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

Analysis of tuberculosis detection using deep learning technique and explainable artificial intelligence

10.11591/ijai.v15.i2.pp1623-1631
Shashikiran Srinivas , Kavita Avinash Patil , Kushalatha Monappa Rama , Sudha Venkateshlu , Jayanthi Muthuswamy , Srinivas Babu Narayanappa
Tuberculosis (TB) affects the health of many individuals and is still a prime worldwide health concern despite having so many advanced treatments, as it still lacks technical advancement in its treatment and diagnosis. Accuracy in identification and early detection is essential to reduce the spread and improve treatment outcomes. Traditional methods of diagnosis, such as sputum microscopy and culture, are labor-dependent and subject to human mistakes as it is done by lab technicians. Recent improvements in deep learning have demonstrated significant potential for enhancing and automating diagnostic accuracy. Our research proposes a deep learning based technique that detects TB from chest X-rays after image processing techniques like augmentation. After training on big data, our model pulls off an astonishing accuracy of 97.42% and a loss of 7.17%, outperforming traditional methods. The model uses convolutional neural network (CNN) as a base and transfer learning method, like DenseNet-121, and explainable artificial intelligence (XAI) technique, like Grad-CAM, to recognize TB related patterns effectively and with low false positives. This approach has the ability to revolutionize the diagnosis of TB and offer more dependable, scalable, and timely solutions to healthcare systems worldwide.
Volume: 15
Issue: 2
Page: 1623-1631
Publish at: 2026-04-01

Evaluating learning rate effects on long short-term memory for Indonesian sentiment classification

10.12928/telkomnika.v24i2.27398
Serly; Universitas Maritim Raja Ali Haji Eldina , Tekad; Universitas Maritim Raja Ali Haji Matulatan , Novrizal Fattah; Universitas Maritim Raja Ali Haji Fahmitra
Hyperparameter optimization is a crucial process for enhancing the performance of deep learning models, particularly in the context of Indonesian sentiment classification. This study examines the impact of varying learning rates on a long short-term memory (LSTM) architecture trained with the adaptive moment estimation (Adam) optimizer. The dataset comprises 9,295 Indonesian comments automatically labeled by the Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT) model. Stratified k-fold cross-validation was employed to maintain class balance during training. Learning curves were analyzed to evaluate convergence and identify potential overfitting, while early stopping was applied when performance improvements became insignificant. The one-way analysis of variance (ANOVA) test (p-adj = 0.000575 < 0.05) revealed significant differences among the learning rate variations. Post-hoc analysis indicated the learning rates of 0.0001, 0.001, and 0.002 differ significantly from 0.02. Descriptive statistics showed that a learning rate of 0.001 was the most optimal, achieving the highest validation accuracy while maintaining a relatively low variance. Evaluation across two data categories demonstrated that lower learning rates (0.0001 and 0.002) achieved the best accuracy, 78.71% on in-domain data, whereas higher learning rates (0.01 and 0.02) performed better on cross-domain data with 36% accuracy. These findings highlight the crucial role of learning rate selection in determining model stability and generalization capability.
Volume: 24
Issue: 2
Page: 564-573
Publish at: 2026-04-01

Collaborative and argumentative decision support system applied to land use planning

10.11591/ijeecs.v42.i1.pp237-251
Nawel Boudraa , Djamila Hamdadou
Group decision-making in land-use planning is based on complex processes, due to the diversity of stakeholders and the plurality of criteria to be considered. This article presents the design of a collaborative group decision support system, K-ProSWOT, combining a multi-agent system and multi criteria approaches to support decision-making processes. The methodology combines the K-means clustering algorithm to group similar actions together and reduce the number of options to be studied, the Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE II) method for quantitative ranking of possible alternatives, and Strengths, Weaknesses, Opportunities, Threats (SWOT) analysis to structure qualitative collective argumentation. These tools are integrated into a participative process, culminating in a collective, well-argued decision-making process. An interactive dashboard accompanies the system, keeping track of the various stages in the decision-making process. The proposed approach aims to enhance the quality of territorial decisions by reconciling an objective assessment of data with the active involvement of stakeholders.
Volume: 42
Issue: 1
Page: 237-251
Publish at: 2026-04-01

Evaluating hybrid and standard deep learning models for maximum temperature forecasting in a semi-arid region

