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

31,458 Article Results

Advanced AI-driven battery state estimation using deep learning and ensemble models

10.11591/ijape.v15.i3.pp1072-1093
N. Sumana Keerthi , B. Jyothi , M. Sharanya , CH. Srinivas , K. Shravani , V. Sanjeeva Rao , Teerdala Rakesh , Nittala Ramchandra , Malligunta Kiran Kumar , K. V. Govardhan Rao
Accurate estimation of the state of charge (SOC) and state of health (SOH) of lithium-ion batteries is essential for improving the performance, safety, and lifespan of electric vehicles (EVs). Traditional estimation methods often face challenges such as high computational complexity, limited adaptability to battery aging, and reduced accuracy under varying operating conditions. To overcome these limitations, this paper presents a hybrid data-driven framework that combines machine learning and deep learning techniques for SOC and SOH prediction. For SOC estimation, linear regression, recurrent neural networks (RNN), gated recurrent unit (GRU), and stacked long short-term memory (LSTM) models are employed. For SOH prediction, ensemble learning methods, including stacking regressor, tree-based pipeline optimization tool (TPOT) regressor, and hybrid GRU-LSTM models, are utilized. The proposed models are evaluated using publicly available lithium-ion battery datasets under different charge-discharge conditions. Results show that deep learning approaches achieve superior performance, with GRU-LSTM and stacked LSTM models providing highly accurate SOC estimation (R² ≈ 0.993, RMSE ≈ 0.015), while the TPOT-based ensemble model delivers near-perfect SOH prediction (R² ≈ 1.0). A web-based implementation further enables real-time battery monitoring, demonstrating the framework’s practicality for advanced battery management systems (BMS) in EV applications.
Volume: 15
Issue: 3
Page: 1072-1093
Publish at: 2026-09-01

Cost-effective hardware solutions for experimental validation in renewable energy emulation and storage systems

10.11591/ijape.v15.i3.pp1287-1298
Yassine El Asri , Abdellah Lassioui , Hassan El Fadil , Anwar Hasni , Marouane El Ancary , Hafsa Abbade , Mohammed Chiheb , Mohamed Koundi
Experimental validation is essential in renewable energy emulators and energy storage systems to ensure reliability, accuracy, and practical implementation. However, the high cost of AC/DC converters, measurement circuits, and microcontroller-based control platforms limits access to experimental validation, particularly in developing regions. This paper proposes cost-effective hardware and software solutions for validating renewable energy systems and storage management. The proposed approach is based on affordable power converters, low-cost voltage and current measurement circuits, data acquisition tools, and open-source control platforms. The methodology includes the design, implementation, and experimental testing of these low-cost solutions under different operating conditions. The obtained results demonstrate satisfactory measurement accuracy, stable behavior, and acceptable error margins, confirming the feasibility of the proposed setup for experimental validation. These solutions provide a scalable and accessible alternative to expensive laboratory platforms, enabling researchers and institutions with limited resources to perform reliable experimental studies and contribute to the advancement of sustainable energy technologies.
Volume: 15
Issue: 3
Page: 1287-1298
Publish at: 2026-09-01

A novel MVVR controlled solar-PV fed MF-DVR for compensation of islanding and PQ issues in utility-grid integrated distribution system

10.11591/ijape.v15.i3.pp1023-1035
Tharinaematam Bhavani , Durgam Rajababu , Md Mujahid Irfan
The depletion of fossil fuels, planning of new industries, and increased population are considered significant motivations for the expansion of new power generation in line with the requisite load demand. In recent days, the solar-PV-based distribution generation is the most suitable power generation in a utility-grid-integrated distribution system. The main intention of this work is to present the effective DG scheme; it delivers the required active power during sudden interruptions, grid-islanding, and sudden block-outs. And also enhancing the voltage stability during voltage-harmonics, voltage sags/swells, and unsymmetrical fault conditions occurred in the utility-grid integrated distribution system through solar-PV fed multi-functional dynamic-voltage restorer (MF-DVR) device. The effective compensation performance of MF-DVR relies on viable reference voltage signals, which are produced by well-known control schemes reported in literature studies. But these regular schemes have reported that the major problems are highlighted and have been eliminated by proposing the novel modified voltage vector reference (MVVR) control scheme. The proposed MVVR controller perfectly produces the unique reference voltage signals for delivering a feasible switching pattern to the MF-DVR device. In this work, the design and performance of the proposed MVVR-controlled solar-PV-fed MF-DVR have been verified to enhance power quality and grid-islanding issues through MATLAB/Simulation software tool. The extracted simulation findings are presented with appealing interpretations complying with IEEE-519/2022 standards.
Volume: 15
Issue: 3
Page: 1023-1035
Publish at: 2026-09-01

