Journal of Informatics and Web Engineering

Editorial Preview for February 2025 Issue

Su-Cheng Haw — Fri, 14 Feb 2025 00:00:00 +0800

Effective from Volume 3, JIWE has transitioned to a triannual publication release effort. Specifically, releases occur each February, June, and October. This change would thus ensure steady and timely publication of research articles in the fast-changing domains of informatics and web engineering. This issue contains a diverse collection of 24 papers that demonstrate the recent developments and innovative applications in various fields such as Information Systems (IS), Web Technologies, Artificial Intelligence (AI), Machine Learning (ML), Data Mining (DM), Blockchain, IoT, Cybersecurity, Healthcare and Software Engineering that persist in moulding the digital landscape.

Comprehensive Insights into Smart Contracts: Architecture, Sectoral Applications, Security Analysis, and Legal Frameworks

Fri, 14 Feb 2025 00:00:00 +0800

Most conventional contract systems have issues with middlemen, drawn-out implementation procedures, fraud risk, and human error. Considering this, the project uses smart contract technology to provide a decentralized, automated, and safe solution in an effort to address such inefficiencies and the trust issues they raise. Smart contracts enable self-execution of contracts whose conditions are expressed explicitly in lines of code by presenting solutions using blockchain technology. The concept behind a smart contract is that each party may carry out their portion of the duties without depending on a third party and the contract will automatically execute in the meantime. This automation significantly reduces transaction costs while simultaneously improving security and transparency. With the use of this underlying technology, smart contracts may be used to directly code parties' compliance with their duties under the agreement and the blockchain will keep an immutable record of every transaction. For smooth and dependable transactions, smart contracts offer a dependable and effective substitute for conventional contract methods. Furthermore, integrating smart contracts with cutting-edge technologies like machine learning and artificial intelligence could improve decision-making and accelerate operations in a variety of sectors. Their application extends beyond financial transactions to areas such as supply chain management, energy trading, and healthcare, showcasing their versatility. Despite these advantages, issues like energy consumption, scalability, and regulatory compliance still need creative solutions. Ongoing research and development aim to address these issues, fostering the evolution of smarter, more sustainable contract systems. By leveraging these advancements, smart contracts keep opening the door for a revolution in the digital economy that will increase productivity and confidence.

Predicting Short-Range Weather in Tropical Regions Using Random Forest Classifier

Sellappan Palaniappan, Rajasvaran Logeswaran, Anitha Velayutham, Bui Ngoc Dung — Fri, 14 Feb 2025 00:00:00 +0800

In this paper, we present a Random Forest classifier machine learning model for predicting short-range weather in in tropical regions like Malaysia. Our model uses environmental factors such as temperature, humidity, wind speed, and cloud cover to predict weather conditions like clear skies, rain, and thunderstorms. Tropical weather, influenced by high humidity, fluctuating temperatures, and frequent rainfall, present unique challenges for forecasting accurately. To address these challenges, we trained a Random Forest classifier on a synthetic (simulated) dataset comprising 1,500 samples, each representing a specific weather scenario. Our model achieved an accuracy of 98.66% in predicting short-term weather conditions, identifying cloud cover, precipitation intensity, and humidity as the most influential factors. Our model’s high accuracy demonstrates its potential for predicting short-range weather conditions in tropical regions. Potential applications of the model spans sectors like agriculture, energy, tourism, disaster management, and public health. In agriculture, the model can be used to optimize irrigation schedules and crop management. In the energy sector, it can be used to optimize energy production and distribution. In disaster management, it can alert residents of impending bad weather, so they are more prepared. In the health sector, it can provide timely weather alerts and assist those who are more prone to arthritis and migraine attacks. We can enhance the model by using real-world data and regional customization.

A Comparative Study of Oracle ERP Netsuite and Microsoft Dynamics 365 Contributions to Contemporary Business Development in India

Padmanabhan Subramanian, Ponmalar S — Fri, 14 Feb 2025 00:00:00 +0800

ERP systems centrally provide support to a company's business operations and are capable of providing solutions in the area of resource management, process streamlining, and making data-driven decisions. Acceptance of ERP systems is growing in India as companies begin to become more efficient and competitive. Among the most prominent players are Oracle ERP Netsuite and Microsoft Dynamics 365, both holding unique attributes which pose a challenge for businesses when choosing the right system. The aim of this paper of study is to compare between Oracle ERP Netsuite and Microsoft Dynamics 365 by exploring their contribution to business development in India. With respect to the implementation complexity, user satisfaction, ROI, and overall business impact, this research study weighs the merits and demerits of each platform according to India. Although high-end multinationals prefer it for its strength and integrated features, the SME prefers Microsoft Dynamics 365 because of its flexibility and smooth integration with other products of Microsoft. Basing the conclusion drawn from the afore findings, the study does provide recommendations to the Indian business in the choice of the most appropriate ERP system. Thus, valuable inputs into the understanding of the adoption of ERP in India are expected from this article.

Improved Accuracy for Heart Disease Diagnosis Using Machine Learning Techniques

Neeraja Joshi, Tejal Dave — Fri, 14 Feb 2025 00:00:00 +0800

This work primarily focuses on diagnosis of heart disease before explicit visit to the expert doctor. Machine learning based systems have been found useful in medical diagnosis applications because of their ability to learn human like expertise and to utilize acquired knowledge for diagnosis. This work is performs classification of heart disease utilizing subject’s vital parameters. Pathological laboratory results available after testing are not understood by common people and patients have to wait till they visit expert doctors for inference. In this paper, traditional methods like linear regression to various machine learning based systems including back propagation neural network, support vector machine(SVM) and k-nearest neighbor are developed for heart diseases classification. The proposed system transforms sensor inputs to stroke stage classification. With a view to ascertain the efficacy of proposed system, performances of all methods are compared on standard Cleveland database and with similar work. Simulation results show 100 percent correct diagnosis and henceforth robustness of SVM based approaches for test data given.

Enhancing Financial Literacy: A Progressive Web Application Approach for Malaysian Youth

Jun-Xuan Kok, Sin-Ban Ho, Chuie-Hong Tan — Fri, 14 Feb 2025 00:00:00 +0800

Financial management is a crucial skill that individuals of all age ranges should acquire and master. It offers a transparent view of our financial status, enabling us to comprehend where our expenses are directed and manage every facet of our finances. Studies have indicated that Malaysian youth lack understanding in financial management. Nowadays, with so many people using the internet, we have the opportunity to share this expertise with a larger audience. Providing easily accessible materials for learning about and managing personal finances is essential to comprehending people's individual financial circumstances. In light of this, the purpose of this article is to develop a useful, progressive web system for personal finance management that makes budgeting and cost tracking easier. This personal finance management system will be implemented using the Tailwind Cascading Style Sheets, Firebase, and React framework as development tools. React frameworks are used due to their ability to produce dynamic user interfaces. To sum up, this user-friendly interface mechanism enables the formulation of budgets and the tracking of expenses. It also consists of other features for data visualization, such as charts. This research has the potential to add some additional enhancements to its existing functionality. For instance, it could introduce a predictive budgeting function that uses historical user spending data to perform predictive analysis.

Social Engineering Threat Analysis Using Large-Scale Synthetic Data

Fri, 14 Feb 2025 00:00:00 +0800

We frequently hear news about compromised systems, virus attacks, spam emails, stolen bank account numbers, and loss of money. Safeguarding and protecting digital assets against these and other cyber-attacks are extremely important in our digital connected world today. Many organizations spend substantial amounts of money to protect their digital assets. One type of cyber threat that is rampant these days is social engineering attacks that work on human psychology. These attacks typically persuade, convince, trick and threaten naïve and innocent individuals to divulge sensitive information to the attackers. Consequently, traditional approaches have not been effective or successful in preventing these attack types. In this paper, we propose a machine learning model to detect these types of threats. The model is trained using a large synthetic dataset of 10,000 samples to simulate various types of real-world social engineering threats such as phishing, spear phishing, whaling, vishing, smishing, baiting, and pretexting. Our analysis on attack types, patterns, and characteristics revealed interesting insights. Our model achieved an accuracy of 0.8984 and an F1 score of 0.9253, demonstrating its effectiveness in detecting social engineering attacks. The use of synthetic data overcomes the problem of lack of availability of real-world data due to privacy issues, and is demonstrated in this work to be safe, scalable, ethics friendly and effective.

