Search results for: machine learning techniques

Authors: Animish Jain

Abstract:

This study deals with using Multiplicative Weight Update within artificial intelligence and machine learning to create models that can diagnose skin cancer using microscopic images of cancer samples. In this study, the multiplicative weight update method is used to take the predictions of multiple models to try and acquire more accurate results. Logistic Regression, Convolutional Neural Network (CNN), and Support Vector Machine Classifier (SVMC) models are employed within the Multiplicative Weight Update system. These models are trained on pictures of skin cancer from the ISIC-Archive, to look for patterns to label unseen scans as either benign or malignant. These models are utilized in a multiplicative weight update algorithm which takes into account the precision and accuracy of each model through each successive guess to apply weights to their guess. These guesses and weights are then analyzed together to try and obtain the correct predictions. The research hypothesis for this study stated that there would be a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The SVMC model had an accuracy of 77.88%. The CNN model had an accuracy of 85.30%. The Logistic Regression model had an accuracy of 79.09%. Using Multiplicative Weight Update, the algorithm received an accuracy of 72.27%. The final conclusion that was drawn was that there was a significant difference in the accuracy of the three models and the Multiplicative Weight Update system. The conclusion was made that using a CNN model would be the best option for this problem rather than a Multiplicative Weight Update system. This is due to the possibility that Multiplicative Weight Update is not effective in a binary setting where there are only two possible classifications. In a categorical setting with multiple classes and groupings, a Multiplicative Weight Update system might become more proficient as it takes into account the strengths of multiple different models to classify images into multiple categories rather than only two categories, as shown in this study. This experimentation and computer science project can help to create better algorithms and models for the future of artificial intelligence in the medical imaging field.

Keywords: artificial intelligence, machine learning, multiplicative weight update, skin cancer

Procedia PDF Downloads 79

Authors: Tasanee Satthapong

Abstract:

The purpose of the study was to determine the relationship between learning style preferences, teaching style preferences, and learning with happiness of college students who were majors in five different academic areas at the Suansunandha Rajabhat University in Thailand. The selected participants were 729 students 1st year-5th year in Faculty of Education from Thai teaching, early childhood education, math and science teaching, and English teaching majors. The research instruments are the Grasha and Riechmann learning and teaching styles survey and the students’ happiness in learning survey, based on learning with happiness theory initiated by the Office of the National Education Commission. The results of this study: 1) The most students’ learning styles were participant style, followed by collaborative style, and independent style 2) Most students’ happiness in learning in all subjects areas were at the moderate level: Early Childhood Education subject had the highest scores, while Math subject was at the least scores. 3) No different of student’s happiness in learning were found between students who has learning styles that match and not match to teachers’ teaching styles.

Keywords: learning style, teaching style, learning with happiness

Procedia PDF Downloads 691

Authors: Mohamed Jama Madar, Oso Wilis

Abstract:

E-learning is the application of information technology in the teaching and learning process. This paper presents the Funnel model as a solution for the problems of implementation of e-learning in tertiary education institutions. While existing models such as TAM, theory-based e-learning and pedagogical model have been used over time, they have generally been found to be inadequate because of their tendencies to treat materials development, instructional design, technology, delivery and governance as separate and isolated entities. Yet it is matching components that bring framework of e-learning strategic implementation. The Funnel model enhances all these into one and applies synchronously and asynchronously to e-learning implementation where the only difference is modalities. Such a model for e-learning implementation has been lacking. The proposed Funnel model avoids ad-ad-hoc approach which has made other systems unused or inefficient, and compromised educational quality. Therefore, the proposed Funnel model should help tertiary education institutions adopt and develop effective and efficient e-learning system which meets users’ requirements.

Keywords: e-learning, pedagogical, technology, strategy

Procedia PDF Downloads 452

Authors: Derejaw Lake Melie, Alemu Kumlachew Tegegne

Abstract:

The increasing prevalence of social media in Ethiopia has exacerbated societal challenges by fostering the proliferation of negative emotional posts and comments. Illicit use of social media has further exacerbated divisions among the population. Addressing these issues through manual identification and aggregation of emotions from millions of users for swift decision-making poses significant challenges, particularly given the rapid growth of Amharic language usage on social platforms. Consequently, there is a critical need to develop an intelligent system capable of automatically detecting and categorizing negative emotional content into social, religious, and political categories while also filtering out toxic online content. This paper aims to leverage sentiment analysis techniques to achieve automatic detection and filtering of negative emotional content from Amharic social media texts, employing a comparative study of deep learning algorithms. The study utilized a dataset comprising 29,962 comments collected from social media platforms using comment exporter software. Data pre-processing techniques were applied to enhance data quality, followed by the implementation of deep learning methods for training, testing, and evaluation. The results showed that CNN, GRU, LSTM, and Bi-LSTM classification models achieved accuracies of 83%, 50%, 84%, and 86%, respectively. Among these models, Bi-LSTM demonstrated the highest accuracy of 86% in the experiment.