Sustainable e-mobility with controlled charging scheme based on grid energy using machine learning

10.11591/ijape.v15.i3.pp1036-1050
Archana Kadam , Ramesh Mali , Reena Gunjan , Virendra Shete , Pradeep Mane
The electric vehicle (EV) popularity has taken off among consumers, which has in turn led to efforts to create an efficient EV charging infrastructure. This paper addresses this challenge by proposing a scheduled charging scheme that uses real-time data from a grid-connected charging station at Baner, Pune, operated by Pune Mahanagar Parivahan Mahamandal Ltd (PMPML). The proposed system makes use of advanced machine learning techniques such as the Stochastic dual coordinate ascent (SDCA) and Fast Forest (FF) algorithm, both of which allow for precise and efficient computations to predict charging finish times and make optimal scheduling decisions. The use of these algorithms in conjunction with ToU tariffs is cost effective when compared to flat rate tariffs. Grid load analysis shows that scheduling according to time lowers peak demand, equalizes load distribution, and lowers operating costs. A quantitative comparison has demonstrated both grid stability and economic efficiency gains over uncontrolled charging. The result is an extremely flexible framework for different charging events or stations which will be a viable way of managing energy in the fast-growing EV charging networks.
Volume: 15
Issue: 3
Page: 1036-1050
Publish at: 2026-09-01

Voltage stability analysis of power transmission systems using multi-index framework of hybrid whale and particle swarm optimization technique

10.11591/ijape.v15.i3.pp1439-1457
Titus Terwase Akor , Theophilus Chukwudolue Madueme , Chibuike Peter Ohanu , Tole Sutikno
The persistent increase in grid collapse has necessitated the need for robust solutions for stability. Hybrid whale and particle swarm optimization (WAPSO) algorithm integrated with multi-index stability indices (MIS) has been applied to enhance voltage stability in this paper. The method is tested on the Nigeria 48-bus, 330 kV transmission system and simulated in MATPOWER embedded in MATLAB. The WAPSO algorithm is optimized with parameters w = 0.4, c₁ = 1.4 and c₂ = 1.5. The outcome achieved 98.84% reduction in mean MIS from 0.3959 to 0.0048 and a robustness index of 0.0051. This depicts low variability of 0.057 and 100% success rate across five dynamic scenarios explored such as gradual load growth with 98.79%, sudden spikes achieved 98.84%, cyclic fluctuations at 98.67%, renewable uncertainty at 98.74%, and N-1 contingencies at 98.84% improvement, respectively. Critical lines, 34-35 and 24-33 exhibit more than 99% MIS improvement, while weak lines, 21-22 and 24-40 achieved 85–87% enhancement, indicating areas for further reinforcement. The LSI and FVSI are reduced to 0.0048 and 0.1477 showing 56.79% improvement respectively as against the 38.9% MIS improvement obtained with the PSO-GA. This demonstrates WAPSO as a highly robust and adaptable technique offering a scalable solution for enhancing grid reliability under dynamic conditions.
Volume: 15
Issue: 3
Page: 1439-1457
Publish at: 2026-09-01

Performance analysis of multi carrier PWM techniques for a 5-phase three level NPC inverter in EV applications

10.11591/ijape.v15.i3.pp1264-1274
Venu Yarlagadda , N. Kavitha , Chava Sunil Kumar , G. Naveen , Swetha Mareddy , S. Venkata Rami Reddy , K. V. Govardhan Rao
Multi-phase multilevel inverters have become more popular in contemporary applications due to their many benefits, which include lower switching losses, decreased common mode voltage, and reduced stress from voltage on switches. This study focuses on enhancing total harmonic distortion (THD) performance in a five-phase multilevel neutral point clamped (NPC) inverter using various multi-carrier pulse width modulation (PWM) techniques, including PD, POD, APOD, IC, PSC, and VFC. These approaches are particularly suitable for electric vehicle and industrial motor applications. Several PWM approaches were used in the SIMULINK environment to model and simulate a 5-phase, 3-level NPC inverter. In this study, the performance of load voltage THD is compared using R and RL loads connected to a multilevel inverter. Additionally, 5-phase induction motor and permanent magnet synchronous motor models are developed as loads for electric vehicle applications, and variations in torque, speed, and stator current are analyzed. The PD modulation technique showed the lowest THD among the various PWM methods, demonstrating its effectiveness in maximizing inverter performance.
Volume: 15
Issue: 3
Page: 1264-1274
Publish at: 2026-09-01

