cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Reza Muamar Zaki
Contact Email
info@polteksci.ac.id
Phone
+6287743788687
Journal Mail Official
bustechnopolteksci@gmail.com
Editorial Address
Desa Panambangan Kecamatan Sedong Kabupaten Cirebon Jawa Barat, Indonesia
Location
Kab. cirebon,
Jawa barat
INDONESIA
Journal of Business, Social and Technology
Published by Politeknik Siber Cerdika Internasional
ISSN : 28072928     EISSN : 28076362     DOI : 10.59261
Core Subject : Economy, Social, Engineering,
Economics, Econometrics & Finance Industrial & Manufacturing Engineering Social Sciences
This journal publishes research articles covering all aspects of information technology, information systems, agricultural technology, computer social and political sciences, and economics that belong to the business, social, and technological context.
Arjuna Subject : Bisnis, Menejemen, dan Akutansi (semua kategori) - Bisnis, Menejemen, dan Akutansi (Lain-Lain)
Articles 286 Documents
 25   26   27   28   29 
Comparative Analysis of YOLOv8 and MobileNetV2 for Digital Image-Based Bird's Eye Chili Leaf Disease Classification I Gede Tiar Eka Saputra; I Made Gede Sunarya
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.723

Abstract

Background: Bird’s eye chili is an important horticultural commodity in Indonesia but is highly vulnerable to leaf diseases such as mosaic virus, leaf spot, and chlorosis. Visual disease identification is often inaccurate and can delay treatment, while previous deep learning studies have mainly used laboratory-acquired datasets with limited applicability to field conditions. Objective: This study compares the performance of YOLOv8 classification (YOLOv8-cls) and MobileNetV2 in classifying bird’s eye chili leaf diseases using digital images acquired under field conditions. Methods: A dataset of 800 leaf images representing four classes (healthy, mosaic virus, leaf spot, and chlorosis) was collected under natural field conditions. The images were preprocessed and used to train both models through transfer learning using ImageNet-pretrained weights. Performance was evaluated using stratified 5-fold cross-validation and measured using accuracy, precision, recall, F1-score, and the Matthews correlation coefficient (MCC). Results: Both models achieved average accuracies above 98%. YOLOv8-cls achieved the best overall performance, with 98.38% accuracy, 98.55% precision, 98.35% recall, and 98.41% F1-score, while requiring only 2.84 MB of storage, making it suitable for deployment on edge devices. MobileNetV2 achieved 98.25% accuracy, 98.36% precision, 98.16% recall, and 98.24% F1-score, while reducing training time by approximately 40%. Conclusion: YOLOv8-cls is the more suitable architecture for mobile and edge-based plant disease detection because of its superior classification performance and compact model size, whereas MobileNetV2 is advantageous when rapid model retraining is required. These findings provide a practical basis for developing accessible digital agriculture applications for early disease detection.
Multi-Router Network Traffic Monitoring System Based on Python Flask Muhamad Eko Wahyudi; Imam Suharjo
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/bustechno.v7i3.726

Abstract

Background: Network traffic monitoring in multi-router environments is often constrained by reliance on a single protocol and decentralized access management. Objective: This study develops a web-based monitoring system using the Python Flask framework that is capable of simultaneously monitoring eight MikroTik routers and incorporates SSH failover and Role-Based Access Control (RBAC) features. Methods: The implemented solution includes an automatic failover mechanism between the MikroTik API and SSH, the implementation of Role-Based Access Control (RBAC), and flexible historical report extraction functionality. Testing was conducted on eight MikroTik routers using failover time, data loss, and role-based access validation as the primary evaluation parameters. The failover scenario involved deliberately disabling the primary API service to evaluate the system’s ability to transition to SSH-based access. Results: The evaluation results demonstrate that the system maintains the availability of monitoring data during primary access failure, with a maximum protocol transition recovery time of 2.2 seconds and no observed data loss. Testing also confirms that RBAC effectively secures system configurations by differentiating the access privileges of administrators and regular users. The failover test was conducted in two trials, yielding consistent recovery times of 2.073 and 2.077 seconds, respectively, and all seven role-based access test cases were successfully validated. Conclusion: The scientific contribution of this study lies in integrating centralized multi-router monitoring, API–SSH failover, RBAC, and historical reporting into a single Flask-based platform. The proposed system provides an empirically validated reference model for developing reliable and secure web-based network monitoring systems.
The Influence of the Physical Work Environment and Work Discipline on Employee Performance with Motivation as a Mediating Variable Yulia Puspita Dewi; Nurul Hermina
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.730

