Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

28,451 Article Results

An approximate model SpMV on FPGA assisting HLS optimizations for low power and high performance

10.11591/ijres.v14.i2.pp375-387
Alden C. Shaji , Zainab Aizaz , Kavita Khare
High performance computing (HPC) in embedded systems is particularly relevant with the rise of artificial intelligence (AI) and machine learning at the edge. Deep learning models require substantial computational power, and running these models on embedded systems with limited resources poses significant challenges. The energy-efficient nature of field-programmable gate arrays (FPGAs), coupled with their adaptability, positions them as compelling choices for optimizing the performance of sparse matrix-vector multiplication (SpMV), which plays a significant role in various computational tasks within these fields. This article initially did analysis to find a power and delay efficient SpMV model kernel using high level synthesis (HLS) optimizations which incorporates loop pipelining, varied memory access patterns, and data partitioning strategies, all of this exert influence on the underlying hardware architecture. After identifying the minimum resource utilization model, we propose an approximate model algorithm on SpMV kernel to reduce the execution time in Xilinx Zynq-7000 FPGA. The experimental results shows that the FPGA power consumption was reduced by 50% when compared to a previously implemented streaming dataflow engine (SDE) flow, and the proposed approximate model improved performance by 2× times compared to that of original compressed sparse row (CSR) sparse matrix.
Volume: 14
Issue: 2
Page: 375-387
Publish at: 2025-07-01

Design and structural modelling of patient-specific 3D-printed knee femur and tibia implants

10.11591/ijres.v14.i2.pp575-586
Bolugoddu Sandeep , Saravanan Dhanushkodi , Sudhakar Kumarasamy
Arthritis is a degenerative joint condition that progressively damages the knee, leading to pain, stiffness, and limited mobility. To alleviate these symptoms and restore joint functionality, total knee arthroplasty (TKA) is performed. This procedure becomes necessary due to either sudden trauma to the knee or gradual wear and tear of the meniscus and cartilage. TKA involves meticulous planning, precise bone cutting, and the placement of prosthetic components made from high-density polyethylene and metal alloys. However, traditional methods creating customized knee implants are expensive and time-intensive. This study explores the challenges in manufacturing personalized knee implants for TKA and evaluates the potential of three-dimensional (3D) printing technology in this process. Variations in knee joint anatomy across populations complicate surgery, as optimal outcomes rely on precise alignment and implant dimensions. A preoperative computed tomography (CT) scan identifies the region of interest (ROI), such as the knee joint. The scan data is then processed using computer-aided design (CAD) software to generate a printable file. The patient’s CT scan data is converted into a standard triangulation language (STL) file and CAD models of the knee joint. Errors such as overlapping triangles or open loops in the STL file are corrected, and unwanted geometries near the ROI are removed. Resection techniques are applied to create CAD models tailored to the patient’s bone morphology. Fused deposition modeling (FDM) is then used to produce prototypes of the knee joint and implants. Despite visible layer lines in the printed prototypes, challenges encountered during the process were effectively resolved.
Volume: 14
Issue: 2
Page: 575-586
Publish at: 2025-07-01

Building a photonic neural network based on multi-operand multimode interference ring resonators

10.11591/ijres.v14.i2.pp311-319
Thanh Tien Do , Hai Yen Pham , Trung Thanh
Photonic neural networks (PNNs) offer significant potential for enhancing deep learning networks, providing high-speed processing and low energy consumption. In this paper, we present a novel PNN architecture that employs nonlinear optical neurons using multi-operand 4×4 multimode interference (MMI) multi-operand ring resonators (MORRs) to efficiently perform vector dot-product calculations. This design is integrated into a photonic convolutional neural network (PCNN) with two convolutional layers and one fully connected layer. Simulation experiments, conducted using Lumerical and Ansys tools, demonstrated that the model achieved a high test accuracy of 98.26% on the MNIST dataset, with test losses stabilizing at approximately 0.04%. The proposed model was evaluated, demonstrating high computation speed, improved accuracy, low signal loss, and scalability. These findings highlight the model’s potential for advancing deep learning applications with more efficient hardware implementations.
Volume: 14
Issue: 2
Page: 311-319
Publish at: 2025-07-01

