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

29,922 Article Results

Enhancing wind energy prediction accuracy with a hybrid Weibull distribution and ANN model: a case study across ten locations in Java Island, Indonesia

10.11591/ijeecs.v41.i1.pp180-190
Silvy Rahmah Fithri , Nurry Widya Hesty , Rudi P. Wijayanto , Bono Pranoto , Prima Trie Wijaya , Akhmad Faqih , Wisnu Ananta Kusuma , Agus Nurrohim , Agus Sugiyono , Yudiartono Yudiartono
Accurate wind speed forecasting is essential for optimizing renewable energy (RE) systems, especially in coastal and island regions with high variability. This study proposes a hybrid predictive model that combines Weibull distribution parameters with artificial neural networks (ANN) to enhance forecasting accuracy. Using ten years of hourly NASA POWER data from 10 locations across Java Island, 24 scenarios were tested with varying combinations of Weibull and meteorological variables. Results demonstrate that incorporating both Weibull shape (k) and scale (c) parameters significantly improves performance, with the best configuration (Scenario 1) achieving a MAPE of 0.44% in Garut. Excluding one or both parameters sharply reduced accuracy, with errors rising up to 35.12%. Beyond technical accuracy, the findings emphasize the practical relevance of Weibull-informed ANN models for energy planning. Reliable forecasts support better wind resource assessment, grid integration, and investment decisions, reducing uncertainties that often hinder wind power deployment. By providing accurate and stable predictions across diverse locations, this approach offers policymakers and planners a robust tool to accelerate RE development and meet national energy targets.
Volume: 41
Issue: 1
Page: 180-190
Publish at: 2026-01-01

Remaining useful life estimation of turbofan engine: a sliding time window approach using deep learning

10.11591/ijeecs.v41.i1.pp283-299
Alawi Alqushaibi , Mohd Hilmi Hasan , Said Jadid Abdulkadir , Shakirah Mohd Taib , Safwan Mahmood Al-Selwi , Ebrahim Hamid Sumiea , Mohammed Gamal Ragab
System degradation is a common and unavoidable process that frequently oc curs in aerospace sector. Thus, prognostics is employed to avoid unforeseen breakdowns in intricate industrial systems. In prognostics, the system health status, and its remaining useful life (RUL) are evaluated using numerous sen sors. Numerous researchers have utilized deep-learning techniques to estimate RUL based on sensor data. Most of the studies proposed solving this problem with a single deep neural network (DNN) model. This paper developed a novel turbofan engine RUL predictor based on several DNN models. The method includes a time window technique for sample preparation, enhancing DNN’s ability to extract features and learn the pattern of turbofan engine degradation. Furthermore, the effectiveness of the proposed approach was confirmed using well-known model evaluation metrics. The experimental results demonstrated that among four different DNNs, the long short-term memory (LSTM)-based predictor achieved the better scores on an independent testing dataset with a root mean-square error of 15.30, mean absolute error score of 2.03, and R-squared score of 0.4354, which outperformed the previously reported results of turbofan RULestimation methods.
Volume: 41
Issue: 1
Page: 283-299
Publish at: 2026-01-01

Development of a machine learning model with optuna and ensemble learning to improve performance on multiple datasets

10.11591/ijeecs.v41.i1.pp375-386
Akmar Efendi , Iskandar Fitri , Gunadi Widi Nurcahyo
Machine learning, a subset of artificial intelligence (AI) is vital for its ability to learn from data and improve system performance. In Indonesia, advancements in ML have significant potential to boost competitiveness and foster sustainable development. However, issues like overfitting and suboptimal parameter settings can hinder model effectiveness. This study aims to improve the classification performance of ML models on various datasets. Advanced techniques like hyperparameter tuning with Optuna and ensemble learning with extreme gradient boosting (XGBoost) are integrated to enhance model performance. The study evaluates the performance of K nearest neighbors (KNN), support vector machine (SVM), and Gaussian naïve Bayes (GNB) algorithms across three datasets: academic records from the Islamic University of Riau (UIR), diabetes data from Kaggle, and Twitter data related to the 2024 elections. The findings reveal that the GNB algorithm outperforms KNN and SVM across all datasets, achieving the highest accuracy, precision, recall, and F1-score. Hyperparameter tuning with Optuna significantly improves model performance, demonstrating the value of systematic optimization. This study highlights the importance of advanced optimization techniques in developing high-performing ML models. The results suggest that robust algorithms like GNB, combined with hyperparameter tuning and ensemble learning, can significantly enhance classification performance.
Volume: 41
Issue: 1
Page: 375-386
Publish at: 2026-01-01

