Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Analysis of the power sector in Bangladesh: current trends, challenges, and future perspectives
Get PDFBangladesh’s economic development is largely dependent on the power sector, which promotes sustainability and growth. The country’s future energy security, however, is seriously threatened by the natural gas reserves running out by 2028. As a result, the current energy mix has to be modified right away to ensure Bangladesh’s sustained economic growth. This research paper offers a thorough analysis of Bangladesh’s power sector’s current state. With a focus on important metrics like installed capacity, electricity generation, and distribution infrastructure, the study seeks to provide insights into the sector’s opportunities, challenges, and strengths. The research highlighting the importance of energy security and forecasting the projected energy demand in Bangladesh. The study also looks at current projects and advancements that have shaped Bangladesh’s power industry. This research also provides an ideal energy option that supports Bangladesh's sustainable growth. This analysis offers significant insights into the dynamics of the power industry in Bangladesh, elucidating it is present trajectory, the challenges it encounters, and the potential avenues for achieving a more sustainable and resilient energy future
Advancing breast cancer prediction: machine learning, data balancing, and ant colony optimization
Get PDFBreast cancer constitutes a significant threat to women's health worldwide. The World Health Organization (WHO) reports around 2.3 million new cases each year, making this disease the primary reason for cancer-related fatalities among women. In light of this alarming situation, developing innovative tools for early detection and optimal treatment is imperative, as it directly addresses the pressing need to enhance our capabilities in the quest to overcome breast cancer. This study fits in with this approach, introducing a comparative assessment of multiple machine learning algorithms and integrating data preprocessing, data balancing and feature selection techniques. The studied Coimbra dataset, composed of 116 records and including 10 medical characteristics, exhibited promising performance in all classification metrics, reaching an accuracy of 89.74%, and an area under the receiver operating characteristic curve (AUC-ROC) of 89.68%. These findings highlight the significant potential of our approaches to improve breast cancer treatment and detection systems, providing health practitioners with more efficient resources
The role of chat generative pre-trained transformer in facilitating decision-making and the e-learning process in higher education
Get PDFDigital technology and artificial intelligence technologies have been progressing rapidly, thus giving rise to intelligent chatbots such as chat generative pre-trained transformer (ChatGPT). These chatbots make searching for information more efficient and provide higher education institutions with assistance in decision-making. The goal of this research is to explore the capabilities of ChatGPT technology and its role in enhancing the e-learning process. Moreover, it seeks to determine whether ChatGPT can provide useful suggestions to improve the decision-making process in higher education. ChatGPT is effective in an e-learning environment for the following reasons: it facilitates personalized learning experiences, offers real-time support, and enhances decision-making by leveraging natural language processing capabilities. As suggested by the findings, ChatGPT has significant potential in higher education, as demonstrated by its ability to improve interactive participation, educational strategies, and educational outcomes. This study highlights the importance of incorporating ChatGPT into higher education settings to improve e-learning and decision-making
A comprehensive achievement investigation of iterative mean filter for outlier extinguish aspiration on ubiquitous FVIN
Get PDFUnder commonwealth of the outlier extinguish inspection, exclusively on the impulsive outlier, the outlier extinguish algorithm is a substantial step, which is early performed prior to further computer vision steps thereupon the iterative mean filter (IMF) is inaugurated for fix value impulsive noise (FVIN) and grown into one of the superior achievement outliers extinguish algorithms. This academic article focuses to investigate the correlative achievement of the outlier extinguish algorithm established on IMF, is inaugurated from mean filter (MF) for carrying out the poor achievement of the aforesaid outlier extinguish algorithms (standard median filter (SMF), MF, and adaptive median filter (AMF)), for FVIN at omnipresent scattering of outlier consistency (5-90%). The analytical experiment comprehensively exploits on bountiful figures (F16, Girl, Lena, and Pepper) that are inspected in order to analyze the correlative achievement of an outlier extinguish algorithm established on IMF. In contrast with the aforesaid outlier extinguish algorithms (SMF, MF, and AMF), the outlier extinguish algorithm established on IMF has superior achievement from the experimental results
A discernment of round-robin vs SD-WAN load-balancing performance for campus area network
Get PDFEfficient load balancing is crucial for optimizing network performance and ensuring seamless connectivity in modern campus area networks (CANs). With the proliferation of data-intensive applications and the increasing reliance on cloud-based services, organizations are seeking effective load-balancing solutions to distribute network traffic evenly across available resources. The continuous improvement of devices, tools, and techniques to cater a large amount of network traffic, started to be employed on different campuses. Understanding the best approach to maximize the utilization of the network resources is crucial in order to stabilize and maintain the network. The study aims to discern the round-robin and software defined-wide area network (SD-WAN) techniques based on defined metrics and conducted with a predefined payload for commonly used application conditions. The analysis shows that SD-WAN delivers a much superior performance than round-robin based on the criteria. The local area network (LAN) test shows difference between the two types of technology for the three given metrics. The WAN test shows that the round-robin has higher packet loss, latency, and jitter than the SD-WAN technology. While round-robin may suffice for small-scale deployments with relatively homogeneous traffic patterns, SD-WAN offers more sophisticated capabilities for larger CANs with diverse application workloads and distributed locations
