cover
Contact Name
Riska Rosita
Contact Email
lppm@udb.ac.id
Phone
+6285725003989
Journal Mail Official
lppm@udb.ac.id
Editorial Address
Universitas Duta Bangsa Surakarta Jl. Bhayangkara No 55 Surakarta 57154 sekretariat@udb.ac.id 0271 - 719552
Location
Kota surakarta,
Jawa tengah
INDONESIA
Proceeding of International Conference Health, Science And Technology (ICOHETECH)
ISSN : -     EISSN : 2962634X     DOI : https://doi.org/10.47701/icohetech.v3i1
- Health and Medical - Health Information Technology - Science - Engineering - Information Technology
Articles 620 Documents
Diagnosis and Mitigation of INT8 Quantization Failure in MobileNetV3 for Plant Leaf Disease Classification Sopingi; Afu Ichsan Pradana; Kevien Ollyvie Jolanda; Nauval Nabil Iman
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/qs6esj44

Abstract

Edge deployment of deep learning models for plant disease classification requires model compression to fit resource-constrained hardware, yet post-training quantization (PTQ) may introduce accuracy loss that is not always well characterized for compact architectures. This progress report presents interim results from a wider study optimizing a fine-tuned MobileNetV3-Small model for tomato leaf disease classification. After training reached 99.71% validation accuracy on a 10-class PlantVillage subset, standard INT8 static PTQ using ONNX Runtime and TensorFlow Lite produced a severe accuracy collapse (10.4-27.4%) despite systematically testing eleven quantization configurations, including per-channel/per-tensor granularity, calibration methods, operator exclusion, and export settings. Diagnostic analysis revealed a persistent class-wise failure pattern rather than random noise, and an explicit shape-mismatch error confirmed a quantizer defect in per-channel bias requantization for grouped convolutions. As a mitigation, dynamic weight-only and dynamic-range quantization schemes were adopted, restoring laboratory accuracy to 99.4% with 29.3-72.0% size reduction, although field-condition accuracy on secondary open field data dropped to 43.1-43.9%, indicating a substantial domain generalization gap that motivates the next research phase.
INCOME AND FEASIBILITY OF RICE FARMING IN BLORA REGENCY, CENTRAL JAVA Retna Dewi Lestari; Afu Ichsan Pradana; Erna Chotidjah Suhatmi; Nastiti Winahyu
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/sf0g0005

Abstract

This study aims to analyze the income and feasibility of rice farming in Blora Regency, Central Java. The research uses a quantitative method with a descriptive approach. Primary data was obtained from 38 rice farmers selected using purposive sampling, while secondary data was obtained from the Central Statistics Agency and other relevant sources. Data analysis includes revenue, production costs, revenue, and Revenue Cost Ratio (R/C Ratio). The results of the study showed that the average income of rice farming was IDR 51,341,936.84 per respondent, the average total production cost was IDR 13,569,197, and the average income was IDR 37,772,740 per respondent. Farming income is in the range of -IDR 2,975,000 to IDR 158,037,000. The R/C Ratio value is in the range of 0.78-8.22 with an average of 3.68. These results show that rice farming is on average feasible because the R/C Ratio value is greater than one, even though there are farmers with an R/C Ratio value of less than one.
EVALUATING THE IMPACT OF HYPERPARAMETER TUNING ON THE PERFORMANCE OF AN ESEMBLE RF-SVM MODEL FOR SME SALES PREDICTION Eko Purwanto; Bangun Prajadi Cipto Utomo; Hanifah Permatasari; Farahwahida Mohd
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/64b5ez58

