Human Gait Recognition (HGR) is a biometric technique that has been utilized for security purposes for the last decade. The performance of gait recognition can be influenced by various factors such as wearing clothes, carrying a bag, and the walking surfaces. Furthermore, identification from differing views is a significant difficulty in HGR. Many techniques have been introduced in the literature for HGR using conventional and deep learning techniques. However, the traditional methods are not suitable for large datasets. Therefore, a new framework is proposed for human gait recognition using deep learning and best feature selection. The proposed framework includes data augmentation, feature extraction, feature selection, feature fusion, and classification. In the augmentation step, three flip operations were used. In the feature extraction step, two pre-trained models were employed, Inception-ResNet-V2 and NASNet Mobile. Both models were fine-tuned and trained using transfer learning on the CASIA B gait dataset. The features of the selected deep models were optimized using a modified three-step whale optimization algorithm and the best features were chosen. The selected best features were fused using the modified mean absolute deviation extended serial fusion (MDeSF) approach. Then, the final classification was performed using several classification algorithms. The experimental process was conducted on the entire CASIA B dataset and achieved an average accuracy of 89.0. Comparison with existing techniques showed an improvement in accuracy, recall rate, and computational time.
An intelligent emergency system for hazard monitoring and building evacuation is a very important application area in Internet of Things (IoT) technology. Through the use of smart sensors, such a system can provide more vital and reliable information to first-responders and also reduce the incidents of false alarms. Several smart monitoring and warning systems do already exist, though they exhibit key weaknesses such as a limited monitoring coverage and security, which have not yet been sufficiently addressed. In this paper, we propose a monitoring and emergency response method for buildings by utilizing beacons and Unmanned Aerial Vehicles (UAVs) on an IoT security platform. In order to demonstrate the practicability of our method, we also implement a proof of concept prototype, which we call the UAV-EMOR (UAV-assisted Emergency Monitoring and Response) system. Our UAV-EMOR system provides the following novel features: (1) secure communications between UAVs, smart sensors, the control server and a smartphone app for security managers; (2) enhanced coordination between smart sensors and indoor/outdoor UAVs to expand real-time monitoring coverage; and (3) beacon-aided rescue and building evacuation.
Currently, many levels of autonomous driving are being rapidly developed and are near deployment. No human intervention is required above level 4 of autonomous driving. Imperatively, a method for preventing and reproducing accidents that may occur during autonomous driving is desirable. In this study, the state change that occurs in V2X (vehicle to everything) environment is treated as first-class data to examine the cause by reproducing the accident when an accident occurs. We propose a framework that reproduces and restores state using event sourcing techniques that store first-class data. CCS Concepts • Computer systems organization ➝ Architectures ➝ Other architectures➝ Data flow architectures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.