International Journal of Wireless and Microwave Technologies @ijwmt
Journal articles - International Journal of Wireless and Microwave Technologies
All articles: 674
FLAT: A Federated Graph Attention Network for Secure Routing and Attack Detection in MANETs
Scientific article
Abstract: Mobile Ad Hoc Networks (MANETs) are autonomous wireless networks that do not rely on fixed infrastructure for communication among the mobile nodes. The mobile nodes communicate with each other with no centralized control, and routes are not established in advance. This makes MANETs vulnerable to routing attacks such as Black Hole and Sybil attacks, which divert or drop packets and thereby degrade network performance. This paper presents a novel hybrid approach combining Federated Learning (FL) and Graph Attention Network (GAT), which is termed as FLAT. GAT dynamically assigns importance to neighbouring nodes, allowing the model to capture the mobility, link instability, and heterogeneous node behaviour inherent in MANETs. FL, in turn, enables routing and attack patterns to be learned in a decentralized manner without sharing raw data. The approach was evaluated in NS-3.36 on networks ranging from 10 to 150 nodes, under Black Hole and Sybil attacks with 20% of the nodes acting maliciously, and was compared against AODV, SAODV, AOMDV, and the optimization-based Dolphin Cat Optimizer, using PDR, PLR, throughput, and end-to-end delay as evaluation metrics. It is found that the PDR of FLAT is approximately 15.1% higher than AODV and 8.2% higher than the Dolphin Cat Optimizer, while its PLR is reduced by about 77% relative to AODV, 75% relative to SAODV, and 50% relative to the Dolphin Cat Optimizer. With respect to throughput performance, FLAT shows a performance level of about 4.4, 2.8, 2.3, and 2.1 times higher than AODV, SAODV, AOMDV, and Dolphin Cat Optimizer respectively. The above findings clearly show that FLAT outperforms current techniques with regard to all measured parameters.
Free
Fast Matching Algorithm Based on Fingerprint Classification Information
Scientific article
This paper focuses on fingerprint minutia matching algorithm. A special minutia neighbor structure is proposed during the matching process in this algorithm. It can locate fingerprints using the singular from classification information. In addition, minutia structure can be used to save the time of matching minutia in a simple but effective way. Then, the matching of minutia is based on the changeable sized boundary box. At the same time, possible reference position is computed to make sure the algorithm more robust to nonlinear deformation from fingerprint images. Experimental results on Fingerprint verification competition FVC2004 databases show that this algorithm can speed up the matching of fingerprint database with a preferable performance.
Free
Scientific article
Wireless Sensor Networks (WSNs) play a critical role in various applications, including environmental monitoring, healthcare, and industrial automation. However, these networks face significant challenges related to energy efficiency, fault tolerance, and reliable data transmission, particularly in dynamic environments. Existing clustering and routing techniques often fail to ensure seamless fault tolerance and energy optimization simultaneously. Many traditional approaches lack robust mechanisms to handle Cluster Head (CH) failures, resulting in reduced network stability and shorter operational lifetimes. To address these limitations, this study proposes a Fault-Tolerant Backup Cluster Head with Ant Colony Optimization (FT-BKCH-ACO) approach that enhances energy efficiency and network resilience. The methodology involves optimized CH and Backup CH (BKCH) selection, considering parameters such as residual energy, distance to the base station, and network density. Additionally, Ant Colony Optimization (ACO) is employed to dynamically adjust pheromone levels for energy-efficient routing, ensuring reliable intra-cluster and inter-cluster communication. Simulation results demonstrate that the FT-BKCH-ACO approach significantly improves energy consumption by 23.2%, packet delivery ratio by 10.5% and end-to-end delay by 17.8% compared to existing models. The inclusion of backup CHs ensures seamless communication even in the event of node failures, making this method highly suitable for IoT-enabled WSN applications. The proposed approach bridges the gap between fault-tolerant clustering and adaptive routing, offering a scalable and energy-efficient solution for large-scale sensor networks.
Free
Feature Dimension Reduction Algorithm Based Prediction Method for Protein Quaternary Structure
Scientific article
Knowing the quaternary structure of an uncharacterized protein often provides useful clues for finding its biological function and interaction process with other molecules in a biological system. Here, dimensionality reduction algorithm is introduced to predict the quaternary structure of proteins. Our jackknife test results indicate that it is very promising to use the dimensionality reduction approaches to cope with complicated problems in biological systems, such as predicting the quaternary structure of proteins.
