Enabling smart technologies in agriculture has led to the improvement of crop productivity. In India, agriculture is a primary occupation, and 70% of the population is dependent on it. Plant diseases cause significant losses in an agriculture-oriented economy. Timely monitoring of plant health and detecting plant disease is a laborious process. Automated monitoring and detection techniques hold great promise for identifying plant condition and providing useful information to facilitate effective agricultural management measures. Deep learning (DL) algorithms improve the detection accuracy in many computer vision applications of smart and precision agriculture. This paper presents a plant disease detection and classification method using YOLOv3 (You Only Look Once) model to design an Internet-of-Things (IoT) device. An approximate computing technique has been adopted that minimizes the computational complexity of DL algorithms to deploy on any embedded devices efficiently. The proposed model achieves an average of 96.92% of classification accuracy while detecting plant disease for three different classes.

The demand for a smart classroom has been compounded by Covid-19, which allows students to have a meaningful learning experience while staying home. Students who join a classroom in online mode don't have the opportunity to experience a classroom setting because of the hybrid mode of teaching (both online and offline classes). As a result, they have problems such as not being able to see the board clearly, not being able to follow the lecturer because he or she is out of frame, and thus having difficulty learning. Furthermore, this results in lower interaction between the online students and the professor. To teach effectively, the professor is unable to use the entire length of the board as it would not be visible to students joining in online mode. As students and instructors, we identified the issue and developed a plug-and-play device which is portable to address the aforesaid problem during this testing and difficult period of time of the pandemic. The paper outlines the practical implementation of a plug-and-play device that meets the aforementioned requirements. The model also considers power usage, as it can dynamically control energy-consuming resources such as lighting and air conditioning in response to the environment and the presence of students.