A custom reduced instruction set computer-V based architecture for real-time electrocardiogram feature extraction

10.11591/ijres.v14.i2.pp412-427
Vinayak Vikram Shinde , Sheetal Umesh Bhandari , Deepti Snehal Khurge , Satyashil Dasharath Nagarale , Ujwal Ramesh Shirode
The growing demand for energy-efficient and real-time biomedical signal processing in wearable devices has necessitated the development of application-specific and reconfigurable embedded hardware architectures. This paper presents the register transfer level (RTL) design and simulation of a custom reduced instruction set computer-V (RISC-V) based hardware architecture tailored for real-time electrocardiogram (ECG) feature extraction, focusing on R-peak detection and heart rate (HR) calculation. The proposed system combines ECG-specific functional blocks including a specialized ECG arithmetic logic unit and a finite state machine-based ECG control unit with a compact 16-bit RISC-V control core. Hardware optimized algorithms are used to carry out pre-processing activities such high-pass and low-pass filtering as well as feature extraction processes including moving average filtering, derivative calculation, and threshold based peak identification. Designed to reduce memory footprint and control complexity, a custom instruction set architecture supports modular reconfigurability. Functional validation is carried out by Xilinx Vivado simulating RTL components described in very high speed integrated circuit (VHSIC) hardware description language (VHDL). The present work shows successful simulation of important architectural components, complete system-level integration and custom ECG data validation. This work provides the basis for an application-specific, reconfigurable, power efficient hardware solution for embedded health-monitoring devices.
Volume: 14
Issue: 2
Page: 412-427
Publish at: 2025-07-01

Enhancing intrusion detection systems with hybrid HHO-WOA optimization and gradient boosting machine classifier

10.11591/ijres.v14.i2.pp518-526
Mosleh M. Abualhaj , Ahmad Adel Abu-Shareha , Roqia Rateb
In this paper, we propose a hybrid intrusion detection system (IDS) that leverages Harris Hawks optimization (HHO) and whale optimization algorithm (WOA) for feature selection to enhance the detection of cyberattacks. The hybrid approach reduces the dimensionality of the NSL KDD dataset, allowing the IDS to operate more efficiently. The reduced feature set is then classified using logistic regression (LR) and gradient boosting machine (GBM) classifiers. Performance evaluation demonstrates that the GBM-HHO/WOA combination outperforms the LR-HHO/WOA approach, achieving an accuracy of 97.68%. These results indicate that integrating HHO and WOA significantly improves the IDS's ability to identify intrusions while maintaining high computational efficiency. This research highlights the potential of advanced optimization techniques to strengthen network security against evolving threats.
Volume: 14
Issue: 2
Page: 518-526
Publish at: 2025-07-01

A novel approach to transparent and accurate fuel dispensing for consumer protection

10.11591/ijres.v14.i2.pp353-364
Gayatri Phade , Sharada Narsingrao Ohatkar , Murugan Pushpavalli , Vidya Chitre , Vijaya Pawar , Omkar Suresh Vaidya , Harikrishnan Ramachandran
Consumer rights are exploited around the world and it is necessary for to protect consumer rights by means of safeguarding consumers from various unfair trade practices. Those most vulnerable to such exploitation must be shielded, and this is achieved through consumer protection measures. One such example of unethical behavior is fuel stealing at fuel stations. To overcome this critical issue, a low-cost fuel quantity sensing and monitoring system is proposed in this paper. A fuel detection system will ensure the exact quantity of fuel filled in fuel tank and will detect fuel theft, if any, at fuel pumps. An embedded system is developed for this purpose, consisting of sensors, display devices, communication devices and microcontroller. The quantity of fuel filled in the tank is transmitted to mobile phone of the consumer to avoid fuel theft. Performance of the system is validated by comparing the displayed amount of fuel dispensed and actual filled in the tank and achieve 99.95% accuracy. With this consumer right to get the value for amount paid for the petrol will be protected. This novel feature can be added in the fuel tank of the smart vehicle development and design as a future scope.
Volume: 14
Issue: 2
Page: 353-364
Publish at: 2025-07-01

