检索结果-内蒙古大学图书馆

Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model

Plant Phenomics 2023年第3期5卷 501-519页

作者： Qianding Huang Xingcai Wu Qi Wang Xinyu Dong Yongbin Qin Xue Wu Yangyang Gao Gefei Hao State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China Text Computing&Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou UniversityGuiyang 550025China National Key Laboratory of Green Pesticide Guizhou UniversityGuiyang 550025China

Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food *** detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating ***,existing methods are still limited to single crop disease *** importantly,the existing model has a large number of parameters,which is not conducive to deploying it to agricultural mobile ***,reducing the number of model parameters tends to cause a decrease in model *** solve these problems,we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple *** detail,we design 2 strategies to build 4 different lightweight models as student models:the YOLOR-Light-v1,YOLOR-Light-v2,Mobile-YOLOR-v1,and Mobile-YOLOR-v2 models,and adopt the YOLOR model as the teacher *** develop a multistage knowledge distillation method to improve lightweight model performance,achieving 60.4%mAP@.5 in the PlantDoc dataset with small model parameters,outperforming existing ***,the multistage knowledge distillation technique can make the model lighter while maintaining high *** only that,the technique can be extended to other tasks,such as image classification and image segmentation,to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart *** code is available at https://***/QDH/MSKD.

关键词： Plant diagnosis image

来源：评论

学校读者我要写书评

暂无评论

Kernel-Based Causal Discovery in Large Time Series datasets 8

Kernel-Based Causal Discovery in Large Time Series Datasets

引用

8th International Conference on big data and Information Analytics, bigDIA 2022

作者： Liu, Lihua Li, Yanmin Huang, Hongbin Chen, Qiuju Sun, Jiao Wang, Mao National University of Defense Technology Laboratory for Big Data and Decision Changsha China School of Information Science and Technology University of Science and Technology of China Hefei China

ISBN: (数字)9781665487962

ISBN: (纸本)9781665487962

Discovering causal relationships from a large-scale observational time series dataset is an emerging topic in the current field of research, such as neuroscience and system monitoring. Traditional causal inference approaches in such fields are challenging since the curse of dimensionality and the large sample size. Here, we propose a kernel-based causal discovery (KCD) method by capitalizing on a characterization of conditional independence in reproducing kernel Hilbert spaces. Specifically, KCD uses an iterative and heuristic procedure to add variables into the causal parents set and then adopts the kernel-based conditional independence test to determine the true causal parents. We validated this approach on a large-scale synthetic dataset that simulates the typical properties of real-world data. The results of the experiments have shown that the proposed method is superior to currently existing technologies in terms of detection capabilities, which provides a completely new way to explore how to discover and quantify causal networks from time series in the current research field.a © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Face anti-spoofing based on multi-modal and multi-scale features fusion

引用

The Journal of China Universities of Posts and Telecommunications 2022年第6期29卷 73-82页

作者： Kong Chao Ou Weihua Gong Xiaofeng Li Weian Han Jie Yao Yi Xiong Jiahao School of Big Data and Computer Science Guizhou Normal UniversityGuiyang 550025China Special Key Laboratory of Artificial Intelligence and Intelligent Control of Guizhou Province Guizhou Institute of TechnologyGuiyang 550003China Guizhou Science and Technology Information Center Department of Science and Technology of Guizhou ProvinceGuiyang 550002China

Face anti-spoofing is used to assist face recognition system to judge whether the detected face is real face or fake face. In the traditional face anti-spoofing methods, features extracted by hand are used to describe the difference between living face and fraudulent face. But these handmade features do not apply to different variations in an unconstrained environment. The convolutional neural network(CNN) for face deceptions achieves considerable results. However, most existing neural network-based methods simply use neural networks to extract single-scale features from single-modal data, while ignoring multi-scale and multi-modal information. To address this problem, a novel face anti-spoofing method based on multi-modal and multi-scale features fusion(MMFF) is proposed. Specifically, first residual network(Resnet)-34 is adopted to extract features of different scales from each modality, then these features of different scales are fused by feature pyramid network(FPN), finally squeeze-and-excitation fusion(SEF) module and self-attention network(SAN) are combined to fuse features from different modalities for classification. Experiments on the CASIA-SURF dataset show that the new method based on MMFF achieves better performance compared with most existing methods.

