13264 research outputs found
Sort by
Reliability Test on Vienna Rectifier for Wide Bandgap Devices in EV Charging Systems
No full textThis study examines the reliability of several electronic components in a Vienna Rectifier
configuration, which is a critical topology for power conversion systems. Component selection has become
increasingly important over the past few years since the power electronics of today demand more efficiency,
power density, and operational reliability. Extreme reliability testing such as temperature cycling, electrical
overload, and long duration of high-frequency operation was a part of the study. GaN MOSFETs had an edge
over Si and SiC MOSFETs in several aspects, such as decreased conduction and switching losses, better
thermal management, and more consistent performance with time. While GaN MOSFETs performed better
in general and especially at high frequencies and temperatures, SiC MOSFETs showed some improvements
over the conventional Si devices. Capacitors, diodes, MOSFETs, and inductors are put to test for reliability
under different stress conditions. The combination of diodes and GaN MOSFETs showed a synergistic
effect in improving system dependability and reducing temperature-induced degradation. This is a significant
result. The combined effects allowed active and passive parts to last longer and function more reliably. These
results open insights into selecting components for systems in the automotive and aerospace industries, which
mostly rely on reliabilit
The impact of AI chatbot adoption on customer experience in e-retailing
No full textDue to the outbreak of the COVID-19 pandemic, the changes in shopping norms from offline to online and rapid development in the field of artificial intelligence (AI) have redefined customer experience. This change has brought lucrative opportunities for organisations to provide better customer service by interacting with customers using chatbots. Thus, this research was conducted to examine the attributes of AI chatbots that affect online customer experience in the e-retailing market. This paper applied theTechnology Acceptance Model (TAM) to design a research model to investigate the relationship between chatbot usability, responsiveness, and online customer experience. A quantitative method was employed to test the research model, and data were collected from an online survey. A total of 101 usable responses were received and examined using SPSS software. The results show a positive relationship between chatbot usability and online customer experience, while no significant relationship is observed between chatbot responsiveness and online customer experience. The findings of this study offer insights for academics, industry practitioners, and policymakers aiming to utilise the potential of AI chatbots to enhance online customer experience and elevate overall customer satisfaction in the e-retail secto
Machine Learning Approaches for Detecting Vine Diseases: A Comparative Analysis
No full textThis study investigates the classification of vine leaf diseases using convolutional neural networks (CNNs), focusing on three major diseases: powdery mildew, caused by fungus Uncinula necator, Red Blotches associated with pathogens such as Phomopsis viticola, Grapevine Leafroll Disease and leafroll associated Grape -linked virus (GLRaV). Accurate diagnosis of these high-risk diseases is critical to vine health and yields. We evaluated the performance of three CNN algorithms—MobileNetV2, ResNet50, and VGG16—by comparing their training and validation accuracies, as well as loss over ten seasons. MobileNetV2 emerged as the most robust model, exhibiting high accuracy and low loss, indicating strong generalizability. ResNet50 showed a steady increase in accuracy, but with high variability, indicating that probabilities with complex models or extended training requirements VGG16 showed notable improvements in training accuracy but encountered difficulties itinvolves consistency during validation, which means overfitting. Although MobileNetV2 proved to be the most efficient for this task, our analysis suggests that replicating ResNet50 and VGG16 can improve their performance. Future research will explore longer training times, larger datasets, and other methods to further improve the generalizability and robustness of this model This work highlights the ability of CNN to detect vine leaves emphasize early diseases andprovide a strategy for sustainable viticultural practices
Implementing Identity-based Signature Schemes for Secure Data Transfer in Cloud Computing Environments
No full textIn this paper, we present the implementation of the Cha-Cheon Identity-Based Signature (IBS) scheme to enhance secure data transfer in cloud computing environments. Cloud computing rely on traditional Public Key Infrastructure (PKI) systems, which is burdened by certificate management infrastructure. The primary focus of this research to simplify key and certificate management by leveraging identity-based elliptic curve cryptography (ECC) within the Cha-Cheon IBS framework. We show that the proposed IBS solution integrates seamlessly with Amazon Web Services (AWS), utilizing services like S3 for secure data storage and KMS for key management. By applying ECC, the Cha-Cheon scheme achieves efficient cryptographic operations with smaller key sizes, resulting in reduced computational overhead, faster key generation, signature creation, and verification times compared to RSA-based systems. We conducted extensive performance evaluations to compare the Cha-Cheon IBS scheme with traditional PKI-based systems. The results demonstrate that our implementation significantly outperforms RSA in terms of key generation, encryption, and signature verification times, especially under increased user loads and data sizes. Moreover, the security analysis confirms the robustness of the Cha-Cheon IBS against key compromise, offering strong resistance to unauthorized access and key revocation issues. The scheme also scales efficiently as the number of users increases, making it ideal for large-scale cloud infrastructures. This research highlights the potential of IBS as a viable alternative to PKI systems, providing a more streamlined and efficient approach to secure data transfers in cloud environments
