Dynamic graph embedding learns representation vectors for vertices and edges in a graph that evolves over time. We aim to capture and embed the evolution of vertices' temporal connectivity. Existing work studies the vertices' dynamic connection changes but neglects the time it takes for edges to evolve, failing to embed temporal linkage information into the evolution of the graph. To capture vertices' temporal linkage evolution, we model dynamic graphs as a sequence of snapshot graphs, appending the respective timespans of edges (ToE). We co-train a linear regressor to embed ToE while inferring a common latent space for all snapshot graphs by a matrix-factorization-based model to embed vertices' dynamic connection changes. Vertices' temporal linkage evolution is captured as their moving trajectories within the common latent representation space. Our embedding algorithm converges quickly with our proposed training methods, which is very time efficient and scalable. Extensive evaluations on several datasets show that our model can achieve significant performance improvements, i.e. 22.98% on average across all datasets, over the state-of-the-art baselines in the tasks of vertex classification, static and time-aware link prediction, and ToE prediction.

Visual appeal has been shown to influence perceptions of usability and credibility, and we hypothesize that something similar is happening with user judgments of website security: What is beautiful is secure . Web certificates provide reliable information about a website’s level of security, presented in browser interfaces. Users should use this to inform their trust decisions online, but evidence from laboratory studies and real-world usage suggests that they do not. We conducted two studies—one in lab, and one online—in which participants view and interact with websites with high and low visual appeal, and various security levels, and then make security-related judgments. In both studies, participants consistently rated visually appealing websites as more secure, and indicated they would be more likely to enter sensitive information into visually appealing websites—even when they were less secure. Our results provide evidence that users rely on visual appeal when making security and trust decisions on websites. We discuss how these results may be used to help users.

Missing values appearing in multivariate time series often prevent further and in-depth analysis in real-world applications. To handle those missing values, advanced multivariate time series imputation methods are expected to (1) consider bi-directional temporal correlations, (2) model cross-variable correlations, and (3) approximate original data's distribution. However, most of existing approaches are not able to meet all the three above-mentioned requirements. Drawing on advances in machine learning, we propose BRNN-GAN, a generative adversarial network with bi-directional RNN cells. The BRNN cell is designed to model bi-directional temporal and cross-variable correlations, and the GAN architecture is employed to learn original data's distribution. By conducting comprehensive experiments on two public datasets, the experimental results show that our proposed BRNN-GAN outperforms all the baselines in terms of achieving the lowest Mean Absolute Error (MAE).

Repetitive activities like breathing and walking account for a large fraction of human activities. Monitoring these activities with sensing technology plays a vital role in numerous applications ranging from health monitoring to manufacturing management. Over the last decade, traditional machine learning approaches and recent end-to-end deep learning paradigms have achieved massive successes in human activity recognition. However, these approaches are mostly scenario dependent and computationally expensive. Moreover, real-world repetitive activities may have varying time intervals between each repetition, which invalidate existing sliding window methods. In this paper, we propose STEM, a Scalable Template Extraction Method for scenario independent monitoring of repetitive activities with varying intervals. Instead of using sliding windows, we detect and locate the appearance of repeating patterns based on the Matrix Profile. Distributional features are then extracted from the identified patterns such that domain knowledge can be avoided. The approach is efficient and robust as shown by the evaluation on three public datasets, in which around 95% of the undesired computation were eliminated with up to 4% accuracy improvement. It is also generic as demonstrated by a use case of respiration rate estimation using wireless signals.

A successive similar pattern (SSP) is a series of similar sequences that occur consecutively at non-regular intervals in time series. Mining SSPs could provide valuable information without a priori knowledge, which is crucial in many applications ranging from health monitoring to activity recognition. However, most existing work is computationally expensive, focuses only on periodic patterns occurring in regular time intervals, and is unable to recognize patterns containing multiple periods. Here we investigate a more general problem of finding similar patterns occurring successively, in which the similarity between patterns is measured by the z -normalized Euclidean distance. We propose a linear time, robust method, called Multiple-length Successive sIMilar PAtterns Detector (mSIMPAD), that mines SSPs of multiple lengths, making no assumptions regarding periodicity. We apply our method on the detection of repetitive movement using a wearable inertial measurement unit. The experiments were conducted on three public datasets, two of which contain simple walking and idle data, whereas the third is more complex and contains multiple activities. mSIMPAD achieved F-score improvements of 3.2% and 6.5%, respectively, over the simple and complex datasets compared to the state-of-the-art walking detector. In addition, mSIMPAD is scalable and applicable to real-time applications since it operates in linear time complexity.

