Search

Despite the existence of various super‐resolution (SR) methods, most of them focus on designing models for specific upscaling factors rather than fully exploiting inter‐scale correlation to improve efficiency. In contrast, multi‐scale SR methods can effectively reduce the redundancy of network parameters by aggregating the feature extraction processes corresponding to multiple scales into a unified process. The aim of this study is to enhance the compactness and efficiency of the SR model. Thus, an efficient multi‐scale SR method called the diverse branch feature refinement network (DBFRN) is proposed. By decoupling the training process and inference process based on the idea of structural re‐parameterization, multi‐branch topology is adopted to enrich multi‐scale learning and merge branches to achieve efficient inference with equivalent effects. Specifically, two re‐parameterization strategies are designed and two corresponding feature refinement blocks for different feature levels in multi‐scale SR network. Extensive experiments demonstrate that the proposed multi‐scale SR method is effective and efficient, and it can outperform advanced single‐scale methods in terms of quantity and quality. [ABSTRACT FROM AUTHOR]

Aiming to solve the problem of the identity switching of objects with similar appearances in real scenarios, a multi-object tracking approach combining contextual features and trajectory prediction is proposed. This approach integrates the motion and appearance features of objects. The motion features are mainly used for trajectory prediction, and the appearance features are divided into contextual features and individual features, which are mainly used for trajectory matching. In order to accurately distinguish the identities of objects with similar appearances, a context graph is constructed by taking the specified object as the master node and its neighboring objects as the branch nodes. A preprocessing module is applied to exclude unnecessary connections in the graph model based on the speed of the historical trajectory of the object, and to distinguish the features of objects with similar appearances. Feature matching is performed using the Hungarian algorithm, based on the similarity matrix obtained from the features. Post-processing is performed for the temporarily unmatched frames to obtain the final object matching results. The experimental results show that the approach proposed in this paper can achieve the highest MOTA. [ABSTRACT FROM AUTHOR]

Multi-camera video surveillance has been widely applied in crowd statistics and analysis in smart city scenarios. Most existing studies rely on appearance or motion features for cross-camera trajectory tracking, due to the changing asymmetric perspectives of multiple cameras and occlusions in crowded scenes, resulting in low accuracy and poor tracking performance. This paper proposes a tracking method that fuses appearance and motion features. An implicit social model is used to obtain motion features containing spatio-temporal information and social relations for trajectory prediction. The TransReID model is used to obtain appearance features for re-identification. Fused features are derived by integrating appearance features, spatio-temporal information and social relations. Based on the fused features, multi-round clustering is adopted to associate cross-camera objects. Exclusively employing robust pedestrian reidentification and trajectory prediction models, coupled with the real-time detector YOLOX, without any reliance on supplementary information, an IDF1 score of 70.64% is attained on typical datasets derived from AiCity2023. [ABSTRACT FROM AUTHOR]

Crowd counting, as a basic computer vision task, plays an important role in many fields such as video surveillance, accident prediction, public security, and intelligent transportation. At present, crowd counting tasks face various challenges. Firstly, due to the diversity of crowd distribution and increasing population density, there is a phenomenon of large-scale crowd aggregation in public places, sports stadiums, and stations, resulting in very serious occlusion. Secondly, when annotating large-scale datasets, positioning errors can also easily affect training results. In addition, the size of human head targets in dense images is not consistent, making it difficult to identify both near and far targets using only one network simultaneously. The existing crowd counting methods mainly use density plot regression methods. However, this framework does not distinguish the features between distant and near targets and cannot adaptively respond to scale changes. Therefore, the detection performance in areas with sparse population distribution is not good. To solve such problems, we propose an adaptive multi-scale far and near distance network based on the convolutional neural network (CNN) framework for counting dense populations and achieving a good balance between accuracy, inference speed, and performance. However, on the feature level, in order to enable the model to distinguish the differences between near and far features, we use stacked convolution layers to deepen the depth of the network, allocate different receptive fields according to the distance between the target and the camera, and fuse the features between nearby targets to enhance the feature extraction ability of pedestrians under nearby targets. Secondly, depth information is used to distinguish distant and near targets of different scales and the original image is cut into four different patches to perform pixel-level adaptive modeling on the population. In addition, we add density normalized average precision (nAP) indicators to analyze the accuracy of our method in spatial positioning. This paper validates the effectiveness of NF-Net on three challenging benchmarks in Shanghai Tech Part A and B, UCF_ CC_50, and UCF-QNRF datasets. Compared with SOTA, it has more significant performance in various scenarios. In the UCF-QNRF dataset, it is further validated that our method effectively solves the interference of complex backgrounds. [ABSTRACT FROM AUTHOR]