Keywords: negative emotion, emotion detection, social media filtering sentiment analysis, deep learning.

Procedia PDF Downloads 23

Authors: Komon Paisal

Abstract:

The purposes of this research were (1) to create a learning activity for constructivism, (2) study the Mathematical Analysis courses learning achievement, and (3) study students’ attitude toward the learning activity for constructivism. The samples in this study were divided into 2 parts including 3 Mathematical Analysis courses instructors of Suan Sunandha Rajabhat University who provided basic information and attended the seminar and 17 Mathematical Analysis courses students who were studying in the academic and engaging in the learning activity for constructivism. The research instruments were lesson plans constructivism, subjective Mathematical Analysis courses achievement test with reliability index of 0.8119, and an attitude test concerning the students’ attitude toward the Mathematical Analysis courses learning activity for constructivism. The result of the research show that the efficiency of the Mathematical Analysis courses learning activity for constructivism is 73.05/72.16, which is more than expected criteria of 70/70. The research additionally find that the average score of learning achievement of students who engaged in the learning activities for constructivism are equal to 70% and the students’ attitude toward the learning activity for constructivism are at the medium level.

Keywords: constructivism, learning management, mathematics analysis courses, learning activity

Procedia PDF Downloads 532

Authors: Sirine Sayed, Mostapha Tarfaoui, Abdelmalek Toumi, Youssef Qarssis, Mohamed Daly, Chokri Bouraoui

Abstract:

This paper delves into the combination of additive manufacturing (AM) and artificial intelligence (AI) to solve challenges related to the mechanical behavior of AM-produced parts. The article highlights the fundamentals and benefits of additive manufacturing, including creating complex geometries, optimizing material use, and streamlining manufacturing processes. The paper also addresses the challenges associated with additive manufacturing, such as ensuring stable mechanical performance and material properties. The role of AI in improving the static behavior of AM-produced parts, including machine learning, especially the neural network, is to make regression models to analyze the large amounts of data generated during experimental tests. It investigates the potential synergies between AM and AI to achieve enhanced functions and personalized mechanical properties. The mechanical behavior of parts produced using additive manufacturing methods can be further improved using design optimization, structural analysis, and AI-based adaptive manufacturing. The article concludes by emphasizing the importance of integrating AM and AI to enhance mechanical operations, increase reliability, and perform advanced functions, paving the way for innovative applications in different fields.

Keywords: additive manufacturing, mechanical behavior, artificial intelligence, machine learning, neural networks, reliability, advanced functionalities

Procedia PDF Downloads 10

Authors: Yuanchao Sang, Zhihao Gong, Longsheng Chen, Long Chen

Abstract:

Clothing fashion represents a human’s aesthetic appreciation towards everyday outfits and appetite for fashion, and it reflects the development of status in society, humanity, and economics. However, modelling fashion by machine is extremely challenging because fashion is too abstract to be efficiently described by machines. Even human beings can hardly reach a consensus about fashion. In this paper, we are dedicated to answering a fundamental fashion-related problem: what image feature best describes clothing fashion? To address this issue, we have designed and evaluated various image features, ranging from traditional low-level hand-crafted features to mid-level style awareness features to various current popular deep neural network-based features, which have shown state-of-the-art performance in various vision tasks. In summary, we tested the following 9 feature representations: color, texture, shape, style, convolutional neural networks (CNNs), CNNs with distance metric learning (CNNs&DML), AutoEncoder, CNNs with multiple layer combination (CNNs&MLC) and CNNs with dynamic feature clustering (CNNs&DFC). Finally, we validated the performance of these features on two publicly available datasets. Quantitative and qualitative experimental results on both intra-domain and inter-domain fashion clothing image retrieval showed that deep learning based feature representations far outweigh traditional hand-crafted feature representation. Additionally, among all deep learning based methods, CNNs with explicit feature clustering performs best, which shows feature clustering is essential for discriminative fashion feature representation.

Keywords: convolutional neural network, feature representation, image processing, machine modelling

Procedia PDF Downloads 139

Authors: Mahdi Allaoua Seklab, Süleyman BaşTürk

Abstract:

In the quest to enhance coastal environmental health, this study introduces a fully autonomous beach cleaning machine, a breakthrough in leveraging green energy and advanced artificial intelligence for ecological preservation. Designed to operate independently, the machine is propelled by a solar-powered system, underscoring a commitment to sustainability and the use of renewable energy in autonomous robotics. The vehicle's autonomous navigation is achieved through a sophisticated integration of LIDAR and a camera system, utilizing an SSD MobileNet V2 object detection model for accurate and real-time trash identification. The SSD framework, renowned for its efficiency in detecting objects in various scenarios, is coupled with the lightweight and precise highly MobileNet V2 architecture, making it particularly suited for the computational constraints of on-board processing in mobile robotics. Training of the SSD MobileNet V2 model was conducted on Google Colab, harnessing cloud-based GPU resources to facilitate a rapid and cost-effective learning process. The model was refined with an extensive dataset of annotated beach debris, optimizing the parameters using the Adam optimizer and a cross-entropy loss function to achieve high-precision trash detection. This capability allows the machine to intelligently categorize and target waste, leading to more effective cleaning operations. This paper details the design and functionality of the beach cleaning machine, emphasizing its autonomous operational capabilities and the novel application of AI in environmental robotics. The results showcase the potential of such technology to fill existing gaps in beach maintenance, offering a scalable and eco-friendly solution to the growing problem of coastal pollution. The deployment of this machine represents a significant advancement in the field, setting a new standard for the integration of autonomous systems in the service of environmental stewardship.

Keywords: autonomous beach cleaning machine, renewable energy systems, coastal management, environmental robotics

Procedia PDF Downloads 27

Authors: Matthew Montebello

Abstract:

The way e-learning effectiveness has been notoriously measured within an academic setting is by comparing the e-learning medium to the traditional face-to-face teaching methodology. In this paper, a simple yet innovative comparison methodology is introduced, whereby the effectiveness of next generation e-learning systems are assessed in contrast not only to the face-to-face mode, but also to the classical e-learning modality. Ethical and logistical issues are also discussed, as this three-way approach to compare teaching methodologies was applied and documented in a real empirical study within a higher education institution.

Keywords: e-learning effectiveness, higher education, teaching modality comparison

Procedia PDF Downloads 387

Authors: Syed Auon Raza, Tahir Mahmood, Syed Basit Ali Bukhari

Abstract:

In power system properly coordinated protection scheme is designed to make sure that only the faulty part of the system will be isolated when abnormal operating condition of the system will reach. The complexity of the system as well as the increased user demand and the deregulated environment enforce the utilities to improve system reliability by using a properly coordinated protection scheme. This paper presents overview of over current relay coordination techniques. Different techniques such as Deterministic Techniques, Meta Heuristic Optimization techniques, Hybrid Optimization Techniques, and Trial and Error Optimization Techniques have been reviewed in terms of method of their implementation, operation modes, nature of distribution system, and finally their advantages as well as the disadvantages.

Keywords: distribution system, relay coordination, optimization, Plug Setting Multiplier (PSM)

Procedia PDF Downloads 399

Authors: Leena Alfarani

Abstract:

Although mobile devices are ubiquitous on university campuses, teacher-readiness for mobile learning has yet to be fully explored in the non-western nations. This study shows that two main factors affect the adoption and use of m-learning among female teachers within a university in Saudi Arabia—resistance to change and perceived social culture. These determinants of the current use and intention to use of m-learning were revealed through the analysis of an online questionnaire completed by 165 female faculty members. This study reveals several important issues for m-learning research and practice. The results further extend the body of knowledge in the field of m-learning, with the findings revealing that resistance to change and perceived social culture are significant determinants of the current use of and the intention to use m-learning.

Keywords: blended learning, mobile learning, technology adoption, devices

Procedia PDF Downloads 464

Authors: Saed Khawaldeh, Mohamed Elsharnouby, Alaa Eddin Alchalabi, Usama Pervaiz, Tajwar Aleef, Vu Hoang Minh

Abstract:

Taxonomic classification has a wide-range of applications such as finding out more about the evolutionary history of organisms that can be done by making a comparison between species living now and species that lived in the past. This comparison can be made using different kinds of extracted species’ data which include DNA sequences. Compared to the estimated number of the organisms that nature harbours, humanity does not have a thorough comprehension of which specific species they all belong to, in spite of the significant development of science and scientific knowledge over many years. One of the methods that can be applied to extract information out of the study of organisms in this regard is to use the DNA sequence of a living organism as a marker, thus making it available to classify it into a taxonomy. The classification of living organisms can be done in many machine learning techniques including Neural Networks (NNs). In this study, DNA sequences classification is performed using Convolutional Neural Networks (CNNs) which is a special type of NNs.

