Claim Missing Document
Check
Articles

Found 16 Documents
Search

Field Evaluation of an IoT-VFD Smart Ventilation System for Energy-Efficient Rice Seed Storage Riskiawan, Hendra Yufit; Anwar, Saiful; Setyohadi, Dwi Putro Sarwo; Arifin, Syamsul; Widiawan, Beni; Jannah, Annisa Nurul Hidayati; Setiawan, Akas Bagus
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 2 (2026): Article Research April, 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i2.15962

Abstract

Stable storage conditions are required in Rice Seed Storage to preserve seed quality and suppress fungal contamination, yet many warehouse ventilation systems still rely on inefficient on-off operation with limited responsiveness to changing temperature and humidity conditions. This study addresses the lack of integrated IoT-VFD control with field-validated energy and microclimate performance in seed warehouses. It proposes an IoT-based Ventilation Control architecture that combines ESP32, MQTT communication, and a Variable Frequency Drive to regulate a three-phase exhaust fan in both offline and online operating modes. The novelty of this work lies in integrating variable-speed control, real-time supervision, and field-based performance validation within a single seed warehouse deployment. The prototype was implemented in a 900 m3 warehouse at Politeknik Negeri Jember and evaluated through a 7-day field trial with continuous monitoring of temperature, humidity, and motor speed. The controlled system brought warehouse conditions closer to the intended storage setpoints and produced statistically significant improvements in both temperature and humidity (p < 0.001). Control performance was stable, with high target-hit accuracy and low RMSE, while energy testing showed lower electricity consumption than conventional non-VFD operation. Over an equivalent 2-hour operating period, energy use was reduced by 30.4%. The system also maintained 99.64% MQTT uptime, and no mold incidence was observed during controlled operation. These findings indicate that the proposed IoT-VFD architecture is a practical approach for improving microclimate stability, reducing energy use, and supporting fungus-preventive seed warehouse management.
Performance Comparison of CNN Transfer Learning Models for Coffee Bean Quality Classification Fadli, Nur Muhammad; Destarianto, Prawidya; Riskiawan, Hendra Yufit; Susanto, Bekti Maryuni; Priyambada, Satrio Adi; Nur, Wawan Hendriawan; Gumilang, Mukhamad Angga
Jurnal Teknologi Informasi dan Terapan Vol 12 No 2 (2025): December
Publisher : Jurusan Teknologi Informasi Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25047/jtit.v12i2.457

Abstract

According to SNI Standard No. 01-2907-2008, accurate sorting of coffee beans is crucial for improving export value. Manual sorting is time-consuming, subjective, and error-prone, especially when visual differences are subtle between roast levels. This study proposes and evaluates an automatic, machine-learning based system to support quality assurance in coffee production. We compare three transfer-learning CNN architectures: Xception, MobileNetV2, and EfficientNet-B1 on a publicly available dataset of 1,600 coffee bean images divided into four classes (dark, medium, light, green). All models were trained with the same preprocessing and hyperparameter settings. EfficientNet-B1 achieved the highest test accuracy (100%), followed by Xception (99.5%) and MobileNetV2 (97%). We discuss trade-offs between accuracy and computational efficiency and recommend EfficientNet-B1 for high-accuracy applications and MobileNetV2 for edge/mobile deployment.
Explainable Clinical-Operational Intelligence for Hospital Length of Stay Prediction Using Integrated Multi-Source Admission Data with Time-Based Evaluation Dwi Putro Sarwo Setyohadi; Hendra Yufit Riskiawan; Aji Seto Arifianto; I Gede Wiryawan; Akas Bagus Setiawan
Journal of Vocational, Informatics and Computer Education Vol 4, No 2 (2026): June 2026
Publisher : Academic Bright Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66053/voice.v4i2.507

Abstract

Purpose - Hospital length of stay (LOS) affects bed turnover, discharge planning, staffing, and capacity. Integrated hospital data can strengthen LOS prediction and support decision-making. This study developed an explainable clinical-operational intelligence framework for LOS prediction using integrated admission data. Methods - The dataset comprised 45,000 admissions with supporting patient, diagnostic, prescription, billing, ward, bed, staff, and insurance records. It is based on a structured simulation designed to resemble the operational data of hospitals. An admission-level master table was constructed from demographic, temporal, clinical, pharmaceutical, insurance, operational, and patient history features. Length of stay (LOS) regression and high-risk LOS classification were evaluated using a temporal split of 2020-2023 for training, 2024 for validation, and 2025 for testing. Ridge, Random Forest, XGBoost, and CatBoost were compared, followed by threshold optimization, label screening, and SHAP analysis. Findings – CatBoost achieved the best LOS regression performance, with a test MAE of 1.606, an RMSE of 2.028, and an R2 of 0.614. For classification, very_high_los_q90 produced the most balanced extreme-risk formulation, with an accuracy of 0.885 and ROC-AUC of 0.802, whereas high_los_q75 yielded a recall of 0.998 and an F1-score of 0.604. SHAP indicated that prior admission history, diagnostic burden, medication-related features, and ward-level context were prominent drivers of LOS. Research implications – Integrated hospital data are useful for detecting prolonged and extreme LOS, supporting better hospital planning and resource management Originality – This study offers an explainable modeling approach using integrated admission data to support LOS prediction and hospital analytics
Penerapan Teknologi Silase Pakan Komplit Guna Memperbaiki Manajemen Pakan di CV An-Kim Indo Farm dan Faris Jaya Farm Theo Mahiseta Syahniar; Mira Andriani; Nurkholis Nurkholis; Refa Firgiyanto; Hendra Yufit Riskiawan; Maya Weka Santi
Journal of Community Development Vol. 6 No. 1 (2025): August
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v6i1.1443

