Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Progression of polymeric nanostructured fibres for pharmaceutical applications
Get PDFElectrospinning has emerged as a simple and cost-effective technique for producing polymer nanofibers, offering a versatile approach for creating nanostructured fibers from a wide range of polymer materials. The pharmaceutical field has particularly welcomed the advent of electrospun nanofibers, as they hold immense potential for revolutionizing drug delivery systems. The recent surge of interest in electrospun nanofibers can be attributed to their unique characteristics, including elasticity and biocompatibility, which make them highly suitable for various biomedical applications. By incorporating functional ingredients into blends of nanostructured fibers, the capabilities and reliability of drug delivery devices have been significantly enhanced. This review aims to provide a comprehensive summary of recent research endeavors focusing on the concept of nanofibrous mesh and its multifaceted applications. With an emphasis on the simplicity of fabrication and the virtually limitless combinations of materials achievable through this approach, nanofibrous meshes hold the promise of transforming specific treatment modalities. By streamlining the delivery of therapeutic agents and offering enhanced control over drug release kinetics, nanofibrous meshes may herald a new era in targeted and personalized medicine
Cybersecurity challenges in healthcare: mitigating risks in a rapidly evolving digital landscape
Get PDFThe rapid digital transformation of the healthcare sector brings significant benefits but also exposes institutions to escalating cybersecurity risks. This study analyzes vulnerabilities such as ransomware, supply chain compromises, and insider threats, drawing on international reports from World Health Organization (WHO), Healthcare Information and Management Systems Society (HIMSS), Ponemon, and Verizon. The paper contributes a unique mitigation framework that consolidates three strategic pillars: i) continuous cybersecurity training for medical staff, ii) deployment of advanced technological safeguards, and iii) establishment of collaborative incident reporting mechanisms. Beyond mapping current threats, the study provides policy-oriented guidance for strengthening resilience in both developed and emerging healthcare systems. With healthcare breaches costing an average of $10.1 million per incident, the findings highlight the urgent need for coordinated action to ensure patient safety, service continuity, and institutional trust
Enhanced Semarang batik classification using deep learning: a comparative study of CNN architectures
Get PDFBatik is an important part of Indonesia’s cultural heritage, with each region producing unique designs. In Central Java, Semarang is known for its distinctive batik patterns that reflect rich local traditions. However, many people are still unfamiliar with these designs, which threatens their preservation. This study develops an automated system to classify Semarang batik patterns, showing how technology can help safeguard cultural heritage. A convolutional neural network (CNN) approach was used to recognize ten batik types, including Asem Arang, Asem Sinom, Asem Warak, Blekok, Blekok Warak, Gambang Semarangan, and Kembang Sepatu. Pre-processing steps—such as image resizing, cropping, flipping, and rotation—improved model performance and reduced complexity. Five CNN architectures (MobileNetV2, ResNet-50, DenseNet-121, VGG-16, and EfficientNetB4) were tested using 224×224 input size, Adam optimizer, ReLU activation, and categorical cross-entropy loss. Results show VGG-16, ResNet-50, and DenseNet-121 achieved perfect accuracy (1.0) on a dataset of 3,000 locally collected images. These findings highlight CNN models’ strong potential for batik pattern recognition, supporting digital preservation of Indonesian culture
Mobile application to optimize appointment management in a specialized dental center
Get PDFThe objective of the research was to implement a mobile application for the management of appointments in a specialized dental center, to improve patient care, allowing them to make their reservation from the place and at the time they want. The research has a quantitative approach, of experimental type with a pre-experimental design. The population consisted of 70 patients, with a total sample of 60. The SPSS statistical software was used for the elaboration of the results, obtaining positive results. With all the above mentioned in this research work, it is concluded that the implementation of the mobile application for appointment management for the dental center will facilitate patients to have better attention, which allows a reduction of time and satisfaction with the service. In indicator 1, referring to appointment registration time, a reduction of 44.13% was obtained. In indicator 2 on the number of patients presenting for appointments, an increase of 17.58% was obtained, and finally, in indicator 3 on the level of satisfaction, an increase of 65% was obtained
An enhanced key schedule mechanism to improve the security strength of the data encryption standard algorithm
Get PDFThe rapid growth of internet accessibility requires strong data security measures, mainly for safeguarding sensitive information. Since many threats and attacks steal our private data. Data encryption standard (DES) is one of the cryptographic methods that uses a symmetric key encryption method to resist various types of cryptographic attacks. This work proposes an improved key scheduling algorithm (KSA) to enhance DES security. The modified KSA is evaluated using criteria such as frequency test, hamming weight, and bit difference to measure round key randomness and resilience. Moreover, the avalanche effect is evaluated to assess the diffusion and confusion character of the generated ciphertext. The final result indicates that the enhanced KSA attains better frequency distribution (0.89-1.0), increased hamming weight consistency (97.13%), and high bit transition rates compared to the original DES KSA. These enhancements demonstrate increased randomness and complexity, making the algorithm more resistant to brute-force and other cryptographic attacks. Our proposed work shows enhanced security capabilities, albeit with increased computational requirements, and establishes a foundation for future improvement in symmetric key cryptography
Analog artificial intelligence hardware for neural networks: design trends and considerations
