检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Frontiers Technology of Information and computer, ICFTIC 2021

作者： Sun, Yiwen Zhang, Jingyao Han, Chaoyue Tianjin University of Technology School of Computer Science and Engineering Tianjin China University of Electronic Science Technology of China School of Software Engineering Beijing China Northwest A F University College of Mechanical and Electronic Engineering Xian China

ISBN: (纸本)9781665406055

Flower identification is the basic research in many fields, such as botany research, so the study of flower identification has far-reaching significance. The traditional flower recognition has the characteristics of weak generalization ability, high cost, and low accuracy. Because of the above problems, this paper proposes to use a lightweight neural network MobileNet model based on CNN to recognize flowers. The depth-separable convolution model reduces the number of parameters by dividing the convolution into Depthwise Convolution and Pointwise Convolution. That is to say, compared with the traditional convolutional neural network, the number of layers of the separable convolutional neural network can be deeper in the case of the same number of parameters. In this experiment, the CNN and MobileNet neural network models are trained by using public data sets, and the final experimental results show that the correct rate of the MobileNet model reaches 88. 37%, which is 22. 3% higher than that of the traditional CNN network model. © 2021 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Self-temperature compensation approach for fiber specklegram magnetic field sensor based on polarization specklegram analysis 8

Self-temperature compensation approach for fiber specklegram...

引用

8th Symposium on Novel Photoelectronic Detection Technology and Applications

作者： Hu, Shicheng Liu, Haifeng Liu, Bo Lin, Wei Zhang, Hao Song, Binbin Wu, Jixuan Tianjin Key Laboratory of Micro-Scale Optical Information Science and Technology Institute of Modern Optics Nankai University Tianjin300350 China Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology Institute of Modern Optics Nankai University Tianjin300350 China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai519000 China Key Laboratory of Computer Vision and Systems Ministry of Education School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems College of Electronic and Information Engineering Tianjin Polytechnic University Tianjin300387 China

ISBN: (数字)9781510653122

ISBN: (纸本)9781510653115

In this letter, we proposed a self-temperature-compensation approach for fiber specklegram sensor (FSS) based on polarization specklegram analysis. The temperature compensation is achieved by comparing the variation difference of the two specklegrams with vertical linear polarization state. We designed a fiber specklegram magnetic field sensor employing this method and the magneto-birefringence effect of magnetic fluid. The measurement of magnetic field with high stability and good repeatability has been successfully achieved, which demonstrated the effectiveness of the proposed method. Due to the merits of low cost, ease of implement and system simplicity, the proposed method can promote the practical use of the FSS in long term monitoring. © 2022 SPIE

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution 39

Diffusion Prior Interpolation for Flexibility Real-World Fac...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yang, Jiarui Dai, Tao Zhu, Yufei Li, Naiqi Li, Jinmin Xia, Shu-Tao College of Artificial Intelligence Nankai University Tianjin China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)157735897X

Diffusion models represent the state-of-the-art in generative modeling. Due to their high training costs, many works leverage pre-trained diffusion models’ powerful representations for downstream tasks, such as face super-resolution (FSR), through fine-tuning or prior-based methods. However, relying solely on priors without supervised training makes it challenging to meet the pixel-level accuracy requirements of discrimination task. Although prior-based methods can achieve high fidelity and high-quality results, ensuring consistency remains a significant challenge. In this paper, we propose a masking strategy with strong and weak constraints and iterative refinement for real-world FSR, termed Diffusion Prior Interpolation (DPI). We introduce conditions and constraints on consistency by masking different sampling stages based on the structural characteristics of the face. Furthermore, we propose a condition Corrector (CRT) to establish a reciprocal posterior sampling process. DPI can balance consistency and diversity and can be seamlessly integrated into pre-trained models. In extensive experiments conducted on synthetic and real datasets, along with consistency validation in face recognition, DPI demonstrates superiority over SOTA FSR methods. 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

A Vision-Based Algorithm of Slope Angle Estimation by Using Cooperation of Snake Robots

A Vision-Based Algorithm of Slope Angle Estimation by Using ...

