.

Keywords: harbor protection, diver detection, active sonar, wake detection, diver classification

Procedia PDF Downloads 237

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Manufacturing companies are facing global competition and enormous cost pressure. The use of machine learning applications can help reduce production costs and create added value. Predictive quality enables the securing of product quality through data-supported predictions using machine learning models as a basis for decisions on test results. Furthermore, machine learning methods are able to process large amounts of data, deal with unfavourable row-column ratios and detect dependencies between the covariates and the given target as well as assess the multidimensional influence of all input variables on the target. Real production data are often subject to highly fluctuating boundary conditions and unbalanced data sets. Changes in production data manifest themselves in trends, systematic shifts, and seasonal effects. Thus, Machine learning applications require intensive pre-processing and feature selection. Data preprocessing includes rule-based data cleaning, the application of dimensionality reduction techniques, and the identification of comparable data subsets. Within the used real data set of Bosch hydraulic valves, the comparability of the same production conditions in the production of hydraulic valves within certain time periods can be identified by applying the concept drift method. Furthermore, a classification model is developed to evaluate the feature importance in different subsets within the identified time periods. By selecting comparable and stable features, the number of features used can be significantly reduced without a strong decrease in predictive power. The use of cross-process production data along the value chain of hydraulic valves is a promising approach to predict the quality characteristics of workpieces. In this research, the ada boosting classifier is used to predict the leakage of hydraulic valves based on geometric gauge blocks from machining, mating data from the assembly, and hydraulic measurement data from end-of-line testing. In addition, the most suitable methods are selected and accurate quality predictions are achieved.

Keywords: classification, achine learning, predictive quality, feature selection

Procedia PDF Downloads 161

Authors: H. Jung, N. Kim, B. Kang, J. Choe

Abstract:

History matching is a crucial procedure for predicting reservoir performances and making future decisions. However, it is difficult due to uncertainties of initial reservoir models. Therefore, it is important to have reliable initial models for successful history matching of highly heterogeneous reservoirs such as channel reservoirs. In this paper, we proposed a novel scheme for regenerating geological models using support vector machine (SVM) and principal component analysis (PCA). First, we perform PCA for figuring out main geological characteristics of models. Through the procedure, permeability values of each model are transformed to new parameters by principal components, which have eigenvalues of large magnitude. Secondly, the parameters are projected into two-dimensional plane by multi-dimensional scaling (MDS) based on Euclidean distances. Finally, we train an SVM classifier using 20% models which show the most similar or dissimilar well oil production rates (WOPR) with the true values (10% for each). Then, the other 80% models are classified by trained SVM. We select models on side of low WOPR errors. One hundred channel reservoir models are initially generated by single normal equation simulation. By repeating the classification process, we can select models which have similar geological trend with the true reservoir model. The average field of the selected models is utilized as a probability map for regeneration. Newly generated models can preserve correct channel features and exclude wrong geological properties maintaining suitable uncertainty ranges. History matching with the initial models cannot provide trustworthy results. It fails to find out correct geological features of the true model. However, history matching with the regenerated ensemble offers reliable characterization results by figuring out proper channel trend. Furthermore, it gives dependable prediction of future performances with reduced uncertainties. We propose a novel classification scheme which integrates PCA, MDS, and SVM for regenerating reservoir models. The scheme can easily sort out reliable models which have similar channel trend with the reference in lowered dimension space.

Keywords: history matching, principal component analysis, reservoir modelling, support vector machine

Procedia PDF Downloads 158

Authors: Manutchanok Jongprasithporn, Rawiphorn Srivilai, Paweena Pongsopha

Abstract:

Fall is the most serious accident leading to increased unintentional injuries and mortality. Falls are not only the cause of suffering and functional impairments to the individuals, but also the cause of increasing medical cost and days away from work. The early detection of falls could be an advantage to reduce fall-related injuries and consequences of falls. Smartphones, embedded accelerometer, have become a common device in everyday life due to decreasing technology cost. This paper explores a physical activity monitoring and fall detection application in smartphones which is a non-invasive biomedical device to determine physical activities and fall event. The combination of application and sensors could perform as a biomedical sensor to monitor physical activities and recognize a fall. We have chosen Android-based smartphone in this study since android operating system is an open-source and no cost. Moreover, android phone users become a majority of Thai’s smartphone users. We developed Thai 3 Axis (TH3AX) as a physical activities and fall detection application which included command, manual, results in Thai language. The smartphone was attached to right hip of 10 young, healthy adult subjects (5 males, 5 females; aged< 35y) to collect accelerometer and gyroscope data during performing physical activities (e.g., walking, running, sitting, and lying down) and falling to determine threshold for each activity. Dependent variables are including accelerometer data (acceleration, peak acceleration, average resultant acceleration, and time between peak acceleration). A repeated measures ANOVA was performed to test whether there are any differences between DVs’ means. Statistical analyses were considered significant at p<0.05. After finding threshold, the results were used as training data for a predictive model of activity recognition. In the future, accuracies of activity recognition will be performed to assess the overall performance of the classifier. Moreover, to help improve the quality of life, our system will be implemented with patients and elderly people who need intensive care in hospitals and nursing homes in Thailand.

Keywords: activity recognition, accelerometer, fall, gyroscope, smartphone

Procedia PDF Downloads 691

Authors: Kristina Sakalauskiene, Renaldas Raisutis, Gintare Linkeviciute, Skaidra Valiukeviciene

Abstract:

Cutaneous melanoma is a melanocytic skin tumour, which has a very poor prognosis while is highly resistant to treatment and tends to metastasize. Thickness of melanoma is one of the most important biomarker for stage of disease, prognosis and surgery planning. In this study, we hypothesized that the automatic analysis of spectrophotometric images and high-frequency ultrasonic 2D data can improve differential diagnosis of cutaneous melanoma and provide additional information about tumour penetration depth. This paper presents the novel complex automatic system for non-invasive melanocytic skin tumour differential diagnosis and penetration depth evaluation. The system is composed of region of interest segmentation in spectrophotometric images and high-frequency ultrasound data, quantitative parameter evaluation, informative feature extraction and classification with linear regression classifier. The segmentation of melanocytic skin tumour region in ultrasound image is based on parametric integrated backscattering coefficient calculation. The segmentation of optical image is based on Otsu thresholding. In total 29 quantitative tissue characterization parameters were evaluated by using ultrasound data (11 acoustical, 4 shape and 15 textural parameters) and 55 quantitative features of dermatoscopic and spectrophotometric images (using total melanin, dermal melanin, blood and collagen SIAgraphs acquired using spectrophotometric imaging device SIAscope). In total 102 melanocytic skin lesions (including 43 cutaneous melanomas) were examined by using SIAscope and ultrasound system with 22 MHz center frequency single element transducer. The diagnosis and Breslow thickness (pT) of each MST were evaluated during routine histological examination after excision and used as a reference. The results of this study have shown that automatic analysis of spectrophotometric and high frequency ultrasound data can improve non-invasive classification accuracy of early-stage cutaneous melanoma and provide supplementary information about tumour penetration depth.

