检索结果-内蒙古大学图书馆

IAENG International Journal of computer Science 2025年第6期52卷 2015-2021页

作者： Zheng, Shuailong Tao, Huawei Yu, Hang Xi, Ji Zhu, Chunhua Wang, Xuemei Key Laboratory for Grain Information Processing and Control Henan Key Laboratory of Grain Storage Information Intelligent Perception and Decision Making Henan University of Technology Zhengzhou450001 China Computer Information Engineering Changzhou Institute of Technology Jiangsu213000 China

The limited number of labeled samples can significantly affect the accuracy of speech lie detection systems. However, semi-supervised algorithms have been shown to effectively improve detection performance under such constraints. To address this challenge, this paper proposes a semi-supervised speech lie detection algorithm that utilizes multiple features and adaptive thresholds. First, through comparative analysis, this paper identifies 312-dimensional acoustic features and 768-dimensional self-supervised features as the key elements of lie detection. Then, these acoustic features are processed using a bidirectional long short-term memory network (Bi-LSTM), which obtains comprehensive information by analyzing acoustic statistical features in both forward and backward directions. Subsequently, this paper develops a semi-supervised feature fusion module (BSFM) to extract deeper insights from basic features and achieves adaptive feature fusion through targeted training. In addition, based on a detailed analysis of the distribution characteristics of lie detection samples, this paper proposes an improved Freematch algorithm to better utilize unlabeled data. Experimental results show that the proposed algorithm outperforms most existing methods on the self-built H-Wolf dataset and the Columbia/SRI/Colorado Corpus (CSC). © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Contrastive Learning With Hard Negative Sampling for Code Search Tasks 39

Uncertainty-Aware Contrastive Learning With Hard Negative Sa...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liu, Han Zhan, Jiaqing Zhang, Qin College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University China

ISBN: (纸本)157735897X

Code search is a highly required technique for software development. In recent years, the rapid development of transformer-based language models has made it increasingly more popular to adapt a pre-trained language model to a code search task, where contrastive learning is typically adopted to semantically align user queries and codes in an embedding space. Considering that the same semantic meaning can be presented using diverse language styles in user queries and codes, the representation of queries and codes in an embedding space may thus be non-deterministic. To address the above-specified point, this paper proposes an uncertainty-aware contrastive learning approach for code search. Specifically, for both queries and codes, we design an uncertainty learning strategy to produce diverse embeddings by learning to transform the original inputs into Gaussian distributions and then taking a reparameterization trick. We also design a hard negative sampling strategy to construct query-code pairs for improving the effectiveness of uncertainty-aware contrastive learning. The experimental results indicate that our approach outperforms 10 baseline methods on a large code search dataset with six programming languages. The results also show that our strategies of uncertainty learning and hard negative sampling can really help enhance the representation of queries and codes leading to an improvement of the code search performance. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Domain Adversarial Interaction Network for Cross-Domain Fault Diagnosis 4th

Domain Adversarial Interaction Network for Cross-Domain Fau...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Lu, Weikai Chen, Jian Zheng, Hao Fan, Haoyi Wei, Eng Yee Cao, Xinrong Zhang, Deyang School of Electronic Electrical Engineering and Physics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Henan Provincial Institute of Scientific and Technical Information Zhengzhou450003 China

ISBN: (纸本)9783031200984

Intelligent fault diagnosis has been widely used in the industry and plays a crucial role in the health management of machinery. In recent years, unsupervised domain adaptation (UDA) has been applied to fault diagnosis, showing excellent performance under variable working conditions. However, most existing UDA-based methods do not consider the temporal relations in the fault signal, resulting in sub-optimal performance. In this paper, we proposed a domain adversarial interaction network (DAIN) to solve this problem. By downsampling sub-sequences of fault signals and interacting with their features, DAIN can obtain feature representations containing the temporal relations. In addition, domain adversarial learning and maximum mean discrepancy (MMD) are applied to DAIN to align the domain discrepancy and distribution discrepancy of source and target domains. We conducted extensive experiments on the public Paderborn university (PU) dataset, and the results demonstrate that the proposed method can achieve higher cross-domain fault diagnosis accuracy than the existing methods. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

ReviveDiff: A Universal Diffusion Model for Restoring Images in Adverse Weather Conditions

arXiv

引用

arXiv 2024年

作者： Huang, Wenfeng Xu, Guoan Jia, Wenjing Perry, Stuart Gao, Guangwei The Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China