Abstract

Sheep farming in Indonesia is generally still carried out conventionally to semi-intensively, and there is also minimal support for the sheep farming business being run. Livestock partners from CV An-Kim Indo Farm and Faris Jaya Farm are partners who still run sheep farming businesses by relying on the availability of green fodder in the form of field grass and rice straw as their main feed. Both of these feed ingredients have low nutritional quality. The level of sheep productivity is maintained if the feed contains a minimum of PK 10.90-12.70%, and TDN 55-60%. This factor causes the sheep of partner farmers to not be able to produce optimally. In fact, other feed sources besides field grass are widely available around partner farms and can be used as alternative feed, for example various agricultural waste. However, the low knowledge and skills of farmers in identifying and processing alternative feeds cause the nutritional needs of sheep not to be met and affect their productivity. The solution to this problem is to conduct socialization regarding increasing the nutritional value of animal feed through the manufacture of complete feed using alternative feed raw materials from agricultural waste. Complete feed silage innovation is a practical solution to overcome the availability of fresh feed for partner sheep farmers at CV An-Kim Indo Farm and Faris Jaya Farm. This silage saves labor and time, reduces dependence on field grass, its application is expected to improve feed management, save time and energy for farmers, and increase efficiency.
Peningkatan Kemampuan Petani Dalam Pemenuhan Standar Pasar Ekspor Mangga Melalui Penerapan GAP di Kelompok Tani Margi Mulyo Kecamatan Wuluhan Huda Oktafa; Dian Galuh Pratita; Hendra Yufit Riskiawan; Refa Firgiyanto
Journal of Community Development Vol. 5 No. 3 (2025): April
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/comdev.v5i3.1462

Abstract

The Margi Mulyo farmer group is one of the farmer groups in Wuluhan District, Jember Regency. The high potential for mango production in Wuluhan District is the main background for the implementation of service with the aim of increasing the capacity of human resources in cultivating mangoes to produce mangoes that can meet national and export market standards through the implementation of good agricultural practices (GAP). The main problem that occurs at the activity location is that mango cultivation is still not standardized by members of farmer groups so that the mango fruit produced does not fully meet market standards. Mangoes are only marketed in a slash system so farmers cannot get high returns on the fruit sold. So the high interest in mangoes as national fruit consumption is not accompanied by mango production according to market standards. The method used in this activity is the active participatory method, in three main activities, namely counseling, implementation, and mentoring. This activity was carried out from August to September 22024. The results of the service activity included an increase in the knowledge of members of the Margi Mulyo farmer group regarding the application of GAP, an increase in farmers' ability to apply mango flowering induction and the use of certified seeds.
Performance Evaluation of Motion Estimation and Compensation Algorithms in SNR Scalable Video Encoding Agus Purwadi Purwadi; Hendra Yufit Riskiawan; Agus Hariyanto; Nugroho Setyo Wibowo; Rani Purbaningtyas
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 11, No. 2, May 2026
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v11i2.2466

Abstract

Motion estimation is the sequential determination of the direction of motion of an object in a video. The movement of an object is denoted by the term motion vector. Between the current and reference frames, motion vectors can signify shift points. The SAD (Sum of Absolute Different) block matching technique is fundamentally dependent on the assessment of an object's motion. This study proposes a hybrid approach that integrates the Three-Step Search (TSS) and Full Search (FS) algorithms. This integration aims to design a block matching algorithm that is applied to video encoding using signal-to-noise ratio (SNR) scalability. From this design, the study aims to obtain the performance results and evaluate the motion estimation process using both the TSS and FS algorithms for performance comparison in SNR scalability video encoding, in terms of video frame quality, bit rate, and PSNR, based on the average comparison of the two algorithms. Based on the experimental results, the FS algorithm achieved a total BD-PSNR of 0.22 dB with an efficiency rate of 12.45%, whereas the TSS algorithm achieved a total BD-PSNR of 0.18 dB and an efficiency rate of 7.6%. Therefore, the FS algorithm demonstrates superior performance compared to the proposed TSS algorithm in video transmission with SNR scalability.