Earticle

Deep reinforcement learning can effectively address resource allocation in wireless networks. However, its learning speed may be slower in more complex networks and a new policy should be learned for a newly-arrived system due to a lack of network adaptability. To address these issues, we propose a federated learning framework for resource allocation in wireless networks with multiple systems. It accelerates the learning speed by aggregating the policy at each system into a central policy and ensures network adaptability by using the central policy. Through experiments, we demonstrate that our proposed framework achieves both learning acceleration and network adaptability.

Neural Network Learning (NNL) is compute-intensive. It often involves a dropout technique which effectively regularizes the network to avoid overfitting. As such, a hardware accelerator for dropout NNL has been proposed; however, the existing method encounters a huge transfer cost between hardware and software. This paper proposes Slightly-Slacked Dropout (SS-Dropout), a novel deterministic dropout technique to address the transfer cost while accelerating the process. Experimental results show that our SS-Dropout technique improves both the usual and dropout NNL accelerator, i.e., 1.55 times speed-up and three order-of-magnitude less transfer cost, respectively.

This research presented an implementation of autostereoscopic virtual three-dimensional (3D) button device as non-contact style. The proposed device has several characteristics about visible feature, non-contact use and artificial intelligence (AI) engine. The device was designed to be contactless to prevent virus contamination and consists of 3D buttons in a virtual stereoscopic view. To specify the button pressed virtually by fingertip pointing, a simple deep learning network having two stages without convolution filters was designed. As confirmed in the experiment, if the input data composition is clearly designed, the deep learning network does not need to be configured so complexly. As the results of testing and evaluation by the certification institute, the proposed button device shows high reliability and stability.

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

Virtual network embedding plays a vital role in network virtualization, as it determines the deployment and connection of virtual networks to the physical network in the 5G and beyond. An efficient virtual network embedding algorithm is essential to ensure that virtual networks are embedded in a way that meets the performance, security, and resource requirements of the virtual networks and their users. The integration of reinforcement learning with virtual network embedding can lead to more intelligent and efficient network management, which can enhance the performance of large-scale networked systems. Reinforcement learning has the potential to improve and overcome some limitations of traditional algorithms, such as the need for prior knowledge of network conditions and the difficulty in dealing with non-linear and dynamic network environments. Therefore, we conducted this survey to provide a comprehensive overview and examine potential future directions for the optimal reinforcement learning-based virtual network embedding solutions. However, applying reinforcement learning directly to virtual network embedding is a challenging task that requires further research and study. Additionally, it encourages researchers to examine the potential of reinforcement learning in virtual network embedding, identify the challenges for its application, and cover various factors related to the reinforcement learning application in virtual network embedding, including motivations, performance metrics, and challenges.

This paper presents a systematic review of deep learning (DL) techniques for Network-based Intrusion Detection Systems (NIDS) based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses: (PRISMA2020) guidelines. It explores recent advancements in data preparation, DL architectures, and performance evaluation metrics for NIDS. The review provides insights into various datasets and tools used in the field, highlighting the effectiveness of DL in improving NIDS performance. Additionally, it discusses the applications of NIDS across different industries and identifies emerging research trends, offering a comprehensive resource for researchers and practitioners in cybersecurity.

Reinforcement learning (RL) has been used in combination with cooperative caching to deal with growing traffic in mobile networks, but the performance of RL based caching policies depends heavily on network settings. This paper investigates the impact of access delays within network infrastructures and popularity and similarity properties of the contents requested on network performance. A deep Q-network based caching framework is established in both basic and extended cooperative edge networks. Our simulation results reveal explicit relationships between the performance and influential parameters, which can provide a guidance and benchmark for the design of effective caching polices with RL and cooperation technologies.

In real time applications, due to their effective cost and small size, wireless networks play an important role in receiving particular data and transmitting it to a base station for analysis, a process that can be easily deployed. Due to various internal and external factors, networks can change dynamically, which impacts the localisation of nodes, delays, routing mechanisms, geographical coverage, cross-layer design, the quality of links, fault detection, and quality of service, among others. Conventional methods were programmed, for static networks which made it difficult for networks to respond dynamically. Here, machine learning strategies can be applied for dynamic networks effecting self-learning and developing tools to react quickly and efficiently, with less human intervention and reprogramming. In this paper, we present a wireless networks survey based on different machine learning algorithms and network lifetime parameters, and include the advantages and drawbacks of such a system. Furthermore, we present learning algorithms and techniques for congestion, synchronisation, energy harvesting, and for scheduling mobile sinks. Finally, we present a statistical evaluation of the survey, the motive for choosing specific techniques to deal with wireless network problems, and a brief discussion on the challenges inherent in this area of research.