Deep-fuzzy personalisation framework for robot-assisted learning for children with autism

10.11591/ijeecs.v41.i1.pp320-330
Rose-Mary Owusuaa Mensah Gyening , James Ben Hayfron-Acquah , Michael Asante , Kate Takyi , Peter Appiahene
Research exploring the efficacy of robots in autism therapy has predominantly relied on the Wizard-of-Oz method, where robots execute predetermined behaviours. However, this approach is constrained by its heavy reliance on human intervention. To address this limitation, we introduce a novel deep-fuzzy personalization framework for social robots to enhance adaptability in interactions with autistic children. This framework incorporates a deep learning model called singleshot emotion detector (SED) with a mean average precision of 93% and a fuzzy-based engagement prediction engine, utilizing factors such as scores, IQ levels, and task complexity to estimate the engagement of autistic children during robot interactions. Implemented on the humanoid robot RoCA, our study assesses the impact of this personalization approach on learning outcomes in interactions with Ghanaian autistic children. Statistical analysis, specifically Mann Whitney tests (U=3.0, P=0.012), demonstrates the significant improvement in learning gains associated with RoCA's adoption of the deep fuzzy approach.
Volume: 41
Issue: 1
Page: 320-330
Publish at: 2026-01-01

Incipient anomalous detection in a brain using the IBIGP algorithm

10.11591/ijeecs.v41.i1.pp119-127
Mohamed Hichem Nait Chalal , Benabdellah Yagoubi , Sidahmed Henni
The detection of an incipient anomalous growth of tissue in a brain is often a difficult task. Various algorithms for brain anomalous detection have been suggested abundantly in the existing literature. In the last decade, many detection methods have been suggested to improve and facilitate abnormal tissue detection. However, the most attractive techniques to many researchers are maybe those that are magnetic resonance imagery (MRI)- based algorithms. A technique known as the inverse of the belonging individual Gaussian probability (IBIGP) is applied to MRI in this work in order to mitigate incipient anomalous tissue detection in a brain. This study demonstrates that the IBIGP technique, applied to the MRI image, is extremely effective in early detecting an anomalous change in the brain MRI image. Although this technique is still in its infancy, it has a great potential to enhance brain anomalous early detection.
Volume: 41
Issue: 1
Page: 119-127
Publish at: 2026-01-01

Enhancing cybersecurity in 5G networks systems through optical wireless communications

10.11591/ijeecs.v41.i1.pp250-257
Iyas Abdullah Alodat , Shadi Al-Khateeb
In this paper we will discuss with the recent global deployment of 5G networks, it has become imperative to ensure secure and reliable communications in addi tion to basic responsibility. Given that standard radio frequency (RF) communi cations have security flaws such as eavesdropping, signal jamming, and cyber attacks, wireless optical communications (WOC) offers a viable alternative. Us ing technologies such as visible light communications (VLC) and the free space optics (FSO) technologies, 5G networks can enhance the speed and efficiency of data transmission, while simultaneously enhancing cyber security. In addition to discussing the advantages of wireless on-chip communication technology com pared to RF solutions and the challenges that need to be addressed, this paper examines how WOC technology can enhance cyber security in 5G networks.
Volume: 41
Issue: 1
Page: 250-257
Publish at: 2026-01-01

Predictive control strategy for a novel 15-level inverter with reduced power components

