Unjuk Kerja Real-time Data Logger Berbasis Model Convolutional-Recurrent Neural Network-Connectionist Temporal Classification (CRNN-CTC) untuk Perekaman Data Display Seven Segment

Birgita Putri Grania Effendi, Budi Adiperdana, Ferry Faizal

Abstract


Umumnya alat ukur digital jenis lama atau beberapa alat ukur digital praktis menampilkan hasil pengukurannya dengan struktur seven segment display, tetapi tidak banyak yang dapat menyimpan data hasil pengukurannya secara otomatis. Keperluan pencatatan data ukur untuk pemantauan atau kebutuhan eksperimen memerlukan otomatisasi, terutama jika dilakukan dalam waktu sangat panjang karena pencatatan data manual meningkatkan probabilitas terjadinya kesalahan manusia dalam mencatat. Sementara itu, modifikasi pada alat ukur untuk menambahkan data logger  terlalu rumit sehingga dibutuhkan sistem yang dapat mencatat data hasil pengukuran tanpa perlu mengubah sistem yang ada. Penelitian ini dilakukan untuk  mengembangkan sistem pencatat data real-time berbasis pengenalan karakter optik (OCR) untuk seven segment display agar dapat mengenali barisan bilangan desimal yang tertera pada display dengan panjang karakter yang berbeda melibatkan Convolutional-Recurrent Neural Networks (CRNN) dan algoritma Connectionist Temporal Classification (CTC). Metode yang dipilih menilik dari tantangan segmentasi dari penelitian-penelitian yang sudah dilakukan ketika diterapkan dalam kasus pengenalan bilangan desimal seperti pada penelitian ini. Hasil pengujian model dan eksperimen sederhana menunjukkan model yang dibuat dapat berperan sebagai data logger dengan kemampuan generalisasi yang baik dibuktikan dengan tingkat akurasi model dalam mengenali karakter-karakter bilangan desimal yang dievaluasi dengan Character Error Rate (CER) 3,6%  serta data yang dicatat dari eksperimen sesuai dengan yang ditampilkan pada display. 

Kata kunci: CRNN, CTC, OCR pada seven segment display, pencatat data desimal otomatis

References


R. Samkria et al., “Automatic PV Grid Fault Detection System with IoT and LabVIEW as Data Logger,” Comput. Mater. Contin., vol. 69, no. 2, pp. 1709–1723, 2021, doi: 10.32604/cmc.2021.018525.

G. N. Santiago and I. Ciampitti, “Multiple channels, low-cost, and dual data storage data logger for building a soil temperature network,” HardwareX, vol. 20, no. September, p. e00582, 2024, doi: 10.1016/j.ohx.2024.e00582.

W. K. Ao, A. Pavic, B. Kurent, and F. Perez, “Novel FRF-based fast modal testing of multi-storey CLT building in operation using wirelessly synchronised data loggers,” J. Sound Vib., vol. 548, no. July 2022, 2023, doi: 10.1016/j.jsv.2023.117551.

V. N. Shenoy and O. O. Aalami, “Utilizing Smartphone-Based Machine Learning in Medical Monitor Data Collection: Seven Segment Digit Recognition,” AMIA ... Annu. Symp. proceedings. AMIA Symp., vol. 2017, pp. 1564–1570, 2017.

A. R. Syafeeza, N. A. Hamid, Y. C. Wong, M. F. Ramli, and Z. M. Noh, “Smart Data Recognition System for Seven Segment,” vol. 4, no. 2, 2020.

U. Suttapakti, T. Titijaroonroj, W. Nunsong, and D. Kakanopas, “Seven Segment Display Detection and Recognition via Deep Learning Technique,” 19th Int. Conf. Electr. Eng. Comput. Telecommun. Inf. Technol. ECTI-CON 2022, pp. 1–4, 2022, doi: 10.1109/ECTI-CON54298.2022.9795620.

L. M. Low, F. H. Mohd Salleh, Y. F. Law, and N. Z. Zakaria, “Detecting and recognizing seven segment digits using a deep learning approach,” ITM Web Conf., vol. 63, p. 01007, 2024, doi: 10.1051/itmconf/20246301007.

K. Kanagarathinam and K. Sekar, “Text detection and recognition in raw image dataset of seven segment digital energy meter display,” Energy Reports, vol. 5, pp. 842–852, Nov. 2019, doi: 10.1016/j.egyr.2019.07.004.

SachalZADI, “Seven-Segment-OCR.” Accessed: Mar. 07, 2025. [Online]. Available: https://github.com/SachaIZADI/Seven-Segment-OCR/tree/master/Datasets

Ultralytics, “YOLOv8 - Ultralytics YOLO Docs,” 2022. [Online]. Available: https://docs.ultralytics.com/models/yolov8/

J. Ravi, “Handwritten alphabet classification in Tamil language using convolution neural network,” Int. J. Cogn. Comput. Eng., vol. 5, no. March, pp. 132–139, 2024, doi: 10.1016/j.ijcce.2024.03.001.

M. M. Taye, “Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions,” Computation, vol. 11, no. 3, 2023, doi: 10.3390/computation11030052.

P. N., K. R., K. A., and V. Kakani, “A Bidirectional LSTM approach for written script auto evaluation using keywords-based pattern matching,” Nat. Lang. Process. J., vol. 5, no. September, p. 100033, 2023, doi: 10.1016/j.nlp.2023.100033.

N. Toiganbayeva et al., “KOHTD: Kazakh offline handwritten text dataset,” Signal Process. Image Commun., vol. 108, no. June, p. 116827, 2022, doi: 10.1016/j.image.2022.116827.

Z. Chen, F. Yin, X. Y. Zhang, Q. Yang, and C. L. Liu, “MuLTReNets: Multilingual text recognition networks for simultaneous script identification and handwriting recognition,” Pattern Recognit., vol. 108, 2020, doi: 10.1016/j.patcog.2020.107555.

I. A. Ibadurrohman, N. Hamidi, L. Yuliati, Winarto, and M. Mikami, “The impact of ethanol addition on the droplet combustion mechanism of saturated and unsaturated fatty acid/fatty acid methyl ester molecules,” Fuel, vol. 334, no. P1, p. 126731, 2023, doi: 10.1016/j.fuel.2022.126731.

J. Martinka, P. Rantuch, and I. Wachter, “Impact of water content on energy potential and combustion characteristics of methanol and ethanol fuels,” Energies, vol. 12, no. 18, 2019, doi: 10.3390/en12183491.

Y. Liu, W. Liu, H. Liao, W. Zhou, and C. Xu, “An experimental and kinetic modelling study on laminar premixed flame characteristics of ethanol/acetone mixtures,” Energies, vol. 14, no. 20, pp. 1–18, 2021, doi: 10.3390/en14206713.




DOI: https://doi.org/10.24198/jiif.v9i2.64116

Refbacks

  • There are currently no refbacks.


Journal Indexed By:
Visit Statistics: