检索结果-内蒙古大学图书馆

Deep representation learning for road detection using siamese network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Huafeng Han, Xiaofeng Li, Xiangrui Yao, Yazhou Huang, Pu Tang, Zhenming School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China

Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network. The RGB images are fed into another branch of our proposed network. The feature maps that these two branches extract in multiple scales are fused before each pooling layer, via padding additional fusion layers. Extensive experimental results on public dataset KITTI ROAD demonstrate the effectiveness of our proposed approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Roads and streets

Temporal data fusion at the edge

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Yang, Linfu Liu, Bin School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

—As an enabler technique, data fusion has gained great attention in the context of Internet of things (IoT). In traditional settings, data fusion is done at the cloud server. So the data to be fused should be transferred from the sensor nodes to the cloud server before data fusion. Such an application mode of data fusion inherits disturbing concerns from the cloud computing framework, e.g., privacy-leaking, large latency between data capture and computation, excessive ingress bandwidth consumption. We take into account how to do temporal data fusion at the edge to bypass the above issues. We present a Gaussian process based temporal data fusion (GPTDF) method targeted for the problem of sequential online prediction at the edge. The GPTDF method fits the edge computing framework and thus inherits desirable properties from edge computing, such as privacy-preserving, low latency between data capture and computation, and tiny bandwidth consumption. Through a real-data experiment using archived traffic datasets from the Caltrans Performance Measurement System (PeMS), we demonstrate that the application of GPTDF can provide more timely and accurate real-time predictions at the network edge. Copyright © 2019, The Authors. All rights reserved.

关键词： Internet of things

Temporal data Fusion at the Edge

学校读者我要写书评

暂无评论

Temporal Data Fusion at the Edge

IEEE International Symposium on Parallel and Distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Linfu Yang Bin Liu School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781728152103

As an enabler technique, data fusion has gained great attention in the context of Internet of things (IoT). In traditional settings, data fusion is done at the cloud server. So the data to be fused should be transferred from the sensor nodes to the cloud server before data fusion. Such an application mode of data fusion inherits disturbing concerns from the cloud computing framework, e.g., privacy-leaking, large latency between data capture and computation, excessive ingress bandwidth consumption. We take into account how to do temporal data fusion at the edge to bypass the above issues. We present a Gaussian process based temporal data fusion (GPTDF) method targeted for the problem of sequential online prediction at the edge. The GPTDF method fits the edge computing framework and thus inherits desirable properties from edge computing, such as privacy-preserving, low latency between data capture and computation, and tiny bandwidth consumption. Through a real-data experiment using archived traffic datasets from the Caltrans Performance Measurement System (PeMS), we demonstrate that the application of GPTDF can provide more timely and accurate real-time predictions at the network edge.

关键词： data privacy Gaussian processes Internet of Things sensor fusion data fusion Gaussian processes Internet of things data integration data privacy Sensor fusion Edge of a figure or solid data capture Privacy

Incentivizing the workers for truth discovery in crowdsourcing with copiers

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Lingyun Niu, Xiaofu Xu, Jia Yang, Dejun Xu, Lijie Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing Jiangsu210023 China Department of Computer Science Colorado School of Mines GoldenCO80401 United States

Crowdsourcing has become an efficient paradigm for performing large scale tasks. Truth discovery and incentive mechanism are fundamentally important for the crowdsourcing system. Many truth discovery methods and incentive mechanisms for crowdsourcing have been proposed. However, most of them cannot be applied to deal with the crowdsourcing with copiers. To address the issue, we formulate the problem of maximizing the social welfare such that all tasks can be completed with the least confidence for truth discovery. We design an incentive mechanism consisting truth discovery stage and reverse auction stage. In truth discovery stage, we estimate the truth for each task based on both the dependence and accuracy of workers. In reverse auction stage, we design a greedy algorithm to select the winners and determine the payment. Through both rigorous theoretical analysis and extensive simulations, we demonstrate that the proposed mechanisms achieve computational efficiency, individual rationality, truthfulness, and guaranteed approximation. Moreover, our truth discovery method shows prominent advantage in terms of precision when there are copiers in the crowdsourcing systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Crowdsourcing

Sequential online prediction in the presence of outliers and change points: An instant temporal structure learning approach

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Bin Qi, Yu Chen, Ke-Jia School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Key Lab of Big Data Security and Intelligent Processing Nanjing Jiangsu210023 China College of Computer Science and Technology Zhejiang University Hangzhou Zhejiang310058 China

In this paper, we consider sequential online prediction (SOP) for streaming data in the presence of outliers and change points. We propose an INstant TEmporal structure Learning (INTEL) algorithm to address this problem. Our INTEL algorithm is developed based on a full consideration to the duality between online prediction and anomaly detection. We first employ a mixture of weighted Gaussian process models (WGPs) to cover the expected possible temporal structures of the data. Then, on the basis of the rich modeling capacity of this WGP mixture, we develop an efficient technique to instantly learn (capture) the temporal structure of the data that follows a regime shift. This instant learning is achieved only by adjusting one hyper-parameter value of the mixture model. A weighted generalization of the product of experts (POE) model is used for fusing predictions yielded from multiple GP models. An outlier is declared once a real observation seriously deviates from the fused prediction. If a certain number of outliers are consecutively declared, then a change point is declared. Extensive experiments are performed using a diverse of real datasets. Results show that the proposed algorithm is significantly better than benchmark methods for SOP in the presence of outliers and change points. Copyright © 2019, The Authors. All rights reserved.