Keywords: deep networks, convolutional neural networks, taxonomic classification, DNA sequences classification

Procedia PDF Downloads 442

Authors: Pooja Khanal, Huaming Zhang

Abstract:

Labeling of issues/bugs, also known as bug classification, plays a vital role in software engineering. Some known labels/classes of bugs are 'User Interface', 'Security', and 'API'. Most of the time, when a reporter reports a bug, they try to assign some predefined label to it. Those issues are reported for a project, and each project is a repository in GitHub/GitLab, which contains multiple issues. There are many software project repositories -ranging from individual projects to commercial projects. The labels assigned for different repositories may be dependent on various factors like human instinct, generalization of labels, label assignment policy followed by the reporter, etc. While the reporter of the issue may instinctively give that issue a label, another person reporting the same issue may label it differently. This way, it is not known mathematically if a label in one repository is similar or different to the label in another repository. Hence, the primary goal of this research is to find the semantic differences between bug labeling of different repositories via machine learning. Independent optimal classifiers for individual repositories are built first using the text features from the reported issues. The optimal classifiers may include a combination of multiple classifiers stacked together. Then, those classifiers are used to cross-test other repositories which leads the result to be deduced mathematically. The produce of this ongoing research includes a formalized open-source GitHub issues database that is used to deduce the similarity of the labels pertaining to the different repositories.

Keywords: bug classification, bug labels, GitHub issues, semantic differences

Procedia PDF Downloads 200

Authors: Muhammad Nawaz, Sandeep N. Kundu, Farha Sattar

Abstract:

Augmented reality sandbox adds new dimensions to education and learning process. It can be a core component of geoscience teaching and learning to understand the geographic contexts and landform processes. Augmented reality sandbox is a useful tool not only to create an interactive learning environment through spatial visualization but also it can provide an active learning experience to students and enhances the cognition process of learning. Augmented reality sandbox can be used as an interactive learning tool to teach geomorphic and landform processes. This article explains the augmented reality sandbox and the constructivism approach for geoscience teaching and learning, and endeavours to explore the ways to teach the geographic processes using the three-dimensional digital environment for the deep learning of the geoscience concepts interactively.

Keywords: augmented reality sandbox, constructivism, deep learning, geoscience

Procedia PDF Downloads 402

Authors: Shan Zhang, Peter Suechting

Abstract:

Predicting trade patterns is critical to decision-making in public and private domains, especially in the current context of trade disputes among major economies. In the past, U.S. recycling has relied heavily on strong demand for recyclable materials overseas. However, starting in 2017, a series of new recycling policies (bans and higher inspection standards) was enacted by multiple countries that were the primary importers of recyclables from the U.S. prior to that point. As the global trade flow of recycling shifts, some new importers, mostly developing countries in South and Southeast Asia, have been overwhelmed by the sheer quantities of scrap materials they have received. As the leading exporter of recyclable materials, the U.S. now has a pressing need to build its recycling industry domestically. With respect to the global trade in scrap materials used for recycling, the interest in this paper is (1) predicting how the export of recyclable materials from the U.S. might vary over time, and (2) predicting how international trade flows for recyclables might change in the future. Focusing on three major recyclable materials with a history of trade, this study uses data-driven and machine learning (ML) algorithms---supervised (shrinkage and tree methods) and unsupervised (neural network method)---to decipher the international trade pattern of recycling. Forecasting the potential trade values of recyclables in the future could help importing countries, to which those materials will shift next, to prepare related trade policies. Such policies can assist policymakers in minimizing negative environmental externalities and in finding the optimal amount of recyclables needed by each country. Such forecasts can also help exporting countries, like the U.S understand the importance of healthy domestic recycling industry. The preliminary result suggests that gravity models---in addition to particular selection macroeconomic predictor variables--are appropriate predictors of the total export value of recyclables. With the inclusion of variables measuring aspects of the political conditions (trade tariffs and bans), predictions show that recyclable materials are shifting from more policy-restricted countries to less policy-restricted countries in international recycling trade. Those countries also tend to have high manufacturing activities as a percentage of their GDP.

Keywords: environmental economics, machine learning, recycling, international trade

Procedia PDF Downloads 168

Authors: Rujia Chen, Ajit Narayanan

Abstract:

Convolutional neural networks (CNN), as typically applied in deep learning, use layer-wise backpropagation (BP) to construct filters and kernels for feature extraction. Such filters are 2D or 3D groups of weights for constructing feature maps at subsequent layers of the CNN and are shared across the entire input. BP as a gradient descent algorithm has well-known problems of getting stuck at local optima. The use of genetic algorithms (GAs) for evolving weights between layers of standard artificial neural networks (ANNs) is a well-established area of neuroevolution. In particular, the use of crossover techniques when optimizing weights can help to overcome problems of local optima. However, the application of GAs for evolving the weights of filters and kernels in CNNs is not yet an established area of neuroevolution. In this paper, a GA-based filter development algorithm is proposed. The results of the proof-of-concept experiments described in this paper show the proposed GA algorithm can find filter weights through evolutionary techniques rather than BP learning. For some simple classification tasks like geometric shape recognition, the proposed algorithm can achieve 100% accuracy. The results for MNIST classification, while not as good as possible through standard filter learning through BP, show that filter and kernel evolution warrants further investigation as a new subarea of neuroevolution for deep architectures.