Abstract

Accurate demand forecasting is a critical enabler of digital transformation for fashion-retail Small and Medium Enterprises (SMEs), whose sales patterns are strongly shaped by seasonality, promotions, and rapidly shifting trends. Prior hybrid Random Forest–Support Vector Machine (RF-SVM) models have reported near-perfect accuracy in predicting retail transaction value, but were trained with default hyperparameters and were not evaluated on demand-volume forecasting. This study evaluates the extent to which systematic hyperparameter tuning improves the performance of an ensemble RF-SVM model when applied to weekly demand-volume prediction for fashion-retail SMEs. Weekly sales records from retail SMEs in the Surakarta region (Indonesia) were collected, pre-processed, and split into training and test sets (80:20). Random Forest and Support Vector Regression base learners were each optimised through Grid-Search cross-validation, and their tuned predictions were combined using a validation-optimised weighted hybridisation scheme. The tuned ensemble RF-SVM model achieved a Mean Squared Error (MSE) of 0.001109, a Root Mean Squared Error (RMSE) of 0.033308, and a coefficient of determination (R²) of 0.981786 on normalised test data. Predicted-versus-actual and residual plots indicate close tracking of actual demand with errors randomly distributed around zero, showing no systematic bias. Explicit hyperparameter tuning meaningfully strengthens the robustness of ensemble RF-SVM models against SME demand fluctuations, offering a practical route to more reliable, data-driven inventory and promotion planning for retail SMEs undergoing digital transformation.
MAPPING INDUSTRIAL SUSTAINABILITY ASSESSMENT METHOD: A STUDY OF TEXTILE Febrina Agusti; Ringgo Ismoyo Buwono; Pitoyo Amrih; Ilyas Syafiq Darul Ridzuan; Khelsyana Rosa Rosemery
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/a6k1ka30

Abstract

Indonesia's textile and textile product (TPT) industry is a strategic manufacturing sector facing various challenges in maintaining competitiveness and sustainability. These issues encompass energy and raw material efficiency, waste management, demands for improved workforce welfare, technological modernization, and supply chain resilience. The complexity of these challenges indicates that sustainability assessment in the textile industry requires a multidimensional approach that considers the interrelationships among indicators. This research aims to develop a measurement model and a strategy for enhancing the sustainability of Indonesia's TPT industry using a Multi-Criteria Decision Making (MCDM) approach. The study employs the Delphi method to identify and validate sustainability indicators, the Analytical Hierarchy Process (AHP) to determine indicator weights, the Decision-Making Trial and Evaluation Laboratory (DEMATEL) to analyze cause-and-effect relationships among indicators, and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to measure and prioritize sustainability performance. The developed indicators cover five dimensions: economic, environmental, social, technological, and supply chain. The integration of these methodologies is expected to yield an assessment model capable of determining the industry's sustainability level, identifying critical indicators and key causal factors, and establishing priorities for improvement strategies within the textile industry.
IMPLEMENTATION OF WEB-BASED AND MACHINE LEARNING DECISION SUPPORT SYSTEM "BUNDA DINI" FOR MATERNAL HEALTH RISK DETECTION Pramono; Rovica Probowati; Arif Setiawan
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/jd3szx05

Abstract

Maternal Mortality Ratio (MMR) remains a strategic issue in Indonesia's national health system. Efforts to reduce MMR are often hindered by the slow early detection of high-risk pregnant women at primary healthcare facilities. To bridge this gap, this study developed "Bunda Dini", a web-based Decision Support System (DSS) integrating a predictive machine learning model. The application was built using the framework Laravel and MySQL database management system. The system architecture was designed with a multi-tenant approach, enabling secure data isolation between various clinics or hospitals, as well as structured access permissions for Midwives, Obstetricians, Clinic Admins, and Super Admins (Developers). The system's inference engine is powered by an optimized Extreme Gradient Boosting (XGBoost) algorithm, which has been proven capable of classifying pregnancy risk levels based on six vital parameters with an accuracy rate of 84.24% and a high-risk class Recall reaching 96.36%. Key features of the application include an intelligent anamnesis form, risk level visualization real-time, as well as a comprehensive reporting module supporting patient data recapitulation in both PDF and Excel formats. Test results show that the system interface is highly responsive, easy for medical staff to use, and guarantees the confidentiality of medical records across clinics. The implementation of the "Bunda Dini" web platform has high potential to become a reliable medical triage instrument, accelerating emergency obstetric care responses, and directly contributing to efforts to reduce maternal mortality.
SCIENCE FOR SUSTAINABILITY: BRIDGING RESEARCH AND INNOVATION TO ACHIEVE THE SDGS Niño Ismael Sanchez Pastor
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/qqq1rq81

