检索结果-内蒙古大学图书馆

The research of forecasting model of automobile parts recycling cost based on data intelligence 2019

学校读者我要写书评

暂无评论

The research of forecasting model of automobile parts recycl...

2019 International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2019

作者： Fan, Bo Cai, Yueshun School of Information Science and Technology Southwest Jiaotong University National Engineering Laboratory of Industrial Big-Data Application Technology CASIC ChengDu China

ISBN: (纸本)9781450372022

In view of the problem of reducing the cost control of the used parts in the after-sales service cost analysis process of the automobile enterprises, the multi-dimensional intelligent analysis of the used business data is carried out by extracting and cleaning the relevant business data resources of the used parts. This paper proposes a method based on data intelligence for cost forecasting, which assists enterprises in mining valuable information and knowledge contained in used parts data, making the used parts business data intelligent and realizing the value-added of used parts data. The management of used parts recycling is an important value link for automotive enterprises to reduce costs and increase efficiency, and is the key to building a reverse supply chain coordination architecture and achieving circular economy. There are many factors influencing the cost of recycling used parts, and too much interference will affect the forecasting effect. Therefore, before establishing the corresponding used parts recovery cost prediction model, the data should be decomposed into a stable time series, so that the prediction results are more accurate. This paper compares several typical prediction algorithms, uses the theory of empirical mode decomposition to preprocess the business data of used parts data, then builds the ARMA model, selects the ARMA model parameters through the AIC information criterion, and designs the supplier's used parts recycling cost prediction model. And the model is validated using the used piece business data piece data to predict the cost of the supplier's used parts recovery and provide support for the actual business system. © 2019 Association for Computing Machinery.

关键词： Cost reduction

Surface soil moisture inversion based on DEFS-GA-BP model using Sentinel-1/2 remote sensing data 5

学校读者我要写书评

暂无评论

Surface soil moisture inversion based on DEFS-GA-BP model us...

IET International Radar Conference 2020, IET IRC 2020

作者： Zhang, Chenyang Min, Lin Zhao, Jianhui College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475004 China Network Information Center Office Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

The major work is to retrieve the surface soil moisture under crop cover in this paper. This paper proposes an improved GA-BP model called as DEFS-GA-BP model. This model is proposed to retrieve the surface soil moisture distribution using Sentinel-1 and Sentinel-2 remote sensing data. After extracting nine polarization features and one roughness parameter from Sentinel-1 data, five vegetation indexes from Sentinel-2 data. The differential evolution feature selection (DEFS) algorithm is applied to select the optimal feature subset. By using the genetic algorithm (GA) to optimize the node weights, the back propagation (BP) neural network is trained using the optimal feature subset and then used to generate the surface soil moisture distribution. The results of inversion algorithm indicate that the proposed DEFS-GA-BP model has a better inversion precision than GA-BP model, and demonstrates its application potential in surface soil moisture inversion. © 2020 Institution of engineering and technology. All rights reserved.

关键词： Genetic algorithms

Interacting multiple model estimator for event-triggered cyber-physical systems against Denial-of-service attacks

学校读者我要写书评

暂无评论

Interacting multiple model estimator for event-triggered cyb...

Chinese Automation Congress (CAC)

作者： Zengwang Jin Shuting Zhang Yanning Zhang Changyin Sun School of Cyberspace Security Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China School of Automation Southeast University Nanjing China

ISBN: (纸本)9781665426480

This paper investigates the problem of security state estimation of event-triggered cyber-physical systems (CPSs) under constrained bandwidth and random DoS attacks. Two independent Markov chains are introduced to separately describe the transition of system models and the occurrence of DoS attacks. By presenting an event-triggered scheduling mechanism based on the measurement innovation, the impact of bandwidth and power limitations in CPSs is mitigated. For the purpose of reducing the complexity of model sequences, the interacting multiple model (IMM) framework is extended event-triggered CPSs to cut down the the branch of exponential growth assumptions. In addition, the statistical information of event-triggered conditions are utilized to estimate the continuous state, identify the system mode and detect DoS attacks. Finally, the performance of the proposed method is validated by Monte Carlo simulation in a two-dimensional maneuvering target tracking.

