Houman Zarrabi

Topologies and performance of intelligent algorithms: a comprehensive review

Recently, optimization makes an important role in our day-to-day life. Evolutionary and population-based optimization algorithms are widely employed in several of engineering areas. The design of an optimization algorithm is a challenging endeavor caused of physical phenomena in order to obtain appropriate local and global search operators. Generally, local operators are fast. In contrast, global operators are used to find best solution in the search space; therefore they are slower compare to the local ones. The best review-knowledge of papers show that there are many optimization algorithms such as genetic algorithm, particle swarm optimization, artificial bee colony and etc in the engineering as a powerful tools. However, there is not a comprehensive review for theirs topologies and performance; therefore, the main goal of this paper is filling of this scientific gap. Moreover, several aspects of optimization heuristic designs and analysis are discussed in this paper. As a result, detailed explanation, comparison, and discussion on AI are achieved. Furthermore, some future research fields on AI are well summarized.

Intelligent Guardrails: An IoT Application for Vehicle Traffic Congestion Reduction in Smart City

This paper discusses vehicle traffic congestion which leads to air pollution, driver frustration, and costs billions of dollars annually in fuel consumption. Finding a proper solution to vehicle congestion is a considerable challenge due to the dynamic and unpredictable nature of the network topology of vehicular environments, especially in urban areas. Recent advances in sensing, communication and computing technologies enables us to gather real-time data about traffic condition of the roads and mitigate the traffic congestion via various ways such as Vehicle Traffic Routing Systems (VTRSs), electronic toll collection system (ETCS), and intelligent traffic light signals (TLSs). Regarding this issue, an innovative technology, called Intelligent Guardrails (IGs), is presented in this paper. IGs takes advantages of Internet of Things (IoT) and vehicular networks to provide a solution for vehicle traffic congestion in large cities. IGs senses the roads traffic condition and uses this information to set the capacity of the roads dynamically.

A soft cooperative spectrum sensing in the presence of most destructive smart PUEA using energy detector: A soft cooperative spectrum sensing in the presence of most destructive smart PUEA using energy detector

Recently, the growth of Internet of Things (IoT) and its remarkable impacts on human well‐being life style are deniable. On the connectivity side, IoT is highly related to Wireless Sensor Network (WSN) concept. The key elements include the data, which is machine‐produced, specifically by sensors, and the data communication through connectivity technologies. On the security side, primary user emulation attack (PUE) is one of the well‐defined attacks in cognitive radio (CR)–based WSN. Here, we investigate a smart primary user emulation attacker that has the most destructive effect on the spectrum sensing unit of cognitive radio users. To deal with this attack, a soft cooperative spectrum sensing using an energy detector is proposed. In the proposed method, the values of sensing information of each secondary user are sent to a fusion center. Once the values are received, they will be combined with some appropriate coefficients in order to minimize spectrum sensing probability of error for a given probability of false alarm. The coefficients are the variables of a constrained optimization problem. Based on simulation results, our method has a lower error probability in spectrum sensing in comparison to hard combination schemes (eg, OR rule) and soft combination schemes (eg, CSINR method).

A Green Ant-Based method for Path Planning of Unmanned Ground Vehicles

Planning of optimal/shortest path is required for proper operation of unmanned ground vehicles (UGVs). Although most of the existing approaches provide proper path planning strategy, they cannot guarantee reduction of consumed energy by UGVs, which is provided via onboard battery with constraint power. Hence, in this paper, a new ant-based path planning approach that considers UGV energy consumption in its planning strategy is proposed. This method is called Green Ant (G-Ant) and integrates an ant-based algorithm with a power/energy consumption prediction model to reach its main goal, which is providing a collision-free shortest path with low power consumption. G-Ant is evaluated and validated via simulation tools. Its performance is compared with ant colony optimization, genetic algorithm, and particle swarm optimization approaches. Various scenarios were simulated to evaluate G-Ant performance in terms of UGV travel time, travel length, computational time by taking into account different numbers of iterations, different numbers of obstacle, and different population sizes. The obtained results show that the G-Ant outperforms the existing methods in terms of travel length and number of iteration.

HIDCC: A hybrid intrusion detection approach in cloud computing

The rapid growth of distributed computing systems that heavily communicate and interact with each other has raised the importance of confrontation against cyber intruders, attackers, and subversives. With respect to the emergence of cloud computing and its deployment all over the world, and because of its distributed and decentralized nature, a special security requirement is needed to protect this paradigm. Intrusion detection systems could differentiate usual and unusual behaviors by means of supervising, verifying, and controlling the configurations, log files, network traffic, user activities, and even the actions of different processes by which they could add new security dimensions to the cloud computing systems. The position of the intrusion detection mechanisms in cloud computing systems as well as the applied algorithms in those mechanisms are the 2 main factors in which many researches have focused on. The goal of those researches is to uncover intrusions as much as possible and to increase the rate and accuracy of detections while reducing the false warnings. Those solutions, however, mainly have high computational loads, low accuracy, and high implementation costs. In this paper, we present a comprehensive and accurate solution to detect and prevent intrusions in cloud computing systems by using a hybrid method, called HIDCC. The implementation results of the proposed method show that the intrusion coverage, intrusion detection accuracy, reliability, and availability in cloud computing systems are considerably increased, and false warnings are significantly reduced.

Could-based vehicular networks: a taxonomy, survey, and conceptual hybrid architecture

In recent times, vehicular network research has attracted the attention of both researchers and the industry partly due to its potential applications in efficient traffic management, road safety, entertainment, etc. Resources such as communication, on-board unit, storage and computing units, and battery are generally installed in the vehicles participating in intelligent transportation systems. The need to maximize the utilization of these resources has also resulted in interest in cloud based vehicular networks (CVNs), an area of active research. This paper survey the CVNs literature published between 2010 and 2016. In addition, a taxonomy based on three main CVN categories, namely vehicular cloud computing (VCC), vehicle using cloud (VuC) and hybrid cloud (HC), is presented. In the taxonomy, we focus on related systems, architectures, applications and services. Although VCC has been extensively discussed in the literature, a comprehensive survey on the two other categories is lacking. Hence, this motivates our research. Through an extensive comparison of common characteristics among cloud computing, mobile cloud computing, VCC, VuC and HC and overview of the existing architectures, we present a conceptual HC architecture. Finally, we conclude the paper with open issues and challenges.