检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ye, Yiwen Xie, Yutong Zhang, Jianpeng Chen, Ziyang Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China The University of Adelaide Australia DAMO Academy Alibaba Group China

The universal model emerges as a promising trend for medical image segmentation, paving up the way to build medical imaging large model (MILM). One popular strategy to build universal models is to encode each task as a one-hot vector and generate dynamic convolutional layers at the end of the decoder to extract the interested target. Although successful, it ignores the correlations among tasks and meanwhile is too late to make the model ‘aware’ of the ongoing task. To address both issues, we propose a prompt-driven Universal Segmentation model (UniSeg) for multi-task medical image segmentation using diverse modalities and domains. We first devise a learnable universal prompt to describe the correlations among all tasks and then convert this prompt and image features into a task-specific prompt, which is fed to the decoder as a part of its input. Thus, we make the model ‘aware’ of the ongoing task early and boost the task-specific training of the whole decoder. Our results indicate that the proposed UniSeg outperforms other universal models and single-task models on 11 upstream tasks. Moreover, UniSeg also beats other pre-trained models on two downstream datasets, providing the community with a high-quality pre-trained model for 3D medical image segmentation. Code and model are available at https://***/yeerwen/UniSeg. Copyright © 2023, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

ISSSR 2022 Keynote Speech II: Human-Machine Cooperation in Junior Science Education: Development, Opportunities, and Challenges

ISSSR 2022 Keynote Speech II: Human-Machine Cooperation in J...

引用

International Symposium on System and Software Reliability (ISSSR)

作者： Liang Luo Assistant Director of National & Local Joint Engineering Lab of Next Generation Internet Data Processing Technology School of Computer Science and Engineering (School of Cyberspace Security) University of Electronic Science and Technology of China

ISBN: (数字)9781665453974

ISBN: (纸本)9781665453981

Human-Machine-Environment (HME) Tri-Co (Coexisting, Cooperative, Cognitive) Education is an indispensable prerequisite and the main content of Artificial Intelligence empowering junior science education. Moreover, it is also a critical requirement for improving the quality of education and promoting the high-end development of education information. Building a unique learning environment with scene perception and an intelligent cognitive process is a tremendous challenge for diverse needs in junior scientific learning scenarios. Therefore, it is necessary to study human-machine cooperation scenarios and design advanced software and hardware. This talk will introduce some of our recent work in affective analysis, multimodal affection data processing methods, and reliability and security of affective computing systems, etc. We will also discuss some directions that are worthy of further studies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Human-Written Commit Messages to Document Code Changes

引用

Journal of computer Science & Technology 2020年第6期35卷 1258-1277页

作者： Yuan Huang Nan Jia Hao-Jie Zhou Xiang-Ping Chen Zi-Bin Zheng Ming-Dong Tang National Engineering Research Center of Digital Life School of Data and Computer ScienceSun Yat-sen University Guangzhou 510006China School of Information Engineering Hebei GEO UniversityShijiazhuang 050031China Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion School of Communication and DesignSun Yat-sen UniversityGuangzhou 510006China School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou 510006China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou 510006China

Commit messages are important complementary information used in understanding code changes. To address message scarcity, some work is proposed for automatically generating commit messages. However, most of these approaches focus on generating summary of the changed software entities at the superficial level, without considering the intent behind the code changes (e.g., the existing approaches cannot generate such message:"fixing 'null' pointer exception"). Considering developers often describe the intent behind the code change when writing the messages, we propose ChangeDoc, an approach to reuse existing messages in version control systems for automatical commit message generation. Our approach includes syntax, semantic, pre-syntax, and pre-semantic similarities. For a given commit without messages, it is able to discover its most similar past commit from a large commit repository, and recommend its message as the message of the given commit. Our repository contains half a million commits that were collected from SourceForge. We evaluate our approach on the commits from 10 projects. The results show that 21.5% of the recommended messages by ChangeDoc can be directly used without modification, and 62.8% require minor modifications. In order to evaluate the quality of the commit messages recommended by ChangeDoc, we performed two empirical studies involving a total of 40 participants (10 professional developers and 30 students). The results indicate that the recommended messages are very good approximations of the ones written by developers and often include important intent information that is not included in the messages generated by other tools.