Abstract

Background: Sustained employee performance is especially important in security services, where work is dispersed across locations and depends on reliable discipline and operational readiness. Earlier findings on whether the physical work environment and work discipline directly improve performance remain mixed, suggesting that work motivation may be the process through which these conditions are converted into stronger work outcomes. Objective: This study evaluates the direct effects of the physical work environment and work discipline on employee performance at PT Bandung Perkasa Madani and examines whether work motivation carries those effects. Methods: A quantitative descriptive-verificative design was applied to all 100 permanent employees using a saturated sample. Questionnaire data were processed with Structural Equation Modeling based on Partial Least Squares (PLS-SEM) in SmartPLS 4. Results: Neither the physical work environment nor work discipline showed a significant direct relationship with employee performance. Both, however, were significant positive predictors of work motivation, and motivation significantly predicted performance. The indirect paths were also significant, indicating that work motivation fully mediates the effects of the physical work environment and work discipline on employee performance. Conclusion: The findings position work motivation as the principal mechanism linking workplace conditions and disciplined behavior to performance. Managerial efforts should therefore combine improvements in the physical work setting and consistent discipline with incentives, recognition, and other practices that strengthen employees' motivation.
Service Innovation and New Product Performance in Indonesian Tutoring SMEs Meliyana Rizki Prabaningrum; Agus Suroso; Weni Novandari
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.733

Abstract

Background: Tutoring SMEs increasingly need to renew their service delivery as digitalisation and changing parent and student preferences reshape competition. Objective: This study examines the effect of service innovation on new product performance and tests whether market turbulence moderates that relationship among tutoring SMEs in Banyumas, Purbalingga, and Banjarnegara. Methods: A quantitative, purposive-sampling design was analysed in SPSS Version 30 using item validity and reliability tests and an ordinary least-squares interaction model. Results: Service innovation positively predicted new product performance (B = 0.383, t = 2.547, p = .017), while market turbulence had a direct positive association (B = 0.451, t = 3.933, p < .001). The interaction was not significant (B = 0.014, t = 0.344, p = .734). Conclusion: Service innovation is associated with stronger new product performance, whereas market turbulence operates as a direct contextual correlate rather than a moderator in this sample.
Job Demands, Resources, and Turnover Intention: Job Satisfaction Mediation among Outsourced Ground Handling Employees Putu Dea Saraswati Wirawan; Yoseva Maria Pujirahayu Sumaji; Bisma Jatmika Tisnasasmita
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.735

Abstract

Background: Turnover intention remains a persistent problem in labour-intensive service industries, particularly among outsourced workers who face job insecurity, limited career mobility, and heavy operational demands. Evidence on how job resources and job demands translate into withdrawal intentions remains inconsistent, and job satisfaction has rarely been tested as a transmission mechanism within a single Job Demands–Resources model in aviation ground handling. Objective: This study examines the effects of job motivation, job stress, and quality of work life on turnover intention, with job satisfaction as a mediator, among outsourced employees of PT Gapura Angkasa at I Gusti Ngurah Rai International Airport. Methods: An explanatory quantitative design was applied to 192 respondents drawn by proportionate stratified random sampling from a population of 372 outsourced employees. Data were analysed with Partial Least Squares–Structural Equation Modelling in SmartPLS 4 using a disjoint two-stage hierarchical component model. Results: Job motivation and quality of work life significantly reduced turnover intention, whereas job stress showed no significant direct effect. Job satisfaction mediated the motivation and stress pathways but not the quality of work life pathway. Conclusion: The findings extend Job Demands–Resources Theory by showing that job satisfaction is the principal transmission mechanism of the health impairment process, while job resources also operate through a direct motivational route. Management should prioritise structured recognition, workload redistribution, and contract transparency to retain outsourced ground handling personnel.
Flood Tidal Risk Modeling on the Coast of West Sulawesi Using Geographic Information Systems to Support Climate Change Adaptation Planning Haryanto Asri; Hardianti Nur
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.736

