Abstract
Objective. Wireless sensor networks, crucial for various applications, face growing security challenges due to the escalating complexity and diversity of attack behaviours. This paper presents an advanced intrusion detection algorithm, leveraging featureweighted Naive Bayes (NB), to enhance network attack detection accuracy. Methodology. Initially, a feature weighting algorithm is introduced to assign contextbased weights to different feature terms. Subsequently, the NB algorithm is enhanced by incorporating Jensen–Shannon (JS) divergence, feature weighting, and inverse category frequency (ICF). Eventually, the improved NB algorithm is integrated into the intrusion detection model, and network event classification results are derived through a series of data processing steps applied to corresponding network traffic data. Results. The effectiveness of the proposed intrusion detection algorithm is evaluated through a comprehensive comparative analysis using the NSLKDD dataset. Results demonstrate a significant enhancement in the detection accuracy of various attack types, including normal, denial of service (DoS), probe, remotetolocal (R2L), and usertoroot (U2R). Moreover, the proposed algorithm exhibits a lower false alarm rate compared to other algorithms. Conclusion. This paper introduces a wireless network intrusion algorithm that not only ensures improved detection accuracy and rate but also reduces the incidence of false detections. Addressing the evolving threat landscape faced by wireless sensor networks, this contribution represents a valuable advancement in intrusion detection technology.
1. Introduction
In recent years, there has been a rapid development in computer communication and networking technologies, particularly with the emergence of the Internet of Things (IoT). These advancements have introduced new and effective ways to facilitate interaction between human society and the physical world. This has led to the integration of human society, the physical world, and the computing world [1, 2]. Wireless sensor networks (WSNs), as a technology derived from microelectronics, play an irreplaceable role in important fields such as healthcare, traffic control, and natural disasters [3–5]. Furthermore, they have profound impacts on daily life, such as smart homes and modern agriculture [6, 7].
WSN is a distributed wireless network composed of a large number of lowpower sensor nodes deployed in the sensing area, communicating through wireless links [8]. These sensor nodes are miniaturized computing units with limited storage capacity, computational capabilities, and battery power [9, 10]. However, due to the openness of wireless networks and the inherent limitations of sensor nodes, WSNs face various security threats and network attacks.
To counter network attacks, existing network intrusion solutions have introduced key management and authentication mechanisms as the first line of defence to effectively withstand attacks from outside the WSN. However, by capturing nodes, attackers can gain access to confidential information inside the nodes and launch internal attacks, rendering the first line of defence ineffective against internal attacks in WSNs. Therefore, intrusion detection technology serves as a crucial second line of defence, capable of fundamentally detecting security threats and minimizing the losses caused by attacks [11]. However, due to the limitations of WSNs, traditional intrusion detection techniques cannot be directly applied to WSN environments. As a result, the research on novel intrusion detection techniques suitable for WSNs has attracted widespread attention from experts and scholars both domestically and internationally.
In order to improve the classification accuracy and algorithmic efficiency of network intrusion detection algorithms, this paper proposes a new intrusion detection method for wireless networks, that is, an improved NB algorithm utilizing JS dispersion and inverse category frequency (ICF), i.e., JINB intrusion detection algorithm. The algorithm reduces the limitations of the conditional independence assumption of NB by introducing a weighting factor for each feature term through JS scattering and ICF, resulting in the improved detection rate and detection accuracy. The main innovations of this paper are as follows:(1)The use of JS divergence to measure the weights of each feature term, highlighting the differences between different feature terms. By utilizing JS divergence, we are able to better assess the contributions of feature terms to intrusion detection, thereby improving classification accuracy.(2)The introduction of ICF to enhance the calculation of feature weights, further reducing the influence of conditional independence. Traditional intrusion detection algorithms are typically based on the assumption of Naive Bayes, where features are considered mutually independent. However, in practical scenarios, there may be certain correlations among features that can impact the accuracy of classification. Incorporating ICF allows for more accurate calculation of feature weights, reducing the impact of conditional independence on classification results and enhancing detection accuracy.
This paper is divided into five main sections as follows: the introduction, the literature review, the methodology, the analysis and discussion of results, and the conclusion.
The motivation behind this study is to enhance the security of wireless sensor networks by developing an intrusion detection algorithm that improves detection accuracy and reduces false alarms. This research aims to contribute to the evolving field of intrusion detection in WSNs.