Free
Feature Engineering for Cyber-attack detection in Internet of Things
Scientific article
Internet of Things (IoT) consists of group of devices which communicates information over private networks. One of the key challenges faced by IoT networks is the security breaches. With the objective of automating the detection of possible security breaches in five categories, IoT traffic created with Message Queue Telemetry Transport (MQTT) protocol is analyzed. The five categories of cyber-attacks considered are brute force, denial of service (DoS), flooding, malformed data, and SlowITe attacks along with legitimate traffic. The popular five machine learning (ML) models, LightGBM, Random Forest, MLP, AdaBoost, and Decision Tree Classifiers are trained to predict cyber-attacks. In traditional traffic analysis all the available features of MQTT traffic were utilized for the ML modeling and in this work, we challenge the practice by showing that automated feature selection improves the performance of the overall ML models. The average accuracy, precision, recall and the F1 score are used as performance evaluation metrics. It is observed that all models in average are able to achieve 90% of accuracy in classification, while MLP model is trained 10 times faster than the other models. Further the optimal number of features for correct classification is identified as 10 features through Monte Carlo analysis. With the reduced features, it is possible to detect DoS, flooding, and SlowITe attacks with more than 90% accuracy and precision. Yet, it is difficult to tell apart brute force and malformed data attacks.
Free
Federated Graph Attention Network for IoT Edge Anomaly Detection
Scientific article
The rapid evolution of Internet of Things (IoT) networks has presented serious security threats because of the enormous volume of distributed data produced by connected devices. Traditional IDSs (IDS) usually follow centralized data collection, resulting in communication overhead, scalability issues, and privacy problems. Although federated learning (FL) offers a way to train distributed models while preserving privacy, many current FL-based AD techniques cannot be adapted to account for the interaction relationships between IoT devices. To address these challenges, this study introduces the federated graph attention network (FL-GAT) for anomaly detection in IoT-edge environments. The proposed framework treats IoT devices as graph nodes and introduces a multi-head graph attention mechanism to capture the spatial interaction among devices while guaranteeing data privacy by adopting federated learning. Local models are trained in a distributed manner on edge devices without sharing raw data. Distributed IoT attack scenarios were used to evaluate the proposed framework using the TON_IoT and Bot-IoT benchmark datasets. Experimental results show that FL-GAT achieved 95.2 % accuracy and 94.5 % F1 score on TON_IoT and 94.8 % accuracy and 94.1 % F1 score on Bot-IoT, with better results than centralized deep learning and federated deep learning baseline models, and graph-based baseline models. Furthermore, the attention mechanism enhances the interpretability of the model by identifying the key interactions between devices that lead to unusual activities. Although the proposed framework shows encouraging performance and scalability, the evaluation was conducted using benchmark IoT datasets under a simulated experimental setting. Future work will focus on real-world deployment scenarios, dynamic network conditions, and lightweight edge optimization for resource-constrained IoT devices.
Free
Scientific article
Dynamic spectrum access (DSA) in 5G IoT setups with cognitive radio is characterized by rapid and decentralized decision-making processes in highly non-stationary wireless environments, limited communication needs, and restrictive bounds. In this work, we present F-DMRL, a federated, communication-efficient decentralized meta-reinforcement learning framework for allowing a massive number of IoT devices to meta-learn collectively about spectrum-access strategies in a decentralized way without centralized control and without an extensive amount of inter-agent communication. Our method incorporates lightweight federated meta-parameter aggregation with gradient sparsification and periodic communication, allowing devices to only compress the meta-updates during this process and then adapt locally for task-specificity. We have presented analytical speedup guarantees and upper bounds on communication cost under bounded environmental drift and shown that using the approach proposed here, F-DMRL preserves convergence properties while posing a large reduction in coordination overhead at the same time. Simulations across various 5G IoT spectrum environments showed that F-DMRL performed faster adaptation (up to 45% fewer episodes), higher spectral efficiency, and lower interference probability compared to centralized meta-RL, federated DRL, and traditional decentralized RL baselines. Simulation results averaged across 10 independent runs demonstrate improvements of 45% faster adaptation and 60–80% lower communication overhead relative to baseline methods, while maintaining stable convergence.
