检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Song, Yuhui Xu, Chenchu Wang, Boyan Du, Xiuquan Chen, Jie Zhang, Yanping Li, Shuo School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230051 China Department of Computer Science and Technology Tsinghua University Beijing100084 China School of Engineering Case Western Reserve University Cleveland44106 United States

Few-shot learning alleviates the heavy dependence of medical image segmentation tasks on large-scale labeled data, but it shows a strong performance gap when dealing with new targets and new tasks compared with traditional deep learning. Existing few-shot medical image segmentation models mainly realize segmentation by learning the semantic class knowledge of a few known (support) samples and extending it to unknown (query) samples. However, the neglect of the differences between known and unknown samples leads to a certain deviation in the transfer of class knowledge, and the trained model tends to overfit the class knowledge of training classes, which greatly reduces the segmentation and generalization performance of few-shot model. In this work, we propose an interactive prototype learning and self-learning network to alleviate the above problems. Specifically, we propose an interactive prototype learning network to promote feature consistency between support images and query images to improve the accuracy of prototype metric learning. In addition, to avoid overfitting the training class knowledge and reduce the over-dependence of query segmentation on the class knowledge, we introduce a query features-guided self-learning network to achieve the finer segmentation of query images through its rich feature information. Our model obtained the competitive segmentation results on three multi-organ and multi-modal public datasets that show a substantial improvement in generalization ability. © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A Joint Learning Sentiment Analysis Method Incorporating Emoji-Augmentation

A Joint Learning Sentiment Analysis Method Incorporating Emo...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Jie Chen Luping Luo Bojing Ji Shu Zhao Yanping Zhang The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University China School of Big Data and Artificial Intelligence Chizhou University China

ISBN: (纸本)9781665456579

Social media is the platform for most people to share their opinions, emojis are also widely used to express moods, emotions, and feelings on social media. There have been many researched on emojis and sentiment analysis. However, existing methods mainly face two limitations. First, since deep learning relies on large amounts of labeled data, the training samples of emoji are not enough to achieve the training effect. Second, they consider the sentiment of emojis and texts separately, not fully exploring the impact of emojis on the sentiment polarity of texts. In this paper, we propose a joint learning sentiment analysis method incorporating emoji-augmentation, and the method has two advantages compared with the existing work. First, We optimize the easy data augmentation method so that the newly generated sentences can also preserve the semantic information of emojis, which relieves the problem of insufficient training data with emojis. Second, it fuses emojis and text features to allow the model to better learn the mutual emotional semantics between text and emojis, jointly training emojis and words to obtain the sentence representations containing more semantic information of both emojis and text. Our experimental results show that the proposed method can significantly improve the performance compared with several baselines on two datasets.

关键词： Training Sentiment analysis Social networking (online) Fuses Text recognition Mood Semantics

来源：评论

学校读者我要写书评

暂无评论

Identifying Disease Modules Based on Connectivity and Semantic Similarities 14th

Identifying Disease Modules Based on Connectivity and Semant...

引用

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Su, Yansen Zhu, Huole Zhang, Lei Zhang, Xingyi Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China

ISBN: (纸本)9789811534140

The identification of disease modules has attracted increasing attention due to the importance in comprehending pathogenesis of complex diseases. Most of the existing methods were based on the protein-protein interaction (PPI) networks with the incompleteness and incorrectness of the interactome, which results in many disease-related proteins and pathways not within their disease modules. In this paper, we propose a method named IDMCSS to effectively identify disease modules by adding some potential interactions and removing some incorrect interactions in the existing human PPI network. Firstly, the connective similarity and semantic similarity are calculated between the known disease proteins and each of their neighbors. Then, the network is adjusted by adding the interactions with large connective and semantic similarity, and removing those with small connective and semantic similarity. Further, the proteins are sorted in the descending order according to the similarity to the known disease proteins, and the sorted proteins are added into a candidate node set one by one until a certain biological information is not enriched in the candidate node set. Finally, the connected subnetwork with the largest number of nodes in the candidate node set is selected as the disease module. The disease modules identified by IDMCSS involve crucial biological processes of related diseases and can predict 12 targets for drug intervention. The experimental results on asthma demonstrate the effectiveness of the proposed method in comparison to existing algorithms for disease module identification. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Robust Optimization-based Neural Architectures Against Adversarial Attacks

Robust Optimization-based Neural Architectures Against Adver...