In addition to introducing innovative technologies such as JS divergence and ICF, this study also incorporates a feature weighting algorithm. This contribution enhances the algorithm’s sensitivity to different features, aiding in better discrimination and utilization of various features, thereby improving the accuracy of intrusion detection. Furthermore, this study combines the improved Naive Bayes (NB) algorithm with an intrusion detection model and applies it to the corresponding network traffic data processing. This leads to an overall performance enhancement, resulting in higher detection accuracy when facing various attack types.
2. Literature Review
In the existing literature, various intrusion detection models and algorithms have been proposed for different network environments and challenges. Zhao et al. proposed an intrusion detection model based on a deep artificial neural network with backpropagation (DANBP) [12]. It is tailored for handling massive, complex, and multidimensional network data. The primary aim is to address the need for effective intrusion detection in such environments. Similarly, Maheswari and Arunesh present a new hybrid multilevel intrusion detection model that focuses on improving the detection rate of specific attack behaviours, including probe, U2R, and R2L [13]. The model combines the Knearest neighbor (KNN) outlier detection algorithm with network traffic similarity to achieve accurate detection without interference from anomalous behaviours.
In the context of resourceconstrained intrusion detection systems (IDS) in wireless sensor networks (WSNs), Huang and Zhu proposed a dynamic multistage intrusion detection model with a gametheoretic approach [14]. This model predicts the most vulnerable nodes to intrusion and incorporates Bayesian rule analysis to identify malicious nodes. Another improvement in intrusion detection is presented by Wang et al. [15], where an algorithm based on integration learning is introduced. This algorithm addresses the limitations of integrated learning intrusion detection methods, such as loss of edge information and timeconsuming model fusion. By transforming the original problem into multiple binary classification problems and incorporating probabilistic prediction results, the algorithm achieves better performance.
While deep neural networks and integrated learning methods [16, 17] may not be suitable for certain network structures and computational limitations [18], alternative approaches have been explored. For example, Jaber and Rehman proposed a cloud computingbased intrusion feature extraction method for ship communication networks [19]. This method utilizes signal processing techniques and a feature detection framework to extract relevant features. A network intrusion detection method based on an improved random forest classifier is introduced by Zhang et al. [20]. The method utilizes Gaussian mixture models and random forest classifiers to extract intrusion features.
Ling et al. used a rough set theory to enhance intrusion detection models based on artificial immunity [21]. This method combines anomaly detection and misuse detection, achieving vaccine injection without terminating the intrusion detection behavior. In addition, Ling et al. introduced a Kmeans algorithm to address the clustering issue and local optima problems [22]. Although these methods demonstrate improvement in detection performance, challenges related to outliers and unbalanced clustering remain.
To tackle the issue of low efficiency caused by a large amount of data, Wang et al. combined adaptive affinity propagation (AP) clustering with intrusion detection [23]. This adaptive AP clustering algorithm reduces the number of samples to be clustered, resulting in decreased clustering time and continuous model adjustment. Duan and Xiao proposed an improved fuzzy Cmeans clustering algorithm, which uses the Mercer kernel and Lagrange multiplier method for enhanced optimization and convergence speed [24]. However, the impact of unbalanced clustering and noise points on clustering results is not addressed.
Moreover, recent research has explored innovative approaches for intrusion detection. For instance, a vehicularedge computing fogging scheme is proposed by Mourad et al. [25], which offloads intrusion detection tasks to federated vehicles, considering their high mobility and resource availability. Rahman proposes a privacypreserving joint learning scheme for IoT intrusion detection [26], where devices train their own models to maintain privacy and securityaware data. Deep learning models with recurrent neural network (RNN) with long shortterm memory (LSTM) and gated recurrent unit (GRU) frameworks were developed by Gautam et al. [27]. This model can overcome the problem of longer dependencies in RNN models. However, the effectiveness of these models in classifying certain types of attacks remains a challenge.
