JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Systematic Literature Review: An Early Detection for Schizophrenia Classification Using Machine Learning Algorithms
Get PDFSchizophrenia is a complex mental health disorder that poses significant challenges in diagnosis and treatment due to its multifaceted symptoms, such as hallucinations, delusions, and cognitive impairments. Early detection is crucial for effective intervention, yet traditional diagnostic methods often fail in precision and scalability. This systematic literature review investigates the application of machine learning (ML) algorithms in the early detection and classification of schizophrenia. By synthesizing findings from 40 primary studies, the review highlights the effectiveness of diverse ML models, including Random Forests, Support Vector Machines (SVM), and advanced deep learning techniques like Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. Key datasets such as clinical records, EEG signals, and neuroimaging data were analyzed to evaluate model performance across metrics like accuracy, precision, and sensitivity. Studies demonstrated that hybrid approaches, integrating multiple data sources and deep learning architectures, achieved classification accuracies exceeding 90%, with notable advancements in early-stage diagnosis. However, the review identifies critical challenges, including data quality issues, biases, and limited external validation, which hinder the widespread clinical application of these models. Through a comparative analysis of ML methods and traditional supervised approaches, the study underscores the transformative potential of ML in enhancing diagnostic accuracy and facilitating personalized treatment plans. Addressing current limitations, such as expanding data diversity and improving model interpretability, is essential for translating these findings into practical healthcare solutions. This research contributes to the growing knowledge in ML-driven diagnostics, advocating for its integration into clinical workflows to optimize schizophrenia management
Detecting Distributed Denial-of-Service (DDoS) Attacks Through the Log Consolidation Processing (LCP) Framework
Get PDFOne major problem commonly faced by organizations is a network attack especially if the network is vulnerable due to poor security policies. Network security is vital in protecting not only the infrastructure but most importantly, the data that moves around the network and is stored within the organization. Ensuring a secure network requires a complex combination of hardware including both network and security devices, specialized applications such as web filtering and log management, and a group of well-trained network administrators and highly skilled analysts. This paper aims to present an alternative to the current log management solution. A hindrance to the current log management solution is the difficulty in amalgamating and correlating a vast number of logs with different formats and variables. This paper uses a novel framework called Log Consolidation Processing (LCP) based on the System Information Event Management (SIEM) technology, to monitor the behavior and the fitness of a network. LCP provides a flexible and complete solution to collect, correlate, and analyze logs from multiple devices as well as applications. An experiment testing the effectiveness of LCP in detecting DDoS attacks in a campus network environment was conducted, demonstrating a highly successful rate of detection. Besides threat detection and avoidance through log monitoring and analysis, other benefits of implementing the LCP framework are also included. This paper concludes by mentioning suggested enhancements for the LCP framework
A Prototype of Decentralized Applications (DApps) Population Management System Based on Blockchain and Smart Contract
Get PDFThe Indonesian population reached 270,20 million in 2020. Each resident is equipped with various secret identities. The COVID-19 pandemic has made all activities use technology as a basis, causing residents' identities to be stored digitally. Some applications that keep these identities experience data leaks. However, with the advent of Web3 and its emphasis on decentralization through blockchain, a new era of secure data management is possible. Blockchain, with its inherent security features, ensures that data stored is secure, difficult to damage or lose due to mutual consensus. Every transaction is recorded, making it easy to carry out the audit process. Therefore, this research will design and implement prototype dApps for secure population management, leveraging the superior security of blockchain technology. The initial stage of research is to conduct a literature study. Furthermore, it is to create designs such as system, infrastructure, and activity diagrams. Then do the development of the dApps prototype. The last is testing using OWASP ZAP and cost analysis. A dApps prototype was implemented on a blockchain. Every transaction is recorded and publicly viewable through the Etherscan platform. Other data stored on a blockchain have gone through an AES-256 encryption process with the data owner's account key so that the owner can only see the data. The results of the tests performed show that there is no high-level warning. The cost analysis results show that the most used costs are when deploying smart contracts and making new data. For further development, it is implementing permissionless blockchain and multi-accounts
Architectural Visualization Approach Using Google SketchUp and Lumion on the Development of Maritime Tourism
Get PDFThis study aims to portray the strategy and design of marine tourism development through a data visualization approach using Google SketchUp and Lumion. The type of research conducted is Research and Development (R&D), employing the ADDIE approach (Analysis, Design, Development, Implementation, and Evaluation). The findings of this study reveal that the miniature design of Pulau Sembilan on Larea-rea Island incorporates local cultural themes in the construction of Rulan (Nine House), with a visualization of the roof following the design of the traditional Karampuang house. Additionally, the researcher presents designs concerning the jetties of Larea-rea Island and the product facility designs. Ultimately, contributes to development of Rulan (Nine House) and the efficient land utilization contributes to the region's income enhancement in the tourism sector of Larea-rea Island. It is recommended that future research on marine tourism development should involve a more comprehensive analytical framework that considers social, economic, and environmental aspects. This will help in understanding the overall impacts of marine tourism development. It is also important to investigate the ecological impacts of tourism and come up with effective mitigation strategies to prevent harm to the marine environment. Another interesting research area is to integrate the perspectives of local communities and their participation in the planning and implementation of tourism development. This will ensure the sustainability of such projects and gain community acceptance
Grey Level Differences Matrix for Alcoholic EEG Signal Classification
Get PDFElectroencephalogram (EEG) signals can provide information on abnormalities in a person's brain and characterize brain activity. Brain injury or diseases can manifest as brain disorders. Trauma or the use of specific chemicals or medications, such as alcohol, can result in brain damage. Previous research has demonstrated variations in the patterns of EEG signals between alcohol-using and non-drinking people. Various techniques, including wavelet and entropy, have been developed to detect alcoholic EEG using event-related potential (ERP) testing. This work proposes a feature extraction technique based on texture analysis for the classification of alcohol EEG signals because ERP-measured EEG often involves many channels. An NxM image is thought to be equivalent to an EEG signal with N channels and a recording duration of M samples. The NxM matrix is formed by channelizing the N-channel EEG signal in this investigation. Normalization is then used to get a matrix value of 0-255 or an 8-bit image in the following step. Five features are measured in four directions, and the Grey Level Difference Matrix (GLDM) approach is utilized for feature extraction. Using five grey-level difference matrix (GLDM) features and linear discriminant analysis as a classifier, the maximum accuracy was achieved at 73.3%. Image processing can still be used to increase accuracy even though the final product is less accurate than the earlier technique. The suggested approach can still be adjusted to work with biomedical signals or image processing techniques like the Grey Level Co-occurrence Matrix (GLCM)
Detecting Need-Attention Patients using Machine Learning
Get PDFIn healthcare, detecting patients who need immediate attention is difficult. Identifying the critical variables is challenging in patient detection because human intervention in variable selection is required. Consequently, patients who need immediate attention often experience prolonged waiting times. Researchers have investigated various approaches to identify those who require attention. One of the techniques is leveraging Artificial Intelligence (AI). However, identifying the optimal feature set and predictive model is complex. Therefore, this study has attempted to (i) identify the critical features and (ii) develop and evaluate predictive models in detecting those who need attention. The dataset is collected from one of the healthcare companies. The dataset collected contains 67 variables and 51102 records. It consists of patient information and questionnaires answered by each participant registered in the Selangor Saring Program. Important features were identified in detecting those who need attention on treated data. Multiple classifiers were developed due to their simplicity. The models were evaluated before and after hyperparameter tuning based on accuracy, precision, recall, F1-score, Geometric Mean, and Area Under the Curve. The findings showed that the Stacking Classifier produced the highest accuracy (69.9%) when using the blood dataset. In contrast, Extreme Gradient Boosting achieved the highest accuracy (81.7%) when the urine dataset was used. This work can be extended to explore the incorporation of Points of Interest and geographical data near patients’ residences and study other ensemble models to enhance the performance of detecting those who need attention
The Relationship among Academic Self-Efficacy, Academic Resilience, and Academic Flow: The Mediating Effect of Intensity Using Learning Management System