An optimized simulated annealing memetic algorithm for power and wirelength minimization in VLSI circuit partitioning

10.11591/ijres.v14.i2.pp365-374
P. Rajeswari , Smitha Sasi
The development of physical architecture standards for very large scale integration (VLSI) single and multichip platforms is still in its early stages. To deal with the growing complexity of modern VLSI systems, it has become common practice to split large circuit architectures into smaller, easier-to-manage sub-circuits. Circuit partitioning improves parallel modeling, testing, and system performance by lowering chip size, number of components and interconnects, wire length (WL), and delays. VLSI partitioning's primary goal is to split a circuit into smaller blocks with as few connections as possible between them. This is frequently accomplished by recursive bi-partitioning until the required complexity level is reached. Thus, partitioning is a fundamental circuit design challenge. An efficient remedy that offers a heuristic method that explores the design space to iteratively enhance outcomes is evolutionary computation. In order to minimize WL, area, and interconnections, we provide an optimized simulated annealing memetic algorithm (OSAMA) that combines local search methods with evolutionary tactics. The efficiency of the method was evaluated using criteria like runtime, cost, delay, area, and WL. OSAMA's ability for effective partitioning is demonstrated by experimental results, which confirm that it dramatically lowers important design parameters in VLSI circuits.
Volume: 14
Issue: 2
Page: 365-374
Publish at: 2025-07-01

Enhancing TV program success prediction using machine learning by integrating people meter audience metrics with digital engagement metrics

10.11591/ijeecs.v39.i1.pp353-363
Khalid El Fayq , Said Tkatek , Lahcen Idouglid
With the emergence of numerous media services on the internet, television (TV) remains a highly demanded medium in terms of reliability and innovation, despite intense competition that compels us to devise strategies for maintaining audience engagement. A key indicator of a TV channel’s success is its reach, representing the percentage of the target audience that views the broadcasts. To aid TV channel managers, the industry is exploring new methods to predict TV reach with greater accuracy. This paper investigates the potential of advanced machine learning models in predicting TV program success by integrating people meter audience metrics with digital engagement metrics. Our approach combines convolutional neural networks (CNNs) for processing digital engagement data, long short-term memory (LSTM) networks for capturing temporal dependencies, and gaussian processes (GPs) for modeling uncertainties. Our results demonstrate that the best-performing hybrid model achieves a prediction accuracy of 95%. This study contributes to the field by addressing manual scheduling errors, financial losses, and decreased viewership, providing a more comprehensive understanding of audience behavior and enhancing predictive accuracy through the integration of diverse data sources and advanced machine learning techniques.
Volume: 39
Issue: 1
Page: 353-363
Publish at: 2025-07-01

Autonomous driving system and system hacking protection using V2X communication

10.11591/ijeecs.v39.i1.pp131-138
Eugene Rhee , Junhee Cho
In this paper, a new autonomous driving system is proposed and problems such as systematic errors that may occur in the autonomous driving system were solved through vehicle to everything (V2X) communication technology. In the actual driving environment, accidents caused by the absence of communication between drivers and communication with infrastructure are frequently exposed. To solve these problems, a system was established that linked V2X communication with a vehicle system. In order to predict and study how this technology works in real traffic situations, it requires a lot of time, manpower, and funds because it requires building an environment similar to real traffic situations and using measuring equipment. For this reason, the system was built with simple model, and the research was conducted through simple simulation. In addition, as network technology and sensing technology for autonomous vehicles develop, the risk of hacking is also increasing. In this paper, various expected attack paths and methods that can hack autonomous vehicles are explained, and methods for defending them are presented.
Volume: 39
Issue: 1
Page: 131-138
Publish at: 2025-07-01

