检索结果-内蒙古大学图书馆

On-Street Parking Occupancy inference Based on Payment Transactions

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第8期23卷 10680-10691页

作者： Assemi, Behrang Paz, Alexander Baker, Douglas Queensland Univ Technol QUT Gardens Point Sch Architecture & Built Environm Brisbane Qld 4000 Australia Queensland Univ Technol QUT Gardens Point Sch Civil & Environm Engn Brisbane Qld 4000 Australia

A record of spatial and temporal parking occupancy is critical to optimize on-street parking resources and to develop effective parking policies. Such data are often obtained through advanced and costly occupancy monitoring technologies. Moreover, it is usually challenging to integrate bay-level occupancies and parking data from other systems. Accurate occupancy-payment data are required for a wide range of analytical and practical purposes, including but not limited to investigating payment behavior, estimating and forecasting occupancy, and evaluating the efficiency and effectiveness of enforcement policies. This study proposes a metaheuristic optimization algorithm to integrate snapshots of bay-level parking occupancy, captured using simple cameras, with transactions from a conventional parking payment management system. The resulting integrated data were used to develop, calibrate and validate a parking occupancy estimation method utilizing parking payment data only. Details of the design, implementation, and validation of the proposed algorithm and modelling technique are provided. Logistic regression analysis was used to tune parameters of the data integration algorithm. Deep learning, gradient boosting and random forests were used to develop a model of parking occupancy. Evaluation of the algorithm indicated an accuracy of 76% of correct data integration;that is, individual bay occupancies integrated with the correct corresponding payment transactions. The best occupancy estimation model also showed a very high accuracy, with an R-2 above 94% and a root mean square error (RMSE) of 1.2 (occupied bays), when tested with a random sample from the integrated data.

关键词： Monitoring Estimation Data models Cameras Reliability Software algorithms Prediction algorithms Learning (artificial intelligence) prediction algorithms software algorithms inference algorithms heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Learned Factor Graphs for inference From Stationary Time Sequences

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 366-380页

作者： Shlezinger, Nir Farsad, Nariman Eldar, Yonina C. Goldsmith, Andrea J. Ben Gurion Univ Negev Sch ECE IL-8400711 Beer Sheva Israel Ryerson Univ Dept CS Toronto ON M5B 2K3 Canada Weizmann Inst Sci Fac Math & CS IL-7610001 Rehovot Israel Princeton Univ Dept EE Princeton NJ 08544 USA

The design of methods for inference from time sequences has traditionally relied on statistical models that describe the relation between a latent desired sequence and the observed one. A broad family of model-based algorithms have been derived to carry out inference at controllable complexity using recursive computations over the factor graph representing the underlying distribution. An alternative model-agnostic approach utilizes machine learning (ML) methods. Here we propose a framework that combines model-based algorithms and data-driven ML tools for stationary time sequences. In the proposed approach, neural networks are developed to separately learn specific components of a factor graph describing the distribution of the time sequence, rather than the complete inference task. By exploiting stationary properties of this distribution, the resulting approach can be applied to sequences of varying temporal duration. Learned factor graphs can be realized using compact neural networks that are trainable using small training sets, or alternatively, be used to improve upon existing deep inference systems. We present an inference algorithm based on learned stationary factor graphs, which learns to implement the sum-product scheme from labeled data, and can be applied to sequences of different lengths. Our experimental results demonstrate the ability of the proposed learned factor graphs to learn from small training sets to carry out accurate inference for sleep stage detection using the Sleep-EDF dataset, as well as for symbol detection in digital communications with unknown channels.

关键词： Signal processing algorithms inference algorithms Hidden Markov models Training Computational modeling Time series analysis Task analysis Factor graphs deep learning time sequences

来源：评论

学校读者我要写书评

暂无评论

Generalized Bilinear Factorization via Hybrid Vector Message Passing

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2024年 72卷 5675-5690页

作者： Jiang, Hao Yuan, Xiaojun Guo, Qinghua Univ Elect Sci & Technol China Natl Key Lab Wireless Commun Chengdu 611731 Peoples R China Univ Wollongong Sch Elect Comp & Telecommun Engn Wollongong NSW 2522 Australia