The demands of high-quality videos captured by camera become bigger due to the rapid development of pattern recognition and artificial intelligence. Video denoising is the key technology to obtain clear videos. However, the research on video denoising is far from enough now. In this paper, we propose a video denoising method based on convolutional neural network architecture to reduce the noise from the sensor system. We improve the loss function of noise estimation by imposing adaptive penalty on under-estimation error of noise level which makes our method perform robustly. Furthermore, we make use of multi-level features to guide the spatial denoising, where multilayer semantic information of the image is regarded as the perceptual loss. Instead of relying on Optical Flow solving the characterization of inter-frame information, we utilize U-Net-like structure to handle motion implicitly. It is less computationally expensive and avoids distortions caused by inaccurate flow and object occlusion. In order to locate temporal features and suppress useless information, the attention mechanism is introduced to the skip connections of the U-Net-like structure. Experimental results demonstrate that the proposed algorithm outputs more convincing results in both peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) indexes when processing Gaussian noise, synthetic real noise, and real noise compared with selected approaches. [ABSTRACT FROM AUTHOR]

Compared with convolutional operation, non‐local operation can directly capture long‐range dependencies and thus has a larger receptive field. However, the computation and memory consumption of non‐local operation is much higher than convolutional operation, so it cannot be used repeatedly as a general component directly. In this paper, in order to balance the accuracy and computational complexity of non‐local enhancement, the non‐local operation is simplified based on local importance‐based pooling, which can dynamically extract discriminative features during the down‐sampling process by learning adaptive weights. Such simplified non‐local enhancement is able to prevent unacceptable computational consumption caused by directly processing the entire feature maps containing a large number of features. In order to verify the effectiveness of the proposed method, 2D and 3D feature extraction blocks are constructed based on the simplified non‐local operations, and they are stacked as feature extraction networks for space‐time video super‐resolution task, which aims to increase resolution in both time and space simultaneously. Extensive experiments demonstrate that the proposed simplified non‐local networks can effectively improve the performance of space‐time video super‐resolution task both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

To solve the problems that the background reference frames are seriously contaminated by the foreground, and the bit rate increases suddenly incurred by the one-time transmission of the background frames, a progressive background frame generation method with image block as the basic unit was proposed for surveillance video application. An image block codebook model based on clustering was formulated. The image blocks at the same position in the video sequence were effectively clustered by using perceptual hash-based element matching. The background symbol was accurately detected by using the characteristics of the background image area. A complete background frame was produced by extracting the background blocks in different frames based on the codebook model. Experimental results demonstrate that the proposed method achieves 17.89% coding efficiency for luma component compared with standard HM16.20, and can effectively improve the quality of the produced background reference frame. Besides, the proposed method complexity meets the real-time requirements of video applications. [ABSTRACT FROM AUTHOR]

Due to the rapid development of social computerization and smart devices, there is an increasing demand for indoor positioning of mobile robots in the robotics field, so it is very important to realize the autonomous navigation of mobile robots. However, in indoor scenes, due to factors such as dark walls, the global positioning system cannot effectively locate, and the broadband and wired positioning technologies used indoors have problems such as base station laying and delay. Computer vision positioning technology has greatly improved the camera hardware due to its simple equipment and low cost. Compared with other sensor cameras, it is less affected by environmental changes, so visual positioning has received extensive attention. Image matching has become the most critical link in visual positioning. The accuracy, speed, and robustness of image matching directly determine the results of visual positioning, so image matching has become the main topic of this study. In this study, the neural network algorithm is systematically optimized, especially for the robot's local obstacle avoidance, and an obstacle data acquisition method based on VGG16 and fast RCNN is proposed. In order to solve the problem that the semantic image segmentation algorithm based on AlexNet and ResNet is difficult to accurately obtain the information of multiple objects, and an image semantic segmentation algorithm combined with VGG16 is designed to classify the background and road in the image at the pixel level and capture the path boundary line. The collection of robot obstacle path information improves the speed and accuracy of highly automated local obstacle avoidance. This study uses neural network algorithms to systematically optimize computer vision positioning and also studies the accuracy optimization of local obstacle avoidance, aiming to promote its better development. [ABSTRACT FROM AUTHOR]

