检索结果-内蒙古大学图书馆

From Laboratory to Field:Unsupervised Domain Adaptation for Plant Disease Recognition in the Wild

Plant Phenomics 2023年第2期5卷 195-208页

作者： Xinlu Wu Xijian Fan Peng Luo Sruti Das Choudhury Tardi Tjahjadi Chunhua Hu College of Information Science and Technology Nanjing Forestry UniversityNanjing 210037China Institute of Forest Resource Information Techniques Chinese Academy of ForestryBeijing 100091China Key Laboratory of Forestry Remote Sensing and Information System National Forestry and Grassland AdministrationBeijing 100091China Department of Computer Science and Engineering University of Nebraska-LincolnLincolnNE 68588USA School of Engineering University of WarwickCoventry CV47ALUK

Plant disease recognition is of vital importance to monitor plant development and predicting crop ***,due to data degradation caused by different conditions of image acquisition,e.g.,laboratory *** environment,machine learning-based recognition models generated within a specific dataset(source domain)tend to lose their validity when generalized to a novel dataset(target domain).To this end,domain adaptation methods can be leveraged for the recognition by learning invariant representations across *** this paper,we aim at addressing the issues of domain shift existing in plant disease recognition and propose a novel unsupervised domain adaptation method via uncertainty regularization,namely,Multi-Representation Subdomain Adaptation Network with Uncertainty Regularization for Cross-Species Plant Disease Classification(MSUN).Our simple but effective MSUN makes a breakthrough in plant disease recognition in the wild by using a large amount of unlabeled data and via nonadversarial ***,MSUN comprises multirepresentation,subdomain adaptation modules and auxiliary uncertainty *** multirepresentation module enables MSUN to learn the overall structure of features and also focus on capturing more details by using the multiple representations of the source *** effectively alleviates the problem of large interdomain *** adaptation is used to capture discriminative properties by addressing the issue of higher interclass similarity and lower intraclass ***,the auxiliary uncertainty regularization effectively suppresses the uncertainty problem due to domain *** was experimentally validated to achieve optimal results on the PlantDoc,Plant-Pathology,Corn-Leaf-Diseases,and Tomato-Leaf-Diseases datasets,with accuracies of 56.06%,72.31%,96.78%,and 50.58%,respectively,surpassing other state-of-the-art domain adaptation techniques considerably.

关键词： Plant breakthrough details

来源：评论

学校读者我要写书评

暂无评论

Modeling of the resilient supply chain system from a perspective of production design changes

引用

Frontiers of engineering Management 2023年第1期10卷 96-106页

作者： Shuangshuang ZHANG Hongfeng WANG Guo LI Junwei WANG College of Information Science and Engineering Northeastern UniversityShenyang 110819China School of Management and Economics Beijing Institute of TechnologyBeijing 100081China Department of Industrial and Manufacturing System Engineering The University of Hong KongHong KongChina

Building an effective resilient supply chain system (RSCS) is critical and necessary to reduce the risk of supply chain disruptions in unexpected scenarios such as COVID-19 pandemic and trade wars. To overcome the impact of insufficient raw material supply on the supply chain in mass disruption scenarios, this study proposes a novel RSCS considering product design changes (PDC). An RSCS domain model is first developed from the perspective of PDC based on a general conceptual framework, i.e., function-context-behavior-principle-state-structure (FCBPSS), which can portray complex systems under unpredictable situations. Specifically, the interaction among the structure, state and behavior of the infrastructure system and substance system is captured, and then a quantitative analysis of the change impact process is presented to evaluate the resilience of both the product and supply chain. Next, a case study is conducted to demonstrate the PDC strategy and to validate the feasibility and effectiveness of the RSCS domain model. The results show that the restructured RSCS based on the proposed strategy and model can remedy the huge losses caused by the unavailability of raw materials.

