Search results for: STS benchmark dataset

Authors: Shriya Shukla, Lachin Fernando

Abstract:

Pneumonia, a leading cause of mortality in young children globally, presents significant diagnostic challenges, particularly in resource-limited settings. This study presents an approach to diagnosing pediatric pneumonia using Chest X-Ray (CXR) images, employing a lightweight MobileNetV2 model enhanced with synthetic data augmentation. Addressing the challenge of dataset scarcity and imbalance, the study used a Variational Autoencoder-Generative Adversarial Network (VAE-GAN) to generate synthetic CXR images, improving the representation of normal cases in the pediatric dataset. This approach not only addresses the issues of data imbalance and scarcity prevalent in medical imaging but also provides a more accessible and reliable diagnostic tool for early pneumonia detection. The augmented data improved the model’s accuracy and generalization, achieving an overall accuracy of 95% in pneumonia detection. These findings highlight the efficacy of the MobileNetV2 model, offering a computationally efficient yet robust solution well-suited for resource-constrained environments such as mobile health applications. This study demonstrates the potential of synthetic data augmentation in enhancing medical image analysis for critical conditions like pediatric pneumonia.

Keywords: pneumonia, MobileNetV2, image classification, GAN, VAE, deep learning

Procedia PDF Downloads 55

Authors: R. N. Begum, Ambalika Sharma, G. K. Singh

Abstract:

Identity theft has serious ramifications beyond data and personal information loss. This necessitates the implementation of robust and efficient user identification systems. Therefore, automatic biometric recognition systems are the need of the hour, and ECG-based systems are unquestionably the best choice due to their appealing inherent characteristics. The CNNs are the recent state-of-the-art techniques for ECG-based user identification systems. However, the results obtained are significantly below standards, and the situation worsens as the number of users and types of heartbeats in the dataset grows. As a result, this study proposes a highly accurate and resilient ECG-based person identification system using CNN's dense learning framework. The proposed research explores explicitly the calibre of dense CNNs in the field of ECG-based human recognition. The study tests four different configurations of dense CNN which are trained on a dataset of recordings collected from eight popular ECG databases. With the highest FAR of 0.04 percent and the highest FRR of 5%, the best performing network achieved an identification accuracy of 99.94 percent. The best network is also tested with various train/test split ratios. The findings show that DenseNets are not only extremely reliable but also highly efficient. Thus, they might also be implemented in real-time ECG-based human recognition systems.

Keywords: Biometrics, Dense Networks, Identification Rate, Train/Test split ratio

Procedia PDF Downloads 145

Authors: Md Rafiqul Islam, Ashir Ahmed, Anwaar Ulhaq, Abu Raihan M. Kamal, Yuan Miao, Hua Wang

Abstract:

Mental health of people is equally important as of their physical health. Mental health and well-being are influenced not only by individual attributes but also by the social circumstances in which people find themselves and the environment in which they live. Like physical health, there is a number of internal and external factors such as biological, social and occupational factors that could influence the mental health of people. People living in poverty, suffering from chronic health conditions, minority groups, and those who exposed to/or displaced by war or conflict are generally more likely to develop mental health conditions. However, to authors’ best knowledge, there is dearth of knowledge on the impact of workplace (especially the highly stressed IT/Tech workplace) on the mental health of its workers. This study attempts to examine the factors influencing the mental health of tech workers. A publicly available dataset containing more than 65,000 cells and 100 attributes is examined for this purpose. Number of machine learning techniques such as ‘Decision Tree’, ‘K nearest neighbor’ ‘Support Vector Machine’ and ‘Ensemble’, are then applied to the selected dataset to draw the findings. It is anticipated that the analysis reported in this study would contribute in presenting useful insights on the attributes contributing in the mental health of tech workers using relevant machine learning techniques.

Keywords: mental disorder, diagnosis, occupational stress, IT workplace

Procedia PDF Downloads 273

Authors: Aditya Karade, Sharada Falane, Dhananjay Deshmukh, Vijaykumar Mantri

Abstract:

Brain tumors pose a significant challenge in healthcare due to their complex nature and impact on patient outcomes. The application of deep learning (DL) algorithms in medical imaging have shown promise in accurate and efficient brain tumour detection. This paper explores the performance of various pre-trained DL models ResNet50, Xception, InceptionV3, EfficientNetB0, DenseNet121, NASNetMobile, VGG19, VGG16, and MobileNet on a brain tumour dataset sourced from Figshare. The dataset consists of MRI scans categorizing different types of brain tumours, including meningioma, pituitary, glioma, and no tumour. The study involves a comprehensive evaluation of these models’ accuracy and effectiveness in classifying brain tumour images. Data preprocessing, augmentation, and finetuning techniques are employed to optimize model performance. Among the evaluated deep learning models for brain tumour detection, ResNet50 emerges as the top performer with an accuracy of 98.86%. Following closely is Xception, exhibiting a strong accuracy of 97.33%. These models showcase robust capabilities in accurately classifying brain tumour images. On the other end of the spectrum, VGG16 trails with the lowest accuracy at 89.02%.

