Efficient Deep Learning for Plant Disease Classification in Resource Constrained Environment

Abstract

Deep Neural Networks (DNNs) have been widely used in today’s applications. In many applications such as video analytics, face recognition, computer vision, and classification problems like plant disease classification, etc. DNN models are constrained by efficiency constraints (e.g., latency). Many deep learning applications require low inference latency, which must fall within the parameters set by a service level objective. The prediction of the inference time of DNN models raises another problem which are the limited resources of Internet of Things devices. These devices need an effective way to run DNN models on them. One of the most widely discussed technological developments since the Internet of Things is edge machine learning (Edge ML), and with good reason. Edge Machine Learning is a fast-growing well-known technological improvement since the existence of the Internet of Things (IoT). Edge ML allows smart devices to use machine learning and deep learning techniques to analyze data using servers locally or at the device level, which reduces the need for cloud networks. This is caused by a variety of issues, including poor internet access, expensive cloud resources, low-resource edge devices, and a high failure rate of Internet of Things (IoT) devices, either because of battery or connection issues. Finding a way to effectively run the DNN models locally on IoT devices is crucial.