JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
Comparative Analysis of Machine Learning Algorithms for Cross-Site Scripting (XSS) Attack Detection
Get PDFCross-Site Scripting (XSS) attacks pose a significant cybersecurity threat by exploiting vulnerabilities in web applications to inject malicious scripts, enabling unauthorized access and execution of malicious code. Traditional XSS detection systems often struggle to identify increasingly complex XSS payloads. To address this issue, this research evaluated the efficacy of Machine Learning algorithms in detecting XSS threats within online web applications. The study conducts a comprehensive comparative analysis of XSS attack detection using four prominent Machine Learning algorithms, which consist of Extreme Gradient Boosting (XGBoost), Random Forest (RF), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). This research utilizes a comparative methodology to assess the selected Machine Learning algorithms by analyzing their performance metrics, including confusion matrix, 10-fold cross-validation, and assessment of training time to thoroughly evaluate the models. By exploring dataset characteristics and evaluating the performance metrics of each selected algorithm, the study determined the most robust Machine Learning solution for XSS detection. Results indicate that Random Forest is the top performer, achieving 99.93% accuracy and balanced metrics across all criteria evaluated. These findings will significantly enhance web application security by providing reliable defenses against evolving XSS threats
Enhancement of Secure Hospital Healthcare Monitoring System Based–Software Defined Network (SDN) with Machine Learning
Get PDFHandling delicate and crucial knowledge by healthcare providers requires security measures to prevent unapproved use. Software-defined networks (SDNs) are extensively used in medical facilities to ensure resource efficiency, security, and superior network management and management. Despite these advantages, SDNs present a significant threat from various assaults due to the sensitivity of patient information. Our work's primary goal is to propose a global connection between SDN technology and machine learning-based assaults in healthcare. This paper aims to draw attention to a few relevant options. Additionally, we give a framework using software-defined network principles that illustrate linkages between a collection of people, each of whom has a Nano network residing within their bodies, and medical providers via the local network of a medical center. In health care, the initiative is sometimes called an issue of machine learning assault systems and amenities. The current possibilities for machine learning cyberattacks on the medical industry are quite promising. It is also highly well-liked because of its capacity to identify and assess. From a single instrument to the enormous amounts of data gathered, this evolution radically changes how we approach medicine. This work uses a range of ML approaches and attacks to test MLCAH (Machine Learning-based Cyber Attacks Healthcare). For every combination of machine learning methods and assaults, an efficiency assessment highlights the benefits and drawbacks of different algorithms for defending against a specific assault
A Conceptual Framework for Personalized Early Prediction of Asthma Exacerbation Attacks Using Proximal Policy Optimization
Get PDFAsthma, a chronic respiratory ailment affecting millions worldwide, presents significant challenges due to the unpredictable nature of exacerbation episodes. Existing methodologies struggle to accurately predict exacerbations individually, particularly across diverse patient demographics. This paper introduces an innovative conceptual framework for the early prediction of asthma exacerbations, leveraging advanced reinforcement learning (RL) techniques, specifically proximal policy optimization, along with patient-specific data and environmental factors. The primary goal is to revolutionize asthma management by providing customized predictions and tailored reward mechanisms that enable proactive interventions and optimize resource allocation. The framework comprises critical components such as patient profiling through a mobile application, trigger identification, a RL-based predictive model, an early warning mechanism, and a personalized reward scheme. Data for patient profiling is gathered through a mobile application, which includes medical history, demographics, symptoms, and triggers. Profiling forms the foundation for the prediction model, enabling it to identify subtle patterns and anticipate exacerbation events more accurately and efficiently. The significant contributions of this research include offering a novel approach by incorporating custom reward functions to enhance learning across heterogeneous patient populations, tailoring interventions to unique triggers and symptom presentations, and addressing challenges associated with patient diversity. By addressing the limitations of existing methodologies and offering a comprehensive solution, this research promises significant improvements in asthma care and healthcare delivery, paving the way for future advancements in personalized medicine and predictive healthcare systems
Conceptualizing Digital Readiness, Strategic Foresight, and Strategic Flexibility as Drivers of Digitalization and Performance of Small and Medium Enterprises
Get PDFThe drivers of digitalization and small and medium enterprises (SMEs) performance have been primarily examined through resource-based theories. Hence, this study presents an alternative perspective based on such organizations' readiness and dynamic capabilities through a conceptual framework. A conceptual framework is developed by drawing upon the digital readiness theory (DRT) along with the dynamic capabilities view (DCV) to propose an integrated framework that posits a set of propositions linking constructs that reflect both digital readiness as well as the dynamic capabilities of an organization as possible drivers of business process digitalization (BPD) and performance. The empirical literature based on the DRT suggests that digital readiness will likely drive BPD and performance. Whereas leveraging the premise of the DCV indicates that the ability to sense opportunities and threats is reflected by strategic foresight. In contrast, the ability to seize and transform is reflected through strategic flexibility. The propositions posit that all three factors influence performance directly and through the mediating effect of BPD. The framework developed in this study may provide clues to practitioners and policymakers related to SME development regarding potential drivers of digitalization and performance. Growing scholarly publications on antecedents of digitalization and the performance of SMEs have focused primarily on resources. The current study offers an alternate perspective by integrating the two theories based on such organizations' readiness and dynamic capabilities.
