PSO_KAN: A Hybrid Particle Swarm Optimization and Kolmogorov Arnold Network for Detection DDoS Attacks in Wireless Sensor Networks

Abstract

The increasing adoption of wireless sensor networks (WSNs) has brought forth significant security challenges, particularly in mitigating distributed denial-of-service (DDoS) attacks. These attacks significantly degrade network performance by bombarding sensor nodes with high volumes of traffic, causing resource depletion and service interruptions. Due to the constrained processing capacity, memory, and energy of WSNs, they are highly susceptible to such threats, which can rapidly drain battery power, reduce communication efficiency, and jeopardize data accuracy. As a result, essential functions like real-time data collection and transmission may be disrupted, impacting critical applications such as environmental monitoring, healthcare, and industrial automation. Moreover, DDoS attacks can introduce security weaknesses, increasing the risk of further exploitation by malicious entities. This paper introduces PSO_KAN, a novel hybrid model that integrates Particle Swarm Optimization (PSO) with the Kolmogorov-Arnold Network (KAN) to improve the detection of such attacks in WSNs. Utilizing Kolmogorov’s superposition theorem; KAN decomposes complex multivariate functions into simpler univariate components. In this framework, PSO plays a key role in optimizing the choice and tuning of these univariate functions and their parameters to ensure accurate representation of attack behaviors. By harnessing PSO’s ability to perform global optimization, the proposed model delivers enhanced performance in terms of detection accuracy, scalability, and computational efficiency. The experimental findings indicate that PSO-KAN attains a remarkable accuracy of 97.5%, surpassing conventional Neural Networks (91.2%), Convolutional Neural Networks (94.5%), Long Short-Term Memory networks (95.1%), and even Neural Networks optimized with PSO (96.7%). This represents a 6.3% improvement over standard Neural Networks and a 0.8% gain compared to other PSO-enhanced models, demonstrating the superiority of the proposed method. Additionally, the model consistently achieves high Precision, Recall, and F1-Scores across various attack types, reinforcing its reliability in network security applications. These results underscore the effectiveness of the integration of PSO and KAN, providing a powerful approach for strengthening the security of WSNs against sophisticated cyber threats.

Keywords

Introduction

In recent years, wireless sensor networks (WSNs) have attracted considerable interest from both researchers and industry professionals due to their ability to monitor environmental conditions effectively. Their cost-effectiveness, ease of installation, and user-friendly attributes make them a promising alternative to conventional sensory systems. These benefits have led to their widespread adoption in numerous fields, including healthcare, telecommunications, military applications, environmental observation, and medical research [1]. WSNs function through interconnected sensor nodes, which are arranged in various topologies such as star, tree, or mesh structures [2]. These nodes play a critical role in detecting data transmission and managing communication within the network. Their primary operations include sensing, data processing, computation, and communication [3, 4]. WSNs are commonly deployed in remote and inaccessible regions to monitor natural disasters such as floods, storms, wildfires, volcanic eruptions, and earthquakes. Additionally, they are used in more routine applications, such as tracking patient health metrics, developing smart environments and cities, optimizing logistics and flow management, and enabling Internet of Things (IoT) functionalities [5, 6]. Despite their advantages, WSNs also face several limitations, particularly in terms of security. These networks are vulnerable to various security threats and attacks due to their constrained resources, such as limited battery life, memory, storage, communication bandwidth, and processing power [3]. Furthermore, since WSNs are often deployed in unattended environments, their sensing components are susceptible to significant interference and potential cyber threats. Their accessibility increases the risk of malicious attacks, which can compromise network integrity and disrupt communication. These attacks can be classified into external and internal threats. External attacks involve the introduction of a rogue node that infiltrates the closed network, whereas internal attacks occur when an authorized node is compromised and manipulated by an attacker. The nature and severity of these attacks depend on their intent and the targeted network layer [7]. Among the numerous security threats faced by WSNs, Distributed Denial-of-Service (DDoS) attacks pose a significant challenge. These attacks come in various forms but share the common objective of depleting the energy of sensor nodes, thereby preventing them from performing their designated functions. Different types of DDoS attacks include blackhole, grayhole, flooding, and scheduling attacks. In a blackhole attack, a malicious node falsely claims the role of a cluster head (CH), responsible for forwarding data from sensor nodes to the base station. Instead of relaying the collected data, the attacker intercepts and discards it. Similarly, in a grayhole attack, a malicious node acts as a cluster head but selectively drops data packets at random, forwarding only a portion of the received packets to the base station. In a flood attack, the malicious node transmits excessive cluster head advertisement messages (ADV_CH) at high power levels, causing other sensor nodes to rapidly deplete their energy reserves [8]. This forces distant nodes to use more energy to communicate with the cluster head. In a scheduling attack, the malicious node allocates overlapping data communication slots to multiple sensor nodes, resulting in packet collisions and subsequent data loss. To enhance WSN security and mitigate DDoS attacks, various machine learning and deep learning techniques have been utilized in developing Intrusion Detection Systems (IDS). Algorithms such as Support Vector Machine (SVM) [9], K-Nearest Neighbor (KNN) [10], Perceptron [11], Long Short-Term Memory (LSTM) [12], Recurrent Neural Network (RNN) [13], Convolutional Neural Network (CNN) [14], and Artificial Neural Network (ANN) [15] have demonstrated high accuracy in detecting malicious activities. However, there remains a need for more robust, interpretable, and efficient models that can provide improved security across diverse applications. This paper presents a novel approach for detecting and classifying DDoS attacks in wireless sensor networks using a hybrid model that combines Particle Swarm Optimization (PSO) with the Kolmogorov-Arnold Network (KAN). The proposed system enhances KAN’s ability to optimize univariate functions and parameters by considering each particle in the swarm as a potential solution representing a set of KAN parameters. Initially, PSO generates a population of particles with randomly assigned KAN parameters, such as weights and coefficients for univariate functions. The performance of each particle is assessed by training KAN on the dataset and evaluating its classification accuracy. The particles then refine their positions iteratively based on their own best performance and the best solution found globally, following predefined velocity and position update formulas. This optimization process steers the search towards the most effective KAN parameters, enabling the network to learn optimal function transformations for precise classification. By utilizing PSO’s global search capability, KAN effectively selects the best univariate functions and parameters to strengthen DDoS attack detection in wireless sensor networks.

