Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,456 Article Results

Enhanced thermal management in 3D integrated circuits coupling

10.11591/ijict.v15i3.pp1208-1216
Vempalle Rafi , Shaik Hussain Vali , Pradyumna Kumar Dhal , Sadhu Radha Krishna , Murkur Rajesh , Malagonda Siva Kumar
3D IC integration, which comprises vertically stacking several IC layers, is one of the new technologies that works well with complementary metal-oxide-semiconductor (CMOS) implementations. The layers of a three-dimensional integrated circuit (3D IC) are physically and electrically connected via copper-silicon bonding and through silicon vias (TSVs). Limitations in 3D IC designs, such as layer-to-layer thermal difficulties and TSV-to-substrate and TSV-to-TSV noise coupling, significantly impact system performance as a whole. Integrating 3D ICs relies heavily on heat spreaders and thermal through silicon vias (TTSVs). Overheating is a common cause of IC failure; however, heat spreaders and FIN to TTSV have been suggested as potential remedies for this problem in the last few years. A 3D IC might melt under the stress of an applied voltage because it becomes hotter inside. Engineers have added fins to the TTSV in a number of ways, each of which maximizes heat dissipation in a different way, in order to reduce this danger. The exceptional thermal cooling characteristics of graphene and carbon nanotubes (CNTs) have led to their widespread dissemination. This research shows that a FIN may efficiently transport thermal energy to a heat sink by using heat spreaders and optimum orientations to distribute heat in all directions. Additionally, we demonstrated the many scenarios in which the IC's potential distribution is impacted by various thermal cooling effects. We found that when it comes to transferring heat away from heat sources and TSVs, CNTs outperform Graphene. We included Al2o3, Si3N4, and SiO2 as examples to examine the consequences of modifying the model's dielectric characteristics.
Volume: 15
Issue: 3
Page: 1208-1216
Publish at: 2026-09-01

Interpreting potato disease classification using explainable artificial intelligence

10.11591/ijaas.v15.i3.pp1123-1130
Rakesh Kumar Gumasta , Ajay Somkuwar
Timely and accurate crop diseases detection is most important for ensuring global food security. For detecting diseases in crops, many different machine learning (ML) models were proposed. These models work as a black-box, and without proper explanation of these models’ decisions, farmers may find it difficult to trust these systems. For this, many model explainability methods were also proposed. All these methods have been evaluated qualitatively, but their quantitative and cross-comparison are missing. This study addresses this gap by emphasizing quantitative validation of models’ explanations. This study investigates the interpretability and performance of two approaches for potato leaf disease classification: i) manual feature engineering with relief-based feature selection and artificial neural network (ANN) classification with local interpretable model-agnostic explanations (LIME) and ii) deep convolutional neural networks (CNNs) based on mobile network version 2 (MobileNetV2) with gradient-weighted class activation mapping (Grad-CAM). Quantitative assessment of explanation quality was performed using fidelity and robustness metrics. While LIME achieved a lower average fidelity drop 10.90% and higher robustness 84.27% compared to Grad-CAM 18.68% fidelity drops and 79.38% robustness, Grad-CAM provided clearer visual explanations. These findings suggest that explanation effectiveness is influenced by model design and data characteristics, highlighting the need for careful selection of interpretability techniques in precision agriculture applications.
Volume: 15
Issue: 3
Page: 1123-1130
Publish at: 2026-09-01

Novel approach for assessing the maximum load capacity of buses within a power transmission network

10.11591/ijape.v15.i3.pp1105-1116
Moussa Gonda , Arouna Oloulade , Richard Gilles Agbokpanzo , Maurel Richy Aza-Gnandji , Hassane Ousseyni Ibrahim , Cossi Télesphore Nounangnonhou , François-Xavier Fifatin , Adolphe Moukengue Imano
Achieving a balance between the satisfaction of energy requirements and adherence to environmental and social regulations stipulated in international agreements necessitates the rigorous management of existing electricity systems by electricity network operators, thereby ensuring that thermal and stability limits are not exceeded. Consequently, the assessment of load bus maximum capacity (LBMC) at any given load bus (LB) becomes imperative for ensuring the reliability and efficiency of electricity transmission networks. The extant literature on the subject of assessing LBMC in electrical networks either fails to take into account the combined effects on such networks of their various load points or, if it does, it is computationally intensive. The approach proposed in this paper involves a simplified method for assessing the LBMC for each of the LBs in the network. This is achieved to ensure that the combined effect of increasing the load on each of these buses does not compromise the load planning determined by a given network performance index, either during normal operation or in the event of a malfunction. The findings substantiate the efficacy of the proposed methodology, which facilitates the reliable estimation of LBMC. The reliability of this approach is ensured by the selection of a reliable performance indicator, which in our case is the complex stability index for transmission lines (CSITL).
Volume: 15
Issue: 3
Page: 1105-1116
Publish at: 2026-09-01

