Automatic thresholding is an important technique for rail defect detection, but traditional methods are not competent enough to fit the characteristics of this application. This paper proposes the Maximum Weighted Object Correlation (MWOC) thresholding method, fitting the features that rail images are unimodal and defect proportion is small. MWOC selects a threshold by optimizing the product of object correlation and the weight term that expresses the proportion of thresholded defects. Our experimental results demonstrate that MWOC achieves misclassification error of 0.85%, and outperforms the other well-established thresholding methods, including Otsu, maximum correlation thresholding, maximum entropy thresholding and valley-emphasis method, for the application of rail defect detection.

At this stage, research in the field of Few-shot image classification (FSC) has made good progress, but there are still many difficulties in the field of Few-shot object detection (FSOD). Almost all of the current FSOD methods face catastrophic forgetting problems, which are manifested in that the accuracy of base class recognition will drop seriously when acquiring the ability to recognize Novel classes. And for many methods, the accuracy of the model will fall back as the class increases. To address this problem we propose a new memory-based method called Memorable Faster R-CNN (MemFRCN), which makes the model remember the categories it has already seen. Specifically, we propose a new tow-stage object detector consisting of a memory-based classifier (MemCla), a fully connected neural network classifier (FCC) and an adaptive fusion block (AdFus). The former stores the embedding vector of each category as memory, which enables the model to have memory capabilities to avoid catastrophic forgetting events. The final part fuses the outputs of FCC and MemCla, which can automatically adjust the fusion method of the model when the number of samples increases so that the model can achieve better performance under various conditions. Our method can perform well on unseen classes while maintaining the detection accuracy of seen classes. Experimental results demonstrate that our method outperforms other current methods on multiple benchmarks.

We propose and experimentally demonstrate an all-optical broadband wavelength conversion scheme with simultaneous power amplification based on a pump-modulated fiber optic parametric amplifier (FOPA). All-optical tunable wavelength conversion from one to two wavelengths was achieved with ≥13 dB extinction ratio and <2.7-dB power penalty, accompanied by a high (≥37 dB) and flat ( 3 dB variation) FOPA gain spectrum over 47 nm.

Convolutional neural network (CNN) based vehicle re-identificatioin (ReID) inevitably has many disadvantages, such as information loss caused by downsampling operation. Therefore we propose a vision transformer (Vit) based vehicle ReID method to solve this problem. To improve the feature representation of vision transformer and make full use of additional vehicle information, the following methods are presented. (I) We propose a Quadratic Split Architecture (QSA) to learn both global and local features. More precisely, we split an image into many patches as “global part” and further split them into smaller sub-patches as “local part”. Features of both global and local part will be aggregated to enhance the representation ability. (II) The Auxiliary Information Embedding (AIE) is proposed to improve the robustness of the model by plugging a learnable camera/viewpoint embedding into Vit. Experimental results on several benchmarks indicate that our method is superior to many advanced vehicle ReID methods.

Ground truth based image segmentation evaluation paradigm plays an important role in objective evaluation of segmentation algorithms. So far, many evaluation methods in terms of comparing clusterings in machine learning field have been developed. However, most traditional pairwise similarity measures, which only compare a machine generated clustering to a “true” clustering, have their limitations in some cases, e.g. when multiple ground truths are available for the same image. In this letter, we propose utilizing an information theoretic measure, named NJMI (Normalized Joint Mutual Information), to handle the situations which the pairwise measures can not deal with. We illustrate the effectiveness of NJMI for both unsupervised and supervised segmentation evaluation.

MapReduce is an effective framework for processing large datasets in parallel over a cluster. Data locality and data skew on the reduce side are two essential issues in MapReduce. Improving data locality can decrease network traffic by moving reduce tasks to the nodes where the reducer input data is located. Data skew will lead to load imbalance among reducer nodes. Partitioning is an important feature of MapReduce because it determines the reducer nodes to which map output results will be sent. Therefore, an effective partitioner can improve MapReduce performance by increasing data locality and decreasing data skew on the reduce side. Previous studies considering both essential issues can be divided into two categories: those that preferentially improve data locality, such as LEEN, and those that preferentially improve load balance, such as CLP. However, all these studies ignore the fact that for different types of jobs, the priority of data locality and data skew on the reduce side may produce different effects on the execution time. In this paper, we propose a naive Bayes classifier based partitioner, namely, BAPM, which achieves better performance because it can automatically choose the proper algorithm (LEEN or CLP) by leveraging the naive Bayes classifier, i.e., considering job type and bandwidth as classification attributes. Our experiments are performed in a Hadoop cluster, and the results show that BAPM boosts the computing performance of MapReduce. The selection accuracy reaches 95.15%. Further, compared with other popular algorithms, under specific bandwidths, the improvement BAPM achieved is up to 31.31%.

