cover
Contact Name
Much Aziz Muslim
Contact Email
a212muslim@yahoo.com
Phone
+628164243462
Journal Mail Official
shmpublisher@gmail.com
Editorial Address
J. Karanglo No. 64 Semarang
Location
Kota semarang,
Jawa tengah
INDONESIA
Journal of Soft Computing Exploration
Published by shm publisher
ISSN : 27467686     EISSN : 27460991     DOI : -
Core Subject : Science,
Journal of Soft Computing Exploration is a journal that publishes manuscripts of scientific research papers related to soft computing. The scope of research can be from the theory and scientific applications as well as the novelty of related knowledge insights. Soft Computing: Artificial Intelligence Applied Algebra Neuro Computing Fuzzy Logic Rough Sets Probabilistic Techniques Machine Learning Metaheuristics And Many Other Soft-Computing Approaches Area Of Applications: Data Mining Text Mining Pattern Recognition Image Processing Medical Science Mechanical Engineering Electronic And Electrical Engineering Supply Chain Management, Resource Management, Strategic Planning Scheduling Transportation Operational Research Robotics
Articles 146 Documents
Implementation of internet of things for leakage current monitoring system in medical equipment Pradana, Dio Alif; Mukhammad, Yanuar; Hyperastuty, Agoes Santika
Journal of Soft Computing Exploration Vol. 6 No. 1 (2025): March 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i1.536

Abstract

The rise in electricity consumption, especially in the health sector, has heightened concerns about electrical safety, particularly leakage current in medical equipment. The main objective of this research is to develop an IoT-based leakage current monitoring system specifically designed for low-voltage medical devices, aiming to enhance safety and prevent electrical hazards such as electric shocks and equipment damage. The system used two current sensors module (PZEMT-004T) to measure leakage at points near the voltage source and medical components. Data were processed by a microcontroller and transmitted to a web server for real-time monitoring via mobile devices. Testing on humidifiers and ECGs showed average accuracies of 90.11% and 92.49%, respectively, within a 10 mA range. However, the system could not detect currents below the 3 mA safety threshold because of the sensors reading limitation at 10 mA, indicating a need for sensor improvements. The IoT-based system enhances medical equipment safety, with future work focusing on better sensors and AI for predictive maintenance.
An advanced logistic regression model for forecasting payer revenue in private hospitals: a case study in manado Mokodaser, Wilsen; Koapaha, Hartiny Pop
Journal of Soft Computing Exploration Vol. 6 No. 1 (2025): March 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i1.555

Abstract

Manado, the provincial capital, stands as a vital center for healthcare services, where private hospitals compete intensively to attract patients from various economic and social backgrounds. Accurate revenue forecasting for partnered payers is essential for effective management strategies. This study employs a logistic regression model, achieving a notable accuracy of 79.55% in predicting hospital revenue based on payer partnerships. The confusion matrix reveals 21 true negatives (TN), confirming the model accurately identified low-revenue customers, with zero false positives (FP), indicating no misclassification of these individuals. However, 9 false negatives (FN) highlight a critical risk, as high-revenue customers were miscategorized as low revenue, even though 14 true positives (TP) were precisely identified. Based on these insights, hospitals can strategically target 61 payers projected to exceed median revenue, presenting a significant opportunity for income growth. Conversely, the 159 payers identified as below median revenue warrant urgent attention. To enhance engagement and increase revenue from these lower-revenue groups, targeted business strategies such as intensified marketing, personalized service offerings, and promotional discounts are recommended. This research contributes a novel approach to leveraging predictive analytics in healthcare, underscoring the pressing need for hospitals to innovate their operational strategies to optimize revenue in a competitive landscape.
Improved human image density detection with comparison of YOLOv8 depth level architecture and drop-out implementation Yulita, Winda; Ramadhani, Uri Arta; Mufidah, Zunanik; Atmajaya, Gde KM; Bagaskara, Radhinka; Kesuma, Rahman Indra; Aprilianda, Mohamad Meazza
Journal of Soft Computing Exploration Vol. 6 No. 1 (2025): March 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i1.556

