检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Bi, Zhangqian Wan, Yao Chu, Zhaoyang Hu, Yufei Zhang, Junyi Zhang, Hongyu Xu, Guandong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is computationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Geometric Latent Diffusion Model for Graph Generation 41

Hyperbolic Geometric Latent Diffusion Model for Graph Genera...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright 2024 by the author(s)

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Precision Irrigation for Coconut Plantations: Enhancing Growth and Sustainability 8

IoT-Enabled Precision Irrigation for Coconut Plantations: En...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Reddy, M.Jaganmohan Ramu, V. Grace Shalini, T. Vincysahaba, R. Devaki, M. Athiraja, A. Telangana Secunderabad India Telangana Hanamkonda India Srm Institute of Science and Technology Kattankulathur School of Computing Department of Computational Intelligence Chengalpattu India St.Joseph College of Engineering Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Velammal College of Engineering and Technology Department of Eee Tamil Nadu Madurai India

ISBN: (纸本)9798350367904

In agriculture, precision irrigation plays a pivotal role in optimizing crop growth and resource utilization. In this study, must proposean Internet of Things based irrigation remote monitoring system tailored for enhancing coconut plant growth. The system integrates sensor technology, Internet of Things connectivity, and data analytics to provide real-time monitoring and control of irrigation parameters such as soilmoisture, temperature, and humidity. Leveraging a network of sensors deployed in the coconut plantation, the system collects and analyzes environmental data to optimize irrigation schedules and ensure optimal growing conditions for coconut plants. Through a user-friendly interface accessible via web or mobile applications, farmers can remotely monitor the status of their plantation and adjust irrigation settings as ***, the system incorporates predictive analytics capabilities to anticipate irrigation needs based on historical data and weather forecasts, thereby enhancing water efficiency and crop productivity. Field trials demonstrate the effectiveness of this Internet of Things based irrigation system in improving coconut plant growth while reducing water consumption and operational costs. This findings underscore the potential of Internet of Things technologies in revolutionizing agricultural practices, facilitating sustainable crop management, and enhancing food security in coconut-producing regions. © 2024 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Development of A Multipurpose Healthcare Mobile App Using JAVA

Development of A Multipurpose Healthcare Mobile App Using JA...

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Pongiannan, R.K. Bushra, S. Nikkath Lathif, Syed Ismail Abdul Pradhan, Saahil Brindha, R. Franklin, J. Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur India Data Science and Business Systems School of Computing Srm Institute of Science and Technology Kattankulathur India Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur India Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Kattankulathur India

ISBN: (纸本)9798350315127

Health care has become an essential part of present human life. The preliminary requirement to select the basic information about medical facilities through a mobile app will serve the needs of the common people. This paper presents an integrated mobile app developed using JAVA. This app is user-friendly in terms of login, registration, and bookings. This caters to the facility to select information regarding doctors, medical lab facilities, pharmacy details, and health articles. This app will provide communication. © 2023 IEEE.

关键词： Medicine

来源：评论

学校读者我要写书评

暂无评论

AGU2-Net: Multi-Scale U2-Net Enhanced by Attention Gate Mechanism for Image Tampering Localization

引用

IEEE Access 2025年 13卷 99659-99671页

作者： Kefei Wu Lin Li Qingyan Li School of Science Jimei University Xiamen China Computer Engineering College Jimei University Xiamen China Digital Fujian Big Data Modeling and Intelligent Computing Institute Jimei University Xiamen China

The advancement of image editing and compositing technologies has posed significant challenges to the authenticity of digital images. Although deep learning algorithms based on convolutional neural networks (CNNs) have made notable progress in image forgery detection, they still face certain limitations in effectively detecting and localizing tampered areas due to the subtle nature of existing manipulation traces. To address this limitation, we propose AGU2-Net, a novel network architecture that integrates an advanced attention mechanism with multi-scale feature extraction. The architecture employs a nested U-structure as its backbone, enabling effective integration of image features across various scales. Additionally, AGU2-Net is an end-to-end autonomous training network with a lightweight framework that incurs low computational overhead. A significant innovation of the architecture is the introduction of the attention gate mechanism, which enhances the network’s ability to selectively process multi-scale features. By adaptively fusing feature information from the encoder and decoder, this mechanism increases spatial perception and improves the network’s ability to capture intricate local tampering details. Experiments on four publicly available benchmarks show that AGU2-Net achieves top F1 scores of 0.556, 0.338, and 0.273 on the CASIA, NIST16, and IMD2020 datasets, respectively, confirming its superior tamper-detection accuracy and sharper pixel-level localization compared with state-of-the-art methods.