Performance Analysis of Feature Mel Frequency Cepstral Coefficient and Short Time Fourier Transform Input for Lie Detection using Convolutional Neural Network
Get PDFThis study aims to determine which model is more effective in detecting lies between models with Mel Frequency Cepstral Coefficient (MFCC) and Short Time Fourier Transform (STFT) processes using Convolutional Neural Network (CNN). MFCC and STFT processes are based on digital voice data from video recordings that have been given lie or truth information regarding certain situations. Data is then pre-processed and trained on CNN. The results of model performance evaluation with hyper-tuning parameters and random search implementation show that using MFCC as Voice data processing provides better performance with higher accuracy than using the STFT process. The best parameters from MFCC are obtained with filter convolutional=64, kerneconvolutional1=5, filterconvolutional2=112, kernel convolutional2=3, filter convolutional3=32, kernelconvolutional3 =5, dense1=96, optimizer=RMSProp, learning rate=0.001 which achieves an accuracy of 97.13%, with an AUC value of 0.97. Using the STFT, the best parameters are obtained with filter convolutional1=96, kernel convolutional1=5, convolutional2 filters=48, convolutional2 kernels=5, convolutional3 filters=96, convolutional3 kernels=5, dense1=128, Optimizer=Adaddelta, learning rate=0.001, which achieves an accuracy of 95.39% with an AUC value of 0.95. Prosodics are used to compare the performance of MFCC and STFT. The result is that prosodic has a low accuracy of 68%. The analysis shows that using MFCC as the process of sound extraction with the CNN model produces the best performance for cases of lie detection using audio. It can be optimized for further research by combining CNN architectural models such as ResNet, AlexNet, and other architectures to obtain new models and improve lie detection accuracy
Exploring Classification Algorithms for Detecting Learning Loss in Islamic Religious Education: A Comparative Study
Get PDFThis study investigates the detection of learning loss in Islamic religious education subjects in Indonesia. Focusing on the effectiveness of multiple classification algorithms, the research assesses learning loss across literacy, numeracy, writing, and science domains. While education traditionally involves knowledge transmission, it also seeks to instill values. Given Indonesia's predominantly Islamic demographic, Islamic Religious Education (IRE) is pivotal in disseminating moral and cultural values, encompassing teachings from the Koran, Hadith, Aqedah, morality, Fiqh, and Islamic history. The study's central aim is to discern learning loss in IRE in Islamic schools, utilizing the Gradient Boosting Classifier as its primary analytical tool. Various classification algorithms, including the Cat Boost Classifier, Light Gradient Boosting Machine, Extreme Gradient Boosting, and others, were tested. The study engaged a sample of 38,326 Islamic Elementary school students, 29,350 Islamic Junior High school students, and 13,474 Islamic High school students across Indonesia. The findings revealed that the Light Gradient Boosting Machine was the most effective model for Islamic Elementary and High school data, while the Cat Boost Classifier excelled for Islamic Junior High school data. These results highlight the extent of learning loss in IRE and offer invaluable perspectives for education stakeholders. Future studies are encouraged to further explore the root causes of this learning loss and devise specific interventions to tackle these issues effectively
Software Agent Simulation Design on the Efficiency of Food Delivery
Get PDFFood delivery services have gained popularity since the emergence of online food delivery. Since the recent pandemic, the demand for service has increased tremendously. Due to several factors that affect how much time additional riders spend on the road; food delivery companies have no control over the location or timing of the delivery riders. There is a need to study and understand the food delivery riders' efficiency to estimate the service system's capacity. The study can ensure that the capacity is sufficient based on the number of orders, which usually depends on the number of potential customers within a territory and the time each rider takes to deliver the orders successfully. This study is an opportunity to focus on the efficiency of the riders since there is not much work at the operational level of the food delivery structure. This study takes up the opportunity to design a software agent simulation on the efficiency of riders' operations in food service due to the lack of simulation to predict this perspective, which could be extended to efficiency prediction. The results presented in this paper are based on the system design phase using the Tropos methodology. At movement in the simulation, the graph of the efficiency is calculated. Upon crossing the threshold, it is considered that the rider agents have achieved the efficiency rate required for decision-making. The simulation's primary operations depend on frontline remotely mobile workers like food delivery riders. It can benefit relevant organizations in decision-making during strategic capacity planning
Continuous Training of Recommendation System for Airbnb Listings Using Graph Learning