Summary: The congestion control mechanism is one of the most important components in Internet, which guarantees network normal operation and prevents network from congestion collapse. It is noticed that traditional loss‐based algorithms are not moving data very well in today's Internet. To get channel resource highly utilized, such algorithms maintain a standing queue of packets at bottleneck and cause large transmission delay. Recently, effort has been devoted from academia and industry to design new solution which could achieve high throughput and low transmission delay simultaneously. There are several fruitful results such as the bottleneck bandwidth and round trip time (BBR) and Vivace, Copa, Cellular Controlled delay TCP (C2TCP). Among them, BBR is the most eminent one. There are other variant algorithms by modifying some parameters in BBR for possible improvement, and BBR has also evolved drastically into version 2 (BBRv2). In this work, a framework is implemented to evaluate the performance of these algorithms on ns3. Interested readers could test other congestion control algorithms or design new methods. Moreover, this work can work as reference for engineers to tune parameters in BBR or choose other solutions for their applications. [ABSTRACT FROM AUTHOR]

Frame interpolation is one of the most challenging tasks in the video processing field. Recent advances have demonstrated that the deep learning‐based frame interpolation methods are promising. However, the experiments show that most existing deep learning‐based methods have the same problem as traditional methods. When these algorithms handle severe occlusions, they will produce distortions, especially around the motion boundaries. To better synthesise the image of the motion areas, the authors design a mask‐guided frame synthesis model, which consists of multiple components, based on deep convolutional neural networks. The proposed model first estimates the asymmetric bi‐directional optical flows from the intermediate frame to the input frames. Then it estimates the occlusion‐aware masks, which can compensate for the optical flow inaccuracy based on optical flows and correlation information. Finally, the warped frames are adaptively fused under the guidance of the masks to generate a high‐quality intermediate frame. Furthermore, to generate more realistic video frames, they train the network model with the pixel‐based loss and the feature‐based loss in a step‐by‐step way. In the experiment, they analyse the proposed model and compare it with the high‐performance methods, both qualitative and quantitative results show that their method performs better. [ABSTRACT FROM AUTHOR]

Summary: Current proposed congestion control algorithms for multipath transmission couple all subflows together to maintain bottleneck fairness by assuming that the subflows traverse a common bottleneck. The coupled form congestion control algorithms restrict the multipath session to gain better throughput in non‐shared bottleneck situation. The throughput of a multipath session following independent rate control is larger than the throughput achieved by coupled form congestion control algorithm. The key point is to find a method to detect whether flows share a common bottleneck. If the subflows of a multipath session are detected out traversing a common bottleneck, the sender could perform coupled congestion control algorithm to guarantee bottleneck fairness and follow independent congestion control algorithm otherwise to improve throughput. Deduced from fluid model of additive increase multiplicative decrease (AIMD) rule, the delay samples can be linearly fitted when the bottleneck link falls into congestion. A delay trend line regression (TR) method is proposed for shared bottleneck detection. The delay slopes in close proximity indicate that the flows traverse the same bottleneck in great probability. Extensive simulations are performed to validate the effectiveness of TR algorithm in shared bottleneck detection. It is further implemented in multipath QUIC Golang codebase to work in collaboration with linked increases algorithm (LIA). Results show a multipath QUIC session with two subflows can gain higher throughput in non‐shared bottleneck situation and is less aggressive in shared bottleneck cases with the implementation of shared bottleneck detection algorithm. [ABSTRACT FROM AUTHOR]

Fingerprint template is considered as an effective method to solve the problem of fingerprint protection, and an indispensable key technology in the identification field. Among them, the Delaunay triangulation net‐based template is a new type of solution. However, such a triangulation net is greatly affected by the elastic distortion of the fingerprint. In this study, a novel improvement, Delaunay tentacle, is proposed to this issue. Based on the orderly degradation of the Delaunay triangulation net, the Delaunay tentacle, kernel, and centre can be generated in turn. By calculating the deformation of the tentacles, this innovative, improved Delaunay triangulation structure can sense and resist distortion. The proposed algorithm is tested on the Fingerprint Verification Competition databases, and the model is compared with other current similar schemes. Experimental results demonstrate that it has promising performance. [ABSTRACT FROM AUTHOR]