10.11591/ijeecs.v42.i1.pp183-193
Oussama Zemnazi , Sanaa El Filali , Sara Ouahabi , Abderrahim Mouhtadi
Temperature forecasting is important for industries affected by climate, especially in semi-arid regions where the weather can change quickly and is hard to predict over time. Many studies have examined various deep learning models, including long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural networks (CNNs), and transformer-based hybrids. However, their performance in data-limited semi-arid environments is often unclear and inconsistent. This study compares six deep learning methods for predicting daily maximum temperatures in Settat, Morocco. It uses 11 years of ground-observed meteorological data. The models examined include a baseline artificial neural network (ANN) and five hybrid structures: ANN-LSTM, ANN-GRU, ANN-CNN, ANN–random forest (RF), and ANN-transformer. The results indicate that the ANN performs the best overall, with MAE = 0.0432, root mean square error (RMSE) = 0.0543, and R² = 0.8820. It surpasses all hybrid models. When using a relative improvement metric, the ANN shows accuracy gains of 32% to 42% compared to the recurrent, convolutional, and attention-based hybrids. These results suggest that in semi-arid climates, where maximum temperature mainly depends on the same-day atmospheric conditions, simpler feedforward models work better than more complex temporal models. The study underscores the need to match model complexity with climatic factors and dataset size, offering a useful benchmark for temperature forecasting in regions with limited data.
Volume: 42
Issue: 1
Page: 183-193
Publish at: 2026-04-01

Agraph neural network framework for vascular streak dieback recognition

10.11591/ijeecs.v42.i1.pp194-204
Slamin Slamin , Rizky Alfanio Atmoko , Antonius Cahya Prihandoko , Muhammad Ariful Furqon , Qurrota A’yuni Ar Ruhimat , Annisa Fitri Maghiroh Harvyanti , Bayu Taruna Widjaja Putra , Roslan Hasni
Vascular streak dieback (VSD) is one of the most destructive diseases affecting cocoa production in Southeast Asia, including Indonesia, where early visual symptoms are often subtle and spatially distributed across the leaf sur face. Conventional image-based disease recognition approaches, particularly those relying solely on convolutional neural networks (CNNs), are effective in extracting local visual features but remain limited in modeling long-range structural relationships such as venation disruption and lesion spread. To ad dress this limitation, this study investigates a hybrid CNN-graph neural network (CNN-GNN) framework for automated VSD recognition from cocoa leaf im ages. A primary dataset consisting of 1,000 RGB images collected directly from cocoa plantations in Jember Regency was used to reflect realistic field condi tions. In the proposed approach, CNNs are employedfor local feature extraction, while graph-based representations enable GNNs to capture global relational pat terns through message passing. Experimental results demonstrate stable learning behavior and strong classification performance, achieving a maximum validation accuracy of 95.2% and an area under the curve (AUC) of approximately 0.94. Further analysis shows balanced precision and recall across classes, indicating reliable discrimination between Sehat and VSD-infected leaves. These findings suggest that hybrid CNN-GNN modeling provides an effective strategy for cap turing both local and distributed structural characteristics of VSD symptoms and highlights the potential of graph-based reasoning to complement convolutional feature learning in plant disease diagnostics.
Volume: 42
Issue: 1
Page: 194-204
Publish at: 2026-04-01

Simultaneous faults diagnosis and prognostic in induction motor drives under nonstationary conditions

10.12928/telkomnika.v24i2.27624
Ameur Fethi; University Tahar Moulay of Saida Aimer , Ahmed Hamida; University of Sciences and Technology of Oran Boudinar , Mohamed El-Amine; University of Sciences and Technology of Oran Khodja , Azeddine; University of Sciences and Technology of Oran Bendiabdellah
In this paper, an auto regressive (AR) model-based approach is applied in the stator current analysis under non-stationary conditions (case of frequency variation due to variable speed operation). Under these conditions, the identification of fault signatures is almost impossible due the variation of the fundamental frequency using conventional analysis methods. Moreover, this approach is used in the diagnosis of multiple faults occurring simultaneously in induction motor drives. In this aim, the stator current signal is decomposed into short segments then the AR modeling approach is applied on each segment. This approach called short-time ROOT-AR is then applied to solve the problem of the non-stationarity of the stator current signal under variable speed operation. The efficiency of the short-time ROOT-AR approach is evaluated through experimental tests in the diagnosis of multiple faults occurring simultaneously in induction motor drive. Finally, the superiority of the proposed approach is highlighted in comparison with conventional techniques in terms of accuracy, computational time and robustness against the noise.
Volume: 24
Issue: 2
Page: 717-726
Publish at: 2026-04-01

