Search results for: deep learning methods

Authors: D. I. George Amalarethinam, A. Emima

Abstract:

Educational Data Mining (EDM) is one of the newest topics to emerge in recent years, and it is concerned with developing methods for analyzing various types of data gathered from the educational circle. EDM methods and techniques with machine learning algorithms are used to extract meaningful and usable information from huge databases. For scientists and researchers, realistic applications of Machine Learning in the EDM sectors offer new frontiers and present new problems. One of the most important research areas in EDM is predicting student success. The prediction algorithms and techniques must be developed to forecast students' performance, which aids the tutor, institution to boost the level of student’s performance. This paper examines various classification techniques in prediction methods and data mining tools used in EDM.

Keywords: classification technique, data mining, EDM methods, prediction methods

Procedia PDF Downloads 114

Authors: Almutasim Billa A. Alanazi, Hal S. Tharp

Abstract:

Safe performance and efficient energy consumption are essential factors for designing a control system. This paper presents a reinforcement learning (RL) model that can be applied to control applications to improve safety and reduce energy consumption. As hardware constraints and environmental disturbances are imprecise and unpredictable, conventional control methods may not always be effective in optimizing control designs. However, RL has demonstrated its value in several artificial intelligence (AI) applications, especially in the field of control systems. The proposed model intelligently monitors a system's success by observing the rewards from the environment, with positive rewards counting as a success when the controlled reference is within the desired operating zone. Thus, the model can determine whether the system is safe to continue operating based on the designer/user specifications, which can be adjusted as needed. Additionally, the controller keeps track of energy consumption to improve energy efficiency by enabling the idle mode when the controlled reference is within the desired operating zone, thus reducing the system energy consumption during the controlling operation. Water temperature control for a hydroponic system is taken as a case study for the RL model, adjusting the variance of disturbances to show the model’s robustness and efficiency. On average, the model showed safety improvement by up to 15% and energy efficiency improvements by 35%- 40% compared to a traditional RL model.

Keywords: control system, hydroponics, machine learning, reinforcement learning

Procedia PDF Downloads 181

Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson

Abstract:

The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.

Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania

Procedia PDF Downloads 100

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

Abstract:

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

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

Procedia PDF Downloads 93

Authors: Shamshuddin K., Nagaraj Vannal, Diwakar Kulkarni, Raghavendra Nakod

Abstract:

In most of the universities and colleges Operating System (OS) course is treated as theoretical and usually taught in a classroom using conventional teaching methods. In this paper we are presenting a new approach of teaching OS through experiential learning, the course is designed to suit the requirement of undergraduate engineering program of Instrumentation Technology. This new approach has benefited us to improve our student’s programming skills, presentation skills and understanding of the operating system concepts.

Keywords: pedagogy, interactive learning, experiential learning, OS, C, UNIX

Procedia PDF Downloads 604

Authors: Iqra Yaseen

Abstract:

One of the well-known areas of computer science and engineering, image processing in the context of computer vision has been essential to automation. In remote sensing, medical science, and many other fields, it has made it easier to uncover previously undiscovered facts. Grading of diverse items is now possible because of neural network algorithms, categorization, and digital image processing. Its use in the classification of agricultural products, particularly in the grading of seeds or grains and their cultivars, is widely recognized. A grading and sorting system enables the preservation of time, consistency, and uniformity. Global population growth has led to an increase in demand for food staples, biofuel, and other agricultural products. To meet this demand, available resources must be used and managed more effectively. Image processing is rapidly growing in the field of agriculture. Many applications have been developed using this approach for crop identification and classification, land and disease detection and for measuring other parameters of crop. Vegetation localization is the base of performing these task. Vegetation helps to identify the area where the crop is present. The productivity of the agriculture industry can be increased via image processing that is based upon Unmanned Aerial Vehicle photography and satellite. In this paper we use the machine learning techniques like Convolutional Neural Network, deep learning, image processing, classification, You Only Live Once to UAV imaging dataset to divide the crop into distinct groups and choose the best way to use it.