10.11591/ijeecs.v41.i1.pp33-44
Taoufiq El Ansari , Ayoub El Gadari , Youssef Ounejjar
This paper proposes a novel fifteen-level H-PTC inverter topology controlled by model predictive control (MPC), which reduces the number of components. The design employs only two DC sources, nine switches, including one bidirectional switch, and a single capacitor. The system’s performance is validated through MATLAB/Simulink simulations under various scenarios, such as steady-state operation, load variations, nonlinear loads, and sudden supply voltage disturbances. Compared to existing topologies, the proposed inverter demonstrates hardware simplicity, high output quality, and enhanced dynamic robustness. Notably, it features very low total standing voltage (TSV) and a minimized cost function value of 2.05. For a load characterized by R = 20 Ω and L = 20 mH, the total harmonic distortion (THD) of the load current is 0.88%, confirming excellent power quality without the need for output filters. The MPC controller ensures a fast dynamic response and strong adaptability, making this topology ideal for modern energy conversion applications.
Volume: 41
Issue: 1
Page: 33-44
Publish at: 2026-01-01

An enhanced NLP approach for BI-RADS extraction in breast ultrasound reports using deep learning

10.11591/ijeecs.v41.i1.pp191-199
Ahmed Sahl , Shafaatunnur Hasan , Maie M. Aboghazalah
Breast cancer stands as one of the top causes of death around the globe, making the accurate interpretation of breast ultrasound reports vital for early diagnosis and treatment. Unfortunately, key findings in these reports are often buried in unstructured text, complicating automated extraction. This study presents a deep learning-based natural language processing (NLP) approach to extract breast imaging reporting and data system (BI-RADS) categories from breast ultrasound data. We trained a recurrent neural network (RNN) model, specifically using a BiLSTM architecture, on a dataset of reports that were manually annotated from a hospital in Saudi Arabia. Our approach also incorporates uncertainty estimation techniques to tackle ambiguous cases and uses data augmentation to boost model performance. The experimental results indicate that our deep learning method surpasses traditional rule-based and machine-learning techniques, achieving impressive accuracy in classification tasks. This research plays a significant role in automating radiology reporting, aiding clinical decision-making, and pushing forward the field of breast cancer research.
Volume: 41
Issue: 1
Page: 191-199
Publish at: 2026-01-01

Tool support for LoRaWAN development: a comparative perspective on simulation and emulation

10.11591/ijeecs.v41.i1.pp233-249
Ntshabele Koketso , Bassey Isong
This paper explores the use of various long range wireless area network (LoRaWAN) simulation and emulation tools when designing and evaluating IoT networks. Simulation tools are often popular with researchers because they are less costly and can easily simulate large-scale networks, allowing for easy and faster tests of the scalability of various protocols and behaviors. However, they often lack the unpredictable nature of real deployments. Emulation and cloud-based tools fill this gap, but with their flexibility they provide a more realistic approximation of real-world performance and allow easier interfacing with actual network hardware infrastructure, although they generally incur a higher cost which is often controlled by technical skill level use. 
Volume: 41
Issue: 1
Page: 233-249
Publish at: 2026-01-01

Optimization of a hybrid forward chaining and certainty factor model for malaria diagnosis based on clinical and laboratory data

10.11591/ijeecs.v41.i1.pp419-429
Patmawati Hasan , Rahmat H. Kiswanto , Susi Lestari
Malaria remains a serious public health problem in Indonesia, particularly in Papua Province, which accounts for 89% of national malaria cases. The similarity of malaria symptoms with other infectious diseases and limited laboratory facilities often lead to delays and inaccuracies in diagnosis. The study proposes an optimized hybrid model that combines forward chaining and certainty factor (CF) by integrating clinical and laboratory data to improve the accuracy of malaria diagnosis. The research design includes acquiring knowledge from medical experts, developing a rule-based system using forward chaining, and applying CFs to overcome uncertainty in symptom interpretation. The system is implemented using Python with support from libraries such as NumPy and PyKnow. The test results showed that the integration of laboratory data significantly improved diagnostic performance, with accuracy increasing from 81% malaria-positive using clinical data alone to 98% malaria-positive after combining with laboratory data. Expert testing to validate the accuracy of clinical and laboratory data results compared to expert validation results in an accuracy score of 98%. These findings show that the optimization of the hybrid forward chaining model and CF for malaria diagnosis based on clinical and laboratory data as a recommendation tool for early diagnosis of malaria in endemic areas.
Volume: 41
Issue: 1
Page: 419-429
Publish at: 2026-01-01