Correlation-based assessment of 4G LTE network performance during rainfall events in tropical regions

10.11591/ijeecs.v42.i1.pp105-114
Ngozi C. Eli-Chukwu , Uma Uzubi Uma , Handel Emezue , Ogechi Akudo Nwogu , Ogah E. Oga , Calister N. Ogbonna-Mba , Samuel I. Ezichi
This paper presents a performance evaluation of a fourth-generation (4G) cel lular network under adverse weather conditions in a tropical region. While the impact of rainfall on frequencies above 10 GHz is well documented, this study addresses the research gap concerning 4G LTE performance (sub-6 GHz) in high-precipitation environments such as Nigeria. Using a drive-test approach with TEMS Investigation software (v16.3), measurements were collected over 48 days between July and September 2025 along a fixed 15 km route in the Lagos metropolis on the MTN Nigeria network. Samples were recorded at 1 second intervals. Four critical key performance indicators (KPIs)—reference signal received power (RSRP), reference signal received quality (RSRQ), signal to-interference-plus-noise ratio (SINR), and received signal strength indicator (RSSI)—wereanalyzedtodeterminetheir influence on the network performance index (NPI). Correlation analysis revealed that while RSRP exhibits no sig nificant correlation with NPI during rainfall (rs = 0.009), SINR and RSRQ demonstrate strong positive correlations (rs = 0.828 and rs = 0.824, respec tively). Despite these high correlations, average performance values remained low (mean SINR = 23.72%), indicating significant rain-induced degradation. These findings provide a novel empirical basis for the development of weather aware adaptive algorithms in tropical 4G network deployments.
Volume: 42
Issue: 1
Page: 105-114
Publish at: 2026-04-01

A sequential attention-enhanced deep learning framework for robust potato leaf disease diagnosis under real field conditions

10.11591/ijai.v15.i2.pp1790-1803
Watcharkorn Yoochomboon , Nithizethe Mhuadthongon , Piyaporn Krachodnok
Diagnosing potato leaf diseases from images collected in real-life field settings is challenging, mainly because of uneven lighting, complex backgrounds, and disease symptoms that are often subtle or visually inconsistent. In this study, a deep learning-based framework was developed to support potato leaf disease diagnosis, with particular attention given to improving generalization and interpretation. Several convolutional neural network (CNN) architectures were first examined under the same experimental conditions, and ResNeXt-50 showed the most stable overall performance. The model was then extended by applying efficient channel attention (ECA), followed by spatial attention adapted from the convolutional block attention module (CBAM). Test results indicate that this sequential attention design performs better than the baseline model as well as variants using only a single attention mechanism. Additional evaluation using 300 real-field images collected under different field conditions suggests improved robustness, while visualization results from gradient weighted class activation mapping (Grad-CAM) show clearer focus on lesion-related regions. Overall, the findings suggest that combining channel wise and spatial attention can improve both prediction reliability and interpretability, making the approach suitable for practical agricultural use.
Volume: 15
Issue: 2
Page: 1790-1803
Publish at: 2026-04-01

Improving multilabel classification of hate speech and abusive language in Indonesian using MAML

10.12928/telkomnika.v24i2.27332
Jasman; Institut Teknologi Nasional Bandung Pardede , Ghixandra; Institut Teknologi Nasional Bandung Julyaneu Irawadi , Rizka; Institut Teknologi Nasional Bandung Milandga Milenio
This study investigates automated multi-label detection of hate speech and abusive language (HSAL) in Indonesian social media, addressing challenges of data imbalance, especially in minority labels. Two training approaches are compared: standard supervised learning and meta-learning using the model-agnostic meta-learning (MAML) algorithm. IndoBERTweet-BiGRU is adopted as the baseline model, while MAML is leveraged to enhance generalization and adaptability with limited training data. Both models are trained on a multilabel dataset with 13 HSAL categories exhibiting highly imbalanced distributions. The best supervised model achieved an F1-Micro of 84.02% and an F1-macro of 77.97%, whereas the best MAML-trained model reached 84.12% and 76.85%, respectively. Although the overall gap is small, MAML demonstrates notable improvements on minority classes such as hate speech (HS) physical, gender, and race, shown through higher F1-score and area under the receiver operating characteristic curve (AUROC) values. These results highlight its strength in low-resource classification settings. This study is limited to Indonesian language and YouTube transcript contexts, and MAML incurs higher training complexity. Cultural and linguistic nuances also present potential bias in real-world use. Despite these constraints, the proposed system offers practical benefits by enabling fine-grained HSAL classification and supporting earlier detection of harmful online content.
Volume: 24
Issue: 2
Page: 549-563
Publish at: 2026-04-01