Keywords: image processing, UAV, YOLO, CNN, deep learning, classification

Procedia PDF Downloads 101

Authors: Chechen Liao, Chin Yi Yang

Abstract:

Although several factors that affect learning to program have been identified over the years, there continues to be no indication of any consensus in understanding why some students learn to program easily and quickly while others have difficulty. Seldom have researchers considered the problem of how to help the students enhance the programming learning outcome. The research had been conducted at a high school in Taiwan. Students participating in the study consist of 330 tenth grade students enrolled in the Basic Computer Concepts course with the same instructor. Two types of training methods-instruction-oriented and exploration-oriented were conducted. The result of this research shows that the instruction-oriented training method has better learning performance than exploration-oriented training method.

Keywords: learning performance, programming learning, TDD, training method

Procedia PDF Downloads 425

Authors: Li Hui, Riyadh Hindi

Abstract:

Concrete structures frequently suffer from crack formation, a critical issue that can significantly reduce their lifespan by allowing damaging agents to enter. Traditional methods of crack detection depend on manual visual inspections, which heavily relies on the experience and expertise of inspectors using tools. In this study, a more efficient, computer vision-based approach is introduced by using the lightweight MobileNetV2 neural network. A dataset of 40,000 images was used to develop a specialized crack evaluation algorithm. The analysis indicates that MobileNetV2 matches the accuracy of traditional CNN methods but is more efficient due to its smaller size, making it well-suited for mobile device applications. The effectiveness and reliability of this new method were validated through experimental testing, highlighting its potential as an automated solution for crack detection in concrete structures.

Keywords: Concrete crack, computer vision, deep learning, MobileNetV2 neural network

Procedia PDF Downloads 65

Authors: Güzi̇n Ti̇rkeş, Özge Teki̇n, Kerem Kurtuluş, Y. Yekta Yurtseven, Murat Baran

Abstract:

A scanning electron microscope (SEM) is a type of electron microscope mainly used in nanoscience and nanotechnology areas. Automatic image recognition and classification are among the general areas of application concerning SEM. In line with these usages, the present paper proposes a deep learning algorithm that classifies SEM images into nine categories by means of an online application to simplify the process. The NFFA-EUROPE - 100% SEM data set, containing approximately 21,000 images, was used to train and test the algorithm at 80% and 20%, respectively. Validation was carried out using a separate data set obtained from the Middle East Technical University (METU) in Turkey. To increase the accuracy in the results, the Inception ResNet-V2 model was used in view of the Fine-Tuning approach. By using a confusion matrix, it was observed that the coated-surface category has a negative effect on the accuracy of the results since it contains other categories in the data set, thereby confusing the model when detecting category-specific patterns. For this reason, the coated-surface category was removed from the train data set, hence increasing accuracy by up to 96.5%.

Keywords: convolutional neural networks, deep learning, image classification, scanning electron microscope

Procedia PDF Downloads 121

Authors: Arefeh Arabaninezhad, Ali Fakher

Abstract:

Since the deterministic analysis methods fail to take system uncertainties into account, probabilistic and non-probabilistic methods are suggested. Geotechnical analyses are used to determine the stress and deformation caused by construction; accordingly, many input variables which depend on ground behavior are required for geotechnical analyses. The Random Set approach is an applicable reliability analysis method when comprehensive sources of information are not available. Using Random Set method, with relatively small number of simulations compared to fully probabilistic methods, smooth extremes on system responses are obtained. Therefore random set approach has been proposed for reliability analysis in geotechnical problems. In the present study, the application of random set method in reliability analysis of deep excavations is investigated through three deep excavation projects which were monitored during the excavating process. A finite element code is utilized for numerical modeling. Two expected ranges, from different sources of information, are established for each input variable, and a specific probability assignment is defined for each range. To determine the most influential input variables and subsequently reducing the number of required finite element calculations, sensitivity analysis is carried out. Input data for finite element model are obtained by combining the upper and lower bounds of the input variables. The relevant probability share of each finite element calculation is determined considering the probability assigned to input variables present in these combinations. Horizontal displacement of the top point of excavation is considered as the main response of the system. The result of reliability analysis for each intended deep excavation is presented by constructing the Belief and Plausibility distribution function (i.e. lower and upper bounds) of system response obtained from deterministic finite element calculations. To evaluate the quality of input variables as well as applied reliability analysis method, the range of displacements extracted from models has been compared to the in situ measurements and good agreement is observed. The comparison also showed that Random Set Finite Element Method applies to estimate the horizontal displacement of the top point of deep excavation. Finally, the probability of failure or unsatisfactory performance of the system is evaluated by comparing the threshold displacement with reliability analysis results.

