Developing a better intrusion detection systems (IDS) has attracted many researchers in the area of computer network for the past decades. In this paper, Genetic Algorithm (GA) is proposed as a tool that capable to identify harmful type of connections in a computer network. Different features of connection data such as duration and types of connection in network were analyzed to generate a set of classification rule. For this project, standard benchmark dataset known as KDD Cup 99 was investigated and utilized to study the effectiveness of the proposed method on this problem domain. The rules comprise of eight variables that were simulated during the training process to detect any malicious connection that can lead to a network intrusion. With good performance in detecting bad connections, this method can be applied in intrusion detection system to identify attack thus improving the security features of a computer network.

Network security is an important aspect in maintaining computer network systems and personal information from being illegally accessed by third parties. The major problem that frequently occurs in computer network systems is the failure in detecting possible network-attacks. Apart from that, the process of recognizing the type of attack that occurs is very crucial as it will determine the elimination process that should take place to counter the intrusion. This paper proposes the application of standard Genetic Algorithm (GA) that combines with immune algorithm process to enhance the computer system's capability in recognizing possible intrusion occurrence in a computer system. Simulation was conducted numerous times to test the effectiveness of the proposed intrusion detection system by manipulating the parameter values for genetic operators utilized in GA. The effectiveness of the proposed method is shown in the gathered results and the analysis conducted further supports and proves that Immune Genetic Algorithm (IGA) has the capability to predict the occurrence of intrusion in computer network.

<span>Internet connection nowadays has become one of the essential requirements to execute our daily activities effectively. Among the major applications of wide Internet connections is local area network (LAN) which connects all internet-enabled devices in a small-scale area such as office building, computer lab etc. This connection will allow legit user to access the resources of the network anywhere as long as authorization is acquired. However, this might be seen as opportunities for some people to illegally access the network. Hence, the occurrence of network hacking and privacy breach. Therefore, it is very vital for a computer network administrator to install a very protective and effective method to detect any network intrusion and, secondly to protect the network from illegal access that can compromise the security of the resources in the network. These resources include sensitive and confidential information that could jeopardise someone’s life or sovereignty of a country if manipulated by wrong hands.  In Network Intrusion Detection System (NIDS) framework, apart from detecting unauthorized access, it is equally important to recognize the type of intrusions in order for the necessary precautions and preventive measures to take place. This paper presents the application of Genetic Algorithm (GA) and its steps in performing intrusion detection process. Standard benchmark dataset known as KDD’99 cup was utilized with forty-one distinctive features representing the identity of network connections. Results presented demonstrate the effectiveness of the proposed method and warrant good research focus as it promises exciting discovery in solving similar-patent of problems.   </span>

No abstract

In the last ten years, polar code research has piqued the interest of firms and researchers, particularly in the communication industry. Polar codes have been utilised as a coding method for the fifth-generation wireless standard (5G). However, the polar decoder does not adequately correct errors in successive cancellation (SC) decoding when dealing with short- to intermediate-length codes. However, SC decoding can correct errors more efficiently by using sequential cancellation list (SCL) decoding. The main drawback of SCL is its higher cost due to computational complexity and throughput. The present research investigates the effect of Gaussian approximation (GA) and different decoding approaches on the performance of polar codes. First, SC and SCL decoders are developed utilising amplitude shift keying modulation; a decoder using GA is then integrated. According to simulation data, the SCL, both with and without GA, exhibits a better block error rate (BLER) than SC. The maximum difference between the SCL decoder and SC decoder is 0.6 dB at BLER=0.1 for N=2048. Furthermore, at BLER=5.6 x 10-6, the SCL decoder with GA performs better than the SC decoder for block lengths, N=1024, with a maximum difference of 2.72 dB. When the polar decoder with GA is utilised, enhancements are observed in polar code performance for various list sizes and block lengths, although time complexity is increased.