Hyperledger Fabric Blockchain for Securing the Edge Internet of Things: A Review

Fri, 14 Feb 2025 00:00:00 +0800

Life has become more convenient, efficient, and productive in aspects like homes, healthcare, and other businesses’ due to applied IoT. Nonetheless, the proliferation of IoT has led to enormous data production, which has presented daunting tasks of providing sound protective security solutions. It is crucial to address the above challenges in order to protect the data assets in IoT systems. This work deals with the concern on how to extend Hyperledger Fabric to IoT, this being a very crucial aspect in allowing for secure techniques in the collection, storage and sharing of data. Hyperledger Fabric offers advanced capabilities of smart contract and offers authorized and conditional access control, and this feature alone is enough to fulfil the IoT security needs. Therefore, this paper introduces a new solution related to the existing security problems in permissioned blockchain architecture, which is based on a four-tier architecture integrated into the Hyperledger Fabric platform. As for architecture, our proposal divides it into four layers: the application layer, the blockchain platform layer, the cloud storage layer and the IoT device layer, to tackle the problems of security and efficiency of the whole process. To establish the proposed solution, a data literature review has been carried out to collate the analysis and apply the data from the different studies. This paper shows that the deployment of blockchain technology in IoT environments also optimises IoT systems in terms of security, efficiency, and capacity in terms of IoT applications. As more and more IoT solutions appear and evolve, the usage of block chain technology as a whole and the specific Hyperledger Fabric platform in particular opens the way to overcoming the rather fluid issues of this constantly developing sphere.

Machine Learning Approaches for Detecting Vine Diseases: A Comparative Analysis

Waheed Ahmad, Eshill Azhar, Maham Anwar, Sarah Ahmed, Tayyaba Noor — Fri, 14 Feb 2025 00:00:00 +0800

This 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 it involves 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 data sets, 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 and provide a strategy for sustainable viticultural practices.

Implementing Identity-based Signature Schemes for Secure Data Transfer in Cloud Computing Environments

Paul Osinuga, Ji-Jian Chin, Terry Shue Chien Lau — Fri, 14 Feb 2025 00:00:00 +0800

In 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.

IoT-Based Nerve Stimulator for Women’s Safety

K Revathi, W Gracy Theresa — Fri, 14 Feb 2025 00:00:00 +0800

Women deserve a right to live free from intimidation, mistreatment, unfair treatment, and eliminating hurdles from a hazardous workplace can help them reach their maximum potential both personally and as contributions to economies, societies, and the workplace. Physical, emotional, and environmental safety have a variety of effects on wellbeing, including stress management, emotional stability, and physical health. The Women Safety System with Nerve Stimulator is a comprehensive system that integrates essential components for women's safety using an Arduino Uno microcontroller. It has an SOS button for emergency activation, a temperature sensor for environmental monitoring, a pulse oximeter for tracking health, a buzzer for auditory warnings, a relay for controlling other devices, a 5V DC vibration motor for tactile feedback, and a rechargeable battery for mobility. In an emergency, the Nerve Stimulator draws attention from nearby by producing controlled vibrations, which improves security. Ongoing global positioning system (GPS) monitoring guarantees accurate position awareness, and a buzzer warns users and anyone in the vicinity of possible hazards. The relay for controlling remote equipment adds to the system's versatility, while the SOS button triggers emergency actions like GPS location sharing. Rechargeable batteries provide continuous functioning, which in turn guarantees the dependability and efficacy of the system in protecting women's safety.