Keywords: brain tumour, MRI image, detecting and classifying tumour, pre-trained models, transfer learning, image segmentation, data augmentation

Procedia PDF Downloads 50

Authors: Manasvi Pinnaka, Brianna Chrisman

Abstract:

Cystic fibrosis patients often develop lung infections that range anywhere in severity from mild to life-threatening due to the presence of thick and sticky mucus that fills their airways. Since many of these infections are chronic, they not only affect a patient’s ability to breathe but also increase the chances of mortality by respiratory failure. With a publicly available dataset of DNA sequences from bacterial species in the lung microbiome of cystic fibrosis patients, the correlations between different microbial species in the lung and the extent of deterioration of lung function were investigated. 16S sequencing technologies were used to determine the microbiome composition of the samples in the dataset. For the statistical analyses, referencing helped distinguish between taxonomies, and the proportions of certain taxa relative to another were determined. It was found that the Fusobacterium, Actinomyces, and Leptotrichia microbial types all had a positive correlation with the FEV1 score, indicating the potential displacement of these species by pathogens as the disease progresses. However, the dominant pathogens themselves, including Pseudomonas aeruginosa and Staphylococcus aureus, did not have statistically significant negative correlations with the FEV1 score as described by past literature. Examining the lung microbiology of cystic fibrosis patients can help with the prediction of the current condition of lung function, with the potential to guide doctors when designing personalized treatment plans for patients.

Keywords: bacterial infections, cystic fibrosis, lung microbiome, 16S sequencing

Procedia PDF Downloads 78

Authors: Mohammadreza Sedighi, Mohammad Said Saidi, Hesamoddin Salarian

Abstract:

A numerical study has been performed to investigate the effect of using different turbulent models on natural convection flow field and temperature distributions in partially heated square cavity compare to benchmark. The temperature of the right vertical wall is lower than that of heater while other walls are insulated. The commercial CFD codes are used to model. Standard k-w model provided good agreement with the experimental data.

Keywords: Buoyancy, Cavity, CFD, Heat Transfer, Natural Convection, Turbulence

Procedia PDF Downloads 323

Authors: Emily Kambalame

Abstract:

Water distribution networks necessitate many investments for construction, prompting researchers to seek cost reduction and efficient design solutions. Optimization techniques are employed in this regard to address these challenges. In this context, the penalty-free multi-objective evolutionary algorithm (PFMOEA) coupled with pressure-dependent analysis (PDA) was utilized to develop a multi-objective evolutionary search for the optimization of water distribution systems (WDSs). The aim of this research was to find out if the computational efficiency of the PFMOEA for WDS optimization could be enhanced. This was done by applying real coding representation and retaining different percentages of feasible and infeasible solutions close to the Pareto front in the elitism step of the optimization. Two benchmark network problems, namely the Two-looped and Hanoi networks, were utilized in the study. A comparative analysis was then conducted to assess the performance of the real-coded PFMOEA in relation to other approaches described in the literature. The algorithm demonstrated competitive performance for the two benchmark networks by implementing real coding. The real-coded PFMOEA achieved the novel best-known solutions ($419,000 and $6.081 million) and a zero-pressure deficit for the two networks, requiring fewer function evaluations than the binary-coded PFMOEA. In previous PFMOEA studies, elitism applied a default retention of 30% of the least cost-feasible solutions while excluding all infeasible solutions. It was found in this study that by replacing 10% and 15% of the feasible solutions with infeasible ones that are close to the Pareto front with minimal pressure deficit violations, the computational efficiency of the PFMOEA was significantly enhanced. The configuration of 15% feasible and 15% infeasible solutions outperformed other retention allocations by identifying the optimal solution with the fewest function evaluation

Keywords: design optimization, multi-objective evolutionary, penalty-free, water distribution systems

Procedia PDF Downloads 35

Authors: Ma. Gracia Corazon Cayanan, Kai Yuen Cheong, Li Sha

Abstract:

Training a language model for a minority language has been a challenging task. The lack of available corpora to train and fine-tune state-of-the-art language models is still a challenge in the area of Natural Language Processing (NLP). Moreover, the need for high computational resources and bulk data limit the attainment of this task. In this paper, we presented the following contributions: (1) we introduce and used a translation pair set of Tagalog and English (TL-EN) in pre-training a language model to a minority language resource; (2) we fine-tuned and evaluated top-ranking and pre-trained semantic textual similarity binary task (STSB) models, to both TL-EN and STS dataset pairs. (3) then, we reduced the size of the model to offset the need for high computational resources. Based on our results, the models that were pre-trained to translation pairs and STS pairs can perform well for STSB task. Also, having it reduced to a smaller dimension has no negative effect on the performance but rather has a notable increase on the similarity scores. Moreover, models that were pre-trained to a similar dataset have a tremendous effect on the model’s performance scores.

Keywords: semantic matching, semantic textual similarity binary task, low resource minority language, fine-tuning, dimension reduction, transformer models

Procedia PDF Downloads 184

Authors: Cuneyt Yucelbas, Seral Ozsen, Sule Yucelbas, Gulay Tezel

Abstract:

Due to the fact that there exist only a small number of complex systems in artificial immune system (AIS) that work out nonlinear problems, nonlinear AIS approaches, among the well-known solution techniques, need to be developed. Gaussian function is usually used as similarity estimation in classification problems and pattern recognition. In this study, diagnosis of breast cancer, the second type of the most widespread cancer in women, was performed with different distance calculation functions that euclidean, gaussian and gaussian-euclidean hybrid function in the clonal selection model of classical AIS on Wisconsin Breast Cancer Dataset (WBCD), which was taken from the University of California, Irvine Machine-Learning Repository. We used 3-fold cross validation method to train and test the dataset. According to the results, the maximum test classification accuracy was reported as 97.35% by using of gaussian-euclidean hybrid function for fold-3. Also, mean of test classification accuracies for all of functions were obtained as 94.78%, 94.45% and 95.31% with use of euclidean, gaussian and gaussian-euclidean, respectively. With these results, gaussian-euclidean hybrid function seems to be a potential distance calculation method, and it may be considered as an alternative distance calculation method for hard nonlinear classification problems.

Keywords: artificial immune system, breast cancer diagnosis, Euclidean function, Gaussian function

Procedia PDF Downloads 420

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 248

Authors: O. Abiodun Adeyinka, B. Adeyemo Adesesan

Abstract:

The forensic use of handwriting depends on the analysis, comparison, and evaluation decisions made by forensic document examiners. When using biometric technology in forensic applications, it is necessary to compute Likelihood Ratio (LR) for quantifying strength of evidence under two competing hypotheses, namely the prosecution and the defense hypotheses wherein a set of assumptions and methods for a given data set will be made. It is therefore important to know how repeatable and reproducible our estimated LR is. This paper evaluated the accuracy and reproducibility of examiners' decisions. Confidence interval for the estimated LR were presented so as not get an incorrect estimate that will be used to deliver wrong judgment in the court of Law. The estimate of LR is fundamentally a Bayesian concept and we used two LR estimators, namely Logistic Regression (LoR) and Kernel Density Estimator (KDE) for this paper. The repeatability evaluation was carried out by retesting the initial experiment after an interval of six months to observe whether examiners would repeat their decisions for the estimated LR. The experimental results, which are based on handwriting dataset, show that LR has different confidence intervals which therefore implies that LR cannot be estimated with the same certainty everywhere. Though the LoR performed better than the KDE when tested using the same dataset, the two LR estimators investigated showed a consistent region in which LR value can be estimated confidently. These two findings advance our understanding of LR when used in computing the strength of evidence in handwriting using forensics.

Keywords: confidence interval, handwriting, kernel density estimator, KDE, logistic regression LoR, repeatability, reproducibility

Procedia PDF Downloads 104

Authors: Iris Vural Gursel, Andrea Ramirez

Abstract:

