Claim Missing Document
Check
Articles

Found 37 Documents
Search

Calibration of Dissolved Oxygen Sensors in IoT Systems for Water Quality Monitoring in Aquaculture Mindara, Gema Parasti; Sholihah, Walidatush; Novianty, Inna; Fathonah, Lathifunnisa; Marcelita, Faldiena; Siskandar, Ridwan; Ariyanto, Dodik; Widodo, Bayu; Setiawan, Aep; Firdaus, Naufal Rizqullah
Spektra: Jurnal Fisika dan Aplikasinya Vol. 10 No. 3 (2025): SPEKTRA: Jurnal Fisika dan Aplikasinya, Volume 10 Issue 3, December 2025
Publisher : Program Studi Fisika Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/SPEKTRA.103.06

Abstract

Dissolved Oxygen (DO) is an important parameter for maintaining water quality in aquaculture systems. The accuracy of DO sensors significantly affects the reliability of Internet of Things (IoT)-based monitoring systems. This study aimed to calibrate the DO sensor using a two-point calibration method and evaluate the accuracy of the sensor readings compared with those of a reference device (standard DO meter). A key novelty of this study lies in its multi-media calibration, performed directly on six distinct aquaculture water types, providing field-realistic validation conditions not commonly explored in previous studies. Furthermore, the accuracy of the calibrated sensor is evaluated quantitatively using MAE, RMSE, and percentage deviation to ensure rigorous performance assessment. The system was developed using an ESP32 microcontroller, DO sensor (SEN0237), DS18B20 temperature sensor, and ADS1115 ADC module. Testing was performed on six types of aquaculture water media and compared with a standard DO meter using a comparative approach. In total, n = 6 field measurement points (one stabilized reading per water medium) were used to compute MAE, RMSE, and percentage deviation. The comparison results showed that the calibrated sensor had high accuracy, with a Mean Absolute Error (MAE) of 0.1083 mg/L and a Root Mean Square Error (RMSE) of 0.2654 mg/L. Significant deviations occurred only in one type of water medium, whereas the other five showed results consistent with the reference device, indicating stable sensor readings. These findings confirm that proper calibration can improve the accuracy and reliability of IoT systems used for water-quality monitoring. Regular calibration is required to maintain the sensor performance, particularly for long-term use in dynamic aquaculture water environments.
PERBANDINGAN AKURASI TESSERACT DAN EASYOCR SEBELUM DAN SESUDAH PRAPEMROSESAN PADA CITRA NOTA Puteri, Khinanti Angelita; Alifia, Faliana; Lailatulrahmi, Puti Aisyah; Mindara, Gema Parasti; Giri, Endang Purnama
Jurnal Informatika dan Teknik Elektro Terapan Vol. 14 No. 1 (2026)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v14i1.8603

Abstract

Pengenalan teks pada citra nota menggunakan Optical Character Recognition (OCR) masih relevan diteliti karena tingginya variasi kualitas citra. Penelitian ini mengevaluasi kinerja Tesseract dan EasyOCR dalam mengenali teks pada citra nota dengan beberapa metode prapemrosesan. Dataset berasal dari Kaggle dengan 50 sampel citra yang dipilih menggunakan stratified sampling. Pengujian dilakukan dengan menghitung Character Error Rate (CER) antara hasil OCR dan ground truth. Hasil menunjukkan nilai CER berada pada kisaran 18%–25%, dengan performa terbaik Tesseract pada mode denoise dan EasyOCR pada mode grayscale. Metode threshold memberikan penurunan akurasi paling signifikan. Kualitas citra dan jenis prapemrosesan terbukti memengaruhi kinerja OCR, sehingga pemilihan prapemrosesan yang tepat sangat penting dalam meningkatkan akurasi pengenalan teks pada citra nota.
Fire Detection Berbasis Computer Vision Menggunakan YOLOv8 Secara Real-Time Sukmosuwarno, Rizq Muhammad; Islam, Muhammad Faris Fadhil; Rahman, Raden Muhammad Raditya; Mindara, Gema Parasti; Giri, Endang Purnama
Jurnal ICT: Information Communication & Technology Vol. 25 No. 2 (2025): JICT-IKMI, December , 2025
Publisher : LPPM STMIK IKMI Cirebon

