Garuda - Garba Rujukan Digital

SISTEM MONITORING GAS AMONIA PADA KANDANG AYAM BERBASIS EMBEDED SYSTEM Rowa, Heruzulkifli; Syadam, Syadam
Jurnal Teknologi dan Sistem Tertanam Vol 5, No 1 (2024): Vol 5 No 01, Februari 2024
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jtst.v5i1.4026

Potensi produksi ayam Indonesia bagus, namun emisi ammonia di kandang berdampak pada kesejahteraan ayam dan manusia. Penelitian ini mengusulkan inovasi dengan sensor MQ-4 untuk deteksi ammonia yang akurat. Tujuan: kembangkan sistem pemantauan gas amonia di kandang ayam dengan ESP32. Tahapan melibatkan identifikasi masalah, perancangan, dan pengujian. Alat yang digunakan: ESP32, sensor MQ-4, LCD, dan motor servo. Pemaparan membahas keamanan di kandang, bahaya gas amonia, dan kebutuhan monitoring. Proses melibatkan fungsi sensor MQ-4, LCD, dan motor servo. Program C mengoperasikan mikrokontroler, source code krusial. Prototipe melibatkan komponen utama: sensor MQ-4, ESP32, LCD, dan Motor Servo. Rangkaian prototipe divisualisasikan melalui Fritzing, kode program mengatur respons deteksi gas amonia. Implementasi bertujuan memberikan peringatan dan merespons kondisi kandang agar aman. Hasil menunjukkan prototipe detektor ammonia dengan sensor MQ-4 berhasil, layak direalisasikan untuk meningkatkan kesejahteraan ayam di peternakan.

Perancangan SPK Dalam Penentuan Kelayakan Perpanjangan Kontrak Kerja Karyawan PT.WBL Devisi Operasional Menggunakan Metode Profile Matching B, Muslimin; Rowa, Heruzulkifli
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 3 No 2 (2020): December
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Private companies currently tend to implement contract systems in all divisions and subdivisions. PT.Wulandari Bangun Laksana(WBL)/ Balikpapan Super Block(BSB) operational scope of the implementation of the contract recruitment system up to several times the contract extension so that the employee is eligible to be appointed as permanent employees. During the extension of the work contract, the operational supervisory supervisor carries out an analysis process in determining the eligibility of employees to be accepted as permanent employees. In order to produce the expected assessment, a mechanism and modeling process is needed that can be processed by a system and evaluation and analysis process carried out by the operational supervisor. This study aims to build a decision support system in determining the feasibility of extending the PT.WBL/Balikpapan Super Block(BSB) employee contract based on good and effective performance objectively using the profile matching method. Decision support system is a technique for using the system in managing the evaluation process by the decision maker (supervisor). The implementation of the profile matching method is the application of a method that can handle the appraisal process based on evaluation of criteria and the value of preferences towards employee alternatives. The data processed is employee data in the scope of the operational division Balikapan Super Block(BSB). The results of the evaluation carried out produce an alternative weight of employees, which can be used as consideration in making decisions on the feasibility of extending the work contract or being appointed as permanent employees. Based on the evaluation process of the criteria and alternatives carried out, it is expected to produce decision values and modeling processes with high accuracy values.

Sistem Pendukung Keputusan Kenaikan Jabatan Menggunakan Metode Profile Matching Sugiartawan, Putu; Rowa, Heruzulkifli; Hidayat, Nurul
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 1 No 2 (2018): December
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Decision Support System is a system that can assist managers in making decisions that are based on the criteria set by the company. Decision Support System helps in the assessment process so it does not happen to be subjective judgment in decision making. Ratings are based on the criteria that have been determined are expected to determine the employee is entitled to a promotion. Many methods can be used in making a decision support system. One method that can be used in making a decision support system that the method Profile Matching. Profile Matching is the process of comparing the profiles of employees with occupational profiles so that the known value of the gap. The smaller the value gap is generated, then the weight value will be even greater gap so that employees the opportunity to get a promotion will be even greater. The results of the calculation with profile matching method in the form of value which ranked based on the largest value. The results of this ranking value will be used as a reference in helping managers to make decisions. Software used in the manufacture of these decision support systems applications with Microsoft Visual Basic 6.0 with MySQL databases.

SVM-Based Approach for Predicting Future Ethereum Prices Using Historical Data Rowa, Heruzulkifli
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 2 (2023): December
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.260

Cryptocurrency markets are volatile and complex, presenting challenges for traditional analysis. This study utilizes a Support Vector Machine (SVM) approach to predict Ethereum’s hourly price movements using historical data, including open, high, low, close prices, and trading volume. Analyzing 34,497 hourly records, the SVM model identifies three market regimes: stable conditions, directional trends, and high-volatility events.Stable conditions dominate 72.7% of the data, marked by consistent price movements and moderate trading volumes, indicating consolidation phases. Directional trends, comprising 15.7%, reflect gradual bullish or bearish price shifts influenced by market sentiment or external factors. High-volatility events, representing 11.5%, are characterized by sharp price spikes or crashes, accompanied by increased trading activity.The Silhouette Score of 0.45 highlights the difficulty of segmenting financial data due to overlapping market states. Despite this, the SVM model effectively captures nonlinear patterns, providing valuable insights into Ethereum's price behavior. This research demonstrates the potential of machine learning in cryptocurrency analysis, enabling better market understanding, improved trading strategies, and enhanced risk management. Future work could integrate advanced features and methods to further boost prediction accuracy and model performance.

KNN-Based Prediction Model for Assessing Hypertension Risk from Lifestyle Features B, Muslimin; Rowa, Heruzulkifli
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 1 (2023): September
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.265

Hypertension is one of the most common chronic conditions associated with serious cardiovascular complications, and its prevalence continues to rise due to the influence of lifestyle related factors, motivating the use of data driven approaches for early risk identification. Although various machine learning models have been applied in health analytics, many still face challenges in processing heterogeneous lifestyle attributes, which limits their ability to accurately detect individuals at risk. This study addresses that gap by implementing the K Nearest Neighbors algorithm to predict hypertension using a dataset of 1,985 records containing variables such as age, salt intake, stress score, sleep duration, body mass index, family history, medication use, physical activity, and smoking status. The motivation for selecting KNN lies in its simplicity, adaptability, and strong performance in classification tasks involving structured health data. The contribution of this research includes the development of a lifestyle based hypertension prediction model supported by a preprocessing pipeline and optimized hyperparameters, enabling effective handling of mixed numerical and categorical features. The model is evaluated using accuracy, precision, recall, f1 score, and confusion matrix visualization, achieving an accuracy of 85 percent with balanced performance across both classes, showing that KNN offers reliable generalization for this dataset. Future work involves comparing KNN with ensemble or deep learning models, exploring feature selection techniques, and expanding dataset diversity to improve model robustness and applicability for real world digital health solutions.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search