Machine learning models for predicting daily profitability in Mauritanian digital banking operations: a case study

10.11591/ijict.v15i3.pp925-934
Mohamed Lemine Sidibba , Mohamedou Cheikh Tourad , Ahmad Outfarouin , Nema Sidi Mohamed Mawloud , Mohamedade Farouk Nanne
This article presents a case study on predicting daily profitability in Mauritanian digital banking operations using machine learning models. We utilized a dataset containing detailed information on daily operations to assess predictive models and predict profitability. The study assesses various machine learning models like logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), and multi-layer perceptron classifier (MLPClassifier), in order to identify the most precise model for predicting daily profitability. A systematic approach guides the analysis of banking transactions by performing detailed preprocessing operations which include type conversions, feature selection and missing value management. The dataset receives systematic partitioning into three parts for training, validation and testing to establish model reliability. LR had a recall rate of 99% and an F1-score of 99%, SVM had a recall rate of 53% and an F1-score of 54%, KNN had a recall rate of 96% and an F1-score of 95%, and MLPClassifier had a recall rate of 94% and an F1-score of 97%. The findings show that the LR model performed better than the other models in terms of both recall and F1-score. Future research will investigate both deep learning approaches and hybrid models to enhance prediction accuracy.
Volume: 15
Issue: 3
Page: 925-934
Publish at: 2026-09-01

Conversational AI in museums: a systematic literature review using the people–process–technology framework

10.11591/ijict.v15i3.pp955-966
Diana Utomo , Siti Elda Hiererra
The adoption of conversational artificial intelligence (AI) in museums has opened a new opportunity to create a richer visiting experience to tell stories for the preservation of culture. This paper contributes a systematic literature review (SLR) of 33 peer-reviewed papers covering the period from 2020 to mid-2025, by applying the people–process–technology (PPT) model to examine the social technological aspects of AI implementation. This combination is novel in a museum context, as previous research has largely treated these separately. Findings indicate a pronounced shift from text based chatbots (21% or 7 of 33 papers) to more immersive and interactive platforms (30% or 10 of 33 papers), reflecting the transition from the pandemic (2020 – 2023) to the post-pandemic period (2024 – 2025). Besides the evolution of these technologies, the technology component highlights the importance of data governance, digital preparedness, and value alignment at and across different levels. The people component includes the relevance of hedonic and utilitarian values. Meanwhile, the process component emphasizes both strategic and technical aspects of AI design and implementation, such as knowledge structuring, media selection, and narrative representation. In line with this agenda, this study addresses the trends in literature and provides a path for sustainable appropriation by museums.
Volume: 15
Issue: 3
Page: 955-966
Publish at: 2026-09-01

Early detection of vascular streak dieback (VSD) disease in cocoa plants using deep learning

10.11591/ijict.v15i3.pp1087-1096
Dewi Marini Umi Atmaja , Arif Rahman Hakim , Fadhil Rozi Hendrawan , Komang Diah Devi Pramesty , Naufal Fadhilah Fitrah , Faiz Rochmatullah Widhaputra
Vascular streak dieback (VSD), caused by Ceratobasidium theobromae, poses a significant threat to cocoa (Theobroma cacao) production, leading to substantial yield losses and plant mortality. Early detection is critical to mitigate disease spread and reduce economic impact. While convolutional neural network (CNN) architectures like VGG-16 and ResNet-50 excel in leaf disease detection, no prior studies address stem-based VSD symptomatology where the disease originates in vascular tissues. This study presents the first CNN specifically developed for cocoa stem VSD detection, achieving 99.16% test accuracy with a lightweight architecture that outperforms VGG16/ResNet50 in both accuracy and mobile inference speed. A novel dataset of 215 cocoa stem images was curated and augmented for robustness. Additional evaluation metrics, including precision, recall, specificity, and F1-score, further confirm the reliability of the model. The model was successfully converted into TensorFlow Lite (TFLite) format, enabling deployment on mobile devices for real-time disease detection. This study highlights the potential of integrating deep learning into mobile and drone-based agricultural systems to support precision farming and early intervention strategies.
Volume: 15
Issue: 3
Page: 1087-1096
Publish at: 2026-09-01