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36054/jict-ikmi.v25i2.330

Abstract

This study presents the development of a fire detection system using image processing techniques based on the YOLOv8 object detection algorithm to achieve fast, accurate, and real-time performance. A dataset of fire images with various visual characteristics was preprocessed, converted into YOLO annotation format, and used to train the model for 30 epochs. Evaluation results demonstrate that the YOLOv8 model performs effectively, achieving an mAP50 of 0.646, a precision of 0.889, and an inference speed of 282.5 ms per frame. The system is integrated with OpenCV to process webcam input and display bounding boxes and confidence scores in real time. The implementation confirms that YOLOv8 is a reliable solution for early fire detection, offering faster and more adaptive responses compared to conventional sensor-based methods. This approach can be applied to modern safety monitoring systems to enhance fire prevention efforts.
PERBANDINGAN KINERJA ALGORITMA KNN DAN SVM DALAM KLASIFIKASI KEMATANGAN BUAH JERUK MEDAN BERDASARKAN CITRA DIGITAL Putri, Fadilla Julianifa; Nurjannah, Siti Laila; Wati, Dwi Febrina; Daulay, Silvia Ariani; Sistamarien, Indira; Giri, Endang Purnama; Mindara, Gema Parasti
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 9 No 1 (2026): Jurnal SKANIKA Januari 2026
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/skanika.v9i1.3661

Abstract

As a regional flagship commodity with a promising selling value, the process of grouping the maturity level of Medan Orange is still dominated by manual visual techniques. This often triggers data inconsistency and requires a long duration of processing due to personnel subjectivity factors. This research aims to compare the performance of two machine learning algorithms, namely KNN and SVM, in classifying the maturity level of Medan Orange fruit based on digital images. The dataset used is a primary dataset collected directly from Medan Orange farmers in field conditions. The research stages include image acquisition, pre-processing, extraction of HSV-based color features and GLCM-based textures, as well as classification of maturity levels into three classes, namely raw, semi-cooked, and mature. The performance of both algorithms is evaluated using accuracy, precision, and recall metrics. The research results show that the KNN algorithm has a superior performance compared to SVM, with an accuracy rate of 96,25%, while SVM produces an accuracy of 91,25%. This result shows that KNN is effective and more suitable to be applied to the automation system of classification of the maturity of Medan Orange fruit based on digital images.
People Counting in Sample Video Footage Using CNN Integrated with YOLOv5 Aulia, Ahmad Hasan Faqih; Balti, Carissa Fathinah; Anatasya, Keisyah Zahra; Mindara, Gema Parasti; Giri, Endang Purnama
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 2 (2026): February 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i2.1933

Abstract

Accurate people counting in dynamic environments remains challenging due to variations in lighting, complex backgrounds, and occlusion. This study proposes a video-based people counting system leveraging a Convolutional Neural Network (CNN) integrated with the YOLOv5 object detection model. The system applies a structured preprocessing pipeline, including frame extraction, normalization, and noise reduction, to enhance data consistency before detection. The model was evaluated using ten real-world campus video sequences to assess detection reliability and counting accuracy. Experimental results demonstrate that the proposed method achieves high precision and recall for real-time detection across diverse scenarios. Performance degradation was observed in frames containing dense crowds or low illumination, indicating limitations under extreme conditions. These findings validate the feasibility of lightweight CNN-based detectors for surveillance and monitoring applications, while highlighting the need for larger datasets and optimized training strategies to improve robustness in more complex environments.
Testing the Teman Ternak Website Using Black Box Testing with the Equivalence Partitioning Method Dermawan, Rival Fitrah; Radiansyah, Fahri; Aslam, Anargya Rabbani; Fadillah, Muhamad Mauladi; Wicaksono, Aditya; Mindara, Gema Parasti
Current STEAM and Education Research Vol. 3 No. 3 (2025): Current STEAM and Education Research, Volume 3 Issue 3, December 2025
Publisher : MJI Publisher by PT Mitra Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58797/cser.030303