Effective utilization of lignin is an important mean for developing economically profitable biorefineries. Current literature suggests that large amounts of lignin will become available in second generation biorefineries. New conversion technologies will, therefore, be needed to carry lignin transformation well beyond combustion to produce energy, but towards high-value products such as chemicals and transportation fuels. In recent years, significant progress on catalysis has been made to improve transformation of lignin, and new catalytic processes are emerging. In this work, a techno-economic assessment of two of these novel conversion routes and comparison with more established lignin pyrolysis route were made. The aim is to provide insights into the potential performance and potential hotspots in order to guide the experimental research and ease the commercialization by early identifying cost drivers, strengths, and challenges. The lignin conversion routes selected for detailed assessment were: (non-catalytic) lignin pyrolysis as the benchmark, direct hydrodeoxygenation (HDO) of lignin and hydrothermal lignin depolymerisation. Products generated were mixed oxygenated aromatic monomers (MOAMON), light organics, heavy organics, and char. For the technical assessment, a basis design followed by process modelling in Aspen was done using experimental yields. A design capacity of 200 kt/year lignin feed was chosen that is equivalent to a 1 Mt/y scale lignocellulosic biorefinery. The downstream equipment was modelled to achieve the separation of the product streams defined. For determining external utility requirement, heat integration was considered and when possible gasses were combusted to cover heating demand. The models made were used in generating necessary data on material and energy flows. Next, an economic assessment was carried out by estimating operating and capital costs. Return on investment (ROI) and payback period (PBP) were used as indicators. The results of the process modelling indicate that series of separation steps are required. The downstream processing was found especially demanding in the hydrothermal upgrading process due to the presence of significant amount of unconverted lignin (34%) and water. Also, external utility requirements were found to be high. Due to the complex separations, hydrothermal upgrading process showed the highest capital cost (50 M€ more than benchmark). Whereas operating costs were found the highest for the direct HDO process (20 M€/year more than benchmark) due to the use of hydrogen. Because of high yields to valuable heavy organics (32%) and MOAMON (24%), direct HDO process showed the highest ROI (12%) and the shortest PBP (5 years). This process is found feasible with a positive net present value. However, it is very sensitive to the prices used in the calculation. The assessments at this stage are associated with large uncertainties. Nevertheless, they are useful for comparing alternatives and identifying whether a certain process should be given further consideration. Among the three processes investigated here, the direct HDO process was seen to be the most promising.

Keywords: biorefinery, economic assessment, lignin conversion, process design

Procedia PDF Downloads 246

Authors: Filip Rusak, Yulia Arzhaeva, Dadong Wang

Abstract:

Machine learning based Computer-Aided Diagnosis (CAD) is gaining much popularity in medical imaging and diagnostic radiology. However, it requires a large amount of high quality and labeled training image datasets. The training images may come from different sources and be acquired from different radiography machines produced by different manufacturers, digital or digitized copies of film radiographs, with various sizes as well as different pixel intensity distributions. In this paper, a content-aware image augmentation method is presented to deal with these variations. The results of the proposed method have been validated graphically by plotting the removed and added seams of pixels on original images. Two different chest X-ray (CXR) datasets are used in the experiments. The CXRs in the datasets defer in size, some are digital CXRs while the others are digitized from analog CXR films. With the proposed content-aware augmentation method, the Seam Carving algorithm is employed to resize CXRs and the corresponding labels in the form of image masks, followed by histogram matching used to normalize the pixel intensities of digital radiography, based on the pixel intensity values of digitized radiographs. We implemented the algorithms, resized the well-known Montgomery dataset, to the size of the most frequently used Japanese Society of Radiological Technology (JSRT) dataset and normalized our digital CXRs for testing. This work resulted in the unified off-the-shelf CXR dataset composed of radiographs included in both, Montgomery and JSRT datasets. The experimental results show that even though the amount of augmentation is large, our algorithm can preserve the important information in lung fields, local structures, and global visual effect adequately. The proposed method can be used to augment training and testing image data sets so that the trained machine learning model can be used to process CXRs from various sources, and it can be potentially used broadly in any medical imaging applications.

Keywords: computer-aided diagnosis, image augmentation, lung segmentation, medical imaging, seam carving

Procedia PDF Downloads 191

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 189

Authors: Shaik Ayesha Fathima, Shaik Noor Jahan, Duvvada Rajeswara Rao

Abstract:

Earth's environment and its evolution can be seen through satellite images in near real-time. Through satellite imagery, remote sensing data provide crucial information that can be used for a variety of applications, including image fusion, change detection, land cover classification, agriculture, mining, disaster mitigation, and monitoring climate change. The objective of this project is to propose a method for classifying satellite images according to multiple predefined land cover classes. The proposed approach involves collecting data in image format. The data is then pre-processed using data pre-processing techniques. The processed data is fed into the proposed algorithm and the obtained result is analyzed. Some of the algorithms used in satellite imagery classification are U-Net, Random Forest, Deep Labv3, CNN, ANN, Resnet etc. In this project, we are using the DeepLabv3 (Atrous convolution) algorithm for land cover classification. The dataset used is the deep globe land cover classification dataset. DeepLabv3 is a semantic segmentation system that uses atrous convolution to capture multi-scale context by adopting multiple atrous rates in cascade or in parallel to determine the scale of segments.

