Artificial intelligence based optical character recognition system and interference suppression in industrial internet of things network | |
| Author | Natthanan Promsuk |
| Call Number | AIT Diss no.TC-20-03 |
| Subject(s) | Artificial intelligence Image processing--Digital techniques Internet of things--Industrial applications |
| Note | A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Engineering in Telecommunications, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Dissertation ; no. TC-20-03 |
| Abstract | The instruments’ displays of the digital meter and the analog meter with needle can show, for instance, temperature, voltage, weight, pressure, or humidity, just to name a few. Most of meters are implemented by the seven-segment displays (SSDs) for digital meters and a needle for analog meters. The human eye error can occur when humans have to collect the data by themselves. Moreover, the collected data from humans cannot use immediately in real-time. Therefore, our low-cost data acquisition system (DAS) is proposed based on the digital image processing (DIP) and a multi-layer perceptron (MLP) for analog and digital meters to reduce the human eye error because the data can be automatically collected. In the low-cost DAS system, it uses the Internet to serve real-time service as the industrial Internet of things (IIoT). However, the interference problem can be easily caused by a huge number of devices communicating with each other through the Internet and using the same or adjacent channels. The effect of the interference signals can reduce the performance of our proposed system. Moreover, the effects of log-normal shadowing fading, path loss, additive white Gaussian noise (AWGN), and multipath fading are considered in a factory environment. However, we proposed an interference suppression technique (IST) based on a long short term memory (LSTM) called LSTM-IR. The performance of LSTM-IR is compared to the MLP based IST, the traditional minimum mean square error (MMSE) approach, and non-IST. The empirical evaluation is done when we calculated BER since the work is done by Monte Carlo simulations. This communication performance is investigated in terms of the cumulative distribution functions (CDFs) of bit error rate (BER). |
| Year | 2020 |
| Corresponding Series Added Entry | Asian Institute of Technology. Dissertation ; no. TC-20-03 |
| Type | Dissertation |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Telecommunications (TC) |
| Chairperson(s) | Attaphongse Taparugssanagorn; |
| Examination Committee(s) | Manukid Parnichkun;Poompat Saengudomlert; |
| Scholarship Donor(s) | AIT Fellowship; |
| Degree | Thesis (Ph.D.) - Asian Institute of Technology, 2020 |