During the current outbreak of the COVID-19 pandemic, controlling and decreasing the possibilities of infections are massively required. One of the most important solutions is to use Artificial Intelligence (AI), which combines both fields of deep learning (DL) and the Internet of Things (IoT). The former one is responsible for detecting any face, which is not wearing a mask. Whereas, the latter is exploited to manage the control for the entire building or a public area such as bus, train station, or airport by connecting a Closed-Circuit Television (CCTV) camera to the room of management. The work is implemented using a Core-i5 CPU workstation attached with a Webcam. Then, MATLAB software is programmed to instruct both Arduino and NodeMCU (Micro-Controller Unit) for remote control as IoT. In terms of deep learning, a 15-layer convolutional neural network is exploited to train 1,376 image samples to generate a reference model to use for comparison. Before deep learning, preprocessing operations for both image enhancement and scaling are applied to each image sample. For the training and testing of the proposed system, the Simulated Masked Face Recognition Dataset ( SMFRD) has been exploited. This dataset is published online. Then, the proposed deep learning system has an average accuracy of up to 98.98 %, where 80 % of the dataset was used for training and 20 % of the samples are dedicated to testing the proposed intelligent system. The IoT system is implemented using Arduino and NodeMCU_TX (for transmitter) and RX (for receiver) for the signal transferring through long distances. Several experiments have been conducted and showed that the results are reasonable and thus the model can be commercially applied

No abstract

No abstract

Abstract:Simple Network Management Protocol (SNMP) is a well established protocol in network management. In order to apply this protocol in smart home environment, a proxy agent should be used. This proxy agent converts sensor readings to an SNMP compatible form. In this work LabVIEW toolkits are used to play this role. First by acquiring the sensors' readings via multiple sub agents then sending them wirelessly to a single master agent through various approaches. The master agent completes the role of the proxy agent by storing these readings in a database file using LabVIEW database toolkits. This paper demonstrates a test bed representing this system is carried out and an SNMP software is used to monitor and control the sensors remotely. The results show that the proposed smart sending approach greatly reduced the amount of traffic needed.

Undoubtedly, the human life tasks rely more and more on computers. Especially after the internet and communication technologies leaded to the E (electronic) to be includes in almost everything from governments to trading and banking system, etc. Hence, the quality of the services can be provided by such systems became a matter of interest. Since the routing protocols are the fundamental procedures controlling the network work. They became the most interest field to be researched. In this paper, we simulate two of the widest used routing protocols, RIP and OSPF performs in different scenarios and network configurations, then we analyze the performance (total data sent and received, total throughput and average end to end delay) of each scenario in different conditions. The result of simulation show that OSPF performs better than RIP especially when it comes to the reliability of connection and the convergence time to cope the network failure. QualNet simulation tool had been used to design the network; analysis of the results was examine using standard tools.