Article Per Year (5 Year)
p-Index From 2021 - 2026
1.909
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering IAES International Journal of Artificial Intelligence (IJ-AI) International Journal of Advances in Applied Sciences Jurnal Buana Informatika Jurnal Edukasi dan Penelitian Informatika (JEPIN) Scientific Journal of Informatics Dinamisia: Jurnal Pengabdian Kepada Masyarakat Jurnal Pemberdayaan: Publikasi Hasil Pengabdian Kepada Masyarakat Journal of Electronics, Electromedical Engineering, and Medical Informatics Indonesian Journal of Electrical Engineering and Computer Science Jurnal Teknik Informatika (JUTIF)
Wiharto Wiharto
Sebelas Maret University
Arts Humanities Computer Science & IT Control & Systems Engineering Earth & Planetary Sciences Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Physics Social Sciences Other

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Squeeze-excitation half U-Net and synthetic minority oversampling technique oversampling for papilledema image classification Wiharto, Wiharto; Syaifuddin, Angga Exca Pradipta
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i2.pp1410-1419

Abstract

The emergence of various convolutional neural networks (CNN) architectures indicates progress in the computer vision field. However, most of the architectures have large parameters, which tends to increase the computational cost of the training process. Additionaly, imbalanced data sources are often encountered, causing the model to overfit. The aim of this study is to evaluate a new method to classify retinal fundus images from imbalanced data into the corresponding classes by using fewer parameters than the previous method. To achieve this, squeeze-excitation half U-Net (SEHUNET) architecture, a modification of half U-Net with squeeze-excite process to provide attention mechanism on each feature maps channel of the model, in combination with synthetic minority oversampling technique (SMOTE) is proposed. The test accuracy of SEHUNET is 98.52% with area under the curve of receiver operation characteristic (AUROC) of 0.999. This result outperforms the previous study that used CNN with Bayesian optimization, achieving accuracy of 95.89% and AUROC of 0.992. SEHUNET is also able to compete with the transfer learning methods used in previous research such as InceptionV3 with 96.35% accuracy, visual geometry group (VGG) with 96.8%, and ResNet with 98.63%. This performance can be achieved by SEHUNET with only 0.268 million parameters compared to the architecture parameters used in previous research ranging from 11 million to 33 million.
Detection of COVID-19 based on cough sound and accompanying symptom using LightGBM algorithm Wiharto, Wiharto; Abdurrahman, Annas; Salamah, Umi
Indonesian Journal of Electrical Engineering and Computer Science Vol 38, No 2: May 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v38.i2.pp940-949

Abstract

Coronavirus disease 19 (COVID-19) is an infectious disease whose diagnosis is carried out using antigen-antibody tests and reverse transcription polymerase chain reaction (RT-PCR). Apart from these two methods, several alternative early detection methods using machine learning have been developed. However, it still has limitations in accessibility, is invasive, and its implementation involves many parties, which could potentially even increase the risk of spreading COVID-19. Therefore, this research aims to develop an alternative early detection method that is non-invasive by utilizing the LightGBM algorithm to detect COVID-19 based on the results of feature extraction from cough sounds and accompanying symptoms that can be identified independently. This research uses cough sound samples and symptom data from the Coswara dataset, and cough sound’s features were extracted using the log mel-spectrogram, mel frequency cepstrum coefficient (MFCC), chroma, zero crossing rate (ZCR), and root mean square (RMS) methods. Next, the cough sound features are combined with symptom data to train the LightGBM. The model trained using cough sound features and patient symptoms obtained the best performance with 95.61% accuracy, 93.33% area under curve (AUC), 88.74% sensitivity, 97.91% specificity, 93.17% positive prediction value (PPV), and 96.33% negative prediction value (NPV). It can be concluded that the trained model has excellent classification capabilities based on the AUC values obtained.
Model Group Decision Support System Based on Depression Anxiety Stress Scales Using Ordered Weighted Averaging Aggregation Method Wiharto, Wiharto; Putri, Della K.; Sihwi, Sari W.; Salamah, Umi; Suryani, Esti; Atina, Vihi; Utomo, Pradityo
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 2 (2025): April
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i2.678