Autonomous, arbitrary pattern formation is one of the most critical applications in multi-robot systems, where robots are required to form into circles, lines, and meshes or any other desired configuration. This task is important in military applications, search and rescue operations, and visual inspection of infrastructure and equipment tasks to name a few. Most existing works are very rigid, and only able to form certain shapes, where slight target changes can cause failure in the predefined pattern-specific rules and trigger algorithm redesign. We propose a novel, deep reinforcement learning-based method that generates general-purpose pattern formation strategies, in the form of deep neural networks (DNN), for any target pattern. Our method uses the trial-and-error feedback of each round of training to gradually generate the pattern formation strategy. Thus, robots are able to query the trained DNN model to select their optimal directions and speeds in a fully distributed manner. Considering that reinforcement learning models do not perform well with large state spaces and highly variant training samples, we employ auto-encoders to learn the condensed representation for each state and compute model-free policy gradients for arbitrary pattern formation. We experimentally show that groups of robots are able to form various general target patterns while minimizing the number of completion time steps.

Recent advances in robotics technology have made it practical to deploy a large number of inexpensive robots in a wide range of application domains. In many of those applications, a group of autonomous robots is required to form a predefined geometric shape such as a line or a circle. This problem, namely pattern formation problem, is one of the most important coordination problems in multi-robot systems. A particular pattern extensively studied in literature is the uniform circle, and the corresponding problem is called uniform circle formation. In uniform circle formation, a set of simple mobile robots (asynchronous, autonomous), starting from arbitrary positions on the plane, have to arrange themselves on the vertices of a regular polygon eventually. Towards addressing the problem, existing works usually make conveniently strong assumptions, i.e., the robots are regarded as mass points and have unlimited sensing and communication range. The question of whether the robots with actual size and limited sensing and communication range could form a uniform circle, to our knowledge, has remained open. In this paper, we propose a new approach towards addressing this issue. Three phases, consensus on the circle, circle formation, and uniform transformation, constitute our approach. Inside our approach, there are some new distributed algorithms such as convex hull construction and cardinality estimation. Simulation result, theoretical analysis, and successful deployment have shown the effectiveness and practicability of our approach.

Summary The segmentation of a shape into a series of meaningful parts is a fundamental problem in shape analysis and part‐based object representation. However, it is difficult to make the result of shape segmentation accord with the expectations of humans performing the same task. There is still a need for an effective way to segment the shape although a variety of methods have been proposed. In this paper, we present a novel shape decomposition algorithm, which is implemented in a coarse‐to‐fine manner, taking into account the critical points on the silhouette. First, a part‐cut hypotheses candidate set is generated and classified into 2 categories. Then, the hypotheses with adjacent endpoints are determined first, and later, the other kinds of hypotheses are finely determined by our presented measures such as chord arc ratio and inner angle. We note that the proposed coarse‐to‐fine decomposition conforms to the mechanism of human vision. The extensive experimental results on a large set of shapes show that our algorithm can generate shape decomposition results that better accord with human intuition compared to competing algorithms.

Organizing shapes by convex parts is a fundamental procedure for many shape-related applications. However, convexity is sensitive to noise and shape variations. Recent publications in the field concentrated on decomposing shapes into near-convex parts. Although a variety of methods have been presented, there is still a need for a robust and versatile method, especially when a shape possesses long curved branches such as a lizard with a long curved tail. It is difficult to capture the tail as a whole part because its concavity is too high based on classic measures. To address this issue, we propose a `Visibility Range', novel shape signature in this paper. Visibility range reaches low values for points in concave regions and high values in convex regions. Moreover, a novel concavity measure based on visibility range is presented. Compared to previous measures, the novel measure describes long curved branches better. With these, a simple but effective shape decomposition algorithm is designed. The decomposition is formulated as a problem of detecting points with extreme visibility range in a visibility matrix. Extensive experiments have been done on shapes with various kinds of near-convex parts, demonstrating that the proposed method is more robust and effective than the state-of-art methods based on other concave-convex features.