Generalized bilinear factorization (GBF), in which two matrices are recovered from noisy and typically compressed measurements of their product, arises in various applications such as blind channel-and-signal estimation, image completion, and compressed video foreground and background separation. In this paper, we formulate the GBF problem by unifying several existing bilinear inverse problems, and establish a novel hybrid vector message passing (HVMP) algorithm for GBF. The GBF-HVMP algorithm integrates expectation propagation (EP) and variational message passing (VMP) via variational free energy minimization, and exchanges matrix-variable messages in closed form. GBF-HVMP is advantageous over its counterparts in several aspects. For example, a matrix-variable message can characterize the correlations between the elements of the matrix, which is not possible in scalar-variable message passing;the hybrid of EP and VMP yields closed-form Gaussian messages associated with the bilinear constraints inherent in the GBF problem. We show that damping is unnecessary for GBF-HVMP to ensure convergence. We also show that GBF-HVMP performs close to the replica bound, and significantly outperforms state-of-the-art approaches in terms of both normalized mean squared error (NMSE) performance and computational complexity.

关键词： Message passing Approximation algorithms Signal processing algorithms Sparse matrices Covariance matrices Correlation Vectors Inverse problems inference algorithms Convergence Generalized bilinear factorization message passing variational free energy minimization expectation propagation variational message passing

来源：评论

学校读者我要写书评

暂无评论

inference-Based Posteriori Parameter Distribution Optimization

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第5期52卷 3006-3017页

作者： Wang, Xuesong Li, Tianyi Cheng, Yuhu Chen, C. L. Philip China Univ Min & Technol Engn Res Ctr Intelligent Control Underground Spac Minist Educ Xuzhou 221116 Jiangsu Peoples R China China Univ Min & Technol Xuzhou Key Lab Artificial Intelligence & Big Data Xuzhou 221116 Jiangsu Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China Univ Macau Fac Sci & Technol Taipa 99999 Macau Sar Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China

Encouraging the agent to explore has always been an important and challenging topic in the field of reinforcement learning (RL). Distributional representation for network parameters or value functions is usually an effective way to improve the exploration ability of the RL agent. However, directly changing the representation form of network parameters from fixed values to function distributions may cause algorithm instability and low learning inefficiency. Therefore, to accelerate and stabilize parameter distribution learning, a novel inference-based posteriori parameter distribution optimization (IPPDO) algorithm is proposed. From the perspective of solving the evidence lower bound of probability, we, respectively, design the objective functions for continuous-action and discrete-action tasks of parameter distribution optimization based on inference. In order to alleviate the overestimation of the value function, we use multiple neural networks to estimate value functions with Retrace, and the smaller estimate participates in the network parameter update;thus, the network parameter distribution can be learned. After that, we design a method used for sampling weight from network parameter distribution by adding an activation function to the standard deviation of parameter distribution, which achieves the adaptive adjustment between fixed values and distribution. Furthermore, this IPPDO is a deep RL (DRL) algorithm based on off-policy, which means that it can effectively improve data efficiency by using off-policy techniques such as experience replay. We compare IPPDO with other prevailing DRL algorithms on the OpenAI Gym and MuJoCo platforms. Experiments on both continuous-action and discrete-action tasks indicate that IPPDO can explore more in the action space, get higher rewards faster, and ensure algorithm stability.

关键词： Task analysis Optimization Training Artificial neural networks Linear programming inference algorithms Markov processes Exploration inference parameter distribution reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Optimal Accuracy-Privacy Trade-Off of inference as Service

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 4031-4046页

作者： Jin, Yulu Lai, Lifeng Univ Calif Davis Dept Elect & Comp Engn Davis CA 95616 USA

In this paper, we propose a general framework to provide a desirable trade-off between inference accuracy and privacy protection in the inference as service scenario (IAS). Instead of sending data directly to the server, the user will preprocess the data through a privacy-preserving mapping, which will increase privacy protection but reduce inference accuracy. To properly address the trade-off between privacy protection and inference accuracy, we formulate an optimization problem to find the privacy-preserving mapping. Even though the problem is non-convex in general, we characterize nice structures of the problem and develop an iterative algorithm to find the desired privacy-preserving mapping, with convergence analysis provided under certain assumptions. From numerical examples, we observe that the proposed method has better performance than gradient ascent method in the convergence speed, solution quality and algorithm stability.

