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

24,371 Article Results

Video conferencing algorithms for enhanced access to mental healthcare services in cloud-powered telepsychiatry

10.11591/ijece.v15i1.pp1142-1151
Rajagopalan Senkamalavalli , Subramaniyan Nesamony Sheela Evangelin Prasad , Mahalingam Shobana , Chellaiyan Bharathi Sri , Rajendar Sandiri , Jayavarapu Karthik , Subbiah Murugan
Exploring the video conferencing algorithms for cloud-powered telepsychiatry to improve mental healthcare access. The goal is to evaluate and optimise these algorithms' latency, bandwidth utilisation, packet loss, and jitter across worldwide locations. To provide a smooth and high-quality virtual consultation between patients and mental health providers. Using performance data to identify areas for development, the effort aims to lower technological hurdles and increase telepsychiatry session dependability. Findings will help create strong, efficient algorithms that can handle different network situations, increasing patient outcomes and extending mental healthcare services. In the 1st instance latent analysis in a sample of 5 cities, the average latency (ms) is 45, the peak latency is 120, the off-peak latency is 30, and the packet loss is 0.5. In another instance, bandwidth utilisation in a sample of 5 sessions ranged from 30 to 120 minutes, with data supplied in MB - 150-600 and received in MB - 160-620, with average bandwidth (Mbps) - 5-15 and maximum bandwidth: 10-20.
Volume: 15
Issue: 1
Page: 1142-1151
Publish at: 2025-02-01

Adaptive control techniques for improving anti-lock braking system performance in diverse friction scenarios

10.11591/ijece.v15i1.pp260-279
Mohammed Fadhl Abdullah , Gehad Ali Abdulrahman Qasem , Mazen Farid Ramadhan , Heng Siong Lim , Chin Poo Lee , Nasr Alsakkaf Alsakkaf
Anti-lock braking systems (ABS) enhance vehicle safety by preventing wheel lock-up, but their effectiveness depends on tire-road friction. Traditional braking systems struggle to maintain effective performance due to the risk of wheel lock-up on varying road surfaces, affecting vehicle stability and control. This study presents a novel method to improve ABS efficiency across varying friction conditions. The proposed approach employs a feedback control mechanism to dynamically adjust the braking force of each wheel based on the prevailing friction coefficient. Specifically, we incorporate a P-controller in the input signal and two additional P-controllers as output and input parameters for friction. By manipulating the proportional control values, key parameters such as wheel speed, stopping distance, and slip rate can be effectively managed. Notably, our investigation reveals intriguing interactions between the proportional controls, highlighting the complexity of ABS optimization. The method was evaluated through simulations across various friction conditions, comparing it to conventional ABS in terms of brake performance, stability, and stopping distances. The results indicate that the proposed method significantly enhances ABS performance across varying friction coefficients; however, additional research is warranted to address stopping distance and time issues, particularly in snowy and icy conditions.
Volume: 15
Issue: 1
Page: 260-279
Publish at: 2025-02-01

Product reviews analysis to extract sentimental insights with class confidence rate using self-organizing map neural network

10.11591/ijece.v15i1.pp980-994
Sara Ahsain , Yasyn Elyusufi , M'hamed Ait Kbir
Customer data analysis helps companies to understand customer intentions and behaviors better. This study introduces an analysis of product reviews to help managers adopt a more efficient strategy to extract valuable knowledge and help detect segment of customers that need a special attention and products that need improvement or with the most impact. The used dataset is a set of Amazon reviews divided into multiple categories; each review has a target column called ‘overall’ that takes a value between 1 and 5 (customer's satisfaction). Based on the ‘overall’ column, multiple labeling methods have been used and compared to get a binary target variable, positive or negative, that affects a class to a review. This dataset contains more than one million reviews and can give companies great insight into products’ quality and customers’ retention. This work has materialized by using customer segmentation and competitive learning with self-organizing map (SOM) Model and adopting a new approach to explore the generated network/map, it is based on clustering and map nodes labelling using a majority voting process. The results show that the proposed dual approach combining the prior knowledge, related to supervised learning, and the competitive learning abilities enhances the SOM model’s capabilities.
Volume: 15
Issue: 1
Page: 980-994
Publish at: 2025-02-01