Web Service Composition (WSC) has been well recognized as a convenient and flexible way of service sharing and integration in service-oriented application fields. WSC aims at selecting and composing a set of initial services with respect to the Quality of Service (QoS) values of their attributes (e.g., price), in order to complete a complex task and meet user requirements. A major research challenge of the QoS-aware WSC problem is to select a proper set of services to maximize the QoS of the composite service meeting several QoS constraints upon various attributes, e.g. total price or runtime. In this article, a fast algorithm based on QoS-aware sampling (FAQS) is proposed, which can efficiently find the near-optimal composition result from sampled services. FAQS consists of five steps as follows. 1) QoS normalization is performed to unify different metrics for QoS attributes. 2) The normalized services are sampled and categorized by guaranteeing similar number of services in each class. 3) The frequencies of the sampled services are calculated to guarantee the composed services are the most frequent ones. This process ensures that the sampled services cover as many as possible initial services. 4) The sampled services are composed by solving a linear programming problem. 5) The initial composition results are further optimized by solving a modified multi-choice multi-dimensional knapsack problem (MMKP). Experimental results indicate that FAQS is much faster than existing algorithms and could obtain stable near-optimal result.

There are a great amount of various resources described in many different ways for service oriented grid environment, while traditional grid resource discovery methods could not fit more complex future grid system. Therefore, this paper proposes a novel grid resource discovery method based on association rule hypergraph partitioning algorithm which analyzes user behavior in history transaction records to provide personality service for user. And this resource discovery method gives a new way to improve resource retrieval and management in grid research.

An unsupervised algorithm is proposed for learning overcomplete topographic representations of nature image. Our method is based on Independent Component Analysis (ICA) model due to its superiority on feature extraction, and overcomes the weakness of traditional method in fast overcomplete learning. Besides, the learnt topographic representation, resembling receptive fields of complex cells, can be used as descriptors to extract invariant features. Recognition experiments on Caltech-101 dataset confirm that these complex cell descriptors are not only efficient in feature extraction but achieve comparable performances to traditional descriptors.

In this letter, a local characteristic image restoration based on convolutional neural network is proposed. In this method, image restoration is considered as a classification problem and images are divided into several sub-blocks. The convolutional neural network is used to extract and classify the local characteristics of image sub-blocks, and the different forms of the regularization constraints are adopted for the different local characteristics. Experiments show that the image restoration results by the regularization method based on local characteristics are superior to those by the traditional regularization methods and this method also has lower computing cost.

Text classification is a fundamental task in natural language processing, which finds extensive applications in various domains, such as spam detection and sentiment analysis. Syntactic information can be effectively utilized to improve the performance of neural network models in understanding the semantics of text. The Chinese text exhibits a high degree of syntactic complexity, with individual words often possessing multiple parts of speech. In this paper, we propose BRsyn-caps, a capsule network-based Chinese text classification model that leverages both Bert and dependency syntax. Our proposed approach integrates semantic information through Bert pre-training model for obtaining word representations, extracts contextual information through Long Short-term memory neural network (LSTM), encodes syntactic dependency trees through graph attention neural network, and utilizes capsule network to effectively integrate features for text classification. Additionally, we propose a character-level syntactic dependency tree adjacency matrix construction algorithm, which can introduce syntactic information into character-level representation. Experiments on five datasets demonstrate that BRsyn-caps can effectively integrate semantic, sequential, and syntactic information in text, proving the effectiveness of our proposed method for Chinese text classification.

Boundary detection is one of the most studied problems in computer vision. It is the foundation of contour grouping, and initially affects the performance of grouping algorithms. In this paper we propose a novel boundary detection algorithm for contour grouping, which is a selective attention guided coarse-to-fine scale pyramid model. Our algorithm evaluates each edge instead of each pixel location, which is different from others and suitable for contour grouping. Selective attention focuses on the whole saliency objects instead of local details, and gives global spatial prior for boundary existence of objects. The evolving process of edges through the coarsest scale to the finest scale reflects the importance and energy of edges. The combination of these two cues produces the most saliency boundaries. We show applications for boundary detection on natural images. We also test our approach on the Berkeley dataset and use it for contour grouping. The results obtained are pretty good.

The key problem of object-based attention is the definition of objects, while contour grouping methods aim at detecting the complete boundaries of objects in images. In this paper, we develop a new contour grouping method which shows several characteristics. First, it is guided by the global saliency information. By detecting multiple boundaries in a hierarchical way, we actually construct an object-based attention model. Second, it is optimized by the grouping cost, which is decided both by Gestalt cues of directed tangents and by region saliency. Third, it gives a new definition of Gestalt cues for tangents which includes image information as well as tangent information. In this way, we can improve the robustness of our model against noise. Experiment results are shown in this paper, with a comparison against other grouping model and space-based attention model.