Attributes conducive to anthropomorphism in artificial intelligence

10.12928/telkomnika.v24i2.27483
Rizwan; Murray State University Syed , Hassan; Murray State University Mistareehi
The rapid development of artificial intelligence (AI), particularly large language models (LLMs), has generated both enthusiasm and concern regarding its role in society. While these systems demonstrate impressive technical capabilities, public acceptance is often hindered by perceptions of unpredictability, mistrust, and fears amplified by media narratives. One potential strategy to improve user acceptance is anthropomorphism, the attribution of human-like qualities to AI systems which can make interactions feel more natural and trustworthy. This paper investigates the attributes most conducive to anthropomorphism by conducting a structured review across psychology, human-robot interaction, communication studies, and business applications. The analysis identifies key traits such as emotional expressiveness, conversational coherence, adaptive social behavior, and role-based framing that enhance perceptions of AI as relatable and dependable. By synthesizing these insights, we propose a conceptual framework that highlights the psychological, social, and technical dimensions of anthropomorphism in AI. The findings provide guidance for designing AI systems that balance efficiency with user trust, thereby supporting more effective integration of AI into business, research, and everyday life.
Volume: 24
Issue: 2
Page: 588-598
Publish at: 2026-04-01

Design of vehicle to vehicle communication: accident collision prevention using light fidelity and wireless fidelity technology

10.12928/telkomnika.v24i2.27570
Folashade Olamide; Landmark University Omua-ran Nigeria Ariba , Yusuf Isaac; Landmark University Omu-Aran Onimisi , Adedotun; Landmark University Omu-Aran Ijagbemi , Dickson Ogochukwu; Landmark University Omu-Aran Egbune
Vehicle-to-vehicle (V2V) communication is a key component of intelligent transportation systems (ITS), enabling seamless data exchange between vehicles to limit collision risks. This study presents a hybrid communication framework that integrates light fidelity (LiFi) and wireless fidelity (WiFi) technologies to enhance safety and reliability in accident prevention. Lifi using visible light communication, provides line-of-sight for short-range communication, while WiFi ensures long-range coverage in dynamic traffic environments. The proposed system allows vehicles to share speed, braking, and positional data, enabling timely warnings to drivers in high-risk scenarios. The system fuses data communication protocol design, simulation, prototype development, testing, and evaluation. The prototype model was designed and simulated to evaluate the performance of the system in terms of functionality, timing and reliability. Results indicate that the hybrid LiFi-WiFi system improves data transmission efficiency and reduces delay compared to standalone wireless systems. This approach demonstrates significant potential in developing safer transportation networks by combining complementary wireless technologies for V2V communication.
Volume: 24
Issue: 2
Page: 396-406
Publish at: 2026-04-01

Semantic-syntactic graph network for aspect-based sentiment analysis

10.11591/ijai.v15.i2.pp1814-1824
Rekha Bdurga Harish , Neelambike Siddalingaiah
Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that identifies sentiment polarities toward specific aspects within a sentence. While conventional models have achieved progress, they often neglect to jointly consider both semantic context and syntactic structure, limiting performance in complex linguistic scenarios. Nevertheless, most existing graph convolutional network (GCN)-based approaches have recently focused on either semantic or syntactic information individually, leading to suboptimal sentiment classification accuracy. Hence, this work aims to design an effective ABSA model that simultaneously captures both semantic relationships and syntactic dependencies for enhanced aspect-level sentiment analysis. For solving issues of GCN-based approaches, this work proposed a model called sentiment semantic syntactic network (SentSemSynNet), which constructs a unified graph by integrating semantic and syntactic features and applies graph neural networks to learn rich, aspect-specific representations. The model was evaluated on the SemEval2014 restaurant and laptop datasets. It achieved 88.25% accuracy and 82.95% macro-F-score for restaurant, and 84.52% accuracy and 80.26% macro-F-score for laptop. The model’s unique integration of both semantic and syntactic importance through a unified graph structure improved sentiment detection accuracy.
Volume: 15
Issue: 2
Page: 1814-1824
Publish at: 2026-04-01

