Search

Streaming data arrives continually and is characterized by fast, massive, dynamic evolution and instability. Different from traditional static data clustering, streaming data clustering algorithms need to consider concept drift, outlier handling, identification and updating of dynamic clustering patterns, etc. DENCLUE is one of the most classical algorithms, which adopts nonparametric estimation and utilizes a finite number of samples to make inferences, to get the distribution of the overall data. However, the basic DENCLUE algorithm suffers from the problem that the Kernel Density Estimation (KDE) window width and density threshold parameter are difficult to choose, which cannot be directly applied to streaming data clustering. Therefore, in this paper, we propose a dual strategies improved DENCLUE streaming data clustering method based on KDE optimization and two-stage clustering, which takes into account the concept drift problem in streaming data. Firstly, a density threshold parameter optimization method based on KDE is proposed to address the challenges associated with selecting the KDE window width and density threshold in the traditional DENCLUE algorithm. Secondly, a two-stage clustering and merging method is designed to improve the performance of traditional DENCLUE clustering. The experimental results show that our algorithm outperforms the traditional Clustream and Denstream algorithms on datasets with arbitrary shapes and sizes, and has good performance on streaming data clustering.

In response to the challenge of three-dimensional path planning for unmanned aerial vehicles (UAVs), this paper introduces a Multi-Strategy Plant Growth Path Planning (MSPGPP) algorithm. Initially, a threat sphere and obstacle avoidance cone model are constructed to ensure safety in avoidance and enhance algorithm accuracy and convergence velocity, while B-spline curves are introduced to improve the quality of the path. Next, the concept of threat level is incorporated along with UAV maneuverability to establish a multi-objective optimization function, enabling the algorithm to plan optimal paths. Finally, an algorithm framework is developed, and comparative simulation results of the improved algorithm against the original algorithm and other optimization algorithms are presented in a three-dimensional environment. The results demonstrate that compared to the original algorithm, the improved algorithm better balances obstacle avoidance safety and UAV maneuverability, planning safer and more effective paths. Additionally, it achieves higher accuracy and faster convergence. Compared to other optimization algorithms, the improved algorithm has better optimization capabilities, higher computational efficiency, and superior path quality.

An approach based on refined critical plane methodology to fretting fatigue lifetime prediction for structures was proposed. A new shear stress-strain interaction (SSI) critical plane equation is developed, predicated on shear strain energy for predicting fretting fatigue lifetime. In order to obtain the fretting fatigue lifetime quickly and intelligently, the SSI critical plane method intelligent prediction software was developed using the Newton-Raphson iteration method. To corroborate the utility of the SSI critical plane method, we conducted a fretting fatigue lifetime test and then compared the calculated results of the SSI fretting fatigue lifetime prediction and traditional SWT prediction with the experimental values. The results indicate that SSI fretting fatigue lifetime prediction is closer to the experimental results than SWT.

With the integration of highly penetrative distributed photovoltaics into the distribution network, the imbalance between PV generation and load power becomes increasingly apparent, resulting in significant voltage security and stability issues in the distribution network. To overcome the limitations of traditional global voltage control and regional voltage cooperative control, a novel two-layer coordinated voltage control strategy, combining regional control and global control, is proposed for active distribution networks. Firstly, an adaptive partitioning of the active distribution network is achieved, without predefining the number of partitions, using the modular function gain change indicator and the Fast Unfolding algorithm. This adaptive partitioning ensures optimal regional control. Secondly, based on the voltage-power sensitivity principle, the reactive power control margin of PV sources is prioritized for regional-level reactive power control at critical nodes experiencing voltage violations. If the reactive power control margin within the region is insufficient, a combination of global-level reactive power control and active power control is employed. Lastly, simulation analysis is discussed by the IEEE 141-node traditional distribution network to confirm the effectiveness of the proposed method. Results demonstrate its ability to reduce the duration of voltage regulation and overcome the limitations of coordinated control range. The proposed method maximizes the utilization of the reactive power control margin of PV sources and significantly enhances PV penetration levels.