Abstract

Bridging the gap between research and innovation is essential to achievingthe United Nations Sustainable Development Goals (SDGs) by 2030.This study evaluated how sustainability science serves as a structuralframework for closing two major systemic barriers: the ResearchImplementation Gap and the Innovation Valley of Death. A retrospectivereview was conducted of two previous health events. Interventions wereevaluated against the SDGs using Nilsson’s 7-Point SDG Interaction Scale.Both previous health events demonstrated that human survival depends oninterdisciplinary data sharing, multi-agency enforcement, adaptivegovernance, and direct community engagement. These elements align withcore principles of sustainability science. The responses revealed positiveSDG interactions—such as scientific data-to-policy pipelines reinforcingpublic health risk reduction (+2)—alongside negative trade-offs, in whichstrict containment blockades directly undermined local livelihoods (-2). Toinstitutionalize these, the research sector must adopt the San FranciscoDeclaration on Research Assessment (DORA) to assess research beyondjournal factors and citations. Innovation leaders must integrate the TripleBottom Line (TBL) framework (People, Planet, Profit). Together, DORAand TBL provide the operational foundation for sustainability science,accelerating the development of resilient policies and supporting long-termhuman survival
A DATA-DRIVEN EVALUATION FRAMEWORK FOR ACADEMIC PROMOTION RECOMMENDATION USING STATISTICAL VALIDATION AND REGRESSION ANALYSIS Joni Maulindar; Jawahir Che Mustapha; Singgih Purnomo
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/jxxyn485

Abstract

The academic promotion process in higher education continues to face challenges related to subjectivity, limited transparency, and inconsistencies in evaluating lecturers’ performance. This study develops and evaluates a data-driven framework for academic promotion assessment by integrating multidimensional academic performance indicators with statistical validation and multiple linear regression analysis. A quantitative approach was employed using data collected through a five-point Likert-scale questionnaire from 168 respondents. The research instrument was initially assessed for validity and reliability, followed by classical assumption tests and multiple linear regression analysis to examine the relationships between academic performance indicators and Academic Promotion (AP). The results confirmed that all measurement items were valid and that all constructs demonstrated acceptable internal consistency, with Cronbach’s Alpha coefficients exceeding 0.60. The regression model also satisfied the assumptions of normality, absence of multicollinearity, and homoscedasticity. The overall regression model was statistically significant (F = 3.840, p = 0.001), indicating that the predictors were collectively associated with Academic Promotion. At the individual level, Technological Works (Y6) was the only predictor with a statistically significant positive coefficient (? = 0.157, p = 0.007), whereas Educational Activities, Scientific Publications, Training, Community Service, Committee Involvement, and Scientific Participation were not statistically significant at the 5% level. These findings highlight the distinctive role of technology-oriented and innovation-related outputs in academic promotion while demonstrating the potential of a statistically validated, data-driven framework to support more transparent, consistent, and evidence-based academic promotion assessment in higher education institutions.
RESILIENT AND SUSTAINABLE SUPPLIER SELECTION UNDER SUPPLY DISRUPTION RISKS Ruchika Jain; Ahmad Rifa’i; Abdullah Azza Al Abas
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/mbdgdd44