Keywords: deep excavation, random set finite element method, reliability analysis, uncertainty

Procedia PDF Downloads 267

Authors: Heramb Somthankar, Anujoy Chakraborty

Abstract:

This paper presents a classification study on yield prediction in semiconductor production using machine learning approaches. A complicated semiconductor production process is generally monitored continuously by signals acquired from sensors and measurement sites. A monitoring system contains a variety of signals, all of which contain useful information, irrelevant information, and noise. In the case of each signal being considered a feature, "Feature Selection" is used to find the most relevant signals. The open-source UCI SECOM Dataset provides 1567 such samples, out of which 104 fail in quality assurance. Feature extraction and selection are performed on the dataset, and useful signals were considered for further study. Afterward, common machine learning algorithms were employed to predict whether the signal yields pass or fail. The most relevant algorithm is selected for prediction based on the accuracy and loss of the ML model.

Keywords: deep learning, feature extraction, feature selection, machine learning classification algorithms, semiconductor production monitoring, signal processing, time-series analysis

Procedia PDF Downloads 105

Authors: Pimploi Tirastittam, Suppara Charoenpoom

Abstract:

Nowadays the asynchronous learning has granted the permission to the anywhere and anything learning via the technology and E-media which give the learner more convenient. This research is about the design of the blended and online learning for the asynchronous learning of the process management subject in order to create the prototype of this subject asynchronous learning which will create the easiness and increase capability in the learning. The pattern of learning is the integration between the in-class learning and online learning via the internet. This research is mainly focused on the online learning and the online learning can be divided into 5 parts which are virtual classroom, online content, collaboration, assessment and reference material. After the system design was finished, it was evaluated and tested by 5 experts in blended learning design and 10 students which the user’s satisfaction level is good. The result is as good as the assumption so the system can be used in the process management subject for a real usage.

Keywords: blended learning, asynchronous learning, design, process management

Procedia PDF Downloads 403

Authors: Sneha Thakur, Sanjeev Karmakar

Abstract:

This paper proposed hybrid Particle Swarm Optimization (PSO) – Long-Short Term Memory (LSTM) model for groundwater level prediction. The evaluation of the performance is realized using the parameters: root mean square error (RMSE) and mean absolute error (MAE). Ground water level forecasting will be very effective for planning water harvesting. Proper calculation of water level forecasting can overcome the problem of drought and flood to some extent. The objective of this work is to develop a ground water level forecasting model using deep learning technique integrated with optimization technique PSO by applying 29 years data of Chhattisgarh state, In-dia. It is important to find the precise forecasting in case of ground water level so that various water resource planning and water harvesting can be managed effectively.

Keywords: long short-term memory, particle swarm optimization, prediction, deep learning, groundwater level

Procedia PDF Downloads 72

Authors: Samina Khalid, Shamila Nasreen

Abstract:

Dimensionality reduction as a preprocessing step to machine learning is effective in removing irrelevant and redundant data, increasing learning accuracy, and improving result comprehensibility. However, the recent increase of dimensionality of data poses a severe challenge to many existing feature selection and feature extraction methods with respect to efficiency and effectiveness. In the field of machine learning and pattern recognition, dimensionality reduction is important area, where many approaches have been proposed. In this paper, some widely used feature selection and feature extraction techniques have analyzed with the purpose of how effectively these techniques can be used to achieve high performance of learning algorithms that ultimately improves predictive accuracy of classifier. An endeavor to analyze dimensionality reduction techniques briefly with the purpose to investigate strengths and weaknesses of some widely used dimensionality reduction methods is presented.