Lung Tumor Segmentation in Medical Imaging Using U-NET

Fri, 14 Feb 2025 00:00:00 +0800

Tumors are a deadly condition often triggered by a range of abnormal modifications and genetic abnormalities. Early tumor diagnosis is essential due to the highly concerned nature of the disease. Early detection and treatment of tumors can significantly reduce mortality rates. This paper presents a model for tumor segmentation in medical imaging that uses the U-NET architecture to increase precision. The model’s encoding and decoding processes have been applied with skip connections to boost performance while simplifying model training. Images were cropped around the lower abdominal regions, and all images used in the study were then resized to 256*256 pixels for standardization. The proposed model deals with the class imbalance using data augmentation and oversampling. The experiments achieved a dice score of 0.853±0.02; F-score of 0.905±0.02; and a sensitivity of 0.897±0.02, compared with various existing models. As part of the model’s application, the pytorch-lightning library is used to successfully identify lung cancer scans, thereby proving to be a precise and efficient method of tumor identification. Accordingly, the study emphasizes the accuracy and speed of the applied model as a useful instrument for the earliest detection of tumors. The proposed approach helps to achieve more relevant and accurate segmentation and thus provides enhancements in medical images analysis if such challenges as an imbalance data set are well handled.

A Hybrid Deep Learning VGG-16 Based SVM Model for Vehicle Type Classification

Muhammad Imran, Jafar Usman , Muntazir Khan, Abdullah Khan — Fri, 14 Feb 2025 00:00:00 +0800

Car classification is important in daily life because there are many distinct types of automobiles made by various manufacturers. Although there are numerous methods for classifying autos, machine learning technologies have not been widely utilized, resulting in low accuracy levels. The goal of this paper is to create a machine learning system that is especially made to categories models of two Pakistan's top automakers, Toyota, and Honda. Ten Toyota models such as Avalon, Land Cruiser, Camry, Corolla, C-HR, Highlander, Prius, Tundra, RAV4, and Yaris and a dataset of Honda automobiles, which also includes 10 models (Accord, Civic, CR-V, Fit, HR-V, Insight, Odyssey, Passport, Pilot, and Ridgeline), are used to evaluate the model's performance. A deep learning-based VGG integrated with support vector machine (SVM) is proposed, utilizing a dataset from Kaggle.com, providing high-definition images for multiple classes. Comparisons with other models such as VGG16, AlexNet, and Convolutional Neural Network (CNN) reveal that the suggested model (VGG16 + SVM) achieves superior accuracy. For the Toyota dataset, the proposed model achieves 99% accuracy, outperforming VGG16 (66%), AlexNet (52%), and CNN (65%). Similarly, for the Honda dataset, the suggested model achieves 98% accuracy, surpassing VGG16 (96%), AlexNet (71%), and CNN (82%). In conclusion, the proposed deep learning-based model demonstrates enhanced accuracy in classifying Toyota and Honda cars, highlighting its effectiveness for image-based classification tasks in the automotive domain.

Early Identification of Parkinson's Disease Using Time Frequency Analysis on EEG Signals

Tanvir Hasib, V Vijayakumar, Ramakrishnan Kannan — Fri, 14 Feb 2025 00:00:00 +0800

Parkinson's Disease (PD) is a progressive neurological disorder. It affects movement and can significantly impact quality of life. Early and accurate diagnosis is crucial for effective management and intervention. Traditional diagnostic methods can be time-consuming and less effective in the early stages of the disease. This study aims to develop an automated approach for identifying PD using time-frequency image analysis of electroencephalogram (EEG) signals. The goal is to enhance diagnostic accuracy and efficiency, facilitating early detection. EEG signals, often contaminated with artifacts such as eye blinks and muscle movements etc., were first cleaned. Time-frequency images were then plotted from the cleaned signals, and Event-Related Spectral Perturbation (ERSP) plots were extracted. A customized deep learning model was employed to classify the ERSP plots, distinguishing PD patients from healthy controls. The deep learning model achieved an accuracy of 94.64% in separating PD patients from healthy controls. The approach demonstrated robustness against common EEG artifacts, ensuring reliable PD detection. The model's architecture was specifically designed to handle the complexities of EEG data, making it a powerful tool for PD classifications. This study highlights the potential of integrating deep learning with EEG analysis to explore PD diagnosis. The proposed method is faster and more accurate than traditional approaches, enabling early detection and timely intervention. By reducing the time required for analysis and enhancing diagnostic accuracy, this approach can significantly improve patient outcomes and support better management of Parkinson's Disease.

