MyMedR

Displaying all 7 publications

Abstract:

Sort:

An efficient intrusion detection model based on convolutional spiking neural network

Wang Z, Ghaleb FA, Zainal A, Siraj MM, Lu X

Sci Rep, 2024 Mar 25;14(1):7054.
PMID: 38528084 DOI: 10.1038/s41598-024-57691-x

Many intrusion detection techniques have been developed to ensure that the target system can function properly under the established rules. With the booming Internet of Things (IoT) applications, the resource-constrained nature of its devices makes it urgent to explore lightweight and high-performance intrusion detection models. Recent years have seen a particularly active application of deep learning (DL) techniques. The spiking neural network (SNN), a type of artificial intelligence that is associated with sparse computations and inherent temporal dynamics, has been viewed as a potential candidate for the next generation of DL. It should be noted, however, that current research into SNNs has largely focused on scenarios where limited computational resources and insufficient power sources are not considered. Consequently, even state-of-the-art SNN solutions tend to be inefficient. In this paper, a lightweight and effective detection model is proposed. With the help of rational algorithm design, the model integrates the advantages of SNNs as well as convolutional neural networks (CNNs). In addition to reducing resource usage, it maintains a high level of classification accuracy. The proposed model was evaluated against some current state-of-the-art models using a comprehensive set of metrics. Based on the experimental results, the model demonstrated improved adaptability to environments with limited computational resources and energy sources.
Fulltext Fairness-Oriented Semichaotic Genetic Algorithm-Based Channel Assignment Technique for Node Starvation Problem in Wireless Mesh Networks

Ghaleb FA, Al-Rimy BAS, Boulila W, Saeed F, Kamat M, Foad Rohani M, et al.

Comput Intell Neurosci, 2021;2021:2977954.
PMID: 34413885 DOI: 10.1155/2021/2977954

Wireless mesh networks (WMNs) have emerged as a scalable, reliable, and agile wireless network that supports many types of innovative technologies such as the Internet of Things (IoT), Wireless Sensor Networks (WSN), and Internet of Vehicles (IoV). Due to the limited number of orthogonal channels, interference between channels adversely affects the fair distribution of bandwidth among mesh clients, causing node starvation in terms of insufficient bandwidth distribution, which impedes the adoption of WMN as an efficient access technology. Therefore, a fair channel assignment is crucial for the mesh clients to utilize the available resources. However, the node starvation problem due to unfair channel distribution has been vastly overlooked during channel assignment by the extant research. Instead, existing channel assignment algorithms equally distribute the interference reduction on the links to achieve fairness which neither guarantees a fair distribution of the network bandwidth nor eliminates node starvation. In addition, the metaheuristic-based solutions such as genetic algorithm, which is commonly used for WMN, use randomness in creating initial population and selecting the new generation usually leading the search to local minima. To this end, this study proposes a Fairness-Oriented Semichaotic Genetic Algorithm-Based Channel Assignment Technique (FA-SCGA-CAA) to solve node starvation problem in wireless mesh networks. FA-SCGA-CAA maximizes link fairness while minimizing link interference using a genetic algorithm (GA) with a novel nonlinear fairness-oriented fitness function. The primary chromosome with powerful genes is created based on multicriterion links ranking channel assignment algorithm. Such a chromosome was used with a proposed semichaotic technique to create a strong population that directs the search towards the global minima effectively and efficiently. The proposed semichaotic technique was also used during the mutation and parent selection of the new genes. Extensive experiments were conducted to evaluate the proposed algorithm. A comparison with related work shows that the proposed FA-SCGA-CAA reduced the potential node starvation by 22% and improved network capacity utilization by 23%. It can be concluded that the proposed FA-SCGA-CAA is reliable to maintain high node-level fairness while maximizing the utilization of the network resources, which is the ultimate goal of many wireless networks.
Fulltext Two-stage motion artefact reduction algorithm for electrocardiogram using weighted adaptive noise cancelling and recursive Hampel filter

Ghaleb FA, Kamat MB, Salleh M, Rohani MF, Abd Razak S

PLoS One, 2018;13(11):e0207176.
PMID: 30457996 DOI: 10.1371/journal.pone.0207176

The presence of motion artefacts in ECG signals can cause misleading interpretation of cardiovascular status. Recently, reducing the motion artefact from ECG signal has gained the interest of many researchers. Due to the overlapping nature of the motion artefact with the ECG signal, it is difficult to reduce motion artefact without distorting the original ECG signal. However, the application of an adaptive noise canceler has shown that it is effective in reducing motion artefacts if the appropriate noise reference that is correlated with the noise in the ECG signal is available. Unfortunately, the noise reference is not always correlated with motion artefact. Consequently, filtering with such a noise reference may lead to contaminating the ECG signal. In this paper, a two-stage filtering motion artefact reduction algorithm is proposed. In the algorithm, two methods are proposed, each of which works in one stage. The weighted adaptive noise filtering method (WAF) is proposed for the first stage. The acceleration derivative is used as motion artefact reference and the Pearson correlation coefficient between acceleration and ECG signal is used as a weighting factor. In the second stage, a recursive Hampel filter-based estimation method (RHFBE) is proposed for estimating the ECG signal segments, based on the spatial correlation of the ECG segment component that is obtained from successive ECG signals. Real-World dataset is used to evaluate the effectiveness of the proposed methods compared to the conventional adaptive filter. The results show a promising enhancement in terms of reducing motion artefacts from the ECG signals recorded by a cost-effective single lead ECG sensor during several activities of different subjects.
Fulltext Smart Home Privacy Protection Methods against a Passive Wireless Snooping Side-Channel Attack

Nassiri Abrishamchi MA, Zainal A, Ghaleb FA, Qasem SN, Albarrak AM

Sensors (Basel), 2022 Nov 07;22(21).
PMID: 36366261 DOI: 10.3390/s22218564

Smart home technologies have attracted more users in recent years due to significant advancements in their underlying enabler components, such as sensors, actuators, and processors, which are spreading in various domains and have become more affordable. However, these IoT-based solutions are prone to data leakage; this privacy issue has motivated researchers to seek a secure solution to overcome this challenge. In this regard, wireless signal eavesdropping is one of the most severe threats that enables attackers to obtain residents' sensitive information. Even if the system encrypts all communications, some cyber attacks can still steal information by interpreting the contextual data related to the transmitted signals. For example, a "fingerprint and timing-based snooping (FATS)" attack is a side-channel attack (SCA) developed to infer in-home activities passively from a remote location near the targeted house. An SCA is a sort of cyber attack that extracts valuable information from smart systems without accessing the content of data packets. This paper reviews the SCAs associated with cyber-physical systems, focusing on the proposed solutions to protect the privacy of smart homes against FATS attacks in detail. Moreover, this work clarifies shortcomings and future opportunities by analyzing the existing gaps in the reviewed methods.
Fulltext A Kullback-Liebler divergence-based representation algorithm for malware detection

Aboaoja FA, Zainal A, Ghaleb FA, Alghamdi NS, Saeed F, Alhuwayji H

PeerJ Comput Sci, 2023;9:e1492.
PMID: 37810364 DOI: 10.7717/peerj-cs.1492

BACKGROUND: Malware, malicious software, is the major security concern of the digital realm. Conventional cyber-security solutions are challenged by sophisticated malicious behaviors. Currently, an overlap between malicious and legitimate behaviors causes more difficulties in characterizing those behaviors as malicious or legitimate activities. For instance, evasive malware often mimics legitimate behaviors, and evasion techniques are utilized by legitimate and malicious software.
PROBLEM: Most of the existing solutions use the traditional term of frequency-inverse document frequency (TF-IDF) technique or its concept to represent malware behaviors. However, the traditional TF-IDF and the developed techniques represent the features, especially the shared ones, inaccurately because those techniques calculate a weight for each feature without considering its distribution in each class; instead, the generated weight is generated based on the distribution of the feature among all the documents. Such presumption can reduce the meaning of those features, and when those features are used to classify malware, they lead to a high false alarms.
METHOD: This study proposes a Kullback-Liebler Divergence-based Term Frequency-Probability Class Distribution (KLD-based TF-PCD) algorithm to represent the extracted features based on the differences between the probability distributions of the terms in malware and benign classes. Unlike the existing solution, the proposed algorithm increases the weights of the important features by using the Kullback-Liebler Divergence tool to measure the differences between their probability distributions in malware and benign classes.
RESULTS: The experimental results show that the proposed KLD-based TF-PCD algorithm achieved an accuracy of 0.972, the false positive rate of 0.037, and the F-measure of 0.978. Such results were significant compared to the related work studies. Thus, the proposed KLD-based TF-PCD algorithm contributes to improving the security of cyberspace.
CONCLUSION: New meaningful characteristics have been added by the proposed algorithm to promote the learned knowledge of the classifiers, and thus increase their ability to classify malicious behaviors accurately.
Fulltext Deep Ensemble Fake News Detection Model Using Sequential Deep Learning Technique

Ali AM, Ghaleb FA, Al-Rimy BAS, Alsolami FJ, Khan AI

Sensors (Basel), 2022 Sep 15;22(18).
PMID: 36146319 DOI: 10.3390/s22186970

Recently, fake news has been widely spread through the Internet due to the increased use of social media for communication. Fake news has become a significant concern due to its harmful impact on individual attitudes and the community's behavior. Researchers and social media service providers have commonly utilized artificial intelligence techniques in the recent few years to rein in fake news propagation. However, fake news detection is challenging due to the use of political language and the high linguistic similarities between real and fake news. In addition, most news sentences are short, therefore finding valuable representative features that machine learning classifiers can use to distinguish between fake and authentic news is difficult because both false and legitimate news have comparable language traits. Existing fake news solutions suffer from low detection performance due to improper representation and model design. This study aims at improving the detection accuracy by proposing a deep ensemble fake news detection model using the sequential deep learning technique. The proposed model was constructed in three phases. In the first phase, features were extracted from news contents, preprocessed using natural language processing techniques, enriched using n-gram, and represented using the term frequency-inverse term frequency technique. In the second phase, an ensemble model based on deep learning was constructed as follows. Multiple binary classifiers were trained using sequential deep learning networks to extract the representative hidden features that could accurately classify news types. In the third phase, a multi-class classifier was constructed based on multilayer perceptron (MLP) and trained using the features extracted from the aggregated outputs of the deep learning-based binary classifiers for final classification. The two popular and well-known datasets (LIAR and ISOT) were used with different classifiers to benchmark the proposed model. Compared with the state-of-the-art models, which use deep contextualized representation with convolutional neural network (CNN), the proposed model shows significant improvements (2.41%) in the overall performance in terms of the F1score for the LIAR dataset, which is more challenging than other datasets. Meanwhile, the proposed model achieves 100% accuracy with ISOT. The study demonstrates that traditional features extracted from news content with proper model design outperform the existing models that were constructed based on text embedding techniques.
Fulltext An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks

Wang Z, Zainal A, Siraj MM, Ghaleb FA, Hao X, Han S

Sci Rep, 2025 Jan 14;15(1):1917.
PMID: 39809850 DOI: 10.1038/s41598-024-85083-8

The application of artificial neural networks (ANNs) can be found in numerous fields, including image and speech recognition, natural language processing, and autonomous vehicles. As well, intrusion detection, the subject of this paper, relies heavily on it. Different intrusion detection models have been constructed using ANNs. While ANNs are relatively mature to construct intrusion detection models, some challenges remain. Among the most notorious of these are the bloated models caused by the large number of parameters, and the non-interpretability of the models. Our paper presents Convolutional Kolmogorov-Arnold Networks (CKANs), which are designed to overcome these difficulties and provide an interpretable and accurate intrusion detection model. Kolmogorov-Arnold Networks (KANs) are developed from the Kolmogorov-Arnold representation theorem. Meanwhile, CKAN incorporates a convolutional computational mechanism based on KAN. The model proposed in this paper is constructed by incorporating attention mechanisms into CKAN's computational logic. The datasets CICIoT2023 and CICIoMT2024 were used for model training and validation. From the results of evaluating the performance indicators of the experiments, the intrusion detection model constructed based on CKANs has an attractive application prospect. As compared with other methods, the model can predict a much higher level of accuracy with significantly fewer parameters. However, it is not superior in terms of memory usage, execution speed and energy consumption.