Abstract

Supplier selection under disruption risk must balance cost, quality, delivery, supplier compliance, and operationalcontinuity. This study develops a BWM–TOPSIS framework using a public anonymized procurement dataset of 777purchase orders from five suppliers. Six criteria are derived: unit cost, defect rate, delivery lead time, compliance rate,cancellation rate, and fulfillment reliability. Since environmental and recovery data are unavailable,sustainability is represented through supplier compliance. BWM provides literature-informed weights, while TOPSISranks suppliers. The baseline ranking is Epsilon_Group, Alpha_Inc, Gamma_Co, Beta_Supplies, and Delta_Logistics.Sensitivity analysis identifies a disruption-risk weight threshold of approximately 0.21, beyond which Gamma_Cobecomes the top-ranked supplier. The study demonstrates a transparent and reproducible approach for risk-awaresupplier selection using transaction-level procurement data.
DEVELOPMENT OF RMEIA: A WEB-BASED ELECTRONIC MEDICAL RECORD MANAGEMENT SYSTEM FOR MATERNAL AND CHILD HEALTH SERVICES Bong Borero Lumabao; Yunita Wisda Tumarta Arif; Khoirul Mustofa; Aril Rizal Saputra
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/bz5g5x15

Abstract

Healthcare services for pregnant women and toddlers stillface challenges in managing medical records throughmanual registration books. This approach presents severallimitations, including the risk of data loss or damage,difficulties in retrieving patients’ medical histories, andinefficiencies in service delivery. In accordance withMinister of Health Regulation No. 24 of 2022 concerningElectronic Medical Records, digital medical recordmanagement is needed to support more effective andintegrated healthcare services. This study aimed to designand develop RMEIA (Rekam Medis Elektronik Ibu dan Anak),a webbased electronic medical record management systemfor maternal and child health services. A descriptivequalitative approach was employed, with systemdevelopment following the Waterfall model within theSoftware Development Life Cycle (SDLC). The researchvariables included outpatient registration procedures,midwife data, patient data, and registration information.RMEIA was developed using PHP and MySQL within theXAMPP environment, while system modeling wasperformed using Data Flow Diagrams (DFD) and Entity Relationship Diagrams (ERD). The results produced a web-based RMEIA system consisting of ten main database tables and providing functional modules for maternal and childhealth services, including antenatal care (ANC), toddlerimmunization, postpartum care, and family planningservices. The implementation of RMEIA facilitates medicalrecord management, accelerates patient data retrieval,reduces dependence on paper-based records, and supportsthe availability of more structured and secure healthinformation. RMEIA also supports the digitaltransformation of maternal and child health services in accordance with national policies on electronic medicalrecord implementation.
Scrotal Hydrocele in a Preterm Neonate With Severe Sepsis: A Case Report Adzka Fahma Rodliya; Mumpuni Intan Pertiwi; Dewi Ajeng Pratiwi; Resa Paksi Mandariska
Proceeding of the International Conference Health, Science And Technology (ICOHETECH) 2026: Proceeding of the 7th International Conference Health, Science And Technology (ICOHETECH)
Publisher : LPPM Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/8cym1e15

Abstract

Hydrocele is a common cause of scrotal enlargement inneonates; however, its assessment becomes more complexin critically ill preterm infants because scrotal swelling mayalso indicate inguinal hernia, testicular torsion, hematoma,infection, or generalized edema. This case report describesa preterm neonate with very low birth weight, severeneonatal sepsis, respiratory distress, hypoalbuminemia,and ultrasonography-confirmed right scrotal hydrocele. Amale infant was delivered by cesarean section at 31 weeksand one day of gestation because of severe maternalpreeclampsia. His birth weight was 1,435 g. The infantexperienced perinatal asphyxia, respiratory distressrequiring continuous positive airway pressure,bronchopneumonia, severe sepsis, anemia,thrombocytopenia, hypoalbuminemia, and systemicedema. Right scrotal edema was observed duringhospitalization, and ultrasonography subsequentlyconfirmed right hydrocele. The infant received intensivesupportive care, respiratory support, antimicrobial therapy,nutritional support, and albumin transfusion but diedfollowing cardiorespiratory arrest. This case highlights theneed for systematic assessment of scrotal swelling incritically ill preterm neonates and careful differentiationbetween hydrocele and urgent inguinoscrotal disorders.