Keywords: neuroevolution, convolutional neural network, genetic algorithm, filters, kernels

Procedia PDF Downloads 186

Authors: Jingyu Hou

Abstract:

This paper proposes a new teaching and learning approach-project and Module Based Teaching and Learning (PMBTL). The PMBTL approach incorporates the merits of project/problem based and module based learning methods, and overcomes the limitations of these methods. The correlation between teaching, learning, practice, and assessment is emphasized in this approach, and new methods have been proposed accordingly. The distinct features of these new methods differentiate the PMBTL approach from conventional teaching approaches. Evaluation of this approach on practical teaching and learning activities demonstrates the effectiveness and stability of the approach in improving the performance and quality of teaching and learning. The approach proposed in this paper is also intuitive to the design of other teaching units.

Keywords: computer science education, project and module based, software engineering, module based teaching and learning

Procedia PDF Downloads 493

Authors: Christopher Thornton, Niina Kolehmainen, Kianoush Nazarpour

Abstract:

Background: Accelerometers are widely used to measure physical activity behavior, including in children. The traditional method for processing acceleration data uses cut points, relying on calibration studies that relate the quantity of acceleration to energy expenditure. As these relationships do not generalise across diverse populations, they must be parametrised for each subpopulation, including different age groups, which is costly and makes studies across diverse populations difficult. A data-driven approach that allows physical activity intensity states to emerge from the data under study without relying on parameters derived from external populations offers a new perspective on this problem and potentially improved results. We evaluated the data-driven approach in a diverse population with a range of rapidly evolving physical and mental capabilities, namely very young children (9-38 months old), where this new approach may be particularly appropriate. Methods: We applied an unsupervised machine learning approach (a hidden semi-Markov model - HSMM) to segment and cluster the accelerometer data recorded from 275 children with a diverse range of physical and cognitive abilities. The HSMM was configured to identify a maximum of six physical activity intensity states and the output of the model was the time spent by each child in each of the states. For comparison, we also processed the accelerometer data using published cut points with available thresholds for the population. This provided us with time estimates for each child’s sedentary (SED), light physical activity (LPA), and moderate-to-vigorous physical activity (MVPA). Data on the children’s physical and cognitive abilities were collected using the Paediatric Evaluation of Disability Inventory (PEDI-CAT). Results: The HSMM identified two inactive states (INS, comparable to SED), two lightly active long duration states (LAS, comparable to LPA), and two short-duration high-intensity states (HIS, comparable to MVPA). Overall, the children spent on average 237/392 minutes per day in INS/SED, 211/129 minutes per day in LAS/LPA, and 178/168 minutes in HIS/MVPA. We found that INS overlapped with 53% of SED, LAS overlapped with 37% of LPA and HIS overlapped with 60% of MVPA. We also looked at the correlation between the time spent by a child in either HIS or MVPA and their physical and cognitive abilities. We found that HIS was more strongly correlated with physical mobility (R²HIS =0.5, R²MVPA= 0.28), cognitive ability (R²HIS =0.31, R²MVPA= 0.15), and age (R²HIS =0.15, R²MVPA= 0.09), indicating increased sensitivity to key attributes associated with a child’s mobility. Conclusion: An unsupervised machine learning technique can segment and cluster accelerometer data according to the intensity of movement at a given time. It provides a potentially more sensitive, appropriate, and cost-effective approach to analysing physical activity behavior in diverse populations, compared to the current cut points approach. This, in turn, supports research that is more inclusive across diverse populations.

Keywords: physical activity, machine learning, under 5s, disability, accelerometer

Procedia PDF Downloads 210

Authors: Dhanuj M. Gandikota

Abstract:

Sensor-derived three-dimensional (3D) point clouds of trees are invaluable in remote sensing analysis for the accurate measurement of key structural metrics, bio-inventory values, spatial planning/visualization, and ecological modeling. Machine learning (ML) holds the potential in addressing the restrictive tradeoffs in cost, spatial coverage, resolution, and information gain that exist in current point cloud sensing methods. Terrestrial laser scanning (TLS) remains the highest fidelity source of both canopy and below-canopy structural features, but usage is limited in both coverage and cost, requiring manual deployment to map out large, forested areas. While aerial laser scanning (ALS) remains a reliable avenue of LIDAR active remote sensing, ALS is also cost-restrictive in deployment methods. Space-borne photogrammetry from high-resolution satellite constellations is an avenue of passive remote sensing with promising viability in research for the accurate construction of vegetation 3-D point clouds. It provides both the lowest comparative cost and the largest spatial coverage across remote sensing methods. However, both space-borne photogrammetry and ALS demonstrate technical limitations in the capture of valuable below-canopy point cloud data. Looking to minimize these tradeoffs, we explored a class of powerful ML algorithms called Deep Learning (DL) that show promise in recent research on 3-D point cloud reconstruction and interpolation. Our research details the efficacy of applying these DL techniques to reconstruct accurate below-canopy point clouds from space-borne and aerial remote sensing through learned patterns of tree species fractal symmetry properties and the supplementation of locally sourced bio-inventory metrics. From our dataset, consisting of tree point clouds obtained from TLS, we deconstructed the point clouds of each tree into those that would be obtained through ALS and satellite photogrammetry of varying resolutions. We fed this ALS/satellite point cloud dataset, along with the simulated local bio-inventory metrics, into the DL point cloud reconstruction architectures to generate the full 3-D tree point clouds (the truth values are denoted by the full TLS tree point clouds containing the below-canopy information). Point cloud reconstruction accuracy was validated both through the measurement of error from the original TLS point clouds as well as the error of extraction of key structural metrics, such as crown base height, diameter above root crown, and leaf/wood volume. The results of this research additionally demonstrate the supplemental performance gain of using minimum locally sourced bio-inventory metric information as an input in ML systems to reach specified accuracy thresholds of tree point cloud reconstruction. This research provides insight into methods for the rapid, cost-effective, and accurate construction of below-canopy tree 3-D point clouds, as well as the supported potential of ML and DL to learn complex, unmodeled patterns of fractal tree growth symmetry.

Keywords: deep learning, machine learning, satellite, photogrammetry, aerial laser scanning, terrestrial laser scanning, point cloud, fractal symmetry

Procedia PDF Downloads 102

Authors: Changqiao Wu, Guoqing Ding, Xin Chen

Abstract:

In this paper, ways of modeling dynamic measurement systems are discussed. Specially, for linear system with single-input single-output, it could be modeled with shallow neural network. Then, gradient based optimization algorithms are used for searching the proper coefficients. Besides, method with normal equation and second order gradient descent are proposed to accelerate the modeling process, and ways of better gradient estimation are discussed. It shows that the mathematical essence of the learning objective is maximum likelihood with noises under Gaussian distribution. For conventional gradient descent, the mini-batch learning and gradient with momentum contribute to faster convergence and enhance model ability. Lastly, experimental results proved the effectiveness of second order gradient descent algorithm, and indicated that optimization with normal equation was the most suitable for linear dynamic models.

Keywords: dynamic system modeling, neural network, normal equation, second order gradient descent

Procedia PDF Downloads 127

Authors: Wannakarn Likitrattanaporn

Abstract:

The purposes of this investigation were to investigate the effects of applying linguistic principles and teaching techniques in teaching English through experimenting the Adapted English Lessons and to determine the teachers’ opinions as well as students’ opinions towards the Adapted Lessons. The subjects of the study were 5 Thai teachers, who teach English, and 85 Grade 10 mixed-ability students at Triamudom Suksa Pattanakarn Ratchada School, Bangkok, Thailand. The research instruments included the Adapted English Lessons, questionnaires asking teachers’ and students’ opinions towards the Adapted Lessons and the informal interview. The data from the research instruments was collected and analyzed concerning the teachers’ and students’ opinions towards adapting linguistic principles and teaching techniques. Linguistic principles of minimal pair and articulatory phonetics and teaching techniques of mimicry-memorization; vocabulary substitution drills, language pattern drills, reading comprehension exercise, practicing listening, speaking and writing skill and communicative activities; informal talk and free writing are applied. The data was statistically compiled according to an arithmetic percentage. The results showed that the teachers and students have very highly positive opinions towards adapting linguistic principles for teaching and learning phonological accuracy. Teaching techniques provided in the Adapted English Lessons can be used efficiently in the classroom. The teachers and students have positive opinions towards them too.

Keywords: applying linguistic principles and teaching techniques, teachers’ and students’ opinions, teaching English, the adapted English lessons

Procedia PDF Downloads 477

Authors: Mohammed Affanuddin H. Siddique, Jayesh S. Shukla, Chetan B. Meshram

Abstract:

The neural networks are one of the power tools of machine learning. After the invention of perceptron in early 1980's, the neural networks and its application have grown rapidly. Neural networks are a technique originally developed for pattern investigation. The structure of a neural network consists of neurons connected through synapse. Here, we have investigated the different algorithms and cost function reduction techniques for optimization of vertical axis wind turbine (VAWT) rotor blades. The aerodynamic force coefficients corresponding to the airfoils are stored in a database along with the airfoil coordinates. A forward propagation neural network is created with the input as aerodynamic coefficients and output as the airfoil co-ordinates. In the proposed algorithm, the hidden layer is incorporated into cost function having linear and non-linear error terms. In this article, it is observed that the ANNs (Artificial Neural Network) can be used for the VAWT’s optimization.

