Pengenalan Karakter Optis untuk Pencatatan Meter Air dengan Long Short Term Memory Recurrent Neural Network

Utomo, Victor Gayuh; Pinem, Agusta Praba Ristadi; Christoko, Bernadus Very

doi:10.29207/resti.v5i1.2807

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Potret dengan banyak informasi warna, memerlukan pengolahan tambahan setidaknya Grayscale. Proses ini, biasanya melalui penyesuaian threshold, bertujuan untuk mengubah potret menjadi format monokrom untuk meningkatkan kinerja Optical Character Recognition [13]. Grayscale mempermudah algoritma dalam membaca potret karena perbedaan hanya terletak pada tingkat keterangan dan intensitas pixel.…”

Section: Gambar 5 Hasil Resizeunclassified

Deteksi Pelat Nomor Dengan Menggunakan Optical Character Recognition Berbasis Algoritma LSTM

Wardhani,

Dwiasnati

2024

FaktorExacta

View full text Add to dashboard Cite

Illegal parking is a recurring issue in the Jakarta area, prompting a system transformation that involves adding automatic parking facilities based on building infrastructure and facilities regulations. The development of an automatic parking system can utilize license plate number detection to minimize manual entry of license plate number in the parking system. In this study, LSTM algorithm is trained and implemented on Optical Character Recognition by Tesseract Engine with the aim to create and develop an accurate license plate number detection system to streamline the workflow of institutions requiring vehicle license plate information. The LSTM algorithm demonstrated good performance in detecting license plate numbers with an accuracy rate of 86.36%. However, the LSTM algorithm performance improved significantly to 95.8% accuracy when implemented on Optical Character Recognition by Tesseract Engine. Therefore, based on the evaluation, the LSTM algorithm integrated with Optical Character Recognition is considered the preferred choice for license plate number detection due to its higher accuracy compared to using the LSTM algorithm alone.

show abstract

Section: Gambar 5 Hasil Resizeunclassified

Deteksi Pelat Nomor Dengan Menggunakan Optical Character Recognition Berbasis Algoritma LSTM

Wardhani,

Dwiasnati

2024

FaktorExacta

View full text Add to dashboard Cite

show abstract

“…Other research records water meters with a neural network [8], [9]. Unlike an IoT-based microcontroller using a neural network, reading water meters can work without an internet connection, but initially takes a technique in optical character recognition.…”

Section: Introductionmentioning

confidence: 99%

Development of mobile billing application system for PAMDES water meter data logging

et al. 2022

View full text Add to dashboard Cite

Along with the growth of Sindangsari's population, the water requirement in this village has increased. So, the drinking water company (PAMDES) in this village must be able to manage the available water to meet the necessities of public life. Now, the water company is still collecting and recording water meters manually. It is very risky to consider the water condition in the village because an officer can make a human error while recording the water meter's value. When the water meter recorder is damaged, the officer estimates the water meter's value. An application is needed to manage bills and record water meters to avoid this in previous studies using the Internet of Things (IoT) or mobile applications that must be sent online to the server in real-time. This solution is not suitable for the internet condition in Indonesia, which is not evenly distributed to remote villages. This study proposes to use a mobile application that can store data on mobile devices. When the internet connection is unavailable, it can be sent later when it is available again. In this study, data obtained that the condition of the meter recorder from 672 customers, 37 water meters recorder is damaged. In addition, water meter data is also obtained for the following month's bill and data on average water usage of 10,661m3 per month. With these data, it is found that the minimum water requirement is 10,661 m3 per month. It is hoped that the application for billing management and recording of PAMDES water meters in Sindangsari village, Cikoneng sub-district, Ciamis district can help increase PAMDES management capacity.

show abstract

Recurrent Neural Network Architectures Comparison in Time-Series Binary Classification on IoT-Based Smart Lighting Control

Putrada

Abdurohman

Perdana

et al. 2022

2022 10th International Conference on Information and Communication Technology (ICoICT)

View full text Add to dashboard Cite

Pengenalan Karakter Optis untuk Pencatatan Meter Air dengan Long Short Term Memory Recurrent Neural Network

Cited by 3 publications

References 7 publications

Deteksi Pelat Nomor Dengan Menggunakan Optical Character Recognition Berbasis Algoritma LSTM

Deteksi Pelat Nomor Dengan Menggunakan Optical Character Recognition Berbasis Algoritma LSTM

Development of mobile billing application system for PAMDES water meter data logging

Recurrent Neural Network Architectures Comparison in Time-Series Binary Classification on IoT-Based Smart Lighting Control

Contact Info

Product

Resources

About