Concerning the low efficiency of calculating flow accumulation on high resolution digital terrain data, a parallel algorithm was put forward based on the Compute Unified Device Architecture (CUDA) and flooding model. Based on the technology of Graphic Processing Unit (GPU), two strategies were designed to improve the speed of the extraction. Firstly, the calculation of flow accumulation was divided into a plurality of independent tasks for parallel processing. Secondly, the time of data exchange was reduced through the asynchronous data transmission. The experimental results show that the efficiency of the parallel algorithm is superior of the serial algorithm. The acceleration of river network extraction reached 62 times in NVIDIA Geforce GTX660 for 600 MB DEM data with 9784×8507 grid size.
To get a path for a continuum robot in the environment like the aircraft fuel tank, a path planning algorithm based on regional-advance strategy was proposed. By combining with the mechanical constraints of the robot, the method could ensure that arbitrary points can be reached in the single cabin. With the flexibility of movement, but the hyper-redundant freedom degree of the continuum robot brings about both the multiple path solutions in three-dimensional space and high time complexity. The approach based on dimension reduction, which is transforming the planning in three-dimensional space into that in two-dimensional plane, was presented to reduce the computing complexity. The single cabin of the aircraft fuel tank was divided to two regions, and the planning strategy was determined by the regional location of the target point. Finally, the Matlab simulation experiments were carried out, and the practicability and effectiveness of the proposed method were verified.
OpenFlow enhances the Quality of Service (QoS) of traditional networks, but it has disadvantage that its network session identification efficiency is low and the network packet forwarding path is poor and so on. On the basis of the current study of the OpenFlow, GPU OpenFlow Massive Data Network Analysis (GOMDI) model was proposed by this paper, through integrating the biological sequence algorithm, GPU parallel computing algorithm and machine learning methods. The network session matching algorithm and path selection algorithm of GOMDI were designed. The experimental results show that the speedup of the GOMDI network session matching algorithm is over 300 higher than the CPU environment in real network, and the network packet loss rate of its path selection algorithm is lower than 5%, the network delay is less than 20ms. Thus, the GOMDI model can effectively improve network performance and meet the needs of the real-time processing for massive information in big data environment.
To deal with the under-resourced labeled pronunciation data in mispronunciation detection, some other data were used to improve the discriminability of feature in the framework of Tandem system. Taking Chinese learning of English as object, unlabeled data, native Mandarin data and native English data which can be relatively easily accessed were selected as the assisted data. The experiments show that these types of data can effectively improve the performance of system, and the unlabeled data performs the best. And the effect to system performance was discussed with different length of frame context, the shallow and deep neural network typically represented by Multi-Layer Perception (MLP) and Deep Neural Network (DNN), and different structure of Tandem feature. Finally the strategy of merging multiple data streams was used to further improve the system performance, and the best system performance was achieved by combining the DNN based unlabeled data stream and native English stream. Compared with the baseline system, the recognition accuracy is increased by 7.96%, and the diagnostic accuracy of mispronunciation type is increased by 14.71%.
Context-aware computing is one of the indispendable key technologies for developing and deploying intelligent applications. Whether the context can really contribute to the applications mainly depends on the following two aspects: the first is how to continuously and steadily monitor/capture high-quality context information from the dynamic interaction environment, the second is how to reason on contexts and make adaptation decisions for applications. A layered middleware infrastructure was designed to achieve the above objectives. It afforded effective supports for not only gathering, managing, interpreting and making use of context information to dynamically adapt applications, but also selecting the most appropriate context sources dynamically at runtime based upon Qualities of Context (QoC). Finally, the experimental results show that the middleware can quickly and efficiently support the development and deployment of context-aware applications, and has better computing performance in comparison with others.
In the field of social influence propagation, social network as the media plays a fundamental role in interaction between social individuals and disseminating information or views. First, the definition of social influence and the essential attribute of social influences as the social relevance were discussed. Then, the independent cascade model and the linear threshold model were expounded, as well as greedy algorithm and heuristic algorithms which can confirm the influential people. Finally, the new trend of research on social influence, such as community-based influence maximization algorithm and research on the influence of multiple subjects and multiple behaviors were deeply analyzed.
Concerning the influence of resident's psychological factors on travel mode choice in the actual travel, a travel mode choice model based on prospect theory was established and a choice method more according to human thinking habits was put forward. Considering psychological reference points of travel time and travel cost comprehensively, satisfied travel mode to resident was obtained. The influence of reference point on travel mode was analyzed by comparing changes of comprehensive prospect value under different reference points. Finally an example gave the application of this travel mode choice method. The experimental results show that residents in the minority whose expectation of travel time is lower prefer bus travel, although the comprehensive prospect value changes of taxi and private car are identical. More residents tend to use private car mode, which is consistent with the fact. The proposed method provides a new way to predict resident travel mode.
Concerning the present situation that Quality of Service (QoS) evaluation methods ignore the implicit service quality assessment and lead to inaccurate results, a service evaluation method that comprehensively considered explicit and implicit quality attributes was put forward. Explicit quality attributes were expressed in vector form, using service quality assessment model, after quantization, normalization, then evaluation values were calculated; and implicit quality attributes were expressed according to the evaluation on similar users' recommendation. The users' credibility and difference between old and new users were considered in the evaluation process. Finally the explicit and implicit quality evaluation was regarded as the QoS evaluation results. The experiments were performed in comparison with three algorithms by using one million Web Service QoS data. The simulation results show that the proposed method has certain feasibility and accuracy.