Suspicious Activity Recognition Using Proposed Deep L4-Branched-Actionnet With Entropy Coded Ant Colony System Optimization

Abstract

Intelligent visual surveillance systems are attracting much attention from research and industry. The invention of smart surveillance cameras with greater processing power has now been the leading stakeholder, making it conceivable to design intelligent visual surveillance systems. It is possible to assure the safety of people in both homes and public places. This work aims to distinguish the suspicious activities for surveillance environments. For this, a 63 layers deep CNN model is suggested and named "L4-Branched-ActionNet". The suggested CNN structure is centered on the alteration of AlexNet with added four blanched sub-structures. The developed framework is first transformed into a pre-trained framework by conducting its training on an object detection dataset called CIFAR-100 with the SoftMax function. The dataset for suspicious activity recognition is then forwarded to this pretrained model for feature acquisition. The acquired deep features are subjected to feature subset optimization. These extracted features are first coded by applying entropy and then an ant colony system (ACS) is utilized on the entropy-based coded features for optimization. The configured features are then fed into numerous SVM and KNN based classification models. The cubic SVM has the highest efficiency scores, with a performance of 0.9924 in terms of accuracy. The proposed model is also validated on the Weizmann action dataset and attained an accuracy of 0.9796. The successful findings indicate the suggested work's soundness.

Categorizing white blood cells by utilizing deep features of proposed 4B-AdditionNet-based CNN network with ant colony optimization

“…Feature selection is the mean through which a large set of extracted features is reduced to a more efficient, smaller set by removing redundant and unproductive features [40]. The accuracy of classification is highly dependent on the feature selection process [41][42][43][44] since the selection of redundant or inefficient features may lead to lower scores and increased computational cost [27]. Gupta et al [45] improved the accuracy of WBC classification with the optimized binary bat algorithm for dimensionality reduction which resulted in an increase in accuracy compared to [46] and [47].…”

Threat Analysis and Distributed Denial of Service (DDoS) Attack Recognition in the Internet of Things (IoT)

“…The high utilization of IoT devices faces IoT security issues in the fast expansion of smart appliances because of connecting to the network. The device-linked IoT devices consist of home automation; thermostats, printers, refrigerators, etc., are operated with the help of artificial intelligence like Google Assistant and Amazon Alexa [7,8]. Hence, hijacking [9] these devices is easy by sending spam emails, conscripted into a botnet, and privacy leaks.…”

Classification of human's activities from gesture recognition in live videos using deep learning

“…Now cameras are monitoring every minor detail. [9][10][11] There are different perspectives of engagement, including technology, education and interaction. In this article, we have targeted examinee invigilation in an educational environment.…”

“…Similarly, how much time the teacher utilized in teaching and how much time the teacher wasted. Now cameras are monitoring every minor detail 9–11 …”