Keywords: area calculation, atrous convolution, deep globe land cover classification, deepLabv3, land cover classification, resnet 50

Procedia PDF Downloads 124

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed-length window in the past as an explicit input. In this paper, we study how the performance of predictive models changes as a function of different look-back window sizes and different amounts of time to predict the future. We also consider the performance of the recent attention-based Transformer models, which have had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (RNN, LSTM, GRU, and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the UCI website, which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Average Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: air quality prediction, deep learning algorithms, time series forecasting, look-back window

Procedia PDF Downloads 138

Authors: Adam Gorine, Faten Spondon

Abstract:

Python is considered the most popular programming language and offers its own ecosystem for archiving and maintaining open-source software packages. This system is called the python package index (PyPI), the repository of this programming language. Unfortunately, one-third of these software packages have vulnerabilities that allow attackers to execute code automatically when a vulnerable or malicious package is installed. This paper contributes to large-scale empirical studies investigating security issues in the python ecosystem by evaluating package vulnerabilities. These provide a series of implications that can help the security of software ecosystems by improving the process of discovering, fixing, and managing package vulnerabilities. The vulnerable dataset is generated using the NVD, the national vulnerability database, and the Snyk vulnerability dataset. In addition, we evaluated 807 vulnerability reports in the NVD and 3900 publicly known security vulnerabilities in Python Package Manager (pip) from the Snyk database from 2002 to 2022. As a result, many Python vulnerabilities appear in high severity, followed by medium severity. The most problematic areas have been improper input validation and denial of service attacks. A hybrid scanning tool that combines the three scanners bandit, snyk and dlint, which provide a clear report of the code vulnerability, is also described.

Keywords: Python vulnerabilities, bandit, Snyk, Dlint, Python package index, ecosystem, static analysis, malicious attacks

Procedia PDF Downloads 110

Authors: Yingkun Huang, Li Guo, Zekang Lan, Kai Tian

Abstract:

Hard disk drives (HDD) failure of the exascale supercomputing system may lead to service interruption and invalidate previous calculations, and it will cause permanent data loss. Therefore, initiating corrective actions before hard drive failures materialize is critical to the continued operation of jobs. In this paper, a highly accurate analysis model based on CNN-LSTM and oversampling technique was proposed, which can correctly predict the necessity of a disk replacement even ten days in advance. Generally, the learning-based method performs poorly on a training dataset with long-tail distribution, especially fault prediction is a very classic situation as the scarcity of failure data. To overcome the puzzle, a new oversampling was employed to augment the data, and then, an improved CNN-LSTM with the shortcut was built to learn more effective features. The shortcut transmits the results of the previous layer of CNN and is used as the input of the LSTM model after weighted fusion with the output of the next layer. Finally, a detailed, empirical comparison of 6 prediction methods is presented and discussed on a public dataset for evaluation. The experiments indicate that the proposed method predicts disk failure with 0.91 Precision, 0.91 Recall, 0.91 F-measure, and 0.90 MCC for 10 days prediction horizon. Thus, the proposed algorithm is an efficient algorithm for predicting HDD failure in supercomputing.

Keywords: HDD replacement, failure, CNN-LSTM, oversampling, prediction

Procedia PDF Downloads 61

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network

Procedia PDF Downloads 114

Authors: Sandesh Achar

Abstract:

Personalized advertising holds greater potential for higher conversion rates compared to generic advertisements. However, its widespread application in the retail industry faces challenges due to complex implementation processes. These complexities impede the swift adoption of personalized advertisement on a large scale. Personalized advertisement, being a data-driven approach, necessitates consumer-related data, adding to its complexity. This paper introduces an innovative data-driven decision-making framework, D3Advert, which personalizes advertisements by analyzing personalities using a BiLSTM network. The framework utilizes the Myers–Briggs Type Indicator (MBTI) dataset for development. The employed BiLSTM network, specifically designed and optimized for D3Advert, classifies user personalities into one of the sixteen MBTI categories based on their social media posts. The classification accuracy is 86.42%, with precision, recall, and F1-Score values of 85.11%, 84.14%, and 83.89%, respectively. The D3Advert framework personalizes advertisements based on these personality classifications. Experimental implementation and performance analysis of D3Advert demonstrate a 40% improvement in impressions. D3Advert’s innovative and straightforward approach has the potential to transform personalized advertising and foster widespread personalized advertisement adoption in marketing.

