The creation and developing of a wireless network communication that is fast, secure, dependable, and cost-effective enough to suit the needs of the modern world is a difficult undertaking. Channel coding schemes must be chosen carefully to ensure timely and error-free data transfer in a noisy and fading channel. To ensure that the data received matches the data transmitted, channel coding is an essential part of the communication system's architecture. NR LDPC (New Radio Low Density Parity Check) code has been recommended for the fifth-generation (5G) to achieve the need for more internet traffic capacity in mobile communications and to provide both high coding gain and low energy consumption. This research presents NR-LDPC for data transmission over two different multipath fading channel models, such as Nakagami-m and Rayleigh in AWGN. The BER performance of the NR-LDPC code using two kinds of rate-compatible base graphs has been examined for the QAM-OFDM (Quadrature Amplitude Modulation-Orthogonal Frequency Division Multiplexing) system and compared to the uncoded QAM-OFDM system. The BER performance obtained via Monte Carlo simulation demonstrates that the LDPC works efficiently with two different kinds of channel models: those that do not fade and those that fade and achieves significant BER improvements with high coding gain. It makes sense to use LDPC codes in 5G because they are more efficient for long data transmissions, and the key to a good code is an effective decoding algorithm. The results demonstrated a coding gain improvement of up to 15 dB at 10-3 BER.

There are billions of inter-connected devices by the help of Internet-of-Things (IoT) that have been used in a number of applications such as for wearable devices, e-healthcare, agriculture, transportation, etc. Interconnection of devices establishes a direct link and easily shares the information by utilizing the spectrum of cellular users to enhance the spectral efficiency with low power consumption in an underlaid Device-to-Device (D2D) communication. Due to reuse of the spectrum of cellular devices by D2D users causes severe interference between them which may impact on the network performance. Therefore, we proposed a Q-Learning based low power selection scheme with the help of multi-agent reinforcement learning to detract the interference that helps to increase the capacity of the D2D network. For the maximization of capacity, the updated reward function has been reformulated with the help of a stochastic policy environment. With the help of a stochastic approach, we figure out the proposed optimal low power consumption techniques which ensures the quality of service (QoS) standards of the cellular devices and D2D users for D2D communication in 5G Networks and increase the utilization of resources. Numerical results confirm that the proposed scheme improves the spectral efficiency and sum rate as compared to Q-Learning approach by 14% and 12.65%.

We described the placing of the mobile agents in a dynamic environment. It formed a dynamic environment for a complex of dynamically changing mobile agents. We described a two-level system of connections at the global and local levels of interaction. Such a scheme allows you to support the survivability of a dynamic environment. We presented the model of placement of mobile agents in a dynamic environment, which forms the basis of the trajectory of interaction between mobile agents, enabling us to combine the dynamic environment into a unified dynamic environment. The proposed method for mobile agents parameters restoring in a unified dynamic environment, taking into account the similarity coefficients, allows restore 80% parameters of an inaccessible mobile agent. This indicates the high efficiency of the objects description in the form of a unified dynamic environment in order to maintain its integrity.

Social media usage has increased tremendously with the rise of the internet and it has evolved into the most powerful networking platform of the twenty-first century. However, a number of undesirable phenomena are associated with increased use of social networking, such as cyberbullying (CB), cybercrime, online abuse and online trolling. Especially for children and women, cyberbullying can have severe psychological and physical effects, even leading to self-harm or suicide. Because of its significant detrimental social impact, the detection of CB text or messages on social media has attracted more research work. To mitigate CB, we have proposed an automated cyberbullying detection model that detects and classifies cyberbullying content as either bullying or non-bullying (binary classification model), creating a more secure social media experience. The proposed model uses Natural Language Processing (NLP) techniques and Machine Learning (ML) approaches to assess cyberbullying contents. Our main goal is to assess different machine learning algorithms for their performance in cyberbullying detection based on a labelled dataset from Formspring [1]. Nine popular machine learning classifiers namely Bootstrap Aggregation or Bagging, Stochastic Gradient Descent (SGD), Random Forest (RF), Decision Tree (DT), Linear Support Vector Classifier (Linear SVC), Logistic Regression (LR), Adaptive Boosting (AdaBoost), Multinomial Naive Bayes (MNB) and K-Nearest Neighbour (KNN) are considered for the work. In addition, we have experimented with a feature extraction method namely CountVectorizer to obtain features that aid for better classification. The results show that the classification accuracy of AdaBoost classifier is 86.52% which is found better than all other machine learning algorithms used in this study. The proposed work demonstrates the effectiveness of machine learning algorithms in automatic cyberbullying detection as against the very intense and time-consuming approaches for the same problem, thereby by facilitating easy incorporation of an effective approach as tools across different platforms enabling people to use social media safely.

