Convolutional neural network-based classification system design with compressed wireless sensor network images

Abstract

With the introduction of various advanced deep learning algorithms, initiatives for image classification systems have transitioned over from traditional machine learning algorithms (e.g., SVM) to Convolutional Neural Networks (CNNs) using deep learning software tools. A prerequisite in applying CNN to real world applications is a system that collects meaningful and useful data. For such purposes, Wireless Image Sensor Networks (WISNs), that are capable of monitoring natural environment phenomena using tiny and low-power cameras on resource-limited embedded devices, can be considered as an effective means of data collection. However, with limited battery resources, sending high-resolution raw images to the backend server is a burdensome task that has direct impact on network lifetime. To address this problem, we propose an energy-efficient pre- and post- processing mechanism using image resizing and color quantization that can significantly reduce the amount of data transferred while maintaining the classification accuracy in the CNN at the backend server. We show that, if well designed, an image in its highly compressed form can be well-classified with a CNN model trained in advance using adequately compressed data. Our evaluation using a real image dataset shows that an embedded device can reduce the amount of transmitted data by ∼71% while maintaining a classification accuracy of ∼98%. Under the same conditions, this process naturally reduces energy consumption by ∼71% compared to a WISN that sends the original uncompressed images.

Biomedical Image Classification in a Big Data Architecture Using Machine Learning Algorithms

“…It provides a higher level of feature abstraction, thus potentially providing better prediction performance [73,74]. Research works based on CNN significantly improved the best performance for many image databases [37,75]. So, to apply DL, the dataset of the image has to contain many images.…”

Fast Color Quantization by K-Means Clustering Combined with Image Sampling

“…The described conversion procedure contained two parts: SLIC (Simple Linear Iterative Clustering) algorithm that segments the input image into superpixels and an MCDA (Mass Constrained Deterministic Annealing) fuzzy clustering algorithm. As another application of our main operations, namely color quantization and image sampling, we can see a wireless image sensor network with reduced battery consumption in its nodes [14]. This network was used for monitoring natural environment phenomena e.g., bird nest monitoring.…”

Detecting Toxic Content Online and the Effect of Training Data on Classification Performance

“…The most popular network structures use either Convolutional Neural Networks (CNN) [4,6,10,13] or Long-Short Term Memory (LSTM) [6,10] that is a type of Recurrent Neural Networks. A conventional viewpoint is that DNN based methods require significant amount of data to train [24], as they naturally involve significantly more parameters to learn compared to classic algorithms. However, in the context of toxic content detection, there are no comparative studies on the learning curves of DNN or classic algorithms.…”