Keywords: personalized advertisement, deep Learning, MBTI dataset, BiLSTM network, NLP.

Procedia PDF Downloads 23

Authors: Qiang Wang, Hongyang Yu

Abstract:

Multi-human 3D pose estimation is a challenging task in computer vision, which aims to recover the 3D joint locations of multiple people from multi-view images. In contrast to traditional methods, which typically only use color (RGB) images as input, our approach utilizes both color and depth (D) information contained in RGB-D images. We also employ a transformer-based model as the backbone of our approach, which is able to capture long-range dependencies and has been shown to perform well on various sequence modeling tasks. Our method is trained and tested on the Carnegie Mellon University (CMU) Panoptic dataset, which contains a diverse set of indoor and outdoor scenes with multiple people in varying poses and clothing. We evaluate the performance of our model on the standard 3D pose estimation metrics of mean per-joint position error (MPJPE). Our results show that the transformer-based approach outperforms traditional methods and achieves competitive results on the CMU Panoptic dataset. We also perform an ablation study to understand the impact of different design choices on the overall performance of the model. In summary, our work demonstrates the effectiveness of using a transformer-based approach with RGB-D images for multi-human 3D pose estimation and has potential applications in real-world scenarios such as human-computer interaction, robotics, and augmented reality.

Keywords: multi-human 3D pose estimation, RGB-D images, transformer, 3D joint locations

Procedia PDF Downloads 61

Authors: Ayush Shrivastava, Arpit Chaudhary, Devang Kulshreshtha, Vibhav Prakash Singh, Rajeev Srivastava

Abstract:

Early diagnosis of breast cancer can improve the survival rate by detecting cancer at an early stage. Breast region segmentation is an essential step in the analysis of digital mammograms. Accurate image segmentation leads to better detection of cancer. It aims at separating out Region of Interest (ROI) from rest of the image. The procedure begins with removal of labels, annotations and tags from the mammographic image using morphological opening method. Pectoral Muscle Sliding Window Algorithm (PMSWA) is used for removal of pectoral muscle from mammograms which is necessary as the intensity values of pectoral muscles are similar to that of ROI which makes it difficult to separate out. After removing the pectoral muscle, Dispersed Region Growing Algorithm (DRGA) is used for segmentation of mammogram which disperses seeds in different regions instead of a single bright region. To demonstrate the validity of our segmentation method, 322 mammographic images from Mammographic Image Analysis Society (MIAS) database are used. The dataset contains medio-lateral oblique (MLO) view of mammograms. Experimental results on MIAS dataset show the effectiveness of our proposed method.

Keywords: CAD, dispersed region growing algorithm (DRGA), image segmentation, mammography, pectoral muscle sliding window algorithm (PMSWA)

Procedia PDF Downloads 292

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 99

Authors: Nahla H. Alaswadko, Rayya A. Hassan, Bayar N. Mohammed

Abstract:

Empirical deterministic models have been developed to predict roughness progression of heavy duty spray sealed pavements for a dataset representing rural arterial roads. The dataset provides a good representation of the relevant network and covers a wide range of operating and environmental conditions. A sample with a large size of historical time series data for many pavement sections has been collected and prepared for use in multilevel regression analysis. The modelling parameters include road roughness as performance parameter and traffic loading, time, initial pavement strength, reactivity level of subgrade soil, climate condition, and condition of drainage system as predictor parameters. The purpose of this paper is to report the approaches adopted for models development and validation. The study presents multilevel models that can account for the correlation among time series data of the same section and to capture the effect of unobserved variables. Study results show that the models fit the data very well. The contribution and significance of relevant influencing factors in predicting roughness progression are presented and explained. The paper concludes that the analysis approach used for developing the models confirmed their accuracy and reliability by well-fitting to the validation data.