DebugProGrade: Improving Automated Assessment of Coding Assignments with a Focus on Debugging

Amit Patel, Hardik Joshi — Fri, 14 Feb 2025 00:00:00 +0800

In 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 high accuracy 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.

Optimising Phishing Detection: A Comparative Analysis of Machine Learning Methods with Feature Selection

Mohamad Asraf Daniel, Siew-Chin Chong, Lee-Ying Chong, Kuok-Kwee Wee — Fri, 14 Feb 2025 00:00:00 +0800

Phishing is an act of cybersecurity attack that tricks people into sharing sensitive data. Due to the inefficiency of the current security technologies, researchers have been paying much attention to employing machine learning methods for phishing detection lately. In our proposed solution, the effectiveness of machine learning techniques with feature selection techniques for phishing detection is investigated. To be specific, Random Forest (RF) and Artificial Neural Network (ANN) are integrated with feature selection techniques, Principal Component Analysis (PCA) and Recursive Feature Elimination (RFE). The goal was to identify and classify the model with the highest accuracy. The experiments were evaluated using a dataset of 4,898 phishing sites and 6,157 legitimate sites, with the phishing data sourced from Kaggle.com. Our experiments demonstrate that the combination of RF model with PCA achieved 95.83% accuracy, while the ANN model with PCA reached 95.07% accuracy. The incorporation of PCA and RFE not only optimised the models' predictive performance but also improved computational efficiency. Overfitting can also be reduced. The experimental results also demonstrate that the proposed ANN with PCA method outperforms the state-of-the-art methods. Consequently, this research highlights the potential of combining advanced feature selection techniques with machine learning algorithms to develop robust solutions for phishing detection. Yet, this undoubtedly contributes to a safer internet environment.

Integrating Moral Values in AI: Addressing Ethical Challenges for Fair and Responsible Technology

Khushboo Shah, Hiren Joshi, Hardik Joshi — Fri, 14 Feb 2025 00:00:00 +0800

Today, Artificial Intelligence (AI) has become an integral part of our day-to-day life. From personal task to professional life everywhere we need AI. All the sectors like - transport, education, healthcare, agriculture, we find AI everywhere. Each coin has two side, similarly AI has its own pros and cons. Main challenge with AI is ethics. There is no doubt in the work efficiency of AI but ultimately, it’s a machine without emotions hence whatever the decision it takes it purely without ethical values. Sometimes, this type of decision may lead to disasters, especially in the industry where human life is involved e.g. healthcare. The focus of this paper is to integrate moral values into AI systems. It also talks about different ethical frameworks like utilitarianism, deontology and virtue ethics along with the state-of-art work and knowledge gaps. This research also explored various case studies where AI implemented with ethics. Integration of moral values with AI has many issues like bias, transparency and accountability. Here author has proposed a new model named Ethical Alignment Algorithm (EAA). This model helps to integrate ethics with AI step-by-step. This approach will help AI to make fair, sensible and responsible decisions. This paper will also help researchers to work with a multidisciplinary approach. Different subject specialists can come together and make AI policies with ethics. EAA has the potential to make the AI systems not only advanced but with high moral values. In the end, the paper highlights current AI development and future scopes. The main aim of this research is to promote justice and fairness in AI decisions for the overall well-being of society.

Creating an Android-based Calisthenics Application to Assist Students in Improving Their Physical Fitness

Restyandito, Narendra Poetra Wisnoewardhana, Danny Sebastian — Fri, 14 Feb 2025 00:00:00 +0800

College students, particularly those heavily involved in coursework, frequently do not prioritize physical fitness. Regular exercise is essential for preserving physical fitness and facilitating demanding academic tasks. Although there are other fitness programs available, such as GYM, jogging, CrossFit, and Yoga, users sometimes fail to make full use of them because the content is confined to exercise videos and descriptions. This matter highlights the progress of the Android application Kali Tech, which specifically concentrates on organizing and documenting calisthenics workouts. This program employs the concept of gamification by utilizing student achievement levels to encourage students to be diligent in doing exercise. The application was developed via the Software Development Life Cycle (SDLC) Prototyping methodology in order to fulfill user requirements by incorporating features that promote regular utilization. Kali Tech underwent a one-month testing period, during which data on the responders' blood pressure was also gathered. The data analysis demonstrated that the utilization of the Kali Tech application resulted in an enhancement of the participants' physical fitness, as seen by the blood pressure graphs nearing the standard levels when using the app. The conclusion was further supported by the results of an Independent Sample T-Test analysis and the visual representations of blood pressure graphs, which demonstrated the consistent levels of respondents' blood pressure.

