Claim Missing Document
Check
Articles

Found 23 Documents
Search

Implementation of Rule-Base and Internet Methods of Things Optimizing Water Mangement For Improving Seed Quality Gerhana, Yana Aditia; Suparman, Deden
ISTEK Vol. 13 No. 1 (2024): Juni 2024
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v13i1.930

Abstract

System hydroponics Nutrients Film Technique (NFT) is one of the increasingly popular plant cultivation techniques used because it can increase the efficiency of water and nutrient use as well as crop yields. The NFT Hydroponic System has problems that are often faced in the form of control that must be optimal for important parameters like pH, temperature water, And concentration nutrition, so that can influence plant health and growth and need a good environment controlled To avoid decline quality plant or withering plant. Study This design uses Arduino Uno as a center control system monitoring hydroponics NFTs Which in add sensors pH For read value from pH water, sensors TDS used For read density nutrition, sensors temperature DS18B20 used For read temperature water Because own waterproff and water sensor features flow to read the amount of water flow. Data is read by the sensor and Then sent to Firebase through module NodeMCU which has been connected to the Arduino Uno then from Firebase it is created output form information to the user through the application mobile. Results testing done with the use 3 media Which were different as much 60 time experienced 58 successes and 2 failures resulted in a score accuracy of 96.6% of the total testing.
Implementation of Convolutional Neural Network CNN Algorithm to Detect Coffe Fruit Maturity Gerhana, Yana Aditia; Heryanto, Rafi Rai; Syaripudin, Undang; Suparman, Deden
ISTEK Vol. 13 No. 2 (2024): Desember 2024
Publisher : Fakultas Sains dan Teknologi UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/istek.v13i2.1247

Abstract

Fruit ripeness detection is important in the agriculture and food processing industries to ensure optimal product quality. Proper fruit ripeness can affect flavour, texture and nutrition, making it a key focus in production process monitoring and control. The fruit ripeness detection process still needs to be done manually, which can be inefficient and inaccurate. This research aims to address these challenges by implementing the CNN algorithm with VGG-19 architecture to detect coffee fruit ripeness automatically. The process involves collecting datasets of fruit images with various ripeness levels, image pre-processing including cropping and resizing, training the CNN VGG-19 model with feature learning and hyperparameter optimisation and evaluating model performance using a confusion matrix. This experiment aims to evaluate the model's performance in detecting fruit ripeness and measure the speed and efficiency of the CNN-based detection system with VGG-19 architecture. The results of this research are expected to help develop a better system for identifying fruit ripeness.
Academic Data Quality Measurement in SALAM Application Using Six Sigma Method Firdaus, Imam; Alam, Cecep Nurul; Gerhana, Yana Aditia; Irfan, Mohamad; Iskandar, Ibrahim
CoreID Journal Vol. 3 No. 2 (2025): July 2025
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v3i2.136

Abstract

Data quality plays a critical role in ensuring the reliability and usefulness of information for decision making in higher education institutions. However, academic data within the SALAM application at UIN Sunan Gunung Djati Bandung has not previously undergone a systematic quality assessment, leading to uncertainty in several managerial and academic decisions. This study aims to evaluate the quality of academic data in the SALAM application using the Six Sigma method with the DMAIC (Define–Measure–Analyze–Improve–Control) framework. Five data quality dimensions completeness, consistency, conformity, uniqueness, and timeliness are employed to measure and analyze data quality performance. The measurement process begins with data definition and extraction, followed by quantitative analysis using sigma metrics. The results indicate that the overall quality of academic data is at a moderate level, with an average sigma score of approximately 3, primarily influenced by incomplete and inconsistent data. In contrast, the timeliness dimension demonstrates excellent performance, achieving a sigma metric of 6 due to the long-term availability of data over more than ten years. This study contributes by providing an empirical, data-driven evaluation of academic data quality and offers practical insights for implementing continuous monitoring and improvement strategies to enhance data reliability and support more effective decision making in higher education institutions.