Even though mainly statistical methods have been used in anomaly network intrusion detection, to detect various attack types, machine learning based anomaly detection was introduced. Machine learning based anomaly detection started from research applying traditional learning algorithms of artificial intelligence to intrusion detection. However, detection rates of these methods are not satisfactory. Especially, high false positive and repeated alarms about the same attack are problems. The main reason for this is that one packet is used as a basic learning unit. Most attacks consist of more than one packet. In addition, an attack does not lead to a consecutive packet stream. Therefore, with grouping of related packets, a new approach of group-based learning and detection is needed. This type of approach is similar to that of multiple-instance problems in the artificial intelligence community, which cannot clearly classify one instance, but classification of a group is possible. We suggest group generation algorithm grouping related packets, and a learning algorithm based on a unit of such group. To verify the usefulness of the suggested algorithm, 1998 DARPA data was used and the results show that our approach is quite useful.

Our paramount task is to examine and detect network attacks, is one of the daunting tasks because the variety of attacks are day by day existing in colossal number. The program proposed detects botnet attacks using the newest CSE-CIC-IDS2018 cyber dataset published by the Canadian Cybersecurity Establishment (CIC). The cyber dataset can be accessed on AWS (Amazon Web Services). The realistic network dataset consists of all the modern and existing attacks such as Brute-force attacks and password cracking, Heartbleed, Botnet, DoS (Denial of Service), DDoS also known as Distributed Denial of Service, Web attacks i.e. vulnerable web app attacks, and infiltration of the network from inside. The objective of the proposed research is to identify a classification of Botnet attacks. Botnet attack is a Trojan Horse malware attack that poses a serious security threat to the banking and financial sectors. Since a specific classifier could possibly work for such datasets it is crucial to finish a comparative examination of classifiers in order to achieve the most noteworthy execution in such basic detection of network attacks. The proposed framework is to incorporate different classifier methods such as KNearset Neighbor classifier, Naive Bayes, Adaboost with Decision Tree, Support Vector Machine classifier, Random Forest classifier, and Artificial Intelligence to distinguish a portrayal of botnet attacks on the recent and realistic cyber dataset CSE-CIC-IDS2018. The results of the classification are given as precise precision for the specific classifiers. And furthermore, the proposed framework uses the Calibration curve as a standard approach in analytical methods which generates reliability diagrams to check the predicted probabilities of various classifiers are well-calibrated or not. Finally, the displayed graph proves how well the artificial intelligence technique outperforms all other classifiers which generates reliability diagrams to check the predicted probabilities of various classifiers are well-calibrated or not.

Hydraulic actuators are important in modern industry due to high power, fast response, and high stiffness. In recent years, hybrid actuation system, which combines electric and hydraulic technology in a compact unit, can be adapted to a wide variety of force, speed and torque requirements. Moreover, the hybrid actuation system has dealt with the energy consumption and noise problem existed in the conventional hydraulic system. Therefore, hybrid actuator has a wide range of application fields such as plastic injection-molding and metal forming technology, where force or pressure control is the most important technology. In this paper, the solution for force control of hybrid system is presented. However, some limitations still exist such as deterioration of the performance of transient response due to the variable environment stiffness. Therefore, intelligent switching control using Learning Vector Quantization Neural Network (LVQNN) is newly proposed in this paper in order to overcome these limitations. Experiments are carried out to evaluate the effectiveness of the proposed algorithm with large variation of stiffness of external environment. In addition, it is understood that the new system has energy saving effect even though it has almost the same response as that of valve controlled system.