Abstract

Depression, anxiety, and stress are common psychological conditions often triggered by the pressures of daily life. Depression Anxiety Stress Scale (DASS), is a widely used tool for assessing the severity of these disorders, available in different versions such as the DASS-21 and DASS-42. In line with these findings, DASS-21 consists of 21 symptom items, categorized into three types of disorders, with seven items assigned to each. In contrast, the DASS-42 includes 42 symptom items, with 14 items allocated per disorder. Both versions serve as standardized tools for assessing the severity of depression, anxiety, and stress, and the different versions show that one item only affects one disorder. In practice, it can affect several disorders with different priorities. This condition increases the risk of subjective bias in a psychologist's decision-making, as personal experiences and perceptions may influence their assessments. Therefore, this study aims to develop a Group Decision Support System (GDSS) model that considers the preferences of several psychologists in determining the priority of disorders based on the DASS-42 and DASS-21 items. The model has been built using the psychologist's preference method for DASS-42 and DASS-21 in fuzzy form, then combined using the Ordered Weighted Averaging (OWA) method to produce one decision. The alignment of top-priority items between GDSS and DASS was assessed as part of the evaluation. The results show a high degree of similarity, with GDSS matching 16 out of 21 symptom items in DASS-21 and 35 out of 42 items in DASS-42. The GDSS model can accommodate the preferences of decision-makers in providing weighting of the influence on each item in the DASS-21 and DASS-42, thereby providing more objective decisions.
Breast Cancer Classification on Ultrasound Images Using DenseNet Framework with Attention Mechanism Azka, Hanina Nafisa; Wiharto, Wiharto; Suryani, Esti
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 7 No 3 (2025): July
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v7i3.779

Abstract

Breast cancer is one of the most prevalent and life-threatening diseases among women worldwide. Early detection of breast cancer being critical for increasing survival rates. Ultrasound image is commonly used for breast cancer screening due to its non-invasive, safe, and cost-effective. However, ultrasound images are often of low quality and have significant noise, which can hinder the effectiveness of classification models. This study proposes an enhanced breast cancer classification model that leverages transfer learning in combination with attention mechanisms to improve diagnostic performance. The main contribution of this research is the introduction of Dense-SASE, a novel architecture that combines DenseNet-121 with two powerful attention modules: Scaled-Dot Product Attention and Squeeze-and-Excitation (SE) Block. These mechanisms are integrated to improve feature representation and allow the model to focus on the most relevant regions of the ultrasound images. The proposed method was evaluated on a publicly available breast ultrasound image dataset, with classification performed across three categories: normal, benign, and malignant. Experimental results demonstrate that the Dense-SASE model achieves an accuracy of 98.29%, a precision of 97.97%, a recall of 98.98%, and an F1-score of 98.44%. Additionally, Grad-CAM visualizations demonstrated the model's capability to localize lesion areas effectively, avoiding non-informative regions, and confirming the model's interpretability. In conclusion, the Dense-SASE model significantly improves the accuracy and reliability of breast cancer classification in ultrasound images. By effectively learning and focusing on clinically relevant features, this approach offers a promising solution for computer-aided diagnosis (CAD) systems and has the potential to assist radiologists in early and accurate breast cancer detection.
Early detection of coronary heart disease based on risk factors using interpretable machine learning Wiharto, Wiharto; Mufidah, Farah Nada
International Journal of Advances in Applied Sciences Vol 13, No 4: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijaas.v13.i4.pp944-956

Abstract

Coronary heart disease (CHD) is the leading cause of death in the world. The risk of coronary heart disease can be reduced or even prevented by early detection. Early detection of CHD has been widely developed using machine learning, but the machine learning algorithms used sometimes have low interpretability. Low interpretability makes it difficult for users to understand the cause of the decision. Referring to this, this research aims to propose an early detection model using machine learning interpretability, which is implemented using the C5.0 algorithm and interpreted using Shapley additive explanations (SHAP). This research method is divided into 3 stages, namely preprocessing, interpretable machine learning, and performance evaluation. This study used 215 patient data from Dr. Moewardi Surakarta Hospital. Testing the resulting model using the k-folds cross-validation method. The test results show that the risk factors that make a high contribution to the output of the coronary heart disease detection model are systolic blood pressure, diastolic blood pressure, and employment level, with the resulting accuracy performance of 84.64%. The proposed model can be an alternative for early prediction of coronary heart disease which can explain the influence of each selected risk factor on the model output.
MSME Entrepreneurship Promotion Training Through On-line Applications and Global Social Media: Pelatihan Promosi Wirausaha UMKM Melalui Aplikasi On-line dan Media Sosial Global Widiarto, Wisnu; Wiharto, Wiharto; Salamah, Umi; Suryani, Esti
Dinamisia : Jurnal Pengabdian Kepada Masyarakat Vol. 8 No. 3 (2024): Dinamisia: Jurnal Pengabdian Kepada Masyarakat
Publisher : Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/dinamisia.v8i3.15761