关键词： Feature extraction Computer architecture Location awareness Computational modeling Forgery Attention mechanisms Logic gates Splicing Convolution Accuracy

来源：评论

学校读者我要写书评

暂无评论

TIGER: A Generating-Then-Ranking Framework for Practical Python Type Inference

arXiv

引用

arXiv 2024年

作者： Wang, Chong Zhang, Jian Lou, Yiling Liu, Mingwei Sun, Weisong Liu, Yang Peng, Xin College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China School of Software Engineering Sun Yat-sen University China

Python’s dynamic typing system offers flexibility and expressiveness but can lead to type-related errors, prompting the need for automated type inference to enhance type hinting. While existing learning-based approaches show promising inference accuracy, they struggle with practical challenges in comprehensively handling various types, including complex parameterized types and (unseen) user-defined types. In this paper, we introduce TIGER, a two-stage generating-then-ranking (GTR) framework, designed to effectively handle Python’s diverse type categories. TIGER leverages fine-tuned pre-trained code models to train a generative model with a span masking objective and a similarity model with a contrastive training objective. This approach allows TIGER to generate a wide range of type candidates, including complex parameterized types in the generating stage, and accurately rank them with user-defined types in the ranking stage. Our evaluation on the ManyTypes4Py dataset shows TIGER’s advantage over existing methods in various type categories, notably improving accuracy in inferring user-defined and unseen types by 11.2% and 20.1% respectively in Top-5 Exact Match. Moreover, the experimental results not only demonstrate TIGER’s superior performance and efficiency, but also underscore the significance of its generating and ranking stages in enhancing automated type inference. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Agricultural Water Conservation through AI-Enhanced Solar IoT Networks 3

Agricultural Water Conservation through AI-Enhanced Solar Io...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Maniraj, S.P. Monisha, J. Amutha, R. Kavitha, R. Shriidhar, P.J. Srinivasan, C. Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Kattankulathur Tamilnadu Chennai India Tamil Nadu Chennai India Ultra College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Madurai India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vinayaka Missions Kirupananda Variyar Engineering College Department of Computer Science and Engineering Tamil Nadu Salem India Saveetha Universityi Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

With the increasing water shortage and climatic uncertainty, creative strategies for effective water management in agriculture are necessary. This research investigates the integration of Artificial Intelligence (AI), particularly Artificial Neural Networks (ANN), with solar-powered Internet of Things (IoT) networks to enhance water utilization in agricultural activities. The proposed system facilitates accurate irrigation scheduling using real-time data from soil moisture sensors, meteorological stations, and crop health monitoring devices. The ANN model analyses this data to predict ideal irrigation schedules and volumes, minimizing water waste while improving crop yields. The solar-powered IoT framework provides sustainability and reduces dependence on traditional energy sources. Field trials indicate that the AI-enhanced system may promote water saving by as much as 30% relative to traditional irrigation techniques. Moreover, using AI enables adaptive learning, enabling the system to enhance its irrigation tactics using historical and real-time data. This novel method conserves water resources and fosters sustainable agriculture practices, coinciding with global initiatives to address water shortages and assure food security. The findings underscore the potential of technology-based solutions to revolutionize agricultural water management for a sustainable future. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Towards the New XAI: A Hypothesis-Driven Approach to Decision Support Using Evidence

arXiv

引用

arXiv 2024年

作者： Le, Thao Miller, Tim Sonenberg, Liz Singh, Ronal School of Computing and Information Systems The University of Melbourne Australia School of Electrical Engineering and Computer Science The University of Queensland Australia CSIRO’s Data61 Australia

Prior research on AI-assisted human decision-making has explored several different explainable AI (XAI) approaches. A recent paper has proposed a paradigm shift calling for hypothesis-driven XAI through a conceptual framework called evaluative AI that gives people evidence that supports or refutes hypotheses without necessarily giving a decision-aid recommendation. In this paper, we describe and evaluate an approach for hypothesis-driven XAI based on the Weight of Evidence (WoE) framework, which generates both positive and negative evidence for a given hypothesis. Through human behavioural experiments, we show that our hypothesis-driven approach increases decision accuracy and reduces reliance compared to a recommendation-driven approach and an AI-explanation-only baseline, but with a small increase in under-reliance compared to the recommendation-driven approach. Further, we show that participants used our hypothesis-driven approach in a materially different way to the two baselines. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilizing BERT and TextCNN for Detecting Depression within Social Media Text Comments

Utilizing BERT and TextCNN for Detecting Depression within S...