The objectives of the paper are summarized as follows.

• To develop a hybrid PSO-KAN model that uses Particle Swarm Optimization (PSO) to optimize the selection and parameters of the Kolmogorov-Arnold Network’s (KAN) univariate functions. This ensures the best transformation of raw wireless sensor network (WSN) traffic data into meaningful representations that enhance classification accuracy for DDoS attack detection.
• To enhance detection accuracy and efficiency by leveraging PSO to fine-tune KAN’s parameters. The proposed system enhances KAN’s ability to optimize univariate functions and parameters by considering each particle in the swarm as a potential solution representing a set of KAN parameters.
• To reduce computational complexity through the integration of PSO with KAN, which helps in finding optimal parameters without exhaustive manual tuning

The rest of this paper is organized as follows: Section II of the paper presents the summary of the state-of-the-art approaches. Section III presents the proposed PSO-KAN framework for detection and classification of DDoS in WSN. Section IV presents the presents the experiment and results obtained. Lastly, section VI concludes the work and its findings.

LITERATURE REVIEW

This section explores and evaluates advanced techniques for detecting and predicting DDoS attacks in Wireless Sensor Networks (WSNs). To enhance node security and ensure safe communication within WSNs, researchers from both academia and industry have proposed various methods. For instance, the study in [16] assessed the effectiveness of three algorithms (Deep Neural Network (DNN), Self-Taught Learning (STL), and Recurrent Neural Network (RNN)) in identifying four types of security threats. Their evaluation, based on accuracy, precision, recall, and F1 score, utilized the KDD and NSL-KDD datasets for training and testing. Results indicated that the STL approach achieved the highest accuracy compared to the benchmarked LSTM model. In [17], researchers developed Scale-Hybrid-IDS-AlertNet, a scalable hybrid DNN framework for real-time network traffic analysis and host-level event detection to proactively identify cyber threats. Initially fine-tuned with the KDD-99 dataset, the model was later validated using multiple benchmark datasets, such as NSL-KDD, UNSW-NB15, Kyoto, WSN-DS, and CICIDS2017. The framework demonstrated a higher accuracy for binary classification as compared to multiclass classification when applied to the WSN-DS dataset. The study in [18] introduced a Deep Learning-based Defense Mechanism (DLDM) designed to detect and mitigate DoS attacks during the Data Forwarding Phase (DFP). This method enhances detection reliability for various DoS attacks, including fatigue, jamming, homing, and flooding. Extensive simulation studies showed that the approach effectively distinguished between legitimate and malicious activities, achieving high detection accuracy, improved throughput, enhanced packet delivery ratio, and optimized overall performance, while also reducing energy consumption and minimizing false alarms. Furthermore, the authors in [19] employed Long Short-Term Memory (LSTM) networks to detect different types of cyber threats, such as DDoS attacks, command injection, and network malware, achieving an accuracy of 86.9%. Their findings demonstrated that LSTM outperformed other traditional machine learning techniques, particularly in identifying untrained malware threats, highlighting its superior ability to detect previously unseen attacks. To evaluate the efficiency of machine learning algorithms in identifying and predicting DDoS attacks in WSNs, the authors of [20] implemented a Random Forest (RF) classifier to detect different types of DoS attacks within the WSN-DS dataset. Their approach yielded high F1-scores for Blackhole, Flooding, Grayhole, Normal, and Scheduling (TDMA) attacks, respectively, with a promising classification accuracy. In [21], a comparative analysis was conducted on five major machine learning classification techniques alongside one deep learning algorithm. The researchers trained an Artificial Neural Network (ANN) and five machine learning models using the dataset, applying K-fold cross-validation to enhance predictive performance. The results confirmed that machine learning techniques like Random Forest and Support Vector Machines, along with deep learning approaches such as ANN, were effective in detecting network intrusions. In [22], the Random Forest algorithm was applied to the NSL-KDD dataset, achieving a maximum accuracy of 85.34%. This classification focused on identifying various attack types, including unauthorized remote access, DoS attacks, remote superuser access, and port scanning. The study in [23] analyzed the WSN-DS dataset, a widely recognized dataset in the WSN field, using seven distinct machine learning models. Among them, the Random Forest algorithm exhibited the highest accuracy in comparison to the other algorithms. Similarly, Okur and Dener [24] investigated IoT botnet attack traffic using machine learning techniques, where the Decision Tree algorithm achieved an outstanding accuracy. In [25], researchers further analyzed the WSN-DS dataset by implementing multiple learning models and classifying data based on attack types while also documenting the False Positive Rate and False Negative Rate percentages. To further enhance the performance of Machine Learning and Deep Learning-based Intrusion Detection Systems, several studies have combined the strengths of multiple algorithms to achieve optimal detection and classification accuracy. For instance, in [26], the authors proposed a CNN-LSTM approach to detect and classify DoS intrusion attacks, including Flooding, Blackhole, Normal, TDMA, and Grayhole. Their study utilized the computer-generated WSN-DS dataset for wireless sensor network intrusion detection. The proposed model showed promising results, achieving an accuracy of 97% in detecting and classifying the attacks. In [27], the researchers introduced a hierarchical neural network model named LuNet, which integrates multiple layers of CNN and RNN to jointly learn from input data. The model was tested on both the NSL-KDD and UNSW-NB15 datasets for binary and multiclass classification tasks. On the NSL-KDD dataset, LuNet achieved a higher accuracy rates for binary classification as compared to multiclass classification.

MATERIALS AND METHODS

In this section, the conventional Particle Swarm Optimization, Kolmogorov Arnold Network and the hybrid Particle Swarm Optimization and Kolmogorov Arnold Network (PSO-KAN) for Detection DDoS attacks in Wireless Sensor Networks (WSN) is presented.

1. Particle Swarm Optimization

Particle Swarm Optimization (PSO) is an optimization technique inspired by the collective movement of birds or fish in search of food. Developed by Kennedy and Eberhart in 1995, PSO has been extensively used to solve optimization problems across different fields. It operates as a population-based method, where multiple candidate solutions, known as particles, navigate the search space to locate the best possible outcome. Each particle's position and velocity are continuously adjusted based on its own past performance and the experience of the entire group. The algorithm aims to direct particles toward the most promising solutions while preserving exploration to prevent convergence to suboptimal points.

1. Initialization and Particle Representation

Each particle i in the swarm represents a potential solution to the optimization problem in an n-dimensional search space. Each particle has a position X_i?, which indicates its current location within the search space, and velocity V_i?, which determines the direction and speed of its movement. The position and velocity of each particle is given in equation 1 and 2 below.