Predicting academic performance: toward a model based on machine learning and learner’s intelligences

10.11591/ijece.v15i1.pp645-653
Jamal Eddine Rafiq , Zakrani Abdelali , Mohammed Amraouy , Said Nouh , Abdellah Bennane
With the rapid evolution of online learning environments, the ability to predict students' academic performance has become crucial for personalizing and enhancing the educational experience. In this article, we present a predictive model based on machine learning techniques, designed to be integrated into online learning platforms using the competency-based approach. This model leverages features from four key dimensions: demographic, social, emotional, and cognitive, to accurately predict learners' academic performance. We detail the methodology for collecting and processing learning traces, distinguishing between explicit traces, such as demographic data, and implicit traces, which capture learners' interactions and behaviors during their learning process. The analysis of these data not only improves the accuracy of performance predictions but also provides valuable insights into skill acquisition and learners' personal development. The results of this study demonstrate the potential of this model to transform online education by making it more adaptive and focused on individual learners' needs.
Volume: 15
Issue: 1
Page: 645-653
Publish at: 2025-02-01

Backstepping controller for speed loop of permanent magnet synchronous motors integrated with a time-varying disturbance load observer for Metro Nhon-Hanoi Station

10.11591/ijece.v15i1.pp235-242
An Thi Hoai Thu Anh , Lam Quang Thai , Pham Duc Minh
Urban rail systems offer the substantial potential for reducing environmental pollution, alleviating traffic congestion, ensuring safety, and maintaining punctuality. Nevertheless, the operation of urban rail demands substantial electrical energy, and saving energy solutions are crucial to exploiting the full advantages of electric trains. This paper proposes the replacement of traditional traction motors with permanent magnet synchronous motors (PMSMs) due to their superior efficiency, reduced power losses, and compact size compared to direct current (DC) motors or other asynchronous three-phase motors with equivalent power, developing a backstepping controller for the speed loop coupled with a load observer-time-varying disturbance (TVD). The simulation results were conducted in MATLAB/Simulink with parameters collected from the Nhon-Hanoi urban railway line, Vietnam, verifying the proposed algorithms' correctness and effectiveness.
Volume: 15
Issue: 1
Page: 235-242
Publish at: 2025-02-01

Real-time paddy grain drying and monitoring system using long range-internet of things

10.11591/ijece.v15i1.pp448-454
Ayong Hiendro , Syaifurrahman Syaifurrahman , F. Trias Pontia Wigyarianto , Fitriah Husin
Grain drying environmental parameters are an important issue throughout the paddy grain production process. A real-time monitoring system requires rapid, online, and accurate measurement results. In the paddy grain drying process, the heated air velocity, temperature, relative humidity, and moisture content have to be carefully monitored and maintained to ensure product quality and safety. This study aimed to propose a real-time paddy grain drying and monitoring system using a long-range internet of things (LoRa-IoT). The real-time monitoring system consisted of sensors, LoRa, and IoT platforms. The LoRa end node and gateway were utilized as a wireless radio communication platform of IoT for long-distance signal transmission. From the experiment, the gateway received data from the end node at a distance of 2 km with a time on air (ToA) of 981 ms. As a result, the proposed monitoring system succeeded in measuring and recording the heated air velocity, temperature, and relative humidity data during the paddy grain drying process from 25% moisture content down to 14%. Regarding moisture content, the accuracy of real-time monitoring information was confirmed with a direct measurement method, resulting in a root mean square error (RMSE) of 6.17%.
Volume: 15
Issue: 1
Page: 448-454
Publish at: 2025-02-01

Handling class imbalance in education using data-level and deep learning methods

10.11591/ijece.v15i1.pp741-754
Rithesh Kannan , Hu Ng , Timothy Tzen Vun Yap , Lai Kuan Wong , Fang Fang Chua , Vik Tor Goh , Yee Lien Lee , Hwee Ling Wong
In the current field of education, universities must be highly competitive to thrive and grow. Education data mining has helped universities in bringing in new students and retaining old ones. However, there is a major issue in this task, which is the class imbalance between the successful students and at-risk students that causes inaccurate predictions. To address this issue, 12 methods from data-level sampling techniques and 2 methods from deep learning synthesizers were compared against each other and an ideal class balancing method for the dataset was identified. The evaluation was done using the light gradient boosting machine ensemble model, and the metrics included receiver operating characteristic curve, precision, recall and F1 score. The two best methods were Tomek links and neighbourhood cleaning rule from undersampling technique with a F1 score of 0.72 and 0.71 respectively. The results of this paper identified the best class balancing method between the two approaches and identified the limitations of the deep learning approach.
Volume: 15
Issue: 1
Page: 741-754
Publish at: 2025-02-01

Digital adaptive control with pulse width modulation of signals

10.11591/ijece.v15i1.pp252-259
Isamiddin Siddikov , Gulchekhra Alimova , Malika Rustamova , Mustafaqul Usanov
The paper presented research results of a digital control system for a dynamic plant with pulse-width modulation (PWM) of control impacts. As the control PWM signal is taken the pulse duty cycle, is calculated on each current cycle of the sample from the measured values. A control algorithm is proposed based on a hybrid application of the linear-quadratic optimization procedure and the theory of observers of minimal complexity. To ensure execution that the conditions of Astatism are met, the dynamic model of the plant is supplemented with a discrete integrator. The proposed approach makes it possible to reduce hardware costs and increase the robustness of the control system due to the exclusion of operations for digital–analogue transformations of signals. The proposed algorithm for digital control of a dynamic plant with varying duty cycle values of the PWM signal shows that the PWM model turned out to be linear and practically inertia less, which makes it easy to take into account the modulator model, which significantly simplifies the solution of the problem of synthesizing a control system for a dynamic plant. The possibility of receiving a high-quality modulated control signal allows for significant suppression of signal pulsations and high control accuracy.
Volume: 15
Issue: 1
Page: 252-259
Publish at: 2025-02-01

Challenges and opportunities to location independent human activity recognition utilizing Wi-Fi sensing

10.11591/ijece.v15i1.pp921-939
Fahd Abuhoureyah , Yan Chiew Wong , Malik Hasan Al-Taweel , Nihad Ibrahim Abdullah
Wireless sensing has emerged as a dynamic field with diverse applications across smart cities, healthcare, the internet of things (IoT), and virtual reality gaming. This burgeoning area capitalizes on the capacity to detect locations, activities, gestures, and vital signs by assessing their impact on ambient wireless signals. This review critically examines the prevailing challenges within wireless sensing and predicts future research trajectories. Even with the potential for nuanced signal processing facilitated by Wi-Fi propagation, its efficacy is impeded by noise interference in confined areas during transmission and reception. Consequently, this work aims to augment signal processing performance accuracy by delving into the most promising techniques and underexplored methods utilizing channel state information (CSI). Furthermore, the work offers a view into the potential of human activity recognition predicated on CSI properties. The study focusses on exploring location-independent sensing technique based on CSI, discussing relevant considerations and contemporary approaches used in Wi-Fi sensing tasks. The optimal practices in analysis are based on model design, data collection, and result interpretation. The discussions analysis investigates in detail the representative applications and outlines the major considerations of developing human activity recognition human activity recognition (HAR) based on Wi-Fi by analyzing the current critical issues of CSI-based behavior recognition methods and pointing out possible future research directions.
Volume: 15
Issue: 1
Page: 921-939
Publish at: 2025-02-01

Context-aware self-powered intelligent soil monitoring system for precise agriculture

10.11591/ijece.v15i1.pp1123-1131
Keh-Kim Kee , Ramli Rashidi , Owen Kwong-Hong Kee , Andrew Ballang Han , Isaiah Zunduvan Patrick , Loreena Michelle Bawen
The agricultural sector is transforming with advanced technologies such as internet of things (IoT), cloud computing, and machine learning, for increased productivity and sustainability. However, fixed sensor deployments struggle to capture the dynamic and heterogeneous soil properties with irregularities in farming operations, and negatively impacting crop performance and resource utilization. This paper presents a novel context-aware, self-powered intelligent soil monitoring system (ISMS) applied in precision agriculture. By integrating advanced sensors, energy harvesting, real-time data analytics, and context-aware decision support, ISMS provides real-time context insights into soil, energy, and weather conditions. The informed decisions are enabled and tailored to their specific agricultural environment. The system utilizes a multi-parameter soil sensor, photovoltaic (PV) panel, and intelligent context-aware analytics for a sustainable, cost-effective solution powered by solar energy and OpenWeather application program interface (API) for weather data. Field tests over two months demonstrated the system's effectiveness, together with continuous operation without grid power. This research highlights ISMS's potential in enhancing soil nutrient management and decision-making and offering significant economic and environmental benefits for modern agriculture, especially in remote areas.
Volume: 15
Issue: 1
Page: 1123-1131
Publish at: 2025-02-01

An efficient strategy for optimizing a neuro-fuzzy controller for mobile robot navigation

10.11591/ijece.v15i1.pp1065-1078
Brahim Hilali , Mohammed Ramdani , Abdelwahab Naji
Autonomous navigation is one of the key challenges in robotics. In recent years, several research studies have tried to improve the quality of this task by adopting artificial intelligence approaches. Indeed, the neuro-fuzzy approach stands out as one of the most commonly employed methods for developing autonomous navigation systems. Nevertheless, it may encounter problems of accuracy, complexity, and interpretability due to redundancy in the fuzzy rule base, particularly in the fuzzy sets associated with the system’s variables. In this work, a strategy is proposed to optimize an adaptive-network-based fuzzy inference system (ANFIS) controller for reactive navigation by addressing the problem of complexity and accuracy. It consists in combining a suite of methods, namely, data-driven fuzzy modeling, fuzzy sets merging, fuzzy rule base simplification, and parameter training. This process has produced a fuzzy inference system-based controller with high accuracy and low complexity, enabling smooth and near-optimal navigation. This system receives local information from sensors and predicts the appropriate kinematic behavior that enables the robot to avoid obstacles and reach the target in cluttered and previously unknown environments. The performance of the proposed controller and the efficiency of the followed strategy are demonstrated
Volume: 15
Issue: 1
Page: 1065-1078
Publish at: 2025-02-01

Estimation of harmonic impedance and resonance in power systems

10.11591/ijece.v15i1.pp67-75
Haitham Ali Alashaary , Ghadeer Nyazi Al Shaba'an , Wael Fawzi Abu Shehab , Shehab Abdulwadood Ali
Since power systems are designed to work at the fundamental frequency, the presence of other frequencies from various sources may induce series and parallel resonances, leading to damage. The behavior of the power system in the presence of harmonics becomes evident with knowledge of harmonic impedance. Measurement offers the most accurate means of estimating harmonic impedance. However, when precise data of the power system parameters are available, highly satisfactory results can be achieved through calculation methods, particularly regarding loads, which are unknown and always change. This paper presents a study on estimating harmonic impedance using the Electromagnetic Transients Program Alternative Transient Program Draw (EMTP-ATPDraw) program, applied to an authentic network of Petrovice line 67, 22/0.4 kV, located in the Czech Republic. Hypothetically, the network was subjected to harmonic injection from a source (3rd, 5th, 7th, 9th, and 11th harmonics), and the harmonic impedance was calculated for three different variants: individual harmonics, all harmonics, and all except the 9th harmonic. The results show that the presence of the 9th harmonic can lead to a parallel resonance. This study is the first to employ EMTP-ATPDraw for programming this network. It gives the possibility to create a network database for different operating conditions, offering an asset for future project planning.
Volume: 15
Issue: 1
Page: 67-75
Publish at: 2025-02-01