Keywords: age related macular degeneration, feature selection feature subset selection feature extraction/transformation, FSA’s, relief, correlation based method, PCA, ICA

Procedia PDF Downloads 491

Authors: Michael Karnes, Alper Yilmaz

Abstract:

This paper presents the application of the omni-modeler towards pedestrian redetection. The pedestrian redetection task creates several challenges when applying deep neural networks (DNN) due to the variety of pedestrian appearance with camera position, the variety of environmental conditions, and the specificity required to recognize one pedestrian from another. DNNs require significant training sets and are not easily adapted for changes in class appearances or changes in the set of classes held in its knowledge domain. Pedestrian redetection requires an algorithm that can actively manage its knowledge domain as individuals move in and out of the scene, as well as learn individual appearances from a few frames of a video. The Omni-Modeler is a dynamically learning few-shot visual recognition algorithm developed for tasks with limited training data availability. The Omni-Modeler adapts the knowledge domain of pre-trained deep neural networks to novel concepts with a calculated localized language encoder. The Omni-Modeler knowledge domain is generated by creating a dynamic dictionary of concept definitions, which are directly updatable as new information becomes available. Query images are identified through nearest neighbor comparison to the learned object definitions. The study presented in this paper evaluates its performance in re-identifying individuals as they move through a scene in both single-camera and multi-camera tracking applications. The results demonstrate that the Omni-Modeler shows potential for across-camera view pedestrian redetection and is highly effective for single-camera redetection with a 93% accuracy across 30 individuals using 64 example images for each individual.

Keywords: dynamic learning, few-shot learning, pedestrian redetection, visual recognition

Procedia PDF Downloads 74

Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh

Abstract:

In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.

Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization

Procedia PDF Downloads 111

Authors: Heesuk Seo, Yongtae Kim

Abstract:

Online learning started in the 1990s, the spread of the Internet has been through the era of e-learning paradigm of online education in the era of smart learning change. Reflecting the different nature of the mobile to anywhere anytime, anywhere was also allows the form of learning, it was also available through the learning content and interaction. We are developing a cloud system, 'TLINKS CLOUD' that allows you to configure the environment of the smart learning without the need for additional infrastructure. Using the big-data analysis for e-learning contents, we provide an integrated solution for e-learning tailored to individual study.

Keywords: authority tool, big data analysis, e-learning, HTML5

Procedia PDF Downloads 403

Authors: Waraporn Thaimit, Yuwadee Insamran, Natchanok Jansawang

Abstract:

Focusing on Analytical Thinking and Learning Achievement are the critical component of visual thinking that gives one the ability to solve problems quickly and effectively that allows to complex problems into components, and the result had been achieved or acquired form of the subject students of which resulted in changes within the individual as a result of activity in learning. The aims of this study are to administer on comparisons between students’ analytical thinking abilities and their learning achievements sample size consisted of 80 students who sat at the 12th grade level in 2 classes from Chaturaphak Phiman Ratchadaphisek School, the 40-student experimental group with the Problem-Based Learning (PBL) and 40-student controlling group with the Concept Mapping Instructional (CMI) methods were designed. Research instruments composed with the 5-lesson instructional plans to be assessed with the pretest and posttest techniques on each instructional method. Students’ responses of their analytical thinking abilities were assessed with the Analytical Thinking Tests and students’ learning achievements were tested of the Learning Achievement Tests. Statistically significant differences with the paired t-test and F-test (Two-way MANCOVA) between post- and pre-tests of the whole students in two chemistry classes were found. Associations between student learning outcomes in each instructional method and their analytical thinking abilities to their learning achievements also were found (ρ < .05). The use of two instructional methods for this study is revealed that the students perceive their abilities to be highly learning achievement in chemistry classes with the PBL group ought to higher than the CMI group. Suggestions that analytical thinking ability involves the process of gathering relevant information and identifying key issues related to the learning achievement information.

