Magnetic flux leakage (MFL) detection of rail surface defects is an important research field for railway traffic safety. Due to factors such as magnetization and material, it can generate background... Show More

Magnetic flux leakage (MFL) detection of rail surface defects is an important research field for railway traffic safety. Due to factors such as magnetization and material, it can generate background noise and reduce detection accuracy. To improve the detection signal strength and enhance the detection rate of more minor defects, a signal filtering method based on minimum entropy deconvolution is proposed to denoise. By using the objective function method, the optimal inverse filter parameters are calculated, which are applied to the filtering detection of MFL signals of the rail surface. The detection results show that the peak-to-peak ratio of the defect signal and noise signal detected by this algorithm is 2.01, which is about 1.5 times that of the wavelet transform method and median filtering method. The defect signal is significantly enhanced, and the detection rate of minor defects on the rail surface can be effectively improved.

To address the problems of existing passenger flow prediction methods such as low accuracy, inadequate learning of spatial features of station topology, and inability to apply to large networks, a... Show More

To address the problems of existing passenger flow prediction methods such as low accuracy, inadequate learning of spatial features of station topology, and inability to apply to large networks, a SAE-GCN-BiLSTM-based passenger flow forecasting method for urban rail transit is proposed. First, the external features are extracted layer by layer using stacked autoencoder (SAE). Then, graph convolutional network (GCN) is used to capture the spatial features of station topology, and bi-directional long and short-term memory network (BiLSTM) is used to extract the bi-directional temporal features, realizing the extraction of the spatio-temporal features. Finally, external features and spatio-temporal features are fused for accurate prediction of urban rail transit passenger flow. The experimental results show that the proposed method is higher than several other advanced models in the evaluation indexes under different granularities, indicating that the model effectively develops the accuracy and robustness of urban rail transit passenger flow prediction.

The increasing integration of renewable energy sources into microgrids has led to challenges in achieving daily optimal scheduling for hybrid alternating current/direct current microgrids (HMGs). To... Show More

The increasing integration of renewable energy sources into microgrids has led to challenges in achieving daily optimal scheduling for hybrid alternating current/direct current microgrids (HMGs). To solve the problem, this article presents a novel hybrid AC/DC microgrid scheduling method based on an improved brain storm optimization (BSO) algorithm. Firstly, with economic and energy storage device health as the primary objective functions, this paper proposes a dispatch model for AC-DC hybrid microgrids. To overcome the limitations of traditional algorithms, including premature convergence and can only find non-inferior solution sets, this article proposes a multi-objective BSO algorithm that integrates learning and selection strategies. Additionally, a fuzzy decision-making method is employed to achieve optimal daily dispatching and select the most suitable compromise solution. Finally, experiments are conducted to verify the effectiveness of the proposed multi-objective optimal scheduling method and to demonstrate the practicality and effectiveness of the method in real application scenarios.

In this article, a novel hybrid binary bat algorithm named HBBA is proposed for global optimization problems. First, to avoid simultaneous updating of bat velocity's dimensional components, i.e.... Show More

In this article, a novel hybrid binary bat algorithm named HBBA is proposed for global optimization problems. First, to avoid simultaneous updating of bat velocity's dimensional components, i.e., elements of velocity vector, a random black hole model is modified to adapt to binary algorithm for updating in unknown spaces for each dimensional component individually. Through this way, the search ability of bats around the current group best is increased greatly. Second, a time-varying v-shaped transfer function, rather than a time-invariant one as in closely related works, is proposed to map velocity in continuous search space to a binary one. This accelerates the speed to switch individuals' positions, i.e., solutions in binary space. Third, a chaotic map is utilized to replace monotonous parameters in original binary bat algorithm, which is beneficial for avoiding premature convergence. Simulation results demonstrate the effectiveness of the proposed algorithm by three types of benchmark functions and unit commitment problem.