The Naive Bayesian classifier (NBC) [28] has gained popularity in intrusion detection due to its simplicity and effectiveness. Various enhancements for the NB algorithm have been proposed. For instance, Alsaadi et al. effectively applied the NB model in IDS and established a framework for the primary intrusion detection process [29]. Alsharif adopted a PCAbased NB algorithm that reduces data redundancy and improves detection efficiency [30]. Zhang et al. constructed a network intrusion detection model based on the NB algorithm and the quantum particle swarm optimization (QPSO) algorithm [31], which performs feature selection and parallelized NB classification. However, the detection rate of lowfrequency and smallsample type data still needs improvement in this method. Panigrahi et al. proposed an extension of the NB algorithm that combines feature simplification and decision tree techniques to improve classification efficiency and accuracy [32]. Nevertheless, this approach introduces interference in the classification of anomalous events. A semisupervised NB algorithm is introduced by Hara and Shiomoto [33], which leverages parallel computing to handle large amounts of network data. However, this algorithm exhibits shortcomings in detecting anomalous data in smallsized and mediumsized local area networks. Addressing the need for efficient intrusion detection, Li et al. presented the locally weighted Naive Bayesian (LWNB) algorithm [34]. This algorithm gradually reduces the feature space and divides it into subspaces for classification using a NB classifier. While this design improves classification speed and correctness, it requires complex preprocessing and increases time and space complexity. Jiang et al. proposed a novel weight calculation method based on the original NB approach [35]. This method estimates feature values derived from network data and significantly eliminates interference data, leading to improved classifier accuracy and recall rate. However, the algorithm still faces challenges related to feature attribute value extraction and the stability of classifier performance.
In summary, the literature review highlights various approaches to intrusion detection, including DANBPbased models, hybrid multilevel models, dynamic multistage models, integration learning algorithms, cloud computingbased methods, improved random forest classifiers, rough setbased models, and extensions of the NB algorithm. While these methods demonstrate advancements in intrusion detection, challenges such as outliers, unbalanced clustering, computational limitations, and classification of specific attack types still persist. Future research should focus on addressing these challenges to further enhance intrusion detection techniques.
3. Methodology
A feature weighting algorithm is employed to enhance the classification accuracy by assigning weights to different feature terms based on their relevance to the situation. This approach calculates each feature’s weight by deriving a weighting factor through JS divergence and ICF.
The JINB algorithm is used to obtain the classification results of network events by performing a series of processes on the corresponding network traffic data (Figure 1).
3.1. NB Classifier
Given a training sample set , where element represents each data record and denotes the xth feature. denotes the xth attribute variable of the sample set. Consider a test sample set , and the mapping function f: indicates that any data record is classified as a category label in C. Suppose is a test sample set, then we calculate the probability that instance belongs to category and obtain the calculation result set Then, the maximum element in set U is further obtained, and the test instance is finally classified as .(1)We calculate the occurrence of category c in the sample set U as follows: where is the category to which the sample belongs to and is the symbolic function for determining and .(2)We compute feature for sample category c in the set P. If attribute is discrete, then we have where is the yth feature of the training sample instance . If the attribute is a continuous value, then we have(3)Then, we count the occurrence of feature in U as follows:(4)We calculate the probability that belongs to category as Among them, is the sample to be measured and is the sample size.(5)From equation (7), it is possible to calculate for sample within the range of , which results in a derived value. . The z probability values are normalized and sorted to obtain the similarity of the sample . The maximum posterior probability WU is thus obtained as follows:(6)The definition of the NB classifier can be calculated from the abovementioned results as
3.2. JS Divergence
Weight (x, y) is the weight of in ; that is, it measures the significance of the feature to category in classification. The NB equation is thus improved as shown in the following equation:
The difference between the probability distribution of and the probability distribution in the sample set with feature can be considered. According to literature [36], the KL (Kullback–Leibler) divergence is used to indicate the importance of the features.
The limitations are evident from the KL divergence calculation in equation (9), which cannot be regarded as a metric in the true sense. Second, the range of its results is not bounded. In this paper, JS divergence [37] is introduced to make up for deficiencies. Since JS divergence possesses symmetry, it serves as a true distance metric. Moreover, its values range from 0 to 1, making it more precise and convenient for similarity assessment. Therefore, employing JS divergence to compare the difference in distance between two probability scenarios assigns appropriate weights to feature items, enabling a better evaluation of the contribution of feature items to intrusion detection.
W_{JS} (x, y) is the JS weighting factor of in category .
The calculation of W_{JS} (x, y) can be derived by subsuming equation (9) into equation (10). From equation (11), it can be observed that if the distribution of feature is more dispersed, the JS weighting factor for becomes smaller.
3.3. Anticategory Frequency
Since feature terms representative of a particular category occur in a small number of classes, it can be further improved by using ICF [38].
The inverse category frequency and feature entropy are introduced into the calculation of feature weights in sample classification. The category frequency (CF) is the number of categories in which feature occurs.
