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

31,456 Article Results

Securing Defi: a comprehensive review of ML approaches for detecting smart contract vulnerabilities and threats

10.11591/ijict.v15i1.pp438-446
Dhivyalakshmi Venkatraman , Manikandan Kuppusamy
The rapid evolution of decentralized finance (DeFi) has brought revolutionary innovations to global financial systems; however, it has also revealed some major security vulnerabilities, especially of smart contracts. Traditional auditing methods and static analysis tools are prone to fail in identifying sophisticated threats, including reentrancy attacks, front-running, oracle manipulation, and honeypots. This review discusses the growing role of machine learning (ML) in enhancing the security of DeFi systems. It provides a comprehensive overview of modern ML-based methods related to the detection of smart contract vulnerabilities, transaction-level fraud detection, and oracle trust assessment. The paper also provides publicly available datasets, necessary toolkits, and architectural designs used for developing and testing these models. Additionally, it provides future directions like federated learning, explainable AI, real-time mempool inspection, and cross-chain intelligence sharing. While it is full of promise, the application of ML in DeFi security is plagued by issues like data scarcity, interoperability, and explainability. This paper concludes by highlighting the need for standardised benchmarks, shared data initiatives, and the integration of ML into development pipelines to deliver secure, scalable, and reliable DeFi ecosystems.
Volume: 15
Issue: 1
Page: 438-446
Publish at: 2026-03-01

Improving the energy efficiency of two-speed motors through the use of new pole-switched windings

10.11591/ijpeds.v17.i1.pp195-210
Zhanat Issabekov , Dauletbek Rismukhamedov , Khusniddin Shamsutdionov , Shakhobiddin Husanov , Sabit Rismukhamedov , Bibigul Issabekova , Assemgul Zhantlessova
This article addresses the design and manufacturing of two-speed asynchronous motors with pole-changing windings. The need for developing two-speed motors with a single pole-changing winding is justified from the standpoint of energy and resource efficiency, as well as improved starting performance of high-power electric drives. An analysis of existing pole-changing winding designs is presented, highlighting their practical limitations in industrial applications. A new pole-changing winding with a 4/2 pole ratio and 48 stator slots was developed using the discrete spatial functions method based on star–delta–double star configurations. The electromagnetic characteristics of the proposed winding were analyzed. Based on this design, a new 4A200L8/4U3 two-speed motor was manufactured and tested under production conditions at the energy motors plant. Experimental results show that at p1 = 4 pole pairs the motor delivers P2 = 20 kW with efficiency η = 87%, cos φ = 0.82, I1 = 43 A at slip s = 2.35%, while at p2 = 2 pole pairs it develops P2 = 36 kW with efficiency η = 91.5%, cos φ = 0.906, I1 = 66 A at slip s = 1.5%. The results confirm more efficient utilization of the active magnetic core at lower polarity and demonstrate the feasibility of implementing such motors for energy-saving applications in heavy-duty drives requiring two equivalent operating speeds.
Volume: 17
Issue: 1
Page: 195-210
Publish at: 2026-03-01

A novel technique for induction heating dryer with temperature and voltage control for power inverter

10.11591/ijpeds.v17.i1.pp438-452
Jeerapong Srivichai , Kittaya Somsai , Akkachai Phuphanin , Nithiroth Pornsuwancharoen
This study presents a novel prototype of an induction heating dryer integrating hysteresis control with phase-shifted pulse width modulation (PWM) for the first time. The system replaces conventional resistance heating, improving energy efficiency and thermal stability. The 2 kW prototype comprises a drying chamber and a hot air unit with controlled airflow of 1.5 m/s. Phase angle adjustment reduces voltage, current, and power consumption while maintaining the power factor within acceptable limits. The temperature control maintains stability within ±1 °C of the setpoint. The results demonstrate fast, energy-efficient, and precise drying, offering potential benefits for food processing and textile industries, and providing a foundation for future development of intelligent, energy-efficient induction dryers.
Volume: 17
Issue: 1
Page: 438-452
Publish at: 2026-03-01

Fuzzy logic-based driver fatigue prediction system for safe and eco-friendly driving