Abstract

Software testing is a crucial stage in the development cycle to ensure program functionality runs as expected and maintains good quality. This process aims to identify errors so they can be fixed before the software is released to users. One of the software objects of this research is the Teman Ternak website. Teman Ternak is a website-based digital platform that functions as telemedicine, designed to overcome distance and time barriers between farmers and veterinarians, providing a platform that allows farmers to obtain remote consultation services, including initial diagnosis and treatment for diseases affecting their livestock. Testing on this website was conducted using the Black Box Testing method by applying the Equivalence Partitions technique. The Black Box method is used to test website functionality from a user perspective without needing to know the internal code structure. Meanwhile, the Equivalence Partitions technique is a testing technique that focuses on designing test cases by grouping input data on each form on the Teman Ternak website. Input data is grouped into test classes (test cases) with expected results of valid or invalid values. The purpose of testing on the Teman Ternak website is to detect and minimize functional failures during implementation, so that errors found can be fixed more quickly and the website quality improves.
PERBANDINGAN GAUSSIAN BLUR, MEDIAN, DAN BILATERAL FILTER UNTUK REDUKSI NOISE CITRA DIGITAL Qonita, Vellisya Afifa; Ramadhani, Keisha; Febriyanti, Dwi; Hamidah, Muthiah; Khobir, Achmad Fauzal; Giri, Endang Purnama; Mindara, Gema Parasti
PROSISKO: Jurnal Pengembangan Riset dan Observasi Sistem Komputer Vol. 13 No. 1 (2026): Prosisko Vol. 13 No. 1 Maret 2026
Publisher : Pogram Studi Sistem Komputer Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/zf6dvz09

