International Journal of Advances in Applied Sciences
Not a member yet
668 research outputs found
Sort by
Stacking architecture-endpoint detection: a hybrid multi layered architecture for endpoint threat detection
Get PDFModern endpoint threat detection systems face persistent challenges in balancing detection accuracy, resilience against zero-day attacks, and the interpretability of artificial intelligence (AI) models. Although deep learning (DL) approaches often achieve high accuracy on benchmark datasets, they remain vulnerable to adversarial perturbations and operate as opaque “black boxes,” thereby reducing trust and limiting practical adoption in critical infrastructures. This research introduces stacking architecture-endpoint detection (STACK-ED), a hybrid multi-layered architecture for endpoint threat detection. STACK-ED integrates three complementary paradigms: supervised learning for known attack patterns, self-supervised Fgraph-based learning for structural relationships, and unsupervised anomaly detection for emerging or unknown threats. The outputs are consolidated by a meta learner, followed by a post-hoc correction (PHC) mechanism to minimize false negatives. The framework was evaluated on a combined benchmark dataset (CSE-CIC-IDS2018 and UNSW-NB15, hereafter referred to as HIDS-Set). Experimental results demonstrate state-of-the-art performance, achieving an F2-score of 98.89% after hybrid integration and active learning, with the primary optimization objective being the reduction of undetected attacks. Furthermore, the Shapley additive explanations (SHAP) method enhances interpretability by revealing feature contributions, while the PHC successfully recovered 62.64% of missed zero-day candidates. The findings position STACK-ED not only as a highly accurate detection model but also as an adaptive, resilient, and transparent framework, offering practical implications for enterprise-grade endpoint defense and future zero-trust cybersecurity systems
Large language models and retrieval-augmented generation-based chatbot for adolescent mental health
Get PDFAccess to fast and efficient information is crucial in today's digital era, especially for teenagers in obtaining mental health services. The manual method used by Youth Information and Counselling Centre (PIK R) to provide mental health information requires significant time and effort. This research presents an AI-based solution by developing a chatbot system using retrieval-augmented generation (RAG) and large language models (LLM). This chatbot is designed to provide accurate and effective mental health information for teenagers throughout the day. An analysis of a dataset consisting of articles on teenage mental health and data from the Alodokter website was used as the basis for the development of this chatbot. The research results show that the chatbot is capable of providing relevant and accurate information, with evaluations using the recall-oriented understudy for gisting evaluation (ROUGE) score method yielding an average of ROUGE-1 with a precision of 87.8%, recall of 83.0%, and F1-measure of 84.0%; ROUGE-2 with a precision of 82.8%, recall of 76.8%, and F1-measure of 78.2%; and ROUGE-L with a precision of 88.0%, recall of 82.6%, and F1-measure of 83.4%. These findings indicate the potential use of chatbots as an effective tool to support the mental health of adolescents
Sulphur corrosion in transformer insulating oils: its effects, detection methods, and mitigation strategies
Get PDFOil-immersed transformers are subjected to electrical, thermal, and mechanical stresses over time, which inevitably affect the insulating oil and paper insulation. The presence of sulphur corrosion also degrades the insulating oil and paper insulation. Sulphur corrosion in insulating oils has been a prevalent problem for many years, as it culminates in the failure of oil-immersed transformers. The longevity of oil-immersed transformers is dependent on the integrity of the insulating oil and paper insulation, which can deteriorate owing to sulphur corrosion. The occurrence and accumulation of copper sulphide (Cu2S) can result in transformer malfunctions, which is a significant issue for transformer manufacturers and operators. This paper provides a concise overview of the effects of sulphur corrosion, its detection methods, as well as its mitigation strategies. It is believed that this paper will enhance the understanding of sulphur corrosion in insulating oils, provide the best practices for sulphur corrosion management, and serve as guidance on enhancing transformer reliability and performance
Solar photovoltaic based cascaded multilevel inverter with 33-levels using phase opposition disposition control method
Get PDFA cascaded multilevel inverter (MLI) tailored for photovoltaic (PV) networks, aiming to improve power quality and support transformer-less operation. The symmetric MLI design is selected for its effectiveness in minimizing harmonics and enhancing fault tolerance in high-power scenarios, where the use of power semiconductor converters can introduce complications. The proposed inverter configuration achieves thirty-three voltage levels, optimizing power quality while using insulated gate bipolar transistor (IGBT) semiconductor switches. The phase opposition disposition (POD) control method is applied to trigger necessary switching signals for the inverter's components. To ensure high output voltage for the MLI, a boost converter is employed, and the overall system is tested with an R load. The effectiveness of the design is validated through MATLAB/Simulink simulations, which demonstrate a notable reduction in total harmonic distortion (THD).