关键词： commit message recommendation code syntax similarity code semantic similarity code change comprehension

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning for Social Motor Coordination in Two Dimensional Space 26

Safe Reinforcement Learning for Social Motor Coordination in...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Yang, Fan Huang, Yuening Zhai, Chao Zhang, Hehong China University of Geosciences School of Automation Wuhan Campus China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Rice University George R. Brown School of Engineering and Computing HoustonTX United States Fuzhou University School of Computer and Data Science Fuzhou China

ISBN: (纸本)9798331521950

This paper presents an interactive motion control method based on reinforcement learning, designed to assist children with autism who have social motor impairments through a mirror game intervention. The virtual teacher uses the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize its actions, guiding the participant to follow a Lissajous trajectory. To ensure safety, a motion-correction mechanism was developed, which automatically adjusts actions when the predicted trajectory surpasses predefined safety boundaries. The reward function considers both the distance between the virtual teacher and the target trajectory, as well as the distance between the virtual teacher and the participant, with dynamic adjustments applied by the motion-correction mechanism. Experimental results demonstrate that the virtual teacher effectively guides the participant towards the target trajectory while adhering to safety constraints. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?

arXiv

引用

arXiv 2024年

作者： Yu, Xiao Liu, Lei Hu, Xing Keung, Jacky Wai Liu, Jin Xia, Xin State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou China Faculty of Electronic and Information Engineering Xi’an Jiaotong University Shanxi Xi’an China Department of Computer Science City University of Hong Kong Hong Kong School of Computer Science Wuhan University Wuhan China College of Computer Science and Technology Zhejiang University Hangzhou China

With the increasing utilization of large language models such as ChatGPT during software development, it has become crucial to verify the quality of code content it generates. Recent studies proposed utilizing ChatGPT as both a developer and tester for multi-agent collaborative software development. The multi-agent collaboration empowers ChatGPT to produce test reports for its generated code, enabling it to self-verify the code content and fix bugs based on these reports. However, these studies did not assess the effectiveness of the generated test reports in validating the code. Therefore, we conduct a comprehensive empirical investigation to evaluate ChatGPT’s self-verification capability in code generation, code completion, and program repair. We request ChatGPT to (1) generate correct code and then self-verify its correctness;(2) complete code without vulnerabilities and then self-verify for the presence of vulnerabilities;and (3) repair buggy code and then self-verify whether the bugs are resolved. Our findings on two code generation datasets, one code completion dataset, and two program repair datasets reveal the following observations: (1) ChatGPT often erroneously predicts its generated incorrect code as correct, its vulnerable completed code as non-vulnerable, and its failed program repairs as successful during its self-verification. (2) The self-contradictory hallucinations in ChatGPT’s behavior arise: (a) ChatGPT initially generates code that it believes to be correct but later predicts it to be incorrect;(b) ChatGPT initially generates code completions that it deems secure but later predicts them to be vulnerable;(c) ChatGPT initially outputs code that it considers successfully repaired but later predicts it to be buggy during its self-verification. (3) The self-verification capability of ChatGPT can be enhanced by asking the guiding question, which queries whether ChatGPT agrees with assertions about incorrectly generated or repaired code and vulnerabil

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Dynamic resource provisioning for workflow scheduling under uncertainty in edge computing environment

Dynamic resource provisioning for workflow scheduling under ...