We introduce SmartGuide, a light-weighted and efficient approach to localize and recognize a distant unknown building. Our approach relies on shooting only a single photo of a target building via a smartphone and a local 2D Google map. SmartGuide first extracts a partial top view contour of a building from its side-view photo by applying vanishing point and the Manhattan World Assumption, and then fetches a candidate building set from a local 2D Google map based on smartphone's GPS readings. Partial top view shape, orientation and distance relative to the camera are used as input parameters in a probability model, which adversely recognizes the best candidate building in the local map. Our model is developed based on kernel density estimation that helps reduce noise in the smartphone sensors, such as GPS readings and camera ray direction reported by noisy accelerometer and compass. Experimental results demonstrate that our approach recognizes buildings ranging from 20m to 520m and achieves 92.7% accuracy in downtown areas where the Manhattan World Assumption is applicable. In addition, the processing time is no more than 6 seconds for 87% of cases. Compared with existing building localization schemes, SmartGuide offers numerous advantages. Our method avoids taking multiple photos, intricate 3D reconstruction or any initial deployment cost of database construction, making it faster and less labor-intensive than existing solutions.

Summary This paper focuses on the topology structure of interconnection networks. To overcome drawbacks in the existing hypercube structure, we present an exchanged folded hypercube (EFH) structure, which is an improvement of the exchanged hypercube. Compared with the existing hypercube structures, EFH shows better performance in terms of many metrics such as smaller diameter, lower cost factor, and constant node degree. In this paper, we first introduce the structure of an EFH; then, we propose a routing algorithm and a load‐balancing algorithm for EFHs. Finally, we analyze the fault tolerance characteristics of EFHs including fault diameter and the cost effectiveness factor. Copyright © 2015 John Wiley & Sons, Ltd.

In this paper, we focus on the cyber-physical system consisting of interdependent physical-resource and computational-resource networks, e.g., smart power grids, automated traffic control system, and wireless sensor and actuator networks, where the physical-resource and computational-resource network are connected and mutually dependent. The failure in physical-resource network might cause failures in computational-resource network, and vice versa. A small failure in either of them could trigger cascade of failures within the entire system. We aim to investigate the issue of cascading failures occur in such system. We propose a typical and practical model by introducing the interdependent complex network. The interdependence between two networks is practically defined as follows: Each node in the computational-resource network has only one support link from the physical-resource network, while each node in physical-resource network is connected to multiple computational nodes. We study the effect of cascading failures using percolation theory and present detailed mathematical analysis of failure propagation in the system. We analyze the robustness of our model caused by random attacks or failures by calculating the size of functioning parts in both networks. Our mathematical analysis proves that there exists a threshold for the proportion of faulty nodes, above which the system collapses. Using extensive simulations, we determine the critical values for different system parameters. Our simulation also shows that, when the proportion of faulty nodes approaching critical value, the size of functioning parts meets a second-order transition. An important observation is that the size of physical-resource and computational-resource networks, and the ratio between their sizes do not affect the system robustness.

Due to the bandwidth limitation in wireless networks, transmission overhead is a big problem in Mobile Visual Search (MVS). Existing work proposes transmitting the compressed local feature descriptors instead of the query image to reduce the transmission overhead. Although many kinds of compressed descriptors are proposed, designing a suitable lossless compressed descriptor has proven elusive. In this paper, we propose a novel framework for MVS with low transmission overhead rather than focusing on compressed descriptors. The key point of the proposed framework is to migrate the vector quantization in the bag of visual words model from the server to the client. In this framework, no matter what descriptors are used, the client only transmits the ID numbers of the visual words to the server, thereby reaching the minimal possible transmission overhead. To achieve this goal, we present vocabulary decomposition by which we can decompose the large vocabulary into several small ones satisfying storage constraints on mobile devices. In this paper, we first formulate vocabulary decomposition as an optimization problem. We then present Joint Product Quantization (JPQ) and Joint Optimized Product Quantization (JOPQ) to address the proposed optimization problem. Finally , we conduct a large number of simulation experiments and real experiments. The experimental results show that the proposed framework outperforms the existing framework by reducing more than 95% of the transmission overhead.

We propose a new decentralized access control scheme for secure data storage in clouds that supports anonymous authentication. In the proposed scheme, the cloud verifies the authenticity of the series without knowing the user's identity before storing data. Our scheme also has the added feature of access control in which only valid users are able to decrypt the stored information. The scheme prevents replay attacks and supports creation, modification, and reading data stored in the cloud. We also address user revocation. Moreover, our authentication and access control scheme is decentralized and robust, unlike other access control schemes designed for clouds which are centralized. The communication, computation, and storage overheads are comparable to centralized approaches.