The present study posits that variations in maximum shear strain energy are the principal determinants for the onset of fretting fatigue cracks. We propose a refined critical plane methodology, termed the shear stress-strain interaction (SSI) critical plane method, predicated on shear strain, for predicting fretting fatigue crack initiation characteristics. The novelty of this methodology resides in its focus on cyclic shear strain as the genesis of crack initiation. To verify the effectiveness of the SSI critical plane method, finite element analyses using ANSYS were executed on fretting bridge and pad models to quantify the SSI interaction parameters. A comprehensive evaluation against established metrics-maximum shear range, stress-weighted tangential parameters, and fretting parameters was undertaken. The findings, in alignment with extant experimental data, confirm the robustness of the proposed method.

The large-scale integration of high-penetration distributed photovoltaic systems into distribution networks can result in significant grid voltage fluctuations within a short period. However, centralized regulation instructions for passive/reactive compensation, by themselves, are insufficient for effectively suppressing these fluctuations. Thus, this study used the grid-forming and grid-following control characteristics of modern power electronic inverters to propose an optimal allocation strategy for reactive power compensation equipment. This strategy aimed to address the insufficient proactive support capacity in the reactive power equipment used to suppress short-time grid voltage fluctuations. After establishing uncertain operation scenarios for the distribution network, we analyzed the respective multi-timescale behavioral characteristics of traditional, grid-forming, and grid-following reactive power compensation devices. The primary and auxiliary objectives were to minimize the investment cost of the special equipment and voltage deviation of the entire network, respectively. To achieve these objectives, we established a collaborative optimal allocation model for grid-forming and grid-following reactive power equipment. A multi-timescale cooperative allocation strategy was proposed to decompose the total reactive power demand curves at the equipment installation nodes into reactive power curves for different response levels and then collaboratively allocate the multiple devices. A comparative analysis of the three schemes in IEEE 33-node and 69-node systems shows that the proposed strategy guarantees lower overall network voltages while reducing the cost by at least 20% compared to those of other schemes.

The proliferation of distributed renewable energy and the extensive use of household energy storage have gradually transformed the users of active distribution network (ADN) from traditional consumers to prosumers. The flexible resources of prosumers on the demand side need a suitable trading mechanism to realize the optimal allocation of resources. Unlike the traditional electricity market with high entry threshold, this paper proposed an energy sharing mechanism based on prosumers with household energy storage devices. Firstly, taking into account the charge and discharge utility of household energy storage equipment as well as the production and consumption utility of prosumers, a transaction decision model of prosumers is established. Then, based on the centralized social welfare maximization energy sharing problem, a distributed energy sharing mechanism of ADN is constructed through alternating direction method of multipliers (ADMM) algorithm. Finally, an illustrative example of two prosumers and a prosumer network of the ADN with 10 nodes are calculated and analyzed respectively. The results show that the proposed energy sharing mechanism can maximize social welfare and improve the local accommodation degree of renewable energy from 84.85% to 85.27%. The social welfare increases with the growth of the number of prosumers with household energy storage.

In this paper, we investigate mobile edge computing (MEC) networks for intelligent information services, where there are N users equipped with K antennas and one access point (AP). The users have some computational tasks, and some of them can be decoupled by the AP, at the cost of a fee charged by the AP. For the considered system, we firstly consider two important metrics of interest: latency and fee. Then, we formulate a stochastic game to model the interaction between users and the AP. In this game, the AP sets prices to maximize its profit, while users devise the offloading strategy to reduce both the latency and charge. We further optimize the system by applying the array signal processing schemes on the users, in order to reduce the transmission latency. Simulation results are finally presented to verify the effectiveness of the stochastic game, and it is shown that the array signal processing scheme can help reduce the transmission latency significantly.

