With the exploding growth of data, the computational complexity required by learning Support Vector Machine (SVM) lays a heavy burden on real-world applications. To address this issue, parallel computational technique...
详细信息
ISBN:
(纸本)9781479986989
With the exploding growth of data, the computational complexity required by learning Support Vector Machine (SVM) lays a heavy burden on real-world applications. To address this issue, parallel computational techniques can be employed such as the Graphics Processing Units (GPUs) and MapReduce model. As it is well known, GPUs are microprocessors on a multi-core architecture which reveal high performance in mass data parallel computing, and MapReduce allows computational tasks to be divided into a plurality of parts, distributed to various computing nodes and combined on a single node. In this paper, we propose a GPU-based MapReduce framework to accelerate SVM learning by jointly utilizing the parallel computing power of GPU and MapReduce. Extensive experimental results have verified the effectiveness and efficiency of the proposed approach.
Considering characteristic of mHealth communication and problems of existing methods, this paper presents a real-time communication method for mHealth based on extended XMPP protocol. The method can maintain the role ...
详细信息
Considering characteristic of mHealth communication and problems of existing methods, this paper presents a real-time communication method for mHealth based on extended XMPP protocol. The method can maintain the role status efficiently and reduce data latency during the communication process. Meanwhile, it can be extended flexibly to meet increasing communication demands of mHealth services. Furthermore, a system framework is presented to support telemonitoring scene. Finally, system implementation and feasibility tests verify the effectiveness of the method and framework.
Consider to the defect of traditional features which have high empirical components. A vehicle classification algorithm based on the fusion of higher-layer features of a deep network and traditional features was propo...
详细信息
Consider to the defect of traditional features which have high empirical components. A vehicle classification algorithm based on the fusion of higher-layer features of a deep network and traditional features was proposed. Firstly, the traditional features of PHOG and LBP-EOH were extracted. Secondly, the higher-layer features excavated from the vehicle pictures by deep belief networks were added, making these three kinds of features together by feature fusion. Finally, support vector machine is used to train and classify the vehicle. When the number of training samples is large enough, the algorithm has a significant effect compared to those with traditional features. It can achieve the accuracy of 95% in the six categories of vehicles.
Hybrid sensor network technology is a key component of future ITS applications. In this paper, we propose a hybrid architecture that combined VANETs and roadside WSNs for intelligent navigation. Different from traditi...
详细信息
Hybrid sensor network technology is a key component of future ITS applications. In this paper, we propose a hybrid architecture that combined VANETs and roadside WSNs for intelligent navigation. Different from traditional ITS application, Sensors in WSNs and VANETs are used to perceive and exchange roadside and vehicular information to support the intelligent navigating decision process. We firstly give the system and protocol architecture, and then we discuss the scenarios and use cases of our system in intelligent navigation. After that, we describe the software and hardware implementation of our prototype, conduct a simulation on the discussed scenarios, and present a detailed data communication experimental result to prove the feasibility of our prototype.
With the explosive growth of Internet information,it is more and more important to fetch real-time and related *** it puts forward higher requirement on the speed of webpage classification which is one of common metho...
详细信息
With the explosive growth of Internet information,it is more and more important to fetch real-time and related *** it puts forward higher requirement on the speed of webpage classification which is one of common methods to retrieve and manage *** get a more efficient classifier,this paper proposes a webpage classification method based on locality sensitive hash *** which,three innovative modules including building feature dictionary,mapping feature vectors to fingerprints using Localitysensitive hashing,and extending webpage features are *** compare results show that the proposed algorithm has better performance in lower time than the na?ve bayes one.
Traffic flow prediction plays a key role in many Intelligent Transportation system research and applications. It aims to forecast the forthcoming traffic conditions with the help of historical data. Urban traffic alwa...