关键词： Privacy Convergence Optimization Servers inference algorithms Data privacy Signal processing algorithms ADMM inference privacy

来源：评论

学校读者我要写书评

暂无评论

Voxel RCNN-HA: A Point Cloud Multiobject Detection Algorithm With Hybrid Anchors for Autonomous Driving

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2024年第3期10卷 7286-7296页

作者： Wang, Hai Tao, Le Peng, Yiming Chen, Zhiyu Zhang, Yong Jiangsu Univ Sch Automot & Traff Engn Zhenjiang 212013 Peoples R China Nanjing Forestry Univ Sch Automot & Traff Engn Nanjing 212001 Peoples R China

The 3-D object detection using Lidar becomes essential for subsequent vehicle decision-making and planning as part of an intelligent vehicle perception system. Voxel region convolutional neural network (RCNN) is a two-stage voxel-based 3-D object detection algorithm that is fast and accurate. However, the detection accuracy for specific categories is insufficient in complex traffic scenarios, and thus, we propose the Voxel RCNN-HA algorithm. First, in light of the shortcomings of Voxel RCNN in detecting pedestrians, a hybrid detection head is proposed to balance the advantages and disadvantages of anchor-based and anchor-free algorithms and significantly improve pedestrian detection performance while maintaining vehicle accuracy. Second, self-attention is introduced in the second stage of the algorithm and a Voxel region of interest (RoI) self-attention pooling module is developed to obtain both local and global features in RoI, which addresses the issue that the original Voxel RoI pooling module is challenging to obtain global features of large objects. On the one million scenes (ONCE) dataset, the proposed Voxel RCNN-HA achieves 66.79% mean average precision (mAP) and 11.7 frames per second (FPS), and outperforms both Voxel RCNN and CenterPoints in terms of detection accuracy. Additionally, experiments on the Waymo Open dataset and Custom-Rslidar dataset further validate the effectiveness and generalization of the proposed method.

关键词： Three-dimensional displays Proposals Prediction algorithms Pedestrians Feature extraction Laser radar inference algorithms 3-D object detection anchor-based anchor-free Lidar self-attention

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Measurement Point Intelligent Selection and End-to-End Network Traffic Calculation in Datacenters

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第3期11卷 2438-2449页

作者： Fan, Weibei Xiao, Fu Han, Lei He, Xin Wang, Junchang Nanjing Univ Posts & Telecommun Coll Comp Jiangsu High Technol Res Key Lab Wireless Sensor N Nanjing 210003 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Jilin 130012 Peoples R China

The effective design and management of data centers needs to follow the end-to-end traffic characteristics of data center networks (DCNs). However, directly measuring the end-to-end traffic of the network requires huge software and hardware costs. Since the particularity of the structure of DCNs, the flow estimation method used in the traditional computer network cannot be applied to existing DCNs. In this article, we study the end-to-end traffic calculation of cloud computing DCNs. We propose LLS-TC, which is an intelligent end-to-end traffic inference algorithm based on network tomography. Only using SNMP (simple network management protocol) data generally supported by switches, end-to-end traffic information can be calculated quickly and accurately. LLS-TC first devices a network traffic measurement point intelligent selection scheme based on node weighting. It first assigns weight to nodes through node criticality, and then uses node weighted incidence matrix approximation algorithm to calculate initial solution. LLS-TC then designs a network tomography method suitable for cloud computing network traffic calculation. It uses the time correlation of data center traffic to model the algorithm problem into a linear state space model, and finally calculates the traffic carried by each path through the improved Kalman filtering algorithm. Our evaluation and analysis demonstrate that LLS-TC can effectively use the extracted coarse-grained traffic characteristics, and greatly improve the accuracy of the calculation on the premise of ensuring the computational efficiency.

关键词： Data centers Cloud computing inference algorithms Feature extraction Costs Tomography Bayes methods network measurement measurement point selection end-to-end performance evaluation

来源：评论

学校读者我要写书评

暂无评论

On the Feasible Region of Efficient algorithms for Attributed Graph Alignment

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第5期70卷 3622-3639页

作者： Wang, Ziao Zhang, Ning Wang, Weina Wang, Lele Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada Univ Oxford Dept Stat Oxford OX1 3LB England Carnegie Mellon Univ Dept Comp Sci Pittsburgh PA 15213 USA

Graph alignment aims at finding the vertex correspondence between two correlated graphs, a task that frequently occurs in graph mining applications such as social network analysis. Attributed graph alignment is a variant of graph alignment, in which publicly available side information or attributes are exploited to assist graph alignment. Existing studies on attributed graph alignment focus on either theoretical performance without computational constraints or empirical performance of efficient algorithms. This motivates us to investigate efficient algorithms with theoretical performance guarantee. In this paper, we propose two polynomial-time algorithms that exactly recover the vertex correspondence with high probability. The feasible region of the proposed algorithms is near optimal compared to the information-theoretic limits. When specialized to the seeded graph alignment problem under the seeded Erd & odblac;s-R & eacute;nyi graph pair model, the proposed algorithms extends the best known feasible region for exact alignment by polynomial-time algorithms.

关键词： Graph theory statistics inference algorithms

来源：评论

学校读者我要写书评

暂无评论

BIC-LP: A Hybrid Higher-Order Dynamic Bayesian Network Score Function for Gene Regulatory Network Reconstruction

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第1期21卷 188-199页

作者： Xin, Junchang Wang, Mingcan Qu, Luxuan Chen, Qi Wang, Weiyiqi Wang, Zhiqiong Northeastern Univ Sch Comp Sci & Engn Shenyang 110819 Liaoning Peoples R China Northeastern Univ Shenyang Key Lab Big Data Management & Analyt Liaoning Prov Shenyang 110819 Liaoning Peoples R China Northeastern Univ Coll Med & Biol Informat Engn Shenyang 110819 Liaoning Peoples R China

Reconstructing gene regulatory networks(GRNs) is an increasingly hot topic in bioinformatics. Dynamic Bayesian network(DBN) is a stochastic graph model commonly used as a vital model for GRN reconstruction. But probabilistic characteristics of biological networks and the existence of data noise bring great challenges to GRN reconstruction and always lead to many false positive/negative edges. ${Score}_{Lasso}$ScoreLasso is a hybrid DBN score function combining DBN and linear regression with good performance. Its performance is, however, limited by first-order assumption and ignorance of the initial network of DBN. In this article, an integrated model based on higher-order DBN model, higher-order Lasso linear regression model and Pearson correlation model is proposed. Based on this, a hybrid higher-order DBN score function for GRN reconstruction is proposed, namely BIC-LP. BIC-LP score function is constructed by adding terms based on Lasso linear regression coefficients and Pearson correlation coefficients on classical BIC score function. Therefore, it could capture more information from dataset and curb information loss, compared with both many existing Bayesian family score functions and many state-of-the-art methods for GRN reconstruction. Experimental results show that BIC-LP can reasonably eliminate some false positive edges while retaining most true positive edges, so as to achieve better GRN reconstruction performance.

关键词： Bayes methods Linear regression Biological system modeling inference algorithms Biology Heuristic algorithms Correlation Gene regulatory network higher-order dynamic Bayesian network method fusion score function structure learning

来源：评论

学校读者我要写书评

暂无评论

Structured Sparse Bayesian Learning Based Multiuser Detectors for Uplink Grant-Free NOMA With Variable User Activities

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第6期73卷 9093-9097页

作者： Zhang, Xiaoxu Fan, Pingzhi Li, Li Hao, Li Zhou, Ziyang Southwest Jiaotong Univ Prov Key Lab Informat Coding & Transmiss Chengdu 611756 Peoples R China

In this work, we study the grant-free non-orthogonal multiple access (GF-NOMA) system to support the massive machine-type communications (mMTC), where the number of users is large, but normally, only a small portion of them activate within a random access opportunity. For the uplink of this system, we develop a structured sparse Bayesian learning based multiuser detection (SSBL-MUD) scheme. In a practical mMTC scenario, the user activity status could change in different time slots. To solve the multiuser detection (MUD) problem, we formulate the uplink GF-NOMA in multiple time slots with variable user activity factors based on multiple measurement vector (MMV) model. In order to leverage the sparse structural feature of the transmitted signal, we propose multiple sparse Bayesian learning multiuser detection (MSBL-MUD) and block sparse Bayesian learning multiuser detection (BSBL-MUD) schemes. Both of them are able to recover the transmitted information by joint user activity detection and data detection, and do not require any prior knowledge of the user sparsity. Simulation results demonstrate that the proposed algorithms significantly outperform the existing classical detectors.

关键词： Bayes methods Uplink Multiuser detection Detectors Data models Matching pursuit algorithms inference algorithms Massive machine-type communications grant-free non-orthogonal multiple access multiple measurement vector structured sparse bayesian learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：