This paper investigates the resource allocation problem in vehicular communications based on multi-agent Deep Deterministic Policy Gradient (DDPG), in which each Vehicle-to-Vehicle (V2V) communication acts as agent and adopts Non-Orthogonal Multiple Access (NOMA) technology to share the frequency spectrum that pre-allocated to Vehicle-to-Infrastructure (V2I) communications. Different with conventional D2D communications, the fast varying channel condition due to the high mobility in vehicular environment causes the difficulty of collecting instantaneous Channel State Information (CSI) at base station. Meanwhile, one tremendous challenge faced by vehicular communications is how to maximize the sum-rate of V2I communications simultaneously guaranteeing the latency and reliability requirements for the transmission of safety-critical information in V2V communications. In response, we formulate the resource allocation problem as a decentralized Discrete-time and Finite-state Markov Decision Process (DFMDP), in which allocation decisions are made by multiple agents that do not have complete and global network information. Due to the complexity of the problem, we propose a DDPG algorithm which is capable of handling continuous high dimensional action spaces to find the optimal allocation strategy. Numerical results verify that each agent can effectively learn from the environment by means of the proposed DDPG algorithm to maximize the sum-rate of V2I communications while satisfying the stringent latency and reliability constraints of V2V communications.

The emergence of multi-server authentication key protocol schemes provides a viable environment for users to easily access the services of multiple legitimate servers through a single registration. Biometric identification technology has the characteristics of forgery difficulty, duplication difficulty and guess difficulty, etc. Therefore, it is an indispensable authentication technology in smart card-based user authentication protocol. There are many shortcomings in the existing schemes based on biometrics, including leakages of biometrics information, smart card theft attack, lack of user anonymity, user impersonation attack, server impersonation, and so on. To overcome these shortcomings, we propose a new user authentication and key agreement scheme in the multi-server environment. To some extent, we not only are able to guarantee the communication security between the user and the servers, but also ensure the physical security of the smart card and biometrics information. In this respect, we use lightweight cryptographic primitives, such as Physically Unclonable Functions (PUFs), Fuzzy extractor and One-way hash functions, and so on. The proposed scheme can effectively protect user's anonymity without the use of password and provide mutual authentication and key agreement in the multi-server environment. Subsequently, we used informal analysis, Burrows-Abadi-Needham Logic (BAN-Logic) proof, and a widely accepted Real-Or-Random model to prove the security and robustness of proposed scheme. Finally, our authentication protocol can protect the security of communication.

In this paper, we proposed an enhanced secure scheme for the wireless communication system threatened by an intelligent attacker, which can work in eavesdropping, jamming, and spoofing modes. The conventional secure scheme is to apply Q-learning-based algorithm to reach a Nash equilibrium (NE) in the framework of a zero-sum game between the transmitter and attacker, which, however, requires the number of antennas at the transmitter to be much larger than that at the attacker. To overcome this limitation, we first consider the scenario where the attacker can flexibly increase the number of antennas in order to increase the attack rate. By adaptively setting the number of antennas at the transmitter and the legitimate receiver equal to that at the attacker, we then apply the beamforming at the transmitter to suppress the eavesdropping and use the filtering at the receiver to prevent the jamming and spoofing. By incorporating the beamforming and filtering, the benefits of the attacker in this game are efficiently restricted. Furthermore, the Q-learning-based power control strategy is used to reach a new NE. The simulation results have been demonstrated to show that the proposed scheme can suppress the intelligent attack efficiently, which outperforms the conventional scheme in the secrecy performance.

Feature selection has been applied to the analysis of complex structured data, such as functional connectivity networks (FCNs) constructed on resting-state functional magnetic resonance imaging (rs-fMRI), for removing redundant/noisy information. Previous studies usually first extract topological measures (e.g., clustering coefficients) from FCNs as feature vectors, and then perform vector-based algorithms (e.g., t-test) for feature selection. However, due to the use of vector-based representations, these methods simply ignore important local-to-global structural information of connectivity networks, while such structural information could be used as prior knowledge of networks to improve the learning performance. To this end, we propose a graph kernel-based structured feature selection (gk-SFS) method for brain disease classification with connectivity networks. Different from previous studies, our proposed gk-SFS method uses the graph kernel technique to calculate the similarity of networks and thus can explicitly take advantage of the structural information of connectivity networks. Specifically, we first develop a new graph kernel-based Laplacian regularizer in our gk-SFS model to preserve the structural information of connectivity networks. We also employ an l1-norm based sparsity regularizer to select a small number of discriminative features for brain disease analysis (classification). The experimental results on both ADNI and ADHD-200 datasets with rs-fMRI data demonstrate that the proposed gk-SFS method can further improve the classification performance compared with the state-of-the-art methods.