Get PDFThe increasing deployment of artificial intelligence (AI) in real-time and edge applications intensified the demand for energy-efficient hardware capable of high-throughput processing. Conventional digital processors were constrained by sequential data processing, memory bandwidth limitations, and high-power consumption, making them suboptimal for edge-based AI. This review presented a comprehensive analysis of analog very-large-scale integration (VLSI) design approaches for neural network (NN) implementation focusing on circuit-level architectures including in-memory analog computing, current-mode circuits, switched-capacitor (SC) techniques, and operational transconductance amplifier (OTA)-based designs. Significant hardware design considerations such as process variation, crossbar scalability, precision–linearity trade-offs, and mixed-signal interface challenges were critically examined. Furthermore, training methodologies—spanning offline learning, circuit calibration, and programmability were discussed in the context of analog AI hardware. The review incorporated case studies, recent developments in edge deployment, and a comparative analysis of advanced analog VLSI chips. Key performance evaluation metrics such as accuracy, calibration overhead, noise robustness, and energy per inference, were also addressed. Circuit-level design aspects that impacted the performance, precision, and reliability of analog computing blocks were discussed. The paper concluded by identifying research gaps and future directions for the development of analog AI hardware suitable for real-world edge applications
Development of an internet of things microstrip antenna for turbo code off-grid emergency communications
Get PDFTechnologies and other things are fully automated, meaning signal processing and microstrip antennas for communication are essential because of their compact size and versatility. Due to inefficiency and other factors, traditional communication methods fail, which means some emergency communication systems encounter difficulties. MATLAB was used to simulate a microstrip antenna for turbo code off-grid emergency communication and signaling of internet of things (IoT) devices. A criterion is followed to determine whether a microstrip antenna’s behavior meets the emergency communication requirements. The results show that the system’s transfer function satisfies the required conditions to meet efficient communication and signaling, especially in emergencies. The step response peaked at 1.04 and an overshoot of 4.6%, meeting the conditions for efficient communication. Besides that, the generated Bode plot and Nyquist plot display the required behavior, meaning that the microstrip antenna can function as a communication device for emergency situations
Hybrid deep learning: a comparative study on ai algorithms in natural language processing for text classification
Get PDFThe objective of this research project is to assess the effectiveness of various machine learning algorithms, including deep learning and combination approaches, in performing tasks such as categorizing products into specific categories using data from an e-commerce platform named "OTHOBA." In this study, a dataset consisting of 19,087 data samples is used to evaluate the effectiveness of seven supervised machine learning models. Among these models are three based on deep learning: long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), and 1D convolutional (Conv1D), as well as a multi-layer model that combines Conv1D and LSTM approaches. The task at hand is the classification of product categories. The LSTM-based model demonstrates the highest accuracy rate of 96.23% among the deep learning models, while the logistic regression (LR) models achieve the highest accuracy scores of 97.00% for product category classification. Overall, the proposed models and techniques show significant progress in natural language processing (NLP) research for text classification, specifically in English, and have practical applications for e-commerce sites
Object detection in video surveillance using MobileNetV2 on resource-constrained low-power edge devices
Get PDFEdge-based video surveillance systems encounter significant obstacles in object detection due to the limited computational power and energy efficiency of edge devices, which are required to deliver real-time processing capabilities. Traditional object detection models are excessively resource-hungry for these environments, making optimization techniques absolutely essential. This study robustly explores the implementation of quantized transfer learning utilizing SSD MobileNet V2 with 8-bit quantization to significantly elevate the performance of object detection on resource-constrained edge devices. Experimental results decisively indicate that the Raspberry Pi 5 and Nvidia Jetson Orin Nano surpass other devices, achieving total latencies of 5 ms and 85 ms, respectively, affirming their exceptional suitability for real-time applications. The quantized int8 model secures an impressive accuracy of 80.65% while dramatically lowering memory consumption and latency when compared to the unoptimized int32 model. Furthermore, the model demonstrates outstanding performance on a masked-unmasked dataset with an F1 score of 0.92 for masked detection. These findings underscore the transformative potential of quantization in enhancing both inference speed and resource efficiency in edge-based surveillance systems. Future research will boldly investigate advanced hybrid quantization strategies and architectural enhancements to achieve an optimal balance of efficiency and accuracy, alongside scalability across a broader spectrum of edge devices and datasets
A scoring approach for detecting fake reviews using MRCS similarity metric enhanced by personalized k-means
Get PDFOnline commerce has grown in the digital age, and as a result, consumers now depend more than ever on other consumer feedback to make informed purchasing decisions. However, as the importance of reviews has increased, so has the prevalence of fake ones, which now infiltrate platforms and manipulate users' perceptions. This presents a significant challenge to preserving confidence and integrity in online marketplaces. This study addresses the difficulty of identifying fake reviews by introducing a distinctive methodology that incorporates advanced natural language processing (NLP) tools. By including a new metric, mean review cosine similarity (MRCS), which enhances textual similarity assessment for more accurate detection, we improve the identification process. Additionally, an exaggeration detection technique is included, enhancing the model's capacity to identify deceptive variations in review content. Furthermore, an adaptive clustering method differs from traditional k-means classification through modifying clusters to adjust to the constant evolution of misleading linguistic patterns. Empirical validation on the Yelp labeled dataset demonstrates the approach's accuracy (90%), with high precision (89%), recall (95%), and F1 score (92%), indicating its effectiveness and highlighting areas for further refinement