Journal of Computer and Knowledge Engineering
Volume:2 Issue: 1, Winter-Spring 2019

A vision-based intelligent traffic control system is a robust framework that controls the traffic flow in real-time by estimating the traffic density near traffic lights. In this paper, a traffic light control system based on fuzzy Q-learning is proposed according to the vehicle density and the pedestrian number estimated from the visual information. The aim of proposed approach is to minimize the pedestrian and the car waiting time and maximize throughput for an isolated 4-way traffic intersection. Also, the pedestrian traffic light is controlled based on the fuzzy logic. The states and actions of the Q-learning variables are set by a fuzzy algorithm which can be learned through environmental interactions. The system can detect the number of pedestrians and vehicles using visual information from cameras and machine vision algorithms. The fuzzy control system can adjust the sequence of green phases to decrease the total waiting time and the mean of the queue length. The proposed algorithm was simulated for one hour for each of 14 different traffic conditions and was assessed and compared with the preset cycle time and vehicle actuated approaches. The results showed the proposed algorithm could decrease the total waiting time and the mean of the queue length effectively.

In this article, one of the most important methods of steganography on VoIP called echo hiding is improved. This method has advantages in maintaining the statistical and perceptual characteristics of audio signals as well as security against the sensitivity of human audio system (HAS). However, it has lots of errors in detecting coded and hidden messages, which is detectable using existing steganalysis methods. The percentage of extracting messages in these improved methods of echo hiding is high, but they lower the security of the method. In this article, a method is presented to improve the method of extracting echo hiding, and enhance its security through a combined method based on spread spectrum. To improve the extraction, a wrong hypothesis is corrected and substituted. To improve security using a pseudo-random key generation algorithm, spread spectrum and echo hiding methods are used randomly. To evaluate the proposed extraction, numerous extraction tests are carried out in the normal state and in the event of attacks. A steganalyser has also been used to assess security improvements. The results gained through different experiments on the security of steganography indicate a 3-percent increase in steganalysis errors. The proposed extraction method was modified based on the main method and resulted in more than 10% improvement.

Since the invention of electricity, global power grids have been at the forefront of technological advances. The antiquated infrastructure of power system which provides power to the city's homes, factories and businesses are replaced with a new power distribution system. This new infrastructure of power distribution includes the collection of digital systems called the smart grid. In the smart grid, one of the main components is the distribution system, and the consumption reports are transferred from the substations to the control center. Currently, the smart substations use the IEC61850, however, it is not completely safe. IEC 62351 is used to secure this standard. However, the security protocols are provided for IEC 62351 standard, and there are different security issues to this standard. This paper presents a key agreement scheme with an authentication mechanism based on ECC for securing the communication between the data center and substation. In addition, it can cover the standard security weaknesses, and the session key is generated due to the time limit for the two important protocols in IEC 62851 (i.e. GOOSE and SV).

Nowadays, routing and the improvement of reliability along with the load balancing and congestion control are the most important and challenging concepts in ad-hoc networks. However, there are some constraints in the bandwidth and the communication range due to the different utility of routing in the Mobile Ad Hoc Network (MANET). These restrictions, in addition to the dynamic network topology, are causing more complexity of routing and data transmission. These problems make the use of conventional methods inefficient, especially in the congestion and traffic control. So, there is a need to propose new solutions for these kinds of networks. This study has used the multipath routing based on the original protocol Ad-Hoc On-Demand Multipath Distance Vector (AOMDV). It proposes an appropriate protocol for the congestion control and balances the favorable loads in the routes. The proposed algorithm is based on different parameters that prepare the fittest multi-paths based on the most efficient routes from the source to the destination, and then it makes a proper traffic distribution pattern in the middle routes based on the congestion analysis of the routes. Simulation results with NS2 shows improvements in the throughput, packet delivery ratio and delay in comparison to the Load Balancing Maximal Minimal Nodal Residual Energy (LBMMRE), Multipath Load Balancing Technique for Congestion Control (MLBCC), and AOMDV routing protocols

The Operating System (OS) is a major part of embedded software systems and its robustness has considerable influence on the robustness of the entire system. Thus, its robustness testing is critical for assessing the dependability of the system. In this paper, a state-aware approach is proposed to evaluate the robustness of components of embedded real-time OSs in the presence of different types of faulty inputs. This approach leads to identifying critical OS states, their criticality level, and the maximum and minimum level of the OS robustness. It also facilitates comparing the robustness level of OS’s components and helps the system developers to select the most appropriate fault tolerance techniques by considering the robustness level and timing limitations. The experimental results demonstrate the ability of the proposed approach in providing more information about the robustness vulnerabilities in the states of the system.

In a large-scale wireless sensor network (WSN), the nodes are usually randomly spread. In such a network, more active nodes consume more energy and shorten the network lifetime. An appropriate approach is nodes management, mainly turning off or deactivating some redundant nodes during some periods of time. The redundant nodes are those that deactivating them does not affect the overall objective operation of the network such as full connectivity and coverage. In this paper two methods for detecting redundant nodes in large-scale WSNs are presented. The proposed methods can detect more redundant nodes, especially lateral redundant nodes, based on heuristic graph theories in the network graph. The simulation results indicated that the proposed methods performs well both in dense and non-dense WSNs and reduces the overall energy consumption of the network better than the previous method.