Faulty sensor detection mechanism using multi-variate sensors in IoT

• Main Author: Al-Atrakchii, Khaldoon Ammar
• Format: Dissertation
• Language: English; English; English
• Published: 2019
• Subjects: TK7800-8360 Electronics
• Online Access: http://eprints.uthm.edu.my/537/

Internet of Thing (IoT) becoming increasingly popular over the past few years because it can be implemented in many applications such as smart cities, smart agriculture, smart health, smart home and etc. IoT devices are equipped with sensors such as temperature, humidity, pulse sensor, smoke and etc., offer many types of services for these applications. IoT devices are lightweight and have limited computational capabilities often exposed to harsh environments, which can cause failure on the IoT devices. The failure on the IoT devices is caused due to limited battery life, hardware failure or human mistakes. Sensor faults can be categorized under one type of hardware failure, such as sensor burn, reduced sensor sensitivity and malfunctioned sensors. Any faulty on the IoT devices can create a problem on the overall operation of the IoT system. Thus, it is very important to manage these IoT devices efficiency. Traditional ways in the management of IoT devices, require a maintenance officer to check each device every day. Because of this, we proposed two methods for Faulty Sensor Detection and Identification mechanism based on multi-variate sensors for Smart Parking System and smart agriculture. The first proposed method is a logical mechanism uses three different types of. The second method proposed is based on a correlation method that can exploit the multi-variable sensor which existing in IoT application. The proposed methods can provide information when one sensor becomes damaged. The accuracy of the algorithm for data correlation may be changing depending on the application that wants to detect the faulty sensor in the system and according to how many data that income to the microcontroller per minute and how many data should take to calculate the correlation coefficient. Therefore, for the smart agriculture which it's used in this project, the period is adjusted to give a good diagnose for the sensor as soon as possible.