International Journal of Wireless and Microwave Technologies @ijwmt
Journal articles - International Journal of Wireless and Microwave Technologies
All articles: 648
A Systematic Review on the use of Deep Learning in Classifying Malicious Network Traffic
Scientific article
Finding and managing malicious network protocols is still very difficult in cybersecurity due to sophisticated attacks and encrypted communications. This systematic review analyzes the 59 most recent studies from 2018 to 2025 discussing using Deep Learning to recognize malicious traffic. Importantly, the study proves that more people rely on transformer networks, consider self-supervised and blended approaches, and do not validate sophisticated systems in real time. In addition, it makes it clear that the data used, evaluation metrics, and methods for deploying models on hardware are not realistic enough. Quantitative synthesis reveals: CNN-based architectures dominate (42% of studies, mean accuracy = 96.8%), followed by hybrid CNN-LSTM models (22%, mean accuracy = 97.4%), while Transformer-based approaches (8% of studies) achieve the highest mean accuracy (98.2%) yet only 12% evaluate real-time latency; NSL-KDD remains the most frequent dataset (n=18, mean accuracy = 94.2%), whereas CICIDS2017 (n=14) yields higher performance (97.1% mean); only 6 of 59 studies (10.2%) report inference latency or throughput; and self-supervised or unsupervised methods appear in just 8.5% of studies despite demonstrating 96%+ zero-day detection capability. These statistically grounded findings provide a roadmap for developing deployable, real-time intrusion detection systems while exposing critical gaps in current research methodology.
Free
A Technique for PUE Detection and Isolation in Cognitive Radio Network
Scientific article
The primary aim of a cognitive radio (CR) system is to optimize spectrum usage by exploiting the existing spectrum holes. Nevertheless, the success of cognitive radio technology is significantly threatened by the primary user emulation attack (PUEA). A rogue secondary user (SU) known as the primary user emulator (PUE) impersonates a legitimate primary user (PU) in a PUEA, thereby preventing other SUs from accessing the spectrum holes. Which leads to the decrease in quality of service (QoS), connection undependability, degraded throughput, energy depletion, and the network experiences a deterioration in its overall performance. In order to alleviate the impact of PUEA on Cognitive Radio Networks (CRNs), it is necessary to detect and isolate the threat agent (PUE) from the network. In this paper, a method for finding and isolating the PUE is proposed. MATLAB simulation results showed that the presence of PUE caused a significant decrease in the throughput of SUs, from to . The throughput was highest at a false alarm (FA) probability of 0.0, indicating no PUE, and decreased as the FA probability increased. At a FA probability of 1, the throughput reached zero, indicating complete takeover of the spectrum by PUE. By isolating the PUE from the network, the other SUs can access the spectrum holes, leading to increased QoS, connection reliability, improved throughput, and efficient energy usage. The presented technique is an important step towards enhancing the security and reliability of CRNs.
Free
A Theoretical Graph based Framework for Parameter Tuning of Multi-core Systems
Scientific article
Multi-core systems are outperforming nowadays. Therefore, various computing paradigms are intrinsically incorporated in the multicore domain to exploit its potential and solve well known computing problems. Parameter tuning is a well-known computing problem in the field of Multicore domain. Addressing the said hurdle would leverage in the performance enhancement of Multicore systems. Various efforts in this direction have been made through the conventional parameter tuning algorithms in a limited scope; however, the problem is yet not addressed completely. In this research article, we have addressed parameter tuning problem by employing applications of graph theory, especially Dijkstra shortest path algorithm to address the said issue. Dijkstra’s principle has been applied to establish correlation among the parameters further tuning by finding the pair of suitable parameters. Two other algorithms which are based on application feedback (to provide performance goals to the system) has been introduced. The proposed algorithms collectively (as a framework), addressed the parameter tuning problem. The effectiveness of the algorithms is verified and further measured in distinct parameter tuning scenarios and promising outcome has been achieved.
Free
A Three-Level Model for Detecting and Identifying Aviation Objects using Deep Learning
Scientific article
This paper presents an intelligent software solution for object identification in images using deep learning models, designed for automated interpretation of monitoring results of aviation objects and infrastructure. The proposed approach addresses the growing demand for enhanced flight safety and improved efficiency of aviation operations. To meet this demand, a three-level model is proposed: Level 1 performs object detection, Level 2 provides optical character recognition (OCR) and text normalization, and Level 3 implements fuzzy matching with an object database. Based on comparative testing of detection models, YOLOv8n was selected as the core of the three-level architecture, providing an optimal balance between real-time processing speed and detection accuracy. A detailed analysis of model architectures revealed specific advantages and limitations in identifying monitoring results from image data. Training on a specialized dataset and subsequent testing confirmed the high efficiency of the proposed solution and its ability to reliably localize objects even under challenging visual conditions such as shadows, glare, and partial occlusion. The obtained results demonstrate the significant potential of the proposed intelligent solution for extending computer vision capabilities in the monitoring of aviation objects and infrastructure. The experimental results also confirm the effectiveness of the OCR and fuzzy matching modules in improving object identification accuracy under real-world conditions.