Abstract

Energy inefficiency due to Air Conditioners (AC) running in empty rooms contribute to unnecessary energy consumption and increased CO₂ emissions. This study explores how different depth levels of the YOLOv8 architecture and dropout regularization can enhance human density detection for smarter AC control systems. By evaluating model accuracy through Mean Average Precision (mAP50-95), we provide quantitative insights into how these modifications improve detection performance. Our dataset consists of 1363 images taken in an office environment at ITERA under varying lighting conditions and different human presence densities. The results show that the YOLOv8m model performs best, achieving an mAP50-95 score of 0.814 in training and 0.813 in validation, outperforming other YOLOv8 variants. Furthermore, applying dropout regularization improves model generalization, increasing mAP50-95 from 0.552 to 0.6 and effectively reducing overfitting. This study highlights the balance between architectural depth and dropout regularization in YOLOv8, demonstrating its effectiveness in energy-efficient smart buildings. The findings support the potential of deep learning-based human density detection in improving energy conservation strategies, making it a valuable solution for intelligent automation systems.
Optimizing Seq2Seq LSTM for Regional-to-National language translation on a web platform Af'idah, Dwi Intan; Susanto, Ardi; Mohamad, Masurah; Alfat, Lathifah
Journal of Soft Computing Exploration Vol. 6 No. 1 (2025): March 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i1.561

Abstract

Machine translation for low-resource languages remains a significant challenge due to the lack of parallel corpora and optimized model configurations. This study developed and optimized a Seq2Seq Long Short-Term Memory (LSTM) model for Tegalan-to-Indonesian translation. A manually curated parallel corpus was constructed to train and evaluate the model. Various hyperparameter configurations were systematically tested, with the best-performing model achieving a BLEU score of 11.7381 using a dropout rate of 0.5, batch size of 64, learning rate of 0.01, and 70 training epochs. The results demonstrated that higher dropout rates, smaller batch sizes, and longer training durations enhanced model generalization and translation accuracy. The optimized model was deployed into a web-based application using Streamlit, ensuring accessibility for real-time translation. The findings highlighted the importance of hyperparameter tuning in neural machine translation for low-resource languages. Future research should explore Transformer-based architectures, larger datasets, and reinforcement learning techniques to further enhance translation quality and generalization.
Design and implementation of a web-based thesis guidance system using the waterfall method Muslihah, Isnawati; Laksani, Hening; Bagaskara, Danendra
Journal of Soft Computing Exploration Vol. 6 No. 2 (2025): June 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i2.513

Abstract

The advancement of technology and the internet has opened up opportunities for the development of information systems in higher education in Indonesia. One significant system is the online thesis guidance system for students. Currently, the guidance process at ISI Surakarta is conducted manually and face-to-face, which has proven to be less effective due to scheduling conflicts between students and lecturers, leading to delays in thesis progress. The development of the online thesis guidance system aims to facilitate interaction between lecturers and students while digitally storing review histories and revisions, enhancing the efficiency of administrative data collection. Additionally, the system is designed to provide announcements and timelines from proposal submission to eligibility examinations, helping students monitor their performance to graduate on time. The Waterfall method is employed in this system's design to ensure a systematic development process, covering all stages from requirements analysis to maintenance. This method allows early detection of potential conditions and ensures that user needs are met before the system is implemented. The implementation of this system is expected to improve the efficiency and quality of academic services, support students in completing their studies on time, and provide benefits to the entire academic community of ISI Surakarta.
Melanoma detection on skin images using deep learning based on convolutional neural network (CNN) Irjanto, Nourman Satya; Hermawan, Ruly
Journal of Soft Computing Exploration Vol. 6 No. 2 (2025): June 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i2.567

Abstract

Melanoma is a life-threatening skin cancer that poses challenges in regions with limited access to specialized medical personnel, such as Papua, Indonesia. Early diagnosis is essential, but accurate detection is hindered by the scarcity of dermatologists. This study develops a melanoma detection system using computer vision, utilizing the VGG16 architecture enhanced with the Convolutional Block Attention Module (CBAM) and fine-tuning via transfer learning. The model was trained on a dataset comprising melanoma and non-melanoma images, with data augmentation to address class imbalance. The model achieved an accuracy of 91.25%, precision of 92.31%, recall of 90%, and an F1-score of 91.13%, demonstrating reliable performance in melanoma classification. High specificity (92.5%) indicates a low false positive rate, while sensitivity (90%) shows effective melanoma detection, though the 10% false negative rate requires improvement. Future enhancements include increasing sensitivity through weighted loss functions, optimizing classification thresholds, and performing external validation. Additionally, Grad-CAM is used for interpretability, and a web-based application is proposed to support healthcare practitioners, offering an accessible diagnostic tool for melanoma screening in resource-limited settings.
Comparison of clustering analysis of K-means, K-medoids, and fuzzy C-means methods: case study of school accreditation in west java Hasnataeni, Yunia; Nurhambali, M Rizky; Ardhani, Rizky; Hafsah, Siti; Soleh, Agus M
Journal of Soft Computing Exploration Vol. 6 No. 2 (2025): June 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i2.575