Xi=(Xi,1, Xi,2, ………Xi,n)    1

Vi=(Vi,1, Vi,2, ………Vi,n)       2

Initially, particles are distributed randomly throughout the search space, and their velocities are assigned random values within set limits. Each particle maintains a record of its personal best position P_b, which represents the most optimal location it has reached based on the objective function. Alongside this, the global best position G_b is determined as the most favorable position discovered by any particle within the swarm.

2. Velocity and Position Update

The velocity and positions of the particles are continuously updated to guide the particle toward an optimal solution based on both individual performance and the swarm’s collective intelligence. The particles' movement is controlled by (3) and (4), which update their velocity and position:

Vit+1=wVit+ c1r1Pb- Xit+ c2r2Gb- Xit   3

Xit+1=Xit+ Vit+1              4

Where the parameter w, known as the inertia weight, regulates the influence of a particle's previous velocity on its current movement. A larger inertia weight fosters broader exploration of the search space, whereas a smaller value enhances exploitation by refining solutions near the best-known positions. The coefficients c₁ and c₂ serve as acceleration factors, controlling the balance between a particle’s tendency to move toward its personal best position and the global best position identified by the swarm. The variables r₁ and r₂ are randomly generated within the interval [0, 1], introducing a degree of randomness to enhance the diversity of the search process and P_b represents the best position that particle i has achieved so far, while G_b denotes the optimal position found by any particle in the swarm.

3. Stopping Criteria

The PSO algorithm continues to run until a specified stopping condition is satisfied, which could be reaching a set number of iterations or attaining a predefined fitness value.

Algorithm 1 presents the Particle Swarm Optimization Algorithm

Algorithm 1: Particle Swarm Optimization Algorithm (PSO)

Kolmogorov Arnold Network

Figure 1PSO-KAN Framework

Figure 2 Distribution of WSN-DS Dataset

Figure 3 Convergence curve for different univariate functions

Figure 4 Accuracy comparison of univariate functions in PSO-KAN

Table 6 provides a comparison of various machine learning models for network attack detection, evaluating them based on their optimization techniques and accuracy percentages. The Model column includes different architectures such as PSO-KAN (Optimized), Traditional Neural Network (NN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Hybrid CNN-LSTM, and PSO-Optimized Neural Network (PSO-NN). The "Optimization Used" column specifies the optimization method applied to each model, including Particle Swarm Optimization (PSO), Backpropagation, Adam, SGD, and RMSprop. The Accuracy (%) column reflects the classification effectiveness of each model in detecting network attacks. Among the models, the PSO-KAN (Optimized) achieves the highest accuracy at 97.5%, utilizing PSO to fine-tune Knowledge-Augmented Network (KAN) parameters, which enhances learning efficiency. In contrast, the Traditional NN, which employs backpropagation, has the lowest accuracy at 91.2%, suggesting that conventional training techniques may not be as effective for this task. The CNN, LSTM, and Hybrid CNN-LSTM models demonstrate increasing accuracy levels of 94.5%, 95.1%, and 96.3%, respectively, highlighting the advantages of deep learning architectures. The PSO-Optimized Neural Network (PSO-NN) achieves 96.7%, indicating that PSO-based weight optimization significantly improves model performance. Overall, the results emphasize the effectiveness of PSO-driven optimization in enhancing neural network models for network security applications.