详细信息
ISBN:
(纸本)9781538676738;9781538676721
Traffic flow prediction plays a key role in many Intelligent Transportation system research and applications. It aims to forecast the forthcoming traffic conditions with the help of historical data. Urban traffic always has its morning and afternoon peak hours. We also observed that the urban traffic flow can always be divided into main trend data and its residual part. The main trend data presents a similar trend on different days. The residual data is time-variant part which reflects the short-term fluctuation of traffic condition over each day. Enlighted by detrending, Principal Component Analysis (PCA) method is applied to extract the main trend data in this paper. The residual data is obtained by subtracting the main trend data from the overall traffic flow data. Then Long Short-Term Memory (LSTM) model is proposed to predict the residual data. With main trend data and predicted residual data, the urban traffic flow can be predicted by the joint PCA and LSTM approach. Finally, the empirical study demonstrates the propose method outperforms similar traffic prediction models.
It is estimated that the breakthrough in the broad deployment of Internet of Things (IoT) could come from smart cars. Indeed, we have seen multi-facet advances around cars: new material, in vehicle infotainment, drive...
详细信息
ISBN:
(纸本)9781479989386
It is estimated that the breakthrough in the broad deployment of Internet of Things (IoT) could come from smart cars. Indeed, we have seen multi-facet advances around cars: new material, in vehicle infotainment, driverless cars, smart transportation, electrical vehicles, etc. However, in-vehicle-networking has been mainly by wire;the wiring for a car is largely prebuilt during the design phase. With more and more things networked within a car, wiring has taken up 1-2 percent of the total weight. This translates into burning up to 0.1 kilogram fuel over 100 kilometers. On the other hand, the advances in wireless technology, especially the broad acceptance of WirelssHART in the industrial settings, has proved its capability in harsh environments. This paper studies what could happen if we use WirelessHART mesh network for in-vehicle communication. While new wireless network protocols are needed to perform the task of CAN, the dominant in-vehicle fieldbus, WirelessHART could take on the work performed by LIN, the fieldbus for peripheral devices. A detailed study is provided to compare these buses. Road tests were performed, in which a WirelessHART network keeps running for the whole 20 minute period.
Statistical background subtraction has proved to be a robust and effective approach for segmenting and extracting objects without any prior information of the foreground objects. This paper presents two contributions ...
详细信息
Statistical background subtraction has proved to be a robust and effective approach for segmenting and extracting objects without any prior information of the foreground objects. This paper presents two contributions on this topic. The first contribution of this paper proposes a novel approach which introduces the motion mask into the Gaussian Mixture Models to reduce the errors of classical GMMs, which always classifies the moving objects as background incorrectly, and affects the accuracy of the steps followed by, when the objects are still in long periods. The second contribution regards the connected component labeling based on the contour tracking algorithm. Experimental results validate the effectiveness of the proposed approach.
Path restoring is a path searching problem in the time-dependent road network with the time constraints of origin and destination. This paper proposes a path restoring algorithm to find the possible path that vehicles...
详细信息
ISBN:
(纸本)9781467395922
Path restoring is a path searching problem in the time-dependent road network with the time constraints of origin and destination. This paper proposes a path restoring algorithm to find the possible path that vehicles may have been driving along. We mined the vehicle trajectories based on historical GPS data and then build a “popular” intersection graph based on its entropy and frequency. Then the restoring path is searched on the sub-graph of the popular intersection graph. The experiment result shows that the proposed algorithm increases 10% compared to that of using time-dependent fastest path method.
Link similarity is widely applied in measuring the similarity between objects, e.g., web pages, scientific papers and social networks. However, there are a lot of drawbacks in existing methods of measuring link simila...
详细信息
ISBN:
(纸本)9781479973507
Link similarity is widely applied in measuring the similarity between objects, e.g., web pages, scientific papers and social networks. However, there are a lot of drawbacks in existing methods of measuring link similarity. In brief, these methods can not handle some semantic-similar content. Moreover, the computation of them are not accurate in some scenes. In this paper, we present a novel method of measuring link similarity called HSim. It introduces the semantic similarity to calculate the similarity between objects, and overcomes the drawback that existing methods ignore the semantic information of objects. We also develop a novel computation function to make the result of similarity more accurate.
暂无评论