Low-cost ESP32-based sound data acquisition system with MATLAB integration for real-time noise monitoring

10.12928/telkomnika.v24i2.27557
Reymark-John; University of Science and Technology of Southern Philippines Villanueva Campus Macapanas , Adrian P.; Mindanao State University Iligan Institute of Technology (MSU-IIT) Galido , Apple Rose B.; Mindanao State University Iligan Institute of Technology (MSU-IIT) Alce
This study presents the design and implementation of a low-cost ESP32-based sound data acquisition system (SDAS) for real-time noise monitoring. The system integrates a micro-electro-mechanical systems (MEMS) microphone for accurate acoustic data capture, an ESP-WROOM-32 microcontroller for signal processing and wireless data transmission, and MATLAB for real-time visualization and analysis. Designed and simulated in KiCAD 8.0, the SDAS includes a microSD module for local data backup and offline analysis. The system was tested in four indoor locations within Mindanao State University – Iligan Institute of Technology, recording mean noise levels ranging from 14.2 dB in laboratory environments to 32.1 dB in classrooms, with corresponding standard deviations of 1.2–7.0 dB. Expert evaluation from eight assessors confirmed the system’s usability, data reliability, and robustness. The system demonstrates effective monitoring for both quiet and dynamic settings. Limitations include single-node configuration, indoor-only testing, and MATLAB-based USB data transfer. Despite these, the proposed SDAS provides a scalable and reproducible model for smart campus and urban environmental monitoring, supporting sustainable development goals (SDG) 3, 9, and 11.
Volume: 24
Issue: 2
Page: 599-607
Publish at: 2026-01-01

Neural-network based representation framework for adversary identification in internet of things

10.11591/ijece.v15i6.pp%p
Thanuja Narasimhamurthy , Gunavathi Hosahalli Swamy
Machine learning is one of the potential solutions towards optimizing the security strength towards identifying complex forms of threats in internet of things (IoT). However, a review of existing machine learning-based approaches showcases their sub-optimal performance when exposed to dynamic forms of unseen threats without any a priori information during the training stage. Hence, this manuscript presents a novel machine-learning framework towards potential threat detection capable of identifying the underlying patterns of rapidly evolving threats. The proposed system uses a neural network-based learning model emphasizing representation learning where an explicit masked indexing mechanism is presented for high-level security against unknown and dynamic adversaries. The benchmarked outcome of the study shows to accomplish 11% maximized threat detection accuracy and 33% minimized algorithm processing time.
Volume: 15
Issue: 6
Page: 6043-6052
Publish at: 2025-12-18

Challenges in radar-based non-supercell tornado detection using machine learning approaches