The impact of fast charging technology on battery longevity in electric vehicles
Get PDFFast charging technology has revolutionized the electric vehicle (EV) industry by addressing range anxiety and significantly reducing charging times. However, this convenience introduces challenges concerning battery longevity, as high charging currents and elevated temperatures accelerate battery degradation. This paper investigates the mechanisms through which fast charging impacts lithium-ion batteries, including thermal stress, lithium plating, and mechanical wear. It synthesizes findings from various studies, highlighting how fast charging can shorten battery lifespan by up to 20-30% compared to standard charging methods. Strategies to mitigate these effects, such as advanced materials, adaptive charging protocols, and efficient thermal management systems, are discussed. Furthermore, the paper emphasizes the importance of standards and policies to promote sustainable fast charging practices. By balancing charging speed with long-term battery health, the EV industry can achieve widespread adoption while ensuring sustainability. This work aims to provide a comprehensive understanding of the trade-offs associated with fast charging and offers actionable insights for improving EV battery durability
Designing business architecture for machinery distribution company using the open group architecture framework method
Get PDFMachinery distribution company plays a crucial role in supporting various industries by providing the necessary machines and spare parts. This research focuses on the challenges faced by machine distribution companies in Jakarta, which have branches in Surabaya and Medan, Indonesia, especially in the management of warehouse data. The manual inspection process of stored goods for a long period of time results in operational inefficiencies and increased costs. To address this issue, this research proposes the application of enterprise architecture, specifically business architecture, using the open group architecture framework (TOGAF). This method to design optimal business processes that can improve productivity, reduce human errors, and enhance service quality. Through the analysis of current business processes and the planning of enterprise model interactions, this research identifies gaps in business architecture and designs business architecture to support the company's goals. The research results are expected to help companies improve operational efficiency and competitiveness in a constantly changing market
The contribution of eco bus technologies to environmental problem mitigation: a systematic review
Get PDFSubstituting diesel technology with eco-technologies in public buses is one of the prominent efforts being made to achieve a sustainable transportation system goal. Among these eco-technologies, commonly used ones include electric vehicles, natural gas fuel, hydrogen fuel, and bio-diesel fuel technology. However, the performance comparison between these technologies in reducing environmental impact at each location where they are implemented remains unanswered by previous studies. Research to measure the effectiveness of each of the eco-technologies in reducing environmental issues has been conducted extensively, employing various methods and metrics. This study conducted a systematic review of 94 articles that met the predefined inclusion criteria to obtain performance comparisons among these technologies. As a result, a general trend has been observed that eco-technologies have successfully achieved their intended goals with various success rates, although electric bus technology has advantages over other technologies based on the articles. However, its effectiveness relies on specific aspects to optimize its environmental performance. Therefore, the suitability of implementation in a region will depend on many factors. This article contributes to determining the extent to which eco-technologies are implemented in buses worldwide, serving as a consideration for decision-makers, and identifying research gaps in this topic
Characterization fine grained low alloy steel 22 NiMoCr 3 7 by magnetic Barkhausen noise analysis
Get PDFTo ensure the quality of mass-produced products, non-destructive material testing (NDT) is required with a method that has high testing speed and accuracy. Products that have undergone heat treatment such as automotive components to obtain a specific hardness value need to be tested to ensure the desired quality. Some parameters such as coercivity and permeability of the ferromagnetic materials, can be used to characterize the shape of the hysteresis curve. The hysteresis curve geometry is related to mechanical hardness, hot working record, and the presence of residual stresses. This paper will present how the coercivity value measurement can be done using the Barkhausen effect, as well as a study of the correlation between the coercivity value and the hardness of a ferromagnetic material using the regression analysis method. Indentation testing has also been done to verify different approaches to obtain hardness value by Barkhausen noise analysis. The research shows that this technique was sufficiently accurate with superior rapid testing and no indentation mark
Application management information systems in research and student activities: a case study of NAEM Vietnam
Get PDFThe management information systems (MIS) for education bring many benefits to management at universities, educational institutions, and academies. The Vietnam National Academy of Education Management (NAEM) has successfully integrated information technology into the management, teaching, and learning process, bringing many benefits. Many professional activities have been included in the standard framework of the academy's faculties. However, more specific and detailed activities at specialized faculties are being actively researched and implemented for management purposes. This article presents a study on the construction and implementation of a management information system to support the management of activities at faculties, such as managing information about lecturers' teaching, information about scientific research activities, and published works, In addition, this system also allows students to engage in learning activities such as registering for internships and internships at enterprises, information about graduation thesis implementation, and lecturers' assignments to guide students. Deploying this system at faculties supports the management of detailed operations, improves data management and processing, and ensures consistency in management
Intelligent metaheuristic algorithm based FOPID controller for CSTR system
Get PDFThe purpose of this research is to assess a continuous stirred-tank reactor (CSTR) system's performance. To enhance its performance, a fractional-order proportional-integral-derivative (FOPID) controller was employed, necessitating the tuning of independent control parameters. For this purpose, a sine-cosine algorithm (SCA) was introduced to optimize these parameters. The FOPID controller, tuned using the SCA, provides a powerful combination that addresses the complexities of the CSTR system. The fractional-order nature of the FOPID controller allows for superior tuning and robustness, offering enhanced flexibility in adjusting the system’s response characteristics and improving overall control performance. The SCA, known for its effective exploration of the search space through sine and cosine functions, ensures that the controller parameters are optimally selected to enhance the system’s performance by achieving an optimal fitness function. To showcase the effectiveness of the proposed SCA-tuned FOPID controller, comparisons were drawn with other optimization techniques designed for the CSTR system. The study presents time-domain characteristics and frequency responses of the proposed controller. The simulation results demonstrated that the SCA-FOPID controller significantly outperforms the other designed controllers, achieving a 54.07% reduction in the integral of time absolute error (ITAE) compared to genetic algorithm (GA), an 18.64% reduction compared to grey wolf optimizer (GWO), and a 34.79% reduction compared to differential evolution (DE). These significant reductions in ITAE underscore the effectiveness of this approach, highlighting the superior performance and robustness of the SCA-tuned FOPID controller in optimizing the CSTR system