DebugProGrade: Improving Automated Assessment of Coding Assignments with a Focus on Debugging
No full textn education, the evaluation of programming assignments is challenging, especially to do with the debugging aspect. Self-grading technologies are unable to capture the level of understanding of students and context-bound responses. In light of these, we created DebugProGrade to take what we normally know about grading and improve it with semantic analysis and keyword extraction. DebugProGrade identified 1000 first-year BCA students who in Google Forms provided their answers to evaluate error detection and solution proposals for a basic C programming assignment. For the explanations’ specificity and for the context-level evaluation, the system employs the SBERT embedding, namely, the sentence-transformer bidirectional encoding representations from transformers. We employ the methods with tuned parameters and apply academic criteria to the evaluations performed by them. Other key functionality in DebugProGrade that should be mentioned is the classification of debugging skills into competence levels providing more comprehensive view of student proficiency regarding bugs which remain unaddressed by traditional grading systems –that is the ability to identify or fix bugs. Upon optimizing the Gradient Boosting Regressor algorithm, it gives outstanding results in terms of evaluating and predicting redshift. The mean squared error is very low with a value of MSE = 0.025107 and the MAE is also quite low with the value 0.031335, overall the high R² score 0.99932 shows that the given dataset has been predicted with highaccuracy with reference to the target variable. DebugProGrade precisely flips the paradigm of conventional grading and provides us with even greater understanding of where exactly students are strong
Fiber Break Prevention Using Machine Learning Approaches
No full textModern fiber-optic communication systems are built around optical fiber, which allows data to be sent by emitting infrared light pulses. It is widely used by telecommunications firms and is essential to the smooth transmission of information in internet communication as well as the transmission of telephone signals. Nonetheless, optical fibers intrinsic fragility raises a problem, especially in areas where building projects are taking place. Especially nowadays construction-related impact and crushing pressures can cause physical damage that jeopardizes the fiber optic's integrity. Therefore, this research emphasizes the necessity of taking preventative and mitigating actions to reduce the possibilities of fiber optic breakages in response to these difficulties by using machine learning approaches. The data collected by an optical fiber sensor and a distributed acoustic sensing interrogator unit (DAS).Five tools are used to simulate fiber break threats on the road surface and the fiber optic signalis denoised by using the bandpass Butterworth filter. The filtered data is then transformed into spectrogram representation and trained by using the machine learning approaches. The results of the experiments in the research achieves the accuracy 99.78%which is a high accuracy which can be potentially applied in classifying the signals of the tools and preventing the breakageof the fiber optic cables
Personalized Drug Recommendation System Using Wasserstein Auto-encoders and Adverse Drug Reaction Detection with Weighted Feed Forward Neural Network (WAES-ADR) in Healthcare
No full textIn recent years, the use of deep learning approaches in healthcare has yielded promising results in a variety of fields, most notably in the detection of adverse drug reactions (ADRs) and drug recommendations. This paper promises a breakthrough in this field by using Wasserstein autoencoders (WAEs) for personalized medicine recommendation and ADR detection. WAEs' capacity to manage complex data distributions and develop meaningful latent representations makes them ideal for modeling heterogeneous healthcare data. This study intends to improvise the precision and efficiency of drug recommendation systems while also improving patient safety by combining WAEs and early ADR detection strategies. Previous research has used social media data for pharmacovigilance, drug repositioning, and other machine learning algorithms to detect ADRs. However, our proposed methodology offers a novel perspective by combining Wasserstein autoencoders with ADR detection methods, outperforming existing approaches. Preliminary results show that the proposed methodology surpasses current methodologies, with much greater accuracy in ADR identification and medicine recommendation. In particular, the proposed model achieves an ADR detection accuracy of 96.04%, which is 15% higher than the most sophisticated techniques, with considerable improvements in precision, recall, and accuracy metrics. In conclusion, our study seeks to develop customized medicine in healthcare, perhaps leading to dramatically improved patient outcomes and safety
Diabetes Risk Prediction using Shapley Additive Explanations for Feature Engineering