Images captured in challenging environments–such as nighttime, foggy, rainy weather, and underwater–often suffer from significant degradation, resulting in a substantial loss of visual quality. Effective restoration of these degraded images is critical for the subsequent vision tasks. While many existing approaches have successfully incorporated specific priors for individual tasks, these tailored solutions limit their applicability to other degradations. In this work, we propose a universal network architecture, dubbed "ReviveDiff", which can address a wide range of degradations and bring images back to life by enhancing and restoring their quality. Our approach is inspired by the observation that, unlike degradation caused by movement or electronic issues, quality degradation under adverse conditions primarily stems from natural media (such as fog, water, and low luminance), which generally preserves the original structures of objects. To restore the quality of such images, we leveraged the latest advancements in diffusion models and developed ReviveDiff to restore image quality from both macro and micro levels across some key factors determining image quality, such as sharpness, distortion, noise level, dynamic range, and color accuracy. We rigorously evaluated ReviveDiff on seven benchmark datasets covering five types of degrading conditions: Rainy, Underwater, Low-light, Smoke, and Nighttime Hazy. Our experimental results demonstrate that ReviveDiff outperforms the state-of-the-art methods both quantitatively and visually. Copyright © 2024, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Fire Detection Based on Improved Feature Fusion 13

Fire Detection Based on Improved Feature Fusion

引用

13th International Conference on information technology in Medicine and Education, ITME 2023

作者： Cao, Xinrong Wu, Jincai Li, Zuoyong College of Computer and Control Engineering Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China School of Electronic Electrical Engineering and Physics Fujian University of Technology Fuzhou350118 China Sichuang Technology Co. Ltd. Fuzhou350100 China

ISBN: (纸本)9798350319156

Fire is a serious disaster that endangers life and property worldwide. Accurate and prompt fire detection can provide early warning information for firefighting efforts. Deep learning-based object detection algorithms have proven to be useful in the field of fire detection. However, fire detection is a particularly challenging task, due to the low-resolution of fire images and the presence of blurring and deformation in the targets. Existing fire detection methods are limited by poor detection accuracy and slow speed in complex fire scenarios. To address these challenges, we propose a fire detection algorithm based on improved YOLOv5s. Firstly, the attention module is embedded into the network structure. We introduce this attention module into the last layer of the backbone to enhance feature extraction ability. Secondly, we modify the Neck structure to fully fuse different feature maps. Through fusing extra low-level features from the backbone, it utilizes various receptive fields to enhance the expression of feature. Thirdly, SIoU is introduced to achieve faster convergence during the training. SIoU take into account the direction of the mismatch to redefine penalty indicators. The experimental results show that our proposed algorithm outperforms commonly used models. Even compared to specific fire detectors, our model exhibits certain advantages. © 2023 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Multi-Attention Gate Based U-net for Retinal Vessel Segmentation 12

Multi-Attention Gate Based U-net for Retinal Vessel Segmenta...

引用

12th International Conference on information technology in Medicine and Education, ITME 2022

作者： Zhu, Yu Li, Rui Teng, Shenghua Cao, Xinrong Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao266590 China College of Computer and Control Engineering Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9798350310153

Retinal blood vessel segmentation images can be used to detect and evaluate various cardiovascular and ophthalmic diseases. However, due to the intricate vessel structures and blurred boundaries of vessels, it is a huge challenge to efficiently and accurately segment blood vessels. To deal with the above problems, this paper improves on the U-net by firstly using multi-scale feature convolution with kernels of varying size for feature extraction. Second, a non-local attention mechanism is applied to obtain richer global semantic information. Then multi-attention gate is used in the skip connection part by inputting feature maps of various scales and dimensions and selectively learning the interrelated regions, which improves the segmentation ability of the network model for the tiny structure of blood vessels. Quantitative and qualitative experimental results on two public datasets, DRIVE and CHASE-DB1, demonstrate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

A Network Combining CNN and Transformer for Blind Image Super-Resolution 12

A Network Combining CNN and Transformer for Blind Image Supe...