Keywords: comparisons, students learning achievements, analytical thinking abilities, the problem-based learning method, the concept mapping instructional method, gene and chromosome issue, chemistry classes

Procedia PDF Downloads 257

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 137

Authors: Ahmed Amin Mousa, M. Abd El-Salam

Abstract:

This study discusses a simple solution for the problem of shortage in learning resources for kindergarten teachers. Occasionally, kindergarten teachers cannot access proper resources by usual search methods as libraries or search engines. Furthermore, these methods require a long time and efforts for preparing. The study is expected to facilitate accessing learning resources. Moreover, it suggests a potential direction for using QR code inside the classroom. The present work proposes that QR code can be used for digitizing kindergarten curriculums and accessing various learning resources. It investigates using QR code for saving information related to the concepts which kindergarten teachers use in the current educational situation. The researchers have established a guide for kindergarten teachers based on the Egyptian official curriculum. The guide provides different learning resources for each scientific and mathematical concept in the curriculum, and each learning resource is represented as a QR code image that contains its URL. Therefore, kindergarten teachers can use smartphone applications for reading QR codes and displaying the related learning resources for students immediately. The guide has been provided to a group of 108 teachers for using inside their classrooms. The results showed that the teachers approved the guide, and gave a good response.

Keywords: kindergarten, child, learning resources, QR code, smart phone, mobile

Procedia PDF Downloads 286

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 140

Authors: Selim M. Khan, Aaron A. Goodarzi, Joshua M. Taron, Tryggve Rönnqvist

Abstract:

Indoor air quality, a prime determinant of health, is strongly influenced by the presence of hazardous radon gas within the built environment. As a health issue, dangerously high indoor radon arose within the 20th century to become the 2nd leading cause of lung cancer. While the 21st century building metrics and human behaviors have captured, contained, and concentrated radon to yet higher and more hazardous levels, the issue is rapidly worsening in Canada. It is established that Canadians in the Prairies are the 2nd highest radon-exposed population in the world, with 1 in 6 residences experiencing 0.2-6.5 millisieverts (mSv) radiation per week, whereas the Canadian Nuclear Safety Commission sets maximum 5-year occupational limits for atomic workplace exposure at only 20 mSv. This situation is also deteriorating over time within newer housing stocks containing higher levels of radon. Deep machine learning (LSTM) algorithms were applied to analyze multiple quantitative and qualitative features, determine the most important contributory factors, and predicted radon levels in the known past (1990-2020) and projected future (2021-2050). The findings showed gradual downwards patterns in Sweden, whereas it would continue to go from high to higher levels in Canada over time. The contributory factors found to be the basement porosity, roof insulation depthness, R-factor, and air dynamics of the indoor environment related to human window opening behaviour. Building codes must consider including these factors to ensure adequate indoor ventilation and healthy living that can prevent lung cancer in non-smokers.

Keywords: radon, building metrics, deep learning, LSTM prediction model, lung cancer, canada, sweden

Procedia PDF Downloads 108

Authors: Mehrnaz Mostafavi, Mahtab Shabani, Alireza Azani, Fatemeh Ghafari

Abstract:

Artificial intelligence (AI) can transform breast cancer diagnosis and therapy by providing sophisticated solutions for screening, imaging interpretation, histopathological analysis, and treatment planning. This literature review digs into the many uses of AI in breast cancer treatment, highlighting the need for collaboration between AI scientists and healthcare practitioners. It emphasizes advances in AI-driven breast imaging interpretation, such as computer-aided detection and diagnosis (CADe/CADx) systems and deep learning algorithms. These have shown significant potential for improving diagnostic accuracy and lowering radiologists' workloads. Furthermore, AI approaches such as deep learning have been used in histopathological research to accurately predict hormone receptor status and categorize tumor-associated stroma from regular H&E stains. These AI-powered approaches simplify diagnostic procedures while providing insights into tumor biology and prognosis. As AI becomes more embedded in breast cancer care, it is crucial to ensure its ethical, efficient, and patient-focused implementation to improve outcomes for breast cancer patients ultimately.