No full textDiabetes is prevalent globally, expected to increase in the next few years. This includes people with different types of diabetes including type 1 diabetes and type 2 diabetes. There are several causes for the increase: dietary decisions and lack of exercise as the main ones. This global health challenge calls for effective prediction and early management of the disease. This research focuses on the decision tree algorithm utilization to predict the risk of diabetes and model interpretability with the integration of SHapley Additive exPlanations (SHAP) for feature engineering. Random forest and gradient boosting models were developed to identify the risk factors and compare the prediction with the decision tree model. The performance of these classifiers was evaluated using the metrics for accuracy, f1-score, precision, and recall. Understanding the features that drive predictions can enhance clinical decision-making as much as predictive accuracy. With the use of a comprehensive dataset having 520 instances with 17 features including the target output, the proposed decision tree model had an accuracy of 97%. The decision tree model’s categorical variables enable straightforward data visualization. The SHAP tool was applied to interpret the model’s prediction after developing the model. This is crucial for healthcare practitioners as it provides specific health metrics to identify high-risk diabetic patients. Preliminary results indicate that a combination of polyuria, polydipsia, and age are predictors of diabetes risk. This study highlights the benefits that the integration of SHAP and decision trees algorithm provides predictive capability and transparent model interpretability. It also contributes to the growing body of literature on machine learning in the healthcare industry. The results advocate for the application of this methodology in clinical settings for prediction fostering trust between the approach and practitioners and patients alike
Machine Learning Model for Assessing Human Well-being Using Brain Wave Activities
No full textThis study presents a novel machine learning approach to assess human well-being through the analysis of brain wave activities. We developed a Random Forest classifier to categorize brain wave patterns into three states of well-being: good, normal, and bad. Using synthetic data simulating electroencephalography (EEG) readings, our model achieved an overall accuracy of 96.17%. The feature importance analysis revealed that alpha waves (34%) and beta waves (29%) were the most significant predictors of well-being states, which aligns with existing neuroscientific literature linking alpha activity to relaxation and beta activity to cognitive engagement. The confusion matrix demonstrated the model's particular strength in distinguishing between optimal and suboptimal well-being states, with no misclassifications between these extremes. ROC curve analysis further confirmed excellent discriminative ability across all three classes, with AUC values ranging from 0.984 to 0.999. The study demonstrates the potential of machine learning in interpreting complex neurophysiological data for personalised health monitoring, potentially enabling real-time assessment and intervention strategies. While promising, the use of synthetic data necessitates further validation with real-world EEG recordings. This research contributes to the growing field of computational neuroscience and its applications in mental health and well-being assessment, potentially paving the way for more objective and personalised mental health interventions. Future directions include incorporating temporal dynamics, accounting for individual variability, and integrating multiple data sources for a more holistic approach to well-being assessment
Factors Affecting Vietnamese Young People’s Impulsive Purchasing Intention on Live-Streaming Commerce
No full textThis paper examines the factors affecting Vietnamese young people’s impulsive purchasing intention in the live-streaming commerce environment. Adopting the S-O-R research model with influencing factors is the Streamer’s Attractiveness (AT), Streamer’s Trustworthiness (TR), Streamer’s Expertise (EP), Perceived Price (PP), Product Usefulness (PU), and Facility Condition (FC). The mediating variables, or the O elements, are Perceived Enjoyment (PCE) and Perceived Usefulness (PCU). Lastly, the response that buyers deliver is Impulsive Purchasing Intention (IPI). The research focused on young Vietnamese people, particularly Millennials and Generation Z, born from 1980 to 2006 (18 to 44 years old). The quantitative research used a snowball sampling technique with a total of 291 qualified surveys. The data was processed and analyzed with the assistance of SPSS version 22 and SmartPLS 4. After thorough analysis, it is proven that perceived enjoyment and perceived usefulness have a positive influence on impulsive purchasing intention; streamer’s attractiveness and trustworthiness, as well as perceived price, have a positive impact on perceived enjoyment and indirectly impact impulsive purchasing intention; product usefulness and facility condition have a positive influence on perceived usefulness and indirectly impact impulsive purchasing intention. However, the streamer’s expertise and perceived price do not impact perceived enjoyment and usefulness, respectively. The study found that impulsive buying intention is often triggered by emotional arousal, yet consumers still care about product quality and usefulness. The proposed model has been verified in the Vietnamese context and delivers practical insights for companies and marketers