Abstract

Reduksi noise merupakan tahapan krusial dalam pengolahan citra digital. Hal ini karena reduksi noise dapat menurunkan kualitas visual dan akurasi analisis citra. Permasalahan utama dalam reduksi noise adalah memilih metode filtering paling efektif untuk jenis noise tertentu dengan tetap mempertahankan detail dan tepi objek. Penelitian ini bertujuan untuk membandingkan efektivitas Gaussian Blur, Median Filter, dan Bilateral Filter dalam mereduksi Gaussian noise dan salt and pepper noise, serta mengevaluasi kualitas visual citra hasil filter melalui penilaian subjektif. Metode pada penelitian ini adalah eksperimen kuantitatif dan kualitatif, dimana citra uji (grayscale) diolah dengan ketiga filter dan diukur menggunakan tiga metrik objektif yaitu Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE), dan Structural Similarity Index (SSIM). Kemudian penelitian dilengkapi dengan survei penilaian visual oleh responden.
Co-Authors Aditya Wicaksono Agus Buono Aisya Tyanafisya Al Fatih, Muhammad Fillah Algyon Faras Alifia, Faliana Anatasya Wenita Putri Anatasya, Keisyah Zahra Andisa, Gany Anggraeni, Aulia Ani Nuraeni Anka Luffi Ramdani Ar Rachman, Muhammad Aqil Musthafa Aslam, Anargya Rabbani Aulia, Ahmad Hasan Faqih Azhar Nadhif Annaufal Azzahra, Kanaya Sabila Balti, Carissa Fathinah BAYU WIDODO Bima Julian Mahardhika Budy Santoso Capriandika Putra Susanto Darmansah, Fadhlan Zaki Daulay, Silvia Ariani Dermawan, Rival Fitrah Destriapani, Elsa Dewanto, Muhammad Arif Bagus Dini Nurul Azizah DODIK ARIYANTO Dwi Febriyanti Endang Purnama Giri Fadillah, Muhamad Mauladi Fahlevy, Annaliah Fahrezy, Muhammad Farhan Fami, Amata Faras, Algyon Fathonah, Lathifunnisa Faturrahman, Nafis Fauzi Adi Saputra Fauzi Ikhsan Suswanto Faylasuf, Hafiz Fadli Firdaus, Naufal Rizqullah Ghaeril Juniawan Parel Hakim Gumelar, Muhammad Galuh Hakim, Ghaeril Juniawan Parel Hamidah, Muthiah Hanifah, Nurrizkyta Aulia Helena Dewi Hapsari Holik, Wildan Ibnu Aqil Mahendar Inna Novianty Irma Rasita Gloria Barus Islam, Muhammad Faris Fadhil Jasmine Aulia Mumtaz Jonser Steven Rajali Manik Juliansyah, Rizki Ka-sasi, R.I. Damai Khobir, Achmad Fauzal Kinaya Khairunnisa Komariansyah Komariansyah, Kinaya Khairunnisa Kuntari, Wien Kurniawan, Fadly Lailatulrahmi, Puti Aisyah Lasardi, Ekky Mulia Luthfi Dika Chandra Manik, Jonser Steven Rajali Marcelita, Faldiena Meliala, Rajhaga Jevannya Meliala, Rajhaga Jevanya Mia Putri Yeza Mochammad Alwan Al Ataya Muchlisinia, Newi Muhamad Ali Imron Muhammad Al Amin Muhammad Galuh Gumelar Muhammad Ilham Nurfajri Muhammad Naufal Ardhani Muhammad Naufal Sutardi Muhammad Rafi Alexander Prayoga Muhammad Rafi' Rusafni Muhammad Rafi’ Rusafni Mumtaz, Jasmine Aulia Musthafa Arrachman, Muhammad Aqil Musthafa Arrachman Muzaqi, Anggito Rangkuti Bagas Nabil Malik Al Hapid Nadhifah, Jauza Nakula Bintang Nashwandra Nashwandra, Nakula Bintang Ningrat, Rangga Wasita Nisa, Afifah Rodhiyatun Novianty, Inna Noviyanti, Inna Nugraha, Nur Iman Nur Aziezah Nur Indah Chasanah Nurbadillah, Nurbadillah Nurjannah, Siti Laila Nurjihan, Saniyyah Wafa Nursaadah, Syifa Nurul Jannah Paramitadevi, Yudith Vega Pasya, Thoriq Muhammad Pratama, Reza Puteri, Khinanti Angelita Putri, Fadilla Julianifa Qonita, Vellisya Afifa Radiansyah, Fahri Rahman, Raden Muhammad Raditya Raisa Mutia Thahir Rajhaga Jevanya Meliala Ramadhan, Herlambang Nurasyid Ramadhani, Keisha Ratih, Faranita Reza Pratama Rheynesta Hannover Riani, Lutfi Ridwan Siskandar Rio Ferddinansya Rivanka Marsha Adzani Rizki Juliansyah Salsabila, Nasywa Shafa Saputra, Fauzi Adi Setiawan, Aep Sholihah, Walidatush Silalahi, Ester Olivia Simangunsong, Gandi Abetnego Sistamarien, Indira Siti Farah Fakhirah Stefanny, Arlyn Sugiana, Lili Rahmawati Sukmosuwarno, Rizq Muhammad Thahir, Raisa Mutia Thoriq Muhammad Pasya Tyanafisya, Aisya Valenza, Ihsan Lana Wati, Dwi Febrina Widhiwipati, David Reza Widiani, Hasna Nabiilah Wiguna, Indra Maki Wina Yulianti Yeza, Mia Putri Yuaziva, Asa Zahra, Afnan Zahra, Nur Rahma Ditta