Abstract

Background: Coastal flooding or tidal inundation (banjir rob) is one of the visible impacts of climate change that increasingly affects coastal regions in Indonesia, including West Sulawesi Province. Sea-level rise, land-use changes, and mangrove degradation have intensified the vulnerability of coastal areas to tidal flooding. Objective: This study aims to model the risk of tidal flooding along the coast of West Sulawesi using Geographic Information Systems (GIS) and to formulate climate change adaptation strategies through spatial and SWOT analyses. Methods: The research utilized spatial datasets, including elevation, slope, distance from the coastline and rivers, land use, and mangrove density. The analysis was conducted using a scoring, weighting, and overlay approach to generate a tidal flood vulnerability map, which was validated using observed flood event data from 2021–2025. Results: The results indicate that low-lying coastal zones below 5 meters above sea level with sparse mangrove cover (particularly in Polewali Mandar, Majene, and Mamuju Regencies) are highly vulnerable to tidal flooding. Spatial projections suggest a significant increase in inundation areas by 2075 in line with projected sea-level rise. Based on the SWOT analysis, the recommended adaptation strategy is an offensive (S–O) approach, emphasizing the utilization of coastal ecosystem potential and conservation policies to promote mangrove-based ecotourism, strengthen community adaptive capacity, and enhance collaboration among government, academia, and local communities. Conclusion: The findings are expected to provide a scientific foundation for climate change mitigation and adaptation planning in the coastal regions of West Sulawesi toward sustainable coastal development.
Photo Aesthetic Assessment via Spatial and Frequency Domain Fusion Using a Vision Transformer Approach Reza Rachmadan; Shintami Chusnul Hidayati
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.737

Abstract

Background: The rapid growth of digital media has increased the demand for automated image aesthetic assessment (IAA) in social media, creative industries, and e-commerce platforms. Although Vision Transformer (ViT)-based models have demonstrated promising performance, most existing approaches rely primarily on spatial representations while overlooking frequency-domain information, which captures complementary characteristics such as sharpness, texture, noise patterns, and bokeh effects. Objective: This study proposes a Dual-Branch Late Fusion FFT-ViT architecture with concatenation-based fusion as an approach for integrating dual-domain representations to improve photo aesthetic assessment (PAA). Methods: The proposed architecture consists of two parallel branches. The RGB branch employs a Vision Transformer (ViT-Small) to extract spatial and compositional features, while the FFT branch utilizes ViT-Tiny to capture frequency-domain characteristics associated with texture, sharpness, and image details. The extracted features from both branches are fused using a concatenation strategy before being passed to the regression layer. Results: The proposed Dual-Branch FFT-ViT with concatenation fusion achieved the best performance, obtaining a PLCC of 0.7336, SRCC of 0.7347, MSE of 0.0193, MAE of 0.1117, and RMSE of 0.1388. Compared with the RGB-only ViT baseline, the proposed model improved the PLCC score by 0.0124, demonstrating the effectiveness of integrating spatial and frequency-domain features for aesthetic score prediction. Conclusion: This study demonstrates that integrating spatial and frequency-domain representations through a dual-branch Vision Transformer architecture enhances photo aesthetic assessment performance.
Job Hopping Dynamics Among Generation Z: The Influence of Emotional Exhaustion, Organizational Commitment, and Perceived Alternative Employment Tio Ramadha Putra; Riani Rachmawati
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.738

Abstract

Background: Job hopping among Generation Z has become an increasingly important issue in human resource management, particularly amid the dynamic transformation of the labor market in Indonesia. Objective: This study aims to examine the effects of emotional exhaustion and perceived alternative employment on job hopping behavior among Generation Z, with organizational commitment serving as a mediating variable. Methods: The study is grounded in Conservation of Resources (COR) Theory and Social Exchange Theory (SET). A quantitative approach was employed using Partial Least Squares Structural Equation Modeling (PLS-SEM) through SmartPLS. Data were collected from 262 Generation Z employees in the Greater Jakarta area who had changed jobs at least two to three times. Results: The results indicate that emotional exhaustion and perceived alternative employment have significant positive effects on job hopping behavior, while organizational commitment has a significant negative effect on job hopping. Furthermore, perceived alternative employment positively influences organizational commitment, whereas emotional exhaustion does not significantly affect organizational commitment. Mediation analysis reveals that organizational commitment mediates the effect of perceived alternative employment on job hopping but does not mediate the relationship between emotional exhaustion and job hopping. Conclusion: These findings contribute to the growing literature on Generation Z job hopping behavior and provide practical implications for organizations in designing more effective employee retention strategies.
The Effect of Capital Intensity, Audit Committee, and Firm Size on Tax Management in Property and Real Estate Sector Companies Griselda Avelyn Maylita; Theresia Hesti Bwarleling
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.740

