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

30,895 Article Results

Smart parking management system: a seamless parking solution using YOLO and QR code payment technology

10.11591/ijai.v15.i4.pp3614-3624
Sumit Kumar , Ruchi Rani , Sanjeev Kumar Pippal
The inefficiencies of traditional parking systems, including manual entry and reliance on sensors, as well as slow payment lines, contribute to congestion and a lower level of user satisfaction. This paper suggests a smart parking management system (SPMS) based on the license plate recognition (LPR) technology using you only look once version 5 (YOLOv5)modelincombination with a QR code based payment system, to automate the parking system. It’s able to detect vehicle license plates in real-time, which means that data doesn’t have to be entered manually, and it also avoids the need for physical sensors, which cuts down on infrastructure costs. With a centralized database, the efficient tracking of vehicles is achieved, and QR-based payment will facilitate contactless payments at exit. Experimental evaluation shows that the proposed system out performs than the other systems, with an accuracy of 98.09% and recall of 98.25% in case of LPR. This system drastically decreases processing time, congestion and improves overall user experience. SPMS is more efficient, scalable, and reliable than traditional and existing smart parking systems. The results show that the proposed method is a cost-effective and practical solution for solving the modern parking management problem.
Volume: 15
Issue: 4
Page: 3614-3624
Publish at: 2026-08-01

Real-time object detection for autonomous driving: a comparative study of YOLO and Faster R-CNN

10.11591/ijai.v15.i4.pp3581-3590
Madhura M. Bhosale , Yogesh S. Angal
Over the past few years, object detection has experienced remarkable progress and development, primarily driven by the development of one-stage and two-stage detection algorithms. Among these, Faster region-based convolutional neural network (Faster R-CNN) and you only look once (YOLO) have achieved notable success due to their strong performance and computational efficiency. Object detection plays a crucial role in various applications, particularly in autonomous driving systems, where accurate detection of pedestrians, vehicles, and road signs is essential for ensuring safety and reliability. This paper conducts a comparative evaluation of YOLO and Faster R-CNN to analyze their performance in autonomous driving environments. The experiments were conducted using the KITTI open-source dataset, which is widely used for benchmarking object detection models. All experiments were performed on an NVIDIA RTX A5000 GPU to ensure efficient computation, with implementations developed using Python version 3.9.13. The experimental findings indicate that YOLO surpasses Faster R-CNN in performance, attaining an accuracy rate of 90%. These findings highlight the effectiveness of YOLO for real-time object detection tasks, making it a suitable and preferred choice for time-sensitive applications such as autonomous driving systems.
Volume: 15
Issue: 4
Page: 3581-3590
Publish at: 2026-08-01

Long short-term memory based activity detection using skeleton joints data: a systematic review

10.11591/ijai.v15.i4.pp3026-3035
Bakkala Santha Kumar , R. Shankar
In today's security and surveillance applications, recognizing abnormal activity is critical component of identifying possible hazardous or unusual human behaviors. There is need for new technologies that can detect abnormal human behaviors precisely. The present review investigates various aspects of detection process, focusing on skeleton joints input data. It then explores adoption of deep learning (DL) architectures, such as long short-term memory (LSTMs) and transformers, to improve accuracy and robustness of recognition models. The review explores synergistic integration of LSTMs and transformers to improve recognition of unusual activity. By integrating LSTMs' processing capabilities and attention mechanisms of transformers, enhanced models can accurately identify intricate patterns of activity. Despite the advancements that have been made in the field, the challenges that remain are still related to recognition of unusual activities. These include lack of scalability for large datasets, need for models that can recognize complex behaviors across diverse applications, and need to ensure that detection is performed in a low-latency manner. The paper explores future directions of developing LSTM-based models that can recognize unusual activity using skeleton joint data in a cloud-based environment. The review emphasizes the potential of such solutions that can take advantage of the processing power of graphics processing units (GPUs) and tensor processing units (TPUs) and enable real-time recognition of activity in large datasets.
Volume: 15
Issue: 4
Page: 3026-3035
Publish at: 2026-08-01

GWO-optimized sparse Bayesian least squares regression for direction-of-arrival estimation in MIMO networks