关键词： resilient supply chain supply chain disruption domain modeling product design changes

来源：评论

学校读者我要写书评

暂无评论

Empowering Deaf Children with Sinhala Sign Language, Emotion Detection, and Sound Recognition 5

Empowering Deaf Children with Sinhala Sign Language, Emotion...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Fernando, W.H.K. Perera, P.L.D.N. Fernando, M.I.N. Gunasekara, P.T.E.W. Fernando, Harinda De Zoysa, Rivoni Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

This study describes a broad endeavor to use cutting-edge technologies to empower deaf primary school students in Sri Lanka. Three key elements make up the study: a sound recognition and classification system, an Android software for translating gestures in Sinhala Sign Language (SSL), and a mobile app for emotion recognition and text-tospeech in Sinhala. By promptly alerting caregivers to potential dangers, the sound recognition technology secures the security of deaf children at home, providing an invaluable layer of security. The Android software bridges the communication gap and improves family interactions by translating SSL gestures captured by the device's camera into textual representations. This promotes successful communication between deaf children and their parents. Convolutional Neural Networks (CNNs) are used in the mobile application to detect and understand emotions based on facial expressions. This enables non-verbal youngsters to communicate successfully through Sinhala textto-speech output with adaptive tone modulation. This research aims to build a caring and inclusive atmosphere, enabling increased independence and enhanced communication skills in deaf children by combining these advances. The suggested solutions could significantly improve the lives of deaf kids, providing them with opportunities for better learning, social interaction, and emotional health. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An action plan for the agri-food sector at the time of the climate and biodiversity crises

引用

National science Review 2023年第7期10卷 16-18页

作者： Francesco Cherubini Ting Hua Wenwu Zhao Industrial Ecology Programme Department of Energy and Process Engineering Norwegian University of Science and Technology (NTNU) State Key Laboratory of Earth Surface Processes and Resource Ecology Faculty of Geographical Science Beijing Normal University Institute of Land Surface System and Sustainable Development Faculty of Geographical Science Beijing Normal University

Land areas on our planet are facing unprecedented levels of *** than70%of the global ice-free land has been affected by human activities,30%of the land is threatened by degradation,biodiversity and other ecosystem services(ESs) are declining,and climate change is altering ecosystem functioning [1].Currently,agriculture is the dominant form of land use,with grazing land comprising27%and cropland 12%(and more than half of the cropland is used to produce animal feed).Agriculture is responsible for about one-third of global greenhouse gas(GHG) emissions [2] and it is the primary driver of deforestation,habitat destruction,global freshwater withdrawals,and global ocean and freshwater pollution [3].As land is a limited resource,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video key concept extraction using Convolution Neural Network 3

Video key concept extraction using Convolution Neural Networ...

引用

3rd IEEE International Conference on AI in Cybersecurity, ICAIC 2024

作者： Sardar, Tanvir H Amin Hazarika, Ruhul Pandey, Bishwajeet Guru Prasad, M.S. Mahmudul Hassan, Sk Dodmane, Radhakrishna Gohel, Hardik Dept. of Computer Science & Engg Bengaluru India Manipal Institute of Technology Department of Information Technology Bengaluru India Astana It University Department of Intelligent System and Cyber Security Kazakhstan Dept. of Computer Science & Engg. Dehradun India VIT-AP School of Computer Science and Engineering India Nmam Institute of Technology Department of Computer Science & Engg. Nitte India University of Houston Department of Cse Victoria United States

ISBN: (纸本)9798350381856

Objectives: This work aims to develop an automated video summarising methodology and timestamping that uses natural language processing (NLP) tools to extract significant video ***: The methodology comprises extracting the audio from the video, splitting it into chunks by the size of the pauses, and transcribing the audio using Google's speech recognition. The transcribed text is tokenised to create a summary, sentence and word frequencies are calculated, and the most relevant sentences are selected. The summary quality is assessed using ROUGE criteria, and the most important keywords are extracted from the transcript using ***: Our proposed method successfully extracts key points from video lectures and creates text summaries. Timestamping these key points provides valuable context and facilitates navigation within the lecture. Our method combines video-to-text conversion and text summarisation with timestamping key concepts, offering a novel approach to video lecture analysis. Existing video analysis methods focus on keyword extraction or summarisation, while our method offers a more comprehensive approach. Our timestamped key points provide a unique feature compared to other methods. Our method enhances existing video reports by (i) providing concise summaries of key concepts and (ii) enabling quick access to specific information through timestamps. (iii) Facilitating information retrieval through a searchable index. Further research directions: (i) Improve the accuracy of the multi-stage processing pipeline. (ii) Develop techniques to handle diverse accents and pronunciations. (iii) Explore applications of the proposed method to other video genres and ***/Improvements: This approach is practical in giving accurate video summaries, saving viewers time and effort when comprehending the main concepts presented in a video. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A four-dimensional model for the information storage/output of life

