Article Per Year (5 Year)
p-Index From 2020 - 2025
0.659
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization TELKA - Telekomunikasi, Elektronika, Komputasi dan Kontrol
Atmanto, Dastin Aryo
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Sistem Monitoring Konsumsi Energi Listrik Berbasis IoT Menggunakan Fuzzy Logic Mamdani Atmanto, Dastin Aryo; Nanditama, Rastra Wardana; Suteddy, Wirmanto; Adiwilaga, Anugrah
TELKA - Telekomunikasi Elektronika Komputasi dan Kontrol Vol 11, No 2 (2025): TELKA
Publisher : Jurusan Teknik Elektro UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/telka.v11n2.151-166

Abstract

Penelitian ini bertujuan mengatasi permasalahan penggunaan energi listrik yang kurang efisien, hal ini disebabkan oleh keterbatasan alat kWh Meter konvensional yang tidak memungkinkan pengguna untuk memantau secara langsung konsumsi energi listrik yang sedang digunakan. Berdasarkan permasalahan tersebut, perlu adanya pemantauan konsumsi energi listrik. Sistem yang dibangun dapat memberikan informasi detail terkait energi harian yang digunakan serta menampilkan grafik visual terkait pemakaian listrik pengguna. Sistem ini memanfaatkan ESP32 dan sensor PZEM004T-100A untuk mengukur data-data listrik yang disajikan menggunakan aplikasi berbasis website secara realtime. Metode fuzzy logic diadopsi untuk memprediksi pemakaian listrik ke dalam kategori hemat, normal, atau boros. Sementara, Real-Time Operating System (RTOS) diterapkan untuk proses monitoring dan komunikasi data yang lebih efisien. Selain itu, sistem ini dibangun dengan adanya robotic arm yang berfungsi untuk meningkatkan aksesibilitas pengguna dalam pengisian token listrik secara otomatis. Berdasarkan pengujian pada seluruh sistem berjalan dengan cukup baik, namun masih terdapat rata-rata nilai kesalahan pada pengukuran tegangan dan arus sensor PZEM004T-100A sebesar 0,27% dan 1,58%, serta nilai kesalahan pada perhitungan algoritma fuzzy sebesar 0,71%. Meskipun demikian, sistem ini berpotensi meningkatkan kesadaran pengguna terhadap konsumsi energi listrik harian, serta efektif dalam mengurangi penggunaan listrik yang tidak efisien, melalui pemanfaatan teknologi terkini dalam pemantauan dan pengelolaan energi listrik. This research aims to overcome the problem of inefficient use of electrical energy, this is caused by the limitations of conventional kWh Meter tools that do not allow users to directly monitor the consumption of electrical energy that is being used. Based on these problems, it is necessary to monitor the consumption of electrical energy. The system built can provide detailed information related to daily energy used and display visual graphs related to user electricity usage. This system utilises ESP32 and PZEM004T-100A sensors to measure electricity data which is presented using a website-based application in real time. Fuzzy logic method is adopted to predict electricity usage into saving, normal, or wasteful categories. Meanwhile, Real-Time Operating System (RTOS) is applied for a more efficient monitoring and data communication process. In addition, this system is built with a robotic arm that serves to increase user accessibility in charging electricity tokens automatically. Based on testing the entire system runs quite well, but there is still an average error value in measuring the voltage and current of the PZEM004T-100A sensor of 0.27% and 1.58%, as well as an error value in the calculation of the fuzzy algorithm of 0.58%. Nonetheless, this system has the potential to increase user awareness of daily electrical energy consumption, and is effective in reducing inefficient electricity use, through the utilisation of the latest technology in monitoring and managing electrical energy.
Offline Handwriting Writer Identification using Depth-wise Separable Convolution with Siamese Network Suteddy, Wirmanto; Agustini, Devi Aprianti Rimadhani; Atmanto, Dastin Aryo
JOIV : International Journal on Informatics Visualization Vol 8, No 1 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.1.2148

Abstract

Offline handwriting writer identification has significant implications for forensic investigations and biometric authentication. Handwriting, as a distinctive biometric trait, provides insights into individual identity. Despite advancements in handcrafted algorithms and deep learning techniques, the persistent challenges related to intra-variability and inter-writer similarity continue to drive research efforts. In this study, we build on well-separated convolution architectures like the Xception architecture, which has proven to be robust in our previous research comparing various deep learning architectures such as MobileNet, EfficientNet, ResNet50, and VGG16, where Xception demonstrated minimal training-validation disparities for writer identification. Expanding on this, we use a model based on similarity or dissimilarity approaches to identify offline writers' handwriting, known as the Siamese Network, that incorporates the Xception architecture. Similarity or dissimilarity measurements are based on the Manhattan or L1 distance between representation vectors of each input pair. We train publicly available IAM and CVL datasets; our approach achieves accuracy rates of 99.81% for IAM and 99.88% for CVL. The model was evaluated using evaluation metrics, which revealed only two error predictions in the IAM dataset, resulting in 99.75% accuracy, and five error predictions for CVL, resulting in 99.57% accuracy. These findings modestly surpass existing achievements, highlighting the potential inherent in our methodology to enhance writer identification accuracy. This study underscores the effectiveness of integrating the Siamese Network with depth-wise separable convolution, emphasizing the practical implications for supporting writer identification in real-world applications.
End-To-End Evaluation of Deep Learning Architectures for Off-Line Handwriting Writer Identification: A Comparative Study Suteddy, Wirmanto; Agustini, Devi Aprianti Rimadhani; Adiwilaga, Anugrah; Atmanto, Dastin Aryo
JOIV : International Journal on Informatics Visualization Vol 7, No 1 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.1.1293

Abstract

Identifying writers using their handwriting is particularly challenging for a machine, given that a person’s writing can serve as their distinguishing characteristic. The process of identification using handcrafted features has shown promising results, but the intra-class variability between authors still needs further development. Almost all computer vision-related tasks use Deep learning (DL) nowadays, and as a result, researchers are developing many DL architectures with their respective methods. In addition, feature extraction, usually accomplished using handcrafted algorithms, can now be automatically conducted using convolutional neural networks. With the various developments of the DL method, it is necessary to evaluate the suitable DL for the problem we are aiming at, namely the classification of writer identification. This comparative study evaluated several DL architectures such as VGG16, ResNet50, MobileNet, Xception, and EfficientNet end-to-end to examine their advantages to offline handwriting for writer identification problems with IAM and CVL databases. Each architecture compared its respective process to the training and validation metrics accuracy, demonstrating that ResNet50 DL had the highest train accuracy of 98.86%. However, Xception DL performed slightly better due to the convergence gap for validation accuracy compared to all the other architectures, which were 21.79% and 15.12% for IAM and CVL. Also, the smallest gap of convergence between training and validation accuracy for the IAM and CVL datasets were 19.13% and 16.49%, respectively. The results of these findings serve as the basis for DL architecture selection and open up overfitting problems for future work.
Co-Authors Adiwilaga, Anugrah Devi Aprianti Rimadhani Agustini Nanditama, Rastra Wardana Wirmanto Suteddy