A deep learning approach for electric vehicle battery charging duration estimation using IoT

10.11591/ijape.v15.i3.pp1375-1385
Tumuluri Kanthimathi , Adhimoolam Sairam , Durairaj Chandrakala , Moorthy Radhika , Bichagal Shadaksharappa , Pitchai John Britto , Minakshi Sanadhya , Balasubramanian Suganya , Chelliah Srinivasan
The rapid development of electric vehicles (EVs) has increased the desire for precise charging duration estimate to enhance charging station administration and elevate customer experience. This research presents a deep learning (DL) architecture that uses internet of things (IoT)-enabled data to categorise charging duration into short, medium, and long classifications. The assessment dataset comprises many numerical and categorical variables affecting battery performance and charging behaviour, providing a thorough foundation for prediction. The system utilises a deep neural network (DNN) architecture with nonlinear transformations and regularisation techniques, trained with adaptive optimisation to provide durable convergence. Extensive experiments indicate that the proposed model achieves an overall accuracy of 99.26%, markedly improving traditional machine learning (ML) techniques. These results highlight the potential of DL to adeptly discern complex linkages in charging dynamics, providing dependable predictions for duration classification. The framework provides an advanced basis for implementation in smart charging infrastructures, facilitating effective scheduling, minimizing waiting times, and endorsing predictive maintenance measures. It enhances the reliability and efficiency of EV charging ecosystems with data-driven, IoT-enabled DL technologies.
Volume: 15
Issue: 3
Page: 1375-1385
Publish at: 2026-09-01

Smart internet of things driven vehicle safety and battery management system

10.11591/ijaas.v15.i3.pp1085-1097
Batchalakuri Jyothi , Bhavana Pabbuleti , Ravi Ponnala , Patil Mounika , Edara Shiva Prasad , Enukonda Soumya , Rakesh Teerdala , Srungaram Ravi Teja , Malligunta Kiran Kumar , Kambhampati Venkata Govardhan Rao , Chilakala Rami Reddy
The proposed system design, the essential results obtained, and its relevance to modern automotive applications. The updated version now begins by identifying the dual challenge of increasing road accidents and the performance degradation of electric vehicle (EV) batteries, emphasizing the lack of integrated solutions that address both safety and battery reliability in a unified manner. Then, this study concisely describes the system design, highlighting the use of an internet of things (IoT)-enabled architecture incorporating an ADXL345 accelerometer for collision detection, global positioning system (GPS)/global system for mobile communications (GSM) modules for emergency alerting, and voltage, current, and temperature sensors for real-time battery monitoring, all interconnected through Arduino and ESP8266-based cloud communication. The abstract now summarizes key experimental results, including the system’s demonstrated accuracy in impact recognition, reduced alert latency, and reliable battery-parameter tracking supported by effective cloud visualization. Finally, this study strengthened the automotive relevance by emphasizing how this integrated platform enhances emergency responsiveness, supports predictive maintenance, and offers practical value for EVs, commercial fleet operations, and broader intelligent transportation applications. The revised abstract now provides a balanced, complete, and technically informative overview aligned with academic and automotive industry expectations.
Volume: 15
Issue: 3
Page: 1085-1097
Publish at: 2026-09-01

Comparative analysis of decision tree-based machine learning algorithms: a trade-off between accuracy and interpretability

10.11591/ijaas.v15.i3.pp1029-1037
Alwatben Batoul Rashed , Aeshah Almutairi , Mansir Abubakar , Mardiyya Lawal Bagiwa
This paper presents a comparative analysis of decision tree (DT)-based machine learning (ML) algorithms using 11 publicly available datasets from the knowledge extraction based on evolutionary learning (KEEL) repository. The study focuses on two critical aspects of DT-based algorithms: interpretability and accuracy. These measures often conflict, making it challenging to optimize both simultaneously. The research examines the trade-offs between accuracy and interpretability in three algorithms: Java implementation of the repeated incremental pruning to produce error reduction algorithm (JRip), projective and recurring trees (PART), and decision table. Experimental results demonstrate that JRip achieves the highest accuracy among the three algorithms across the datasets. However, decision table exhibits the highest interpretability, followed by PART, while JRip scores the lowest due to its pruning mechanism. These findings provide valuable insights into the balance between accuracy and interpretability, assisting researchers and practitioners in selecting the most suitable algorithm for classification tasks. The findings show a definite trade-off between accuracy and interpretability. Although JRip generates more complicated rule sets, it consistently delivers better accuracy across the majority of datasets. Decision tables offer simpler and easier-to-understand models, despite their lower accuracy.
Volume: 15
Issue: 3
Page: 1029-1037
Publish at: 2026-09-01

