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

31,377 Article Results

Optimized ResNet-50 framework for mammogram-based breast cancer classification: a comparative evaluation with EfficientNet-B0

10.11591/ijece.v16i3.pp1199-1212
Muhammad Subali , Lulu Mawaddah Wisudawati , Teresa Teresa
Breast cancer remains one of the most prevalent malignancies worldwide, underscoring the need for accurate and reliable mammographic interpretation. Computer-aided diagnosis (CAD) based on deep learning has emerged as a promising approach to improve both screening performance and diagnostic consistency, yet fairness-driven comparisons between popular convolutional backbones on public mammogram benchmarks remain limited. This study provides a statistically validated, fairness-driven comparison of two widely used convolutional neural network architectures, ResNet-50 and EfficientNet-B0, for mammogram-based breast cancer classification under a rigorously controlled, clinically motivated protocol. The proposed “optimized ResNet-50” framework is defined by patient-level stratified undersampling, paired 5-fold cross-validation with identical partitions, harmonized augmentation and training configurations, and dual statistical testing (paired t-tests and Wilcoxon signed-rank tests), emphasizing methodological rigor rather than architectural novelty. Across MIAS and CBIS-DDSM benchmarks, the models demonstrated complementary strengths, with EfficientNet-B0 excelling in screening-oriented tasks (normal vs. abnormal) and ResNet-50 offering more robust performance for diagnostic-oriented tasks (benign vs. malignant). These findings highlight the value of fairness-driven evaluation protocols in CAD research and support the feasibility of integrating lightweight convolutional neural networks (CNNs) into tiered clinical workflows, where different backbones are strategically deployed for initial screening and confirmatory assessment.
Volume: 16
Issue: 3
Page: 1199-1212
Publish at: 2026-06-01

Enhancing sEMG finger gesture recognition using optimized 1D-convolutional neural network

10.11591/ijece.v16i3.pp1576-1587
Daniel Sutopo Pamungkas , Sumantri K. Risandriya
Robust and precise finger gesture recognition using surface electromyography (sEMG) is essential for developing intuitive prosthetic control systems. However, sEMG signals are inherently stochastic and non-stationary, posing significant challenges for high-accuracy classification in fine-grained movements. This study proposes an optimized 1D convolutional neural network (1D-CNN) framework for classifying 20 distinct fine-grained finger gestures using raw sEMG data from an 8-channel wearable Myo Armband sensor. Unlike traditional methods that rely on manual feature engineering, the proposed 1D-CNN performs end-to-end learning to automatically extract temporal features. The research specifically investigates the impact of temporal windowing strategies, ranging from 400 to 750 ms, on model performance. Experimental results demonstrate that the optimized 1D-CNN achieves a peak test accuracy of 94.4% with a 550 ms window size, demonstrating the model’s robustness across complex gesture classes and significantly outperforming the baseline principal component analysis- support vector machine (PCA-SVM) method which only attained 73.0% accuracy. While the model achieved perfect classification (100%) for index, middle, and little finger movements, a performance drop was observed in thumb recognition (50%) due to muscular crosstalk from deeper anatomical layers. These findings indicate that the integration of optimized windowing and 1D-CNN architectures provides a highly reliable solution for complex large-scale gesture recognition, offering a robust foundation for the next generation of multi-functional prosthetic hands.
Volume: 16
Issue: 3
Page: 1576-1587
Publish at: 2026-06-01