The calculation equation of anticategory frequency ICF is similar to IDF, which can be represented as follows:
The introduction of ICF in feature weighting is based on the assumption that the fewer the number of categories in which a feature appears, the greater the amount of category information it carries. This assumption is called the ICF assumption, which focuses on low and mediumfrequency features at the category level while suppressing highfrequency features. However, ICF only considers the distribution of features between categories and does not consider the distribution of features within each category. If a feature term exhibits a more balanced distribution within a class, it signifies greater representativeness of that class. This indicates a higher capability for class differentiation, warranting a larger weight assignment across all samples belonging to that class. Conversely, if a feature term is concentrated in only a few samples within a class, it does not effectively capture the characteristics of the class. Feature terms with low category differentiation ability should be assigned lower weights. The analysis shows that the size of the entropy value of the distribution of feature terms within a class is consistent with the amount of categorical information that the feature term can provide.
The term entropy of the feature in the class is defined as follows:where represents the total number of frequencies of feature occurring in the samples of class .
well reflects the distribution of feature terms within the class, and its value is proportional to the category differentiation ability of the feature. Based on the abovementioned analysis, this section introduces the XCF and factors into the feature weight calculation and proposes two new feature weight calculation schemes, namely, and .(a)The equation for the program is as follows: In contrast to , is a hybrid feature weighting model. XCF factors are calculated at the category level, and factors measure the distribution of features within classes.(b)The program is calculated as follows: where is the number of samples in which feature appears in the positive class. c is the number of samples in which feature appears in the negative class. It can be seen that the scheme contains four factors. The is the original feature frequency. The factor measures the distribution of feature between positive and negative correlation categories. The XCF factor measures the distribution of feature between categories. The factor is a measure of the distribution of features within classes.
3.4. Algorithm Description
By combining the aforementioned weighting factors, W_{JS} and W_{ICF}, the feature weights, denoted as weight, can be calculated.
The steps of the JINB algorithm are as follows.

Referring to the process outlined in Algorithm 1, we can analyze the time and spatial complexity of the JINB algorithm proposed in this paper. The time complexity of the JINB algorithm can be approximated as O (z + z z + z + z ), which can be simplified to O (z z + z ). Regarding the space complexity, it refers to the additional storage space required during the execution of the algorithm, primarily for storing the training sample set U and variables used for calculations. Assuming that the sizes of other variables are negligible compared to z, the space complexity of the JINB algorithm can be approximated as O (z).
4. Result Analysis and Discussion
4.1. Experimental Dataset
The NSLKDD dataset is used for the experiments in this paper. The NSLKDD dataset is a modified version of the KDD Cup 1999 dataset, which was created for the purpose of evaluating intrusion detection systems. It was developed to overcome some of the limitations and issues found in the original KDD Cup 1999 dataset, which had problems related to redundancy and repetitive data records. It provides a diverse set of network traffic data with various types of attacks, making it a valuable resource for researchers and practitioners in the field of cybersecurity. The distribution of NSLKDD across different attack categories is illustrated in Table 1.
The experimental setup involved a Windows 10 PC equipped with an Intel Core i79750H CPU running at 2.60 GHz and 8 GB of RAM. The algorithms proposed in this paper were implemented using Python 3.7.3. The simulation experiments were conducted using the publicly available NSLKDD dataset, which served as the dataset for this study. The experimental parameters of the algorithm in this paper are set as follows. The number z of categories C is set to 5, due to the 4 attack types (DoS, Probe, R2L, and U2R) and normal state. The number of sample instances is shown in Table 1, and the number of sample J is 132427.
The steps for data preprocessing are as follows:(1)Data collection: first, the NSLKDD dataset was obtained for the experiments(2)Data cleaning: the data were cleaned to check for missing values, duplicate records, or inconsistencies(3)Data exploration: exploratory data analysis (EDA) techniques were employed to gain indepth insights into the dataset’s features and the distribution of attacks across different categories.(4)Data partitioning: the dataset was divided into a training set and a testing set, with the partitioning carried out using the KDD Train +_20Percent.TXT and KDD Test +.TXT files, respectively.
4.2. Experimental Evaluation Methods
The intrusion detection system evaluation index is calculated by the confusion matrix, and its main evaluation index is divided into accuracy rate (Acc), detection rate (DR), false alarm rate (FAR), and missing alarm rate (MAR).
Acc is a measure of overall performance that takes into account all samples correctly classified, but it does not provide detailed information about the accuracy of intrusion detection. DR focuses on intrusion detection accuracy, which measures the extent to which the classifier correctly detects actual intrusions. FAR and MAR are associated with false positives and false negatives and typically exhibit a negative correlation. Reducing FAR may lead to an increase in MAR, and vice versa, representing a tradeoff. When evaluating intrusion detection systems, it is common to strike a balance between FAR and MAR to reduce false positives while minimizing false negatives, thereby enhancing DR and accuracy.