关键词： Technological innovation Target tracking Simulation Bandwidth Markov processes Cyber-physical systems Denial-of-service attack

Tissue Segmentation of Thick-Slice Fetal Brain MR Scans with Guidance from High-Quality Isotropic Volumes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Shijie Zhang, Xukun Cui, Zhiming Zhang, He Chen, Geng Shen, Dinggang School of Biomedical Engineering ShanghaiTech University Shanghai China Academy for Eng. & Tech. Fudan University Shanghai China Department of Radiology Obstetrics and Gynecology Hospital of Fudan University Shanghai China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence company Ltd. Shanghai200030 China Shanghai Clinical Research Trial Center Shanghai201210 China

Accurate tissue segmentation of thick-slice fetal brain magnetic resonance (MR) scans is crucial for both reconstruction of isotropic brain MR volumes and the quantification of fetal brain development. However, this task is challenging due to the use of thick-slice scans in clinically-acquired fetal brain data. To address this issue, we propose to leverage high-quality isotropic fetal brain MR volumes (and also their corresponding annotations) as guidance for segmentation of thick-slice scans. Due to existence of significant domain gap between high-quality isotropic volume (i.e., source data) and thick-slice scans (i.e., target data), we employ a domain adaptation technique to achieve the associated knowledge transfer (from high-quality volumes to thick-slice scans). Specifically, we first register the available high-quality isotropic fetal brain MR volumes across different gestational weeks to construct longitudinally-complete source data. To capture domain-invariant information, we then perform Fourier decomposition to extract image content and style codes. Finally, we propose a novel Cycle-Consistent Domain Adaptation Network (C2DA-Net) to efficiently transfer the knowledge learned from high-quality isotropic volumes for accurate tissue segmentation of thick-slice scans. Our C2DA-Net can fully utilize a small set of annotated isotropic volumes to guide tissue segmentation on unannotated thick-slice scans. Extensive experiments on a large-scale dataset of 372 clinically acquired thick-slice MR scans demonstrate that our C2DA-Net achieves much better performance than cutting-edge methods quantitatively and qualitatively. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance

Chop chop BERT: Visual question answering by Chopping Visualbert's heads

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gao, Chenyu Zhu, Qi Wang, Peng Wu, Qi School of Computer Science Northwestern Polytechnical University Xi'an China School of Software Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology China University of Adelaide Australia

Vision-and-Language (VL) pre-training has shown great potential on many related downstream tasks, such as Visual Question Answering (VQA), one of the most popular problems in the VL field. All of these pre-trained models (such as VisualBERT, ViLBERT, LXMERT and UNITER) are built with Transformer, which extends the classical attention mechanism to multiple layers and heads. To investigate why and how these models work on VQA so well, in this paper we explore the roles of individual heads and layers in Transformer models when handling 12 different types of questions. Specifically, we manually remove (chop) heads (or layers) from a pre-trained VisualBERT model at a time, and test it on different levels of questions to record its performance. As shown in the interesting echelon shape of the result matrices, experiments reveal different heads and layers are responsible for different question types, with higher-level layers activated by higher-level visual reasoning questions. Based on this observation, we design a dynamic chopping module that can automatically remove heads and layers of the VisualBERT at an instance level when dealing with different questions. Our dynamic chopping module can effectively reduce the parameters of the original model by 50%, while only damaging the accuracy by less than 1% on the VQA *** Codes 68T45 Copyright © 2021, The Authors. All rights reserved.

关键词： Visual languages

Revisit the scheduling problem in Hurdle, V.F., 1973: A novel mathematical solution approach and two extensions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Fan, Wenbo School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu China

The scheduling problem in Hurdle (1973) was formulated in a general form that simultaneously concerned the vehicle dispatching, circulating, fleet sizing, and patron queueing. As a constrained variational problem, it remains not fully solved for decades. With technical prowess in graphic analysis, the author unveiled the closed-form solution for the optimal dispatch rates (with key variables undetermined though), but only suggested the lower and upper bounds of the optimal fleet size. Additionally, such a graphic analysis method lacks high efficiency in computing specific scheduling problems, which are often of a large scale (e.g., hundreds of bus lines). In light of this, the paper proposes a novel mathematical solution approach that first relaxes the original problem to an unconstrained one, and then attacks it using calculus of variations. The corresponding Euler-Lagrange equation yields the closed-form solution of the optimal dispatching rates, to which Hurdle's results are a special case. Thanks to the proposed approach, the optimal fleet size can also be solved. This paper completes the work of Hurdle (1973) by formalizing a solution method and generalizing the results. Based on that, we further make two extensions to the scheduling problem of general bus lines with multiple origins and destinations and that of mixed-size or modular buses. Closed-form results are also obtained with new insights. Among others, we find that the solutions for shuttle/feeder lines are a special case to our results of general bus lines. Numerical examples are also provided to demonstrate the effectiveness and efficiency of the proposed approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Scheduling

Camouflaged Object Detection via Context-aware Cross-level Fusion

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Geng Liu, Si-Jie Sun, Yu-Jia Ji, Ge-Peng Wu, Ya-Feng Zhou, Tao Northwestern Polytechnical University Xi’an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering China Data Processing Center School of Power and Energy China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science Inner Mongolia University Hohhot010021 China Artificial Intelligence Institute School of Computer Science Wuhan University Wuhan430072 China

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare C2F-Net with state-of-the-art (SOTA) models. The results show that C2F-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our C2F-Net in COD downstream applications. Our code is publicly available at: https://***/Ben57882/C2FNet-TSCVT. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Fei Xu, Jianian Chen, Jiabin Chen, Li Shang, Ruitao Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes increasingly compelling. However, GPU sharing inevitably brings severe performance interference among co-located inference workloads, as motivated by an empirical measurement study of DNN inference on EC2 GPU instances. While existing works on guaranteeing inference performance service level objectives (SLOs) focus on either temporal sharing of GPUs or reactive GPU resource scaling and inference migration techniques, how to proactively mitigate such severe performance interference has received comparatively little attention. In this paper, we propose iGniter, an interference-aware GPU resource provisioning framework for cost-efficiently achieving predictable DNN inference in the cloud. iGniter is comprised of two key components: (1) a lightweight DNN inference performance model, which leverages the system and workload metrics that are practically accessible to capture the performance interference;(2) A cost-efficient GPU resource provisioning strategy that jointly optimizes the GPU resource allocation and adaptive batching based on our inference performance model, with the aim of achieving predictable performance of DNN inference workloads. We implement a prototype of iGniter based on the NVIDIA Triton inference server hosted on EC2 GPU instances. Extensive prototype experiments on four representative DNN models and datasets demonstrate that iGniter can guarantee the performance SLOs of DNN inference workloads with practically acceptable runtime overhead, while saving the monetary cost by up to 25% in comparison to the state-of-the-art GPU resource provisioning strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

A Lagrangian traffic flow model considering lane changing behavior: Formulation and numerical implementation

学校读者我要写书评

暂无评论

A Lagrangian traffic flow model considering lane changing be...

2020 Forum on Integrated and Sustainable Transportation Systems, FISTS 2020

作者： Lu, Liang Zheng, Fangfang Liu, Xiaobo Yuan, Yufei Southwest Jiaotong University Western Hi-tech Zone Chengdu School of Transportation and Logistics Sichuan611756 China Southwest Jiaotong University School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology 611756 China Delft University of Technology Department of Transport and Planning Delft Netherlands

ISBN: (数字)9781728195032

ISBN: (纸本)9781728195032

This paper proposes a multilane traffic flow model based on the notions of conservation laws in Lagrangian coordinates. Both the mathematical formulation and the graphical representation are provided. A logit choice model is applied to describe drivers' lane choice probability. The lane changing rate is estimated by employing the Incremental Transfer (IT) principle and the lane choice probability model. The numerical implementation of the model in the case of two lanes is discussed. The simulation results reveal that the proposed Lagrangian model is able to describe lane changing dynamics of vehicle platoons;while the lane changing equilibrium curve at the macroscopic level is consistent with that from the multilane Eulerian model as well as the observed data on the highway. © 2020 IEEE.

关键词： Lagrange multipliers