Keywords: roughness progression, empirical model, pavement performance, heavy duty pavement

Procedia PDF Downloads 156

Authors: Sagri Sharma

Abstract:

Analysis of diseases integrating multi-factors increases the complexity of the problem and therefore, development of frameworks for the analysis of diseases is an issue that is currently a topic of intense research. Due to the inter-dependence of the various parameters, the use of traditional methodologies has not been very effective. Consequently, newer methodologies are being sought to deal with the problem. Supervised Learning Algorithms are commonly used for performing the prediction on previously unseen data. These algorithms are commonly used for applications in fields ranging from image analysis to protein structure and function prediction and they get trained using a known dataset to come up with a predictor model that generates reasonable predictions for the response to new data. Gene expression profiles generated by DNA analysis experiments can be quite complex since these experiments can involve hypotheses involving entire genomes. The application of well-known machine learning algorithm - Support Vector Machine - to analyze the expression levels of thousands of genes simultaneously in a timely, automated and cost effective way is thus used. The objectives to undertake the presented work are development of a methodology to identify genes relevant to Hepatocellular Carcinoma (HCC) from gene expression dataset utilizing supervised learning algorithms and statistical evaluations along with development of a predictive framework that can perform classification tasks on new, unseen data.

Keywords: artificial intelligence, biomarker, gene expression datasets, hepatocellular carcinoma, machine learning, supervised learning algorithms, support vector machine

Procedia PDF Downloads 413

Authors: E. M. D. Akuoko, Eliana Vasquez Osorio, Marcel Van Herk, Marianne Aznar

Abstract:

Radiotherapy is an integral part of treatment for many patients with breast cancer. However, side effects can occur, e.g., fibrosis or erythema. If patients at higher risks of radiation-induced side effects could be identified before treatment, they could be given more individual information about the risks and benefits of radiotherapy. We hypothesize that breast density is correlated with the risk of side effects and present a novel method for automatic evaluation based on radiotherapy planning CT scans. Methods: 799 supine CT scans of breast radiotherapy patients were available from the REQUITE dataset. The methodology was first established in a subset of 114 patients (cohort 1) before being applied to the whole dataset (cohort 2). All patients were scanned in the supine position, with arms up, and the treated breast (ipsilateral) was identified. Manual experts contour available in 96 patients for both the ipsilateral and contralateral breast in cohort 1. Breast tissue was segmented using atlas-based automatic contouring software, ADMIRE® v3.4 (Elekta AB, Sweden). Once validated, the automatic segmentation method was applied to cohort 2. Breast density was then investigated by thresholding voxels within the contours, using Otsu threshold and pixel intensity ranges based on Hounsfield units (-200 to -100 for fatty tissue, and -99 to +100 for fibro-glandular tissue). Volumetric breast density (VBD) was defined as the volume of fibro-glandular tissue / (volume of fibro-glandular tissue + volume of fatty tissue). A sensitivity analysis was performed to verify whether calculated VBD was affected by the choice of breast contour. In addition, we investigated the correlation between volumetric breast density (VBD) and patient age and breast size. VBD values were compared between ipsilateral and contralateral breast contours. Results: Estimated VBD values were 0.40 (range 0.17-0.91) in cohort 1, and 0.43 (0.096-0.99) in cohort 2. We observed ipsilateral breasts to be denser than contralateral breasts. Breast density was negatively associated with breast volume (Spearman: R=-0.5, p-value < 2.2e-16) and age (Spearman: R=-0.24, p-value = 4.6e-10). Conclusion: VBD estimates could be obtained automatically on a large CT dataset. Patients’ age or breast volume may not be the only variables that explain breast density. Future work will focus on assessing the usefulness of VBD as a predictive variable for radiation-induced side effects.

Keywords: breast cancer, automatic image segmentation, radiotherapy, big data, breast density, medical imaging

Procedia PDF Downloads 116

Authors: Toktam Khatibi

Abstract:

Self-supervised learning (SSL) includes machine learning models that are trained on one aspect and/or one part of the input to learn other aspects and/or part of it. SSL models are divided into two different categories, including pre-text task-based models and contrastive learning ones. Pre-text tasks are some auxiliary tasks learning pseudo-labels, and the trained models are further fine-tuned for downstream tasks. However, one important disadvantage of SSL using pre-text task solving is defining an appropriate pre-text task for each image dataset with a variety of image modalities. Therefore, it is required to design an appropriate pretext task automatically for each dataset and each downstream task. To the best of our knowledge, the automatic designing of pretext tasks for image analysis has not been considered yet. In this paper, we present a framework based on In-context learning that describes each task based on its input and output data using a pre-trained image transformer. Our proposed method combines the input image and its learned description for optimizing the pre-text task design and its hyper-parameters using Meta-learning models. The representations learned from the pre-text tasks are fine-tuned for solving the downstream tasks. We demonstrate that our proposed framework outperforms the compared ones on unseen tasks and image modalities in addition to its superior performance for previously known tasks and datasets.