10.11591/ijict.v15i1.pp84-92
Raghavan Sheeja , Chidambaranathan Bibin , Selvaraj Vanaja , Shakeela Joy Arul Dhas , Alex Arockia Abins , Padmavathi Balasubramaniam
The advancement of intelligent car systems in recent years has been significantly influenced by developments in information technology. Driver fatigue is a dominant problem in car accidents. The goal of advanced driving assistance is to develop an advanced driving assistance system (ADAS) a eco-friendly model which focuses on the detection of drowsy driver, to notify drivers of their fatigued condition to prevent accidents on the roads. With relation to driving, the driver mustn’t be distracted by alarms when they are not tired. The answer to this unanswered question is provided by 60- second photograph sequences that were taken when the subject’s face was visible. To reduce false positives, two alternative solutions for determining whether the driver is drowsy have been developed. To extract numerical data from photos and feed it into a fuzzy logic-based system, convolutional network is applied initially; later deep learning technique is followed. The fuzzy logic-based solution avoids the false alarm of the system.
Volume: 15
Issue: 1
Page: 84-92
Publish at: 2026-03-01

Lightweight deep learning approach for retinal OCT image classification: A CNN with hybrid pooling and optimized learning

10.11591/ijict.v15i1.pp414-427
Parth R. Dave , Nikunj H. Domadiya
Optical coherence tomography (OCT) is a non-invasive technique through which a retina specialist can see the structure behind the eye. This technol ogy offers a key role to identify various abnormalities in the retina: Drusen, diabetic macular edema (DME) and choroidal neovascularization (CNV). However, manual analysis of OCT scans can be time-consuming and prone to variability among clinicians. To address this challenge, we present a lightweight and explainable deep learning-based approach for automatic classification of retinal OCT images. The primary goal of this research is a model that delivers high diagnostic accuracy. A computer-aided suggestive method can help retinal doctors automatically classify the anomalies with more confidence and precision. In this paper, we proposed a novel approach based on deep learning: a six-layer convolutional neural network (CNN) integrated with hybrid pooling for effective feature extraction. Data augmentation and exponential learning rate is implemented to handle data imbalance between classes and for stabilized learning consecutively. Our proposed approach achieved 98.75% of accuracy while testing on the dataset. To further enhance the interpretability of the model, we also integrate explainable AI (XAI) using class activation mapping (CAM) to visualize the critical regions in the retina that contribute to the classification decisions.
Volume: 15
Issue: 1
Page: 414-427
Publish at: 2026-03-01

Multi-carrier PWM techniques to assess the performance of a 5-level diode clamped multilevel inverter fed PMSM drive

10.11591/ijpeds.v17.i1.pp582-592
K. Lakshmi , T. Vijay Muni , P. Hari Krishna Prasad , Budi Srinivasa Rao , G. Nageswara Rao , K. B. Anilkumar
The advantages of multilevel inverters (MLIs) have led to their increased use in high- and medium-voltage power applications. These inverters reduce harmonic content, common-mode voltage, dv/dt stress on switches, and electromagnetic interference, among other things. In recent decades, drives for permanent magnet synchronous machines (PMSMs) that rely on inverters have become increasingly popular in both commercial and residential settings due to their great performance. Phase disposition (PD), phase opposition disposition (POD), and alternate phase opposition disposition (APOD) are three multi-carrier pulse width modulation (MCPWM) approaches that were simulated in this work to explore a 5-level DCMLI-fed PMSM. In order to create control pulses, each method compares reference signals with carrier signals that are either triangular or trapezoidal. Detailed comparisons with conventional three-level voltage source inverters (VSIs) are made based on the results. A 63.21 percent improvement in the total harmonic distortion (THD) of the output voltage and a 26.52% improvement in the THD of the stator current are both supported by experimental evidence.
Volume: 17
Issue: 1
Page: 582-592
Publish at: 2026-03-01