This paper presents a pioneering approach to personalized English oral education through the integration of deep learning and swarm intelligence algorithms. Leveraging deep learning techniques, our... Show More

This paper presents a pioneering approach to personalized English oral education through the integration of deep learning and swarm intelligence algorithms. Leveraging deep learning techniques, our system offers precise evaluation of various aspects of spoken language, including pronunciation, fluency, and grammatical accuracy. Furthermore, we combine swarm intelligence algorithms to optimize model parameters to achieve optimal performance. We compare the proposed optimization algorithm based on swarm intelligence and its corresponding original algorithm for training comparison to test the effect of the proposed optimizer. Experimental results show that in most cases, the accuracy of the test set using the optimization algorithm based on the swarm intelligence algorithm is better than the corresponding original version, and the training results are more stable. Our experimental results demonstrate the efficacy of the proposed approach in enhancing personalized English oral education, paving the way for transformative advancements in language learning technologies.

The accuracy of the threshold determines the quality of high-definition garden plant image segmentation. How to accurately and quickly search for the best combination of multiple thresholds is... Show More

The accuracy of the threshold determines the quality of high-definition garden plant image segmentation. How to accurately and quickly search for the best combination of multiple thresholds is currently a research difficulty. In this regard, this article proposes an improved adaptive particle swarm optimization algorithm with extremal disturbance (IAPSO), which can to some extent prevent the PSO from falling into local optima by implementing extreme perturbation strategies. Then, by combining IAPSO and Deep Reinforcement Learning (DRL), the IAPSO-RL based on policy gradient off policy is proposed. It enhances information exchange between DRL and PSO. The IAPSO-RL can improve the sample efficiency of PSO. Experiments have shown that it can improve the performance and stability of threshold segmentation for high-definition garden plant images.

In physical education (PE) teaching, the teaching platform is comprehensively applied to provide students with high-quality PE teaching resources to meet their learning needs in different forms. A... Show More

In physical education (PE) teaching, the teaching platform is comprehensively applied to provide students with high-quality PE teaching resources to meet their learning needs in different forms. A human motion trajectory detection method is proposed based on deep learning and superpixels. The initial positioning of human body is performed through the attention mechanism and the YOLOv5 model, and the human target tracking is performed through superpixels. Aiming at the difficulty of cross-domain security management due to the lack of security infrastructure in multi-domain cloud IoT, a lightweight certificateless cross-domain authentication scheme is designed. Simulation results show that the proposed detection method has significantly improved accuracy and running time compared with traditional methods and can adapt to different detection scenarios. Furthermore, the proposed certificateless cross-domain authentication scheme can securely access sensor-generated data under the cloud IoT of the PE teaching platform in colleges.

Human joint moment plays an important role in rehabilitation assessment and human-robot interaction, which cannot be measured directly but can only be predicted via indirect measurement by an... Show More

Human joint moment plays an important role in rehabilitation assessment and human-robot interaction, which cannot be measured directly but can only be predicted via indirect measurement by an artificial neural network (ANN). However, most existing ANN models for human joint moment prediction use fully-connected network which has complex structure and no inclusion of domain knowledge. Thus, this study introduced a novel block-wised and sparsely-connected ANN model (BSANN) for human joint moment prediction, which significantly reduced the computational and storage costs. In this BSANN model, by using an improved Hill musculoskeletal (HMS) model, a single-output fully-connected network was established as a block to take each electromyograph (EMG) signal for the prediction of the muscle moment, and all muscle moments were connected together as inputs to obtain the joint moment. Compared to the ANN, our BSANN model decreased 80.7% connections and keeps good prediction accuracy. It provides embedded portable systems a powerful tool to predict joint moment.

This review paper delves into the original MRFO and its variants, focusing on single-objective algorithms including but not limited to hybrid algorithms, learning strategies, multiple populations... Show More

This review paper delves into the original MRFO and its variants, focusing on single-objective algorithms including but not limited to hybrid algorithms, learning strategies, multiple populations and dynamic parameter adjustment, highlighting the improvements made to enhance the algorithm's efficiency in global optimization, accelerate convergence rates, and improve its capacity to evade local optima. MRFO has emerged as an effective tool for solving complex optimization problems across various domains, including energy optimization, biomedical field, engineering problems, and others. A comprehensive analysis of applications of MRFO in different fields is provided, emphasizing its adaptability and efficacy. The paper concludes with a discussion on the challenges faced by MRFO and potential future research directions, aiming to consolidate the current research status and guide future investigations.