10.11591/ijai.v15.i4.pp3431-3440
Anne Gowda Aleri Byregowda , Babu Nallur Venkateshappa , Anughna Narayanaswamy
Accurate direction-of-arrival (DOA) estimation is a critical requirement for massive multiple-input multiple-output (MIMO) systems operating in fifth-generation (5G) and beyond (5G/B5G) wireless environments. Although sparse Bayesian learning (SBL)–based techniques have demonstrated improved robustness by exploiting signal sparsity, their performance is often limited by fixed hyperparameter selection, sensitivity to noise, and suboptimal residual error minimization. To address these challenges, this paper proposes an optimized sparse Bayesian least squares regression (SBLSR) framework in which grey wolf optimization (GWO) is employed to adaptively optimize Bayesian hyperparameters and regression coefficients. The proposed approach jointly enforces sparsity and minimizes estimation error, enabling robust DOA estimation under dynamic noise conditions and varying network density. Extensive simulations conducted in a massive MIMO environment demonstrate that the optimized SBLSR consistently outperforms conventional SBLSR and state-of-the-art benchmark techniques in terms of root mean square error (RMSE), closely approaching the Cramér–Rao lower bound (CRLB) across a wide range of signal-to-noise ratios, sensor configurations, and Monte Carlo trials. The findings validate that the suggested optimized SBLSR framework offers a noise-resilient solution for high-precision DOA estimation in practical massive MIMO and MIMO radar systems.
Volume: 15
Issue: 4
Page: 3431-3440
Publish at: 2026-08-01

A hierarchical scholar expertise information system based on publication profiles and research records: a case in Universitas Diponegoro

10.11591/ijeecs.v43.i1.pp250-258
Eko Didik Widianto , Hadiyanto Hadiyanto , Teddy Mantoro , Raka Sindu Wardoyo , Muhamad Irham Maulana
One factor that boosts the reputation of higher education institutions (HEIs) in gaining competitive advantage is the research productivity of their scholars, including at Diponegoro University (Undip). However, existing studies focus on metrics and their measurement but lack discussion of systems for leveraging these metrics to promote these scholars’ expertise. This study proposes a scholars’ expertise information system at Undip based on their publications and research track records to bridge information between the campus and outside parties, namely industry, government, and society. It provides expertise searching and browsing facilities in Dewey’s hierarchy of subjects and the institutional structure hierarchy. Scholar publications and research data are retrieved using the science and technology index application program interface (SINTA API). The collected data included lecturer profiles, study programs, SINTA subjects, articles, research, community service, intellectual property rights (IPR), and books. It has been fully deployed and adopted online, presenting the expertise of Undip scholars based on their publications and research records. The finding shows that all pages perform well, with an average GTmetrix B grade and a performance score of 91%, a structure score of 88%, and a 1.8s loading time. With all the functionalities and performances of the system, this study contributes to developing an information system model to promote the expertise of university scholars, primarily based on their publications and research.
Volume: 43
Issue: 1
Page: 250-258
Publish at: 2026-07-01

FPGA based forest fires prediction system

10.11591/ijeecs.v43.i1.pp78-92
Faroudja Abid , Nouma Izeboudjen , Fatiha Louiz
This paper describes the idea of designing and implementing an field programmable gate array (FPGA) based system on chip (SoC) for forest fires prediction (FFP). The FFP in the proposed system is based on the decision tree (DT) algorithm implemented as an intellectual property (IP) in the FFP Zynq-SoC architecture that constitutes the processing part of a smart sensor node. This latter processes the collected meteorological data and takes decision locally at sensor node level; without having to send massive data to the base station for decision. The performance of the decision-tree software classifier in terms of accuracy and recall are about 75% and 0.88, respectively. The hardware implementation results of the DT -based forest fires prediction SoC show that the developed DT IP core is area and power efficient.
Volume: 43
Issue: 1
Page: 78-92
Publish at: 2026-07-01

Advanced state machine-sliding mode current control energy management for multi-source DC microgrid