Abstract

Technological advances have had an impact on various fields. Likewise for UMKM entrepreneurs in Gadingan-Mojolaban-Sukoharjo, to promote karak and romeo businesses. This community service program has been implemented by means of socialization, training and mentoring to UMKM entrepreneurs in Gadingan Village, regarding on-line e-commerce applications, and social media. Preliminary analysis of partners has shown problems that occur in UMKM entrepreneurs, namely a lack of understanding of on-line applications and global social media. Implementation of socialization, training and mentoring for partners has been carried out to empower UMKM entrepreneurs. It is expected that partners can follow the flow of technology and be able to face competition in this digital technology era. With increased competition, UMKM entrepreneurs are required to be able to face all challenges. This can be done by increasing product innovation and expanding marketing networks, promotions and publications about their business. The method that has been used is to provide socialization-training- mentoring in promoting and registering businesses in on-line applications and global social media.
Stroke Risk Prediction using Winsorizing Interquartile Range and Tree-Based Classification with Explainable Artificial Intelligence Rahmadani, Fitria; Wiharto, Wiharto; Zuhdi, Shaifudin
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 6 (2025): JUTIF Volume 6, Number 6, Desember 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.6.4760

Abstract

According to the Global Burden of Disease (GBD) Study, stroke is the third leading cause of death globally. Recognizing its signs early is crucial for both prevention and effective treatment. Although machine learning has made significant progress in predicting strokes, many current models operate like "black boxes", making them hard to interpret and often resulting in high error rates. This study aims to enhance prediction accuracy and interpretability in stroke risk detection by integrating Winsorizing Interquartile Range (IQR) for outlier management, a tree-based classification method, and Explainable Artificial Intelligence (XAI) techniques. The proposed approach applies Winsorizing Interquartile Range to handle extreme values while employing tree-based methods for prediction due to their superior performance in processing tabular data. Additionally, Explainable Artificial Intelligence techniques are utilized to improve model transparency and interpretability. Testing was conducted using the Cerebral Stroke Prediction-Imbalanced Dataset, comparing results with various existing models. The suggested approach demonstrated the lowest prediction error rates, achieving a False Positive Rate (FPR) of 15.74% and a False Negative Rate (FNR) of 8.56%. Additionally, it attained an accuracy of 84.39%, sensitivity of 91.43%, specificity of 84.26%, Area Under the Receiver Operating Characteristic Curve (AUROC) of 94.74%, and G-Mean of 87.76%, outperforming previous studies in stroke risk prediction. The combination of Winsorizing Interquartile Range, Random Under-Sampling, tree-based classification, and Explainable Artificial Intelligence techniques effectively enhances prediction accuracy and transparency, supporting early stroke detection with improved interpretability. This study contributes to medical informatics by integrating transparent predictive models suitable for decision support systems.
Classification of Ultrasound Images Using ResNet-50 with a Convolutional Block Attention Module (CBAM) Afif, Bagus Tegar Zahir; Wiharto, Wiharto; Salamah, Umi
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 8 No 1 (2026): January
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v8i1.1406