CONCLUSION

This paper introduces an innovative method for detecting and classifying DDoS attacks in wireless sensor networks by integrating Particle Swarm Optimization (PSO) with the Kolmogorov-Arnold Network (KAN). The proposed model enhances KAN’s capability to optimize univariate functions and parameters by treating each particle in the swarm as a candidate solution representing a specific set of KAN parameters. Initially, PSO generates a population of particles with randomly assigned parameters, including weights and coefficients for univariate functions. The effectiveness of each particle is evaluated by training KAN on the dataset and measuring its classification accuracy. Through iterative updates, particles adjust their positions based on both their individual best performance and the globally optimal solution, following predefined velocity and position update rules. The combination of Particle Swarm Optimization (PSO) and the Kolmogorov-Arnold Network (KAN) has proven highly effective in detecting DDoS attacks within Wireless Sensor Networks (WSNs). PSO enhances KAN by optimizing its univariate functions and parameters, resulting in improved feature transformation and model adaptability. This leads to a more interpretable and resilient system for recognizing attack patterns. Experimental evaluation using a dataset containing 16 features and five attack types indicates that PSO-optimized KAN surpasses conventional machine learning and deep learning models, such as Neural Networks (NN), CNNs, LSTMs, and hybrid approaches. Achieving a peak accuracy of 97.53%, PSO-KAN offers a powerful defense mechanism against emerging cyber threats in WSNs. The primary strength of PSO-KAN is its adaptability and computational efficiency. Unlike traditional deep learning models that demand extensive hyperparameter tuning and large datasets, KAN’s hierarchical framework allows it to capture meaningful feature representations with reduced computational effort. By leveraging PSO for optimizing univariate functions, the model autonomously determines the most effective transformations for traffic data, enhancing attack classification accuracy while reducing false positives. Furthermore, PSO’s global search ability helps the model avoid local optima, resulting in a more stable and generalized approach for detecting DDoS attacks across diverse network settings. Although PSO-KAN demonstrates high accuracy and adaptability, it has some limitations that require further exploration. A major concern is its computational complexity, as the combination of KAN’s hierarchical transformations and PSO’s iterative optimization can result in longer processing times, particularly when dealing with large-scale WSN datasets.                                          