Get PDFRecommender systems are getting increasingly important nowadays as they can boost user engagement and benefit businesses. However, there remain some unsolved problems. This paper will address two key performance issues. First, the limited ability to identify and leverage intrinsic relationships between data points. Second, the inability to adapt to new data. The first issue is proposed to be addressed through a Graph Neural Network (GNN) to curate better recommendations. GNN will be trained with Airbnb’s review data to utilize its outstanding expressive power to represent complex user-listing interactions at scale, followed by generating embeddings to compute the relevant recommendations to the users. With the generated embeddings, the recommender system will compute a recommendation list to every user based on the embedding similarity between the user and listings or the user’s first-ever reviewed listing and listings. The second issue is proposed to be resolved by incorporating Continuous Training. The proposed recommender system employs GraphSAGE with a customized Rating-Weighted Triplet Ranking Loss function, which outperformed unsupervised GraphSAGE. Offline simulation validated the recommender system's ability to learn from the latest data and improve over time. Overall, the proposed user-to-item (U2I) recommendation rating-weighted GraphSAGE substantially increased by 99.88% in hit-rate@5 and 98.15% in coverage. This offers an effective solution for enhancing the recommender system for Airbnb listings. This research validates the efficacy of GNN-based recommendations in capturing user-item relationships to aid in predicting relevant recommendations, thus significantly driving up the adoption of GNN-based recommender systems
Expert Analysis on the User Interface of an Academic E-Supervision Application Based on Vocational Education Character
Get PDFDesigning information systems to accommodate the unique needs of various users receives a lot of attention in contemporary software engineering. One such distinctive requirement in the educational context is academic supervision. Academic supervision encompasses activities to assist educators in enhancing their skills for managing the learning process and achieving educational objectives. In vocational high schools, the primary educational goals are to prepare students for the job market and empower them to initiate their businesses. These goals can only be realized if teachers incorporate technical and entrepreneurial skills into learning. The main goal of this study is to assist school supervisors and principals in assessing and directing teachers as they incorporate ideas of vocational education into the teaching and learning process. The research methodology used in this study is research and development, which includes several stages: initial needs analysis and assessment of the current state of academic supervision; development, which involves the creation of a conceptual system model; system interface design; model validation and revision; and evaluation, which requires system testing, implementation, and deployment. Based on the initial investigation and analysis of academic supervision, particularly in the context of vocational education, this research presents a conceptual model and system interface design. The outcomes of this research encompass the interface, system architecture, and user guide for the academic e-supervision system. An expert analysis of the user interface design indicates that the interface received positive evaluations from experts, with an overall average rating of 88%
Systematic Literature Review on Augmented Reality with Persuasive System Design: Application and Design in Education and Learning
Get PDFAugmented Reality (AR) is an innovative technology that has gained significant scholarly attention. It uses computer-generated sensory inputs like visuals, sounds, and touch to enhance how we perceive the real world, providing a transformative impact on human sensory experiences. Motivated by the possibilities of augmented reality (AR) in the realm of the educational learning environment, this research aims to document the evolving landscape of augmented reality (AR) applications in education and training, with a specific emphasis on the incorporation of persuasive system design (PSD) elements. The study also explores the diverse technologies and methodologies for developing these applications. A systematic literature review was conducted, analyzing 44 articles following the protocol for PRISMA assessments. Four research questions were formulated to investigate trends in AR applications. Between 2016 and 2023, publications on AR applications doubled, with a significant focus on the educational field. Marker-based AR methods dominated (68.49%), while markerless methods constituted 31.51%. Unity and Vuforia were the most used platforms, accounting for 77.27% of applications. Most research papers assessed application effectiveness subjectively through custom-made questionnaires. University students were identified as the primary target users of AR applications. Only a few applications integrated persuasive elements, even for adult users. This highlights the need for further studies to fully grasp the possibilities of combining persuasive system design with augmented reality applications in educatio