引用

IEEE International Conference on Mechatronics and Automation

作者： Shuai Li Jian Liu Wenjun Liu Ziming Liu Jingrun Tian Ruonan Wang Xuan Xiao Zengzeng Wang School of Software Tiangong University Tianjin China Center of Engineering Practice Training Tiangong University Tianjin China School of Economics&Management Tiangong University Tianjin China School of Computer Science&Technology Tiangong University Tianjin China

When snake robots perform tasks, their ability of sensing the environment is very important. This paper proposes an algorithm for estimating the slope angle based on the cooperation of two snake robots by using the visual system. Through the movement of two snake robots, the corresponding geometric models will be created. After that, the angle of the slope is calculated by substituting the coordinates that are recorded by the visual system. Finally, the experiments are conducted to verify the performance of the algorithm. The results show the errors are within 2° when the slope range is between 15° and 75°.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation

arXiv

引用

arXiv 2024年

作者： Yao, Wenfang Liu, Chen Yin, Kejing Cheung, William K. Qin, Jing School of Nursing The Hong Kong Polytechnic University Hong Kong Department of Computer Science Hong Kong Baptist University Hong Kong School of Software Engineering South China University of Technology China

Integrating multi-modal clinical data, such as electronic health records (EHR) and chest X-ray images (CXR), is particularly beneficial for clinical prediction tasks. However, in a temporal setting, multi-modal data are often inherently asynchronous. EHR can be continuously collected but CXR is generally taken with a much longer interval due to its high cost and radiation dose. When clinical prediction is needed, the last available CXR image might have been outdated, leading to suboptimal predictions. To address this challenge, we propose DDL-CXR, a method that dynamically generates an up-to-date latent representation of the individualized CXR images. Our approach leverages latent diffusion models for patient-specific generation strategically conditioned on a previous CXR image and EHR time series, providing information regarding anatomical structures and disease progressions, respectively. In this way, the interaction across modalities could be better captured by the latent CXR generation process, ultimately improving the prediction performance. Experiments using MIMIC datasets show that the proposed model could effectively address asynchronicity in multimodal fusion and consistently outperform existing methods. © 2024, CC BY-NC-SA.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Dynamic Asynchronous Federated Learning in Mobile Edge Computing Networks

Energy-Efficient Dynamic Asynchronous Federated Learning in ...

引用

IEEE International Conference on Communications (ICC)

作者： Guozeng Xu Xiuhua Li Hui Li Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

To break data silos and address the challenge of green communication, federated learning (FL) is widely used at network edges to train deep learning models in mobile edge computing (MEC) networks. However, many existing FL algorithms do not fully consider the dynamic environment, resulting in slower convergence of the model and larger training energy consumption. In this paper, we design a dynamic asynchronous federated learning (DAFL) model to improve the efficiency of FL in MEC networks. Specifically, we dynamically choose a certain number of mobile devices (MDs) by their arrival order to participate in the global aggregation at each epoch. Meanwhile, we analyze the energy consumption model of local update and upload update, and formulate the problem as a dynamic sequential decision problem to minimize the energy consumption, which is NP-hard. To address it, we propose an energy-efficient algorithm based on deep reinforcement learning named DDAFL, to intelligently determine the number of MDs participating in global aggregation according to the state of MEC networks at each epoch. Compared with baseline schemes, the proposed algorithm can significantly reduce energy consumption and accelerate model convergence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DNN Partitioning and Assignment for Distributed Inference in SGX Empowered Edge Cloud

DNN Partitioning and Assignment for Distributed Inference in...

引用

International Conference on Distributed Computing Systems

作者： Yuepeng Li Deze Zeng Lin Gut Song Guo Albert Y. Zomaya School of Computer Science China University of Geosciences Wuhan China Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Ministry of Education Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing The Hong Kong Polytechnic University Hong Kong School of Computer Science The University of Sydney Australia

ISBN: (数字)9798350386059

ISBN: (纸本)9798350386066

Distributed Deep Neural Network (DNN) inference is a promising technology to explore the distributed resources in edge cloud to realize edge intelligence. Meanwhile the inherent resource sharing nature of edge cloud infrastructure also raises serious concerns on security and privacy. software Guard Ex-tensions (SGX) emerges as a potential hardware-level solution but its limited secure memory (i.e., enclave page cache) imposes new challenges, especially in contrast to memory-hungry DNN models. A task's performance will be severely affected when its memory footprint is beyond the enclave page cache size, due to expensive secure page swapping. In this case, how to appropriately partition a DNN model and assign the partitions to distributed edge servers to efficiently utilize edge resources for fast secure inference becomes a challenging problem. In this paper, we first show that this problem is NP-hard. We further propose a MEmory -aware Distributed Inference Acceleration (MEDIA) algorithm, whose guaranteed approximation ratio is also formally analyzed. We have implemented a prototype system and applied some well-known representative DNN models to evaluate MEDIA's performance. Through extensive experiments, we verify the efficiency of MEDIA by the fact that it reduces the inference time by 19.5%-38.1 % in comparison with state-of-the-art approaches.