Keywords: cutaneous melanoma, differential diagnosis, high-frequency ultrasound, melanocytic skin tumours, spectrophotometric imaging

Procedia PDF Downloads 268

Authors: Besma Khalfoun

Abstract:

In many current Human Activity Recognition (HAR) applications, users' data is frequently shared and centrally stored by third parties, posing a significant privacy risk. This practice makes these entities attractive targets for extracting sensitive information about users, including their identity, health status, and location, thereby directly violating users' privacy. To tackle the issue of centralized data storage, a relatively recent paradigm known as federated learning has emerged. In this approach, users' raw data remains on their smartphones, where they train the HAR model locally. However, users still share updates of their local models originating from raw data. These updates are vulnerable to several attacks designed to extract sensitive information, such as determining whether a data sample is used in the training process, recovering the training data with inversion attacks, or inferring a specific attribute or property from the training data. In this paper, we first introduce PUR-Attack, a parameter-based user re-identification attack developed for HAR applications within a federated learning setting. It involves associating anonymous model updates (i.e., local models' weights or parameters) with the originating user's identity using background knowledge. PUR-Attack relies on a simple yet effective machine learning classifier and produces promising results. Specifically, we have found that by considering the weights of a given layer in a HAR model, we can uniquely re-identify users with an attack success rate of almost 100%. This result holds when considering a small attack training set and various data splitting strategies in the HAR model training. Thus, it is crucial to investigate protection methods to mitigate this privacy threat. Along this path, we propose SAFER, a privacy-preserving mechanism based on adaptive local differential privacy. Before sharing the model updates with the FL server, SAFER adds the optimal noise based on the re-identification risk assessment. Our approach can achieve a promising tradeoff between privacy, in terms of reducing re-identification risk, and utility, in terms of maintaining acceptable accuracy for the HAR model.

Keywords: federated learning, privacy risk assessment, re-identification risk, privacy preserving mechanisms, local differential privacy, human activity recognition

Procedia PDF Downloads 10

Authors: Nassima Noufail, Sara Bouhali

Abstract:

In this work, we develop a semi-supervised solution for the purpose of action detection in videos and propose an efficient algorithm for video segmentation. The approach is divided into video segmentation, feature extraction, and classification. In the first part, a video is segmented into clips, and we used the K-means algorithm for this segmentation; our goal is to find groups based on similarity in the video. The application of k-means clustering into all the frames is time-consuming; therefore, we started by the identification of transition frames where the scene in the video changes significantly, and then we applied K-means clustering into these transition frames. We used two image filters, the gaussian filter and the Laplacian of Gaussian. Each filter extracts a set of features from the frames. The Gaussian filter blurs the image and omits the higher frequencies, and the Laplacian of gaussian detects regions of rapid intensity changes; we then used this vector of filter responses as an input to our k-means algorithm. The output is a set of cluster centers. Each video frame pixel is then mapped to the nearest cluster center and painted with a corresponding color to form a visual map. The resulting visual map had similar pixels grouped. We then computed a cluster score indicating how clusters are near each other and plotted a signal representing frame number vs. clustering score. Our hypothesis was that the evolution of the signal would not change if semantically related events were happening in the scene. We marked the breakpoints at which the root mean square level of the signal changes significantly, and each breakpoint is an indication of the beginning of a new video segment. In the second part, for each segment from part 1, we randomly selected a 16-frame clip, then we extracted spatiotemporal features using convolutional 3D network C3D for every 16 frames using a pre-trained model. The C3D final output is a 512-feature vector dimension; hence we used principal component analysis (PCA) for dimensionality reduction. The final part is the classification. The C3D feature vectors are used as input to a multi-class linear support vector machine (SVM) for the training model, and we used a multi-classifier to detect the action. We evaluated our experiment on the UCF101 dataset, which consists of 101 human action categories, and we achieved an accuracy that outperforms the state of art by 1.2%.

Keywords: video segmentation, action detection, classification, Kmeans, C3D

Procedia PDF Downloads 77

Authors: Zeinab Jafari A., Ali Sharifnezhad B., Mohammad Razi C., Mohammad Haghpanahi D., Arash Maghsoudi

Abstract:

Background and Objective: Sports-related rupture of the anterior cruciate ligament (ACL) and following injuries have been associated with various disorders, such as long-lasting changes in muscle activation patterns in athletes, which might last after ACL reconstruction (ACLR). The rupture of the ACL might result in abnormal patterns of movement execution, extending the treatment period and delaying athletes’ return to sports (RTS). As ACL injury is especially prevalent among athletes, the lengthy treatment process and athletes’ absence from sports are of great concern to athletes and coaches. Thus, estimating safe time of RTS is of crucial importance. Therefore, using a deep neural network (DNN) to classify the health levels of ACL in injured athletes, this study aimed to estimate the safe time for athletes to return to competitions. Methods: Ten athletes with ACLR and fourteen healthy controls participated in this study. Three health levels of ACL were defined: healthy, six-month post-ACLR surgery and nine-month post-ACLR surgery. Athletes with ACLR were tested six and nine months after the ACLR surgery. During the course of this study, surface electromyography (sEMG) signals were recorded from five knee muscles, namely Rectus Femoris (RF), Vastus Lateralis (VL), Vastus Medialis (VM), Biceps Femoris (BF), Semitendinosus (ST), during single-leg drop landing (SLDL) and forward hopping (SLFH) tasks. The Pseudo-Wigner-Ville distribution (PWVD) was used to produce three-dimensional (3-D) images of the energy distribution patterns of sEMG signals. Then, these 3-D images were converted to two-dimensional (2-D) images implementing the heat mapping technique, which were then fed to a deep convolutional neural network (DCNN). Results: In this study, we estimated the safe time of RTS by designing a DCNN classifier with an accuracy of 90 %, which could classify ACL into three health levels. Discussion: The findings of this study demonstrate the potential of the DCNN classification technique using sEMG signals in estimating RTS time, which will assist in evaluating the recovery process of ACLR in athletes.