With the rapid development of digital video, shot boundary detection (SBD) has attracted much attention since it is the fundamental preprocessing for video indexing, annotation, retrieval, and other content-based operations. However, most state-of-the-art SBD methods are based on the spatial features of video image, and the overall characteristics of video shots are not fully considered. We propose a feature extraction method based on shot characteristics and a more robust SBD process. First, a video is divided into several segments, the segments containing consecutive video frames inside a shot are considered as training segments and others are called candidate segments. Afterward, using block-wise principal component analysis on the training segments, shot eigenspaces are established. The video frames in the candidate segment are then projected onto the corresponding shot eigenspace to extract the feature vectors. Finally, analysis and pattern matching for feature vectors are performed to extract the video shot boundary. Experiments on TRECVID test data demonstrate that the mean values of F1 in cut transition detection and gradual transition (GT) detection of our method are 0.901 and 0.866, respectively, obviously higher than the values of the compared methods, especially in GT detection, thus providing better accuracy in SBD. [ABSTRACT FROM AUTHOR]

Audio oriented integrity protection should consider the characteristics of audio signals based on the combination of audio application scenarios. However, in the current popular network interaction environment, traditional verification based solutions can no longer work. A kind of integrity protection scheme for audio business should be redesigned in these new scenarios. In this context, a method of audio integrity protection based on relative phase (RP-AIP) is proposed. Through the design of integrity object (I.O.), the integrity of audio can be abstracted as the completeness and accuracy of it. The I.O. is bound to the audio signal in a uniformly and randomly embedded manner, and the embedding rules are controlled by the relative phase characteristic of the audio itself. The model and strategy of RP-AIP are illustrated, and the corresponding process and algorithm are demonstrated as well. Simulation experiments illustrate the feasibility of the proposed solution and indicate the superiority of its performance. [ABSTRACT FROM AUTHOR]

Summary: Conversational video service is characterized by high bandwidth demand and low delay requirement. Bandwidth and transmission schemes play an important role in providing high‐quality delivery service for point‐to‐point conversational video service. Multipath transmission is regarded as an effective way to aggregate bandwidth. Transmission schemes need to ensure the strict time relation between information entities and to alleviate the negative impact of packet loss on video quality. To achieve this, existing transmission schemes may incur either a large delay or a large amount of duplicated packets that are not suitable for conversational video service. In this paper, we propose an adaptive retransmission mechanism–based multipath transmission (MT‐AR) for conversational video service delivery. MT‐AR takes advantage of historical reception experience to timely detect packet loss with a certain degree of misjudgement. Receiver requests sender to retransmit the lost packet if the lost packet benefits the decoding. Adaptive playout speed adjustment and alternative path retransmission cooperatively optimize the performance of retransmission. Receiver slightly extends playout speed to reserve time for retransmission and accelerates playout speed to alleviate negative impact of cumulative extension. Multiple paths support to conduct retransmission on an optimal path selected from alternative paths to avoid continuous congestion or error on the original path. Finally, we conduct extensive tests to evaluate the performance of MT‐AR. Experimental results show that MT‐AR can effectively improve the quality of experience of conversational video service by retransmission. [ABSTRACT FROM AUTHOR]

A computer vision method is presented for the mobile robot to find humans in scene. Face detection is used for confirming humans. In order to reduce regions of search, optical flow algorithm is used to segment the image in advance. Asymmetric problems in face detection are explained, and relative solutions are put forward by bootstrapping strategy and asymmetric adaboost algorithm. In addition, fisher discriminant analysis further improves the performance of face detection. Multi-view face models are trained to accommodate practical face detection application. At last, experiments demonstrate that our multi-view face detector achieves high detection accuracy and fast detection speed on both standard testing datasets and real-life images. [ABSTRACT FROM AUTHOR]

