检索结果-内蒙古大学图书馆

16th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2023

作者： Wang, Shuxian Liu, Shiyou Su, Zuqiang Wang, Xin Liu, Linlin Zhu, Hang Chongqing University of Posts and Telecommunications School of Advanced Manufacturing Engineering Chongqing China Chongqing University School of Computer Science Chongqing China Xi'An University of Architecture and Technology School of Mechanical and Electrical Engineering Xian China

ISBN: (纸本)9798350327144

As an important reference indicator for transmissions, it is necessary to conduct offline testing of PRND shifting force. By studying the shift force of PRND(Parking, Reverse, Neutral, and Drive), a fault prediction method for PRND shift force based on BP neural network is proposed to improve the offline detection efficiency of PRND shift force. Based on the data obtained from the offline detection platform, a dataset for network training is obtained after processing;Build a PRND shift force fault prediction model, design and train a BP neural network, and after error backpropagation, the next layer gradient determines the gradient of the current layer to obtain the prediction network;Bringing the dataset into the network for simulation and comparing the simulation results, it was found that the network can achieve ideal results. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation

arXiv

引用

arXiv 2024年

作者： Dong, Wei Sun, Yuan Yang, Yiting Zhang, Xing Lin, Zhijun Yan, Qingsen Zhang, Haokui Wang, Peng Yang, Yang Shen, Hengtao College of Information and Control Engineering Xi’an University of Architecture and Technology China School of Computer Science Northwestern Polytechnical University China School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Computer Science and Technology Tongji University China

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To address this limitation, we propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix. We utilize Householder transformations to construct orthogonal matrices that efficiently mimic the unitary matrices, requiring only a vector. The diagonal values are learned in a layer-wise manner, allowing them to flexibly capture the unique properties of each layer. This approach enables the generation of adaptation matrices with varying ranks across different layers, providing greater flexibility in adapting pre-trained models. Experiments on standard downstream vision tasks demonstrate that our method achieves promising fine-tuning performance. © 2024, CC BY.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

ThickV-Stain: Unprocessed Thick Tissues Virtual Staining for Rapid Intraoperative Histology 7

ThickV-Stain: Unprocessed Thick Tissues Virtual Staining for...

引用

7th International Conference on Medical Imaging with Deep Learning, MIDL 2024

作者： Shi, Lulin Hou, Xingzhong Wong, Ivy H.M. Chan, Simon C.K. Chen, Zhenghui Lo, Claudia T.K. Wong, Terence T.W. Translational and Advanced Bioimaging Laboratory Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

Virtual staining has shown great promise in realizing a rapid and low-cost clinical alternative for pathological examinations, eliminating the need for chemical reagents and laborious staining procedures. However, most of the previous studies mainly focus on thin slice samples, which still require tissue sectioning and are unsuitable for intraoperative use. In this paper, we propose a multi-scale model to virtually stain label-free and slide-free biological tissues, allowing hematoxylin- and eosin- (H&E) staining generation in less than a minute for an image with 100 million pixels. We name this ThickV-Stain model, specifically developed to virtually stain intricated and unprocessed thick tissues. We harness the ability of a multi-scale network to encourage the model to capture multiple-level micromorphological characteristics from low-resolution images. Experimental results highlight the advantages of our method for virtual staining on unprocessed thick samples. We also show the effectiveness of ThickV-Stain on thin sections, showing generalizability to other clinical workflows. The proposed method enables us to obtain virtually stained images from unstained samples within minutes and can be seamlessly integrated with downstream pathological analysis tasks, providing an efficient alternative scheme for intraoperative assessment as well as general pathological examination. © 2024 CC-BY 4.0, L. Shi, X. Hou, I.H.M. Wong, S.C.K. Chan, Z. Chen, C.T.K. Lo & T.T.W. Wong.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

EagerReuse: An Efficient Memory Reuse Approach for Complex Computational Graph

EagerReuse: An Efficient Memory Reuse Approach for Complex C...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Ruyi Qian Bojun Cao Mengjuan Gao Qinwen Shi Yida Wang Yuanchao Xu Qirun Huo Keni Qiu College of Information Engineering Capital Normal University Beijing China SKL of Computer Architecture Institute of Computing Technology CAS Beijing China

Memory reuse is a promising approach for deep neural network (DNN) to reduce memory consumption because it does not introduce any additional runtime overhead. We observe that existing memory reuse algorithms consider only the effect of an individual data feature (either tensor size or tensor lifetime) on memory reuse and ignore the relative position relationship (RPR) among tensors. As computational graphs grow slightly more complex, the mining of memory reuse becomes insufficient. To address this issue, we propose a new memory reuse algorithm—EagerReuse, which can exploit more memory reuse opportunities by analyzing RPR among tensors and reusing them as quickly as possible. We evaluated the algorithms with inference models in TensorFlow Model Garden, and the results show that the EagerReuse outperforms the state-of-the-art algorithms in three out of seven cases. For more complex computational graphs, EagerReuse can achieve better memory usage with slightly higher but acceptable overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Generative Imputation Model for Missing Not At Random Data

arXiv

引用

arXiv 2023年

作者： Chen, Jialei Xu, Yuanbo Wang, Pengyang Yang, Yongjian MIC Lab Department of Computer Science and Technology Jilin University Changchun China SKL-IOTSC Department of Computer and Information Science University of Macau China

Data analysis usually suffers from the Missing Not At Random (MNAR) problem, where the cause of the value missing is not fully observed. Compared to the naive Missing Completely At Random (MCAR) problem, it is more in line with the realistic scenario whereas more complex and challenging. Existing statistical methods model the MNAR mechanism by different decomposition of the joint distribution of the complete data and the missing mask. But we empirically find that directly incorporating these statistical methods into deep generative models is sub-optimal. Specifically, it would neglect the confidence of the reconstructed mask during the MNAR imputation process, which leads to insufficient information extraction and less-guaranteed imputation quality. In this paper, we revisit the MNAR problem from a novel perspective that the complete data and missing mask are two modalities of incomplete data on an equal footing. Along with this line, we put forward a generative-model-specific joint probability decomposition method, conjunction model, to represent the distributions of two modalities in parallel and extract sufficient information from both complete data and missing mask. Taking a step further, we exploit a deep generative imputation model, namely GNR, to process the real-world missing mechanism in the latent space and concurrently impute the incomplete data and reconstruct the missing mask. The experimental results show that our GNR surpasses state-of-the-art MNAR baselines with significant margins (averagely improved from 9.9% to 18.8% in RMSE) and always gives a better mask reconstruction accuracy which makes the imputation more principle. Copyright © 2023, The Authors. All rights reserved.

关键词： Statistical methods

来源：评论

学校读者我要写书评

暂无评论

Storage Optimization Model of Undersea Data Center Based on Convective Heat Transfer

Storage Optimization Model of Undersea Data Center Based on ...

引用

2022 IEEE International Conference on Advances in Electrical Engineering and computer Applications, AEECA 2022

作者： Yu, Xinchun Zhang, Longfei Qiu, Jiale Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan China Wuhan University of Technology School of Civil Engineering and Architecture Wuhan China Wuhan University of Technology School of Science Wuhan China

ISBN: (数字)9781665480901

ISBN: (纸本)9781665480901

With the explosive growth of the total amount of global information data, the centralized heat dissipation of subsea data center servers has become a mainstream. In this paper, a container storage optimization model based on convective heat transfer is established to obtain the maximum number of servers that can be stored in a single container. Firstly, the heat conduction equation between container and sea water is obtained by using Fourier law of heat conduction and Newton law of cooling, and the definite solution condition of the heat conduction equation is determined. Then, a server storage optimization model is established based on temperature and volume constraints. Finally, the parameters of thermal diffusivity, convective exchange coefficient and thermal conductivity coefficient are estimated. The model is solved by using the meshless generalized finite difference method and verified by simulation. The maximum number of servers that can be stored is 417, and the space utilization rate is 68.45%. © 2022 IEEE.

关键词： Finite difference method

来源：评论

学校读者我要写书评

暂无评论

Safety Analysis of Riding at Intersection Entrance Using Video Recognition technology

引用

computers, Materials & Continua 2022年第9期72卷 5135-5148页

作者： Xingjian Xue Linjuan Ge Longxin Zeng Weiran Li Rui Song Neal N.Xiong College of Landscape Architecture Central South University of Forestry and TechnologyChangshaHunan410004China College of Logistics and Transportation Central South University of Forestry and TechnologyChangshaHunan410004China Department of Mathematics and Computer Science Northeastern State UniversityTahlequahOK74464United States

To study riding safety at intersection entrance,video recognition technology is used to build vehicle-bicycle conflict models based on the Bayesian *** is analyzed the relationship among the width of nonmotorized lanes at the entrance lane of the intersection,the vehicle-bicycle soft isolation form of the entrance lane of intersection,the traffic volume of right-turning motor vehicles and straight-going non-motor vehicles,the speed of right-turning motor vehicles,and straight-going non-motor vehicles,and the conflict between right-turning motor vehicles and straight-going nonmotor *** to the traditional statistical methods,to overcome the discreteness of vehicle-bicycle conflict data and the differences of influencing factors,the Bayesian random effect Poisson-log-normal model and random effect negative binomial regression model are *** results show that the random effect Poisson-log-normal model is better than the negative binomial distribution of random effects;The width of non-motorized lanes,the form of vehicle-bicycle soft isolation,the traffic volume of right-turning motor vehicles,and the coefficients of straight traffic volume obey a normal *** them,the type of vehicle-bicycle soft isolation facilities and the vehicle-bicycle traffic volumes are significantly positively correlated with the number of vehicle-bicycle *** width of non-motorized lanes is significantly negatively correlated with the number of vehicle-bicycle *** periods and flat periods,the average speed of right-turning motor vehicles,and the average speed of straight-going non-motor vehicles have no significant influence on the number of vehicle-bicycle conflicts.

关键词： Video recognition technology vehicle-bicycle conflict intersection entrance random effect poisson-log-normal model random effect negative binomial regression model

来源：评论

学校读者我要写书评

暂无评论

OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving 39

OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Dr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yan, Tianyi Yin, Junbo Lang, Xianpeng Yang, Ruigang Xu, Cheng-Zhong Shen, Jianbing SKL-IOTSC Computer and Information Science University of Macau China Li Auto Inc China CEMSE Division King Abdullah University of Science and Technology Saudi Arabia Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

To enhance autonomous driving safety in complex scenarios, various methods have been proposed to simulate LiDAR point cloud data. Nevertheless, these methods often face challenges in producing high-quality, diverse, and controllable foreground objects. To address the needs of object-aware tasks in 3D perception, we introduce OLiDM, a novel framework capable of generating high-fidelity LiDAR data at both the object and the scene levels. OLiDM consists of two pivotal components: the Object-Scene Progressive Generation (OPG) module and the Object Semantic Alignment (OSA) module. OPG adapts to user-specific prompts to generate desired foreground objects, which are subsequently employed as conditions in scene generation, ensuring controllable outputs at both the object and scene levels. This also facilitates the association of user-defined object-level annotations with the generated LiDAR scenes. Moreover, OSA aims to rectify the misalignment between foreground objects and background scenes, enhancing the overall quality of the generated objects. The broad effectiveness of OLiDM is demonstrated across various LiDAR generation tasks, as well as in 3D perception tasks. Specifically, on the KITTI-360 dataset, OLiDM surpasses prior state-of-the-art methods such as UltraLiDAR by 17.5 in FPD. Additionally, in sparse-to-dense LiDAR completion, OLiDM achieves a significant improvement over LiDARGen, with a 57.47% increase in semantic IoU. Moreover, OLiDM enhances the performance of mainstream 3D detectors by 2.4% in mAP and 1.9% in NDS, underscoring its potential in advancing object-aware 3D tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AutoDES: AutoML Pipeline Generation of Classification with Dynamic Ensemble Strategy Selection

arXiv

引用

arXiv 2022年

作者： Zhao, Yunpu Zhang, Rui Li, Xiaqing University of Science and Techonology of China China SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

Automated machine learning has achieved remarkable technological developments in recent years, and building an automated machine learning pipeline is now an essential task. However, existing AutoML pipeline approaches adopt monotonous ensemble strategies across different machine learning classification tasks. They ignore the fact that no single ensemble strategy can perform best on all of the various classification tasks, and thus cannot meet the performance requirements in practice. To this end, we propose AutoDESS, an efficient AutoML approach to identifying the best ensemble strategy for machine learning classification tasks by combining different ensemble strategies' strengths. To our best knowledge, AutoDESS is the first trial in AutoML aiming at searching and optimizing ensemble strategies. In the comparison experiments, AutoDESS outperforms the state-of-the-art AutoML approaches while with the same CPU time in 42 classification datasets from the OpenML platform. In addition, ablation experiments also validate the effectiveness of AutoDESS. © 2022, CC BY-NC-ND.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

iNUMAlloc: Towards Intelligent Memory Allocation for AI Accelerators with NUMA

iNUMAlloc: Towards Intelligent Memory Allocation for AI Acce...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Yuanchao Xu Ruyi Qian Yida Wang Qirun Huo College of Information Engineering Capital Normal University Beijing China SKL of Computer Architecture Institute of Computing Technology CAS Beijing China

The amazing success of deep neural network benefits from the rise of big data. As deep learning models are becoming more scale than ever before, their requirements for memory bandwidth are growing at a tremendous pace. Some AI accelerators adopt non-uniform memory access (NUMA) architecture to mitigate this issue and hence complicate device memory allocation. Although extensive studies have been conducted on how to mitigate resource contention and reduce latency, almost all of them target on CPU-oriented NUMA systems but not on AI accelerators where memory allocation precedes task scheduling. The current memory allocator generally adopts an interleaved memory allocation strategy, which is very easy to implement but far from *** tackle this issue, this paper proposes iNUMAlloc, an intelligent memory allocator specialized for AI accelerators with NUMA architecture by combining program behavior and predictable hardware resources altogether. Preliminary evaluation shows that it can help to improve the accuracy and efficiency of memory allocation, thereby achieving stable execution time.

关键词：

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：