Jia He

Data Flow-Oriented Multi-Path Semantic Web Service Composition Using Extended SPARQL

Semantic Web approaches are often used for Web service description, modeling, semantics discovery, capabilities matching, etc. However, as the primary querying tool for Semantic Web, SPARQL is yet to be deeply explored to support Semantic Web service composition. Therefore the description, modeling and composition of Semantic Web services are usually two-tier. This paper extends SPARQL to support path query, so that SPARQL is used in our service composition framework which finds the top-k shortest data flows that satisfy the user constraints. Experiment results on real-world Web service datasets exhibit its applicable performance compared with service compositions using other SPARQL engines/extensions.

Multi-GPUs Gaussian filtering for real-time big data processing

Gaussian filtering has been extensively used in the field of surface metrology. However, the computing performance becomes a core bottleneck for Gaussian filtering algorithm based applications when facing large-scale and/or real-time data processing. Although researchers tried to accelerate Gaussian filtering algorithm by using GPU (Graphics Processing Unit), single GPU still fail to meet the large-scale and real-time requirements of surface texture micro- and nano-measurements. Therefore, to solve this bottleneck problem, this paper proposes a single node multi-GPUs based computing framework to accelerate the 2D Gaussian filtering algorithm. This paper presents that the devised framework seamlessly integrated the multi-level spatial domain decomposition method and the CUDA stream mechanism to overlap the two main time consuming steps, i.e., the data transfer and GPU kernel execution, such that it can increase concurrency and reduce the overall running time. This paper also tests and evaluates the proposed computing framework with other three conventional solutions by using large-scale measured data extracted from real mechanical surfaces, and the final results show that the proposed framework achieved higher efficiency. It also proved that this framework satisfies the real-time and big data requirements in micro- and nano-surface texture measurement.

Dual-channel CNN for efficient abnormal behavior identification through crowd feature engineering

AbstractThis research has been investigating an automatic and online crowd anomaly detection model by exploring a novel compound image descriptor generated from live video streams. A dual-channel convolutional neural network (DCCNN) has been set up for efficiently processing scene-related and motion-related crowd information inherited from raw frames and the compound descriptor instances. The novelty of the work stemmed from the creation of the spatio-temporal cuboids in online (or near real-time) manner through dynamically extracting local feature tracklets within the temporal space while handling the foreground region-of-interests (i.e., moving targets) through the exploration of Gaussian Mixture Model in the spatial space. Hence, the extracted foreground blocks can effectively eliminate irrelevant backgrounds and noises from the live streams for reducing the computational costs in the subsequent detecting phases. The devised compound feature descriptor, named as spatio-temporal feature descriptor (STFD), is capable of characterizing the crowd attributes through the measures such as collectiveness, stability, conflict and density in each online generated spatio-temporal cuboid. A STFD instance registers not only the dynamic variation of the targeted crowd over time based on local feature tracklets, but also the interaction information of neighborhoods within a crowd, e.g., the interaction force through the K-nearest neighbor (K-NN) analysis. The DCCNN developed in this research enables online identification of suspicious crowd behaviors based on analyzing the live-feed images and their STFD instances. The proposed model has been developed and evaluated against benchmarking techniques and databases. Experimental results have shown substantial improvements in terms of detection accuracy and efficiency for online crowd abnormal behavior identification.n

Dual sub-swarm interaction QPSO algorithm based on different correlation coefficients

ABSTRACT A novel quantum-behaved particle swarm optimization (QPSO) algorithm, the dual sub-swarm interaction QPSO algorithm based on different correlation coefficients (DCC-QPSO), is proposed by constructing master-slave sub-swarms with different potential well centres. In the novel algorithm, the master sub-swarm and the slave sub-swarm have different functinons during the evolutionary process through separate information processing strategies. The master sub-swarm is conducive to maintaining population diversity and enhancing the global search ability of particles. The slave sub-swarm accelerates the convergence rate and strengthens the particles’ local searching ability. With the critical information contained in the search space and results of the basic QPSO algorithm, this new algorithm avoids the rapid disappearance of swarm diversity and enhances searching ability through collaboration between sub-swarms. Experimental results on six test functions show that DCC-QPSO outperforms the traditional QPSO algorithm regarding optimization of multimodal functions, with enhancement in both convergence speed and precision.

Ternary Correlation Quantum-Behaved Particle Swarm Optimization Based on Square Potential Well Model

Potential well type selection is critical for the convergence of the QPSO (Quantum-behaved Particle Swarm Optimization) algorithm. This paper analyzed the motion pattern of particles in square potential well, given the position equation of the particles by solving the Schrödinger equation and proposed the Ternary Correlation QPSO Algorithm Based on Square Potential Well (TC-QSPSO). In this novel algorithm, the internal relations during particles own experience information, group sharing information and the distance from the particles current location to the population mean best position was created by using Copula functions. The simulation results of the test functions show that the improved algorithms outperform the original QPSO algorithm and due to the error gradient information will not be over utilized in square potential well, the particles are easy to jump out of the local optimum, the TC-QSPSO is more suitable to solve the functions with correlative variables.

Efficient Context-Aware Nested Complex Event Processing over RFID Streams

With large scale of utilization of monitoring devices such as RFID, sensors and mobile phones, events are generated in a high-speed fashion. Decisions should be made in real time during business processes. Complex Event Processing (CEP) has become increasingly important for tracking and monitoring anomalies and trends in event streams. Nested event detection of RFID event stream is one of the most import class of queries. Current optimization of nested RFID event detection mainly considers caching intermediate results to reduce re-computation of similar results for nested subexpression. In this paper, we use context information of an RFID scenario to optimize nested event detection. We formalize context of an RFID scenario as spatial and temporal constraints and transform these constraints into rules over a nested NFA. Further, we present rewriting context rules to optimize nested event query plan. Experimental results show that with context information introduced, response time had been reduced greatly compared with counterpart methods.

Efficient complex event processing under boolean model

Existing evaluation techniques for complex event processing mainly target sequence patterns. However, boolean expression represents a broader class of patterns and is widely used to model complex events in practice. In this paper, we study efficient evaluation techniques for complex events modeled as boolean expressions. We propose an evaluation approach based on pseudo-NFA. The efficiency of pseudo-NFA approach is investigated and its optimization techniques are presented. We show that the proposed techniques are theoretically sound and demonstrate by extensive experiments that they perform considerably better than existing alternatives.