检索结果-内蒙古大学图书馆

6th International Conference on Electronic Information Technology and Computer engineering, EITCE 2022

作者： Guo, Xin Gu, Shenming Wei, Dan School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China

ISBN: (纸本)9781450397148

Rapid acquisition of fish freshness is an important task. The traditional freshness detection of aquatic fish has the problems of damaging samples, complicated operation and long detection time. A convenient, rapid, nondestructive and accurate freshness detection method is urgently needed in production. In this study, the freshness of aquatic fish was evaluated nondestructively and rapidly by machine vision. Firstly, we select the appropriate data set, and add the attention mechanism module to the end of the MobileNetV1 with the default alpha value. Secondly, the alpha value of all models is reduced to compare the performance for subsequent deployment to the cloud and small embedded devices with limited resources. Finally, the network is trained by real data. The results show that the MobilenetV1 network with attention mechanism module can better evaluate the freshness of fish through the fisheye image. The convergence speed and accuracy of the network are improved compared with the original network, and it is more suitable for the task of determining the freshness of fish through fisheye. © 2022 Association for Computing Machinery.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Gaussian process multi-label classification based on multi-view similarity fusion 4

Gaussian process multi-label classification based on multi-v...

引用

4th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2022

作者： Xiang, Hui Gu, Shenming School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China

ISBN: (纸本)9781450398343

Multi-view multi-label learning serves as a vital framework for learning from objects with diverse representations and rich semantics. The Gaussian process (GP), as an efficient and flexible Bayesian nonparametric model, the GP has effectively solved various tasks in machine learning. However, the Gaussian process has rarely been directly applied to multi-view multi-label learning scenarios. Therefore, in this paper, we propose a new multi-view multi-label learning method (mvml-DSimGP) based on the Gaussian pass latent variable model (GPLVM), which consists of similar non-parametric mapping function learning, rule constraint learning and label learning. Similarity nonparametric study mapping function for multiple-views data analysis, it studied the view within the similarity and latent mapping function between the parameters. On the basis of the similarity of nonparametric function learning, regular constraints are introduced, and put forward multi-label learning. Instances with similar label information are encouraged to have similar output representations in the embedded space, making it sufficient discernment in the embedded space. Numerous experiments on real-world datasets clearly show that mvml-DSimGP has good performance compared to other general multi-view multi-label learning methods. © 2022 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Super-resolution adversarial generative fish classification based on Swin-Transformer 6

Super-resolution adversarial generative fish classification ...

引用

6th International Conference on Electronic Information Technology and Computer engineering, EITCE 2022

作者： Gong, Yaohan Gu, Shenming Guan, Linting School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China

ISBN: (纸本)9781450397148

The development of fish detection and identification technology is crucial in fishery production. Due to the large intra-class difference and high inter-class similarity, fish classification tasks are considered to be fine-grained. In addition, the acquisition of fish images is often affected by lumps, angles, complex backgrounds, weather, and other factors, which makes the classification task difficult. We present a fish classification method that combines super-resolution reconstruction, multi-scale feature information, and self-attention to improve image quality and classification. Through super-resolution reconstruction and data augmentation, image quality can be improved. A feature extraction network based on Swin-Transformer is used to extract the image's multi-scale feature information and self-attention. The method was evaluated using the Nature Conservancy's publicly available fisheries monitoring dataset. The results of the experiments reveal that the approach may significantly increase image quality while completing the fish classification. At the same time, we compared our results to those of other approaches. © 2022 Association for Computing Machinery.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Fine-grained classification network for fish based on the attention mechanism and EfficientNet 4

Fine-grained classification network for fish based on the at...

引用

4th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2022

作者： Gong, Yaohan Gu, Shenming Guan, Linting School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China

ISBN: (纸本)9781450398343

Many countries have been interested in the sustainable development of marine resources. Countries can protect the sustainable development of fishery resources by joining international fisheries organizations such as CCSBT, IATTC, IOTC, ICCAT, and others, and by adhering to the Code of Conduct for Responsible Fisheries. Traditional fishing supervision methods, on the other hand, frequently have the issue that the amount of original data is cumbersome and expensive, which cannot be handled manually and wastes a lot of manpower. This paper investigates fine-grained fish classification methods based on deep learning and attention mechanisms and proposes one that can target complex background and actual working scenarios, allowing countries to reallocate human capital to management and law enforcement activities. © 2022 ACM.

关键词： Fisheries

来源：评论

学校读者我要写书评

暂无评论

Semantic-Reconstructed Graph Transformer Network for Event Detection

Semantic-Reconstructed Graph Transformer Network for Event D...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zhuochun Miao Xingrui Zhuo Gongqing Wu Chenyang Bu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Anhui China

Event detection (ED) is a key subtask of information extraction to extract key events, such as stock rise and fall and social public opinion, from news or social media. Although current GCN-based event detection methods achieve remarkable success via building graphs with dependency trees, they typically suffer from two challenges: 1) They use sequence models to learn contextual information of sentences, ignoring the longterm dependencies problem of sequence models might learn ineffective information and make it propagate in GCN layers. 2) Most methods do not exploit global dependency label information and grammatical structure information that convey rich linguistic knowledge directly, and only consider local dependency label information. To cope with these challenges, we propose a novel event detection model via semantic-reconstructed graph transformer networks (SRGTNED), which incorporates semantic reconstruction and path information collection methods. Using the semantic reconstruction method, we assign a pruned sequence to each word based on the path information to capture contextual information consistent with sentence semantics. Moreover, to better utilize global dependency label information and grammatical structure information, a Graph Transformer Network (GTN)-based heterogeneous graph embedding framework is introduced to automatically learn path information between important words by converting sentences as heterogeneous graphs. We conduct experiments on the ACE2005 dataset and the Commodity News dataset, and the experimental results demonstrate that our method significantly outperforms 11 state-of-the-art baselines in terms of the F1-score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Image Enhancement of Rural Orchard Security Monitoring under Low Illumination 6

Research on Image Enhancement of Rural Orchard Security Moni...