Core methodological classes of text extraction and localization-a snapshot of approaches

10.11591/ijeecs.v39.i1.pp455-465
Dayananda Kodala Jayaram , Puttegowda Devegowda
The motivation to work on text extraction and localization is quite a substantial that potentially influences a larger area of application right from business intelligence to advanced data analytics. At present, there are massive archives of literatures addressing varying ranges of problems associated with text extraction and localization with an effective realization of respective contribution as well as on-going issues. However, problem statement is that all these massive implementation studies are further required to converge down in order to realize the core classes of methodologies involved in text extraction. Hence, this manuscript uses desk research methodology to address this issue by presenting a compact insight of core methodological classes where all the recent implementation work are converged down to understand its strength and weakness. The research outcome contributes towards facilitating information of current research trend and identified research gap. The proposed review study assists in undertaking decision of suitable approach of text extraction, localization, detection, recognition, and classification.
Volume: 39
Issue: 1
Page: 455-465
Publish at: 2025-07-01

Banking security and performance of islamic banks in middle east: the role of regulatory quality

10.11591/ijeecs.v39.i1.pp691-699
Mohammed Abd-Akarim Almomani , Adai Al-Momani
Transaction security is critical for the reputation and trust of banks. Few studies examined how transaction security can impact the financial performance of Islamic banks in developing countries with mixed results emerging in the literature. The research examines how transaction security affects bank financial performance. Three indicators are used to measure the financial performance and includes return on assets (ROA), return on equity (ROE), and Tobin’s Q. Regulatory quality are proposed as a moderating variable. Data was collected from 59 banks in MENA between 2015 and 2022. The results showed that transaction security affected positively ROE and Tobin’s Q. However, there is no significant effect on ROA. Regulatory quality moderated only the effect of transaction security on ROE and Tobin’s Q. Enhance the transaction security and improving the regulatory quality will enhance the financial performance of banks in MENA.
Volume: 39
Issue: 1
Page: 691-699
Publish at: 2025-07-01

Development of a web-based application for real-time eye disease classification system using artificial intelligence

10.11591/ijres.v14.i2.pp558-574
Kennedy Okokpujie , Adekoya Tolulope , Abidemi Orimogunje , Joshua Sokowonci Mommoh , Adaora Princess Ijeh , Mary Oluwafeyisayo Ogundele
The incorporation of artificial intelligence (AI) into the field of medicine has created new strategies in enhancing the detection of disease, with a focus on the identification of eye diseases such as glaucoma, diabetic retinopathy, and macular degeneration associated with age, which can lead to blindness if not detected and treated early enough. Driven by the need to combat blindness, which affects approximately 39 million people globally, according to the World Health Organization (WHO). This research offers a web-based, real time approach to classifying eye diseases from fundus images due to user friendliness. Three pre-trained convolutional neural network (CNN) models are adopted, namely ResNet-50, Inception-v3, and MobileNetV3. The models were trained on a dataset of 8000 fundus images subdivided into four classes: cataract, glaucoma, diabetic retinopathy, and normal eyes. The performance of the models was evaluated in 3-way (normal eye and two diseases) and 4-way (normal eye and three diseases). ResNet-50 had higher performances, with 98% and 97% accuracy in the respective classifications, compared to InceptionV3 and MobileNetV3. Consequently, ResNet-50 was used in an online application that made real-time diagnoses. This research findings reveal the potential of CNNs in the healthcare industry, particularly in reducing over-reliance on specialists and increasing access to quality diagnostic technologies. Especially in critical areas such as this with limited healthcare resources, where the technology can create significant gaps in disease detection and control.
Volume: 14
Issue: 2
Page: 558-574
Publish at: 2025-07-01

Predictive modelling of osteoporosis and effect of BMI on the risk of fracture in femur bone using COMSOL Multiphysics: a computational modelling approach