Their calculation equations are as follows:where NU is the number of abnormal traffic data samples classified as abnormal. NT is the number of normal traffic data samples classified as normal. FU is the number of normal traffic data samples classified as abnormal. FT is the number of abnormal traffic data samples classified as normal. The confusion matrix is shown in Table 2.
The main types of attacks in WSN networks are black hole attacks, gray hole attacks, flooding attacks, replay routing attacks, and wormhole attacks [39]. The following four types of attacks are included in the NSLKDD dataset: denial of service attacks (DoS) [40], sniffing attacks (probe) [41], unauthorized access from a remote machine to a local machine (R2L) [42], and unauthorized access to local superuser (root) privileges (U2R) [43].
4.3. Experimental Results and Analysis
4.3.1. Algorithm Comparison Experiment
The experiments in this section are conducted using the LIB MATLAB simulation platform. To validate the performance of the JINB intrusion detection algorithm, a series of simulation experiments are conducted. These experiments involve a comparative analysis between the algorithm proposed in this paper and other existing algorithms. Furthermore, the proposed misuse detection module and anomaly detection module are individually simulated to evaluate their effectiveness in detecting specific types of attacks. The experiments in this subsection test the NSLKDD dataset using OAA (one against all) [44], SVM (support vector machine), IBT (improved binary tree), HNB (hidden Naive Bayesian) [45], XLSTM [46], and the proposed algorithm. Each group of experiments uses the tenfold crossover method to find the Acc, DR, FAR, and MAR of different attack types and finally takes the corresponding average value as the experimental result. The final experimental results are shown in Table 3.
The JINB algorithm is compared with other mainstream algorithms (OAA, SVM, IBT, HNB, and XLSTM) in terms of intrusion detection, and the results are measured using accuracy, DR, FAR, and MAR (see Figure 2).
(a)
(b)
(c)
(d)
As seen in Figure 2(a), the detection accuracy of the JINB algorithm has improved more significantly. From Figure 2(b), we can see that in terms of the detection rate, the detection rate of various intrusion types has been improved except for DoS, which is slightly lower than that of the HNB method. Figure 2(c) illustrates that the JINB algorithm has significantly reduced the false alarm rate compared to each of the other intrusion types, except for DoS and R2L. Figure 2(d) illustrates that the JINB algorithm has a significantly lower false alarm rate for each intrusion type than the other compared algorithms.
To assess the growth ratio, which reflects the relationship of detection rates between the JINB algorithm and various algorithms for different types of network attacks, Table 4 demonstrates the proportional comparison of the JINB algorithm with the OAA, SVM, IBT, HNB, and LSTM algorithms. Here, the growth ratio is calculated by comparing the detection rate of the JINB algorithm to that of various reference algorithms in the context of different network attack types. The calculation involves determining the difference between the detection rate of the JINB algorithm and the detection rate of each reference algorithm. This difference is then divided by the detection rate of the reference algorithm, and the result is multiplied by 100 to obtain a percentage representation.
By looking at Table 4, it is clear that(1)In the detection of normal and R2L attacks, the growth ratio is not much different.(2)The growth ratio reaches the maximum when detecting probe attacks, reaching 46.5%. This shows a very large growth ratio compared to the detection of normal, DoS, R2L, and U2R, and the growth ratio increases as the number of samples is smaller than the sample set. However, it decreases in U2R, which may be caused by the small percentage and insufficient data samples.
Normal detection and DoS, probe, R2L, and U2R attack types are compared under these five algorithms, and the ROC curve of experimental results is obtained, as shown in Figures 3(a)–3(e).
(a)
(b)
(c)
(d)
(e)
The variation of DR and FAR of the five algorithms for different kinds of attacks can be more intuitively seen by observing Figure 3. The detection effect of the proposed algorithm is significantly higher than the other four compared algorithms as shown by the ROC graph. The detection effect of the algorithm in this paper is more intuitively shown as the data imbalance rate increases.
Finally, an observation of the detection times recorded for the five algorithms (as shown in Table 5) reveals that the proposed algorithm has significantly reduced the time complexity. In particular, the reduction in time is larger when testing, and the exact calculation yields a 52% reduction in testing time relative to OAA. Compared to XLSTM, the training time and detection time of the algorithm in this paper are reduced by 48.9% and 55.5%, respectively.