Keywords: breast cancer, artificial intelligence, cancer diagnosis, clinical practice

Procedia PDF Downloads 57

Authors: Yumeng He

Abstract:

The purpose of this paper is to establish the “extenics” of children music education, the “extenics” thought and methods are introduced into the children music education field. Discussions are made from the perspective of children music education on how to generate new music cognitive from music cognitive, how to generate new music education from music education and how to generate music learning from music learning. The research methods including the extensibility of music art, extensibility of music education, extensibility of music capability and extensibility of music learning. Results of this study indicate that the thought and research methods of children’s extended music education not only have developed the “extenics” concept and ideological methods, meanwhile, the brand-new thought and innovative research perspective have been employed in discussing the children music education. As indicated in research, the children’s extended music education has extended the horizon of children music education, and has endowed the children music education field with a new thought and research method.

Keywords: comprehensive evaluations, extension thought, extension cognition music education, extensibility

Procedia PDF Downloads 222

Authors: Tracy Ho, Huann-Shyang Lin, Mina Lin

Abstract:

This study investigated the different learning path of students with different learning attitude and learning styles in Arts Creation. Based on direct instruction, guided-discovery learning, and discovery learning theories, a tablet app including the following three learning areas were developed for students: (1) replication and remix practice area, (2) guided creation area, and (3) free creation area. Thirty. students with different learning attitude and learning styles were invited to use this app. Students’ learning behaviors were categorized and defined. The results will provide both educators and researchers with insights that can form a useful foundation for designing different content and strategy with the application of new technologies in school teaching. It also sheds light on how an educational App can be designed to enhance Arts Creation.

Keywords: App, arts creation, learning attitude, learning style, tablet

Procedia PDF Downloads 273

Authors: Anita Khadka, Gregory Epiphaniou, Carsten Maple

Abstract:

There is a dramatic surge in the adoption of machine learning (ML) techniques in many areas, including the nuclear industry (such as fault diagnosis and fuel management in nuclear power plants), autonomous systems (including self-driving vehicles), space systems (space debris recovery, for example), medical surgery, network intrusion detection, malware detection, to name a few. With the application of learning methods in such diverse domains, artificial intelligence (AI) has become a part of everyday modern human life. To date, the predominant focus has been on developing underpinning ML algorithms that can improve accuracy, while factors such as resiliency and robustness of algorithms have been largely overlooked. If an adversarial attack is able to compromise the learning method or data, the consequences can be fatal, especially but not exclusively in safety-critical applications. In this paper, we present an in-depth analysis of five adversarial attacks and three defence methods on a crack detection ML model. Our analysis shows that it can be dangerous to adopt machine learning techniques in security-critical areas such as the nuclear industry without rigorous testing since they may be vulnerable to adversarial attacks. While common defence methods can effectively defend against different attacks, none of the three considered can provide protection against all five adversarial attacks analysed.

Keywords: adversarial machine learning, attacks, defences, nuclear industry, crack detection

Procedia PDF Downloads 153

Authors: E. Kempen, M. J. Labuschagne, M. P. Jama

Abstract:

There is evidence that any learning experience should happen in a safe learning environment as students then will interact, experiment, and construct new knowledge. However, little is known about the specific elements required to create a safe learning environment for the millennial generation, especially in optometry education. This study aimed to identify the specific elements that will contribute to a safe learning environment for the millennial generation of optometry students. Methods: An intrinsic qualitative case study was undertaken with undergraduate students from the Department of Optometry at the University of the Free State, South Africa. An open-ended questionnaire survey was completed after the application of nine different teaching-learning methods based on the experiential learning cycle. A total number of 307 questionnaires were analyzed. Two focus group interviews were also conducted to provide additional data to supplement the data and ensure the triangulation of data. Results: Important elements based on the opinions, feelings, and perceptions of student respondents were analyzed. Students feel safe in an environment with which they are familiar, and when they are familiar with each other, the educators, and the surroundings. Small-group learning also creates a safe and familiar environment. Both these elements create an environment where they feel safe to ask questions. Students value an environment where they are able to learn without influencing their marks or disadvantaging the patients. They enjoy learning from their peers, but also need personal contact with educators. Elements such as consistency and an achievable objective also were also analyzed. Conclusion: The findings suggest that to respond to the real need of this generation of students, insight must be gained in students’ perceptions to identify their needs and the learning environment to optimize learning pedagogies. With the implementation of these personalized elements, optometry students will be able to take responsibility and accountability for their learning.

Keywords: experiences and perceptions, safe learning environment, millennial generation, recommendation for optometry education

Procedia PDF Downloads 133

Authors: Nathan Labiosa, Aryan Kohli

Abstract:

This study introduces a hybrid machine learning model for classifying proteins, developed to address the complexities of protein sequence and structural analysis. Utilizing an architecture that combines a lightweight transformer with a concurrent neural network, the hybrid model leverages both sequential and intrinsic physical properties of proteins. Trained on a comprehensive dataset from the Research Collaboratory for Structural Bioinformatics Protein Data Bank, the model demonstrates a classification accuracy of 95%, outperforming existing methods by at least 15%. The high accuracy achieved demonstrates the potential of this approach to innovate protein classification, facilitating advancements in drug discovery and the development of personalized medicine. By enabling precise protein function prediction, the hybrid model allows for specialized strategies in therapeutic targeting and the exploration of protein dynamics in biological systems. Future work will focus on enhancing the model’s generalizability across diverse datasets and exploring the integration of more machine learning techniques to refine predictive capabilities further. The implications of this research offer potential breakthroughs in biomedical research and the broader field of protein engineering.

Keywords: amino acids, deep learning, enzymes, neural networks, protein classification, proteins, transformers

Procedia PDF Downloads 12

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 192

Authors: Abiodun Ezekiel Adesina, Ijeoma Ginikanwa Akubugwo

Abstract:

Information and Communication Technology, ICT can heighten pre-service teachers’ attitudes toward learning and metacognitive learning; however, there is a dearth of literature on the perception of the pre-service teachers on heightening their attitude toward learning and metacognitive learning. Thus, this study investigates the perception of pre-service science teachers on heightening their attitude towards learning and metacognitive learning through ICT. Two research questions and four hypotheses guided the research. A mixed methods research was adopted for the study in concurrent triangulation type of integrating qualitative and quantitative approaches to the study. The cluster random sampling technique was adopted to select 250 pre-service science teachers in Oyo township. Two self-constructed instruments: Heightening Pre-service Science Teachers’ Attitude towards Learning and Metacognitive Learning through Information and Communication Technology Scale (HPALMIS, r=.73), and an unstructured interview were used for data collection. Thematic analysis, frequency counts and percentages, t-tests, and analysis of variance were used for data analysis. The perception level of the pre-service science teachers on heightening their attitude towards learning and metacognitive learning through ICT is above average, with the majority perceiving that ICT can enhance their thinking about their learning. The perception was significant (mean=92.68, SD=10.86, df=249, t=134.91, p<.05). The perception was significantly differentiated by gender (t=2.10, df= 248, p<.05) in favour of the female pre-service teachers and based on the first time of ICTs use (F(5,244)= 9.586, p<.05). Lecturers of science and science related courses should therefore imbibe the use of ICTs in heightening pre-service teachers’ attitude towards learning and metacognitive learning. Government should organize workshops, seminars, lectures, and symposia along with professional bodies for the science education lecturers to keep abreast of the trending ICT.

Keywords: pre-service teachers’ attitude towards learning, metacognitive learning, ICT, pre-service teachers’ perspectives

Procedia PDF Downloads 96