10.11591/ijeecs.v39.i1.pp89-100
Aleena Kamal , Minahil Kamal , Mashal Fatima , Syed Muddusir Hussain , Jawwad Sami Ur Rahman , Sathish Kumar Selvaperumal
This study explores the intricate relationship between osteoporosis, body mass index (BMI), and the risk of femur fractures using computational modeling. Osteoporosis is a silent metabolic disorder that depletes bone density and structure, significantly increasing the risk of fractures, particularly in weight-bearing bones such as the femur. To analyze the impact of mechanical stress on osteoporotic bones, COMSOL Multiphysics was utilized to simulate stress distribution in a femur under varying BMI conditions, providing valuable insights into how BMI influences bone health and fracture risk. A three-dimensional (3D) femur model was designed using computer-aided design (CAD) software, with specific material properties assigned for both healthy and osteoporotic bones. Finite element analysis was conducted by applying different load conditions, representing body weight, on the femur head. The results highlighted stress distribution and deformation patterns, identifying regions most prone to fracture. The findings demonstrate that while higher BMI typically correlates with increased bone density, it also leads to greater deformation in osteoporotic bones under stress, emphasizing the complex interplay between BMI and bone strength. These insights underscore BMI’s critical role in fracture risk management. Future research should incorporate advanced fracture mechanics models and clinical data to enhance predictive accuracy and develop targeted strategies for fracture prevention in osteoporotic patients.
Volume: 39
Issue: 1
Page: 89-100
Publish at: 2025-07-01

Enhanced fault detection in photovoltaic systems using an ensemble machine learning approach

10.11591/ijres.v14.i2.pp507-517
Mohammed Salah Ibrahim , Hussein k. Almulla , Anas D. Sallibi , Ahmed Adil Nafea , Aythem Khairi Kareem , Khattab M. Ali Alheeti
Malfunctioning of photovoltaic (PV) systems is a main issue affecting solar panels and other related components. Detecting such issues early leads to efficient energy production with low maintenance costs and high system performance consistency. This paper proposed an ensemble model (EM) for fault detection (FD) in PV systems. The proposed model utilized advanced machine learning algorithms containing random forest (RF), k-nearest neighbors (KNN), and gradient boosting (GB). Traditional approaches often do not handle the several situations that PV systems can have. Our EM leveraged the power of GB’s algorithm in handling complex data patterns through iterative boosting, KNN’s capability in capturing local data structures, and RF’s strength in handling overfitting and noise through its tree structure randomness. Combining these models enhanced fault detection capabilities, providing excellent accuracy compared to individual models. To evaluate the performance of our EM, different experiments were conducted. The results demonstrated substantial improvements in detection fault, achieving an accuracy rate of 95%. This accuracy rate considered high underscores the model’s capability to handle fault detection of PV systems, posing a consistent solution for instant fault detection and maintenance scheduling.
Volume: 14
Issue: 2
Page: 507-517
Publish at: 2025-07-01

Study on neuromorphic computation and its applications

10.11591/ijeecs.v39.i1.pp272-282
Anjali Chature , A. Raganna , Venkateshappa Venkateshappa
Neuromorphic computing offers a promising alternative to traditional von Neumann architectures, especially for applications that require efficient processing in edge environments. The challenge lies in optimizing spiking neural networks (SNNs) for these environments to achieve high computational efficiency, particularly in event-driven applications. This paper investigates the integration of advanced simulation tools, such as Simeuro and SuperNeuro, to enhance SNN performance on edge devices. Through comprehensive studies of various SNN models, a novel SNN design with optimized hardware components is proposed, focusing on energy and communication efficiency. The results demonstrate significant improvements in computational efficiency and performance, validating the potential of neuromorphic architectures for executing event-driven scientific applications. The findings suggest that neuromorphic computing can transform the way edge devices handle event-driven tasks, offering a pathway for future innovations in diverse application domains.
Volume: 39
Issue: 1
Page: 272-282
Publish at: 2025-07-01
1 2 3
...
1896 1897
Show 73 of 1897

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration