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

30,376 Article Results

Hybrid machine learning framework for chronic disease risk assessment

10.11591/ijece.v16i1.pp321-332
Harini Shadaksharappa , Rashmi K. B. , Shreyas D. K. , Somanath Mikali , Vishesh P. Gowda , Uday Shankar C. A. , Siddarth B. Iyerr
Chronic diseases like asthma, diabetes, stroke, and heart disease are the major causes of morbidity globally, which emphasizes the need for efficient predictive models to facilitate early detection and precautionary measures. Previous studies have used machine learning approaches for single-disease prediction, where models are designed for specific diseases, such as diabetes or heart disease. However, very few attempts have been made to develop unified frameworks for predicting multiple diseases simultaneously. This work presents a novel, unified framework using an ensemble of extreme gradient boosting classifier (XGBClassifier) and artificial neural networks (ANN) as individual classifiers to concurrently predict the risk of developing asthma, diabetes, stroke, and heart disease. This work follows a questionnaire-based approach that utilizes demographic, lifestyle, health metrics, symptoms and exposure-related data to create personalized risk assessments. The model achieves satisfactory accuracy rates of 95.82% for asthma, 96.68% for diabetes, 94.91% for stroke, and 94.52% for heart disease. The findings highlight how this novel hybrid model serves as an effective approach to tackle the intricate interactions between chronic ailments. The research also includes a user-friendly website that comprises a questionnaire and makes use of the best performing model to predict the probabilities of developing different diseases.
Volume: 16
Issue: 1
Page: 321-332
Publish at: 2026-02-01

Methods for identifying informative features in agricultural images

10.11591/ijece.v16i1.pp256-277
Mirzaakbar Hudayberdiev , Baxodir Achilov , Nurmukhammad Alimkulov , Oybek Koraboshev , Fakhriddin Abdirazakov , Nargiza Sayfullaeva
The paper deals with informative aspects of images, their scope and extraction methods. The research addresses numerous different types of features such as texture, color, geometric and structural features that play an important role in the field of image analysis and recognition. Contemporary extraction methods based on machine learning algorithms and fractal dimension are explained. The possibility of usage of these methods in real-life problems such as medical imaging, biometrics, remote sensing images processing and agriculture is considered. Successful implementation examples of information functions in real-life problems are presented and opportunities for further research on the topic are considered.
Volume: 16
Issue: 1
Page: 256-277
Publish at: 2026-02-01

Detection of islanding using empirical mode decomposition and support vector machine

10.11591/ijece.v16i1.pp10-24
Balwant Patil , Diwakar Joshi , Sagar Santaji , Sudhakar C. J.
Accurate detection of islanding remains to be a challenge for grid connected microgrid system. An effective method to identify the islanding of microgrid has been presented which uses only the voltage at point of common coupling (PCC). Accurate islanding detection is necessary to impose appropriate control for the microgrid operation. Following the islanding of microgrid the intrinsic mode functions (IMF’s) of voltage at PCC obtained by empirical mode decomposition (EMD) will be analyzed by support vector machine (SVM) model which identifies the islanding of the microgrid. SVM model learns through the training data set. As many as 150 simulated cases have been used to train the SVM. A practical microgrid system has been simulated for various operating conditions and the data generation has been carried out by series of simulations for various islanding and non-islanding events using MATLAB Simulink. The proposed method gives optimistic results with high accuracy, zero non detection zone (NDZ) and detection time as low as 63.11 ms. Accurate islanding detection leads to smooth transition of microgrid control essential for operators.
Volume: 16
Issue: 1
Page: 10-24
Publish at: 2026-02-01

Implementation of markerless augmented reality and cyber physical-social systems for smart tourism application

10.12928/telkomnika.v24i1.27414
Ilham; Institut Teknologi Sumatera Firman Ashari , Fanesa; Institut Teknologi Sumatera Hadi Permana , Muhammad; Universitas Muhammadiyah Malang Zainal Arifin , Purwono; Institut Teknologi Sumatera Prasetyawan
Lampung province holds substantial tourism potential that remains underutilized due to fragmented information and limited promotional strategies. This study introduces a smart tourism application integrating markerless augmented reality (AR) with cyber-physical-social systems (CPSS), representing the first implementation of its kind for location-based tourism in the region. The novelty lies in the hierarchical coordinate transformation architecture (HCTA), a multi-layer computational framework employing the Haversine formula to achieve high-precision mapping of geographic coordinates into AR-optimized perceptual views. The system was evaluated for geolocation accuracy, resource utilization, backend scalability, AR rendering robustness, and user experience. Results show strong performance: geolocation tests across seven destinations yielded a mean error rate of 1.5%; AR operations remained efficient with 8–10% central processing unit (CPU) and 140–160 MB random access memory (RAM) usage; and rendering was stable across 360° device orientation. Backend tests confirmed scalability, sustaining 56 requests per second with zero failures under 100 concurrent users. A user study with 20 participants using the user experience questionnaire-short (UEQ-S) revealed highly positive outcomes, with overall scores 2.275, all within the Excellent benchmark. These findings confirm that the application is not only technically robust and efficient but also engaging and enjoyable, offering a scalable framework for immersive smart tourism ecosystems.
Volume: 24
Issue: 1
Page: 71-94
Publish at: 2026-02-01

Enhancing Autonomous GIS with DeepSeek-Coder: an open-source large language model approach

10.11591/ijece.v16i1.pp423-436
Kim-Son Nguyen , The-Vinh Nguyen , Van-Viet Nguyen , Minh-Hue Luong Thi , Huu-Khanh Nguyen , Duc-Binh Nguyen
Large language models (LLMs) have paved a way for geographic information system (GIS) that can solve spatial problems with minimal human intervention. However, current commercial LLM-based GIS solutions pose many limitations for researchers, such as proprietary APIs, high operational costs, and internet connectivity requirements, making them inaccessible in resource-constrained environments. To overcome this, this paper introduced the LLM-Geo framework with the DS-GeoAI platform, integrating the DeepSeek-Coder model (the open-source, lightweight version deepseek-coder-1.3b-base) running directly on Google Colab. This approach eliminates API dependence, thus reducing deployment costs, and ensures data independence and sovereignty. Despite having only 1.3 billion parameters, DeepSeek-Coder proved to be highly effective: generating accurate Python code for complex spatial analysis, achieving a success rate comparable to commercial solutions. After an automated debugging step, the system achieved 90% accuracy across three case studies. With its strong error- handling capabilities and intelligent sample data generation, DS-GeoAI proves highly adaptable to real-world challenges. Quantitative results showed a cost reduction of up to 99% compared to API-based solutions, while expanding access to advanced geo-AI technology for organizations with limited resources.
Volume: 16
Issue: 1
Page: 423-436
Publish at: 2026-02-01

Advances in AI, IoT, and smart systems for emerging electrical and computer engineering applications

10.11591/ijece.v16i1.pp555-558
Tole Sutikno
The current issue of the International Journal of Electrical and Computer Engineering (IJECE) showcases a diverse array of research at the intersection of artificial intelligence (AI), Internet of Things (IoT), machine learning (ML), and advanced engineering systems. Highlighted studies explore the application of autonomous mobile robots for logistics and material handling, sensorless control and acceleration profiling of electric drives, hybrid control strategies for high-performance electric vehicles, and deep learning methods for image recognition, emotion detection, and software fault prediction. Further contributions address practical implementations of IoT in heatstroke prevention, hydroponics, Spirulina cultivation, and energy-efficient greenhouse management, demonstrating how intelligent systems can optimize resource use, safety, and productivity. The issue also emphasizes AI-empowered modeling in accelerator design, solar photovoltaic power forecasting, and GIS automation, while exploring cybersecurity through intrusion detection frameworks and fraud detection in financial systems. Cutting-edge deep learning models such as convolutional neural networks (CNN), vision transformers, and TinyML are leveraged for healthcare, nuclear monitoring, and prenatal diagnostics. Collectively, these contributions underline the transformative role of AI, IoT, and hybrid intelligent systems in electrical and computer engineering, bridging theoretical advances with practical, real-world applications. This issue aims to inspire continued research and development toward efficient, secure, and adaptive technologies that advance smart engineering solutions worldwide.
Volume: 16
Issue: 1
Page: 555-558
Publish at: 2026-02-01

AI SWLM: artificial intelligence-based system for wildlife monitoring

10.11591/ijece.v16i1.pp216-229
Arun Govindan Krishnan , Jayaraman Bhuvana , Mirnalinee Thanga Nadar Thanga Thai , Bharathkumar Azhagiya Manavala Ramanujam
Detection and recognition of wild animals are essential for animal surveillance, behavior monitoring and species counting. Intrusion of animals and the disaster to be caused can be averted by the timely recognition of intruding animals. An artificial intelligence-based system for wildlife monitoring (AI SWLM) is designed and implemented on the camera trap images. The challenges such as detecting and recognizing animals of different sizes, shape, angles and scale, recognizing the animals of same and different species, detecting them under various illumination conditions, with pose variants and occlusion are addressed by identifying the optimal weights of the deep learning architecture, AI SWLM. Models were trained using Gold Standard Snapshot Serengeti dataset with random weights and the best weights of model were used as initial weights for training the augmented data. This has doubled the performance in terms of mean average precision, which can be interpreted.
Volume: 16
Issue: 1
Page: 216-229
Publish at: 2026-02-01

From YOLO V1 to YOLO V11: comparative analysis of YOLO algorithm (review)

10.11591/ijece.v16i1.pp450-462
Imane Beqqali Hassani , Soufia Benhida , Nabil Lamii , Khalid Oqaidi , Ahmed Ouiddad , Soukaina Ghiadi
Object detection in images or videos faces several challenges because the detection must be accurate, efficient and fast. The you only look once (YOLO) algorithm was invented to meet these criteria. But with the creation of several versions of this algorithm (from V1 to V11), it becomes difficult for researchers to choose the best one. The main objective of this review is to present and compare the eleven versions of the yolo algorithm in order to know when using the appropriate one for the study. The methodology used for this work is aligned with preferred reporting items for systematic reviews and meta-analyses (PRISMA) principles and the results demonstrate that the choice of the best version mainly depends on the priorities of the study. If the study prioritizes accuracy and detection of small objects, it should use YOLO V4, YOLO V5, YOLO V6, YOLO V7, YOLO V8, YOLO V9, YOLO V10 or YOLO V11. While studies that prioritize detection speed should use YOLO V5, YOLO V6, YOLO V7, YOLO V8, YOLO V10 or YOLO V11. In complex environment, researchers should avoid using YOLO V1, YOLO V2, YOLO V3, YOLO V5, YOLO V7 and YOLO V9. And researchers who are looking for a good accuracy and speed and a reduced number of parameters should use YOLO V10 or YOLO V11.
Volume: 16
Issue: 1
Page: 450-462
Publish at: 2026-02-01

Cumulative aging effects of five-year intermittent exposure on flexible amorphous solar cells

10.11591/ijece.v16i1.pp65-75
Djerroud Salima , Boudghene Stambouli Amine , Benabadji Noureddine , Lakhdari Abdelghani
Amorphous silicon (a-Si) is rarely used for large scale photovoltaic energy production, it remains relevant in flexible electronic applications, where mechanical flexibility and lightweight design are prioritized, where exposure to sunlight is typically limited or irregular. This study conducts an experimental analysis of the long-term aging effects on the proprieties of an amorphous solar cells, under five years of intermittent outdoor climate conditions. Unlike conventional aging studies that focus on degradation over time, this research highlights the cumulative effects of environmental exposure, considering the discontinuous nature of exposure cycles and the non-linearity of degradation phenomena because of the abrupt transitions between outdoor exposure phases and indoor laboratory rest periods. The results show that nearly 50% of the panel’s performances is reduced, with the losses observed as follows: a substantial decline in the fill factor from 55.3% to 30%, a decrease in energy conversion efficiency from 11.36% to 5.5%. This accelerated deterioration mainly attributed to harsh environmental transitions caused by intermittent exposure, which amplify aging mechanism compared to continuous exposure. Beyond the experimental findings, the approach presented here, constitutes a meaningful scientific contribution. By introducing a realistic and underexplored aging scenario, it lays the groundwork for a new line of research.
Volume: 16
Issue: 1
Page: 65-75
Publish at: 2026-02-01

Machine learning-based predictive maintenance framework for seismometers: is it possible?

10.11591/ijece.v16i1.pp187-205
Arifrahman Yustika Putra , Titik Lestari , Adhi Harmoko Saputro
Seismometers are crucial in earthquake and tsunami early warning systems, since they record ground vibrations due to significant seismic events. The health condition of a seismometer is strongly related to the measurement of seismic data quality, making seismometer health condition maintenance critical. Predictive maintenance is the most advanced control or measurement system maintenance method, since it informs about the faults that have occurred in the system and the remaining lifetime of the system. However, no research has proposed a seismometer predictive maintenance framework. Thus, this article reviews general predictive maintenance methods and seismic data quality analysis methods to find the feasibility of developing a predictive maintenance framework for seismometers in seismic stations. Based on the review, it is found that such a framework can be built under particular challenges and requirements. Finally, machine learning is the best approach to build the classification and regression models in the predictive maintenance framework due to its robustness and high prediction accuracy.
Volume: 16
Issue: 1
Page: 187-205
Publish at: 2026-02-01

Design of a thermionic electron gun of 6 MeV linac by using neural network based surrogate model

10.11591/ijece.v16i1.pp477-487
Elin Nuraini , Sihana Sihana , Taufik Taufik , Darsono Darsono , Saefurrochman Saefurrochman , Rajendra Satriya Utama
High performance electron guns are fundamental components in linear accelerators (linacs), directly influencing beam quality and downstream system efficiency. However, designing electron guns for applications such as a 6 MeV linac presents complex trade-offs between current, perveance, and beam emittance. Traditional simulation-driven optimization methods are computationally expensive and limit rapid prototyping. In this study, we develop a neural network-based surrogate model trained on CST Studio Suite simulation data to predict the electron gun's performance metrics. Our approach significantly accelerates the optimization process by providing real-time predictions of beam current and perveance across a wide design parameter space. The surrogate model achieves high prediction accuracy, with training and validation losses on the order of 10⁻⁷. Results demonstrate that neural network models can serve as reliable and efficient tools for electron gun design, offering considerable computational savings while maintaining accuracy. Future extensions include expanding the surrogate model to multi-objective optimization and incorporating thermal and mechanical effects into the design process.
Volume: 16
Issue: 1
Page: 477-487
Publish at: 2026-02-01

Study on the acceleration process of three-phase induction motors driving elevator loads

10.11591/ijece.v16i1.pp135-148
Do Van Can , Phan Gia Tri
Three-phase induction motor drive systems, especially in elevator applications and other precision motion systems, require optimized acceleration profiles to minimize vibrations and extend mechanical lifespan. Previous studies have primarily focused on fast speed response control but often overlooked the impact of jerk, which affects smoothness and operational safety. This paper proposes a combination of field-oriented control (FOC) and S-curve acceleration profiles to reduce jerk and improve motion quality. A dynamic model of the drive system is developed to simulate the acceleration process, demonstrating that the S-curve significantly reduces torque and current oscillations, thus enhancing stability. The S-curve trajectory generation algorithm is implemented and deployed on a field programmable gate array (FPGA) hardware platform. Experimental hardware results confirm that the generated speed control signals possess high resolution and fast response, making the method suitable for embedded control systems in elevator drives and other sensitive motion-control applications. This integrated approach not only addresses the limitations of previous methods but also provides a practical solution to improve comfort, safety, and durability in various electromechanical drive systems.
Volume: 16
Issue: 1
Page: 135-148
Publish at: 2026-02-01

Image classification using two neural networks and activation functions: a case study on fish species

10.11591/ijece.v16i1.pp383-394
Oppir Hutapea , Ford Lumban Gaol , Tokuro Matsuo
Lake Toba is utilized for aquaculture fishing as a clear example of how this technology can be applied. One of the species presents is the red devil fish (Amphilophus labiatus), which is known to have started appearing in the last 10 years. This species is known to be very aggressive and damage the ecosystem. When their populations go unchecked, red-devils can cause a decline in local fish populations, potentially destroying the balance of the food chain in those waters. This study used artificial neural network (ANN) and convolutional neural network (CNN) algorithms to successfully create two classification models for fish species from Lake Toba: red devil fish (Amphilophus labiatus), mujahir fish (Oreochromis mossambicus), sepat fish (Trichogaster trichopterus). The purpose of this model is to automatically identify fish species by using image-based classification techniques. According to the study's findings, both models performed exceptionally well and had a high degree of accuracy. This study addresses the lack of effective automated fish classification systems for ecosystems like Lake Toba, Indonesia, which are threatened by invasive species such as the red devil fish. By comparing CNN and ANN models with different activation functions and optimizers, we found that CNN with rectified linear unit (ReLU) activation and Adam optimizer provides the most accurate and stable results. The findings offer practical implications for fisheries management and biodiversity conservation.
Volume: 16
Issue: 1
Page: 383-394
Publish at: 2026-02-01

Experimental comparison of air, oil, and liquid nitrogen cooling media on the efficiency of a single-phase transformer

10.11591/ijece.v16i1.pp25-35
Heri Nugraha , Agung Imaduddin , Eka Rakhman Priandana , Asep Dadan Hermawan , Nono Darsono , Andika Widya Pramono , Adi Noer Syahid , Sudirman Palaloi , Satrio Herbirowo , Hendrik Hendrik
Transformers are critical component in electric power system, where minimizing energy losses is essential for efficiency and reliability. While ideal transformers operate with zero losses, practical transformers dissipate energy through winding and core losses caused by resistive heating. This study investigates the impact of three cooling media with ambient air, mineral oil, and liquid nitrogen on the efficiency and thermal performance of a 1 kVA single phase copper wound transformer. The experiment applied a resistive load under each cooling condition, recording input and output parameters using a HIOKI power meter model PW3360. Thermal behavior was monitored using infrared thermography and thermocouples. Copper winding resistivity was evaluated using a four-point probe within a cryogenic magnet system. The results show that liquid nitrogen cooling significantly reduced copper resistivity due to low-temperature conditions, achieving a transformer efficiency of 89.9%. Oil cooling improved efficiency to 86.0%, compared to 80.7% with air cooling. Although liquid nitrogen provided the greatest efficiency enhancement, its practical use is limited due to handling complexity and cost. In contrast, oil cooling offers a more feasible and effective solution for improving transformer performance in real world applications. These finding provide valuable insight for optimizing transformer thermal management strategies in power systems.
Volume: 16
Issue: 1
Page: 25-35
Publish at: 2026-02-01

Generalization of reactive power definition for periodical waveforms

10.11591/ijece.v16i1.pp102-110
Grzegorz Kosobudzki , Leszek Ładniak
The article presents a selection of reactive power definitions, which are applicable for implementation in energy meters. For sinusoidal current and voltage waveforms, all provided dependencies yield equivalent reactive power values. However, in the presence of distorted current and voltage, the power values are determined by the applied method (algorithm). Standardization requirements for reactive energy meters stipulate metrological verification under sinusoidal conditions. The selection of an optimal reactive power definition remains a problematic and ongoing subject of debate within the field. The paper shows that a generalized unique definition of additive reactive power derives from the definition of active power. Unlike active power, reactive power must be independent of the conversion of electric energy into work and heat. This independence is achieved if one of the waveforms – the current in the scalar voltage and current product (specifying active power) – is replaced by a special orthogonal waveform. An orthogonal waveform can be derived through either differentiation or integration. Reactive power obtained by this method is an additive within the system. When differentiation is employed, the reactive power for a nonlinear resistive load with a unique, time-invariant current-voltage characteristic will be zero. Some other properties of reactive power defined in this way are presented. This method is straightforward to implement in reactive energy meters.
Volume: 16
Issue: 1
Page: 102-110
Publish at: 2026-02-01
1 2 3
...
2025 2026
Show 83 of 2026

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