Since ISAR is widely applied in many occasions and provides high resolution images of the target, ISAR countermeasures are attracting more and more attention. Most of the present methods of deception jamming are not suitable for engineering realization due to the heavy computation load or the large calculation delay. Deception jamming against ISAR requires large computation resource and real-time performance algorithms. Many studies on false target jamming assume that the jammer is able to receive the target echo or transmit the jamming signal to the real target, which is sometimes not possible. How to impose the target property onto the intercepted radar signal is critical to a deception jammer. This paper proposes a jamming algorithm based on parallel convolution and one-bit quantization. The algorithm is able to produce a single false target on ISAR image by the jammer itself. The requirement for computation resource is within the capabilities of current digital signal processors such as FPGA or DSP. The method processes the samples of radar signal in parallel and generates the jamming signal at the rate of ADC data, solving the problem that the real-time performance is not satisfied when the input data rate for convolution is far higher than the clock frequency of FPGA. In order to reduce the computation load of convolution, one-bit quantization is utilized. The complex multiplication is implemented by logical resources, which significantly reduces the consumption of FPGA multipliers. The parallel convolution jamming signal, whose date rate exceeds the FPGA clock rate, is introduced and analyzed in detail. In theory, the bandwidth of jamming signal can be half of the sampling frequency of high speed ADC, making the proposed jamming algorithm able to counter ultra-wideband ISAR signals. The performance and validity of the proposed method are verified by simulations. This jamming method is real-time and capable of producing a false target of large size at the low cost of FPGA device.

An all-optical phase multiplexing scheme for phase-modulated signals is proposed and experimentally demonstrated using four-wave mixing (FWM) in a highly-nonlinear fiber (HNLF). Two 10-Gb/s π/2-shifted differential phase-shift keying (DPSK) wavelength-division multiplexing (WDM) signals are experimentally demonstrated to be converted and phase-multiplexed into a 20-Gb/s differential quadrature phase-shift keying (DQPSK) signal with non-return-to-zero (NRZ) and return-to-zero (RZ) formats, respectively. Experimental results show that, due to phase-modulation-depth doubling effect and phase multiplexing effect in the FWM process, a DQPSK signal is successfully generated through the proposed all-optical phase multiplexing with improved receiver sensitivity and spectral efficiency.

Salient edge detection which is mentioned less frequently than salient point detection is another important cue for subsequent processing in computer vision. How to find the salient edges in natural images is not an easy work. This paper proposes a simple method for salient edge detection which preserves the edges with more salient points on the boundaries and cancels the less salient ones or noise edges in natural images. According to the Gestalt Principles of past experience and entirety, we should not detect the whole edges in natural images. Only salient ones can be an advantageous tool for the following step just like object tracking, image segmentation or contour detection. Salient edges can also enhance the efficiency of computing and save the space of storage. The experiments show the promising results.

This letter describes a permutation attack (PA) to the subsampling-based watermarking scheme where the high correlations between subimages obtained by subsampling the original image are used for watermark embedding. We show that the correlations can also be easily used to attack the watermarking scheme through a simple permutation procedure, while the quality degradation of attacked watermarked image is visually acceptable. Experimental results show the efficiency of the proposed attack algorithm.

ARM chips with low energy consumption and low-cost investment have been rapidly applied to smart office and smart entertainment including cloud mobile phones and cloud games. This paper first summarizes key technologies and development status of the above scenarios including CPU, memory, IO hardware virtualization characteristics, ARM hypervisor and container, GPU virtualization, network virtualization, resource management and remote transmission technologies. Then, in view of the current lack of publicly referenced ARM cloud constructing solutions, this paper proposes and constructs an implementation framework for building an ARM cloud, and successively focuses on the formal definition of virtualization framework, Android container system and resource quota management methods, GPU virtualization based on API remoting and GPU pass-through, and the remote transmission technology. Finally, the experimental results show that the proposed model and corresponding component implementation methods are effective, especially, the pass-through mode for virtualizing GPU resources has higher performance and higher parallelism.

This paper combines the LBP operator and the active contour model. It introduces a salient gradient vector flow snake (SGVF snake), based on a novel edge map generated from the salient boundary point image (SBP image). The MDGVM criterion process helps to reduce feature detail and background noise as well as retaining the salient boundary points. The resultant SBP image as an edge map gives powerful support to the SGVF snake because of the inherent combination of the intensity, gradient and texture cues. Experiments prove that the MDGVM process has high efficiency in reducing outliers and the SGVF snake is a large improvement over the GVF snake for contour detection, especially in natural images with low contrast and small texture background.

Analysis of the trust network proves beneficial to the users in Online Social Networks (OSNs) for decision-making. Since the construction of trust propagation paths connecting unfamiliar users is the preceding work of trust inference, it is vital to find appropriate trust propagation paths. Most of existing trust network discovery algorithms apply the classical exhausted searching approaches with low efficiency and/or just take into account the factors relating to trust without regard to the role of distrust relationships. To solve the issues, we first analyze the trust discounting operators with structure balance theory and validate the distribution characteristics of balanced transitive triads. Then, Maximum Indirect Referral Belief Search (MIRBS) and Minimum Indirect Functional Uncertainty Search (MIFUS) strategies are proposed and followed by the Optimal Trust Inference Path Search (OTIPS) algorithms accordingly on the basis of the bidirectional versions of Dijkstra's algorithm. The comparative experiments of path search, trust inference and edge sign prediction are performed on the Epinions data set. The experimental results show that the proposed algorithm can find the trust inference path with better efficiency and the found paths have better applicability to trust inference.