Electrocardiogram features detection using stationary wavelet transform

10.11591/ijece.v15i1.pp374-385
Mounaim Aqil , Atman Jbari
The main objective of this paper is to provide a novel stationary wavelet transform (SWT) based method for electrocardiogram (ECG) feature detection. The proposed technique uses the detail coefficients of the ECG signal decomposition by SWT and the selection of the appropriate coefficient to detect a specific wave of the signal. Indeed, the temporal and frequency analysis of these coefficients allowed us to choose detail coefficient of level 2 (Cd2) to detect the R peaks. In contrast, the coefficient of level 3 (Cd3) is determined to extract the Q, S, P, and T waves from the ECG. The proposed method was tested on recordings from the apnea and Massachusetts Institute of Technology–Beth Israel hospital (MIT-BIH) databases. The performances obtained are excellent. Indeed, the technique presents a sensitivity of 99.83%, a predictivity of 99.72%, and an error rate of 0.44%. A further important advantage of the method is its ability to detect different waves even in the presence of baseline wander (BLW) of the ECG signal. This property makes it possible to bypass the filtering operation of BLW.
Volume: 15
Issue: 1
Page: 374-385
Publish at: 2025-02-01

Enhancing millimeter-wave communication: a tropical perspective on raindrop size distribution and signal attenuation

10.11591/ijece.v15i1.pp467-479
Nurul Najwa Md Yusof , Jafri Din , Lam Hong Yin
This study tackles rain attenuation in millimeter-wave (mm-wave) communication, a critical concern for the advancement of 5G wireless technology. It examines the variability of raindrop size distribution (DSD) and its impact on specific attenuation, with a focus on tropical environments such as Malaysia. Using the Joss-Waldvogel disdrometer, this study collected and analyzed extensive DSD data over three years, revealing that the highest DSD concentrations do not necessarily result in the greatest specific attenuation. This study adopted a machine learning approach, specifically supervised learning with linear regression, to enhance the accuracy of attenuation prediction models. A new set of coefficients for the power-law model of specific attenuation was derived and benchmarked against the ITU-R P.838-3 standard and similar studies in comparable climates. The findings emphasize the importance of developing region-specific models that consider local meteorological variations, potentially offering significant improvements to the reliability and design of mm-wave communication systems in the future.
Volume: 15
Issue: 1
Page: 467-479
Publish at: 2025-02-01

Low-cost integrated circuit packaging defect classification system using edge impulse and ESP32CAM

10.11591/ijece.v15i1.pp156-162
Muhammad Adni Kamaruddin , Mohd Syafiq Mispan , Aiman Zakwan Jidin , Haslinah Mohd Nasir , Nurul Izza Mohd Nor
Defects in integrated circuit (IC) packaging are inevitable. Several factors can cause defects in IC packaging such as material quality, errors in machine and human handling operations, and non-optimized processes. An automated optical inspection (AOI) is a typical method to find defects in the IC manufacturing field. Nevertheless, AOI requires human assistance in the event of uncertain defect classification. Human inspection often misses very tiny defects and is inconsistent throughout the inspection. Therefore, this study proposed a low-cost IC packaging defect classification system using edge impulse and ESP32-CAM. The method involves training a deep learning model (i.e., convolutional neural network (CNN)) using a dataset of non-defective and defective ICs on Edge Impulse. For defective ICs, the top surface of the ICs is deliberately scratched to imitate the cosmetic defects. ICs with scratch-free on their top surfaces are considered non-defective ICs. A successfully trained model using Edge Impulse is subsequently deployed on ESP32-CAM. The model is optimized to fit the limited resources of the ESP32-CAM. By using the built-in camera in ESP32-CAM, the trained model can perform a real-time image classification of non-defective/defective ICs. The proposed system achieves 86.1% prediction accuracy by using a 1,571 image dataset of defective and non-defective ICs.
Volume: 15
Issue: 1
Page: 156-162
Publish at: 2025-02-01
1 2 3
...
1624 1625
Show 6 of 1625

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