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

The development of a fast, accurate, and inexpensive position-controlled pneumatic actuator that may be applied to various practical positioning applications with various external loads is described in this paper. A novel modified pulse-width modulation (MPWM) valve pulsing algorithm allows on/off solenoid valves to be used in place of costly servo valves. A comparison between the system response of the standard PWM technique and that of the modified PWM technique shows that the performance of the proposed technique was significantly increased. A state-feedback controller with position, velocity and acceleration feedback was successfully implemented as a continuous controller. A switching algorithm for control parameters using a learning vector quantization neural network (LVQNN) has newly proposed, which classifies the external load of the pneumatic actuator. The effectiveness of this proposed control algorithm with smooth switching control has been demonstrated through experiments with various external loads.

This study presents a new learning algorithm that combines convolutional neural networks (CNNs) with transfer learning to efficiently remove additive white Gaussian noise. The algorithm uses transfer learning to reduce training time by initializing with the weights of a pre-trained model and applies multiscale learning to improve noise removal while preserving the original image's detailed structure. Images for transfer learning are generated using the local steering kernel and modified steering kernel filter, which capture both local and nonlocal information and effectively preserve key structural elements, such as borders and textures. Experimental results show that the proposed algorithm outperforms traditional filtering techniques and other deep learning-based methods in restoration experiments at various noise levels on the Set12 data set. Quantitative evaluation using peak signal to noise ratio (PSNR) confirms that the algorithm achieves high PSNR values and demonstrates strong restoration performance in most noisy environments.

Zero-day attacks threaten IoT security as signature-based detection fails against novel exploits. This paper proposes a hybrid Intrusion Detection System integrating unsupervised anomaly detection, non-parametric Siamese-based cross-dataset dissimilarity filtering, and Proximal Policy Optimization (PPO)-based adaptive defense. Unsupervised models isolate anomalous traffic, Siamese-based correlation extracts structurally rare zero-day candidates, and the PPO agent learns optimal defense policies via environmental feedback. Evaluations on CIC-IoT-2023 and CIC-BCCC-NRC-TabularIoTAttacks-2024 demonstrate 99.28% training accuracy, 99.07% unseen attack accuracy, and 93.94% zero-day detection rate with 0.50 ms latency and 2.21% false-positive rate, providing a scalable, proactive, self-learning defense architecture for autonomous IoT cybersecurity.

The Internet is now of the fastest growing areas of telecommunications and of Computer Assisted Language Learning. It is rapidly becoming more integrated into society and accessible to people form around the world. A number of educators believe there is potential for language teaching and learning opportunities through the Internet, and have already developed uses and resources for this purpose. The range of what is available is growing continually. The purpose of this study is to research CMC via the Internet and other long-distance networks, to investigate the analyse best and worst things about studying English on the internet and to suggest some findings from the comparison between internet and classroom learning by means of questionnaire.

We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the LMPF method can decrease the information loss effectively because of its "learning" ability. Experiments on ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those previous methods to a great extent.

This paper introduces a Deep Reinforcement Learning (DRL)-based framework to enhance Network Function Parallelism (NFP) in Mobile Edge Computing (MEC). Leveraging Network Function Virtualization (NFV), the proposed framework optimizes service delay by solving a fairness-aware throughput maximization problem for service function chain placement. It aims to maximize the long-term cumulative reward while satisfying Quality of Service (QoS) requirements. The framework also preserves resources for future requests by efficiently managing the initialized network functions distribution. Simulation results demonstrate the superior performance of the proposed framework across various metrics. Specifically, our framework improves the average delay and deployment rate by 1.2% and 2.4% compared to the existing best method.

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

Recent advances in communications technologies have paved the way for integrating communication and sensing functionalities into unmanned aerial vehicle (UAV) networks by using reconfigurable intelligent surfaces (RIS). In this paper, we propose a novel approach to maximize the sum rate of RIS-assisted UAV networks by using an integrated sensing and communications (ISAC) network in conjunction with deep reinforcement learning (DRL). The integration of UAVs with ISAC networks results in dynamic and unpredictable channel conditions, which reduces the effectiveness of traditional optimization techniques. To address this challenge, we develop a DRL-based sum-rate maximization algorithm that adaptively configures the beamforming matrix and RIS phase shifts to optimize the communication performance while achieving the signal-to-noise ratio required for sensing. Our simulation results indicate that the proposed algorithm significantly outperforms the existing methods in terms of sum rate while accommodating the dynamic nature of the ISAC-UAV network.