引用

6th International Conference on Electronic Information Technology and Computer engineering, EITCE 2022

作者： Zhou, Zili Gu, Shenming School of Information Engineering Zhejiang Ocean University Zhoushan316022 China Key Laboratory of Oceanographic Big Data Mining Application of Zhejiang Province Zhejiang Ocean University Zhoushan316022 China

ISBN: (纸本)9781450397148

It is great significance to improve the quality of the monitoring image for the low illumination situation and to improve the security of the rural orchard. In this paper, an improved block homomorphic filtering algorithm is proposed to improve the quality of video surveillance image due to low illuminance in real environment. On the basis of image block adaptation and according to different illumination conditions, the filtering effect is improved by adding and adjusting the weight factor of the transfer function, and the blocking edge effect is alleviated by smoothing filtering. In order to solve the problem of low saturation of low illumination image, the image saturation is adjusted hierarchically and the saturation lower than the threshold value is nonlinear pulled up, so as to restore the color saturation of the image as much as possible. The experimental results show that the PSNR, SSIM and IE are improved by 6%, 21% and 4% respectively. Ultimately, it can improve effectively the image quality of orchard video monitoring under low illumination. © 2022 Association for Computing Machinery.

关键词： Orchards

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

Evaluating the Performance to Detecting Topic Shift of Large...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9798350376548

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Classification via Hierarchical Graph Embedding

Multivariate Time Series Classification via Hierarchical Gra...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wenhao Niu Xingrui Zhuo Gongqing Wu JunWei Lv Zan Zhang Chenyang Bu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Anhui China

Multivariate time series classification aims to determine the labels for multivariate time series samples. Although variable interaction relationships and sample similarity relationships exist in multivariate time series, the available related methods usually ignore the rich relationships and are ineffective in exploiting these. To solve this problem, we propose a Hierarchical Graph Embedding for Multivariate Time Series Classification (MTSC-HGE), which consists of a variable-wise attentive graph pooling module and a sample-wise graph convolutional module to obtain the relationships of variables and samples. Specifically, we design an attentive graph pooling module based on self-attention, which can obtain sample features fusing temporal patterns and variable interaction relationships in samples. Furthermore, we propose a graph mapping criterion that converts the MTS dataset into a graph based on dynamic time warping to explicitly reflect the similarity relationships between samples. To capture latent sample relationships, a GCN module is utilized on the sample graph to integrate sample features obtained from the attentive graph pool module. In addition, a classifier takes the rich representation output by the model to get the final predicted class. Extensive experiments on 14 public datasets show that MTSC-HGE significantly outperforms state-of-the-art baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Production quality early warning method for firearms components based on cloud edge collaboration 4

Production quality early warning method for firearms compone...

引用

4th International Conference on Machine Learning and Computer Application, ICMLCA 2023

作者： Sun, Jiawei Hao, Jia Zhang, Xiaoning School of Mechanical Engineering Beijing Institute of Technology Beijing10081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314019 China Key Laboratory of Industry Knowledge and Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing Institute of Technology Beijing10008 China Tianjin Key Laboratory of Space Environment Simulation Technology Tianjing300450 China

ISBN: (纸本)9798400709449

Digital transformation in manufacturing has become a trend with the continuous development of cloud computing and edge computing. The production process of firearms components is highly challenging and quality problems in the production process may directly affect the safety of people's lives and property. Thus, this paper proposes a production-quality early warning method for firearms components based on cloud-edge collaboration. Real-time early warning and rapid processing for abnormal conditions in the production process are realized based on cloud data analysis and edge intelligent prediction, thereby improving production efficiency and quality. The cloud edge collaboration framework is developed for cloud training of the long short-term memory models and real-time sample edge acquisition, enhancing the adaptability of quality early warning algorithms under specific conditions and the real-time quality of early warning for firearms components. © 2023 ACM.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Do Media Reports Matter to House Price Expectations?Evidence from Beijing

引用

Journal of Systems Science and Information 2022年第4期10卷 388-409页

作者： Jing HE Diandian MA Xiuting LI Jichang DONG Postdoctoral Research Center of Agricultural Bank of China Beijing 100005China School of Statistics Renmin University of ChinaBeijing 100872China School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China

House price expectations(HPE)is a key factor affecting housing market *** Beijing as an example,this study innovatively proposes an internet data-based measurement of HPE and text analysis-based quantification of media reports from media attention and media *** model is performed to empirically test the impact of media reports on the level and accuracy of *** empirical results show no significant relationship between media attention and the level of HPE,but a significant relationship to the accuracy of *** higher the media attention(i.e.,the more intensive the media reports),the smaller the deviation between HPE and actual housing *** attitude of media reports is significantly related to the level and accuracy of *** is easier to guide the formation of HPE through media reports with clear opinions,indicating that media could promote the sustainable development of the real estate market.

关键词： media reports real estate market housing prices public expectations

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：