引用

IEEE SSD International Multi-Conference on Systems, signals and Devices

作者： Khaoula Ben Ali Seifeddine Messaoud Mohamed Ali Hajjaji Mohamed Atri Noureddine Liouane Laboratory of Automatic Signal Image Processing National Engineering School Monastir University Monastir Tunisia Faculty of Sciences of Monastir Monastir University Monastir Tunisia Higher Institute of Applied Sciences and Technology of Sousse Sousse University Sousse Tunisia Computer Engineering Department College of Computer Science King Khalid University Abha Saudi Arabia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

Recent years have seen a rapid development in Machine Learning, which has profoundly influenced many areas of science and engineering. Among them, computer vision takes the leading place, where important tasks are image classifications powered by CNNs. Despite the great performance of CNNs in complicated scenarios, they remain sensitive to so-called adversarial attacks, and deliberate perturbations leading them to incorrect predictions. Besides more innocuous consequences, this has serious security implications for critical applications, in-cluding medical diagnostics, where misclassifications might result in disastrous outcomes. This research work discusses adversarial attacks on CNNs and other DNNs in computer vision, studying a full range of the generation and detection methods with details while discussing intrinsic vulnerability and robustness. It also proposes a learning framework that will enhance the robustness and security of DNNs and CNNs against such adversarial perils. The ultimate goal is directed to an improvement in the reliability of such models in absolutely critical scenarios for safe deployment into applications where accuracy is crucial.

关键词： Computer vision Accuracy Perturbation methods Computer network reliability Machine learning Robustness Security Medical diagnosis Resilience Image classification

来源：评论

学校读者我要写书评

暂无评论

A special type of the passive radar imaging using the self-multipath signals on satellites

A special type of the passive radar imaging using the self-m...

引用

IET International Radar Conference (IRC 2023)

作者： Yi Zhou Ying Zhou Hui Ma Shenghua Zhou Yujie Zhang Haoran Sun Xue Wang Lin Liu Hongwei Liu National Laboratory of Radar Signal Processing Xidian University Xi'an People's Republic of China Beijing Institute of Remote-sensing Equipment Science and Technology on Millimeter-wave Laboratory Beijing People's Republic of China Institute of Information Sensing Xidian University Xi'an People's Republic of China

ISBN: (数字)9781837240982

This paper investigates the feasibility of observing the satellite by its own transmitted signals. The system is a special type of the passive radar (PR) using the self-multipath signal (SMS) on satellites. Firstly, the geometry of the SMS-based PR (SMS-PR) is formulated and analysed, and then the direct signals containing self-multipath are modelled. Secondly, the in-pulse matched filtering and the direct-path cancellation are individually considered and corresponding processing algorithms are given. Thirdly, the process algorithms are proposed of the SMS-PR imaging of the satellite, based on the inverse synthetic aperture radar (ISAR) and the orthogonal matching pursuit (OMP). Finally is the post-processing of the proposed scheme is verified by the simulation results. In addition, the paper analyses also the conditions guaranteeing the successful imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anti-jamming performance analysis of multi-OAM-mode vortex radar based on waveform diversity

Anti-jamming performance analysis of multi-OAM-mode vortex r...

引用

International Conference on Radar Systems (RADAR 2022)

作者： D. Hu L. Liu Y. Duan X. Jiang K. Lv H. Ma National Laboratory of Radar Signal Processing Xidian University Xi'an People's Republic of China Beijing Institute of Remote-sensing Equipment Science and Technology on Millimeter-wave Laboratory Beijing People's Republic of China

This paper exploits the electromagnetic vortex (EMV) radar system in anti-jamming applications of digital radio frequency memory (DRFM), considering the orthogonal-waveform-based uniform circular array (UCA) system specifically. Compared to conventional multiple-input-multiple-output (MIMO) system, the EMV radar has a novel dimension of EMV mode proportional to the orbital angular momentum (OAM), providing a new dimension for the orthogonal decomposition of the transmitted waveform, as well as a new dimension for distinguish the DRFM and a real target.

关键词： angular momentum antenna arrays digital radio jamming MIMO communication radar signal processing

来源：评论

学校读者我要写书评

暂无评论

Management strategy of power exchange in a building between grid, photovoltaic and batteries 2nd

Management strategy of power exchange in a building between ...

引用

2nd International Conference on Electronic Engineering and Renewable Energy, ICEERE 2020

作者： Dhriyyef, Mohammed El Mehdi, Abdelmalek Elhitmy, Mohammed Elhafyani, Mohammed Smart and Communication Technologies Laboratory National School of Applied Sciences Mohammed First University Oujda Morocco Electromagnetism Signal Processing and Renewable Energy Laboratory Faculty of Science Mohammed First University Oujda Morocco Electrical Engineering and Maintenance Laboratory Hight School of Technology Mohammed First University Oujda Morocco