Machine Learning Model for Predicting Net Environmental Effects

Sellappan Palaniappan, Rajasvaran Logeswaran , Shapla Khanam, Zhang Yujiao — Fri, 14 Feb 2025 00:00:00 +0800

Environmental sustainability is a global challenge in the face of increasing incidences of disasters affecting communities worldwide. This requires predicting net environmental effects accurately. While various approaches exist, we need more sophisticated prediction models that account for both environmental and social factors. This study presents a proof-of-concept machine learning model for predicting net environmental effects using synthetic data. We developed a multiple linear regression model incorporating nine key features: renewable energy usage, carbon emissions, air quality index, water usage, biodiversity impact, land use, public awareness, and environmental attitudes. We generated a synthetic dataset of 1000 samples using probability distributions and correlation structures derived from environmental literature and expert knowledge. Our model achieved an R-squared value of 0.67, demonstrating moderate predictive power. Feature importance analysis revealed renewable energy usage (coefficient = 0.71) and public awareness (coefficient = 0.44) as significant positive factors influencing environmental outcomes. Model validation included residual analysis and feature importance assessment, with results suggesting reasonable performance within linear regression constraints. Limitations of our study include reliance on synthetic data, assumption of linear relationships between variables, and limited environmental factors. Notwithstanding, our findings provide insights for environmental policymaking, particularly regarding renewable energy adoption and public awareness campaigns. Future work could focus on incorporating real-world data, exploring non-linear modeling approaches, and expanding the feature set to capture more complex environmental interactions. Our research contributes to data-driven environmental assessment by demonstrating the feasibility of combining both physical and social factors in predictive modeling.

Fiber Break Prevention Using Machine Learning Approaches

Fri, 14 Feb 2025 00:00:00 +0800

Modern 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 signal is 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 breakage of the fiber optic cables.

Migraine Generative Artificial Intelligence based on Mobile Personalized Healthcare

Michelle Ting-Ting Yong, Sin-Ban Ho, Chuie-Hong Tan — Fri, 14 Feb 2025 00:00:00 +0800

Migraine is a complicated genetic disorder characterized by episodes of moderate-to-severe headaches that are usually unilateral and are frequently accompanied by nausea and increased sensitivity to sound and light. A migraine attack induces intense pain, hindering an individual from engaging in daily activities and potentially persisting for hours or even days. By the growth of the Internet of Things, we have new opportunities to try to apply it to the medical field. To identify the origin of a migraine, specialists need access to a patient's medical history and a comprehensive understanding of migraine symptoms for effective treatment. Determining the true source of a migraine may take longer than expected. Nowadays, solving problems through the Internet has become very common in people's lives. Hence, the objective of this research is to create a mobile personalized healthcare mechanism that can assist migraine patients in promptly receiving optimal and precise treatment. Moreover, this research would establish a user-friendly interface that facilitates the presentation of compelling evidence regarding the repercussions of patient health issues. Additionally, machine learning training was designed to treat patients based on relevant demographic characteristics of the healthcare treatment, such as medical history and reports provided. Therefore, this paper can provide insights into the state of art in mobile based personalized healthcare system to recommend future paths, for integration and investigation to improve online migraine platforms for a wide range of migraine patients.