引用

作者： Xu, Xiaolong Cao, Hao Geng, Qingfan Liu, Xihua Dai, Fei Wang, Chuanjian School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing China Nanjing University of Information Science and Technology Nanjing China Engineering Research Center of Digital Forensics Ministry of Education Nanjing China School of Big Data and Intelligence Engineering Southwest Forestry University Kunming China College of Information Science and Technology Shihezi University Xinjiang China

Edge computing, an extension of cloud computing, is introduced to provide sufficient computing and storage resources for mobile devices. Moreover, a series of computing tasks in a mobile device are set as structured computing processes and flows to achieve effective management by the workflow. However, the execution uncertainty caused by performance degradation, service failure, and new service additions remains a huge challenge to the user's service experience. In order to address the uncertainty, a software-defined network (SDN)-based edge computing framework and a dynamic resource provisioning (UARP) method are proposed in this paper. The UARP method is implemented in the proposed framework and addresses the uncertainty through the advantages of SDN. In addition, the nondominated sorting genetic algorithm-III is employed to optimize two goals, that is, the energy consumption and the completion time, to obtain balanced scheduling strategies. The comparative experiments are performed and the results show that the UARP method is superior to other methods in addressing the uncertainty, while reducing energy consumption and shortening the completion time. © 2020 John Wiley & Sons, Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Mango Leaf Disease Detection using Yolov8

Deep Learning-based Mango Leaf Disease Detection using Yolov...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Gladson Oliver S Prathusha Perugu Jeevitha S Rashima Mahajan Jasmine Gnana Malar A Raghavan Sheeja AhilanAppathurai Aarti Information Technology Government College of Technology Coimbatore India Department of Computer Science Engineering Sri Venkateswara College of Engineering Tirupathi India Department of Computer Science and Information Technology Kalasalingam Academy of Research and Education Krishnankoil Tamil Nadu India Manav Rachna International Institute of Research and Studies Faridabad India Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tirunelveli India Artificial Intelligence and Data Science R.M.K Engineering College Gummidipoondi Kavaraipettai Tamil Nadu India Department of Electronics and Communication Engineering PSN College of Engineering and Technology Tirunelveli Tamilnadu India School of Computer Science and Engineering Geeta University Panipat

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

The mango holds a significant position in India's fruit crop rotation and plays a major part in the nation's economy. The best strategy to avoid losing money and time is to recognize diseases in crops earlier. Obtaining a comprehensive dataset can be challenging and time-consuming. Additionally, deep learning models may struggle with detecting early-stage symptoms of diseases. In this work, a novel deep learning-based model is proposed for the early detection of mango leaf disease (MLD). An adaptive unsharp mask-guided (AUG) filter is used as a pre-processing step to improve the input pictures from the collected dataset. The enhanced images are fed into the YOLOV8 model for detecting mango leaf disease (MLD) and classifying the different kinds of disease. According to the experimental result, the proposed model attains a 99.29% success rate for the classification of disease in mango leaf. The proposed approach is compared to DL methods such as SSD, Mask RCNN, and YOLO v8. The detection accuracy is improved by the YOLO network over SSD, Mask R-CNN, and Yolo v8 by 7.57%, 4.89%, and 2.36%, respectively. In comparison to SVM, ANN, and CNN-HOG, the proposed approach advances the overall accuracy range by 4.72%, 0.73%, 13.18%, and 5.44%, respectively.

关键词： YOLO Support vector machines Deep learning Adaptation models Accuracy Biological system modeling Neural networks Crops Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

CShaperApp:Segmenting and analyzing cellular morphologies of the developing Caenorhabditis elegans embryo

引用

Quantitative Biology 2024年第3期12卷 329-334页

作者： Jianfeng Cao Lihan Hu Guoye Guan Zelin Li Zhongying Zhao Chao Tang Hong Yan Department of Electrical Engineering City University of Hong KongHong KongChina Centre for Intelligent Multidimensional Data Analysis Limited Hong KongChina College of Computer and Information Hohai UniversityNanjingChina Center for Quantitative Biology Peking UniversityBeijingChina Department of Biology Hong Kong Baptist UniversityHong KongChina State Key Laboratory of Environmental and Biological Analysis Hong Kong Baptist UniversityHong KongChina Peking-Tsinghua Center for Life Sciences Peking UniversityBeijingChina School of Physics Peking UniversityBeijingChina