Free
Fixed Cluster Formations with Nearest Cluster Heads in Wsns
Scientific article
The limited battery usage of a sensor node is one of the significant issues in WSNs. Therefore, extending the lifetime of WSNs through energy efficient mechanisms has become a challenging research area. Previous studies have shown that clustering can decrease the transmission distance of the sensor nodes thus, prolongs the lifetime of the network. In literature, most of the LEACH variants aim to set-up clusters in each round by changing CHs randomly. These formations cause to spend high amount of energy and induce additional network costs. In this paper, an energy-efficient nearest constant clustering approach is proposed to solve the problems of LEACH based protocols. The proposed approach uses constant clusters which are formed only once when algorithm starts. The cluster formation remains fixed until the energies of the all sensors are finished. Proposed approach aims to select nearest CHs in each cluster randomly without changing the cluster formations.
Free
Format-Compliant Encryption of JPEG2000 Codestreams
Scientific article
In this paper, we propose two format-compliant encryption schemes for JPEG2000, which preserve the syntax of the original codestream and do not introduce superfluous markers into the encrypted bitstream. The proposed efficient scheme randomly encrypts either low or upper half bytes of those randomly selected bytes in Codeblock Contribution to Packets (CCPs). The secure scheme encrypts both low and upper half bytes and can protect the nearly whole codestream except for the header information. The proposed schemes can provide efficient, secure, scalable and completely format-compliant protection of JPEG2000, which is proved by lots of experiments.
Free
Fractal Peano Antenna Covered by Two Layers of Modified Ring Resonator
Scientific article
Negative index of refraction has attracted a great attention in literatures. These materials are artificial structures named metamaterials has characteristics not found in nature. Microstrip antennas covered by metamaterial are very interesting areas of study. In this paper fractal Peano shape antenna is proposed and covered by two layers of modified ring resonator. The results show an enhancement in Reflection Coefficients, gain, and directivity.
Free
Fractal multiband microstrip patch antenna for wireless applications
Scientific article
This paper proposes a design of fractal multi-band microstrip patch antenna dedicated for wireless applications. The proposed antenna uses a FR-4 epoxy substrate having permittivity 4.4 and tangent loss to be 0.02.The microstrip antenna proposed is designed by incorporating double I-shape slot on the surface of rectangular patch and simulated by using HFSS software. Further the antenna is modified by inserting fractal shape and obtained the three frequency bands located at 2.4Ghz , 3.5Ghz and 5.50Ghz respectively and antenna parameter like VSWR, return loss, antenna gain, directivity of an antenna and bandwidth has been analyzed. The designing of proposed antenna is to be followed by fabrication by using A FR-4 substrate of thickness 1.60mm. Further, this paper discusses, the simulated and measured results comparison and analysis of the same. For designing and simulating of antennae simulation software HFSS has been used. The simulated and measured results represented are in permissible range.
Free
Frameproof Codes Based on The Generalized Difference Function Families
Scientific article
The frameproof codes are used in copyright protecting. Motivated by the method of constructing frameproof codes coined by D.Tonien etal, in this paper, we introduced a new combinatorial designs which in fact generalized the difference function family introduced by D.Tonien. The new designs can be constructed from difference matrix efficiently. By using the new designs we construct more larger number of frameproof codes .
Free
Scientific article
We are running in the communication era demanding a very large bandwidth for high speed applications. Among the available bandwidth technologies, the optical fiber seems the most appropriate and best fit. The optical fiber technology laid down at the backbone networks has almost replaced the preexisting coax cables. To extend fiber connectivity to the end user, especially in congested and remote areas is quite a difficult task in the context to cost and installation time. Therefore, the first and last mile connectivity (FLMC) is still a bottleneck in extending the beauty of optical fiber to the edge of the network. In most of the applications, the connectivity from backbone to the end user is carried out with the radio or copper links having a much lesser capacity than optical fiber. Keeping in view the nature and size of emerging applications, the FLMC needs to be addressed with the appropriate technology. To address this issue, the emerging solution is optical wireless communication like free space optics (FSO). The FSO is coming as a more promising alternative due to its properties like huge bandwidth and less cost. In this paper, we discuss the possible solution to first and last mile connectivity by FSO links and hence the gap between the optical core and the edge of network can be bridged by FSO communication in reliable and cost effective manner. The significance of the proposed work gives an everlasting impression of using FSO communication in FLMC over the existing ones. The ever increasing demand of high bandwidth can be meticulously met with the FSO communication. The simulation results show that the desirable performance is achieved and is analyzed with performance indicators like Q-factor and BER.