A shape signature is defined as any 1-D function on a shape, which is a compact and concise representation for some essence of the shape. Although a variety of shape signatures are proposed and utilized in shape retrieval and recognition tasks, the existing signatures cannot yet provide entirely satisfactory solutions to describe the shape variations well, especially when significant noise or articulation occurs. Motivated by the fact that electrical charge distributions are almost the same for similar shapes but not vice versa when shapes reach their electrical equilibrium condition, we propose a novel shape signature based on the electrical charge distribution on the shape (ECDS). Compared to other shape descriptors, ECDS is more intuitively and robust, which is computed in a global manner. Furthermore, as well as being invariant to translation, scale and rotation, ECDS is articulation insensitive and therefore exhibits better performance by the introduction of generalized coulomb potentials. This allows it to better match shapes whose parts can move independently, such as scissors. Finally, numerous experiments have done on public databases, demonstrating that ECDS has the above properties and compares well with other shape descriptors in many kinds of shape retrieval and recognition tasks.

In this paper, we propose a new privacy preserving authenticated access control scheme for securing data in clouds. In the proposed scheme, the cloud verifies the authenticity of the user without knowing the user's identity before storing information. Our scheme also has the added feature of access control in which only valid users are able to decrypt the stored information. The scheme prevents replay attacks and supports creation, modification, and reading data stored in the cloud. Moreover, our authentication and access control scheme is decentralized and robust, unlike other access control schemes designed for clouds which are centralized. The communication, computation, and storage overheads are comparable to centralized approaches.

The goal of image segmentation is to partition an image into regions that are internally homogeneous and heterogeneous with respect to neighbouring regions. Recently, a link shifting based pyramidal segmentation method was proposed to resolve existing problems with elongated regions. In this paper, we propose further improvements by replacing pixel intensities at the base level with pixel level higher order local auto-correlation (HLAC) feature vectors over greyscale, RGB, and CIV channels. Thereby, rich texture-like information is incorporated into segmentation. We propose a normalized distance formula between HLAC vectors, where each component contributes with physically same unit. The new algorithms were tested on a set of Landsat images over forested areas, and compared with a non-HLAC variant and several other existing segmentation algorithms. A significant improvement in segmentation quality was achieved compared to non-HLAC variants, and it also gave better results than other existing algorithms on most examples.

This paper describes a new line segment detection and extraction algorithm for computer vision, image segmentation, and shape recognition applications. This is an important pre processing step in detecting, recognizing and classifying military hardware in images. This algorithm uses a compilation of different image processing steps such as normalization, Gaussian smooth, thresholding, and Laplace edge detection to extract edge contours from colour input images. Contours of each connected component are divided into short segments, which are classified by their orientation into nine discrete categories. Straight lines are recognized as the minimal number of such consecutive short segments with the same direction. This solution gives us a surprisingly more accurate, faster and simpler answer with fewer parameters than the widely used Hough Transform algorithm for detecting lines segments among any orientation and location inside images. Its easy implementation, simplicity, speed, the ability to divide an edge into straight line segments using the actual morphology of objects, inclusion of endpoint information, and the use of the OpenCV library are key features and advantages of this solution procedure. The algorithm was tested on several simple shape images as well as real pictures giving more accuracy than the actual procedures based in Hough Transform. This line detection algorithm is robust to image transformations such as rotation, scaling and translation, and to the selection of parameter values.

Broadcasting is a data communication task in which one processor sends the same message to all other processors. Routing is a task where a source processor sends a message to a destination processor. A faulty node is in an error state and cannot participate in the activities or the communication in a given network. In this paper, we consider the family of mesh networks, which include the mesh connected computer (MCC), k-dimensional mesh, torus, and k-ary n-cube. Our goal is to design routing and broadcasting algorithms which will use local knowledge of faults, no additional resources, will work for an arbitrary number and structure of faults, will guarantee delivery to all nodes connected to the source, and will remain optimal in a fault free mesh. We did not find any solution in literature to satisfy these desirable properties. Our routing and broadcasting schemes for MCCs and tori, and our broadcasting algorithm for the all-port model on any faulty mesh network satisfy all of these properties. For routing and broadcasting in a one-port model in higher dimensions, a condition on fault structure needs to be met. We propose a new broadcasting algorithm which guarantees delivery to all processors connected to the source in the all-port model of faulty meshes. We then describe a routing algorithm that guarantees delivery in faulty MCCs and tori, the connectivity of the source and destination being the only obvious requirement. The algorithm can be extended to faulty k-D meshes and k-ary n-cubes, where the delivery will be guaranteed if healthy nodes in every 2-D submesh (sub-tori) remain connected. We then describe broadcasting algorithms for the one-port model, which again guarantee delivery to all connected processors in two-dimensional cases, and guarantee delivery in k-dimensional cases if healthy processors in every 2-D submesh (sub-tori) remain connected.