REFERENCE

1. S. Salmi and L. Oughdir, “Performance evaluation of deep learning techniques for DOS attacks detection in Wireless Sensor Network,” Journal of Big Data, vol. 10, no. 1, Feb. 2023. doi:10.1186/s40537-023-00692-w.
2. H. Sadia et al., “Intrusion Detection System for Wireless Sensor Networks: A machine learning based approach,” IEEE Access, vol. 12, pp. 52565–52582, 2024. doi:10.1109/access.2024.3380014.
3. K. Haseeb, N. Islam, T. Saba, A. Rehman, and Z. Mehmood, ‘‘LSDAR: A light-weight structure based data aggregation routing protocol with secure Internet of Things integrated next-generation sensor networks,’’ Sustain. Cities Soc., vol. 54, Mar. 2020, Art. no. 101995.
4. R. Guetari, H. Ayari, and H. Sakly, ‘‘Computer-aided diagnosis systems: A comparative study of classical machine learning versus deep learningbased approaches,’’ Knowl. Inf. Syst., vol. 65, no. 10, pp. 3881–3921, Oct. 2023.
5. R. P. França, Y. Iano, A. C. Monteiro, and R. Arthur, “Intelligent applications of WSN in the world: A technological and literary background,” Advances in Intelligent Systems and Computing, pp. 13–34, 2020. doi:10.1007/978-3-030-40305-8_2
6. K. Haseeb, I. Ud Din, A. Almogren, and N. Islam, “An energy efficient and secure IOT-based WSN framework: An application to Smart Agriculture,” Sensors, vol. 20, no. 7, p. 2081, Apr. 2020. doi:10.3390/s20072081.
7. M. Dener, C. Okur, S. Al, and A. Orman, “WSN-BFSF: A new data set for attacks detection in wireless sensor networks,” IEEE Internet of Things Journal, vol. 11, no. 2, pp. 2109–2125, Jan. 2024. doi:10.1109/jiot.2023.3292209
8. Ismail et al., “A machine learning-based classification and prediction technique for ddos attacks,” IEEE Access, vol. 10, pp. 21443–21454, 2022. doi:10.1109/access.2022.3152577
9. S. Deshpande, J. Gujarathi, P. Chandre, and P. Nerkar, “A comparative analysis of machine deep learning algorithms for intrusion detection in WSN,” Studies in Systems, Decision and Control, pp. 173–193, 2021. doi:10.1007/978-981-33-4996-4_11.
10. R. Wazirali and R. Ahmad, “Machine learning approaches to detect DOS and their effect on WSNS Lifetime,” Computers, Materials & Continua, vol. 70, no. 3, pp. 4922–4946, 2022. doi:10.32604/cmc.2022.020044.
11. G. Loukas et al., “Cloud-based cyber-physical intrusion detection for vehicles using Deep Learning,” IEEE Access, vol. 6, pp. 3491–3508, 2018. doi:10.1109/access.2017.2782159.
12. M. Shurman, R. Khrais, and A. Yateem, “DOS and ddos attack detection using Deep Learning and ids,” The International Arab Journal of Information Technology, vol. 17, no. 4A, pp. 655–661, Jul. 2020. doi:10.34028/iajit/17/4a/10.
13. P. Wu, H. Guo, and R. Buckland, “A transfer learning approach for network intrusion detection,” 2019 IEEE 4th International Conference on Big Data Analytics (ICBDA), pp. 281–285, Mar. 2019. doi:10.1109/icbda.2019.8713213.
14. J. Kim, J. Kim, H. Kim, M. Shim, and E. Choi, “CNN-based network intrusion detection against denial-of-service attacks,” Electronics, vol. 9, no. 6, p. 916, Jun. 2020. doi:10.3390/electronics9060916.