10.12928/telkomnika.v24i1.27451
Kiki; IPB University Indonesian Agency for Meteorology, Climatology and Geophysics (BMKG) Kiki , Yonny; IPB University Koesmaryono , Rahmat; IPB University Hidayat , Donaldi; Indonesian Agency for Meteorology, Climatology and Geophysics (BMKG) Sukma Permana , Perdinan; IPB University Perdinan , Abdullah; Indonesian Agency for Meteorology, Climatology and Geophysics (BMKG) Ali
Tornado detection in Indonesia remains challenging as most areas are monitored by single-polarization weather radar, while dual-polarization systems offer superior detection capabilities. This study presents a novel approach by applying random forest (RF) and XGBoost machine learning algorithms to detect tornadoes using single-polarization radar data, addressing a critical gap in tropical tornado monitoring where dual-pol infrastructure is limited. Four tornado cases in Surabaya during 2024 were analyzed. Radar features including reflectivity, radial velocity, vorticity, and angular momentum were extracted through a multi-elevation sliding window technique. Spatial labels were assigned based on reports from the Indonesian National Meteorological Services (BMKG) with a 7.5 km radius from the event center. The dataset was balanced using synthetic minority over sampling technique (SMOTE). Evaluation was performed using the leave one-case-out (LOCO) scheme. Within-case evaluation showed strong performance with area under the curve (AUC) >0.94 for both models. XGBoost achieved higher probability of detection (POD 0.67-0.72) but with elevated false alarm rates (FAR up to 70%). RF demonstrated more balanced performance (POD 0.61-0.65, FAR 0.34-0.35). LOCO evaluation revealed significant POD reduction and FAR increase when tested on new cases. This indicates generalization challenges due to variability in tornado characteristics. This study demonstrates the potential of machine learning for tropical tornado early detection using readily available single-polarization radar.
Volume: 24
Issue: 1
Page: 162-174
Publish at: 2025-12-08

Optimizing inventory management in the textile industry: a comprehensive evaluation of UHF-RFID technology integration

10.11591/ijaas.v14.i4.pp1411-1419
Ahmad Darmawi , Rita Istikowati , Galuh Yuli Astrini
The integration of ultra-high frequency radio frequency identification (UHF RFID) technology presents a transformative solution to inventory management challenges in the textile industry. This study examines the implementation of a web-based inventory management system incorporating UHF-RFID technology at AK-Tekstil Solo, focusing on its impact on inventory accuracy, operational efficiency, and product traceability. The developed system facilitates real-time tracking of yarn products, streamlines inventory audits, and minimizes manual errors, resulting in substantial improvements in inventory control and warehouse management processes. By enabling automated data capture and tracking, UHF-RFID technology supports the transition to smart warehousing by providing real-time insights into inventory movements. The findings demonstrate that UHF-RFID technology offers significant advantages, including enhanced inventory visibility, cost savings, and improved customer satisfaction through better product availability. Despite potential implementation challenges, the study shows that the long-term benefits of UHF-RFID integration outweigh the initial costs, proving it to be an effective solution for optimizing inventory management in the textile industry. Future research may explore the integration of complementary technologies such as the internet of things (IoT) and artificial intelligence (AI) to further enhance UHF-RFID enabled inventory management systems.
Volume: 14
Issue: 4
Page: 1411-1419
Publish at: 2025-12-01

E-bikes unplugged: exploring the evolution and environmental benefits of electric cycling

10.11591/ijaas.v14.i4.pp1295-1304
Vasupalli Manoj , Malleti Sreedhar , Rebba Sasidhar , Praveen Kumar Yadav Kundala , Dasyam Chandra Mouli , Ramana Pilla
Electric bicycles (e-bikes) have rapidly emerged as a sustainable alternative to conventional modes of transportation. This study reviews the evolution, technological advancements, and environmental benefits of e-bikes through comparative data analysis, survey results, and case studies. The findings demonstrate that the developments in lithium-ion batteries, lightweight materials, and smart motor systems have significantly improved e-bike performance, efficiency, and affordability. From an environmental perspective, e-bikes can cut greenhouse gas emissions by more than 90% compared to cars, while simultaneously improving urban air quality and reducing overall pollution levels. Survey responses indicate that e-bike users often substitute short car trips, promoting sustainable commuting behaviors and supporting public health. Despite these benefits, challenges persist regarding insufficient infrastructure, inconsistent policy support, and limited battery recycling programs. In summary, e-bikes constitute a transformative element in sustainable urban mobility and climate change mitigation. Beyond policy reforms, future work should prioritize renewable-powered charging systems and circular battery utilization models to ensure e-bikes contribute to a more resilient and environmentally friendly transportation ecosystem.
Volume: 14
Issue: 4
Page: 1295-1304
Publish at: 2025-12-01
1 2 3
...
1994 1995
Show 59 of 1995

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