Performance monitoring of low cost IOT sensor using deep learning | |
| Author | Sapkota, Subash |
| Call Number | AIT Thesis no.CS-23-07 |
| Subject(s) | Internet of things Deep learning (Machine learning) Fault location (Engineering) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | IoT are inexpensive and can be used to generate high-resolution spatio-temporal environmental and meteorological data. However, LCS suffer from performance deterioration and cannot pro duce the same level of accuracy as a RGS due to factors such as sensor limitations, calibration drift, and environmental conditions. The comprehensive assessment of low-cost IoT sensors ne cessitates their validation within real-world deployment settings, as confined lab testing proves insufficient due to the sensor’s susceptibility to environmental factors. A deep learning system that learns the data distribution from the RGS can be used to monitor the performance of nearby LCS. The deep anomaly detection techniques can be used to identify the performance degrada tion of the sensor. However, it becomes the responsibility of the experts to define the criteria for anomaly detection, as it needs a predetermined specification for the definition of outliers and anomalies. In this study, I propose a system for fault detection based on sensor-generated data. The different phases of the pipeline used in this system to achieve fault detection are described. The pipeline consists of anomaly scoring, an anomaly detector, and fault classification. Further more, a Line channel has been implemented as a means to disseminate the sensor’s status and other relevant information. |
| Year | 2023 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Matthew N. |
| Examination Committee(s) | Mongkol Ekpanyapong;Adisorn Lertsinsrubtavee |
| Scholarship Donor(s) | AIT Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2023 |