Raspberry Pi assisted facial expression recognition framework for smart security in law-enforcement services

Sajjad, Muhammad; Nasir, Mansoor; Ullah, Fath U Min; Muhammad, Khan; Sangaiah, Arun Kumar

doi:10.1016/j.ins.2018.07.027

Cited by 92 publications

(41 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can observe from the literature discussed above that the majority of prediction methods are based on statistical features and utilized machine learning techniques for ECP and PC. To overcome these problems and challenges, we introduce an effective deep-learning-based method, due to its high accuracy and performance in the areas of image processing [31], energy and power systems [32,33] and computer vision such as smoke detection [34,35], action recognition [36,37], violence detection [38], and video summarisation [39,40]. The key contributions of this work are as follows: 1.…”

Section: B Deep Learning Methodsmentioning

confidence: 99%

Short-Term Prediction of Residential Power Energy Consumption via CNN and Multi-Layer Bi-Directional LSTM Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Excessive power consumption (PC) and demand for power is increasing on a daily basis, due to advancements in technology, the rise in electricity-dependent machinery, and the growth of the human population. It has become necessary to predict PC in order to improve power management and cooperation between the energy used in a building and the power grid. State-of-the-art energy consumption prediction (ECP) methods are limited in terms of predicting the energy effectively, due to various challenges such as weather conditions and the dynamic behaviour of occupants. Thus, to overcome the drawbacks of these methods, we present an intelligent hybrid technique that combines a convolutional neural network (CNN) with a multi-layer bi-directional long-short term memory (M-BLSTM) method using three steps. When applied to short-term power ECP, this approach helps to provide efficient power management i.e. it can assist the supplier to produce the optimum amount of power. The first step in our proposed method integrates the pre-processing and data organisation mechanisms to refine the data and remove abnormalities. The second step employs a deep learning network, where the sequence of refined data is fed into the CNN via the M-BLSTM network to learn the sequence pattern effectively. The third step generates the ECP/PC by comparing actual and predicted data series and evaluates the prediction using error metrics. The proposed method achieves better prediction results than existing techniques, thus demonstrating its effectiveness. Furthermore, it achieved the smallest value of the Mean Square Error (MSE) and Root Mean Square Error (RMSE) for individual household dataset using 10-fold cross validation (CV) and a hold-out (CV) method. INDEX TERMS Artificial intelligence, deep learning, power consumption, CNN, bi-directional LSTM, and short-term energy consumption.

show abstract

Section: B Deep Learning Methodsmentioning

confidence: 99%

Short-Term Prediction of Residential Power Energy Consumption via CNN and Multi-Layer Bi-Directional LSTM Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, the applications are various, for instance, home automation [40], smart access systems (e.g. access systems based on face recognition) [41], robotics applications [42], among others. However, it is significant consider that these sort of devices with embedded Linux, have not been designed for executing processes in real time which represents the major drawback of SBC platforms.…”

Section: Related Workmentioning

confidence: 99%

Reliable Data Acquisition System for a Low-Cost Accelerograph Applied to Structural Health Monitoring

Muñoz

Guevara

González

et al. 2021

J. Appl. Sci. Eng. Technol. Educ.

View full text Add to dashboard Cite

This paper presents and evaluates a continuous recording system designed for a low-cost seismic station. The architecture has three main blocks. An accelerometer sensor based on MEMS technology (Microelectromechanical Systems), an SBC platform (Single Board Computer) with embedded Linux and a microcontroller device. In particular, the microcontroller represents the central component which operates as an intermediate agent to manage the communication between the accelerometer and the SBC block. This strategy allows the system for data acquisition in real time. On the other hand, the SBC platform is used for storing and processing data as well as in order to configure the remote communication with the station. This proposal is intended as a robust solution for structural health monitoring (i.e. in order to characterize the response of an infrastructure before, during and after a seismic event). The paper details the communication scheme between the system components, which has been minutely designed to ensure the samples are collected without information loss. Furthermore, for the experimental evaluation the station was located in the facilities on a relevant infrastructure, specifically a hydroelectric dam. The system operation was compared and verified with respect to a certified accelerograph station. Results prove that the continuous recording system operates successfully and allows for detecting seismic events according to requirements of structural health applications (i.e. detects events with a frequency of vibration less than 100 Hz). Specifically, through the system implemented it was possible to characterize the effect of a seismic event of 4 MD reported by the regional seismology network and with epicenter located about 30 Km of the hydroelectric dam. Particularly, the vibration frequencies detected on the infrastructure are in the range of 13 Hz and 29 Hz. Regarding the station performance, results from experiments reveals an average CPU load of 51%, consequently the processes configured on the SBC platform do not involve an overload. Finally, the average energy consumption of the station is close to 2.4 W, therefore autonomy provided by the backup system is aroud of 10 hours.

show abstract

“…Recently, convolutional neural networks (CNNs) evolved to have higher accuracy and better results for various computer vision techniques, such as behavior recognition and security [10,27,28], object tracking and activity recognition [29,30], video summarization [31], and disaster management [8]. Inspired by the performance of CNNs in the mentioned domains, we tackle the problems mentioned above by proposing 3D CNN-based violence detection in surveillance.…”

Section: Introductionmentioning

confidence: 99%

Violence Detection Using Spatiotemporal Features with 3D Convolutional Neural Network

Ullah

Muhammad

et al. 2019

Sensors

Self Cite

169

View full text Add to dashboard Cite

The worldwide utilization of surveillance cameras in smart cities has enabled researchers to analyze a gigantic volume of data to ensure automatic monitoring. An enhanced security system in smart cities, schools, hospitals, and other surveillance domains is mandatory for the detection of violent or abnormal activities to avoid any casualties which could cause social, economic, and ecological damages. Automatic detection of violence for quick actions is very significant and can efficiently assist the concerned departments. In this paper, we propose a triple-staged end-to-end deep learning violence detection framework. First, persons are detected in the surveillance video stream using a light-weight convolutional neural network (CNN) model to reduce and overcome the voluminous processing of useless frames. Second, a sequence of 16 frames with detected persons is passed to 3D CNN, where the spatiotemporal features of these sequences are extracted and fed to the Softmax classifier. Furthermore, we optimized the 3D CNN model using an open visual inference and neural networks optimization toolkit developed by Intel, which converts the trained model into intermediate representation and adjusts it for optimal execution at the end platform for the final prediction of violent activity. After detection of a violent activity, an alert is transmitted to the nearest police station or security department to take prompt preventive actions. We found that our proposed method outperforms the existing state-of-the-art methods for different benchmark datasets.

show abstract

Raspberry Pi assisted facial expression recognition framework for smart security in law-enforcement services

Cited by 92 publications

References 27 publications

Short-Term Prediction of Residential Power Energy Consumption via CNN and Multi-Layer Bi-Directional LSTM Networks

Short-Term Prediction of Residential Power Energy Consumption via CNN and Multi-Layer Bi-Directional LSTM Networks

Reliable Data Acquisition System for a Low-Cost Accelerograph Applied to Structural Health Monitoring

Violence Detection Using Spatiotemporal Features with 3D Convolutional Neural Network

Contact Info

Product

Resources

About