Designing self-healing database fabrics for real-time payment rails

10.11591/ijece.v16i3.pp1360-1368
Raghu Gollapudi
Real-time payment platforms operating at scale face an unforgiving operational reality: even brief outages translate directly into failed transactions, regulatory exposure, and eroded customer trust. Database replication and failover automation have matured considerably over the past two decades, yet a troubling blind spot remains. Recovery frameworks built for general-purpose distributed systems were never designed with settlement finality in mind, and that design omission leaves payment operators exposed to split-brain scenarios that generic high-availability tooling cannot reliably prevent. This paper addresses that omission head-on through a self-healing database fabric purpose-built for payment rail environments. The proposed autonomous resilience fabric architecture (ARFA) operates across three coordinated layers: a continuous monitoring layer that harvests telemetry from compute, storage, and network subsystems; a decision layer that fuses rule-based heuristics with an ensemble of isolation forests, recurrent neural networks, and gradient boosting classifiers to separate genuine fault conditions from transient noise; and a deterministic action layer that executes recovery procedures anchored to explicit settlement finality constraints. In fault injection trials covering node crashes, network partitions, replication lag, and performance degradation, the architecture cut average recovery times by 88% against manual baselines, restoring service in roughly 8 seconds rather than the 180 seconds that human-driven remediation typically requires. False positive rates held below 2% across all failure categories, and the system achieved a 98% recovery success rate. Taken together, these results make a practical case that autonomous resilience and regulatory compliance reinforce rather than conflict with each other when the regulatory constraints are designed in from the start.
Volume: 16
Issue: 3
Page: 1360-1368
Publish at: 2026-06-01

Performance analysis of single and multi-stage metaheuristic optimization on DFFNN for electrocardiogram-based emotion classification

10.11591/ijece.v16i3.pp1562-1575
Giovanni Dimas Prenata , Ahmad Ridho’i
Emotion classification based on electrocardiogram (ECG) signals has attracted increasing attention in affective computing and biomedical signal processing. However, training deep feedforward neural networks (DFFNN) using conventional gradient-based learning often suffers from local minima and slow convergence, particularly when dealing with nonlinear and limited datasets. This study presents a comprehensive performance analysis of single-stage and multi-stage metaheuristic optimization strategies applied to DFFNN for ECG-based emotion lassification in elderly participants. Five models were evaluated: Pure DFFNN, DFFNN optimized using genetic algorithm (GA), particle swarm optimization (PSO), grey wolf optimizer (GWO), and a hybrid multi-stage DFFNN+GA+GWO model. Experimental results from six independent trials demonstrate a substantial reduction in mean squared error (MSE) when metaheuristic optimization is applied. Pure DFFNN produced final MSE values in the range of 0.07462–0.08977, whereas DFFNN+GWO reduced MSE to 0.01894–0.02411. The proposed multi-stage DFFNN+GA+GWO achieved the lowest MSE of 0.014286 in the best run and an average MSE of approximately 0.0212 across trials. Training accuracy improved from 57.14%–66.67% (Pure DFFNN) to 80.95%–85.71% using metaheuristic pproaches. Although testing accuracy remained relatively stable at 33.33%–50.00% due to dataset size constraints, convergence behavior analysis shows that multi-stage optimization enhances stability and reduces oscillatory updates. These findings confirm that multi-stage metaheuristic optimization significantly improves training stability and error minimization in DFFNN models, offering a promising strategy for robust ECG-based emotion classification under small-sample conditions.
Volume: 16
Issue: 3
Page: 1562-1575
Publish at: 2026-06-01

Transformer-based hybrid classification for plant leaf disease detection using vision transformer, principal component analysis, and support vector machine

10.11591/ijece.v16i3.pp1399-1406
Vijayalakshmi S. Abbigeri , Geetha D. Devanagavi
Plant diseases remain a critical challenge in agriculture, causing substantial yield losses and threatening food security. In this work, we propose a hybrid deep feature engineering framework that integrates deep learning-based feature extraction with classical machine learning for accurate plant disease detection. A pretrained vision transformer (ViT) model is employed to extract discriminative features from leaf images, effectively capturing complex spatial relationships. To address the curse of dimensionality, principal component analysis (PCA) is applied, retaining 98% of the variance while reducing feature space complexity. The refined features are then classified using a support vector machine (SVM) optimized through hyperparameter tuning. Experimental results on the bean leaf lesions dataset demonstrate strong performance, achieving 92% accuracy and a weighted F1-score of 0.92. The proposed ViT–PCA–SVM pipeline effectively balances accuracy, computational efficiency, and generalization, making it a promising solution for real-time smart farming applications.
Volume: 16
Issue: 3
Page: 1399-1406
Publish at: 2026-06-01