Abstract

This research aims to analyze school accreditation data in West Java using clustering methods: K-Means, K-Medoids, and Fuzzy C-Means, to identify patterns and groups of schools based on similar characteristics. K-Means, known for its simplicity, suggests an optimal two-cluster solution based on silhouette values but employs three clusters for detailed analysis. K-Medoids, noted for its robustness against outliers, achieves the best clustering with a lowest Davies-Bouldin Index (DBI) of 0.8 and the highest Silhouette Information (SI) value of 0.46. Fuzzy C-Means, which assigns membership degrees to each data point across clusters, performs reasonably well with a DBI of 0.87 and an SI value of 0.40, while K-Means shows the highest DBI of 0.9 and the lowest SI value of 0.39. The findings highlight K-Medoids as the superior method for clustering. Regions with lower educational quality, such as Bekasi and Cianjur regions, require priority interventions, whereas areas with better quality, like Bandung and Bekasi regions, can serve as models. Data-driven approaches, inter-regional collaboration, and continuous monitoring and evaluation are recommended to optimize educational policies and enhance overall educational quality in West Java.
Sound detection of gamelan musical instruments using teachable machine Yunitasari, Yessi; Asyhari, Moch Yusuf; Kurniawati, Inung Diah; STT, Latjuba Sofyana
Journal of Soft Computing Exploration Vol. 6 No. 2 (2025): June 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i2.576

Abstract

Gamelan is an instrument of musical expression that has an aesthetic function related to social, moral, and spiritual values. Gamelan consists of a variety of musical instruments that have a unique sound. In this study, the sound detection of nine gamelan musical instruments was carried out using a teachable machine. The gamelan musical instruments detected included gong, kenong, saron, bonang, gambang, kendang, flute, siter, and rebab. The algorithm used is CNN. The CNN algorithm has a fairly good performance for the sound detection process. The test results of the built model show an "acc" value of 25 ranging from 0.99 to 1, which indicates that the model achieves an accuracy rate of 99% to 100% on the training dataset. At the same time, "test accuracy" refers to a measure of the model's effectiveness in predicting data it has not encountered during training. The "test accuracy" score varied from 0. 83, which shows that the validation data has an accuracy of 83%.
Digital image based IoT intelligent fire detection with telegram notification Kharisma, Rizqi Sukma; Ibrahim, Malik
Journal of Soft Computing Exploration Vol. 6 No. 2 (2025): June 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i2.580

Abstract

Due to inadequate handling, fire disasters often result in significant losses and even loss of life. A fire detection system is essential, especially in places prone to fire. In this study, a digital image-based IoT system was built using the YOLO (You Only Look Once) algorithm to detect and provide fire warnings quickly and accurately. This research was conducted to develop a fire detection system from existing research on IoT devices by combining it with digital image processing technology with the YOLOv8 algorithm, as well as integrating the IoT system into the Telegram instant messaging application. This study also combines a fire detection system with a fire sensor, MQ-2 temperature sensor, and MQ-2 smoke sensor. The study results show that the YOLOv8 nano model with ESP32-CAM can detect small flames from candles up to a distance of 220 cm. The ESP32 fire sensor can detect small flames up to a distance of 90 cm and large flames up to a distance of 140 cm. VPS can be sent to the Telegram application, just as the LM35 temperature sensor detects temperatures above 50ºC and the MQ-2 smoke sensor detects smoke levels above 450 ppm. All data obtained can be displayed on the VPS dashboard and the Telegram application.
Design and construction of website-based e-commerce applications for selling food products in the semarang region with payment gateway integration Kafita, Salsabila Rizki Aulia; Murti, Alif Catur; Nindyasari, Ratih
Journal of Soft Computing Exploration Vol. 6 No. 2 (2025): June 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v6i2.584

Abstract

Digital transformation has driven a shift in transactions from traditional systems to e-commerce platforms, which have become the cornerstone of the digital economy. However, existing e-commerce platforms often fail to fully meet the needs of SMEs, particularly regarding flexible withdrawal of sales proceeds and consumer education about products. This study aims to design a website-based e-commerce application with the main features of a flexible fund withdrawal system and product education. This system is developed using the Waterfall System Development Life Cycle (SDLC) model. The implementation of the application creation uses the Laravel framework integrated with the Midtrans API for secure and flexible payment management. This application is equipped with various features, such as product catalogs, shopping carts, order tracking, and reviews, with functional testing carried out through black-box testing methods to ensure the application meets user needs. The results of the study show that web-based e-commerce applications are able to support flexible transactions, expand market reach, and strengthen the local e-commerce ecosystem. From this study, it can be concluded that website design plays an important role in answering challenges, especially increasing the security and convenience of direct fund withdrawal transactions for SMEs.