Level of detail in UML models and its impact on model comprehension: a replication study

10.11591/ijeecs.v41.i3.pp1095-1104
Ariadi Nugroho , Michel R.V Chaudron
This replication study examines the impact of level of detail (LoD) in unified modeling language (UML) on model comprehension, replicating a controlled experiment, which involved 53 MSc students at Eindhoven University of Technology. Using the same UML model and experimental design, we conducted the study with 23 MSc Computer Science students at Bina Nusantara University, Indonesia. Consistent with the original findings, higher LoD was found to enhance comprehension correctness. However, the effect on comprehension efficiency was weaker and not statistically significant, likely due to the smaller sample size and contextual differences in subjects’ backgrounds. Furthermore, we found a potential disconnect between perception and actual comprehension performance in the subjects receiving UML model with low LoD. Specifically, while they viewed the model favourably, their actual understanding may have been impaired by the limited information and therefore the perceived clarity and ease of comprehension are not reflective of the true comprehension. Overall, this study reinforces the importance of LoD in UML modeling and highlights the need for further replication, particularly in contexts involving professional software engineers.
Volume: 41
Issue: 3
Page: 1095-1104
Publish at: 2026-03-10

Overvoltage assessment of wind energy integration in low voltage distributed grids

10.11591/ijeecs.v41.i3.pp859-872
Farid Merahi , Badoud Abd Essalam
Large-scale integration of renewable energy (RE) resources into the electrical grid has increased significantly over the last decade, affecting the network at various nodes even at considerable distances from the common connection point. This paper presents an overvoltage assessment caused by the integration of two wind generators (WGs) into a low voltage distribution grid, which is structured into three zones. Two scenarios are studied, the first one considers the low voltage grid without WGs, representing its natural operating condition. In the second scenario, two WGs are connected in zone 3, inducing voltage rises at different nodes within the same zone, by reaching 7.9%, and affecting nodes located in other zones (Zone 1 and Zone 2). The simulation is performed using MATLAB/Simulink (R2025a), and the results obtained are compared to the standards test feeder IEEE 33-bus network, showing the overvoltage caused by WGs integration at nodes close to the connection point while improving voltage quality at distant nodes.
Volume: 41
Issue: 3
Page: 859-872
Publish at: 2026-03-10

IoT-enabled digital twin with renewable energy for sustainable mudless eel aquaculture

10.11591/ijeecs.v41.i3.pp912-923
Muhammad Ferdiansyah , Lika Mariya , Taufik Rahman , Sugeng Dwiono
This research develops and tests a digital twin (DT)-based smart aquaculture system for mud-free eel farming through the integration of IoT sensing, artificial intelligence (AI)-based prediction, edge computing, and solar energy-based automation. The approach used is experimental systems engineering, which includes system design, hardware and software implementation, virtual replication, and physical-digital two-way synchronization. The system utilizes ESP32-based pH, temperature, dissolved oxygen (DO), ammonia (NH₃), and turbidity sensors, MQTT communication, and Raspberry Pi edge computing. Water quality prediction is performed using long short-term memory (LSTM) and random forest regression. The dataset consists of 30 days of real-time data covering water quality, actuator activity (aerator, pump, feeder), and energy production and consumption by IoT sensors and energy meters. Results show that LSTM excels by R² = 0.94; RMSE = 0.14; MAPE <5% and synchronization latency <1.5 seconds. Solar energy integration reduces energy consumption by 54 67%, whilst automation increases eel survival rate by 78% to 91%. The novelty of this research lies in the first integrated implementation of DT, AIoT, and solar energy-based automation in mud-free eel farming. The proposed framework provides a precise, scalable, and sustainable solution for the development of modern aquaculture.
Volume: 41
Issue: 3
Page: 912-923
Publish at: 2026-03-10
1 2 3
...
2097 2098
Show 116 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