检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Xi, Xin Zhao, Lixia Cao, Haicheng Li, Tuo Liu, Kai Su, Kang Li, Yamin Guo, Jianwen State Key Laboratory of High-end Server & Storage Technology Inspur Group Company Limited. Beijing100089 China Electronic Information Industry Co. Ltd. Shandong Jinan100089 China Institute of Semiconductor CAS Beijing100871 China School of Electrical and Electronic Engineering Tiangong University Tianjin300387 China Electrical and Computer Engineering CEMSE Division King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia

In this paper, we fabricated a GaN/InGaN nano-pyramid photoanode using the selective area growth (SAG) method. This method achieved high water splitting performance with photocurrent enhanced about 6 times compared to planar GaN. The impressive enhancement of water splitting performance is mainly due to the In-rich InGaN grown on the (10-11) plane, the fast separation of carriers caused by a p-n junction, and the large specific surface area that increases light absorption. Moreover, the thin InGaN layer of 3 nm can facilitate the transport of carriers through the GaN barrier by enabling quantum tunneling current. All these significantly contribute to the remarkable enhancement of water splitting performance for GaN/InGaN nano-pyramids. Our work provides a new approach for using the GaN material in highly efficient water splitting applications. © 2023, The Authors. All rights reserved.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

Knowledge-driven crowd evacuation simulation method based on hierarchical deep reinforcement learning

引用

Expert Systems with Applications 2025年 291卷

作者： Zena Tian Guijuan Zhang Xiao Hong Hui Yu Dianjie Lu School of Information Science and Engineering Shandong Normal University Jinan 250358 China State Key Laboratory of High-End Server and Storage Technology Jinan 250013 China School of Business Shandong Normal University Jinan 250358 China

Real-world knowledge within evacuation scenarios is crucial for improving the fidelity of crowd evacuation simulations, directly influencing individual decision-making during emergencies. However, the effective representation and utilization of this knowledge in simulation environments is still a challenging problem. This paper proposes a knowledge-driven crowd evacuation simulation method based on hierarchical deep reinforcement learning (DRL). First, we construct an evacuation knowledge representation model to represent real-world knowledge within emergency scenarios. This model integrates the concept of “approaching benefits and avoiding harm” found in psychological models, constructing an evacuation knowledge graph to effectively represent real-world knowledge. Second, we propose a hierarchical DRL based crowd movement model. The model consists of an EKG-DRL besed path finding model and a RVO-DRL based collision avoidance model. Among them, the former is responsible for finding safe and fast evacuation paths for individuals. The latter is responsible for learning collision-free speeds for individuals to ensure their safety when moving. Finally, we develop a hierarchical DRL based crowd navigation system and visualize the entire evacuation process through three-dimensional animation. Experimental results demonstrate that our proposed method not only enhances the realism of crowd evacuation simulation but also adapts flexibly to different scenarios, significantly improving its generalization performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the status of industrial sewage equipment based on clustering ensemble

Research on the status of industrial sewage equipment based ...

引用

International Conference on Computational Science and Computational Intelligence (CSCI)

作者： Qinlu Li Tao Du Rui Zhang Jin Zhou Shouning Qu School of Information Science and Engineering University of Jinan Jinan China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan China Shandong Management University Jinan China State Key Laboratory of High-end Server and Storage Technology

ISBN: (纸本)9781665458429

The collected industrial data are usually unlabeled, and generally use clustering algorithm for data analysis. However, a single clustering algorithm can not guarantee a good analysis of industrial datasets, and there are many limitations for users. By fusing multiple results obtained by the analysis, clustering ensemble can get more effective results. Therefore, we use density-based selective clustering ensemble method to analysis the collected datasets. The main steps are as follows: (1) use three density based clustering algorithms to analyze the datasets; (2) in order to remove the negative influence of noise, zero the elements in the obtained co-association matrix multiple times, and obtain corresponding results by hierarchical clustering; (3) set the internal validity index to select the best result. Through the experiment and the feedback of relevant factories, the effectiveness of the experiment is proved.

关键词： Data analysis Shape Scientific computing Clustering algorithms Robustness Production facilities Indexes

来源：评论

学校读者我要写书评

暂无评论

UAV Flight Attitude Acquisition Algorithm Based on Multi-Camera

UAV Flight Attitude Acquisition Algorithm Based on Multi-Cam...

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Sun Yuehang Kang Gewen Zhang Kehan Liu Kaiya Zhao Chunmeng Lou Shuli School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu China School of Foreign Lanhuages University of Electronic Science and Technology of China Chengdu China State Key Laboratory of High-end Server & Storage Technology Yantai University Yantai China

ISBN: (纸本)9781665446006

In this paper, an algorithm of UAV flight attitude acquisition based on multi-camera is proposed. Compared with the previous work, this method can realize the recognition and attitude capture of external flying objects and small targets. An algorithm is constructed to capture the flight attitude of UAV by building a camera interface database, and the whole interface pixel database is obtained by regularly calibrating the pitch angle and yaw angle data of a small number of pixels. The whole interface pixel database is obtained by Gaussian dynamic threshold filtering and interpolation. The attitude position of the UAV can be determined by the pitch and yaw line of sight rendezvous of the multi-camera, and the spatial position error caused by the error between the interpolated pitch yaw data and the real pitch yaw data can be expressed by the spatial position offset. In the flight test, when the maximum distance is 50m, the maximum absolute error of pitch angle is less than 1.3°, the average absolute error is less than 0.32°, the maximum absolute error of yaw angle is less than 1.5°, and the average absolute error is less than 0.4°. The spatial position offset of 96% of the data points is less than 0.25m, which has achieved excellent results. Flight test experiments show that this method is feasible, the model is universal and has a wide application prospect.

关键词： Interpolation Databases Target recognition Filtering Heuristic algorithms Image processing Conferences

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Electronic Scoring Scheme based on CKKS

Privacy Preserving Electronic Scoring Scheme based on CKKS

引用

International Conference on Communication technology (ICCT)

作者： Shangshang Chen Yaqian Zhao Ruyang Li Xuelei Li Jian Zhao Kai Liu National Supercomputing Center in Zhengzhou Zhengzhou University Zhengzhou China Inspur Electronic Information Industry Co. Ltd Jinan China Inspur (Beijing) Electronic Information Industry Co. Ltd Beijing China State Key Laboratory of High-end Server & Storage Technology Inspur (Beijing) Electronic Information Industry Co. Ltd Beijing China

Electronic voting (e-voting) is more economical and efficient than traditional voting, however, it also faces the challenges of privacy and security. Existing e-voting schemes take advantage of homomorphic encryption to solve the privacy and security issues for {0,1} type e-voting applications. Unfortunately, existing schemes cannot meet the requirements in (real number) score-type e-voting applications, e.g., in competitive competitions or satisfaction surveys. This paper focuses on solving the privacy and security issues for score-type e-voting applications based on cryptographic technology. In order to solve such issues, we propose an electronic scoring scheme based on the CKKS(Cheon-Kim-Kim-Song) homomorphic encryption algorithm. It supports floating-point computing for exploiting homomorphic encryption in scoring and evaluating procedures. In addition, the security analysis demonstrates that the proposal achieves data privacy and security protection. Furthermore, we design an electronic scoring experiment based on the CKKS scheme in the library of SEAL. The experimental results indicate that it only takes 0.42 seconds to complete the scoring evaluation for 5000 people. Finally, the comparison results show that the proposal is more efficient, flexible, and practical.

关键词： Privacy Electronic voting systems Seals Libraries Proposals Cryptography servers

来源：评论

学校读者我要写书评

暂无评论

Shared and Private Information Learning in Multimodal Sentiment Analysis with Deep Modal Alignment and Self-supervised Multi-Task Learning

Shared and Private Information Learning in Multimodal Sentim...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Songning Lai Jiakang Li Guinan Guo Xifeng Hu Yulong Li Yuan Tan Zichen Song Yutong Liu Zhaoxia Ren Chun Wang Danmin Miao Zhi Liu School of Information Science and Engineering Shandong University Qingdao China School of Information Science and Engineering Lanzhou University Lanzhou China Geography and Planning Sun Yat-sen University Guangzhou China Department of Military Medical Psychology Air Force Medical University Xi’an China National University of Singapore Singapore Assets and Laboratory Management Department Shandong University Qingdao China State Key Laboratory of High Performance Server and Storage Technology Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Designing an effective representation learning method for multimodal sentiment analysis is a critical research area. The primary challenge is capturing shared and private information within a comprehensive modal representation, especially when dealing with uniform multimodal labels and raw feature *** overcome this challenge, we propose a novel deep modal shared information learning module that utilizes the covariance matrix to capture shared information across modalities. Additionally, we introduce a label generation module based on a self-supervised learning strategy to capture the private information specific to each modality. Our module can be easily integrated into multimodal tasks and offers flexibility by allowing parameter adjustment to control the information exchange relationship between modes, facilitating the learning of private or shared information as needed. To further enhance performance, we employ a multi-task learning strategy that enables the model to focus on modal differentiation during training. We provide a detailed formulation derivation and feasibility proof for the design of the deep modal shared information learning *** evaluate our approach, we conduct extensive experiments on three common multimodal sentiment analysis benchmark datasets. The experimental results validate the reliability of our model, demonstrating its effectiveness in capturing nuanced information in multimodal sentiment analysis tasks.

关键词： Training Representation learning Sentiment analysis Analytical models Neural networks Information sharing Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Paratra: A Parallel Transformer Inference Framework for Gpus in Edge Computing

SSRN

引用

SSRN 2022年

作者： Cai, Fenglong Yuan, Dong Cui, Lizhen Xie, Mengwei Su, Zhiyuan School of Software Shandong University 1500 ShunHua Road High Tech Industrial Development Zone Shandong Jinan250101 China Shandong University 1500 ShunHua Road High Tech Industrial Development Zone Shandong Jinan250101 China School of Electrical and Information Engineering University of Sydney DarlingtonNSW2006 Australia State Key Laboratory of High-end Server & Storage Technology 1036 Inspur Road Shandong Jinan250101 China

Edge computing has been widely used for deploying and accelerating deep learning applications. Equipped with GPUs, edge nodes can process concurrent incoming inference requests of the deep learning model. However, the existing parallel processing methods for the inference tasks cannot efficiently use the GPU resources. This paper investigates the popular Transformer deep learning model and develops ParaTra, a parallel inference framework for Transformers that deployed with GPUs in edge computing. In the framework, the Transformer model is partitioned and deployed in users’ devices and the edge node to efficiently utilize their processing power. The concurrent inference tasks with different sizes are dynamically packaged in a scheduling queue and sent in batch to an encoder-decoder pipeline for processing. ParaTra can significantly reduce the overheads of parallel processing and the usage of GPU memory. Experiment results show that ParaTra can save up to 37.1% of GPU memory usage and improve 8.4 times of processing speed. © 2022, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A Silicon-Based MEMS Transducer with Enhanced Frame Rate for Dynamic Infrared Scene Projection

A Silicon-Based MEMS Transducer with Enhanced Frame Rate for...

引用

Telecommunications, Optics and Computer Science (TOCS), IEEE Conference on

作者： Lang Zhou Tuo Li Zhuo Li Kai Liu Hongtao Man Qifeng Li State Key Laboratory of High-end Server & Storage Technology Jinan China Inspur (Beijing) Electronic Information Industry Co. Ltd Beijing China School of Optics and Photonics Beijing Institute of Technology Beijing China Beijing Key Lab for Precision Optoelectronic Measurement Instrument and Technology Beijing China

ISBN: (纸本)9781665424998

This paper reports a novel MEMS transducer used for dynamic infrared scene projection. It can absorb the heat from an incident visible light scene and convert it into a dynamic infrared scene quickly. To improve heat dissipation, a silicon-based microcavity array was introduced as the substrate by a dry-etching fabrication process. Illuminated by a 50 Hz laser, the transient infrared response was obtained with the rising time and falling time of both 4 ms. The highest frame rate of 125 Hz was calculated. The simulation and measured results of transient thermal properties were well consistent. high resolution infrared images and an infrared video with the frequency of 120 Hz were successfully captured in long wave infrared band. These results proved the silicon-based MEMS transducer was a promising candidate in the dynamic infrared scene projection.

关键词： Micromechanical devices Time-frequency analysis Transducers Image resolution Measurement by laser beam Photothermal effects Silicon

来源：评论

学校读者我要写书评

暂无评论

Recommender for Channel Pruning with Weakly Supervised Meta Learning

Recommender for Channel Pruning with Weakly Supervised Meta ...

引用

International Conference on Information Science and Control Engineering (ICISCE)

作者： Wenfeng Yin Gang Dong Yaqian Zhao Rengang Li State Key Laboratory of High-end Server & Storage Technology Inspur Electronic Information Industry Co. Ltd. Jinan China

The switchable neural network makes it feasible to deploy a deep neural network to a specific hardware platform by adjusting architectures but without retraining parameters. However, searching out the suitable architecture to adjust is time consuming and computation-tense. To accelerate searching architectures, this paper designs a recommender which takes one round to search and evaluate without repeating. In training stages, the recommender is alternately trained with a meta network which offers the recommender gradients as weakly supervision. In searching stages, the trained recommender extracts features from a specified layer’s outputs, and generates suggested channels to prune for every layer. The recommender is deployed and evaluated on three common classification neural networks, including ResNet, MobileNet-v1 and MobileNet-v2. Experimental results validate that the proposed recommender is able to obtain compressed architectures whose accuracies surpass the switchable neural network’s accuracy at a speed faster than evolutionary algorithm based searching methods.

关键词： Training Information science Delay effects Neural networks Supervised learning Computer architecture Switches

来源：评论

学校读者我要写书评

暂无评论

A FPGA based intra-parallel architecture for PageRank graph processing

A FPGA based intra-parallel architecture for PageRank graph ...

引用

IEEE International Conference on Edge Computing (EDGE)

作者： Mei Guoqiang Hao Rui Wang Jiangwei Kan Hongwei Li Rengang Inspur (Beijing) Electronic Information Industry Co. ltd. Beijing State Key Laboratory of High-end Server & Storage Technology Beijing

ISBN: (数字)9781728182544

ISBN: (纸本)9781728182551

Acceleration of large-scale graph processing by FPGA has been proved an energy efficient method, especially in edge computation scenarios. FPGA acceleration of graph calculation includes inter partition parallel and intra partition parallel. In this paper, we focus on intra partition parallel and present a novel data selection network of less complexity. Moreover, by intra sub-graph compression, proper inter subgraph scheduling, and some initialization modules, we get our graph processing architecture. We test PageRank algorithm on data set of Twitter using the novel architecture. Experiment shows that the FPGA can support a data selection network of 128 processing units and has an effective processing ability of 51 edges per cycle and a throughput of up to 7650 Mega Traversed Edges PER Second (MTEPS), which results in a 3x throughput improvement and 1.5x DRAM bandwidth utilization rate improvement comparing with state-of-the-art design.

关键词： Random access memory Computer architecture Bandwidth Parallel processing Throughput Acceleration Field programmable gate arrays

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：