ISBN: (纸本)9789811562587

This work presents a system managing electric energy in a building with a varying demand of energy with respect to the need of its occupants. The system uses renewable energy resources such as photovoltaic panels, the battery as an energy storage system and the grid. The objective of this work is to avoid the usage of the grid as much as possible and this is made in the purpose of minimizing the electricity bill. The objective is also to benefit from the photovoltaic energy and the storage system according to their availability in order to satisfy the energy demand by the building. An algorithm that manages these three resources is presented, it is dedicated to managing the energy production and consumption of the building, the surplus of renewable energy production is stored in the system storage or injected into the grid. The study is made in a period of two successive days according to the levels of the batteries SOCs with a varying energy demand and different solar irradiance. This study has succeeded to obtain the energy demand satisfaction, managing the storage system and planning of power exchange between the grid and the building. The results are obtained through simulation by the MATLAB and SIMULINK environments. © Springer Nature Singapore Pte Ltd. 2021.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras

arXiv

引用

arXiv 2024年

作者： Zhu, Yabin Wang, Xiao Li, Chenglong Jiang, Bo Zhu, Lin Huang, Zhixiang Tian, Yonghong Tang, Jin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University China School of Computer Science and Technology Anhui University China School of Artificial Intelligence Anhui University China Beijing Institute of Technology Beijing China School of Electronic and Information Engineering Anhui University China Peng Cheng Laboratory Shenzhen China School of Computer Science Peking University Beijing China School of Electronic and Computer Engineering Peking University Shenzhen China

Existing datasets for RGB-DVS tracking are collected with DVS346 camera and their resolution (346 × 260) is low for practical applications. Actually, only visible cameras are deployed in many practical systems, and the newly designed neuromorphic cameras may have different resolutions. The latest neuromorphic sensors can output high-definition event streams, but it is very difficult to achieve strict alignment between events and frames on both spatial and temporal views. Therefore, how to achieve accurate tracking with unaligned neuromorphic and visible sensors is a valuable but unresearched problem. In this work, we formally propose the task of object tracking using unaligned neuromorphic and visible cameras. We build the first unaligned frame-event dataset CRSOT collected with a specially built data acquisition system, which contains 1,030 high-definition RGB-Event video pairs, 304,974 video frames. In addition, we propose a novel unaligned object tracking framework that can realize robust tracking even using the loosely aligned RGB-Event data. Specifically, we extract the template and search regions of RGB and Event data and feed them into a unified ViT backbone for feature embedding. Then, we propose uncertainty perception modules to encode the RGB and Event features, respectively, then, we propose a modality uncertainty fusion module to aggregate the two modalities. These three branches are jointly optimized in the training phase. Extensive experiments demonstrate that our tracker can collaborate the dual modalities for high-performance track- Copyright © 2024, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Unified-modal Salient Object Detection via Adaptive Prompt Learning

arXiv

引用

arXiv 2023年

作者： Wang, Kunpeng Li, Chenglong Tu, Zhengzheng Liu, Zhengyi Luo, Bin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China The Institute of Physical Science and Information Technology Anhui University Hefei230601 China

Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor and time consumption, as well as high computational and practical deployment costs. In this paper, we attempt to address both single-modal and multi-modal SOD in a unified framework called UniSOD, which fully exploits the overlapping prior knowledge between different tasks. Nevertheless, assigning appropriate strategies to modality variable inputs is challenging. To this end, UniSOD learns modality-aware prompts with task-specific hints through adaptive prompt learning, which are plugged into the proposed pre-trained baseline SOD model to handle corresponding tasks, while only requiring few learnable parameters compared to training the entire model. Each modality-aware prompt is generated from a switchable prompt generation block, which adaptively performs structural switching based on single-modal and multi-modal inputs without human intervention. Through end-to-end joint training, UniSOD achieves overall performance improvement on 14 benchmark datasets for RGB, RGB-D, and RGB-T SOD, which demonstrates that our method effectively and efficiently unifies single-modal and multi-modal SOD tasks. The code and results are available at https://***/Angknpng/UniSOD. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of OSM-OFDM Systems with Carrier Frequency Offset

Performance Analysis of OSM-OFDM Systems with Carrier Freque...

引用

International Conference on Communication technology (ICCT)

作者： Tingmin Jiang Yue Xiao Lilin Dan Xinrong Ji Wenqi Tang Yan Zhao National Key Laboratory of Science and Technology on Communications UESTC Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728181417

ISBN: (纸本)9781728181424

Offset spatial modulation (OSM) is a novel modulation scheme with simplified radio-frequency-switching structure. In this paper, the concept of OSM is combined with orthogonal frequency division multiplexing (OFDM) transmission to take advantage of the benefits of these two techniques. We shed light on the effects of carrier frequency offset (CFO) on the OSM-OFDM systems over multipath Rayleigh fading channel, where the inter-carrier interference (ICI) induced by CFO degrades the system performance. We further derive the theoretical bit-error rate (BER) upper bound of OSM-OFDM impaired by CFO. Simulation results show that the theoretical BER is in good agreement with its simulated counterpart, which demonstrates the accuracy of the theoretical analysis.

关键词： OFDM Transmitting antennas Receiving antennas Precoding Radio frequency Frequency division multiplexing Upper bound

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：