Firstly, a smart terminal is designed based on 5G communication technology, which is embedded with various protection measurement devices to form a 5G smart terminal. A distributed control model for... Show More

Firstly, a smart terminal is designed based on 5G communication technology, which is embedded with various protection measurement devices to form a 5G smart terminal. A distributed control model for the distribution network is constructed based on 5G smart terminals, and an objective function is designed taking into account factors such as restoring important loads, surplus power supply in the distribution network, network losses, and the number of switch actions. Finally, the Sparrow Search Algorithm (SSA) is improved using elite reverse learning strategy and dynamic sine perturbation strategy, and it is used to solve the objective function. Based on the IEEE33 distribution network node system, experimental tests are conducted, and the results show that the average delay of 5G smart terminals is about 30ms. Taking 14:00 as an example, the proposed method achieves network loss, number of switch actions, recovered important load power, and power supply surplus of 46.39 kW, 3 times, 185.65 kW, 240.28 kW, respectively. The fault recovery effect of the distribution network is ideal.

We offer task scheduling algorithms that are economical in terms of energy consumption for edge computing networks that are supported by the Internet of Things (IoT). The challenges of spectrum... Show More

We offer task scheduling algorithms that are economical in terms of energy consumption for edge computing networks that are supported by the Internet of Things (IoT). The challenges of spectrum utilization and energy-efficient work scheduling that lead to novel design are not addressed in this study, despite the fact that it provides encouraging results for task offloading. There is a possibility that the larger homogeneous fog computing architecture will include all homogeneous nodes, in addition to additional spectrum for node-to-node and device-to-device communications and work scheduling. We create a fog computing architecture that is efficient in terms of energy consumption for edge computing networks that are supported by the Internet of Things. By utilizing this approach, user-device nodes are able to collaborate while simultaneously reaping the benefits of diverse computing and network resources. In addition to this, we provide a solution to the problem of task scheduling that maximizes energy efficiency across all of the help nodes.

Nonlinear equations systems (NESs) appear in numerous optimization problems. However, the search performance of the improved evolutionary algorithm is limited due to the lack of analysis of the... Show More

Nonlinear equations systems (NESs) appear in numerous optimization problems. However, the search performance of the improved evolutionary algorithm is limited due to the lack of analysis of the fitness landscape. In this paper, a fitness distance correlation-based adaptive differential evolution (FDCADE) is proposed. Particularly, firstly FDCADE utilizes fitness distance correlation to extract the local landscape feature of NESs; secondly, according to the fitness landscape correlation, FDCADE adopts the combination of hybrid mutation operators and parameter adaptation strategy to guide the algorithm to search more effectively. To investigate the performance of FDCADE, 18 NESs are used as the test suite. Experimental results demonstrate that FDCADE obtains superior performance on root rate and success rate. In addition, FDCADE also gets competitive results for inverse kinematics of spatial 6R robot manipulators.

Swarm intelligence optimization algorithms have been widely used in the fields of machine learning, process control and engineering prediction, among which common algorithms include ant colony... Show More

Swarm intelligence optimization algorithms have been widely used in the fields of machine learning, process control and engineering prediction, among which common algorithms include ant colony algorithm (ACO), artificial bee colony algorithm (ABC) and particle swarm optimization (PSO). Wolf pack algorithm (WPA) as a newer swarm intelligence optimization algorithm has many similarities with ABC. In this paper, the basic principles, algorithm implementation processes, and related improvement strategies of these two algorithms were described in detail; A comparative analysis of their performance in solving different feature-based standard CEC test functions was conducted, with a focus on optimization ability and convergence speed, re-validating the unique characteristics of these two algorithms in searching. In the end, the future development trend and prospect of intelligent optimization algorithms was discussed, which is of great reference significance for the research and application of swarm intelligence optimization algorithms.

The development of technology that enables network convergence and the rising acceptance of heterogeneous network architectures have made it possible for many of the most important cognitive radio... Show More

The development of technology that enables network convergence and the rising acceptance of heterogeneous network architectures have made it possible for many of the most important cognitive radio networks to communicate with a broad variety of authorized networks. Traditional algorithms for network selection make use of selection approaches that are dependent on prior information about the network under consideration. We use the proposed algorithm to choose different networks and integrate them into computers. This paper offers a network selection technique that is based on deep reinforcement learning. This technique can be applied to cognitive radio networks that encompass a range of networks. We will utilize these findings to provide recommendations on how to remediate existing issues in the delivery of services to cognitive users. This paper aims to improve the service quality for cognitive users and find solutions to the identified problems.