A new multiplier less memcapacitor emulator with non-linear applications

10.11591/ijece.v16i3.pp1132-1147
Suresha Basavanna , Chandra Shankar , Rudraswamy S. B.
This study describes a memcapacitor emulator without a multiplier that make use of second-generation current conveyor (CCII), operational trans-conductance amplifier (OTA) and the fewest possible passive components. The proposed memcapacitor is proved mathematically and verified using several simulation approaches, such as process corner, non-volatile and hysteresis analysis. Also, provided the layout of CCII and OTA as well. The standard CMOS 90 nm technology is used in the Cadence Virtuoso tool to simulate the proposed memcapacitor emulator. This article also includes the use of memcapacitor emulator in the applications of R-C frequency selective network as well as adaptable neuromorphic structure. To investigate the experimental outcomes, an experimental setup was constructed with commercially available integrated circuits (ICs) CCII’s AD844AN and OTA’s CA3080EZ.
Volume: 16
Issue: 3
Page: 1132-1147
Publish at: 2026-06-01

Ensemble windows intrusion detection system using XGBoost and deep learning

10.11591/ijict.v15i2.pp565-577
Pranitha Kedambady Shiva , Pushparaj D. Shetty
Intrusion detection systems (IDS) are critical for preserving the Windows environment from an ever-changing collection of cyber threats. Current IDS uses deep learning (DL), which are heavy models if used for detection, while others use machine learning (ML) techniques, which require external feature extraction. To resolve this challenge, this paper introduces XGBNN, a new ensemble model that combines the benefits of ML and DL to identify and mitigate attacks against Windows machines effectively. The various ML methods are trained on the publicly available dataset to classify eight types of attacks in a Windows environment. Additionally, deep neural networks (DNNs) are proposed by optimizing the layers and hyperparameters to achieve the best accuracy. Then, the DNN model and XGBoost model are integrated to detect intrusions by utilizing the feature extraction ability of DNN and providing the intermediate features extracted from the last second layer of the DNN to the XGB for classification. The Ensemble model XGBNN optimizes features and offers better decisions. The proposed model achieves an exceptional accuracy of 100%, as demonstrated by the empirical results, and outperforms the benchmark models with an improvement of 0.004%. The purpose of this study is to highlight the effectiveness of hybrid architectures in intrusion detection. These architectures offer a more robust, scalable, and effective method to improve the security of the Windows system against more sophisticated attacks.
Volume: 15
Issue: 2
Page: 565-577
Publish at: 2026-06-01

A multi-modal framework for improving the accuracy of phishing email detection

10.11591/ijece.v16i3.pp1608-1625
Lamees Mohamed Faraj , Sayed Abdel-Gaber , Hanan Fahmy
Phishing emails continue to pose a significant cybersecurity threat, particularly through the increasing use of malicious attachments to evade traditional text-based detection systems. Most existing approaches focus primarily on email content, creating a blind spot in attachment-aware phishing detection. This paper proposes a multi-modal phishing email classification model that integrates email header features, body text analysis, and attachment inspection within an ensemble learning framework. Independent machine learning classifiers are employed for each email component, and a majority voting mechanism is used to determine the final classification decision. The proposed model is evaluated using publicly available email and attachment datasets that are combined to simulate attachment-bearing phishing emails. Experimental results demonstrate strong detection performance across multiple evaluation metrics. Nevertheless, the study acknowledges the limitation of using synthetically paired email bodies and attachments, which may not fully capture real-world semantic relationships. The findings highlight the importance of incorporating attachment-aware analysis into phishing detection systems and provide a foundation for future research on semantic consistency modeling and transformer-based architectures.
Volume: 16
Issue: 3
Page: 1608-1625
Publish at: 2026-06-01

An enhancement of stock price forecasting based on hybrid BiLSTM-Transformer model