Multipath transport faces a lot of challenges caused by path diversity, network dynamics, and service diversity. An effective end-to-end multipath transport control mechanism becomes essential to efficiently utilize multiple paths. On the base of the general framework of multipath transport system based on application-level relay proposed in our previous work, this paper presents a multipath transport control mechanism supporting various applications with different transmission requirements. We propose a multipath transport protocol suite, which is extensible and suitable for various applications, and a multipath transport control model in which an application-dependent splitting granularity named flow block is introduced. Two load distribution models are explored: the earliest idle path first load distribution for reliable data transmission to maximize the data throughput and the packet reordering-controlled load distribution for real-time data transmission to minimize the packet reordering thereby reducing end-to-end delay and packet loss rate of multipath transport. Simulation results show that the proposed models can effectively improve data throughput for applications with reliable transmission requirements and reduce the total packet loss rate of the destination for applications with real-time transmission requirements. [ABSTRACT FROM AUTHOR]

Compared with training multiple single-scale models to achieve different scale image super-resolution (SR), using the internal correlation of multiple scales to aggregate multi-scale learning into a single model can effectively reduce the network parameters and improve efficiency. Correspondingly, it is important to study how to take the advantage of inter-scale correlation at a fixed model size for the performance improvement of multi-scale SR. We combine the capture of richer context dependencies and convolutional response modulation to improve the discriminative ability of the model, and then propose a global context-aware feature modulation network, which has a stronger representational capability for multi-scale SR. Specifically, we first model the global context based on the self-attention mechanism, which can effectively extract rich global information from convolutional features. Then, we propose to modulate the feature responses using global contextual dependencies in spatial and channel dimensions respectively. Further, we construct the global context-aware feature modulation block, which can be stacked to form a deep feature modulation network and applied to the unified multi-scale SR architecture to learn inter-scale correlation. Extensive experiments demonstrate that the proposed global context-aware modulation is effective, which can improve the performance of multi-scale SR task both quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

The ever-increasing transmission requirements of quality of service (QoS)-sensitive applications, especially real-time multimedia applications, can hardly be met by the single path routing protocols. Multipath transmission mechanism is a feasible approach to provide QoS for various applications. On the basis of the general framework of multipath transport system based on application-level relay, we present a relay path allocation scheme, whose goal is to select suitable relay paths, while balancing the overlay traffic among the different domains and relayers. With the application-layer traffic optimization service under the standardization within the Internet Engineering Task Force (IETF), the controller has the topology-aware ability to allocate relay paths with excellent routing performance. To further develop the universality of our method, the controller perceives transmission performance of relay overlay network through relayers' performance detection processes and, thus, has the application-aware ability to allocate relay paths with excellent transmission performance for different applications by consulting application-specific transmission metrics. Simulation results demonstrate that the proposed relay path allocation algorithm performs well in allocating superior relay paths and can balance the distribution of overlay traffic across domains in different network situations. [ABSTRACT FROM AUTHOR]

At present, to realize or improve the quality of experience (QoE) is a major goal for network media transmission service, and QoE evaluation is the basis for adjusting the transmission control mechanism. Therefore, a kind of QoE collaborative evaluation method based on fuzzy clustering heuristic algorithm is proposed in this paper, which is concentrated on service score calculation at the server side. The server side collects network transmission quality of service (QoS) parameter, node location data, and user expectation value from client feedback information. Then it manages the historical data in database through the 'big data' process mode, and predicts user score according to heuristic rules. On this basis, it completes fuzzy clustering analysis, and generates service QoE score and management message, which will be finally fed back to clients. Besides, this paper mainly discussed service evaluation generative rules, heuristic evaluation rules and fuzzy clustering analysis methods, and presents service-based QoE evaluation processes. The simulation experiments have verified the effectiveness of QoE collaborative evaluation method based on fuzzy clustering heuristic rules. [ABSTRACT FROM AUTHOR]

A reliable transmission with QoE (Quality of Experience) guarantee is crucial for internet conversational service applications. However, due to the limited network bandwidth bottleneck effect and the drawback of transmission technology, there exists no mature and open QoE technical solution for this service. In this paper, we focused our attention on a load distribution strategy for multipath relay transmission to meet the QoE requirements of conversational real-time HD video services. It consisted of three stages: First, a series of relay nodes was deployed in the backbone network, and a software defined overlay network was constructed to perform the multipath relay transmission for the service. Second, by an analysis of the QoE feature, a bijection was built for each quantitative QoE and its MOS (Mean Opinion Score) score. Finally, considering the influence of the coupling relation between paths on the service quality in multipath relay transmission, fuzzy cooperative game theory was used to design the service load distribution strategy. Many experiments showed that compared with state-of-the-art methods in the single-path transmission scene, the strategy we designed can dynamically adjust the load distribution of each sub-path according to the change in QoS (Quality of Service) information of the transmission path in real time. While meeting the strict real-time constraints of the service, it can effectively avoid the impact of network random congestion on the service QoE. [ABSTRACT FROM AUTHOR]

Multipath diversity significantly impacts multipath transmission quality. Enough multipath diversity would minimize the negative influence brought by an individual path, thus improving tolerance capability of network congestion and failure. However, multipath diversity is hard to guarantee on overlay networks because of inaccurate awareness of underlay network and multipath generating methods considering little about underlay diversity. In this paper, we design a multi-dimension spatial method for topology awareness and multipath generating. Analyzing that the complicated underlay networks with multiple autonomous systems reduce the accuracy of network positioning for topology awareness, we decompose the underlay networks into multiple dimensions, namely intra and inter autonomous system dimensions. We generate independent views for each autonomous system and merge views by embedding exchange points. Then, we design some spatial mechanisms to evaluate link diversity and to constrain multipath generating. Based on the multi-dimensional view, multipath generating is conducted in inter and intra autonomous system phases. Experiments demonstrate that the proposed method improves topology awareness accuracy and guarantees multipath diversity better and the transmission quality is improved. [ABSTRACT FROM AUTHOR]

Summary: Multipath transmission (MT) promotes transmission quality effectively. Path diversity (PD) impacts MT quality by aggregating capabilities of paths with little correlation. Enough PD contributes to improving concurrent link utilization and weakening negative impacts from a single path so that abilities of congestion and failure tolerance are enhanced. However, PD is hard to guarantee on overlay networks due to little awareness of underlay networks and few evaluation methods. In this paper, we propose the spatial geometry–based multipath routing (SGMR) method to improve PD for MT on overlay networks. Considering that paths are composed of overlay nodes and network coordinates effectively characterize node diversity (ND), we employ some geometric mechanisms on the spatial coordinate–based view to convert ND to PD. Firstly, coordinates are generated to match the overlay and underlay networks and meanwhile to characterize ND. Then, for generating multiple paths, transmission direction facilitates the path convergence, transmission surface constrains intermediate nodes, and deviation angle guarantees link diversity. Simulation and real‐world evaluations demonstrate that SGMR guarantees PD better, and the multipath transmission quality is improved thanks to enough PD. This paper entitled "SGMR: A Spatial Geometry‐based Multipath Routing Method on Overlay Networks" is completed by Yunchong Guan, Weimin Lei*, Wei Zhang, Hao Li and Songyang Zhang. In frameworks of relay‐based multipath transmission, path diversity (PD) determines the link utilization and congestion/fault‐tolerance of multiple paths. In this paper, we improve PD from geometry perspectives in multipath routing. Motivated by that classical network coordinate (NC) reflects node diversity effectively, we take advantages of NC to reduce correlation between paths. Novel geometric terms are proposed to characterize path diversity, and they are exploited to generate end‐to‐end multiple paths from origin to destination nodes incrementally and iteratively. [ABSTRACT FROM AUTHOR]

Summary: The evolution of distributed and virtualized network services makes service selection difficult, as service providers and their links are becoming open and random. The trust degree of service providers is considered as an effective guidance, but it is unmethodical to establish and maintain a clear and stable trust relationship between them. Traditional solutions of service trust evaluation are not comprehensive and accurate enough, because they generally do not take randomness and fuzziness into account. In this context, a model of service trust evaluation based on clustering fuzzy inference for guiding network service selection is proposed in this paper. Four clustering evaluation indexes are determined, and an evaluation mechanism is established based on the fuzzy membership function. The valuation process is time‐aware, and the fuzzy knowledge base can be iteratively updated to keep the trust degree fresh. Simulation experiments illustrate the feasibility of the proposed model and indicate the superiority of greater performance compared with other similar solutions. The trust evaluation indexes are extracted from the network service scenarios, and the fuzzy inference is implemented after the evaluation index is processed. The trust inference results can guide the selection of network services. The trust degree of service providers is a good guidance for users to select network services. Four clustering evaluation indexes are determined, and an evaluation mechanism is established based on the fuzzy membership function. The valuation process is time‐aware, and the fuzzy knowledge base can be iteratively updated to keep the trust degree fresh. [ABSTRACT FROM AUTHOR]