关键词： Computational modeling Prototypes Artificial neural networks Media Approximation algorithms Inference algorithms software

来源：评论

学校读者我要写书评

暂无评论

Dynamic Random Route Mutation Mechanism for Moving Target Defense in SDN 6

Dynamic Random Route Mutation Mechanism for Moving Target De...

引用

6th International Symposium on computer and Information Processing Technology, ISCIPT 2021

作者： Zhang, Bofeng Han, Li Sun, Shimin Tianjin University of Technology School of Computer Science and Engineering Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin China Tiangong University Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Computer Science and Technology Tianjin China

ISBN: (纸本)9781665441377

Moving Target Defense (MTD) is commonly used in changing the asymmetric situation between attack and defense in cyberspace. Route mutation is a vital branch of MTD. Current route mutation methods still have some limitations on unpredictability of mutating routing paths and time overhead. In this paper, we propose a Dynamic Random Route Mutation (DRRM) mechanism in order to maximize the unpredictability of mutation and reduce the time overhead. First, we adopt Jaccard distance matrix and temporal constraint to improve mutation space. Mutation space can be dynamically shifted to enhance the unpredictability. Then, we weaken attackers' capabilities of launching effective eavesdropping at a certain node by using route weight. Finally, we construct a pre-distribution strategy to reduce the transmission latency caused by route mutation. Simulation results show that DRRM not only raises the difficulty of network eavesdropping, but also ensures low mutation time overhead. © 2021 IEEE.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Service Migration in Mec: An Approach Based on Deep Reinforcement Learning and Fuzzy Logic

SSRN

引用

SSRN 2023年

作者： Zhang, Xinyang Bu, Chao Wang, Jinsong Key Laboratory of Computer Vision System of Ministry of Education School of Computer Science and Engineering Tianjin University of Technology China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China

As a new computing paradigm, Mobile Edge Computing (MEC) sinks resources to the network edge to support real-time re-sponses of services. Facing the demand for migrating services caused by the frequent movement of the mobile device, it is a great challenge to reduce the operation costs of migrating services with user requirements satisfied, especially for the continu-ous optimization of services deployed in hot spot areas. In order to address the above challenge, we propose the mechanism of dynamically migrating and optimally deploying services, which optimizes the latency and energy consumption of the service mi-gration. Firstly, we introduce Markov Decision Process (MDP) to model changes of deployment locations of the single-user ser-vice, and devise the approach to determine whether to migrate a service at the current network status based on the dueling Deep Q-Network (DQN). Secondly, we propose the service pre-migration decision approach to determine where to migrate a ser-vice by combining the Long Short-Term Memory (LSTM) network and the attention mechanism, so as to determine the future moving area of the user and perform the migration decision in advance with the impact of migration service on service quality considered. Finally, we devise the distance-weighted matching algorithm based on the fuzzy logic to further optimize the selec-tion of the most appropriate services to migrate in hotspot areas and the corresponding service migration regions, thus, the load pressure of the edge computing node caused by the imbalanced deployment density of service among multiple regions. Simula-tion results show that the proposed mechanism has significant improvements in overall operating costs compared with the cur-rent state of the art. © 2023, The Authors. All rights reserved.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Automatic Diagnosis for Knee Meniscus Tear in Magnetic Resonance Images

CNN-Based Automatic Diagnosis for Knee Meniscus Tear in Magn...

引用

Chinese Intelligent Systems Conference, CISC 2020

作者： Zhou, Hao Zhang, Liyan Zhang, Bing Wang, Juan Xia, Chengyi Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9789811584497

The meniscus tear is common for athletes and the elderly, and because of its irresistible nature, early diagnosis and treatment is particularly important. Magnetic Resonance (MR) Imaging is noninvasive and has a high diagnostic accuracy of 98%, which has been considered as an ideal method to diagnose meniscus tear. However, it is a time consuming process for radiologists to diagnose meniscus tear by comparing dozens of MR images and to diagnose the tear grade. Here, the convolutional neural network (CNN) is used to accomplish the aim of automatic diagnosis of tear grade. At first, we apply the Hough transformation to preprocess the data, during which we shrink the image to about 1/10 of its original size so that the meniscus local candidate frame (LCF) is formed. Then, to validate the method, 3062 actual clinical MR images were used and an accuracy of 89.5% is achieved. The experimental result has demonstrated the validity of our proposed method, which can meet the needs of radiologists for computer-aided diagnosis of meniscus tear classification. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Magnetic resonance imaging

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：