Free
Scientific article
This paper encompasses the numerical analysis involved with the Electromagnetic (EM) full-wave simulation tool Advanced Design System (ADS) which uses the Method of Moment (MOM) and Finite Element Method (FEM). MOM is utilized to solve Maxwell’s equations which are transformed into integral equations before discretization and boundary conditions are applied while FEM computes the electrical behavior of the high frequency EM wave distribution, and then analyze the antenna parameters. The main objective is to investigate the effect of reactive loading on the microstrip patch surface which is used to control the behavior of the impedance bandwidth and obtain dual-band frequency operation. The study further examines how the perturbed patch antenna design targets the operating frequencies of 2.4 GHz and 5.8 GHz for possible range and speed. The proposed method provides insight into the analysis of the mathematical model employed in attaining the Driving Point Impedance Function (DPF) of the E-patch microstrip patch antenna. This approach was done to quantify the reduction in reflections for improved Radio Frequency (RF) network output.
Free
FusionNet - SQL-Fusion-Based Deep Learning Model for SQL Injection Detection
Scientific article
SQL injection is a hacking attack where malicious code is inserted into database queries through user inputs like search boxes, login forms, or URL parameters. These attacks pose a significant threat to web applications and ERP systems, making early detection crucial. Traditional detection methods, such as rule-based and signature-based approaches, rely on known SQL injection patterns. However, they often fail to identify novel, obfuscated, or zero-day attacks, highlighting the need for more adaptive and intelligent detection mechanisms. This research proposes FusionNetSQL, a fusion-based deep learning model that combines Convolutional Neural Networks, Long Short-Term Memory networks, and Transformers to detect SQL injection attacks. By integrating these architectures, FusionNet-SQL gains a comprehensive understanding of SQL queries, enabling it to differentiate between legitimate interactions and malicious injections. The CNN captures local patterns, the LSTM models sequential dependencies, and the Transformer enhances global context understanding. The model achieves high performance, with 98.02% accuracy, 99.39% precision, 96.79% recall, 98.07% F1-score, and 98.07% AUC-ROC. With its robust performance and adaptability, FusionNet-SQL offers a powerful solution for securing web applications and ERP systems against SQL injection attacks. Its ability to detect both straightforward and sophisticated attacks makes it well-suited for real-world deployment, reinforcing database security and protecting critical data. This research marks a significant step forward in combating evolving cybersecurity threats.
Free
GSM based Monitoring and Control of Systems
Scientific article
In this paper we have proposed a method to make a base for the monitoring and Control of systems. The monitoring and Control of systems could be from monitoring of movements in any particular area to the monitoring of any external electrical, mechanical device. Every person is pocketed with the cell. So, taking the advantage of the same we developed the system for the monitoring and Control system using GSM technology. This will provide the owner, manager of the system to know about the working or any kind of default in the system. Also the system is controlled which is needed in special circumstances and is be implemented with the help of complete circuitry which is a different module (DTMF module) has a specific code as input through GSM encoder that is processed by decoder circuitry of our system. The goal is to find an improvement over the previous surveillance systems .The maintainability of the new and improved is quite efficient as it is easy to handle it by simple software demo. The facilities provided by it such as easy handling, a secrecy support, an immediate action are granted. A prototype is built in the Windows platform using C# to demonstrate the functioning of the entire system.
Free
Scientific article
Signature-based IDS is becoming more difficult due to the ever-increasing amount of encrypted network traffic. Hence, the demand for interpretable and lightweight intrusion detection techniques becomes essential. In this paper, we propose Graph-Temporal Adaptive Intrusion Detection-Non-Parametric (GTAID-NP), which is a novel graph-temporal framework that exploits degree-based graph structure, temporal periodicity extracted using Fast Fourier Transform, and non-parametric log-odds estimation. We evaluate our proposed model on the BCCC-DarkNet-2025 benchmark dataset that contains 22,795 flow records, among which 6,317 are encrypted and 16,478 are not encrypted, which are expressed by 427 features. An extensive ablation study on 192 experiment setups was done to analyze the influence of bin granularity, total-variation smoothing, feature selection strategy, top-K feature selection threshold, graph augmentation, temporal periodicity extraction, and leakage-guard correction based on an 80:20 stratified train-test split. Among all experimental setups, the best setup achieves an AUC of 0.878. The results suggest that fine granular binning, weak smoothing, and joint consideration of graph-structure and temporal properties contribute to better detection performance. We also conduct robustness evaluation of GTAID-NP through five different random seed runs, which achieve a mean AUC of 0.9074 ± 0.0036, showing the stable performance of GTAID-NP on various train/test splits. While the ensemble methods outperform our model on the benchmark score, GTAID-NP can be regarded as a transparent and lightweight approach for intrusion detection on encrypted traffic. Future research works include adversarial robustness, federated inference, and adaptive online learning.
Free
Geometric Invariant Robust Image Hashing Via Zernike Moment
Scientific article
Robust image hashing methods require the robustness to content preserving processing and geometric transform. Zernike moment is a local image feature descriptor whose magnitude components are rotationally invariant and most suitable for image hashing application. In this paper, we proposed Geometric invariant robust image hashing via zernike momment. Normalized zernike moments of an image are used as the intermediate hash. Rotation invariance is achieved by taking the magnitude of the zernike moments. Image normalization method is used for scale and translation invariance. A randomization diffusion processing enhance hashing security. The test results show that our method is robust with respect to the geometrical distortions and content preserving processing.
Free
Scientific article
Human beings live in a world that is vulnerable to disasters and huge security threats. The common occurrence of global natural disasters and security threats call for major attention by the government of nations and the International community. Man continues to live under perpetual fear of the unknown because of these events. Notably, the human being is at the receiving end of these events either as a victim or at times as a perpetrator. Locating and rescuing victims or perpetrators of these events can be effectively achieved using smart digital devices that are configured with their unique identities and this will aid in achieving sustainable peace and stability in society. Equally, the global proliferation of digital devices is always on the rise; hardly today is there anyone on the planet earth without a form of one digital device or the other. This study is exploring the use of smart mobile digital devices, geospatial, cloud, communication, and technologies in mitigating the impact of natural and security threats with the significance of promoting peaceful human co-existence in the society. A Google App for finding a device, clock- timer app, an Internet speed check app and an online weather app were used for the experiments conducted for the proof of concept of the model. A test of model robustness was evaluated using response time and visibility. The model consistently showed good attributes of robustness in its behavior. Furthermore, the following parameters: latency, upload speed, download speed, air quality index, visibility, humidity, wind gust and temperature were observed against the response time in the experiments. A single sample (one-tail) t-test for the response time with a mean population of 0.9 gave a t-test value of 1. The value of p is 0.162791 and the result is not significant at p<.05. This indicates that there was no significant difference in the response time of the model irrespective of the time of the day, weather conditions, and the communication parameters. The result showed that the response time of the conceptual model was fast and consistent with the experiments indicating that the model can be leveraged, to address the problem identified in an affordable manner. The study is highly significant due to the fact that exploring the technologies that support location-based systems has greater potential in addressing the problem occasioned by natural disasters and security threats to humans. Future consideration is focused on enhancing the model by scaling up the biometrics features of the victim or perpetrator for speedy location.
Free
Scientific article
Antenna selection in reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output (MIMO) systems presents has significant computational challenges. The contribution of each transmit antenna is determined by the combined effects of direct and RIS-reflected channels. To address the complexity of combinatorial search a graph neural network (GNN)-based antenna selection framework is proposed. In this framework transmit antennas are represented as graph nodes with channel-correlation information forming. The graph edges and magnitude-phase channel statistics serve as node features. A three-layer feedforward GNN is trained using greedy-selection labels generated from 1000 channel realizations and evaluated on 200 independent test realizations. For a 16×8 MIMO system assisted by a 64-element RIS at 28 GHz the proposed method achieves a spectral efficiency of 63.41 bits/s/Hz and corresponding to 94.5% of the greedy baseline performance of 67.09 bits/s/Hz. While reducing the average selection time from 0.441 ms to 0.025 ms. These results determine that graph-structured learning enables near-greedy antenna selection with considerably lower inference complexity. The current study is limited to simulated settings with fixed system dimensions and idealized channel assumptions; future work will address broader channel models and larger-scale configurations.
Free