Monitoring,understanding and predicting Origin-destination(OD)flows in a city is an important problem for city planning and human activity.Taxi-GPS traces,acted as one kind of typical crowd sensed data,it can be used ...Monitoring,understanding and predicting Origin-destination(OD)flows in a city is an important problem for city planning and human activity.Taxi-GPS traces,acted as one kind of typical crowd sensed data,it can be used to mine the semantics of OD flows.In this paper,we firstly construct and analyze a complex network of OD flows based on large-scale GPS taxi traces of a city in China.The spatiotemporal analysis for the OD flows complex network showed that there were distinctive patterns in OD flows.Then based on a novel complex network model,a semantics mining method of OD flows is proposed through compounding Points of Interests(POI)network and public transport network to the OD flows network.The propose method would offer a novel way to predict the location characteristic and future traffic conditions accurately.展开更多
In order to reduce the occurrence of traffic accidents and assist drivers to avoid dangerous driving. This paper presents a smart in-vehicle safety system that utilises the Yolov5 algorithm. Yolov5 algorithm is used t...In order to reduce the occurrence of traffic accidents and assist drivers to avoid dangerous driving. This paper presents a smart in-vehicle safety system that utilises the Yolov5 algorithm. Yolov5 algorithm is used to anticipate driver fatigue and distraction behaviours, and remind drivers to pay attention to safe driving in time. The system continuously splits the frames and analyses the frame content through the video feedback from the front camera, compared to the traditional machine learning, Yolov5’s mosaic data is enhanced, resulting in a batch size enhancement of 92.3%, and it also uses the Drop Block mechanism to prevent overfitting. The hardware of this system uses STM32 microcontroller and uses system DMA interrupt control and buzzer alarm device to warn about dangerous driving behaviour.展开更多
Today, parallel programming is dominated by message passing libraries, such as message passing interface （MPI）. This article intends to simplify parallel programming by generating parallel programs from parallelized...Today, parallel programming is dominated by message passing libraries, such as message passing interface （MPI）. This article intends to simplify parallel programming by generating parallel programs from parallelized algorithm design strategies. It uses skeletons to abstract parallelized algorithm design strategies, as well as parallel architectures. Starting from problem specification, an abstract parallel abstract programming language＋ （Apla＋） program is generated from parallelized algorithm design strategies and problem-specific function definitions. By combining with parallel architectures, implicity of parallelism inside the parallelized algorithm design strategies is exploited. With implementation and transformation, C＋＋ and parallel virtual machine （CPPVM） parallel program is finally generated. Parallelized branch and bound （B＆B） algorithm design strategy and paraUelized divide and conquer （D ＆ C） algorithm design strategy are studied in this article as examples. And it also illustrates the approach with a case study.展开更多
This paper presents an indoor floor positioning method with the smartphone’s barometer for the purpose of solving the problem of low availability and high environmental dependence of the traditional floor positioning...This paper presents an indoor floor positioning method with the smartphone’s barometer for the purpose of solving the problem of low availability and high environmental dependence of the traditional floor positioning technology.First,an initial floor position algorithm with the“entering”detection algorithm has been obtained.Second,the user’s going upstairs or downstairs activities are identified by the characteristics of the air pressure fluctuation.Third,the moving distance in the vertical direction and the floor change during going upstairs or downstairs are estimated to obtain the accurate floor position.In order to solve the problem of the floor misjudgment from different mobile phone’s barometers,this paper calculates the pressure data from the different cell phones,and effectively reduce the errors of the air pressure estimating the elevation which is caused by the heterogeneity of the mobile phones.The experiment results show that the average correct rate of the floor identification is more than 85%for three types of the cell phones while reducing environmental dependence and improving availability.Further,this paper compares and analyzes the three common floor location methods–the WLAN Floor Location(WFL)method based on the fingerprint,the Neural Network Floor Location(NFL)methods,and the Magnetic Floor Location(MFL)method with our method.The experiment results achieve 94.2%correct rate of the floor identification with Huawei mate10 Pro mobile phone.展开更多
With the rapid development of computer vision,point clouds technique was widely used in practical applications,such as obstacle detection,roadside detection,smart city construction,etc.However,how to efficiently ident...With the rapid development of computer vision,point clouds technique was widely used in practical applications,such as obstacle detection,roadside detection,smart city construction,etc.However,how to efficiently identify the large scale point clouds is still an open challenge.For relieving the large computation consumption and low accuracy problem in point cloud classification,a large scale point cloud classification framework based on light bottle transformer(light-Bot Net)is proposed.Firstly,the two-dimensional(2D)and three-dimensional(3D)feature values of large scale point cloud were extracted for constructing point cloud feature images,which employed the prior knowledge to normalize the point cloud features.Then,the feature images are input to the classification network,and the light-Bot Net network is applied for point cloud classification.It is an interesting attempt to combine the traditional image features with the transformer network.For proving the performance of the proposed method,the large scale point cloud benchmark Oakland 3D is utilized.In the experiments,the proposed method achieved 98.1%accuracy on the Oakland 3D dataset.Compared with the other methods,it can both reduce the memory consumption and improve the classification accuracy in large scale point cloud classification.展开更多
基金This work is supported by Shandong Provincial Natural Science Foundation,China under Grant No.ZR2017MG011This work is also supported by Key Research and Development Program in Shandong Provincial(2017GGX90103).