The time complexity includes the training time for the classifier corresponding to the algorithm and the detection time for the algorithm to perform the attack detection, and the time complexity is expressed as shown in the following equation:
Based on the abovementioned simulation environment, intrusion detection is simulated using NS2. NS2 records the actions of each packet at every link and node during the simulation using a specific format trace file. It is instrumental in simulating probabilistic broadcast schemes for conventional ad hoc networks, intelligent routing protocols for wireless sensor networks, and routing protocols for flying ad hoc networks (FANETs).
As the quantity of malicious nodes in the network grows, the network topology becomes more intricate and the network is subjected to more DoS attacks, causing the detection rates of various algorithms to decline. The proposed algorithm resolves diversity and outlier sensitivity issues. This enhances its generalization capacity, making it outperform other comparative algorithms in this paper. Even when there are more malicious nodes, the algorithm in this paper has a good performance (as shown in Figure 4).
4.3.2. Network Energy Efficiency Analysis
As shown in Figures 5 and 6, the average remaining energy of the network nodes and the number of surviving nodes change over time for OAA, SVM, IBT, HNB, XLSTM, and the proposed algorithm. The network survival time is the longest for OAA defence because there is no additional energy consumption. HNB defence requires two modules to be turned on at the same time, which leads to a sharp increase in the energy consumption of the cluster head nodes and reduces the survival time of the network. In contrast, JINB defence only turns on one detection module at a time. SVM defence, IBT defence, and XLSTM defence activate a similar number of intrusion and misuse detection modules during network attacks and defence. This leads to comparable energy consumption and similar average energy and survival number curves of network nodes.
Experiments have proven that the JINB defence strategy effectively extends the survival time of the network and balances the accuracy and energy efficiency of the intrusion detection system.
The proposed intrusion detection algorithm based on featureweighted NB improves the detection accuracy of network attacks in wireless sensor networks. By integrating a feature weighting algorithm, Jensen–Shannon divergence, and inverse category frequency, the algorithm enhances the performance of the Naive Bayes classifier. This allows for realtime processing of network events using the corresponding network traffic data, resulting in a significant improvement in the detection accuracy for various attack types. Therefore, the proposed model provides practicality for realtime network intrusion detection. Furthermore, the proposed intrusion detection algorithm based on featureweighted NB offers costeffectiveness in network security. By improving the detection accuracy and reducing false detections, the algorithm enhances the effectiveness of network attack detection. This leads to cost savings by minimizing expenses related to false alarms and mitigating potential losses from undetected attacks. In addition, the algorithm utilizes existing network traffic data and incorporates weighting factors without imposing significant resource requirements. This makes it costeffective to implement and integrate into existing systems. The algorithm’s realtime event processing capability further contributes to its costeffectiveness by enabling prompt responses to detected attacks. Overall, the proposed model provides a costeffective solution for enhancing the security of wireless sensor networks.
5. Conclusion
The security of wireless sensor networks is facing various challenges. To improve the detection accuracy of network attacks, an improved intrusion detection algorithm based on featureweighted NB is proposed in this paper. A feature weighting algorithm is proposed by assigning corresponding weights to different feature terms according to the situation. The Jensen–Shannon (JS) divergence is combined with feature weighting and inverse category frequency (ICF) to improve the Naive Bayes algorithm. In the experimental session, the algorithm of this paper is compared and analyzed with other algorithms on the NSLKDD dataset. The results show that the wireless network intrusion algorithm proposed in this paper can ensure improved detection accuracy and detection rate, while reducing the false detection rate.
The limitations of this study are related to the algorithm’s performance in the data preprocessing stage. Specifically, (1) the discretization and normalization abilities of the algorithm require improvement. To enhance the algorithm’s stability and adaptability, future work should focus on analyzing and implementing more effective data preprocessing methods. (2) The study acknowledges the need to develop a threat model for evaluating the algorithms’ performance in reducing system threat metrics. This development will comprehensively assess the algorithms’ effectiveness in realworld threat scenarios. In the future, we will comprehensively discuss realtime computing efficiency checks and possibilities, including an exploration of the applicability in broader network environments and largescale deployments.
Data Availability
The data used to support the findings of this study are available from the corresponding author upon request.
Conflicts of Interest
The author declares that there are no conflicts of interest.
Acknowledgments
This work was supported by the Henan Vocational College of Tuina.