With the rapid development of Web Virtual Reality (WebVR) technology, increasing focus has been placed on this domain. WebVR indoor scenario design studies have been of important value in both academia and industry. However, many bottlenecks still need to be overcome, such as the weak computing capacity and limited memory space available in web browsers. In particular, there are many deficiencies in virtual scenes, i.e., lack of fidelity, low automation and poor scene interactability. In this paper, we propose a novel WebVR indoor furniture layout design framework to enhance the capabilities of automatic furniture layout and significantly enhance the interactiveness of virtual scenarios. In particular, we present a hand-drawn sketch recognition scheme based on the ResNet convolutional neural network (CNN), which can strongly improve scenario interactiveness by allowing the user to conveniently add new furniture by means of free-hand drawing operations rather than tedious manual drag-and-pull operations. In addition, based on a deep Q-learning network (DQN), the best positions (states) for these pieces of furniture (agents) in virtual scenarios can be automatically determined, making it easy to satisfy popular design principles. Finally, we report experiments conducted to validate the feasibility of our proposed framework, and the results fully demonstrate that this framework is completely feasible.

Artificial stent implantation is one of the most effective ways to treat vascular diseases. However, commonly used metal stents have many negative effects, such as being difficult to remove and recover, whereas bio-absorbable stents have become the best way to treat vascular diseases because of their absorbability and harmlessness. It is very important in vascular medical imaging, such as optical coherence tomography (OCT), to be able to effectively track the position of stents in blood vessels. This task is undoubtedly labor-intensive, and it is inefficient to rely on experts to identify various scaffolds from medical images. In this paper, a novel automatic detection method for bioresorbable vascular scaffolds (BVSs) via a U-shaped convolutional neural network is developed. The method is composed of three steps: data preparation, network training, and network testing. First, in the data preparation step, we complete the task of labeling related samples based on expert experience, and then, these labeled OCT images are divided into the original and masked OCT images (corresponding to X and Y in supervised learning, respectively). Next, we train our data on a U-shaped convolutional neural network, which consists of five downsampling modules and four upsampling modules. We can obtain a related training model, which can be used to predict the related samples. In the testing stage, we can easily utilize the trained model to predict the input OCT data so that we can obtain the relevant information about a BVS in an OCT image. Obviously, this method can assist doctors in diagnosing the disease and in making important decisions. Finally, some experiments are performed to validate our proposed method, and the IoU criterion is used to measure the superiority of our proposed method. The results show that our proposed method is completely feasible and superior.

In the MIMO broadcasting system, channel state information (CSI) is often used for data detection at the receiver or preprocessing techniques such as the power control and user scheduling at the transmitter and hence, the study of its acquisition is important. Usually, the CSI can be obtained by the training-based channel estimation. Assuming that the users have the channels' statistical information and adopt the minimum mean-square-error (MMSE) receivers, this paper studies how to design an optimal training sequence to minimize the total weighted mean square error (MSE) of channel estimation. Following this objective, we formulate this problem as a positive semidefinite problem (SDP) with two constraints, and further transform it into a dual problem. In the solving process of the dual problem, we model it as an optimization problem on the positive definite matrix manifold and solve it by use of the iterative geodesic equation on the matrix manifold. The convergence and correctness of the proposed method are demonstrated by computer simulation; the effects of key system parameters on the weighted MSE are also investigated. Under various system configurations, the superiority of the proposed method is shown by comparing with a few other existing schemes.

Recently, telemedicine has been widely applied in remote diagnosis, treatment and counseling, where the Internet of Things (IoT) technology plays an important role. In the process of telemedicine, data are collected from remote medical equipment, such as CT machine and MRI machine, and then transmitted and reconstructed locally in three-dimensions. Due to the large amount of data to be transmitted in the reconstructed model and the small storage capacity, data need to be compressed progressively before transmission. On this basis, we proposed a lightweight progressive transmission algorithm based on large data visualization in telemedicine to improve transmission efficiency and achieve lossless transmission of original data. Moreover, a novel four-layer system architecture based on IoT has been introduced, including the sensing layer, analysis layer, network layer and application layer. In this way, the three-dimensional reconstructed data at the local end is compressed and transmitted to the remote end, and then visualized at the remote end to show reconstructed 3D models. Thus, it is conducive to doctors in remote real-time diagnosis and treatment, and then realize the data processing and transmission between doctors, patients and medical equipment.