Caenorhabditis elegans has been widely used as a model organism in developmental biology due to its invariant *** this study,we developed a desktop software CShaperApp to segment fluorescence-labeled images of cell membranes and analyze cellular morphologies interactively during *** *** on the previously proposed framework CShaper,CShaperApp empowers biologists to automatically and efficiently extract quantitative cellular morphological data with either an existing deep learning model or a fine-tuned one adapted to their in-house *** results show that it takes about 30 min to process a three-dimensional time-lapse(4D)dataset,which consists of 150 image stacks at a~1.5-min interval and covers *** embryogenesis from the 4-cell to 350-cell *** robustness of CShaperApp is also validated with the datasets from different ***,modularized implementation increases the flexibility in multi-task applications and promotes its flexibility for future *** cell morphology over development has emerged as a focus of interest in developmental biology,CShaperApp is anticipated to pave the way for those studies by accelerating the high-throughput generation of systems-level quantitative data *** software can be freely downloaded from the website of Github(cao13jf/CShaperApp)and is executable on Windows,macOS,and Linux operating systems.

关键词： C.elegans embryogenesis cellular morphology cellular segmentation deep learning desktop software

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation and Service Provisioning for Softwarized Network Slicing Using Game Theory: A Techno-Economic Approach

Resource Allocation and Service Provisioning for Softwarized...

引用

IEEE India Conference (INDICON)

作者： Deborsi Basu Samriddha Sanyal Goutam Das Uttam Ghosh Raja Datta G. S. Sanyal School of Telecommunications Indian Institute of Technology Kharagpur India Dept. of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur India Dept. of Computer Science and Data Science School of Applied Computational Sciences MMC TN USA

ISBN: (数字)9798350391282

ISBN: (纸本)9798350391299

Softwarized Network Slicing (SNS) is a forthcoming technological advancement that is going to transform conventional resource allocation techniques. Optimizing the flow of slice resources among the key network players, namely MVNOs (Mobile Virtual Network Operators), MIPs (Mobile Infrastructure Providers), and UEs (User Entities), is a complex and challenging task due to its complicated combinatorial nature. Moreover, maintaining the concurrent quality of service of end-users based on UE fairness is also difficult. Considering these factors, in this work, we have proposed a novel resource allocation strategy using a two-tier matching game between MIPs, MVNOs, and UEs, which not only minimizes the resource allocation cost but also maintains a decent UE satisfaction by providing desired UE SINR. An MILP (Mixed Integer Linear Programming) is formed for cost minimization, and the same is solved using a modified differed acceptance stable algorithm. We have compared our improvement with existing and latest state-of-the-art techniques.

关键词： Costs Network slicing Games Transforms Quality of service Interference Minimization Mixed integer linear programming Resource management Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Linn: A Lightweight Image Hiding Method Based on Invertible Neural Network

SSRN

引用

SSRN 2024年

作者： Cheng, Dapeng Zhu, Minghui Mao, Yanyan Gao, Xiaolian Jing, Wanting Kong, Yue Li, Jinjiang School of Computer Science and Technology Shandong Technology and Business University Shandong Yantai264005 China Yantai Key Laboratory of Big Data Modeling and Intelligent Computingy Shandong Yantai264005 China School of Information and Electronic Engineering Shandong Technology and Business University Shandong Yantai264005 China

Image steganography aims to conceal a secret image within a cover image, allowing only those who are informed can recover it. Compared to ordinary steganography, image steganography not only demands the recovered secret image to closely resemble the original image while keeping the stego image well concealed, but also requires a larger capacity. Existing image hiding methods based on invertible neural network have met this requirement, but they generally have a large number of parameters, the complexity of the model is high. In this paper, we propose a lightweight image hiding framework based on invertible neural network called LINN. This framework incorporates the idea of residuals, aiming to minimize the network depth while ensuring image quality. Additionally, it incorporates a spatial attention module, enabling adaptive identiffcation of regions more suitable for concealing secret images. We also try to ensure that the spatial domain and frequency domain of the original image and the image processed by the model are consistent through loss function. Experimental results demonstrate that the method proposed in this paper has stronger generalization ability and a smaller number of parameters, and the image quality generated is better than that generated by other existing methods, while having higher security. © 2024, The Authors. All rights reserved.

关键词： Image quality

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：