Free
A Three-Party Password Authenticated Key Exchange Protocol with Key Confirmation
Scientific article
Three-party authenticated key exchange protocol is an important cryptographic technique in the secure communication areas, by which any two clients can verify the ability to use a server to establish communication. Recently, researchers have begun proposing new key exchange protocols that would not require the use of server public keys, but a human-memorable password. In this paper, we propose a new three-party password authenticated key exchange protocol with key confirmation. The security of our proposed protocol relies on the hardness of the bilinear Diffie-Hellman problem and Diffie-Hellman problem in the random oracle model, and the proposed protocol achieves the security attributes: dictionary attack resilience, known session key security, perfect forward secrecy, no key compromise impersonation, no unknown key share and no key control.
Free
A Trust Evaluation Model for Industrial Control Ethernet Network
Scientific article
Industrial control ethernet networks are more impotant in connecting with equipments each other of enterprise comprehensive automation and integrating information. With the explosive growth of network techniques, the traditional control networks can no longer satisfy the security demands on network connectivity, data storage and information exchanges.New types of networks emerged in recent years in order to provide solutions for the increasing requirements on networked services. We propose a trust evaluation model for industrial control ethernet network . Our study shows the importance and necessity of applying theoretical analyses to understand the complex characteristics of trusted industrial control ethernet networks.
Free
A Trust-based Security Approach in Hierarchical Wireless Sensor Networks
Scientific article
In recent decades Significant expansion and popularity of wireless sensor networks in various applications have attracted the attention of many researchers. The main challenges of WSN for the researchers are Energy and security restrictions. Recently trust as a new, efficient and soft method has been able to provide satisfactory security in WSN. In this study by using a simple method, first each node calculates the trust values of neighbors and according to these values exchanges data with neighbor nodes, then from each cluster, a node whose trust is greater than a threshold value can be candidate for being cluster head. Finally by using fuzzy logic a node with the most trusted neighbors and desirable energy level among the candidate nodes is selected as a cluster head. Simulation results show that proposed system has been able to greatly improve security and prevent untrusted and malicious nodes from becoming the cluster head.
Free
A Weighed Least Square TDOA Location Algorithm for TDMA Multi-target
Scientific article
In order to improve the location precision of multiple targets in a time division multiple address (TDMA) system, a new weighed least square algorithm is presented for multi-target ranging and locating. According to the time synchronization of the TDMA system, the range difference model between multiple targets is built using the time relations among the slot signals. Thus, the range of one target can be estimated by the other one's, and a group of estimated value can be acquired for every target. Then, the weighed least square algorithm is used to estimate the range of every target. Due to the time differences of arrival (TDOA) of all targets are used in one target's location, the location precision is improved. The ambiguity and non-solution problems in the traditional TDOA location algorithm are avoided also in the presented algorithm. At the end, the simulation results illustrate the validity of the proposed algorithm.
Free
A Wireless Solution to Collecting and Displaying Oil Temperature Data Based on Zigbee Network
Scientific article
In some oil fields of China, monitoring oil temperature during producing almost relies on manual operation. According to this, we designed a solution based on Zigbee network and sensor technology. In our design of sampling nodes, with JN5139 module as the core, uses sensor PT100 to collect temperature data and LCD module LCM141C-01 to display the final result. The whole solution has an advantage of a simple structure, low power consumption etc, therefore, it has a positive meaning in improving monitoring work efficiency in oil fields.
Free
A double auction scheme based on secret sharing and safe comparing protocol
Scientific article
At present most practical electrical auction schemes that based on secret sharing, group signature and hash chain assume the existence of a trusted thid party, while the schemes that based on commitment, zero knowledge or homomorphic encryption without the TTP model face the problem of high cost of communication and computation. The double auction scheme proposed by Bogetoft is based on secure multiparty computation without a TTP and get very high efficiency. In this article, we improve the above scheme. Based on secret sharing and constant round safe comparing protocol, we reduce the requirement of honest majority in the original scheme. We improve the security of the scheme while maintain the high efficiency.