With the arrival of the Web 2.0 era and the rapid development of virtual reality (VR) technology in recent years, WebVR technology has emerged as the combination of Web 2.0 and VR. Moreover, the concept of “WebVR + medical science”is also proposed to advance medical applications. However, due to the limited storage space and low computing capability of Web browsers, it is difficult to achieve real-time rendering of large-scale medical vascular models on the Web, let alone large-scale vascular animation simulations. The framework proposed in this paper can achieve virtual display of the medical blood vasculum, including lightweight processing of the vasculum and virtual realization of blood flow. This innovative framework presents a simulation algorithm for the virtual blood path based on the Catmull-Rom spline. The mechanisms of progressive compression and online recovery of the lightweight vascular structure are further proposed. The experimental results show that our framework has a shorter browser-side response time than existing methods and achieves efficient real-time simulation.

Clouds are becoming a very important platform for hybrid real-time tasks. To enhance the reliability of cloud, fault tolerance of cloud becomes a critical issue. However, the complexities and specialties of traditional fault-tolerant mechanisms cannot meet the fault-tolerant requirements of clouds. To address this issue, we propose a novel fault-tolerant scheduling algorithm named ARCHER for hybrid tasks in cloud. ARCHER has three significant characteristics: 1) it integrates the traditional primary/backup model and checkpoint technology which can flexibly determine the execution time of the backup copies of tasks, so it greatly enhances the resource utilization and produces more time slots to execute tasks as many as possible; 2) it employs task classification mechanism to realize precise scheduling for different types of tasks and virtual machines, which reduces the response time of clouds; and 3) it uses time slot exploiting mechanism, task forward mechanism, and task transform mechanism to achieve high-resource utilization. We conduct extensive simulations to evaluate the performance of ARCHER by comparing it with four baseline algorithms. The experimental results show that ARCHER can effectively improve the resource utilization of cloud while guaranteeing fault tolerance.

In the field of medical imaging, many medical image data can be rebuilt into 3-D medical models for use in medical education and analysis. In fact, the 3-D medical models help ordinary people (including patients and students) to more easily understand and learn medical knowledge. In addition, with the rapid development of Web3D technology, the demand for 3-D visualization technology based on the web browser increases. However, the limited bandwidth and low load capacity of the browser have seriously restricted the development of technology. Therefore, this paper proposes a framework to better show 3-D skeleton shapes. In particular, mesh compression is one of the most effective methods to achieve a fast transmission data process. In addition, because of the poor rendering capabilities of the browsers, it is notably difficult to render the entire model at once. Moreover, it often makes the browser crash; thus, the transmitted model data are only rendered once. In addition, a mesh segmentation algorithm is proposed to realize component-wise rendering and lightweight for shape. A voxel-based component repetition method is used to detect the repetitive components; thus, we can perform matrix transformation to finish the repetitive-component Web3D visualization, i.e., lightweight for shape. Finally, the related experiments are performed to validate our proposed framework. The results show that the proposed framework is feasible and superior.

Research on lower limb exoskeleton (LLE) for rehabilitation have developed rapidly to meet the need of the population with neurologic injuries. LLEs for rehabilitation include therapeutic LLEs that aim to restore walking ability for patients, and assistive LLEs that offer support on activities in daily life. A substantial part of them can serve both purposes. However, these devices are yet to reach the final goal of performing human-machine joint movement agilely and smartly. Control strategy plays an important role in achieving their designed goal. At present, control strategies face three major challenges: how to detect human intention, how to do motion control with given intentions, and how to optimize control parameters to suit different individuals. As a contribution, this paper offers an overview on the state-of-the-art control strategies for rehabilitation LLEs by classifying them into eight categories, each of which is presented with a technical summary and tabulated information of representative papers. Moreover, current approaches addressing the three challenges are discussed in a macroscopic perspective. Finally, it has been explored which requirements the future control strategies should meet for maximizing the performance of rehabilitation LLEs.