Advanced materials for crosstalk and power optimization in TSV-enabled 3D ICs

10.11591/ijict.v15i3.pp1143-1153
Tappeta Chinna Sanjeeva Rayudu , Merrin Prasanna Nagadasari
The continued scaling of semiconductor devices has exposed the limitations of traditional two-dimensional (2D) integrated circuit architectures. To address performance bottlenecks and interconnect constraints, the industry is increasingly adopting three-dimensional (3D) integration technologies. through-silicon vias (TSVs) are a fundamental enabler of this advancement, facilitating vertical signal transmission between stacked silicon layers. Despite their benefits, TSVs face critical challenges related to crosstalk, power dissipation, and signal delay issues that are especially pronounced in dense via arrays. This research explores the use of multi-walled carbon nanotube (MWCNT) based TSVs insulated with different dielectric liners, including silicon dioxide (SiO₂), PPC, polyimide, and benzocyclobutene (BCB). HSPICE simulations are used to evaluate crosstalk noise, power dissipation, power delay product (PDP), and energy delay product (EDP) across varying TSV pitches. Among the materials studied, BCB demonstrates the most promising results. Specifically, MWCNT TSVs with BCB at a 10,000 μm pitch achieve up to 58% reduction in functional crosstalk, 75% in dynamic crosstalk, 78% in power dissipation, and a 52% improvement in PDP compared to single-walled CNT (SWCNT) based TSVs. These findings confirm the suitability of combining MWCNT cores with low-k BCB liners for enhancing performance, energy efficiency, and signal reliability in advanced 3D integrated circuits.
Volume: 15
Issue: 3
Page: 1143-1153
Publish at: 2026-09-01

A multi-cancer detection framework using deep learning and hybrid machine learning approaches

10.11591/ijict.v15i3.pp1443-1452
Karan Singh , Amruta Pawar , Drishya Tomar , Amrita Yadav , Aditi Chhabria , Vaibhav Narawade
The diagnostic solutions offered by the present artificial intelligence (AI) solutions suffer from non-generalizability and heavy reliance on complex models. In an attempt to solve these issues, we propose a lightweight yet versatile method consisting of a combination of ResNet50 transfer learning and hybrid machine learning. Image features are extracted using dermoscopy, magnetic resonance imaging (MRI), and histopathological images. These are subjected to principal component analysis (PCA) dimensionality reduction followed by classification using support vector machine (SVM), random forest (RF), logistic regression (LR), and XGBoost algorithms. This segregation of the two processes improves efficiency. The hybrid approach using ResNet50 + LR yielded an accuracy of 91.01% in the case of breast cancer detection compared to 86.26% of a baseline convolutional neural network (CNN). Also, ResNet50 gave an accuracy of 96.61% in diagnosing skin cancer. Custom CNN provided an accuracy of 99.42% for lung cancer and 96.33% for brain tumor detection.
Volume: 15
Issue: 3
Page: 1443-1452
Publish at: 2026-09-01

Navigating digital parenting: a bibliometric exploration of trends on children’s digital soothing practices

10.11591/ijict.v15i3.pp1431-1442
Rita Wong Mee Mee , Noor Hanim Harun , Lim Seong Pek , Suzulaikha Mohamed , Tengku Shahrom Tengku Shahdan , Nurul Asyiqin Jalil , Anisa Ahmad , Tirzah Zubeidah Zachariah
The digital age has transformed parenting practices, with an increasing reliance on digital devices for managing children’s behavior, particularly as calming tools. This study addresses the growing phenomenon of digital parenting, highlighting its implications on child development and family dynamics. Despite the benefits of digital media, concerns persist regarding its overuse for emotional regulation, which may impede children’s self-regulation skills and parent-child interactions. This study aims to explore the evolution of research on digital parenting using bibliometric analysis. A comprehensive dataset was extracted from the Scopus database, focusing on publications from 2020 to 2024 within the Social Sciences domain. The inclusion criteria included peer-reviewed, open-access articles written in English. A systematic methodology ensured the analysis of performance metrics, trends, and co-authorship patterns. Results indicate a significant increase in scholarly attention to digital parenting, with 837 articles meeting the inclusion criteria. Leading contributions emerged from journals such as Sustainability Switzerland and Education Sciences, with prolific authors and institutions from the United Kingdom and the United States dominating the field. The analysis underscores the interdisciplinary nature of the topic, reflecting contributions from education, media studies, and child development. This study offers valuable theoretical insights and practical recommendations, emphasizing balanced digital media use and informed parenting strategies to foster healthier family dynamics.
Volume: 15
Issue: 3
Page: 1431-1442
Publish at: 2026-09-01

Ensemble deep learning framework for accurate and robust cervical cancer classification

10.11591/ijeecs.v43.i3.pp834-846
Sankarasubramanian Meenakshi
Early and accurate cervical cancer diagnosis (CCD) is essential for improving treatment outcomes and reducing mortality. However, manual examination of cervical cytology images is labor-intensive, time-consuming, and subject to inter-observer variability. To address these limitations, this paper proposes an ensemble deep learning framework for automated cervical cancer classification. The proposed methodology integrates multiple convolutional neural network (CNN) models to exploit their complementary feature extraction capabilities, thereby improving classification accuracy and robustness. Image preprocessing and data augmentation techniques are employed to enhance image quality, reduce noise, and increase the diversity of the training dataset, enabling better model generalization. The outputs of the individual CNN models are combined through an ensemble decision strategy to generate more reliable diagnostic predictions than those obtained from a single classifier. Experimental results demonstrate that the proposed framework consistently outperforms conventional deep learning methods in terms of accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). The ensemble approach effectively reduces classification errors while maintaining stable performance across different cervical cell categories. These findings indicate that the proposed framework can serve as a reliable computer-aided diagnostic tool for cervical cancer screening, supporting clinicians in early diagnosis and improving the efficiency, consistency, and reliability of clinical decision making.
Volume: 43
Issue: 3
Page: 834-846
Publish at: 2026-09-01

An improved MVDR beamformer’s noise reduction based on post- filtering

10.11591/ijeecs.v43.i3.pp947-955
Nguyen Thi Huyen Chau , Quan Trong The , Nguyen Minh Thang
Nowadays, microphone array (MA) technology has been installed into almost acoustic equipments, such as surveillance device, mobile phone, voice con trolled- device, teleconference system. Due to its high diversity, high directivity index towards the sound source, MA allows obtaining the original useful of desired talker, the clean speech data or necessary component while attenuating the effect of interferences, annoying background noise, third- party talker with promising spatial diversity, directivity index or different acoustic factors. Minimum variance distortionless response (MVDR) beamformer based on the optimum constrained formulation of mitigating complicated environment, back ground noise field while saving the speech component. However, in realistic recording scenario, because of the error of estimating the direction of arrival, the different microphone quality, the error of sampling frequency, the displacement of microphone geometry, the existence of internal electrical noise, the MVDR beamformer’s evaluation degraded. Consequently, the existence of the remaining noise or speech distortion usually occur. This contribution introduced an additive post- Filtering, which blocks the noise level and increases the speech quality from 10.8 to 12.7 dB and reduces the noise level to 11.2 dB. The numerical experiment has confirmed the effectiveness of the author’s suggested technique in improving the robustness of MVDR beamformer in complex environment.
Volume: 43
Issue: 3
Page: 947-955
Publish at: 2026-09-01

SqueezeNet-driven AI framework for OCR of handwritten English characters and digits

10.11591/ijeecs.v43.i3.pp928-939
Areen Arabiat , Muneera Altayeb
Optical character recognition (OCR) plays a pivotal role in automated data entry, document digitization, and intelligent user interfaces, particularly as digital content continues to expand across diverse applications. Handwritten character recognition remains a challenging task due to variations in writing styles, noise, and structural complexity. This study investigates the use of artificial intelligence (AI) and machine learning (ML) strategies for classifying handwritten English characters and digits, employing the orange3 platform and a dataset of 2,728 images sourced from Kaggle, partitioned into 70% training and 30% testing sets. A SqueezeNet-based feature extraction approach was implemented to generate 1,000 discriminative features, which were subsequently used to train multiple ML classifiers, including support vector machine (SVM), decision tree (DT), and random forest (RF). Experimental evaluation revealed that the RF classifier achieved the highest accuracy of 99.3%, outperforming DT (90.3%) and SVM (89.9%). These findings highlight the effectiveness of lightweight deep learning architectures such as SqueezeNet in enhancing OCR performance, while demonstrating the robustness of ensemble learning methods in achieving near-perfect classification accuracy. The proposed framework underscores the potential of combining efficient feature extraction with ML classifiers to advance OCR systems for handwritten text recognition in real-world applications.
Volume: 43
Issue: 3
Page: 928-939
Publish at: 2026-09-01

Deep learning–driven automated prediction and data analysis of the Indian stock index