10.11591/ijeecs.v43.i1.pp63-77
Hamza Rezigue , Mabrouk Khemliche , Samia Latreche , Badreddine Kanouni , Hamza Khemliche
This work addresses effective power management in a multi-source DC microgrid. An innovative energy management technique utilizing a state machine control (SMC) integrated with a sliding mode current control (SMCC) has been developed. This approach offers advantages through its equitable distribution of power among sources, storage devices, and demand loads, thereby optimizing the flow rate, discharge, and charge cycles of energy storage devices; additionally, it improves the response time of PEMFC power across various states in comparison to a conventional PI controller. The SMC-SMCC has proposed nine scenarios, categorized into three state of charge (SOC) situations, to fulfill a predetermined set of parameters for the operation of the DC microgrid. Simulation studies conducted with a precise model in MATLAB/Simulink have demonstrated that the proposed SMC-SMCC is proficient in achieving effective power sharing, rapid DC link voltage control in terms of stability, and maintaining the SOC within its constraints; additionally, the SMC-SMCC exhibits a quicker response time compared to conventional SMC-PI.
Volume: 43
Issue: 1
Page: 63-77
Publish at: 2026-07-01

Automated drone-assisted detection system for rice leaf pathologies a deep learning approach

10.11591/ijeecs.v43.i1.pp148-156
Erfan Rohadi , Cahya Rahmad , Septian Enggar Sukmana , Aida Sartimbul , Kismet Anak Hong Ping , Dimas Rosiawan , Ahmad Afifuddin Zakki
Early and accurate detection of plant diseases is vital for maintaining agricultural productivity. This study investigates an automated disease identification system specifically designed for the IR64 rice cultivar. By combining drone-captured aerial imagery (UAV) taken during the plant's vegetative stage with public datasets, we established a comprehensive training dataset. The study evaluates and compares four convolutional neural network (CNN) architectures, InceptionV3, ResNet50, EfficientNetV2S, and MobileNetV2, assessing their predictive accuracy and real-world computational efficiency. Our 10-fold cross-validation results indicate varying levels of inference speed and accuracy among the models. InceptionV3 and MobileNetV2 displayed the highest stability and minimal misclassification rates across multiple disease types. In contrast, the performance of ResNet50 and EfficientNetV2S fluctuated significantly depending on the detected pathogen. In conclusion, coupling UAV imagery with fine-tuned deep learning models provides a fast, scalable solution for continuous crop monitoring and precision agriculture.
Volume: 43
Issue: 1
Page: 148-156
Publish at: 2026-07-01

Smart panel design for renewable energy generation

10.11591/ijeecs.v43.i1.pp18-27
Rudi Syahputra , Nelly Safitri , Fauzan Fauzan , Yassir Yassir , Teuku Hasannuddin , Akhyar Akhyar , Radhiah Radhiah , Zulfikar Zulfikar
The aim of this study is to design and develop a smart panel module specifically for solar power generation, which includes three critical functions: the automatic transfer switch (ATS), the automatic main failure (AMF), and capabilities for remote monitoring and control. The ATS and AMF features employ Haiwell AT12MOT Ethernet PLC control equipment in conjunction with the Haiwell B7H Ethernet IoT cloud HMI, both designed for remote operation through an IoT system and integrated with the Haiwell cloud application. The developed PLC program interacts with HMI software that is created using NB designer. Inputs from the PLC are monitored and managed via the Haiwell cloud application, which connects with the relay designated as input for the Haiwell AT12MOT PLC. The resulting design interfaces with the PLC output located within an electrical panel specifically designed to handle industrial loads. This research results in a smart panel capable of operating in an industrial context with a power capacity of 2,200 VA. It is noteworthy that during automatic operations, load transfers between solar power systems and PLN (the national grid company of Indonesia) do not occur instantaneously; instead, there is a delay of 10 seconds as the system stabilizes back to normal conditions.
Volume: 43
Issue: 1
Page: 18-27
Publish at: 2026-07-01

Insights on routing and scheduling approaches in the IoT from the perspective of energy, QoS, and security–a systematic review

10.11591/ijeecs.v43.i1.pp335-344
Rajeshwari Kenchammana Hosakote Nanjappa , Manuvinakurike Narasimha Sastry Suma
The internet of things (IoT) has been conceptualized to bring more efficient and seamless connectivity to a large number of low-power and low-cost embedded devices. In the context of IoT, limited radio resources create new challenges, such as collisions and access conflicts. Another challenge arises in dealing with energy constraints, as battery-powered IoT sensors have limited energy capacity in the sensing layer. Consequently, routing mechanisms play a fundamental role in dealing with route optimization and reliable data transmission problems in the transport layer, whereas broadcast and link scheduling are also considered as appealing solutions for fulfilling the energy efficiency, collision-free transmissions and latency requirements in the IoT. Also, security vulnerabilities are hard to identify in the IoT perception and transport layer due to its ad-hoc network topological factors. Thus, deploying efficient routing schemes in IoT demands effective collaborative solutions for cost-effective and secure route formation with energy-aware scheduling performance, which were not, explored much in the past. This investigation thereby analyses the strengths and limitations of existing efficient routing and scheduling solutions in IoT and extracts the critical findings which could provide quick survey to many researchers in this application area.
Volume: 43
Issue: 1
Page: 335-344
Publish at: 2026-07-01

Analysis of OFDM and filter bank multicarrier with offset quadrature amplitude modulation for 5G communication: a comparative study

10.11591/ijeecs.v43.i1.pp127-138
Magda Yousef Mοhаmеd , Esraa M. Eid , Mohammed Abo-Zahhad , Ahmed Hassan Еldеib
Emerging applications for 5G and beyond require wireless communication systems with high spectral efficiency, low latency, reliable synchronization, and robust channel estimation techniques. This paper presents a comparative analysis between orthogonal frequency division multiplexing (OFDM) and filter bank multicarrier with offset quadrature amplitude modulation (FBMC/OQAM) under identical simulation conditions. The comparison is performed in terms of spectral efficiency, power spectral density (PSD), bit error rate (BER), peak-to-average power ratio (PAPR), and channel estimation performance. Simulation results show that FBMC/OQAM has higher spectral efficiency and significantly reduced out-of-band (OOB) emissions than OFDM due to its superior spectral containment. Moreover, FBMC/OQAM provides better channel estimation performance in the frequency-selective multipath fading environment. On the other hand, OFDM has lower computational complexity and better PAPR performance. The obtained results highlight the performance differences between OFDM and FBMC/OQAM systems and demonstrate the potential of FBMC/OQAM as a promising waveform candidate for future wireless communication systems.
Volume: 43
Issue: 1
Page: 127-138
Publish at: 2026-07-01

Deep Q learning algorithm for detecting DDoS attacks on IoT devices

10.11591/ijeecs.v43.i1.pp299-313
Lana Kamla Ahmed , Kayhan Zrar Ghafoor
The rapid expansion of internet of things (IoT) networks has heightened security risks, particularly regarding distributed denial of service (DDoS) attacks against devices with limited computing capacity. High detection accuracy is crucial for these resource-constrained environments, where false positives can disrupt legitimate traffic and false negatives allow attacks to persist. However, modern reinforcement learning (RL) and machine learning (ML) intrusion detection solutions often exhibit poor generalization due to static state representations. To address this, this paper proposes a deep Q-learning (DQL) framework that integrates K-means clustering directly into the RL action space. Unlike prior RL-based IDS models, our approach dynamically integrates clustering into the learning process, enabling adaptive state representation and improved generalization to unseen traffic patterns. The system is formulated as a Markov decision process where the agent optimizes a composite reward function based on accuracy, precision, recall, and F1-score. Evaluated on the N-BaIoT dataset using 10-fold cross-validation, the proposed method achieves a classification accuracy of 98.95% and a weighted F1-score of 98.73%, significantly outperforming traditional ML and RL baselines. These results demonstrate the framework's effectiveness as a scalable, adaptive solution for intelligent IoT DDoS detection.
Volume: 43
Issue: 1
Page: 299-313
Publish at: 2026-07-01

Dung-beetle-optimization algorithm-based P-I-D controller for a separately excited DC-motor

10.11591/ijeecs.v43.i1.pp93-102
Kerrache Soumia , Haidas Mohammed
Understanding the proportional, integral, and derivative (P-I-D) control system is crucial for optimizing its parameters to achieve the desired system performance. The proportional gain determines how aggressively the system responds to the error, while the integral gain helps to eliminate any steady state error. The derivative gain plays a role in stabilizing the system by damping out any oscillations caused by sudden changes in the error. P-I-D control is a widely used control technique in various engineering applications, including the control of DC-motors, which is refers to adjust the motor’s input voltage, current, speed or position in order to achieve a desired output. One approach to tuning P-I-D parameters is the ziegler nichols (ZN) methods, where the first one involves to plot the step response of the model’s open loop with its tangent line. The other method conists systematically increasing the gains until the system becomes unstable, and then adjusting the gains to find the ultimate gain and ultimate period. One of the main advantages of metaheuristic algorithms is their ability to quickly converge to near-optimal solutions without getting stuck in local optima. This is achieved by using a combination of exploration and exploitation strategies to efficiently search through the solution space. Within our study, we seek to incorporate the Dung-Beetle based optimization algorithm (DBO) to adjust the P-I-D controller for a separately excited DC-motor’s (SEDCM) speed control using MATLAB-software relies on the objective functions: the integral absolue error (IAE), the integral squared error (ISE) and the integral time absolue error (ITAE). The results obtained are compared in their best performances on rise time, settling time, overshoot, peak response and peak time.
Volume: 43
Issue: 1
Page: 93-102
Publish at: 2026-07-01

Electrical engineering in the era of autonomous intelligence: building sustainable, resilient, and self-evolving energy systems

10.11591/ijeecs.v43.i1.pp1-6
Tole Sutikno
Electrical engineering is entering a transformative era in which autonomous intelligence is becoming an integral component of modern energy infrastructures rather than merely an auxiliary computational tool. The convergence of advanced power electronics, renewable energy technologies, intelligent sensing, edge computing, artificial intelligence, and high-speed communications is enabling electrical systems to evolve from passive and centrally controlled networks into adaptive, resilient, and self-evolving ecosystems. This editorial discusses the emerging paradigm of autonomous electrical engineering, where future power systems are expected to perceive operating conditions, learn from historical and real-time data, predict disturbances, and autonomously optimize their performance while maintaining reliability, security, and sustainability. Beyond conventional objectives such as efficiency and stability, next-generation electrical systems must address increasing renewable penetration, distributed energy resources, electrified transportation, cyber-physical security, and climate resilience. The editorial also highlights several promising research directions, including AI native power system operation, autonomous microgrids, digital twins, physics-informed intelligence, trustworthy and explainable AI, intelligent power electronic converters, and coordinated human–AI decision-making. These developments position electrical engineering as a foundational discipline for achieving sustainable development and future energy transition, while emphasizing that autonomous intelligence should augment engineering expertise to create safer, more reliable, and environmentally responsible electrical infrastructures.
Volume: 43
Issue: 1
Page: 1-6
Publish at: 2026-07-01

Coral classification in underwater images using a dual-branch deep learning framework

10.11591/ijeecs.v43.i1.pp207-218
Pracharat Sa-ngadsup , Chawan Koopipat
Automated coral classification from underwater imagery is essential for large-scale reef monitoring but remains challenging due to color attenuation, illumination variability, and differences between texture-focused close- range images and morphology-focused colony-level observations. To address these challenges, this study proposes a dual-branch convolutional neural network that integrates information from the CIELAB (LAB) color space with structural descriptors derived from the discrete wavelet transform (DWT). RGB images are first converted to the LAB color space to separate luminance and chromatic components in separate channels, enabling the model to exploit color and lightness information more explicitly. Structural information is extracted from the luminance channel using wavelet decomposition to capture high-frequency morphological patterns. The two representations are processed through parallel convolutional branches and fused at the feature level for classification. Experiments conducted on a unified coral dataset containing texture dominant and morphology-focused imagery across 14 classes show that the proposed method achieves 96.52% accuracy on the texture-focused RSMAS dataset and 88.33% accuracy on the morphology-focused structure RSMAS dataset, reducing the cross-domain performance gap from 22.46% to 8.19% compared with RGB baselines, demonstrating improved cross domain robustness for coral classification under heterogeneous underwater imaging conditions.
Volume: 43
Issue: 1
Page: 207-218
Publish at: 2026-07-01
1 2 3
...
2059 2060
Show 22 of 2060

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