Keywords: anterior cruciate ligament reconstruction, return to sports, surface electromyography, deep convolutional neural network

Procedia PDF Downloads 77

Authors: Maxence Queyrel, Edi Prifti, Alexandre Templier, Jean-Daniel Zucker

Abstract:

Analysis of the human microbiome using metagenomic sequencing data has demonstrated high ability in discriminating various human diseases. Raw metagenomic sequencing data require multiple complex and computationally heavy bioinformatics steps prior to data analysis. Such data contain millions of short sequences read from the fragmented DNA sequences and stored as fastq files. Conventional processing pipelines consist in multiple steps including quality control, filtering, alignment of sequences against genomic catalogs (genes, species, taxonomic levels, functional pathways, etc.). These pipelines are complex to use, time consuming and rely on a large number of parameters that often provide variability and impact the estimation of the microbiome elements. Training Deep Neural Networks directly from raw sequencing data is a promising approach to bypass some of the challenges associated with mainstream bioinformatics pipelines. Most of these methods use the concept of word and sentence embeddings that create a meaningful and numerical representation of DNA sequences, while extracting features and reducing the dimensionality of the data. In this paper we present an end-to-end approach that classifies patients into disease groups directly from raw metagenomic reads: metagenome2vec. This approach is composed of four steps (i) generating a vocabulary of k-mers and learning their numerical embeddings; (ii) learning DNA sequence (read) embeddings; (iii) identifying the genome from which the sequence is most likely to come and (iv) training a multiple instance learning classifier which predicts the phenotype based on the vector representation of the raw data. An attention mechanism is applied in the network so that the model can be interpreted, assigning a weight to the influence of the prediction for each genome. Using two public real-life data-sets as well a simulated one, we demonstrated that this original approach reaches high performance, comparable with the state-of-the-art methods applied directly on processed data though mainstream bioinformatics workflows. These results are encouraging for this proof of concept work. We believe that with further dedication, the DNN models have the potential to surpass mainstream bioinformatics workflows in disease classification tasks.

Keywords: deep learning, disease prediction, end-to-end machine learning, metagenomics, multiple instance learning, precision medicine

Procedia PDF Downloads 124

Authors: Alvaro Figueira, Bruno Cabral

Abstract:

Nowadays, students are used to be assessed through an online platform. Educators have stepped up from a period in which they endured the transition from paper to digital. The use of a diversified set of question types that range from quizzes to open questions is currently common in most university courses. In many courses, today, the evaluation methodology also fosters the students’ online participation in forums, the download, and upload of modified files, or even the participation in group activities. At the same time, new pedagogy theories that promote the active participation of students in the learning process, and the systematic use of problem-based learning, are being adopted using an eLearning system for that purpose. However, although there can be a lot of feedback from these activities to student’s, usually it is restricted to the assessments of online well-defined tasks. In this article, we propose an automatic system that informs students of abnormal deviations of a 'correct' learning path in the course. Our approach is based on the fact that by obtaining this information earlier in the semester, may provide students and educators an opportunity to resolve an eventual problem regarding the student’s current online actions towards the course. Our goal is to prevent situations that have a significant probability to lead to a poor grade and, eventually, to failing. In the major learning management systems (LMS) currently available, the interaction between the students and the system itself is registered in log files in the form of registers that mark beginning of actions performed by the user. Our proposed system uses that logged information to derive new one: the time each student spends on each activity, the time and order of the resources used by the student and, finally, the online resource usage pattern. Then, using the grades assigned to the students in previous years, we built a learning dataset that is used to feed a machine learning meta classifier. The produced classification model is then used to predict the grades a learning path is heading to, in the current year. Not only this approach serves the teacher, but also the student to receive automatic feedback on her current situation, having past years as a perspective. Our system can be applied to online courses that integrate the use of an online platform that stores user actions in a log file, and that has access to other student’s evaluations. The system is based on a data mining process on the log files and on a self-feedback machine learning algorithm that works paired with the Moodle LMS.

Keywords: data mining, e-learning, grade prediction, machine learning, student learning path

Procedia PDF Downloads 121

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 105

Authors: Arindam Chaudhuri

Abstract:

Classification of data has been actively used for most effective and efficient means of conveying knowledge and information to users. The prima face has always been upon techniques for extracting useful knowledge from data such that returns are maximized. With emergence of huge datasets the existing classification techniques often fail to produce desirable results. The challenge lies in analyzing and understanding characteristics of massive data sets by retrieving useful geometric and statistical patterns. We propose a supervised parallel fuzzy rough support vector machine (PFRSVM) for data classification in cloud environment. The classification is performed by PFRSVM using hyperbolic tangent kernel. The fuzzy rough set model takes care of sensitiveness of noisy samples and handles impreciseness in training samples bringing robustness to results. The membership function is function of center and radius of each class in feature space and is represented with kernel. It plays an important role towards sampling the decision surface. The success of PFRSVM is governed by choosing appropriate parameter values. The training samples are either linear or nonlinear separable. The different input points make unique contributions to decision surface. The algorithm is parallelized with a view to reduce training times. The system is built on support vector machine library using Hadoop implementation of MapReduce. The algorithm is tested on large data sets to check its feasibility and convergence. The performance of classifier is also assessed in terms of number of support vectors. The challenges encountered towards implementing big data classification in machine learning frameworks are also discussed. The experiments are done on the cloud environment available at University of Technology and Management, India. The results are illustrated for Gaussian RBF and Bayesian kernels. The effect of variability in prediction and generalization of PFRSVM is examined with respect to values of parameter C. It effectively resolves outliers’ effects, imbalance and overlapping class problems, normalizes to unseen data and relaxes dependency between features and labels. The average classification accuracy for PFRSVM is better than other classifiers for both Gaussian RBF and Bayesian kernels. The experimental results on both synthetic and real data sets clearly demonstrate the superiority of the proposed technique.

Keywords: FRSVM, Hadoop, MapReduce, PFRSVM

Procedia PDF Downloads 489

Authors: Oluwafunmibi Omotayo Fasanya, Augustine Kena Adjei

Abstract:

To develop a machine learning model to predict diabetes (DM) prevalence in the U.S. population using demographic characteristics, physical indicators, and lifestyle habits, and to analyze how these factors contribute to the likelihood of diabetes. We analyzed data from 23,546 participants aged 20 and older, who were non-pregnant, from the 2009-2018 National Health and Nutrition Examination Survey (NHANES). The dataset included key demographic (age, sex, ethnicity), physical (BMI, leg length, total cholesterol [TCHOL], fasting plasma glucose), and lifestyle indicators (smoking habits). A weighted sample was used to account for NHANES survey design features such as stratification and clustering. A classification machine learning model was trained to predict diabetes status. The target variable was binary (diabetes or non-diabetes) based on fasting plasma glucose measurements. The following models were evaluated: Logistic Regression (baseline), Random Forest Classifier, Gradient Boosting Machine (GBM), Support Vector Machine (SVM). Model performance was assessed using accuracy, F1-score, AUC-ROC, and precision-recall metrics. Feature importance was analyzed using SHAP values to interpret the contributions of variables such as age, BMI, ethnicity, and smoking status. The Gradient Boosting Machine (GBM) model outperformed other classifiers with an AUC-ROC score of 0.85. Feature importance analysis revealed the following key predictors: Age: The most significant predictor, with diabetes prevalence increasing with age, peaking around the 60s for males and 70s for females. BMI: Higher BMI was strongly associated with a higher risk of diabetes. Ethnicity: Black participants had the highest predicted prevalence of diabetes (14.6%), followed by Mexican-Americans (13.5%) and Whites (10.6%). TCHOL: Diabetics had lower total cholesterol levels, particularly among White participants (mean decline of 23.6 mg/dL). Smoking: Smoking showed a slight increase in diabetes risk among Whites (0.2%) but had a limited effect in other ethnic groups. Using machine learning models, we identified key demographic, physical, and lifestyle predictors of diabetes in the U.S. population. The results confirm that diabetes prevalence varies significantly across age, BMI, and ethnic groups, with lifestyle factors such as smoking contributing differently by ethnicity. These findings provide a basis for more targeted public health interventions and resource allocation for diabetes management.

Keywords: diabetes, NHANES, random forest, gradient boosting machine, support vector machine

Procedia PDF Downloads 4

Authors: Mohsen Bahrami, Banafsheh Nikmehr, Yueqiang Song, Anuradha Koduru, Ayse K. Vuruskan, Hongkun Lu, Tamer M. Yalcinkaya

Abstract:

In recent years, we have witnessed an explosion of studies aimed at using a combination of artificial intelligence (AI) and time-lapse imaging data on embryos to improve IVF outcomes. However, despite promising results, no study has used a matched cohort of transferred embryos which only differ in pregnancy outcome, i.e., embryos from a single clinic which are similar in parameters, such as: morphokinetic condition, patient age, and overall clinic and lab performance. Here, we used time-lapse data on embryos with known pregnancy outcomes to see if the rich spatiotemporal information embedded in this data would allow the prediction of the pregnancy outcome regardless of such critical parameters. Methodology—We did a retrospective analysis of time-lapse data from our IVF clinic utilizing Embryoscope 100% of the time for embryo culture to blastocyst stage with known clinical outcomes, including live birth vs nonpregnant (embryos with spontaneous abortion outcomes were excluded). We used time-lapse data from 200 elective single transfer embryos randomly selected from January 2019 to June 2021. Our sample included 100 embryos in each group with no significant difference in patient age (P=0.9550) and morphokinetic scores (P=0.4032). Data from all patients were combined to make a 4th order tensor, and feature extraction were subsequently carried out by a tensor decomposition methodology. The features were then used in a machine learning classifier to classify the two groups. Major Findings—The performance of the model was evaluated using 100 random subsampling cross validation (train (80%) - test (20%)). The prediction accuracy, averaged across 100 permutations, exceeded 80%. We also did a random grouping analysis, in which labels (live birth, nonpregnant) were randomly assigned to embryos, which yielded 50% accuracy. Conclusion—The high accuracy in the main analysis and the low accuracy in random grouping analysis suggest a consistent spatiotemporal pattern which is associated with pregnancy outcomes, regardless of patient age and embryo morphokinetic condition, and beyond already known parameters, such as: early cleavage or early blastulation. Despite small samples size, this ongoing analysis is the first to show the potential of AI methods in capturing the complex morphokinetic changes embedded in embryo time-lapse data, which contribute to successful pregnancy outcomes, regardless of already known parameters. The results on a larger sample size with complementary analysis on prediction of other key outcomes, such as: euploidy and aneuploidy of embryos will be presented at the meeting.

Keywords: IVF, embryo, machine learning, time-lapse imaging data

Procedia PDF Downloads 91

Authors: T. Thein, S. Kalyar Myo

Abstract:

Human uses visual information for understanding the speech contents in noisy conditions or in situations where the audio signal is not available. The primary advantage of visual information is that it is not affected by the acoustic noise and cross talk among speakers. Using visual information from the lip movements can improve the accuracy and robustness of automatic speech recognition. However, a major challenge with most automatic lip reading system is to find a robust and efficient method for extracting the linguistically relevant speech information from a lip image sequence. This is a difficult task due to variation caused by different speakers, illumination, camera setting and the inherent low luminance and chrominance contrast between lip and non-lip region. Several researchers have been developing methods to overcome these problems; the one is lip reading. Moreover, it is well known that visual information about speech through lip reading is very useful for human speech recognition system. Lip reading is the technique of a comprehensive understanding of underlying speech by processing on the movement of lips. Therefore, lip reading system is one of the different supportive technologies for hearing impaired or elderly people, and it is an active research area. The need for lip reading system is ever increasing for every language. This research aims to develop a visual teaching method system for the hearing impaired persons in Myanmar, how to pronounce words precisely by identifying the features of lip movement. The proposed research will work a lip reading system for Myanmar Consonants, one syllable consonants (င (Nga)၊ ည (Nya)၊ မ (Ma)၊ လ (La)၊ ၀ (Wa)၊ သ (Tha)၊ ဟ (Ha)၊ အ (Ah) ) and two syllable consonants ( က(Ka Gyi)၊ ခ (Kha Gway)၊ ဂ (Ga Nge)၊ ဃ (Ga Gyi)၊ စ (Sa Lone)၊ ဆ (Sa Lain)၊ ဇ (Za Gwe) ၊ ဒ (Da Dway)၊ ဏ (Na Gyi)၊ န (Na Nge)၊ ပ (Pa Saug)၊ ဘ (Ba Gone)၊ ရ (Ya Gaug)၊ ဠ (La Gyi) ). In the proposed system, there are three subsystems, the first one is the lip localization system, which localizes the lips in the digital inputs. The next one is the feature extraction system, which extracts features of lip movement suitable for visual speech recognition. And the final one is the classification system. In the proposed research, Two Dimensional Discrete Cosine Transform (2D-DCT) and Linear Discriminant Analysis (LDA) with Active Contour Model (ACM) will be used for lip movement features extraction. Support Vector Machine (SVM) classifier is used for finding class parameter and class number in training set and testing set. Then, experiments will be carried out for the recognition accuracy of Myanmar consonants using the only visual information on lip movements which are useful for visual speech of Myanmar languages. The result will show the effectiveness of the lip movement recognition for Myanmar Consonants. This system will help the hearing impaired persons to use as the language learning application. This system can also be useful for normal hearing persons in noisy environments or conditions where they can find out what was said by other people without hearing voice.

Keywords: feature extraction, lip reading, lip localization, Active Contour Model (ACM), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Two Dimensional Discrete Cosine Transform (2D-DCT)

Procedia PDF Downloads 282

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 129

Authors: Sofia Papadimitriou

Abstract:

INTRODUCTION: The differential diagnosis between acute viral and bacterial infections is an important cost-effectiveness parameter at the stage of the treatment process in order to achieve the maximum benefits in therapeutic intervention by combining the minimum cost to ensure the proper use of antibiotics.The discovery of sensitive and robust molecular diagnostic tests in response to the role of the host in infections has enhanced the accurate diagnosis and differentiation of infections. METHOD: The study used a sample of six independent blood samples (total=756) which are associated with human proteins-proteins, each of which at the transcription stage expresses a different response in the host network between viral and bacterial infections.Τhe individual blood samples are subjected to a sequence of computer filters that identify a gene panel corresponding to an autonomous diagnostic score. The data set and the correspondence of the gene panel to the diagnostic patents a new Bangalore -Viral Bacterial (BL-VB). FINDING: We use a biomarker based on the blood of 10 genes(Panel-VB) that are an important prognostic value for the detection of viruses from bacterial infections with a weighted average AUROC of 0.97(95% CL:0.96-0.99) in eleven independent samples (sets n=898). We discovered a base with a patient score (VB 10 ) according to the table, which is a significant diagnostic value with a weighted average of AUROC 0.94(95% CL: 0.91-0.98) in 2996 patient samples from 56 public sets of data from 19 different countries. We also studied VB 10 in a new cohort of South India (BL-VB,n=56) and found 97% accuracy in confirmed cases of viral and bacterial infections. We found that VB 10 (a)accurately identifies the type of infection even in unspecified cases negative to the culture (b) shows its clinical condition recovery and (c) applies to all age groups, covering a wide range of acute bacterial and viral infectious, including non-specific pathogens. We applied our VB 10 rating to publicly available COVID 19 data and found that our rating diagnosed viral infection in patient samples. RESULTS: Τhe results of the study showed the diagnostic power of the biomarker VB 10 as a diagnostic test for the accurate diagnosis of acute infections in recovery conditions. We look forward to helping you make clinical decisions about prescribing antibiotics and integrating them into your policies management of antibiotic stewardship efforts. CONCLUSIONS: Overall, we are developing a new property of the RNA-based biomarker and a new blood test to differentiate between viral and bacterial infections to assist a physician in designing the optimal treatment regimen to contribute to the proper use of antibiotics and reduce the burden on antimicrobial resistance, AMR.

Keywords: acute infections, antimicrobial resistance, biomarker, blood transcriptome, systems biology, classifier diagnostic score

Procedia PDF Downloads 155

Authors: Sandra Smieszek, Jonathan Haines

Abstract:

Introduction: Numerous research efforts have focused on searching for ‘longevity genes’. However, attempting to decipher the genetic component of the longevous phenotype have resulted in limited success and the mechanisms governing longevity remain to be explained. We conducted a genome-wide homozygosity analysis (GWHA) of the founder population of the Amish community in central Ohio. While genome-wide association studies using unrelated individuals have revealed many interesting longevity associated variants, these variants are typically of small effect and cannot explain the observed patterns of heritability for this complex trait. The Amish provide a large cohort of extended kinships allowing for in depth analysis via family-based approach excellent population due to its. Heritability of longevity increases with age with significant genetic contribution being seen in individuals living beyond 60 years of age. In our present analysis we show that the heritability of longevity is estimated to be increasing with age particularly on the paternal side. Methods: The present analysis integrated both phenotypic and genotypic data and led to the discovery of a series of variants, distinct for stratified populations across ages and distinct for paternal and maternal cohorts. Specifically 5437 subjects were analyzed and a subset of 893 successfully genotyped individuals was used to assess CHIP heritability. We have conducted the homozygosity analysis to examine if homozygosity is associated with increased risk of living beyond 90. We analyzed AMISH cohort genotyped for 614,957 SNPs. Results: We delineated 10 significant regions of homozygosity (ROH) specific for the age group of interest (>90). Of particular interest was ROH on chromosome 13, P < 0.0001. The lead SNPs rs7318486 and rs9645914 point to COL4A2 and our lead SNP. COL25A1 encodes one of the six subunits of type IV collagen, the C-terminal portion of the protein, known as canstatin, is an inhibitor of angiogenesis and tumor growth. COL4A2 mutations have been reported with a broader spectrum of cerebrovascular, renal, ophthalmological, cardiac, and muscular abnormalities. The second region of interest points to IRS2. Furthermore we built a classifier using the obtained SNPs from the significant ROH region with 0.945 AUC giving ability to discriminate between those living beyond to 90 years of age and beyond. Conclusion: In conclusion our results suggest that a history of longevity does indeed contribute to increasing the odds of individual longevity. Preliminary results are consistent with conjecture that heritability of longevity is substantial when we start looking at oldest fifth and smaller percentiles of survival specifically in males. We will validate all the candidate variants in independent cohorts of centenarians, to test whether they are robustly associated with human longevity. The identified regions of interest via ROH analysis could be of profound importance for the understanding of genetic underpinnings of longevity.

Keywords: regions of homozygosity, longevity, SNP, Amish

Procedia PDF Downloads 232

Authors: Ran Goldblatt, Nicholas Jones, Jennifer Mannix, Brad Bottoms

Abstract:

Accurate, complete, and up-to-date geospatial information is the foundation of successful disaster management. When the 2010 Haiti Earthquake struck, accurate and timely information on the distribution of critical infrastructure was essential for the disaster response community for effective search and rescue operations. Existing geospatial datasets such as Google Maps did not have comprehensive coverage of these features. In the days following the earthquake, many organizations released high-resolution satellite imagery, catalyzing a worldwide effort to map Haiti and support the recovery operations. Of these organizations, OpenStreetMap (OSM), a collaborative project to create a free editable map of the world, used the imagery to support volunteers to digitize roads, buildings, and other features, creating the most detailed map of Haiti in existence in just a few weeks. However, large portions of the island are still not fully covered by OSM. There is an increasing need for a tool to automatically identify which areas in Haiti, as well as in other countries vulnerable to disasters, that are not fully mapped. The objective of this project is to leverage different types of remote sensing measurements, together with machine learning approaches, in order to identify geographical areas where OSM coverage of building footprints is incomplete. Several remote sensing measures and derived products were assessed as potential predictors of OSM building footprints coverage, including: intensity of light emitted at night (based on VIIRS measurements), spectral indices derived from Sentinel-2 satellite (normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), soil-adjusted vegetation index (SAVI), urban index (UI)), surface texture (based on Sentinel-1 SAR measurements)), elevation and slope. Additional remote sensing derived products, such as Hansen Global Forest Change, DLR`s Global Urban Footprint (GUF), and World Settlement Footprint (WSF), were also evaluated as predictors, as well as OSM street and road network (including junctions). Using a supervised classification with a random forest classifier resulted in the prediction of 89% of the variation of OSM building footprint area in a given cell. These predictions allowed for the identification of cells that are predicted to be covered but are actually not mapped yet. With these results, this methodology could be adapted to any location to assist with preparing for future disastrous events and assure that essential geospatial information is available to support the response and recovery efforts during and following major disasters.

Keywords: disaster management, Haiti, machine learning, OpenStreetMap, remote sensing

Procedia PDF Downloads 122

Authors: Soyon Kim, Edward Kim

Abstract:

In order to retrieve information from the massive stream of songs in the music industry, music search by title, lyrics, artist, mood, and genre has become more important. Despite the subjectivity and controversy over the definition of music genres across different nations and cultures, automatic genre classification systems that facilitate the process of music categorization have been developed. Manual genre selection by music producers is being provided as statistical data for designing automatic genre classification systems. In this paper, an automatic music genre classification system utilizing non-negative matrix factorization (NMF) is proposed. Short-term characteristics of the music signal can be captured based on the timbre features such as mel-frequency cepstral coefficient (MFCC), decorrelated filter bank (DFB), octave-based spectral contrast (OSC), and octave band sum (OBS). Long-term time-varying characteristics of the music signal can be summarized with (1) the statistical features such as mean, variance, minimum, and maximum of the timbre features and (2) the modulation spectrum features such as spectral flatness measure, spectral crest measure, spectral peak, spectral valley, and spectral contrast of the timbre features. Not only these conventional basic long-term feature vectors, but also NMF based feature vectors are proposed to be used together for genre classification. In the training stage, NMF basis vectors were extracted for each genre class. The NMF features were calculated in the log spectral magnitude domain (NMF-LSM) as well as in the basic feature vector domain (NMF-BFV). For NMF-LSM, an entire full band spectrum was used. However, for NMF-BFV, only low band spectrum was used since high frequency modulation spectrum of the basic feature vectors did not contain important information for genre classification. In the test stage, using the set of pre-trained NMF basis vectors, the genre classification system extracted the NMF weighting values of each genre as the NMF feature vectors. A support vector machine (SVM) was used as a classifier. The GTZAN multi-genre music database was used for training and testing. It is composed of 10 genres and 100 songs for each genre. To increase the reliability of the experiments, 10-fold cross validation was used. For a given input song, an extracted NMF-LSM feature vector was composed of 10 weighting values that corresponded to the classification probabilities for 10 genres. An NMF-BFV feature vector also had a dimensionality of 10. Combined with the basic long-term features such as statistical features and modulation spectrum features, the NMF features provided the increased accuracy with a slight increase in feature dimensionality. The conventional basic features by themselves yielded 84.0% accuracy, but the basic features with NMF-LSM and NMF-BFV provided 85.1% and 84.2% accuracy, respectively. The basic features required dimensionality of 460, but NMF-LSM and NMF-BFV required dimensionalities of 10 and 10, respectively. Combining the basic features, NMF-LSM and NMF-BFV together with the SVM with a radial basis function (RBF) kernel produced the significantly higher classification accuracy of 88.3% with a feature dimensionality of 480.

Keywords: mel-frequency cepstral coefficient (MFCC), music genre classification, non-negative matrix factorization (NMF), support vector machine (SVM)

Procedia PDF Downloads 301

Authors: Akbar Gharbali, Ali Abbasian Ardekani, Afshin Mohammadi

Abstract:

Introduction: Thyroid nodules have an incidence of 33-68% in the general population. More than 5-15% of these nodules are malignant. Early detection and treatment of thyroid nodules increase the cure rate and provide optimal treatment. Between the medical imaging methods, Ultrasound is the chosen imaging technique for assessment of thyroid nodules. The confirming of the diagnosis usually demands repeated fine-needle aspiration biopsy (FNAB). So, current management has morbidity and non-zero mortality. Objective: To explore diagnostic potential of automatic texture analysis (TA) methods in differentiation benign and malignant thyroid nodules by ultrasound imaging in order to help for reliable diagnosis and monitoring of the thyroid nodules in their early stages with no need biopsy. Material and Methods: The thyroid US image database consists of 70 patients (26 benign and 44 malignant) which were reported by Radiologist and proven by the biopsy. Two slices per patient were loaded in Mazda Software version 4.6 for automatic texture analysis. Regions of interests (ROIs) were defined within the abnormal part of the thyroid nodules ultrasound images. Gray levels within an ROI normalized according to three normalization schemes: N1: default or original gray levels, N2: +/- 3 Sigma or dynamic intensity limited to µ+/- 3σ, and N3: present intensity limited to 1% - 99%. Up to 270 multiscale texture features parameters per ROIs per each normalization schemes were computed from well-known statistical methods employed in Mazda software. From the statistical point of view, all calculated texture features parameters are not useful for texture analysis. So, the features based on maximum Fisher coefficient and the minimum probability of classification error and average correlation coefficients (POE+ACC) eliminated to 10 best and most effective features per normalization schemes. We analyze this feature under two standardization states (standard (S) and non-standard (NS)) with Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Non-Linear Discriminant Analysis (NDA). The 1NN classifier was performed to distinguish between benign and malignant tumors. The confusion matrix and Receiver operating characteristic (ROC) curve analysis were used for the formulation of more reliable criteria of the performance of employed texture analysis methods. Results: The results demonstrated the influence of the normalization schemes and reduction methods on the effectiveness of the obtained features as a descriptor on discrimination power and classification results. The selected subset features under 1%-99% normalization, POE+ACC reduction and NDA texture analysis yielded a high discrimination performance with the area under the ROC curve (Az) of 0.9722, in distinguishing Benign from Malignant Thyroid Nodules which correspond to sensitivity of 94.45%, specificity of 100%, and accuracy of 97.14%. Conclusions: Our results indicate computer-aided diagnosis is a reliable method, and can provide useful information to help radiologists in the detection and classification of benign and malignant thyroid nodules.

Keywords: ultrasound imaging, thyroid nodules, computer aided diagnosis, texture analysis, PCA, LDA, NDA

Procedia PDF Downloads 277

Authors: Jie Lin, Yiwen Pan, Li Zhang, Zhangyong Xia

Abstract:

Atherosclerosis is a chronic inflammatory disease characterized by the accumulation of lipids, immune cells, and extracellular matrix in the arterial walls. This pathological process can lead to the formation of plaques that can obstruct blood flow and trigger various cardiovascular diseases such as heart attack and stroke. The underlying molecular mechanisms still remain unclear, although many studies revealed the dysfunction of endothelial cells, recruitment and activation of monocytes and macrophages, and the production of pro-inflammatory cytokines and chemokines in atherosclerosis. This study aimed to identify hub genes involved in the progression of atherosclerosis and to analyze their biological function in silico, thereby enhancing our understanding of the disease’s molecular mechanisms. Through the analysis of microarray data, we examined the gene expression in media and neo-intima from plaques, as well as distant macroscopically intact tissue, across a cohort of 32 hypertensive patients. Initially, 112 differentially expressed genes (DEGs) were identified. Subsequent immune infiltration analysis indicated a predominant presence of 27 immune cell types in the atherosclerosis group, particularly noting an increase in monocytes and macrophages. In the Weighted gene co-expression network analysis (WGCNA), 10 modules with a minimum of 30 genes were defined as key modules, with blue, dark, Oliver green and sky-blue modules being the most significant. These modules corresponded respectively to monocyte, activated B cell, and activated CD4 T cell gene patterns, revealing a strong morphological-genetic correlation. From these three gene patterns (modules morphology), a total of 2509 key genes (Gene Significance >0.2, module membership>0.8) were extracted. Six hub genes (CD36, DPP4, HMOX1, PLA2G7, PLN2, and ACADL) were then identified by intersecting 2509 key genes, 102 DEGs with lipid-related genes from the Genecard database. The bio-functional analysis of six hub genes was estimated by a robust classifier with an area under the curve (AUC) of 0.873 in the ROC plot, indicating excellent efficacy in differentiating between the disease and control group. Moreover, PCA visualization demonstrated clear separation between the groups based on these six hub genes, suggesting their potential utility as classification features in predictive models. Protein-protein interaction (PPI) analysis highlighted DPP4 as the most interconnected gene. Within the constructed key gene-drug network, 462 drugs were predicted, with ursodeoxycholic acid (UDCA) being identified as a potential therapeutic agent for modulating DPP4 expression. In summary, our study identified critical hub genes implicated in the progression of atherosclerosis through comprehensive bioinformatic analyses. These findings not only advance our understanding of the disease but also pave the way for applying similar analytical frameworks and predictive models to other diseases, thereby broadening the potential for clinical applications and therapeutic discoveries.

Keywords: atherosclerosis, hub genes, drug prediction, bioinformatics

Procedia PDF Downloads 65

Authors: Safaa M. Hassan; Safwat S. Gabr, Mohamed F. Sadek

Abstract:

This study is proposed for the lithological and iron oxides detection in the old mine areas of El-Bahariya Depression, Western Desert, using ASTER and Landsat-8 remote sensing data. Four old iron ore occurrences, namely; El-Gedida, El-Haraa, Ghurabi, and Nasir mine areas found in the El-Bahariya area. This study aims to find new high potential areas for iron mineralization around El-Baharyia depression. Image processing methods such as principle component analysis (PCA) and band ratios (b4/b5, b5/b6, b6/b7, and 4/2, 6/7, band 6) images were used for lithological identification/mapping that includes the iron content in the investigated area. ASTER and Landsat-8 visible and short-wave infrared data found to help mapping the ferruginous sandstones, iron oxides as well as the clay minerals in and around the old mines area of El-Bahariya depression. Landsat-8 band ratio and the principle component of this study showed well distribution of the lithological units, especially ferruginous sandstones and iron zones (hematite and limonite) along with detection of probable high potential areas for iron mineralization which can be used in the future and proved the ability of Landsat-8 and ASTER data in mapping these features. Minimum Noise Fraction (MNF), Mixture Tuned Matched Filtering (MTMF), pixel purity index methods as well as Spectral Ange Mapper classifier algorithm have been successfully discriminated the hematite and limonite content within the iron zones in the study area. Various ASTER image spectra and ASD field spectra of hematite and limonite and the surrounding rocks are compared and found to be consistent in terms of the presence of absorption features at range from 1.95 to 2.3 μm for hematite and limonite. Pixel purity index algorithm and two sub-pixel spectral methods, namely Mixture Tuned Matched Filtering (MTMF) and matched filtering (MF) methods, are applied to ASTER bands to delineate iron oxides (hematite and limonite) rich zones within the rock units. The results are validated in the field by comparing image spectra of spectrally anomalous zone with the USGS resampled laboratory spectra of hematite and limonite samples using ASD measurements. A number of iron oxides rich zones in addition to the main surface exposures of the El-Gadidah Mine, are confirmed in the field. The proposed method is a successful application of spectral mapping of iron oxides deposits in the exposed rock units (i.e., ferruginous sandstone) and present approach of both ASTER and ASD hyperspectral data processing can be used to delineate iron-rich zones occurring within similar geological provinces in any parts of the world.