Free
A hybrid cryptosystem to enhance security in IoT health care system
Scientific article
Internet of Things (IoT) based health care system provides an essential interface between tiny devices and customers, who require customary checking by remedial focus. The technological innovation is important to guarantee the data protection and security among customer and devices, though it is vulnerable by various security assaults. The cryptographic technique is a prominent method for data protection in a healthcare management system. Single cryptographic algorithm based solution suffered to provide efficient security as its high probability of attacks. So this paper proposes a hybrid cryptographic algorithm that secures the sensitive medicinal information in IoT health care system. The proposed hybrid algorithm is dealing with various security attacks in a proficient way, and also increases its performance when compared to other cryptographic algorithms.
Free
A modified semi-supervised color image segmentation method
Scientific article
The paper proposed a modified color image segmentation method basing on semi-supervised hidden Markov random fields (HMRF) with constraints. Making use of MeanShift algorithm to get supervision information and, cluster number and initial values for cluster centroids, color images can be segmented effectively with the method in this paper by K-Means algorithm. The experimental results are very encouraging.
Free
A novel energy efficient cluster head selection method for wireless sensor networks
Scientific article
Wireless Sensor Networks are becoming a worldwide sensational topic with recent advances in wireless communications and digital electronics. It serves as the backbone for controlling real-life applications. It consists of group of sensor nodes that sense the information from an event area and passes it to the base station which reacts according to the environment. There are number of cluster based routing protocols, in which a region is divided into number of clusters and within each cluster, a cluster head is elected based on some parameter. So, a novel selection method for the cluster head having efficiency in energy is based on Flower Pollination Algorithm (FPA) is proposed in this paper. The performance of our proposed scheme is being analyzed and is compared with the already existing protocols like LEACH, C-LEACH and K-Means in terms of energy efficiency, number of alive nodes, packet drop ratio and energy dissipation etc
Free
A power-based method for improving the ODMRP protocol performance in mobile ad-hoc networks
Scientific article
Mobile AD hoc Networks as a special type of wireless networks have received special attention due to having special features such as no need for central management, no need for infrastructure and high mobility capability and can be used in cases where creating an effective communication infrastructure is not cost-effective or is practically impossible, such as conferences, such as battles and communications after natural disasters. Several routing protocols are proposed for these networks. ODMRP protocol is one of the most famous and used protocols in Mobile AD hoc networks. This study was carried out aimed to discuss this routing protocol and then provide a new routing method for this protocol for increasing its efficiency. In the ODMRP protocol, the optimal route is selected based on the shortest route. In wireless communications and getting the nodes away from each other, the received signal levels are weakened and may result in loss of data, and in practice, the shortest path that works based on the number of hops loses its effectiveness. In the proposed protocol, the route is selected based on the received signal strength level. According to the simulation results, the performance of the proposed protocol increases by decreasing control overhead and increasing the packet delivery rate compared to the original protocol.
Free
Scientific article
Blockchain’s vast applications in different industries have drawn several researchers to pursue extensive research in securing blockchain technologies. In recent times we could see several institutions coming together to create consortium based blockchain networks such as Hyperledger. Although for applications of blockchain such as Bitcoin, Litcoin, etc. the majority-attack might not be a great threat but for consortium based blockchain networks where we could see several institutions such as public, private, government, etc. are collaborating, the majority-attack might just prove to be a prevalent threat if collusion among these institutions takes place. This paper proposes a methodology where we can use intelligent software agents to monitor the activity of stakeholders in the blockchain networks to detect anomaly such as collusion, using supervised machine learning algorithm and algorithmic game theory and stop the majority attack from taking place.
Free
A stable routing protocol based on DSR protocol for mobile ad hoc networks
Scientific article
Mobile ad hoc network is a wireless non-centralized network. This network includes a set of distributed nodes with any base or central management, develop a temporary network. Such a way, routing is of the basic challenges of these kinds of networks. Till now, various protocols have been provided for routing in these kinds of networks. One of the optimum routing techniques in these networks is stable routing. In the stable routing, the target is to use paths for send and receive that probably have a higher life period. This causes the data to be sent from a more confident path and the need to new routing will be less, due to liquidation of the current path. In this paper, the target is to provide a stable routing protocol with high efficiency for these kinds of networks, by improving the DSR routing protocol. In the provided protocol, beside the path stability, the energy of the path nodes and path length will be considered too, in order to discover a path with higher quality and use it. The provided protocol will be called as ST-DSR. The result of stimulation in the NS-2 environment shows that the ST-DSR has a better operation toward the base protocol, meaning DSR.