关键词： face anti-spoofing multi-modal fusion multi-scale fusion self-attention network(SAN) feature pyramid network(FPN)

来源：评论

学校读者我要写书评

暂无评论

Inductive Relation Prediction with Logical Reasoning Using Contrastive Representations

Inductive Relation Prediction with Logical Reasoning Using C...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Pan, Yudai Liu, Jun Zhang, Lingling Zhao, Tianzhe Lin, Qika Hu, Xin Wang, Qianying School of Computer Science and Technology Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Lenovo Research Beijing China

Relation prediction in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant embedding paradigm has a restriction on handling unseen entities during testing. In the real-world scenario, the inductive setting is more common because entities in the training process are finite. Previous methods capture an inductive ability by implicit logic in KGs. However, it would be challenging to preciously acquire entity-independent relational semantics of compositional logic rules and to deal with the deficient supervision of logic caused by the scarcity of relational semantics. To this end, we propose a novel graph convolutional network (GCN)-based model LogCo with logical reasoning by contrastive representations. LogCo firstly extracts enclosing subgraphs and relational paths between two entities to supply the entity-independence. Then a contrastive strategy for relational path instances and the subgraph is proposed for the issue of deficient supervision. The contrastive representations are learned for a joint training regime. Finally, prediction results and logic rules for reasoning are attained. Comprehensive experiments on twelve inductive datasets show that LogCo achieves outstanding performance comparing with SOTA inductive baselines. © 2022 Association for Computational Linguistics.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Design of Wrist Rehabilitation Robot 12

Design of Wrist Rehabilitation Robot

引用

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

作者： Zhenfeng, Wang Key Laboratory of Big Data and Artificial Intelligence in University of Fujian Province MinNan Science and Technology University Quanzhou China

ISBN: (纸本)9798350310153

We have developed a wrist rehabilitation manipulator to help patients with wrist injuries during exercise achieve sustained and standardized rehabilitation. Based on the theory of rehabilitation medicine, a 3RRP spherical parallel three-dimensional exoskeleton repair manipulator was developed. According to the principle of ergonomics, the shape safety of the robot was optimized. The virtual prototype system is used to simulate the rehabilitation manipulator and MATLAB is used to operate the recovery manipulator. The simulation results show that the designed manipulator has three degrees of freedom, which can meet our needs. The working area is part of the spherical area, and there is no cavity. The appearance, color and humanistic dimension can enable patients to obtain better treatment experience. Conclusion: It provides some basis for the industrial design of manipulator. © 2022 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Legal Judgement Prediction via Contrastive Learning Based-Retrieval and Semantic Embedding

Legal Judgement Prediction via Contrastive Learning Based-Re...

引用

2024 IEEE International Symposium on Product Compliance Engineering-Asia, ISPCE-AS 2024

作者： Wei, Chaoyu Zhang, Qixuan Xu, Juan Wang, Yanling Huang, Zhenhua Hao, Tianyong School of Computer Science South China Normal University GuangZhou China Big Data Rule of Law Research Institute Nanjing University of Information Science & Technology Nanjing China School of Law South China Normal University GuangZhou China

ISBN: (纸本)9798331523008

Legal judgment prediction is a significant task in Legal Artificial Intelligence, aiming to predict judgment results based on fact descriptions automatically. The judgment output may include law articles, charges, prison terms, or combinations. Relevant legal cases with similar backgrounds or events should likewise be considered essential references for judgment, as they play an indispensable role in evaluating the prediction task. However, when applied to Chinese legal data, current methodologies often neglect the specialized preprocessing required for unique semantic attributes of Chinese, which affects their prediction performance. This paper proposes a novel contrastive learning- based model for legal judgment prediction named CLR-LJP to improve prediction performance. According to the legal judgment process in real life, law article prediction is converted as a multi- label classification task that includes both relative law cases and law articles. The CLR-LJP firstly converts fact descriptions, law articles, and charges into vectors by embedding Chinese semantics. Then, contrastive learning is introduced in retrieval training to distinguish the similar content of different label definitions. Finally, the role embedding method is applied to learn the interactions among multiple law articles to predict prison terms. Experiment results indicate that our CLR-LJP model achieves the best performance compared to the state-of-the-art models, especially in the task of prison term prediction. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Design of the Smart Bedside Table Based on Single-Chip Microcomputer 12

Design of the Smart Bedside Table Based on Single-Chip Micro...

引用

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

作者： Shijia, Yang Weiqiang, Yang Xiehua, Yu Key Laboratory of Big Data and Artificial Intelligence University of Fujian Province MinNan Science and Technology University Quanzhou China

ISBN: (纸本)9798350310153

With the popularization of smart home, nightstand plays an increasingly important role in people's daily life. By means of questionnaire survey and data collection, it is found that most household nightstands only play the role of storage, the bedroom space is always not enough for all kinds of furniture, the nightstand cannot be interconnected with other smart devices. The existing smart nightstands on the market have common problems: uneven functions and low practicability. In view of the above problems, combined with the smart home system, this paper studies and designs a smart nightstand with HT66F2390 microcontroller as the core. To save the bedroom space, other furniture functions are integrated, such as adaptive adjustment of night light and brightness, refrigeration and fresh-keeping, heating and insulation, drawer fingerprint unlock, LED light group changing in different occasions. LCD displays the user interface for easy operation. The smart nightstand is set up to test the environment and optimize the functions of each module. The results show that the designed intelligent bedside table can integrate the functions of other furniture. It effectively saves bedroom space and optimizes living experience. The expected design goal has been achieved. © 2022 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

data Augmentation for Tensor Completion via Embedding Gradient Tracking 10

Data Augmentation for Tensor Completion via Embedding Gradie...