10.11591/ijeecs.v43.i3.pp780-791
Vijaykumar Bidve , Ketki Kshirsagar , Jayashree Tamkhade , Sunil Sangve , Geetha R Chillarge , Aryani Gangadhara , Shailesh Kediya , Priyanka Paygude
This study focuses on the Indian stock index (NIFTY50), employing advanced deep learning methodologies to enhance predictive accuracy and support intelligent trading decisions. The research investigates the relationship between the volatility index (VIX) and NIFTY50, analyzing how fluctuations in VIX influence market direction and futures performance. By monitoring real-time variations in VIX during trading hours, the study aims to capture intraday volatility patterns and provide actionable insights for investors. To achieve this, the proposed framework leverages long short term memory (LSTM) networks, a sophisticated deep learning technique well-suited for sequential data analysis and financial forecasting. The methodology encompasses data collection, preprocessing, feature engineering, and the design of an LSTM-based predictive model, followed by rigorous evaluation and back-testing. Experimental results demonstrate the effectiveness of the approach in forecasting NIFTY50 movements, highlighting the potential of LSTM networks to outperform traditional statistical and machine learning models. The findings contribute to the growing body of research on AI-driven financial prediction, offering a paradigm shift in the application of deep learning for stock market analysis and paving the way for more reliable, automated decision-making in investment strategies.
Volume: 43
Issue: 3
Page: 780-791
Publish at: 2026-09-01

Dual view explainability-aware log preprocessing for robust anomaly detection toward ER-CyRIS

10.11591/ijeecs.v43.i3.pp871-879
Fathoni Mahardika , Ema Utami , Kusrini Kusrini , Ferry Wahyu Wibowo
Machine learning based intrusion detection can achieve strong benchmark performance yet remain fragile under operational telemetry changes. This paper proposes a dual-view, explainability-aware log preprocessing layer for robust anomaly detection toward ER-CyRIS. The novelty is the use of dynamic-token preservation together with feature stability score (FSS), which turns SHapley additive exPlanations (SHAP)-ranking stability into a preprocessing-level evaluation criterion rather than a post-hoc explanation only. The layer preserves structural log patterns and contextual dynamic tokens, and is evaluated through detection performance, noise degradation, and SHAP-ranking stability. A leakage-controlled ablation on HDFS, BGL, CICIDS2018, and UNSW-NB15 shows that the CICIDS2018 baseline reached F1 = 0.9999 but degraded by 68.1% for XGBoost and 93.9% for random forest under small Gaussian noise. Contextual preprocessing reduced degradation to 58.7%, 54.9%, and 53.6% in selected settings. FSS reached 100% for XGBoost on HDFS and CICIDS2018. The results show that preprocessing mitigates, but does not eliminate, operational brittleness.
Volume: 43
Issue: 3
Page: 871-879
Publish at: 2026-09-01

Aluminium nitride piezoacoustic transducer design for CMOS compatible high-performance ultrasound devices

10.11591/ijeecs.v43.i3.pp718-725
J. Manga , V. J. K. Kishor Sonti
Piezoelectric materials are fundamental to ultrasound probes and scanning devices, enabling the bidirectional conversion of mechanical energy into electrical signals for applications in medical imaging, fingerprint recognition, and non-destructive testing. This capability supports accurate visualization of internal structures, thereby enhancing diagnostic precision. Traditionally, lead zirconate titanate (PZT-4) has been the dominant choice for handheld ultrasound probes due to its high piezoelectric coefficients; however, its limitations include low output efficiency, brittleness, high temperature processing requirements, and significant environmental hazards, particularly marine eco-toxicity during disposal. To overcome these drawbacks, this study investigates aluminium nitride (AlN) as a safer, environmentally sustainable, and thermally stable alternative. AlN offers compatibility with complementary metal oxide semiconductor (CMOS) technology, facilitating integration into compact, high-performance ultrasound devices suitable for biomedical and portable applications. Using COMSOL Multiphysics simulations at 200 kHz, the piezoacoustic response of AlN is analyzed to evaluate its acoustic field behavior under specific electrical inputs. Results highlight AlN’s ability to generate uniform acoustic pressure distributions, supporting its potential for photoacoustic imaging and advanced biomedical diagnostics. This work establishes AlN as a promising material for next-generation ultrasound transducers, combining environmental safety with superior functional performance.
Volume: 43
Issue: 3
Page: 718-725
Publish at: 2026-09-01
1 2 3
...
2097 2098
Show 32 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