15. M. Asad et al., “DeepDetect: Detection of distributed denial of service attacks using Deep Learning,” The Computer Journal, vol. 63, no. 7, pp. 983–994, Jul. 2019. doi:10.1093/comjnl/bxz064
16. Lee B, Amaresh S, Green C, Engels D. Comparative study of deep learning models for network intrusion detection””. SMU Data Science Review. 2018;1(1):8.
17. R. Vinayakumar et al., “Deep learning approach for Intelligent Intrusion Detection System,” IEEE Access, vol. 7, pp. 41525–41550, 2019. doi:10.1109/access.2019.2895334.
18. M. Premkumar and T. V. P. Sundararajan, “DLDM: Deep learning-based Defense Mechanism for denial of service attacks in wireless sensor networks,” Microprocessors and Microsystems, vol. 79, p. 103278, Nov. 2020. doi: 10.1016/j.micpro.2020.103278
19. G. Loukas et al., “Cloud-based cyber-physical intrusion detection for vehicles using Deep Learning,” IEEE Access, vol. 6, pp. 3491–3508, 2018. doi:10.1109/access.2017.2782159
20. T.-T.-H. Le, T. Park, D. Cho, and H. Kim, “An effective classification for DOS attacks in Wireless Sensor Networks,” 2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN), pp. 689–692, Jul. 2018. doi:10.1109/icufn.2018.8436999.
21. Deshpande S, Gujarathi J, Chandre P, Nerkar P. A comparative analysis of machine deep learning algorithms for intrusion detection in wsn. In: Security Issues and Privacy Threats in Smart Ubiquitous Computing, 2021; pp. 173–193.
22. M. Anwer, U. Muhammad K Farooq, F. Waseemullah, “Attack detection in IoT using machine learning,” Engineering, Technology & Applied Science Research,11 (3), 7273-727, 2021.
23. C. Okur, M. Dener, “Detection of dos attacks using machine learning methods in wireless sensor networks,” El-Cezerî Journal of Science and Engineering, 8(3), 1550-1564, 2021.
24. C. Okur, M. Dener, “M. Detecting IoT botnet attacks using machine learning methods,” 13. International Conference on Information Security and Cryptology, Ankara, 21-25, 2020.
25. R. Wazirali, R. Ahmad, “Machine Learning Approaches to Detect DoS and Their Effect on WSNs Lifetime,” Computers, Materials & Continua, 70(3), 2021.
26. S. Salmi and L. Oughdir, “CNN-LSTM based approach for DOS attacks detection in wireless sensor networks,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 4, 2022. doi:10.14569/ijacsa.2022.0130497.
27. P. Wu, H. Guo, and R. Buckland, “A transfer learning approach for network intrusion detection,” 2019 IEEE 4th International Conference on Big Data Analytics (ICBDA), pp. 281–285, Mar. 2019. doi:10.1109/icbda.2019.8713213.
28. J. Kennedy and R. Eberhart, "Particle swarm optimization," Proceedings of ICNN'95 - International Conference on Neural Networks, Perth, WA, Australia, 1995, pp. 1942-1948 vol.4, doi: 10.1109/ICNN.1995.488968.
29. Z. Liu, Y. Wang, S. Vaidya, F. Ruehle, J. Halverson, M. Solja?i?, and M. Tegmark, “KAN: Kolmogorov-Arnold networks,” arXiv preprint arXiv:2404.19756, 2024.
30. I. Almomani, B. Al-Kasasbeh, and M. AL-Akhras, “WSN-DS: A dataset for intrusion detection systems in wireless sensor networks,” Journal of Sensors, vol. 2016, pp. 1–16, 2016. doi:10.1155/2016/4731953.