Practice-based teaching using an AI platform to strengthen faculty competency

10.11591/ijict.v15i1.pp171-178
Angsana Phonsuk , Phakharach Plirdpring
This research aimed to i) analyze faculty members’ knowledge, understanding, and skills in using AI for practice-based teaching enhancement, ii) evaluate factors affecting faculty readiness in integrating AI into teaching processes, and iii) design and develop an AI platform to enhance faculty competency in practice-based teaching. The questionnaire, validated by five experts, was administered to 200 respondents divided into two groups: 100 faculty members from public universities and 100 from private universities. Comparative analysis revealed that public university faculty and private university faculty statistically significant differences in challenges and concerns at the 05 level, with public university faculty expressing higher concerns. Significant differences were found in AI experience and skills, attitudes toward AI use, and challenges and concerns. However, no significant differences were observed in three other areas: AI knowledge and understanding, AI readiness, and belief in AI’s effectiveness for practice-based learning enhancement. Data from both groups were utilized in designing and developing the AI platform to enhance practicebased teaching competency in higher education. Expert evaluation of the platform’s suitability showed high levels of demand for the AI platform and high appropriateness of the technology used in platform development.
Volume: 15
Issue: 1
Page: 171-178
Publish at: 2026-03-01

Privacy-preserving fitness recommendation system using modified seagull monarch butterfly optimized deep learning model

10.11591/ijict.v15i1.pp393-404
Esmita Gupta , Shilpa Shinde
This paper presents a novel modified seagull monarch butterfly optimization (MSMBO) algorithm, with a multi-objective focus on privacy and personalization in the fitness recommender system using a refined three-tier deep learning structure. The method is divided into three phases. In the first phase, fitness data from wearable devices undergoes preprocessing to eliminate noise and standardize features. The second phase incorporates improved elliptic curve cryptography (IECC) alongside the MSMBO to encrypt user data securely, ensuring privacy in cloud storage. This phase also enhances neural network performance by optimizing weights and hyperparameters through feature selection, effectively reducing data complexity while boosting accuracy. In the third phase, ConvCaps extracts spatial data features, while Bi-LSTM identifies temporal dependencies. The proposed system balances multiple objectives like novelty, accuracy, and precision, while safeguarding user data through robust encryption. With the experimental findings, our suggested method performs better than current existing models, especially in heart rate prediction and fitness pattern identification. The overall outcome makes the system ideal for privacyconscious, personalized fitness recommendations. The model’s shows significant improvement in mean squared error (MSE), normalized mean squared error (NMSE), and mean absolute percentage error (MAPE), thus verifying its effectiveness in secure, real-time fitness tracking.
Volume: 15
Issue: 1
Page: 393-404
Publish at: 2026-03-01

MPC and FOC for LVRT performance in hybrid renewable energy systems

10.11591/ijpeds.v17.i1.pp405-413
Oday Saad Fares , Riyadh G. Omar , Kassim A. Al-Anbarri
This paper proposes a wind and solar energy-based hybrid generation system integrated with a photovoltaic (PV) array controlled using model predictive control (MPC) and a doubly fed induction generator (DFIG) wind turbine controlled using field-oriented control (FOC). The system employs cascaded-based and bridge-based structures for two renewable sources, and they are connected to an ordinary common load, and designed to meet the stringent conditions of low-voltage ride-through (LVRT) required during fault conditions and grid-side perturbations. In order to safeguard the power electronic converter from sharp voltage dips, a crowbar protection circuit is used on the rotor side of the DFIG. In order to verify the enhanced LVRT capability of the offered system, extensive modeling, control design, implementation steps, and numerous simulation results have been included. The use of sophisticated control methodologies and protective measures improves the reliability and stability of wind-solar power plants. Simulation results reveal that for a serious grid disturbance, the system manages to maintain the output voltage at 70% of its nominal value and keeps the waveform steady and sinusoidal. In addition, the control scheme ensures that the rotor current is not just sinusoidal but also well-balanced, yielding a steady-state electromagnetic torque. This combination of control and protective measures is paramount for achieving stability, power quality, and reliability in current hybrid renewable power systems.
Volume: 17
Issue: 1
Page: 405-413
Publish at: 2026-03-01

A decision support system for mushroom classification using Naïve Bayesian algorithm