Keywords: in-context learning (ICL), meta learning, self-supervised learning (SSL), vision-language domain, transformers

Procedia PDF Downloads 57

Authors: Zakaria Kharbouch, Mustapha Bouchaara, F. Elkouihen, A. Habbal, A. Ratnani, A. Faik

Abstract:

Solid-state lithium-ion batteries have garnered increasing interest in modern energy research due to their potential for safer, more efficient, and sustainable energy storage systems. Among the critical components of these batteries, the electrolyte plays a pivotal role, with LLZO garnet-based electrolytes showing significant promise. Garnet materials offer intrinsic advantages such as high Li-ion conductivity, wide electrochemical stability, and excellent compatibility with lithium metal anodes. However, optimizing ionic conductivity in garnet structures poses a complex challenge, primarily due to the multitude of potential dopants that can be incorporated into the LLZO crystal lattice. The complexity of material design, influenced by numerous dopant options, requires a systematic method to find the most effective combinations. This study highlights the utility of machine learning (ML) techniques in the materials discovery process to navigate the complex range of factors in garnet-based electrolytes. Collaborators from the materials science and ML fields worked with a comprehensive dataset previously employed in a similar study and collected from various literature sources. This dataset served as the foundation for an extensive data refinement phase, where meticulous error identification, correction, outlier removal, and garnet-specific feature engineering were conducted. This rigorous process substantially improved the dataset's quality, ensuring it accurately captured the underlying physical and chemical principles governing garnet ionic conductivity. The data refinement effort resulted in a significant improvement in the predictive performance of the machine learning model. Originally starting at an accuracy of 0.32, the model underwent substantial refinement, ultimately achieving an accuracy of 0.88. This enhancement highlights the effectiveness of the interdisciplinary approach and underscores the substantial potential of machine learning techniques in materials science research.

Keywords: lithium batteries, all-solid-state batteries, machine learning, solid state electrolytes

Procedia PDF Downloads 38

Authors: Hankyu Lee, Seoung Bum Kim

Abstract:

The issue with imbalance and overlapping in the class distribution becomes important in various applications of data mining. The imbalanced dataset is a special case in classification problems in which the number of observations of one class (i.e., major class) heavily exceeds the number of observations of the other class (i.e., minor class). Overlapped dataset is the case where many observations are shared together between the two classes. Imbalanced and overlapped data can be frequently found in many real examples including fraud and abuse patients in healthcare, quality prediction in manufacturing, text classification, oil spill detection, remote sensing, and so on. The class imbalance and overlap problem is the challenging issue because this situation degrades the performance of most of the standard classification algorithms. In this study, we propose a classification procedure that can effectively handle imbalanced and overlapped datasets by splitting data space into three parts: nonoverlapping, light overlapping, and severe overlapping and applying the classification algorithm in each part. These three parts were determined based on the Hausdorff distance and the margin of the modified support vector machine. An experiments study was conducted to examine the properties of the proposed method and compared it with other classification algorithms. The results showed that the proposed method outperformed the competitors under various imbalanced and overlapped situations. Moreover, the applicability of the proposed method was demonstrated through the experiment with real data.

Keywords: classification, imbalanced data with class overlap, split data space, support vector machine

Procedia PDF Downloads 291

Authors: Umm-E-Hani, Faiza Babar, Hanif Durad

Abstract:

Malware-detecting approaches suffer many limitations, due to which all anti-malware solutions have failed to be reliable enough for detecting zero-day malware. Signature-based solutions depend upon the signatures that can be generated only when malware surfaces at least once in the cyber world. Another approach that works by detecting the anomalies caused in the environment can easily be defeated by diligently and intelligently written malware. Solutions that have been trained to observe the behavior for detecting malicious files have failed to cater to the malware capable of detecting the sandboxed or protected environment. Machine learning and deep learning-based approaches greatly suffer in training their models with either an imbalanced dataset or an inadequate number of samples. AI-based anti-malware solutions that have been trained with enough samples targeted a selected feature vector, thus ignoring the input of leftover features in the maliciousness of malware just to cope with the lack of underlying hardware processing power. Our research focuses on producing an anti-malware solution for detecting malicious PE files by circumventing the earlier-mentioned shortcomings. Our proposed framework, which is based on automated feature engineering through autoencoders, trains the model over a fairly large dataset. It focuses on the visual patterns of malware samples to automatically extract the meaningful part of the visual pattern. Our experiment has successfully produced a state-of-the-art accuracy of 99.54 % over test data.

Keywords: malware, auto encoders, automated feature engineering, classification

Procedia PDF Downloads 57