文摘Monitoring,understanding and predicting Origin-destination(OD)flows in a city is an important problem for city planning and human activity.Taxi-GPS traces,acted as one kind of typical crowd sensed data,it can be used to mine the semantics of OD flows.In this paper,we firstly construct and analyze a complex network of OD flows based on large-scale GPS taxi traces of a city in China.The spatiotemporal analysis for the OD flows complex network showed that there were distinctive patterns in OD flows.Then based on a novel complex network model,a semantics mining method of OD flows is proposed through compounding Points of Interests(POI)network and public transport network to the OD flows network.The propose method would offer a novel way to predict the location characteristic and future traffic conditions accurately.
文摘In order to reduce the occurrence of traffic accidents and assist drivers to avoid dangerous driving. This paper presents a smart in-vehicle safety system that utilises the Yolov5 algorithm. Yolov5 algorithm is used to anticipate driver fatigue and distraction behaviours, and remind drivers to pay attention to safe driving in time. The system continuously splits the frames and analyses the frame content through the video feedback from the front camera, compared to the traditional machine learning, Yolov5’s mosaic data is enhanced, resulting in a batch size enhancement of 92.3%, and it also uses the Drop Block mechanism to prevent overfitting. The hardware of this system uses STM32 microcontroller and uses system DMA interrupt control and buzzer alarm device to warn about dangerous driving behaviour.
基金National Natural Science Foundation of China (60773054)National Basic Research Program of China (2003CCA02800)
文摘Today, parallel programming is dominated by message passing libraries, such as message passing interface （MPI）. This article intends to simplify parallel programming by generating parallel programs from parallelized algorithm design strategies. It uses skeletons to abstract parallelized algorithm design strategies, as well as parallel architectures. Starting from problem specification, an abstract parallel abstract programming language＋ （Apla＋） program is generated from parallelized algorithm design strategies and problem-specific function definitions. By combining with parallel architectures, implicity of parallelism inside the parallelized algorithm design strategies is exploited. With implementation and transformation, C＋＋ and parallel virtual machine （CPPVM） parallel program is finally generated. Parallelized branch and bound （B＆B） algorithm design strategy and paraUelized divide and conquer （D ＆ C） algorithm design strategy are studied in this article as examples. And it also illustrates the approach with a case study.
基金funded by the National Key Research and Development Project from the Ministry of Science and Technology of the People’s Republic of China[grant number 2016YFB0502204].
文摘This paper presents an indoor floor positioning method with the smartphone’s barometer for the purpose of solving the problem of low availability and high environmental dependence of the traditional floor positioning technology.First,an initial floor position algorithm with the“entering”detection algorithm has been obtained.Second,the user’s going upstairs or downstairs activities are identified by the characteristics of the air pressure fluctuation.Third,the moving distance in the vertical direction and the floor change during going upstairs or downstairs are estimated to obtain the accurate floor position.In order to solve the problem of the floor misjudgment from different mobile phone’s barometers,this paper calculates the pressure data from the different cell phones,and effectively reduce the errors of the air pressure estimating the elevation which is caused by the heterogeneity of the mobile phones.The experiment results show that the average correct rate of the floor identification is more than 85%for three types of the cell phones while reducing environmental dependence and improving availability.Further,this paper compares and analyzes the three common floor location methods–the WLAN Floor Location(WFL)method based on the fingerprint,the Neural Network Floor Location(NFL)methods,and the Magnetic Floor Location(MFL)method with our method.The experiment results achieve 94.2%correct rate of the floor identification with Huawei mate10 Pro mobile phone.
基金supported by the National Natural Science Foundation of China(No.71872131)the STU Scientific Research Initiation Grant(No.20007)+1 种基金the Wenzhou Science and Technology Plan Project(No.G20220035)the General Scientific Research Fund of Zhejiang Provincial Education Department(No.Y202248776)。
文摘With the rapid development of computer vision,point clouds technique was widely used in practical applications,such as obstacle detection,roadside detection,smart city construction,etc.However,how to efficiently identify the large scale point clouds is still an open challenge.For relieving the large computation consumption and low accuracy problem in point cloud classification,a large scale point cloud classification framework based on light bottle transformer(light-Bot Net)is proposed.Firstly,the two-dimensional(2D)and three-dimensional(3D)feature values of large scale point cloud were extracted for constructing point cloud feature images,which employed the prior knowledge to normalize the point cloud features.Then,the feature images are input to the classification network,and the light-Bot Net network is applied for point cloud classification.It is an interesting attempt to combine the traditional image features with the transformer network.For proving the performance of the proposed method,the large scale point cloud benchmark Oakland 3D is utilized.In the experiments,the proposed method achieved 98.1%accuracy on the Oakland 3D dataset.Compared with the other methods,it can both reduce the memory consumption and improve the classification accuracy in large scale point cloud classification.