Abstract

Background: State tax receipts finance the greater part of Indonesia’s national development agenda, although firms tend to regard tax as an expense that should be minimised wherever possible. Given that the property and real estate industry combines substantial investment in fixed assets with intricate transaction structures, its tax management practices warrant closer scholarly attention. Objective: This research investigates how capital intensity, the audit committee, and firm size influence tax management practices among property and real estate firms listed on the Indonesia Stock Exchange (IDX) over the 2021–2024 period. Methods: A quantitative approach was employed, relying on secondary data obtained from audited annual reports. A purposive sampling procedure yielded a final sample of 20 firms, producing 80 firm-year observations. The dataset was analysed with IBM SPSS Statistics 29 through multiple linear regression. Results: Tax management is represented by the Effective Tax Rate (ETR), where a higher figure denotes a heavier realised tax burden and, correspondingly, a less aggressive approach to tax management. Capital intensity exerts a positive influence on ETR, suggesting that firms with substantial fixed-asset holdings do not translate depreciation into a lighter tax burden. The audit committee likewise exerts a positive influence, indicating that more robust internal oversight pushes firms toward a more compliant tax stance. Firm size, however, shows no significant influence. Conclusion: Tax management outcomes appear to be driven more by asset structure and governance quality than by firm scale. These results contribute to the body of Indonesian taxation literature.
Hybrid Machine Learning for Classifying Ringworm, Chickenpox, and Shingles from Image Embeddings Billy Hiskia Sigalingging; Imam Yuadi
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.741

Abstract

Background: Skin diseases caused by fungal and viral infections, such as ringworm, chickenpox, and shingles, often exhibit similar visual patterns in their early stages, making manual classification difficult and potentially leading to misdiagnosis. Objective: This study proposes an image-based skin disease classification approach that combines visual feature extraction with machine learning algorithms.Methods: Feature extraction is performed using pretrained models (Inception-v3, VGG-16, and VGG-19) to generate image embeddings. The extracted features are classified using logistic regression, support vector machine (SVM), and neural network models via the Orange Data Mining platform.Results: Performance evaluation using AUC, classification accuracy (CA), F1 score, precision, recall, and Matthews correlation coefficient (MCC) shows that the combination of Inception-v3 and SVM achieves the best performance. Pretrained feature extraction effectively improves the accuracy of machine learning-based classification. Conclusion: Combining pretrained feature extraction with machine learning provides an efficient and accurate approach to skin disease classification, with strong potential for development into an early-stage clinical decision-support system.

Page 27 of 29 | Total Record : 286

 25   26   27   28   29 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 4 (2026): Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology Vol. 7 No. 2 (2026): Journal of Business, Social and Technology Vol. 7 No. 1 (2026): Journal of Business, Social and Technology Vol. 6 No. 2 (2025): Journal of Business, Social and Technology Vol. 6 No. 1 (2025): Journal of Business, Social and Technology Vol. 5 No. 2 (2024): Journal of Business, Social and Technology Vol. 5 No. 1 (2024): Journal of Business, Social and Technology Vol. 4 No. 2 (2023): Journal of Business, Social and Technology Vol. 4 No. 2 (2023): Article In Press: Journal of Business, Social and Technology Vol. 4 No. 1 (2023): Journal of Business, Social and Technology Vol. 4 No. 1 (2023): Journal of Business, Social and Technology (Bustechno) Vol. 3 No. 2 (2022): Journal of Business, Social and Technology Vol. 3 No. 1 (2022): Journal of Business, Social and Technology Vol. 2 No. 2 (2021): Journal of Business, Social and Technology Vol. 2 No. 1 (2021): Journal of Business, Social and Technology Vol. 1 No. 2 (2020): Journal of Business, Social and Technology Vol. 1 No. 1 (2020): Journal of Business, Social and Technology More Issue