Keywords: VAWT, ANN, optimization, inverse design

Procedia PDF Downloads 324

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 199

Authors: Claire Xu, Welton Wang, Manasvi Pinnaka, Anqi Pan, Michael Han

Abstract:

Hospitalizations account for one-third of the total health care spending in the US. Early risk detection and intervention can reduce this high cost and increase the satisfaction of both patients and physicians. Due to the lack of awareness of the potential arising risks in home environment, the opportunities for patients to seek early actions of clinical visits are dramatically reduced. This research aims to offer a highly personalized remote patients monitoring and risk assessment AI framework to identify the potentially preventable hospitalization for both acute as well as chronic diseases. A hybrid-AI framework is trained with data from clinical setting, patients surveys, as well as online databases. 20+ risk factors are analyzed ranging from activities, biometric info, demographic info, socio-economic info, hospitalization history, medication info, lifestyle info, etc. The AI model yields high performance of 87% accuracy and 88 sensitivity with 20+ features. This hybrid-AI framework is proven to be effective in identifying the potentially preventable hospitalization. Further, the high indicative features are identified by the models which guide us to a healthy lifestyle and early intervention suggestions.

Keywords: hospitalization prevention, machine learning, remote patient monitoring, risk prediction

Procedia PDF Downloads 230

Authors: Kherafa Abdennasser

Abstract:

The application of Information and Communication Technologies (ICT) to the training area led to the creation of this new reality called E-learning. That last one is described like the marriage of multi- media (sound, image and text) and of the internet (diffusion on line, interactivity). Distance learning became an important totality for training and that last pass in particular by the setup of a distance learning platform. In our memory, we will use an open source platform named Dokeos for the management of a distance training of GPS called e-GPS. The learner is followed in all his training. In this system, trainers and learners communicate individually or in group, the administrator setup and make sure of this system maintenance.

Keywords: ICT, E-learning, learning plate-forme, Dokeos, GPS

Procedia PDF Downloads 477

Authors: Chandu Rathnayake, Isuri Anuradha

Abstract:

Early detection and accurate diagnosis of lung diseases play a crucial role in improving patient prognosis. However, conventional diagnostic methods heavily rely on subjective symptom assessments and medical imaging, often causing delays in diagnosis and treatment. To overcome this challenge, we propose a novel lung disease prediction system that integrates patient symptoms and X-ray images to provide a comprehensive and reliable diagnosis.In this project, develop a mobile application specifically designed for detecting lung diseases. Our application leverages both patient symptoms and X-ray images to facilitate diagnosis. By combining these two sources of information, our application delivers a more accurate and comprehensive assessment of the patient's condition, minimizing the risk of misdiagnosis. Our primary aim is to create a user-friendly and accessible tool, particularly important given the current circumstances where many patients face limitations in visiting healthcare facilities. To achieve this, we employ several state-of-the-art algorithms. Firstly, the Decision Tree algorithm is utilized for efficient symptom-based classification. It analyzes patient symptoms and creates a tree-like model to predict the presence of specific lung diseases. Secondly, we employ the Random Forest algorithm, which enhances predictive power by aggregating multiple decision trees. This ensemble technique improves the accuracy and robustness of the diagnosis. Furthermore, we incorporate a deep learning model using Convolutional Neural Network (CNN) with the RestNet50 pre-trained model. CNNs are well-suited for image analysis and feature extraction. By training CNN on a large dataset of X-ray images, it learns to identify patterns and features indicative of lung diseases. The RestNet50 architecture, known for its excellent performance in image recognition tasks, enhances the efficiency and accuracy of our deep learning model. By combining the outputs of the decision tree-based algorithms and the deep learning model, our mobile application generates a comprehensive lung disease prediction. The application provides users with an intuitive interface to input their symptoms and upload X-ray images for analysis. The prediction generated by the system offers valuable insights into the likelihood of various lung diseases, enabling individuals to take appropriate actions and seek timely medical attention. Our proposed mobile application has significant potential to address the rising prevalence of lung diseases, particularly among young individuals with smoking addictions. By providing a quick and user-friendly approach to assessing lung health, our application empowers individuals to monitor their well-being conveniently. This solution also offers immense value in the context of limited access to healthcare facilities, enabling timely detection and intervention. In conclusion, our research presents a comprehensive lung disease prediction system that combines patient symptoms and X-ray images using advanced algorithms. By developing a mobile application, we provide an accessible tool for individuals to assess their lung health conveniently. This solution has the potential to make a significant impact on the early detection and management of lung diseases, benefiting both patients and healthcare providers.