引用

12th International Conference on information technology in Medicine and Education, ITME 2022

作者： Zhang, Shuhao Li, Zuoyong Teng, Shenghua Zeng, Kun Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao266590 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China

ISBN: (纸本)9798350310153

Blind super-resolution (SR) requires not only estimating blur kernel, but also super-resolving low-resolution image based on estimated blur kernel. Most blind SR methods use convolutional neural networks (CNNs) for kernel estimation, which cannot exploit long-range dependency within image domain, thus failing to predict blur kernel accurately. To address this issue, we propose a network combining CNN and transformer named NCCT for kernel estimation. By modeling local and non-local image priors simultaneously, NCCT outperforms other blind SR methods in terms of kernel estimation accuracy. Moreover, we design a network module named RRFDB for constructing lightweight blind SR network, which runs faster and achieves comparative SR performance with fewer parameters compared with other state-of-the-art blind SR methods. © 2022 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Survey on Image Object Detection Algorithms Based on Deep Learning 7th

Survey on Image Object Detection Algorithms Based on Deep Le...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Fang, Wei Shen, Liang Chen, Yupeng School of Computer and Software Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China

ISBN: (纸本)9783030786083

With the development of image processing technology, computer vision is becoming more and more popular. In recent years, deep learning has flourished, significant progress has been made in object detection. Especially after the R-CNN framework was proposed, the object detection framework based on deep learning has gradually become the mainstream, which can be divided into two categories: region-based and regression-based. Taking these two types of frameworks as the main body, this paper summarizes the research background and then discusses the object detection algorithms based on candidate regions represented by Faster R-CNN and the algorithms based on regression represented by the YOLO series. According to the development history, this paper summarizes the framework proposed in recent years, compares and analyzes the performance of object detection algorithms on public datasets, and introduces the application scenarios of those algorithms. Finally, this paper discusses the current difficulties and challenges in object detection and looks forward to the future development direction. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Short-Term Electric Load Forecasting Method Based on the Fusion of Global and Local Features 9

A Short-Term Electric Load Forecasting Method Based on the F...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Gu, Haozhan Tian, Hangwei Wang, Jingchun Li, Yumei Shandong University Of Arts Academy of Fine Arts China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350391367

Accurate short-term electric load forecasting is crucial for ensuring the stability and efficiency of the power grid. This study proposes an innovative dual-branch electric load forecasting model that enhances the accuracy of predictions by processing global and local features in parallel. Global features are extracted through the Savitzky-Golay filter and a linear model to capture the overall trends of the load data. Local features are identified using the Convolutional Self-Attention Module, which integrates the local perception capabilities of Convolutional neural network with the self-attention mechanism of Transformers. By employing a Weighted Feature Fusion Network, we effectively integrate global and local information to enhance the performance of load forecasting. Experimental results demonstrate that the proposed model significantly outperforms existing models in predictive performance. The model presented in this study offers a new perspective on electric load forecasting and has the potential to become an effective tool for power system planning and scheduling. © 2024 IEEE.

关键词： Deep learning Feature fusion Load prediction Time series data analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification Segmentation Method of Gastric Cancer Pathological Images Based on Deep Learning

Multi-Classification Segmentation Method of Gastric Cancer P...

引用

2024 lEEE International Conference on Advanced information, Mechanical Engineering, Robotics and Automation, AIMERA 2024

作者： Zhou, Hehu Pan, Jingshan Na, Li Ding, Qingyan Zhou, Chengjun Du, Wantong Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China The Second Hospital of Shandong University Department of Pathology Jinan China

ISBN: (纸本)9798350343335

Gastric cancer is a serious health threat, and pathological imaging is important in detecting it. These images can assist doctors in accurately determining the location of the cancer, thereby providing an important reference for clinical decision-making. In the field of image processing, deep learning technology is leading to more and more excellent segmentation models. The Trans-Unet model has achieved success in the image segmentation. However, when applying this model to gastric cancer pathological section data, the segmentation boundary appears jagged. We propose three possible solutions. First, we designed an attention connection module to replace the skip connections in the model to enhance the prediction accuracy of the model. Second, we designed a prediction processing unit that takes the model's prediction results as input and uses a Conditional Random Field (CRF) for further prediction calculations. To enable the model to meet the requirements of multi-classification of images, we designed a dynamic weight selection module to enhance the model's accuracy for multi-classification tasks. After our optimization, the optimized model improved by 8% on the DSC evaluation index and 39% on the HD evaluation index. In addition, the jagged boundary problem in the prediction results has also been effectively improved. Through comparative experiments and erosion experiments, we found that the improved method enhances the accuracy of model prediction and reduces the jagged results at the boundary. © 2024 IEEE.

关键词： Health risks

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：