Transmission of images on the network is considered insecure which has security-related issues. In this paper, to provide security to digital images, an encryption system that uses four chaotic maps for binary key sequence generation is proposed. The system consists of stages namely, confusion, generation of random binary chaotic key sequence, pseudo-random number generation (RN), and diffusion. Keys for encryption are chosen randomly based on a pseudo random generator from the selected chaotic maps by the linear feedback shift register (LFSR). The algorithm achieves good results in terms of NPCR, UACI, and entropy values. The developed cryptosystem resists differential attacks, is sensitive to minor alterations in the keys, and has a large key space.

In the scenario of Distributed Denial of Service (DDoS) attacks are increasing in a significant manner, the attacks should be mitigated in the beginning itself to avoid its devastating consequences for any kind of business. DDoS attack can slow down or completely block online services of business like websites, email or anything that faces internet. The attacks are frequently originating from cloud virtual machines for anonymity and wide network bandwidth. Hyper-Calls Analysis(HCA) enables the tracing of command flow to detect any clues for the occurrence of malicious activity in the system. A DDoS attack detection approach proposed in this paper works in the hypervisor side to perform hyper calls based introspection with machine learning algorithms. The system evaluates system calls in hypervisor for the classification of malicious activities through Support Vector Machine and Stochastic Gradient Descent (SVM & SGD) Algorithms. The attack environment created using XOIC attacker tool and CPU death ping libraries. The system’s performance also evaluated on CICDDOS 2019 dataset. The experimental results reveal that more than 99.6% of accuracy in DDoS detection without degrading performance.

Mobile agent is a processing unit works on the behalf of host computer. Mobile agent with intelligence provides a new computing prototype that is totally different from conventional prototype. Mobile agents are automatically itinerating from one host Computer to another host computer and execute assigned task on the behalf of user in heterogeneous environment under own control. Because mobile agents roam around distributed networks automatically, the security of the agents and platforms is a major concern. The number of mobile agents-based software applications has increased dramatically over the past year. It has also enhanced the security risks associated with such applications. Most protection systems in the mobile agent paradigm focus on platform security and provide few guidelines for mobile agent security, which is still a challenging topic. There is a risk to information carries by mobile agents from the malicious mobile agents who can modify and steal the confidential information. In this paper proposed multilevel authentication framework of mobile agents and platform based on Lagrange interpolation and fast Fourier transformation (LIFFT). In this frame work ‘n’ number of mobile agent have two level of security first level key used authentication and second level of key used for execution of mobile agents.

Load balancing plays a major part in improving the performance of fog computing, which has become a requirement in fog layer for distributing all workload in equal manner amongst the current Virtual machines (VMs) in a segment. The distribution of load is a complicated process as it consists of numerous users in fog computing environment. Hence, an effectual technique called Mutated Leader Algorithm (MLA) is proposed for balancing load in fogging environment. Firstly, fog computing is initialized with fog layer, cloud layer and end user layer. Then, task is submitted from end user under fog layer with cluster of nodes. Afterwards, load balancing process is done in each cluster and the resources for each VM are predicted using Deep Residual Network (DRN). The load balancing is accomplished by allocating and reallocating the task from the users to the VMs in the cloud based on the resource constraints optimally using MLA. Here, the load balancing is needed for optimizing resources and objectives. Lastly, if VMs are overloaded and then the jobs are pulled from associated VM and allocated to under loaded VM. Thus the proposed MLA achieved minimum execution time is 1.472ns, cost is $69.448 and load is 0.0003% respectively.

Wireless sensor networks (WSNs) has been envisioned as a potential paradigm in sensing technologies. Achieving energy efficiency in a wireless sensor network is challenging since sensor nodes have confined energy. Due to the multi-hop communication, sensor nodes spend much energy re-transmitting dropped packets. Packet loss may be minimized by finding efficient routing paths. In this research, a routing using fuzzy logic and reinforcement learning procedure is designed for WSNs to determine energy-efficient paths; to achieve reliable data delivery. Using the node’s characteristics, the reward is determined via fuzzy logic. For this paper, we employ reinforcement learning to improve the rewards, computed by considering the quality of the link, available free buffer of node, and residual energy. Further, simulation efforts have been made to illustrate the proposed mechanism’s efficacy in energy consumption, delivery delay of the packets, number of transmissions and lifespan.