关键词： Statistics

DUE Distribution and Pairing in D2D Communication

学校读者我要写书评

暂无评论

DUE Distribution and Pairing in D2D Communication

International Conference on computer Communications and Networks (ICCCN)

作者： Weifeng Lu Xiaoqiang Ren Jia Xu Siguang Chen Lijun Yang Jian Xu Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China College of IoT Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

The D2D (Device-to-Device) communication has been very popular as it is a promising and low-cost solution to reduce the burden on the cellular network. However, there are rare concerns about the distribution and pairing of DUEs(D2D user equipments), which have a significant impact on QoS (Quality of Service) of D2D communication. In this paper, we propose a novel algorithm based on the coalitional game to optimally adjust the distribution of DUEs. The proposed algorithm aims to form the optimal coalition structure, which achieves a balance between the throughput and power consumption of each coalition, obtaining the enhanced QoS of D2D. We show that our algorithm is superior to the benchmark models in terms of the throughput and energy efficiency of the DUE coalition. To further improve the QoS, we also propose a method to predict and maximize the pairing probability of DUEs. The proposed prediction method adopts the Logistic Regression to model the global pairing probability according to the communication parameters of DUEs. Experimental results show that the proposed prediction method is significantly superior to the benchmark methods in terms of prediction accuracy. In addition, the pairing probability maximization algorithm proposed also significantly improves the pairing probability.

关键词： Device-to-device communication Throughput Power demand Fading channels Games Quality of service Time division multiple access

Risk evaluation of financial websites based on structure mining

学校读者我要写书评

暂无评论

Risk evaluation of financial websites based on structure min...

International Conference on Applications and Techniques in Cyber security and Intelligence, ATCSI 2017

作者： Li, Huakang Dai, Yuhao Jin, Xu Sun, Guozi Li, Tao Xu, Zheng Jiangsu Key Lab of Big Data and Security and Intelligent Processing School of Computer Science and Technology School of Software Nanjing University of Posts and Telecommunications Nanjing China The Third Research Institute of the Ministry of Public Security Shanghai China

ISBN: (纸本)9783319670706

With the development of network communication and security authentication technologies, Internet finance, a new financial business model which allows customers to achieve online financing, payment, investment and lending, becomes more and more popular. Risk of internet finance is much higher than that of traditional financial system because of the rapid fund flowing, lack of personal credit audit, deficiency of standard network operation and imperfect of information security. Current risk control of Internet finance mainly contains network security, financial self-discipline, investor education and governmental regulatory. In this paper, we propose a risk evaluation method based on structure mining for financial website after analyzing a large number of Internet financial sites. The kernel functions algorithm of natural language syntax tree is introduced to classify the security level of website. While the URL is considered as a long sentence and the path segments are defined as keywords. The experimental results demonstrate that the structure mining method can simply evaluate the risk of Internet financial website to achieve acceptable accuracy. © 2018, Springer International Publishing AG.

关键词： Websites

Adaptive Teacher-and-Student Model for Heterogeneous Domain Adaptation

学校读者我要写书评

暂无评论

Adaptive Teacher-and-Student Model for Heterogeneous Domain ...

IEEE International Conference on data Mining (ICDM)

作者： Yunyun Wang Xuzhang Chen Songcan Chen Hui Xue College of Computer Science Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts & Telecommunications Nanjing China College of Computer Science & Technology/AI MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics & Astronautics Nanjing China College of Computer Science and Engineering Southeast University Nanjing China

In heterogeneous domain adaptation (HDA), since the feature spaces of the source and target domains are different, knowledge transfer from the source to the target domain is really challenging. How to align the different feature spaces and then adaptively transfer the related knowledge is critical for HDA. In this paper, we develop an adaptive teacher-and-student model for heterogeneous domain adaptation (AtsHDA). In AtsHDA, the source domain as a teacher and the target domain as a student are aligned or co-adapted to each other first, so that their correlation can be maximized. Then the target domain adaptively learns from the source domain. Specifically, there is a balance between the learning by the target domain itself and the instruction from the source domain. That is, when the guidance from the source domain is helpful for learning, the learning of target classifier emphasizes the instruction of source knowledge, and considers its own knowledge more, otherwise. Further, an ensemble method is designed to decide such a balance. Finally, empirical results show that AtsHDA can achieve competitive results compared with the state-of-arts.

关键词：

FIMI： A Constant Frugal Incentive Mechanism for Time WindowCoverage in Mobile Crowdsensing

学校读者我要写书评

暂无评论

Journal of computer science & Technology 2017年第5期32卷 919-935页

作者： Jia Xu Jian-Ren Fu De-Jun Yang Li-Jie Xu Lei Wang Tao Li School of Computer Science Nanjing University of Posts and Telecommunications Nanjing 210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing 210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing 210023 China Department of Computer Science Colorado School of Mines Golden 80401 U.S.A.

Mobile crowdsensing has become an efficient paradigm for performing large-scale sensing tasks. An incentive mechanism is important for a mobile crowdsensing system to stimulate participants and to achieve good service quality. In this paper, we explore truthful incentive mechanisms that focus on minimizing the total payment for a novel scenario, where the platform needs the complete sensing data in a requested time window (RTW). We model this scenario as a reverse auction and design FIMI, a constant frugal incentive mechanism for time window coverage. FIMI consists of two phases, the candidate selection phase and the winner selection phase. In the candidate selection phase, it selects two most competitive disjoint feasible user sets. Afterwards, in the winner selection phase, it finds all the interchangeable user sets through a graph-theoretic approach. For every pair of such user sets, FIMI chooses one of them by the weighted cost. Further, we extend FIMI to the scenario where the RTW needs to be covered more than once. Through both rigorous theoretical analysis and extensive simulations, we demonstrate that the proposed mechanisms achieve the properties of RTW feasibility (or RTW multi-coverage), computation efficiency, individual rationality, truthfulness, and constant frugality.

关键词： crowdsensing incentive mechanism constant frugality