Abstract

Liver fibrosis staging is a crucial component in the clinical management of chronic liver disease because it directly affects prognosis, therapeutic decision-making, and long-term patient monitoring. Ultrasound imaging is widely used as a noninvasive diagnostic modality due to its safety, low cost, and broad accessibility. Nevertheless, ultrasound-based fibrosis assessment remains challenging because liver parenchymal echotexture often exhibits low contrast, speckle noise, and subtle inter-stage variations, particularly among adjacent METAVIR stages. These characteristics frequently limit the effectiveness of conventional convolutional neural networks, which tend to emphasize dominant global patterns while suppressing weak but clinically meaningful texture cues. This study presents a task-oriented integration of a Convolutional Block Attention Module into a ResNet-50 backbone to enhance feature discrimination for five-stage liver fibrosis classification using heterogeneous B-mode ultrasound images. Rather than introducing a new attention mechanism, the contribution lies in the systematic insertion of CBAM after residual outputs across multiple network stages, enabling repeated channel and spatial recalibration from low-level texture descriptors to higher-level semantic representations. To further improve robustness and reduce prediction variance, a stratified 5-fold training strategy is combined with logit-level ensemble inference, where logits from independently trained fold models are averaged prior to Softmax normalization. Experiments were conducted on a publicly available dataset comprising 6,323 ultrasound images acquired from two tertiary hospitals using multiple ultrasound systems, with fibrosis stages labeled from F0 to F4 according to histopathology-based METAVIR scoring. The proposed framework achieves a test accuracy of 98.34%and consistently high precision, recall, and F1 scores across all fibrosis stages, with the most pronounced improvement observed for intermediate stages. Statistical analysis based on paired fold-wise comparisons confirms that the performance gain over the baseline ResNet 50 model is statistically significant. These results demonstrate that combining lightweight attention-based feature refinement with logit ensemble inference effectively addresses the inherent challenges of ultrasound-based liver fibrosis staging and provides a reliable noninvasive decision support framework with strong potential for clinical application and future multicenter validation.
Mental Health Detection Expert System Model Based on DASS-42 Using Fuzzy Inference System Rahmat, Eko Ginanjar Basuki; Wiharto, Wiharto; Salamah, Umi
Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol 8 No 1 (2026): January
Publisher : Department of Electromedical Engineering, POLTEKKES KEMENKES SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/jeeemi.v8i1.1443

Abstract

Mental health disorders such as depression, anxiety, and stress frequently co-occur and exhibit overlapping symptoms, making accurate diagnosis challenging due to the subjective nature of psychological assessments. Conventional use of the Depression Anxiety Stress Scales (DASS-42) relies on rigid score aggregation, while many machine learning approaches fail to adequately represent uncertainty and expert reasoning. This study aims to develop an expert system for mental health detection by integrating fuzzy logic with expert knowledge derived from the DASS-42 instrument. The main contribution of this research is a hybrid knowledge-based framework that combines decision tree–based rule extraction with psychological expert validation, ensuring both interpretability and clinical relevance. The proposed method employs a Fuzzy Inference System (FIS) using triangular and trapezoidal membership functions to model symptom intensity as linguistic variables, followed by rule generation using the CART decision tree algorithm and expert refinement. System performance is evaluated using Cohen’s Kappa coefficient, including standard error and 95% confidence intervals, to measure inter-rater reliability between the expert system, the DASS instrument, and two human experts. The results indicate that the expert system achieves almost perfect agreement in identifying dominant psychological conditions, with an average Kappa value of 0.918. For severity-level classification, strong agreement is observed for depression (Kappa = 0.842) and stress (Kappa = 0.811), while anxiety severity shows moderate-to-substantial agreement (Kappa = 0.648), reflecting inherent variability in expert interpretation. In conclusion, the proposed FIS-based expert system effectively captures expert diagnostic reasoning and outperforms decision tree–only models, demonstrating strong potential as an interpretable and reliable mental health screening tool.
Co-Authors Abdurrahman, Annas Afif, Bagus Tegar Zahir Anita Indrasari Atina, Vihi Azka, Hanina Nafisa Esti Suryani Katarina Novi Wahyudiani, Katarina Novi Meiyanto ES Mufidah, Farah Nada Mufidah, Yasmin Pamundi, Dias Lanjar Pradityo Utomo Pratama, Fadil Putri, Della K. Rahmadani, Fitria Rahmat, Eko Ginanjar Basuki Sihwi, Sari W. Syaifuddin, Angga Exca Pradipta Syamsul Arifin Umi Salamah Wina Isti Retnani Wisnu Widiarto Zuhdi, Shaifudin