10.11591/ijece.v16i3.pp1298-1306
Pham Hoang Vuong , Lam Hung Phu , Le Nhat Duy , Pham The Bao , Tan Dat Trinh
Stock price forecasting presents a challenging problem due to factors like nonlinearity, seasonality, and economic volatility in financial data. Deep learning approaches can handle nonlinearity and complexity of financial data, but they often face limitations in capturing both local and global dependencies. This study introduces a hybrid Transformer–bidirectional long short-term memory (BiLSTM) model to improve stock price forecasting. Our method combines the strength of BiLSTM with the global context understanding of the Transformer by embedding a 1D convolutional layer. The model can efficiently capture short-term and long-term dependencies in stock data. Experimental results on various datasets show that our hybrid model outperforms other well-known models.
Volume: 16
Issue: 3
Page: 1298-1306
Publish at: 2026-06-01

Harnessing NLP and AI to decode political discourse: speech patterns, sentiment analysis, and public perception

10.11591/ijict.v15i2.pp674-682
Malayaj Kumar , Anuj Kumar Singh , Soumitra Das
Using natural language processing (NLP) and artificial intelligence (AI), this study analyzes the frequencies of words and phrases in political leaders’ speeches to track patterns in political discourse. The objective is to identify language patterns, sentiments, and topics of political addresses using state of-the-art methods like automatic transcription (Whisper), Bidirectional gated recurrent unit (GRU) for sentiment analysis, and BERTopic. Through the use of Whisper’s state-of-the-art transcription service, we were able to transcribe the political speeches into machine-readable text, which in turn provides for other types of analysis. Bidirectional GRU classifies sentiment as positive, negative, or neutral with the aim to study how politicians use sentiment to manipulate their listeners. Furthermore, we use BERTopic for tracking the evolution of rhetoric, key trend summarisation, and topic mining and analysis. It illustrates how politicians employ discursive strategies and epilinguistic elements to manage the public mind and reality. Achievements and objectives are framed with positive and defensive emotions aimed at threats or criticisms. The emotional grab of it all is still important. It locates in these the thematic coherence and shifting sentiment that lie at the heart of political storytelling. It shows how political communication is evolving to stay relevant in the digital media age and delivers language – even real-time language pattern tracking – via the use of AI and big data. Further study is needed of multimodal and flexible techniques for analysing political discourse across languages and time periods.
Volume: 15
Issue: 2
Page: 674-682
Publish at: 2026-06-01

Exploring the relationship of learning engagement, learning interaction, and learning outcomes in gamified massive open online courses

10.11591/ijece.v16i3.pp1329-1338
Azizul Mohd Yusoff , Sazilah Salam , Siti Nurul Mahfuzah Mohamad , Bambang Pudjoatmodjo
This study investigates the interplay between learning engagement, interaction, and outcomes within the context of gamified massive open online courses (G-MOOCs). By synthesizing literature on MOOCs, gamification, and user engagement, the research identifies significant correlations among these variables. Utilizing a structural equation model partial least squares (SEM-PLS) approach, the study analyzes data from a survey of Bachelor of Computer Science students at a technical and vocational education and training (TVET) public university. Results indicate that both learning engagement and interaction significantly influence learning outcomes, with optimal results achieved when both factors are high. These findings highlight the potential of gamification to enhance educational experiences and suggest directions for future research in gamified learning environments.
Volume: 16
Issue: 3
Page: 1329-1338
Publish at: 2026-06-01

Enhancing road damage detection performance using the YOLOv9 model

10.11591/ijict.v15i2.pp616-624
Muhammad Farkhan Adhitama , Sutikno Sutikno , Rismiyati Rismiyati
Roads are essential infrastructure that support community mobility, and their condition significantly impacts road user safety. However, manual road damage detection remains inefficient, time-consuming, costly, and prone to human error. To address this issue, this study proposed the YOLOv9 model for automated road damage detection and explored parameter combinations to optimize its performance. The proposed solution leverages the YOLOv9 model, which offers enhanced detection speed and accuracy compared to previous YOLO versions, due to its improved backbone and dynamic label assignment techniques. The method uses pre-trained weights and performs parameter tuning to adapt the model for identifying common road defects, including potholes, longitudinal, lateral, and alligator cracks. A publicly available dataset of road condition images was used for training and evaluation. Experimental results demonstrated that the optimized YOLOv9 model achieved a mean average precision (mAP) of 62.8%, indicating a promising ability to detect multiple types of road damage accurately. This study highlights the potential of YOLOv9 as an effective tool for road monitoring systems, contributing to proactive maintenance strategies and more efficient infrastructure management.
Volume: 15
Issue: 2
Page: 616-624
Publish at: 2026-06-01

