Computer Networks

Face mining is characterized as the revelation of picture designs in a given gathering of pictures. It is an exertion that generally attracts upon information PC vision, picture handling, information mining, AI, database, and man-made reasoning. Facial acknowledgment breaks down and thinks about the examples from the facial pictures. Facial component extraction is a programmed acknowledgment of human faces by recognizing its highlights for example eyes, eyebrows and lips. In this paper, we are assessing the execution of PCA, GMM, GLCM and SVM to perceive seven distinctive outward appearances of two people, for example, cheerful, unbiased, and furious, nauseate, dismal, dread and astonishment. Our point is to speak to best systems which work best for facial acknowledgment. The present investigation demonstrates the plausibility of outward appearance acknowledgment for viable applications like reconnaissance and human PC communication.

The application of the Internet of Things (IoT) in agriculture captures an enormous amount of data for decision making. However, hardest-to-detect abnormal data points that are transmitted can be harmful if not detected at an earlier stage. This paper presents an application of the Superimposed-Rule Based Classification Algorithm (SRBCA) using IoT in agriculture that lowers the false positive in anomaly detection by training one-class dataset of a ground-truth collection of agricultural sensor readings and evaluating using the combination of ground-truth and synthetic balanced test set. The CRoss-Industry Standard Process for Data Mining (CRISP-DM) methodology was used as a guide in the development of the study. The SRBCA was developed to detect conditional anomalous instances. The model was tested with one (1) year daily collection of environmental sensors. This algorithm considers the behavior and indicator features for anomaly detection. Moreover, a confusion matrix is presented showing the accuracy of the result of the SRBCA compared with One-Class Support Vector Machine (OCSVM) and its types which were considered as the closest prior art of the algorithm. The experimental results show that SRBCA performed better in identifying conditional anomaly over OCSVM and its varieties.

This study is carried out to evaluate the effect of computer virus infection of files and productivity of business enterprises. Chi-square test, tables, graphs, percentage and other simple statistical tools were used in the analysis of the data collated. The findings show that virus infection has effect on productivity of business enterprise. The magnitude of the effect depends on installation or uninstallation of anti-virus software on computer system. The study recommends that business enterprise owners should make sure that their computers run antivirus software; this software must be updated regularly as new virus appears daily; files should be regularly backed up in case the computer becomes infected, that way valuable data would not be lost.

Vehicular ad-hoc networks (VANETs) technology has been emerged as a critical research area. Being ad-hoc in nature, VANET is a type of networks that is created from the concept of establishing a network of cars for a specific need or situation. Communication via routing packets over the high-speed vehicles is a challenging task. Vehicles mobility, speed can vary depending on the road specification. However, on highway, the speed can be increase up to 120-200 Km/H. Moving at high speed can affect the efficiency of data delivery. In particular V2I traffic where moving car trying to deliver data to fixed space units which are designed to collect and process data from vehicles. Different protocols have been proposed to be implemented for VANET infrastructure, including 802.11 and 802.11p. The performance of these proposed protocols has not been compared and investigated to find out the robust mechanism for handling high speed VANETs. In this paper, the performance of the most widely deployed MAC protocols for handling wireless communication which is 802.11 and the 802.11p have been compared, which is a customized version for high speed modes. Performance is investigated in term of data delivery evaluation metrics including network throughput, delay and packet delivery ration. Results show that 802.11p has efficiently enhanced the network performance where network throughput is increased, delay is decreased, and packet delivery ratio is increased as well. 1. INTRODUCTION Recently, Vehicular Ad-hoc Networks (VANET) becomes more popular and widely deployed over all the roads across the world. Most of modern cars are equipped with Wireless modules which provides vehicles to communicate with each other's and with communication control points [1]. Enhancing Inter-Vehicle communication and roadside communication are considered as the most popular wireless communication research topic. VANET allows road vehicles to notify other vehicles about traffic jams, sudden stops and other hazardous road conditions [2]. The huge number of expected benefits of VANET and a number of supporting vehicles are likely become the most realized implementation of mobile Ad hoc networks. Short range IEEE 802.11 can be used for vehicle communications using suitable radio interface technology [3]. However, a new standard for both physical and MAC layer has been developed to meet the requirement of communication between vehicles, IEEE 802.11p is an approved amendment to the IEEE