Keywords: CNN, random forest, decision tree, machine learning, deep learning

Procedia PDF Downloads 73

Authors: Ramzi Rihane, Yassine Benayed

Abstract:

Epilepsy is a chronic neurological disorder characterized by recurrent, unprovoked seizures resulting from abnormal electrical activity in the brain. Timely and accurate detection of these seizures is essential for improving patient care. In this study, we leverage the UK Bonn University open-source EEG dataset and employ advanced deep-learning techniques to automate the detection of epileptic seizures. By extracting key features from both time and frequency domains, as well as Spectrogram features, we enhance the performance of various deep learning models. Our investigation includes architectures such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), 1D Convolutional Neural Networks (1D-CNN), and hybrid CNN-LSTM and CNN-BiLSTM models. The models achieved impressive accuracies: LSTM (98.52%), Bi-LSTM (98.61%), CNN-LSTM (98.91%), CNN-BiLSTM (98.83%), and CNN (98.73%). Additionally, we utilized a data augmentation technique called SMOTE, which yielded the following results: CNN (97.36%), LSTM (97.01%), Bi-LSTM (97.23%), CNN-LSTM (97.45%), and CNN-BiLSTM (97.34%). These findings demonstrate the effectiveness of deep learning in capturing complex patterns in EEG signals, providing a reliable and scalable solution for real-time seizure detection in clinical environments.

Keywords: electroencephalogram, epileptic seizure, deep learning, LSTM, CNN, BI-LSTM, seizure detection

Procedia PDF Downloads 12

Authors: Ashish James, Anusha James

Abstract:

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Ensemble of NNs typically produce good predictions but uncertainty estimates tend to be inconsistent. Inspired by these, this paper presents a framework that can quantitatively estimate the uncertainties by leveraging the advances in transfer learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments with known and unknown distributions show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

Keywords: uncertainty estimation, neural networks, transfer learning, regression

Procedia PDF Downloads 135

Authors: Abdul Basit Kiani, Maryam Kiani

Abstract:

Online developers now have the tools necessary to create online apps that are not only reliable but also highly interactive, thanks to the introduction of JavaScript frameworks and APIs. The objective is to give a broad overview of the recent advances in the area. The fusion of machine learning (ML) and artificial intelligence (AI) has expanded the possibilities for web development. Modern websites now include chatbots, clever recommendation systems, and customization algorithms built in. In the rapidly evolving landscape of modern websites, it has become increasingly apparent that user engagement and personalization are key factors for success. To meet these demands, websites now incorporate a range of innovative technologies. One such technology is chatbots, which provide users with instant assistance and support, enhancing their overall browsing experience. These intelligent bots are capable of understanding natural language and can answer frequently asked questions, offer product recommendations, and even help with troubleshooting. Moreover, clever recommendation systems have emerged as a powerful tool on modern websites. By analyzing user behavior, preferences, and historical data, these systems can intelligently suggest relevant products, articles, or services tailored to each user's unique interests. This not only saves users valuable time but also increases the chances of conversions and customer satisfaction. Additionally, customization algorithms have revolutionized the way websites interact with users. By leveraging user preferences, browsing history, and demographic information, these algorithms can dynamically adjust the website's layout, content, and functionalities to suit individual user needs. This level of personalization enhances user engagement, boosts conversion rates, and ultimately leads to a more satisfying online experience. In summary, the integration of chatbots, clever recommendation systems, and customization algorithms into modern websites is transforming the way users interact with online platforms. These advanced technologies not only streamline user experiences but also contribute to increased customer satisfaction, improved conversions, and overall website success.

Keywords: Javascript, machine learning, artificial intelligence, web development

Procedia PDF Downloads 80

Authors: Aly Elshafei, Daniela Romano

Abstract:

With the development of autonomous vehicles, a human-machine interaction (HMI) system is needed for a safe transition of control when a takeover request (TOR) is required. An important part of the HMI system is the ability to monitor the level of situational awareness (SA) of any driver in real-time, in different scenarios, and without any pre-calibration. Presenting state-of-the-art machine learning models used to measure SA is the purpose of this systematic review. Investigating the limitations of each type of sensor, the gaps, and the most suited sensor and computational model that can be used in driving applications. To the author’s best knowledge this is the first literature review identifying online and offline classification methods used to measure SA, explaining which measurements are subject or session-specific, and how many classifications can be done with each classification model. This information can be very useful for researchers measuring SA to identify the most suited model to measure SA for different applications.

Keywords: situational awareness, autonomous driving, gaze metrics, EEG, ECG

Procedia PDF Downloads 119