Keywords: Landsat-8, ASTER, lithological mapping, iron exploration, western desert

Procedia PDF Downloads 142

Authors: Vivek Mahadev, Manoj Kumar, Neelu Mathur, Brahm Dutt Pandey

Abstract:

Perimeter guarding and protection of critical installations require prompt intrusion detection and assessment to take effective countermeasures. Currently, visual and electronic surveillance are the primary methods used for perimeter guarding. These methods can be costly and complicated, requiring careful planning according to the location and terrain. Moreover, these methods often struggle to detect stealthy and camouflaged insurgents. The object of the present work is to devise a surveillance technique using seismic sensors that overcomes the limitations of existing systems. The aim is to improve intrusion detection, assessment, and characterization by utilizing seismic sensors. Most of the similar systems have only two types of intrusion detection capability viz., human or vehicle. In our work we could even categorize further to identify types of intrusion activity such as walking, running, group walking, fence jumping, tunnel digging and vehicular movements. A virtual fence of 60 meters at GCNEP, Bahadurgarh, Haryana, India, was created by installing four underground geophones at a distance of 15 meters each. The signals received from these geophones are then processed to find unique seismic signatures called features. Various feature optimization and selection methodologies, such as LightGBM, Boruta, Random Forest, Logistics, Recursive Feature Elimination, Chi-2 and Pearson Ratio were used to identify the best features for training the machine learning models. The trained models were developed using algorithms such as supervised support vector machine (SVM) classifier, kNN, Decision Tree, Logistic Regression, Naïve Bayes, and Artificial Neural Networks. These models were then used to predict the category of events, employing weighted ensemble voting to analyze and combine their results. The models were trained with 1940 training events and results were evaluated with 831 test events. It was observed that using the weighted ensemble voting increased the efficiency of predictions. In this study we successfully developed and deployed the virtual fence using geophones. Since these sensors are passive, do not radiate any energy and are installed underground, it is impossible for intruders to locate and nullify them. Their flexibility, quick and easy installation, low costs, hidden deployment and unattended surveillance make such systems especially suitable for critical installations and remote facilities with difficult terrain. This work demonstrates the potential of utilizing seismic sensors for creating better perimeter guarding and protection systems using multiple machine learning models in weighted ensemble voting. In this study the virtual fence achieved an intruder detection efficiency of over 97%.

Keywords: geophone, seismic perimeter surveillance, machine learning, weighted ensemble method

Procedia PDF Downloads 78

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: Kenneth A. Rostowsky, Alexander S. Maher, Nahian F. Chowdhury, Andrei Irimia

Abstract:

The clinical significance of cerebral microbleeds (CMBs) due to mild traumatic brain injury (mTBI) remains unclear. Here we use magnetic resonance imaging (MRI), diffusion tensor imaging (DTI) and connectomic analysis to investigate the statistical association between mTBI-related CMBs, post-TBI changes to the human connectome and neurological/cognitive deficits. This study was undertaken in agreement with US federal law (45 CFR 46) and was approved by the Institutional Review Board (IRB) of the University of Southern California (USC). Two groups, one consisting of 26 (13 females) mTBI victims and another comprising 26 (13 females) healthy control (HC) volunteers were recruited through IRB-approved procedures. The acute Glasgow Coma Scale (GCS) score was available for each mTBI victim (mean µ = 13.2; standard deviation σ = 0.4). Each HC volunteer was assigned a GCS of 15 to indicate the absence of head trauma at the time of enrollment in our study. Volunteers in the HC and mTBI groups were matched according to their sex and age (HC: µ = 67.2 years, σ = 5.62 years; mTBI: µ = 66.8 years, σ = 5.93 years). MRI [including T1- and T2-weighted volumes, gradient recalled echo (GRE)/susceptibility weighted imaging (SWI)] and gradient echo (GE) DWI volumes were acquired using the same MRI scanner type (Trio TIM, Siemens Corp.). Skull-stripping and eddy current correction were implemented. DWI volumes were processed in TrackVis (http://trackvis.org) and 3D Slicer (http://www.slicer.org). Tensors were fit to DWI data to perform DTI, and tractography streamlines were then reconstructed using deterministic tractography. A voxel classifier was used to identify image features as CMB candidates using Microbleed Anatomic Rating Scale (MARS) guidelines. For each peri-lesional DTI streamline bundle, the null hypothesis was formulated as the statement that there was no neurological or cognitive deficit associated with between-scan differences in the mean FA of DTI streamlines within each bundle. The statistical significance of each hypothesis test was calculated at the α = 0.05 level, subject to the family-wise error rate (FWER) correction for multiple comparisons. Results: In HC volunteers, the along-track analysis failed to identify statistically significant differences in the mean FA of DTI streamline bundles. In the mTBI group, significant differences in the mean FA of peri-lesional streamline bundles were found in 21 out of 26 volunteers. In those volunteers where significant differences had been found, these differences were associated with an average of ~47% of all identified CMBs (σ = 21%). In 12 out of the 21 volunteers exhibiting significant FA changes, cognitive functions (memory acquisition and retrieval, top-down control of attention, planning, judgment, cognitive aspects of decision-making) were found to have deteriorated over the six months following injury (r = -0.32, p < 0.001). Our preliminary results suggest that acute post-TBI CMBs may be associated with cognitive decline in some mTBI patients. Future research should attempt to identify mTBI patients at high risk for cognitive sequelae.

Keywords: traumatic brain injury, magnetic resonance imaging, diffusion tensor imaging, connectomics

Procedia PDF Downloads 169