引用

computing Innovation, Intelligence, Technologies and Education (CIITE), International Conference on

作者： Wenqi An Shaidah Jusoh School of Computing and Data Science Xiamen University Malaysia Sepang Selangor Malaysia School of Electrical Engineering and Artificial Intelligence Xiamen University Malaysia Sepang Selangor Malaysia

ISBN: (数字)9798350377286

ISBN: (纸本)9798350377293

Depression is a common symptom associated with various mental health conditions. Social media platforms have become a space for people to openly share their thoughts and feelings. These online expressions may have signs of depression. As such, the ability to detect depression in people’s social media content is a crucial step towards addressing and preventing mental health issues. Deep learning techniques have emerged as effective approaches for analyzing large textual datasets, such as social media posts. This paper examines two well-established deep learning (DL) models, namely BERT and TextCNN in detecting depressive symptoms from text. The findings suggest that both the BERT and TextCNN models exhibit the capability to identify signs of depression within text-based content. While the TextCNN model was found to have a faster training time, the BERT model demonstrated a higher overall accuracy rate in detecting depressive symptoms. These results highlight the potential of deploying both models and natural language processing techniques to gain insights into depressive symptoms from people’s online expressions.

关键词： Deep learning Training Accuracy Runtime Social networking (online) Mood Computational modeling Mental health Depression Context modeling

来源：评论

学校读者我要写书评

暂无评论

Correction to: Consistent Prompt Tuning for Generalized Category Discovery (International Journal of Computer Vision, (2025), 10.1007/s11263-024-02343-w)

引用

International Journal of Computer Vision 2025年 1-10页

作者： Yang, Muli Yin, Jie Gu, Yanan Deng, Cheng Zhang, Hanwang Zhu, Hongyuan Singapore Singapore School of Electronic Engineering Xidian University Xi’an China Norinco Group Testing and Research Institute Xi’an China College of Computing and Data Science Nanyang Technological University Singapore Singapore

The original publication of this article was published with several errors and has been corrected as follows. In the Section 4.3.1, the hyperlink for the Section 5 citation was missing and has been included. In Table 6, the significance ‘Reimplemented using CLIP’s image encoder’ was incorrectly provided for the method ‘CPT (Ours) and has been removed. In Table 12, the method name was incorrectly listed as ‘CLIP-GC’ but should read as ‘CLIP-GCD’. Additionally, the significance ‘Reimplemented using (Open/Meta) CLIP’s image encoder’ was missing for the method ‘CLIP-GCD’ and has been included. In Table 15, the incorrect significance ‘Reimplemented using CLIP’s image encoder’ was provided for the methods GCD (2022a), SimGCD (2023) and GPC (2023). This should be removed and the correct significance ‘Training with estimated category number’ has been included. In Table 22, the species "andrias acropora acuminata (staghorn coral)" was missing and has been included before the species "andrias davidianus (chinese giant salamander)." For completeness and transparency, the old incorrect and the corrected versions of Tables are displayed below. The original article has been corrected. Incorrect Table 6: GCD accuracy (%) in the customized setting on NICO dataset dataset → NICO-10 NICO-33 NICO-100 Method ↓ All Old New All Old New All Old New GCD (2022a) 95.1 97.3 94.0 38.6 58.4 25.1 48.0 67.0 39.1 PromptCAL (2023b) 89.6 80.9 93.6 30.5 42.4 22.5 45.3 53.4 41.5 SimGCD (2023) 97.3 97.0 97.4 45.9 67.7 46.3 65.1 37.4 PIM (2023) 96.4 97.2 96.0 42.2 67.6 24.9 49.5 67.5 41.0 GCD† 98.0 39.3 65.0 21.8 51.6 54.5 PromptCAL† 97.5 97.1 29.2 41.8 20.6 48.9 64.4 41.7 SimGCD† 97.5 46.6 29.1 69.4 44.6 PIM† 97.5 97.0 71.8 50.0 39.2 CPT (Ours)† 98.5 Bold value indicates the best results and underlined value indicates the second best results †Reimplemented using CLIP’s image encoder Corrected Table 6: GCD accuracy (%) in the customized setting on NICO dataset dataset → NICO-10 NICO-33 NICO-100 Method ↓

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：