Free
A study on Need of Adaptation Layer in 6LoWPAN Protocol Stack
Scientific article
Emergence of wireless embedded applications is resulting in the communication among sensor nodes connected in a wireless personal area network. Sensor nodes gather the real time information and transmit it to the desired application. This requires transmission of IPv6 packets over Low-power wireless personal area network and is called 6LoWPAN. IPv6 is resource intensive protocol whereas 6LoWPAN is resource constraint due to small packet size, limited device memory, short transmission range, and less data rate of sensor nodes. Also these nodes in 6LoWPAN are mainly battery operated hence minimum power consumption is also a major constraint. To make the efficient transmission of information in such a resource constraint network, an adaptation layer was suggested and implemented by Internet Engineering Task Force (IETF). The placing of this additional layer is in between network layer and data link layer of TCP/IP protocol stack. This paper contributes in the detailed analysis of need of adaptation layer in 6LoWPAN protocol stack. The necessity of this additional layer is justified by explaining the major functions like header compression, fragmentation and reassembly of packets and packet routing handled by it.
Free
Scientific article
The optimal capacity expansion of base station subsystems in Next Generation Wireless Network (NGWN) problem with respect to multi-demand type and system capacity constraints is known to be NP-complete. In this paper, we propose a novel ant colony optimization algorithm to solve a network topology has two levels in which mobile users are sources and both base stations and base station controllers are concentrators. There are two important aspects of upgrading to NGWN. The first importance of backward compatibility with pre-existing networks, and the second is the cost and operational benefit of gradually enhancing networks, by replacing, upgrading and installing new wireless network infrastructure elements that can accommodate both voice and data demand. Our objective function is the sources to concentrators connectivity costas well as the cost of the installation, connection, replacement, and capacity upgrade of infrastructure equipment. We evaluate the performance of our algorithm with a set of real world and data randomly generated. Numerical results show that our algorithms is a promising approach to solve this problem.
Free
Scientific article
This research presents a pioneering investigation into the tangible outcomes of implementing an Artificial Intelligence (AI) driven network security strategy, with a specific emphasis on dynamic threat landscape adaptation and the integration of time series analysis algorithms. The study focuses on the innovative fusion of adaptive mechanisms to address the ever-evolving threat landscape, coupled with the application of the Autoregressive Integrated Moving Average (ARIMA) time series analysis algorithm. Real-world case studies are employed to provide concrete evidence of the efficacy of these strategies in fortifying network defenses and responding dynamically to cyber threats. Novelty is introduced through the unified integration of dynamic threat landscape adaptation mechanisms that continuously learn and evolve. The paper details adaptive access controls, showcasing how the security system dynamically adjusts permissions in real time to respond to emerging threats. Additionally, the application of the ARIMA time series analysis algorithm represents a pioneering contribution to the field of cybersecurity. By unveiling temporal patterns in security incidents, ARIMA adds a predictive element to network defense strategies, offering valuable insights into potential future threats and enabling a proactive response. The findings underscore the practical impact of the applied strategies, with real-world case studies demonstrating substantial improvements in threat detection rates, the effectiveness of adaptive responses, and the predictive capabilities facilitated by ARIMA. This research contributes to the advancement of AI in network security by providing tangible evidence of the innovative and effective nature of the integrated approach. The outcomes bridge the gap between theoretical concepts and practical applications, offering valuable insights for organizations seeking adaptive and predictive strategies to enhance their cybersecurity resilience in dynamic threat environments.
Free
Scientific article
All new mobile radio communication systems undergo a cautious cellular network planning and re-planning process in order to resourcefully utilize the allotted frequency band and also ensure that the geographical area of focus is adequately fortified with integrated base stations transmitters. To this end, efficient radio propagation model prediction and tuning is of huge importance, as it assists radio network engineers to effectively assess and plan the cellular network signal coverage area. In this research work, an adaptive least absolute deviation approach is proposed and verified to fine-tune the parameters of Ericsson propagation model. The adaptive tuning technique have been verified experimentally with field propagation loss data acquired over three different suburban locations of a recently deployed LTE radio cellular network in Waterlines area of Port Harcourt City. In terms of the mean absolute percentage error and coefficient of efficiency, the outcomes of the proposed adaptive tuning approach show a higher degree of prediction performance accuracy on the measured loss data compared to the commonly applied least squares regression tuning technique.
Free