Multilevel local region sparse shape composition model for liver cancer classification

10.11591/ijaas.v15.i3.pp932-943
Balasubramanian Sakthisaravanan , Ramakrishnan Meenakshi , Thirugnanasambandam Akila , Saravanan Durga Devi , Subbiah Murugan
Machine learning and computer-assisted disease detection are two technological innovations that have significantly improved medical advancement, and recent research has demonstrated their effectiveness. Liver cancer is one of the important causes of cancer-related deaths internationally. Tumor detection in the liver and its classification is challenging due to poor accuracy and high processing requirements available in the existing techniques. In these, there is a loss of edge information and the quality of the images considered. To address these issues in the segmentation and classification of liver cancer, a novel feature extraction method and algorithm called the novel multilevel local region (MLR)-based sparse shape composition model (NMLR-SSC) were developed. This innovative technique identifies the existence of tumors on abdominal computed tomography (CT) images. The input images were obtained from the 3D-IRCADb-01 dataset. The algorithm showed an improvement of 0.22%. When compared to other classifiers. The proposed algorithm showed 100% specificity, sensitivity, and a 98% accuracy rate in detecting the liver tumor.
Volume: 15
Issue: 3
Page: 932-943
Publish at: 2026-09-01

Modeling Indonesia’s regional economic growth for sustainable development planning

10.11591/ijaas.v15.i3.pp1286-1296
Julia Loisa , Suryo Widiantoro , Caecelia Cynthia Limanan , Kezia Kezia , Kenvil Lesmana
This study aims to evaluate Indonesia’s regional economic performance using gross regional domestic product (GRDP) per capita at the provincial level from 2015 to 2021. Utilizing business intelligence technology through Tableau, the study integrates descriptive, predictive, and prescriptive analytics to examine interregional GRDP dynamics. The k-means clustering method is employed to classify provinces into three clusters based on economic similarity. The results reveal a persistent economic disparity between the western and eastern regions of Indonesia, with provinces such as DKI Jakarta and East Kalimantan grouped in the high GRDP cluster, while East Nusa Tenggara and Papua fall into the lowest cluster. Trendline and forecasting analyses provide projections of economic growth through 2030, indicating that some provinces demonstrate stable upward trends, whereas others show stagnation or declining patterns. Based on these findings, this research offers data-driven policy recommendations aimed at promoting more equitable and sustainable economic development across Indonesia.
Volume: 15
Issue: 3
Page: 1286-1296
Publish at: 2026-09-01

A study of onshore wind turbine spatial arrangement in Thailand

10.11591/ijaas.v15.i3.pp1297-1315
Suparatchai Vorarat , Watcharapong Tantawat
This study examines the impact of wind turbine spatial arrangement on electricity generation efficiency in onshore wind energy farms within Thailand's meteorological and geographical context. An empirical analysis was conducted on 20 operational wind energy farms representing approximately 96% of Thailand's installed onshore wind capacity. Geographic information system (GIS) techniques were applied to measure the spacing and layout of the turbines, and the National Renewable Energy Laboratory's (NREL's) system advisor model (SAM) was employed to simulate the amount of electricity generated each year, considering wake effects, terrain, and site-specific wind resources. Capacity factors were calculated and compared against operational data. Results indicate capacity factors range from 17.12% to 30.75%, with a mean of 23.34%. Research reveals that wind turbine spacing is not the primary determinant of wind energy farm performance in Thailand. When the wind resources and site characteristics are good, the wind energy farms can have good performance from many different spacing setups. On the other hand, layout optimization by itself can't make up for bad wind conditions. These findings demonstrate the need for a more comprehensive design for wind energy farms in areas with moderate wind resources.
Volume: 15
Issue: 3
Page: 1297-1315
Publish at: 2026-09-01

Intrusion detection in evolving internet of things environments using decentralized data systems