Sustainability dimensions in enhancing the energy and resource efficiency of big data systems
Get PDFBig data systems are essential for many businesses to grow, leveraging the vast amounts of data they generate and access. However, big data systems are plagued by significant sustainability challenges. Thus, this study aims to identify metrics that can measure the sustainability of big data systems. This research conducted a comprehensive literature review to identify five key sustainability dimensions: technical, environmental, economic, social, and individual. Then, a set of 29 metrics corresponding to these dimensions was developed. To ensure the relevance and applicability of these metrics, an expert validation session was carried out with five experts in the big data field. The validation process confirmed the appropriateness of our proposed metrics and modification take place. The findings of this study present 30 metrics upon experts’ validation that could enhance the sustainability of big data systems, offering meaningful insights for researchers and practitioners aiming to enhance resource and energy efficiency in this domain
Securing IoT edge device communication with efficient ECC middleware for resource-constrained systems
Get PDFThe internet of things (IoT) rapidly grows into various parts of life. However, it has significant obstacles during setup and deployment, particularly in terms of network segmentation, administration, and security at all tiers, from physical to application. While IoT provides several advanced features and benefits, it is also vulnerable to security threats and flaws that must be thoroughly investigated to avoid misuse. Cryptographic approaches are routinely used to address these security concerns. Message queuing telemetry transport (MQTT), an application layer protocol, is vulnerable to various known and undisclosed security flaws. Integrating encryption techniques within the MQTT protocol to provide secure data flow is a potential strategy for increasing security. This study provides a middleware broker that improves authentication processes, securing connections between cloud servers and resource-constrained devices. Using a Java Servlet and the elliptic curve cryptography (ECC) technique, the study creates a system for creating encrypted identification keys within a web-based transaction framework. This system intends to provide asymmetric authentication that is energy and resource-efficient, with a focus on cost minimization. It also includes a security feature to protect users from common internet threats. The system's efficacy, including its low energy usage of only 4 mJ per device, is thoroughly tested, proving it meets the original protocol criteria
A novel method of detecting malware on Android mobile devices with explainable artificial intelligence
Get PDFThe increasing prevalence of malware targeting android mobile devices has raised significant concerns regarding user privacy and security. In response, effective methods for malware classification and detection are crucial to protect users from malicious applications. This paper presents an approach that leverages deep learning techniques and explainable artificial intelligence (XAI) for android mobile malware classification and detection. Convolutional neural networks (CNNs) are deep learning model that has shown impressive performance in several application areas, including image and text classification. In the context of android mobile malware, CNNs have shown promising results in capturing intricate patterns and features inherent in malware samples. By training these models on large datasets of benign and malicious applications, accurate classification can be achieved. To enhance transparency and interpretability, XAI techniques are integrated into the classification process. These techniques provide insights into the decision-making process of the deep learning models, enabling the identification of critical features and characteristics that contribute to the classification results. This research, by combining deep learning and XAI methods, presents a fresh strategy for identifying and categorizing Android malware. This research paper will focus on a fascinating CNN-based malware categorization technique
Efficiency and performance ratio of photovoltaics on a 50 kWp Universitas Pamulang Viktor rooftop solar power plant
Get PDFTo overcome the fossil energy crisis due to the increasing need for electrical energy, new renewable energy sources are needed. Due to technological developments in the fields of transportation, industry, household, and commercial use. Indonesia’s geography has the potential to apply new renewable energy, more specifically photovoltaic (PV). However, it is greatly influenced by environmental factors such as solar radiation, voltage, which have an impact on the output power efficiency and performance. So, it is necessary to test both measurements and calculations to see the optimization of output power and PV efficiency. From previous research, it has not been carried out, especially in the experimental method Universitas Pamulang: measurement and empirical and for a sufficiently high capacity with the aim of optimal output power. Methods of measuring sunlight intensity, voltage and current, the calculation of converting sunlight intensity to solar constellation, power, efficiency, and performance ratio (PR). The average value being 721 W/m2 an efficiency value of 19.9% and a value PR is obtained of 0.967 or 96.7% is still realistic. So that the system is declared optimal
Handwritten digit recognition using a column scheme-based local directional number pattern
Get PDFOne of the most well-known challenges in computer vision and machine learning is the recognition of handwritten digits. This study presents an advanced approach to improving isolated-digit recognition through the use of advanced feature extraction techniques. For example, digit recognition is commonly used to read numbers on forms and checks in banks. This paper introduces a novel method of extending the local directional number pattern (LDNP) to a column scheme using two different masks and their resolutions. A new descriptor of the LDNP column scheme is being proposed that combines derivative Gaussian and Kirsch masks in order to enhance textural analysis and capture more detailed local textual information. This approach is highly efficient and robust, able to handle variations in size, shape, and slant. Additionally, the support vector machine (SVM) is employed as a classifier, which has been shown to make better decisions. The empirical investigation is carried out using the CVL dataset, resulting in recognition rates that are comparable with the latest advancements in the field. The overall precision of 96.64% is achieved, outperforming existing similar works