Get PDFUniversity students can have low academic flow when using a Learning Management System (LMS). Three variables are predicted to correlate with the academic flow (FA) of students who use LMS: academic self-efficacy (ASE), academic resilience (AR), and LMS use intensity (LMSI). This study looks at the link between academic self-efficacy, academic resilience, LMS use intensity, and academic flow among university students who use LMS. This study employs a quantitative approach, using correlational approaches and path analysis. Furthermore, 740 Indonesian university students who used LMS participated in this study. This study used the partial least squares-structural equation model (PLS-SEM) to analyze data. This study found that academic resilience and LMS use intensity are both positively and significantly associated with academic flow in university students who use LMS. Furthermore, the current research results show that academic self-efficacy is not directly related to academic flow among university students. Aside from that, the study's findings imply that LMS usage intensity is a deciding variable for academic flow among university students who use LMS and that it can control the link between academic self-efficacy, academic resilience, and academic flow. Academic resilience and LMS use intensity must be considered when improving university students' academic flow using LMS
A Mixed Integer Linear Programming for Exam-Invigilator Assignment Problem: A Case Study at Universiti Pertahanan Nasional Malaysia
Get PDFThe assignment of invigilators for examinations is a complex and challenging task, particularly when faced with numerous factors that must be carefully considered. Critical elements are essential in this process, including staff availability, room capacity, and time constraints, requiring thorough evaluation and coordination. This paper focuses on improving the allocation of invigilators for examinations at Universiti Pertahanan Nasional Malaysia (UPNM). The issue arises when academic staff members responsible for teaching the subject are also assigned as exam invigilators, which conflicts with their primary role of assisting students in addressing their queries during examinations. It is essential to reconsider the distribution of invigilator roles, ensuring that academic staff members can focus solely on providing educational support. In contrast, qualified non-academic staff handle invigilation duties effectively. A mixed-integer linear programming (MILP) model is formulated using the existing examination timetable to solve this problem. The model is solved using a simple algorithm implemented in the XPress MP programming language, resulting in an improved solution that requires less computational effort than the conventional method. This approach offers an alternative and better solution for scheduling examination invigilators at UPNM, ensuring the efficient and effective management of exam procedures while maximizing the utilization of available resources. It can serve as a starting point for future investigations into UPNM's scheduling procedures
Classification of Air Pollutant Index on Data with Outliers and Imbalance Class Problem
Get PDFThe problem of air pollution has become a global issue that has received attention from various countries. Jakarta, Indonesia's capital city, is unavoidable from the same problem. This study will use four parameters of substances PM10, SO2, CO, O3, and nitrogen dioxide to categorize Jakarta's air quality (NO2). The data used is daily data taken from the Air Quality Monitoring Station in Jakarta throughout 2020. The methods used include SVM, Random Forest, Logistic Regression, KNN, CART, and Stacking Algorithm. At the data preparation stage, we found missing values, outliers, and class imbalance problems. Before applying machine learning methods and evaluating accuracy, we used data pre-processing techniques such as the MissForest method, median substitution, and ADASYN. The results prove that the original dataset has a higher accuracy score (0.882 – 0.977) than the balanced dataset (0.829 – 0.976). According to the evaluation results, the Random Forest method has the highest accuracy score for original and balanced datasets. The overall result is better than the identical research, which produces 96.61% accuracy using a neural network. It shows that preprocessing steps such as missing values handling an imbalanced class handling is essential in classification performance
Artificial intelligence applications in solar energy
Get PDFRenewable energy research has become significant in the modern period owing to escalating prices of fossil fuels and the pressing need to reduce greenhouse gas emissions. Solar energy stands out among these sources due to its abundance and global accessibility. However, its weather-dependent and cyclical nature add inherent risks, making effective planning and management difficult. Soft computing technologies provide attractive solutions for modeling such systems, while machine learning and optimization techniques are gaining popularity in the solar energy industry. The current literature highlights the growing use of soft computing technologies, emphasizing their potential to address difficult challenges in solar energy systems. To effectively reap the benefits, these strategies must be seamlessly connected with emerging technologies like the Internet of Things (IoT), big data analytics, and cloud computing. This integration provides a unique opportunity to improve the scalability, flexibility, and efficiency of solar energy systems. Researchers can use these synergies to create intelligent, linked solar energy ecosystems capable of real-time optimization of energy production, delivery, and consumption. These technologies have the potential to transform the renewable energy environment, allowing for more resilient and sustainable energy infrastructures. Furthermore, as these technologies improve, there is a growing demand for trained experts to address associated cybersecurity problems, assuring the integrity and security of these sophisticated systems. Researchers may pave the road for a more sustainable and energy-efficient future by working collaboratively and using interdisciplinary methodologies