10.11591/ijaas.v15.i3.pp1252-1261
Zobayer Alam , Arnab Bishakh Sarker , Jariatun Islam , Sifat Rahman Ahona
Growing internet of things (IoT) deployments have widened the attack surface for cyber threats that static, signature-dependent intrusion detection systems (IDSs) struggle to counter, particularly against previously unseen attack variants. This research introduces a hybrid IDS framework built on a stacking ensemble of four heterogeneous base classifiers, namely random forest (RF), extreme gradient boosting (XGBoost), light gradient-boosting machine (LightGBM), and a shallow multi-layer perceptron (MLP), coupled with a PyTorch-based neural network meta-classifier. Recursive feature elimination (RFE) guided by a RF estimator selected the 15 most informative behavioral flow features, while a hybrid random sampling approach corrected severe class imbalance in the training data. Detection outputs are stored immutably through the interplanetary file system (IPFS) via the Pinata gateway, enabling decentralized, content-addressed logging of IDS alerts. Evaluated on the CIC-BCCC-NRC-TabularIoT-2024 benchmark, the model achieved a classification accuracy of 99.51%, precision of 99.71%, recall of 99.30%, and an F1-score of 99.51%, establishing that pairing meta-learning with decentralized log storage yields a robust, auditable IDS suited for dynamic IoT environments.
Volume: 15
Issue: 3
Page: 1252-1261
Publish at: 2026-09-01

Hybrid machine learning for predictive spare parts replacement in medical equipment

10.11591/ijaas.v15.i3.pp990-997
Fabian Halley Pata Alban Dattu , Syed Tarmizi Syed Shazali , Shirley Jonathan Tanjong , Abdul Rani Achmed Abdullah , Nurlaila Rosli
Stability of medical equipment is critical for uninterrupted healthcare services, yet hospital computerized maintenance management systems (CMMS) records are often incomplete, heterogeneous, and partially labeled for spare parts usage. In the analyzed CMMS dataset, spare-part-related work orders accounted for approximately 65.1% of maintenance cases, indicating that spare-part readiness is a major contributor to maintenance response time and potential equipment downtime. This study proposes a semi‑supervised hybrid random forest-neural network (RF-NN) model to predict whether a work order will require spare‑parts replacement and to support proactive inventory planning. Retrospective CMMS work‑order records from six hospitals (N = 295) were pre‑processed using leakage‑safe pipelines (categorical one‑hot encoding, text feature extraction from fault descriptions, and standardization of numeric fields). Semi‑supervised self‑training was used to exploit unlabeled or weakly labeled records through iterative pseudo‑labelling. Models were evaluated using stratified 10‑fold cross‑validation and reported as mean ± SD. The hybrid RF-NN achieved Accuracy = 0.986 ± 0.018, precision = 0.980 ± 0.026, recall = 1.000 ± 0.000, and F1‑score = 0.990 ± 0.013, outperforming RF, NN, and Markov baselines. These results demonstrate the practical advantage of combining semi‑supervised learning with hybrid modelling to reduce missed spare‑parts cases, minimize downtime risk, and strengthen CMMS‑ready procurement decision support.
Volume: 15
Issue: 3
Page: 990-997
Publish at: 2026-09-01

Mapping significant clinical factors to relapse-free survival prognosis in breast cancer patients

10.11591/ijaas.v15.i3.pp1193-1202
Boby Al Qurthuby , I Made Murwantara
This study explores the role of clinical factors in influencing relapse-free survival (RFS) in breast cancer patients through comprehensive survival analysis (SA). The data were derived from a large cohort of breast cancer patients, encompassing clinical variables such as age at diagnosis, tumor size, number of positive lymph nodes, tumor grade, histological subtype, and receipt of chemotherapy and radiotherapy. Analytical methods included Kaplan-Meier plots, log-rank tests, Cox proportional hazards modeling, and feature ranking based on univariate and multivariate log-rank and Cox tests. The results show that patients who received chemotherapy demonstrated a shorter median RFS compared to those who did not (102.7 vs. 145.0 months, p = 0.03), likely due to high-risk patients being selected for chemotherapy. Meanwhile, radiotherapy was associated with improved prognosis (hazard ratio (HR) < 1 in Cox model, p < 10−5), in line with meta-analyses showing reduced breast cancer mortality post-radiotherapy. The contribution maps the key clinical determinants of RFS in breast cancer and highlights the practicality of performing SA.
Volume: 15
Issue: 3
Page: 1193-1202
Publish at: 2026-09-01
1 2 3
...
2097 2098
Show 38 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