10.11591/ijict.v15i1.pp138-151
Vilchor G. Perdido , Thelma D. Palaoag
Mushrooms are rich in vitamins and proteins, a well-known superfood, however, cases of harmful mushroom consumption worldwide result in hallucinations, illness, or death. A significant challenge is that some poisonous mushrooms closely resemble edible varieties, making it difficult for mushroom foragers to distinguish between them. This study introduced KabuTeach, a decision support system (DSS) designed to classify mushrooms based on their morphological characteristics using the Naïve Bayes (NB) algorithm. The classification model was applied to a real-world dataset of 8,124 instances from Kaggle, containing 23 attributes. Evaluation metrics, including accuracy, recall, precision, specificity, and F1-score, were used to assess the classifier’s performance. Results indicated that the NB classification algorithm integrated into KabuTeach achieved a high accuracy level of 89.13%, using a 70:30 data split and 5-fold cross-validation approaches. The 0.98 AUC (area under the curve) value further concluded that the model was excellent in classifying between edible and poisonous mushrooms. These findings showed that KabuTeach is a reliable classification tool that aids mushroom foragers in differentiating mushrooms and promoting safer consumption practices. This innovation in agricultural technology could potentially reduce health risks by minimizing accidental ingestion of toxic mushrooms, ultimately contributing to public health safety.
Volume: 15
Issue: 1
Page: 138-151
Publish at: 2026-03-01

Design and implementation of a buck converter-based PV emulator using dynamic evolution control

10.11591/ijpeds.v17.i1.pp809-822
Ahmad Saudi Samosir , Dikpride Despa , Herri Gusmedi , Sony Ferbangkara
This paper presents the design, simulation, and experimental implementation of a photovoltaic (PV) emulator based on a buck converter controlled using the dynamic evolution control (DEC) technique. The proposed system accurately reproduces the nonlinear current-voltage (I-V) and power-voltage (P-V) characteristics of a commercial GREEN CELL SM100-18P (100 Wp) PV module under standard test conditions (1000 W/m2, 25 °C). The electrical characteristics of the reference module are embedded in the controller through a lookup table (LUT), which is integrated with the DEC algorithm to enable adaptive real-time regulation of output voltage and current. System modeling and validation are first conducted in MATLAB/Simulink to analyze steady-state and transient performance. A hardware prototype based on an XL4016 buck converter and Arduino Nano microcontroller is then implemented, with real-time monitoring provided via an ILI9341 TFT display. Experimental results show that the emulator achieves a maximum power deviation of 0.8%, a normalized root mean square error (RMSE) of 0.015, a settling time of approximately 12 ms, overshoot below 1.5%, voltage ripple under 2%, and peak conversion efficiency of 94% near the MPP region. These results confirm that the proposed PV emulator provides accurate static and dynamic reproduction of PV characteristics, offering a low-cost, stable, and repeatable platform for laboratory-scale evaluation of PV-related power electronic converters.
Volume: 17
Issue: 1
Page: 809-822
Publish at: 2026-03-01

A comparative study and design investigation: scalable magnitude comparators across technology nodes

10.11591/ijict.v15i1.pp13-20
Anitha Juliette Albert , Umamaheswari Ramalingam , Ashlin Leon A. S. , Sinthia Panneer Selvam , Sripriya Thiagarajan , Arunkumar Kuppusamy
In recent times, the convergence of innovative design technologies such as very large-scale integration (VLSI), cadence design systems, and fieldprogrammable gate array (FPGA) has become crucial to address the growing demand for enhanced efficiency, scalability, and reduced power consumption in electronic designs. This paper introduces a novel approach to designing non-pipelined and pipelined scalable magnitude comparators (MCs), which integrates 4-bit MCs. The frontend implementation of the MCs is achieved using quartus prime, an FPGA board. The backend implementation is done using cadence design system, evaluated across the three distinct CMOS technology nodes. The literature review highlights the influence of technology scaling on area, power consumption, and propagation delay, analyzing various comparator designs and their associated trade-offs. The results provide valuable insights into the design and optimization of MCs for future applications in image processing and nano computing.
Volume: 15
Issue: 1
Page: 13-20
Publish at: 2026-03-01

The effects of surface albedo and photovoltaic system tilt angle on improving light energy utilization efficiency