Exploration of The Impact of Cyber Situational Awareness On Small and Medium Enterprises (SMEs) in Malaysia

Tan Chee Keong, Sofiah Kadar Khan, Umar Farooq Khattak — Fri, 14 Feb 2025 00:00:00 +0800

The objective of this study is to explore the cyber situational awareness (CSA) level among the employees of small and medium-sized enterprises (SME) in Malaysia, by extending Endsley's situation awareness (SA) theory. It is crucial to understand the level of cyber situational awareness among employees as it sheds light on how well the employees understand the cyber threats and if they can handle them effectively. Literature has reviewed that SMEs are subject to a greater danger of cyber-attacks. Therefore, employees' awareness of cyber situations is of the utmost significance in studying cyber security. A convenient non-probability sampling method was chosen due to less expensive to deploy and increase the efficiency of data collection processes. IBM SPSS was used to conduct descriptive exploration data analysis that provides insight into the employee's current CSA by categorizing the employees into good, average, and poor understanding of the CSA. A total of 443 surveys were collected in the study, the findings reveal that most employees are not adequately aware of cyber situations, and employees understand the need to adhere to cyber security policy within the organization but fail to comply. The study contributes to practical domain by identifying the current level of CSA, SMEs should be set forth to create a strong culture of cyber security awareness and compliance and prioritize cyber security as part of the organization's culture to improve overall employee engagement and motivation in dealing with cyber threats.

Climate Change Analysis in Malaysia Using Machine Learning

Anishalache Subramanian, Naveen Palanichamy, Kok-Why Ng, Sandhya Aneja — Fri, 14 Feb 2025 00:00:00 +0800

Climate change presents significant challenges to ecosystems, economies, and societies globally. In Malaysia, a tropical country highly dependent on its natural resources, the impacts are evident in altered rainfall patterns, rising temperatures, and extreme weather events. Despite these challenges, many studies still predominantly rely on traditional statistical methods, which limit their capacity for making accurate climate predictions and developing effective policy solutions.This study effectively addresses the existing gap in research by analyzing extensive historical climate data using advanced machine learning (ML) techniques. The primary focus is on accurately forecasting trends in both precipitation patterns and surface air temperature fluctuations. Performance measures like Mean Absolute Error (MAE), Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) are used to assess three ML models: Support Vector Regression (SVR), Random Forest Regression (RFR) and Linear Regression (LR). The findings demonstrate that LR performs better than the other models in forecasting patterns of precipitation and temperature. The results suggest a significant increase in temperature and unpredictable patterns of precipitation, and that poses major implications for agriculture, infrastructure resilience, and water management. Malaysia's climate resilience is improved by this research, which promotes data-driven policymaking by assessing current climate adaptation methods and offering practical ideas.

Path To a Healthy Work-Life Balance: Mobile Application for Work and Personal Life Mastery

Erfan Rahmani, Zarina Che Embi — Fri, 14 Feb 2025 00:00:00 +0800

Drawing insights from diverse organizational methods, this study endeavors to facilitate effective self-development and organization in the face of contemporary demands as solutions for integrating goal tracking, event coordination, and task management within a unified calendar framework in a mobile application. There are three primary objectives of this study: firstly, to explore essential functionalities crucial for addressing the multifaceted challenges of modern life; secondly, to design and develop a mobile application that seamlessly integrates these functionalities; and finally, to evaluate the usability of the application through rigorous testing and feedback mechanisms. Envisaged deliverables include a fully functional mobile application designed to operate on the Android platform. Guided by the principles of agile software development, this study emphasizes continuous improvement and responsiveness to user needs throughout the development process. By adopting an iterative approach, the study aims to ensure the highest quality outcome, thereby enhancing the user experience and maximizing the application's efficacy in promoting work-life balance. Through this comprehensive approach, this study seeks to contribute to the ongoing discourse on work-life balance and offer practical solutions to individuals grappling with the complexities of modern living. By bridging the gap between organizational tools and personal development strategies, this study aspires to empower users in their pursuit of a harmonious and fulfilling lifestyle with a mobile application.

Personalized Drug Recommendation System Using Wasserstein Auto-encoders and Adverse Drug Reaction Detection with Weighted Feed Forward Neural Network (WAES-ADR) in Healthcare

J Omana, P. N Jeipratha , K Devi, S Benila, K Revathi — Fri, 14 Feb 2025 00:00:00 +0800

In 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.