A critical review of information retrieval techniques: current trends and challenges

10.11591/ijict.v15i2.pp456-464
Sanket D. Patil , Zahir Aalam
The realm of information retrieval is witnessing transformative advancements, driven by the integration of deep learning techniques, specialized algorithms, and domain-specific applications. Information retrieval systems play an important role in many applications including in the Artificial Intelligence powered systems that can be seen in many applications. Information Retrieval, generally, acts an important task in the knowledge discovery phase of any query based intelligent system. This paper presents a comprehensive review by conducting a detailed analysis of the technological nuances, dataset specifications, and pivotal findings. This detailed review has been done with the special emphasis on the kind of technology used to achieve accurate information retrieval, domain of the study, and the system’s ability to retain or work with tables and figures, among other parameters. Navigating through the rich tapestry of methodologies, the paper underscores the pivotal role of deep learning frameworks in revolutionizing traditional retrieval paradigms. Furthermore, it sheds light on the innovative integration of textual information, algorithmic advancements, and specialized datasets to enhance the efficacy and granularity of information retrieval mechanisms.
Volume: 15
Issue: 2
Page: 456-464
Publish at: 2026-06-01

Surface passivation-induced enhancement of light absorption in photoanodes for quantum dot-based solar cells

10.11591/ijape.v15.i2.pp948-954
Ho Minh Trung , Le Xuan Thuy
Quantum dot-sensitized solar cells hold promise for low-cost, high-efficiency photovoltaic applications; however, instability due to quantum dot degradation and poor interfacial charge transport remain key challenges. In this study, a copper-doped Zn(S,Se) passivation layer was chemically synthesized and applied onto TiO₂/CdS/CdSe@Cu photoanodes. The goal was to shield quantum dots from corrosive polysulfide electrolytes and enhance photon absorption. The morphology, structure, and optical characteristics of the Zn(S,Se):Cu layers were systematically analyzed using field-emission scanning electron microscopy (FESEM), energy-dispersive X-ray spectroscopy (EDX), X-ray diffraction (XRD), and UV-Vis spectroscopy. J-V measurements demonstrated that the ZnSe:Cu-coated photoelectrode achieved a higher power conversion efficiency (5.31%) than the ZnS:Cu counterpart (4.5%). Moreover, electrochemical impedance spectroscopy revealed a lower charge transfer resistance (Rct2 = 331 Ω), indicating improved electron transport and reduced recombination. These findings highlight the potential of Zn(S,Se):Cu layers in enhancing the stability and efficiency of quantum dot-sensitized solar cells, paving the way for more durable and efficient solar energy devices.
Volume: 15
Issue: 2
Page: 948-954
Publish at: 2026-06-01

Sub-X-band reconfigurable antenna network with graphene slots

10.11591/ijece.v16i3.pp1249-1260
Hassna Agoumi , Seddik Bri , Youssef El Amraoui , Adil Saadi
This paper presents the design and analysis of a graphene-slotted hexagonal microstrip patch antenna and its extension to a compact 4×4 planar array operating in the sub-X-band. The objective of this work is to demonstrate that graphene-based electrical reconfigurability can be extended from a single antenna element to an array configuration while improving radiation performance. The proposed antenna integrates graphene slots etched into the radiating patch, where reconfigurability is achieved by electrically tuning the graphene conductivity through an external gate voltage Vg. The single antenna operates around 9.4 GHz with an impedance bandwidth of 400 MHz and a peak gain of 6 dB. The design is then extended to a 4×4 array with an inter-element spacing of approximately 1.2 wavelengths. The array operates in the 9–10 GHz range, provides a bandwidth of 380 MHz, and achieves a maximum gain of 13.08 dB. The results confirm that graphene-enabled reconfigurability can be preserved at the array level without increasing structural complexity.
Volume: 16
Issue: 3
Page: 1249-1260
Publish at: 2026-06-01
1 2 3
...
2091 2092
Show 76 of 2092

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