10.11591/ijpeds.v17.i1.pp740-751
Ahmed Daud Mosheer , Ahmed Hussein Duhis , Hussain Abdulkarim Hammas
The ground-surface reflection (albedo) significantly influences the amount of solar radiation absorbed by photovoltaic panels and, thus, the optimum tilt angle for maximizing annual energy generation. Nevertheless, the majority of design models presume a constant albedo value, therefore could not accurately represent actual field conditions. This study aims to identify the optimal tilt angle for each albedo value that maximizes the annual energy output of a stationary on-grid photovoltaic system of 20.48 kWp installed in Baghdad, Iraq. Seven albedo values, varying from 0.09 to 0.87, were simulated using PVsyst software, with the reference case established at an albedo of 0.2 and a tilt angle of 31°. The results indicate that the optimum tilt angle is directly proportional to the surface reflection. For albedo levels below the reference of 0.2 (0.18 and 0.09), increased energy generation occurred at reduced tilt angles of 30.5° and 29°, respectively. Conversely, for increased albedo values (i.e., exceeding the reference of 0.2, spanning from 0.25 to 0.87), greater tilt angles were necessitated, reaching 45° at an albedo of 0.87, where the annual energy rose from 35.212 to 36.999 MWh/yr, signifying a 5.07% increase relative to the reference condition. The results validate that the optimal tilt angle fluctuates with ground-surface albedo, as surface reflectivity affects solar irradiation and energy output. Integrating actual albedo values in photovoltaic models is crucial for precise tilt adjustment and enhanced system efficiency.
Volume: 17
Issue: 1
Page: 740-751
Publish at: 2026-03-01

Enhancing SAPF performance with VOC and SVM for electrical networks depollution

10.11591/ijpeds.v17.i1.pp593-601
Kamal Bayoude , Mohamed Moutchou , Yassine Zahraoui
This paper presents a significant enhancement in the filtering performance of shunt active power filters (SAPF) by leveraging the voltage oriented control(VOC) in combination with a three-level NPC inverter using space vector modulation (SVM). The VOC technique enables precise control of the SAPF by utilizing the orientation of the voltages, thereby optimizing harmonic compensation and reference tracking. Incorporating a three-level inverter allows for more refined voltage modulation, resulting in a substantial reduction in injected harmonic content. Simulation results from MATLAB/Simulink demonstrate the effectiveness of this approach. Before compensation, the measured total harmonic distortion (THD) reaches 27.98%, exceeding the IEEE 519-1992 standard threshold of 5%. However, after applying the SAPF, the THD drops to 0.85%, aligning with international standards for power quality. The figures included in the study illustrate the stability of the phase-locked loop(PLL)voltages and the noticeable improvement in the source current waveforms, which exhibit a near-sinusoidal profile after filtering. These findings validate the superiority of the VOC strategy coupled with an NPC inverter and SVM in effectively mitigating harmonic distortions and enhancing power quality in modern electrical networks.
Volume: 17
Issue: 1
Page: 593-601
Publish at: 2026-03-01

Reputation-enhanced two-way hybrid algorithm for detecting attacks in WSN

10.11591/ijict.v15i1.pp428-437
Divya Bharathi Selvaraj , Veni Sundaram
Wireless sensor networks (WSNs) are susceptible to a variety of attacks, such as data tampering attacks, blackhole attacks, and grayhole attacks, that can affect the reliability of communication. We proposed a reputationenhanced two-way hybrid algorithm (RCHA) that uses cryptographic hash functions and reputation-based trust management to detect and de-escalate attacks accurately. The RCHA algorithm implements two hash functions RACE integrity primitives’ evaluation message digest (RIPEMD) and secure hash algorithm (SHA-3), to initiate the integrity check for the entire packet sent across the network. Every node in the WSN tracks a reputation score for each neighbor the node is connected to, and this score is dynamically updated based on the behavior of each neighbor. If a neighboring node’s reputation drops below a threshold, the node is sent a maliciousness designation. At that time, the node will broadcast an alert message to its neighboring nodes and begin to reroute its data through one of its trusted neighbors to ensure the reliability of the communication. The simulation results reported that the RCHA algorithm improved the accuracy of the attack detection rate and the number of packets delivered compared to traditional attack detection methods. The RCHA algorithm was able to maintain low computational and energy overhead for the WSN, making it an attractive option for a resource-constrained application in a WSN. Given the trends towards more collaborative networks, the reputation mechanism in the RCHA algorithm improves the overall reliability and capabilities of the WSN, regardless of adversaries.
Volume: 15
Issue: 1
Page: 428-437
Publish at: 2026-03-01
1 2 3
...
2097 2098
Show 126 of 2098

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