引用

10th IEEE International Conference on Cyber Security and Cloud Computing and 9th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Deng, Han Li, Yuhui Xie, Songyou Yang, Yang Liu, Yaqin Big Data Development and Research Center Guangzhou College of Technology and Business Guangzhou528138 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

ISBN: (纸本)9798350312461

How can we enhance the performance of neural tensor completion models for sparse data recovery? The task of tensor completion is crucial for network monitoring since it is the basis of network operation and management. Neural tensor completion models can exploit the multi-dimensional structure of tensors to recover missing entries in partially observed tensors. However, they can produce inaccurate estimations as real-world tensors are very sparse. These models tend to overfit a small amount of data, leading to limited accuracy on recovered data. In this paper, we propose LightTracker, a general data augmentation framework that enhances the prediction accuracy of neural tensor completion models. Specifically, LightTracker first trains a neural tensor completion model and tracks the gradient from the view of embeddings. After training, we use the tracked entity gradient to determine the importance of unknown tensor entries. Then, we aggregate the entries' importance to calculate the importance of each entity. Finally, LightTracker creates an augmented tensor by mixing observed data and predicted entries with the highest importance. Experiments conducted on two network traffic datasets show that LightTracker effectively enhanced the imputation accuracy of different tensor completion baselines, showing its generality and effectiveness. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep learning-based Real-time Migration Strategies for Containers in SDN 6

Efficient Deep learning-based Real-time Migration Strategies...

引用

6th International Conference on Next Generation data-Driven Networks, NGDN 2024

作者： Huang, Shan Liu, Yanan Li, Yanuo He, Feili Duan, Xiaodong School of Computer Science and Engineering Dalian Minzu University Dalian China Key Laboratory of Big Data Application Technology of the State Ethnic Affairs Commission Dalian China Dalian Ethnic Culture Digital Technology Key Laboratory Dalian China

ISBN: (纸本)9798350388374

Container technology is widely used and improve the efficiency of container real-time migration has become an important research topic. Existing studies mainly focus on optimizing iterative dumping of containers without fully considering the impact of migration node selection on migration efficiency. Software-defined networking (SDN), achieves centralized control of the network by separating the control plane and the forwarding plane. Applying deep learning to SDN makes tasks such as traffic prediction and network optimization more intelligent. This paper proposes Prediction Model based on CLCB (CNN-LSTM-CBAM) uses real-time collected load data as input, extracts feature components of load data using one-dimensional convolutional neural networks, and then predicts using LSTM. To improve prediction accuracy, a lightweight CBAM attention module is introduced, and the prediction results are output through fully connected layers. The Network Traffic Prediction Model based on GCGRU-Conv (GCN-GRU-CNN) considers both spatial and temporal features of network traffic. GCN and GRU are used to extract spatial and temporal features of network traffic, respectively, and then these features are fused together using convolutional neural networks. To address the gradient problem caused by increasing network depth, a residual network structure is introduced. Experimental results show that the method proposed can effectively reduce the container migration time and has better prediction results. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Speech Encryption in Linear Canonical Transform Domain Based on Chaotic Dynamic Modulation

引用

Journal of Beijing Institute of technology 2021年第3期30卷 295-304页

作者： Liyun Xu Tong Zhang Chao Wen Institute of Big Data Science and Industry School of Computer and Information TechnologyShanxi UniversityTaiyuan 030006China

In order to transmit the speech information safely in the channel,a new speech encryp-tion algorithm in linear canonical transform(LCT)domain based on dynamic modulation of chaot-ic system is *** algorithm first uses a chaotic system to obtain the number of sampling points of the grouped encrypted *** three chaotic systems are used to modulate the corres-ponding parameters of the LCT,and each group of transform parameters corresponds to a group of encrypted ***,each group of signals is transformed by LCT with different ***-nally,chaotic encryption is performed on the LCT domain spectrum of each group of signals,to realize the overall encryption of the speech *** experimental results show that the proposed algorithm is extremely sensitive to the keys and has a larger key *** with the original signal,the waveform and LCT domain spectrum of obtained encrypted signal are distributed more uniformly and have less correlation,which can realize the safe transmission of speech signals.

关键词： communication security linear canonical transform transform domain encryption chaotic system

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：