引用

Nano Research 2023年第2期16卷 2630-2634页

作者： Bo Song Lei Jiang Key Laboratory of Optical Technology and Instrument for Medicine Ministry of EducationShanghai Key Lab of Modern Optical SystemSchool of Optical-Electrical Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Key Laboratory of Bio-inspired Materials and Interfacial Science Technical Institute of Physics and ChemistryChinese Academy of SciencesBeijing 100190China School of Future Technology University of Chinese Academy of SciencesBeijing 100049China

A large amount of progress has achieved in neuroscience,however,there is still a lack of reasonable model for the storage/output(S/O)of life *** cyclical motion of cardio-and pulmonary-myocyte is a typical process of the life information S/O,while the opening and closing sites of Ca^(2+)ion channels during the motion can form a genetically programmed time-dependent three-dimensional(3D)*** phenomena indicate a strong correlation of the information S/O model of these myocytes with the time-sequence 3D ***,based on the time-dependent Ca^(2+)fluorescence imaging during the motion of cardio-and pulmonary-myocyte,here we suggest a four-dimensional(4D)code of information S/O model in cell and nervous *** from the fact of pulmonary myocyte motion able to be controlled by brain,it is deduced that the 4D code in brain has a role of controlling muscles through a pathway of the central nervous system,peripheral nervous system,neuromuscular junction,and muscle *** addition,we also suggested the 4D code of non-innate skill that can be programmed by the learning/training of a long time(~3 years),such as walking,writing,painting,sports,speech,singing,and ***,this 4D S/O model is reasonable for the ultralow energy consumption of life information transmission.

关键词： four-dimensional(4D)storage/output model life information cell nervous system

来源：评论

学校读者我要写书评

暂无评论

A Multi-mode Low Energy Consumption system Control and Reliability Evaluation Method

A Multi-mode Low Energy Consumption System Control and Relia...

引用

2023 International Conference on Smart Electrical Grid and Renewable Energy, SEGRE 2023

作者： Zhang, Ying Zhao, Yifei Lv, Zhanggang Wang, Shihui Yang, Bo Beijing Institute of Aerospace Automatic Controls System Engineering Research Department Beijing China Beijing Institute of Aerospace Automatic Controls Committee on Science and Technology Beijing China Beijing Institute of Precision Mechatronics and Controls Beijing China

ISBN: (纸本)9798350323269

The multi-mode low energy consumption system control and reliability evaluation method proposed in this paper has the novelty by implementing multi-mode control and operation status monitoring. Man-machine interaction mode switch, and real-time display of the controlled object, program-controlled power supply, can control the internal power supply of each part of the output state, system power consumption, system reliability, the realization of the system under the multi-mode real-time operating state monitoring. The health status of the low energy consumption system can be divided into five states: healthy state, mildly degraded state, moderately degraded state, severely degraded state, and fault state, which characterized the health status of the system operation. By quantifying the health status of low-power multi-mode systems, a fine-grained health assessment of voltage parameters between 21.50 and 23.00 volts is achieved through collecting the observable state quantity of the low energy consumption system, with wavelet packet transformation, and the HMM prediction model. The multi-mode energy consumption control method and reliability estimation strategy proposed in this paper , which has the simulation results with 22.20~22.50 V as normal status and wider 22.05~22.75 V as fault status,have important application significance for reducing system power consumption, evaluating system health status, timely carrying out health maintenance, and extending system service life. © 2023 IEEE.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Process Industry system Modeling Based on Time Series Imputation: A Case Study of Paste Thickener

Process Industry System Modeling Based on Time Series Imputa...

引用

2024 International Conference on Automation in Manufacturing, Transportation and Logistics, ICaMaL 2024

作者： Li, Xiaorui Ban, Xiaojuan Shao, Yizhou Chen, Haowei Yao, Chao Yuan, Zhaolin Liu, Guangsheng Guo, Lijie Institute of Artificial Intelligence University of Science and Technology Beijing Beijing China School of Artificial Intelligence Hebei University of Technology Beijing China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Hong Kong Polytechnic University Department of Industrial and Systems Engineering Hong Kong Hong Kong BGRIMM Technology Group Beijing China

ISBN: (纸本)9798350378658

In process CPS systems, highly accurate modeling of the production system is essential for optimal control, fault diagnosis, and flexible manufacturing. Traditional data-driven modeling of industrial processes focuses on predicting future trends based on variable periodicity and trends, often neglecting the impact of control variables. This paper proposes a new approach to improve CPS accuracy, particularly for systems heavily influenced by controlled variables. Firstly, CPS modeling is redefined as a time series imputation problem, introducing exogenous variables via a sequence modeling algorithm based on a state space model to enhance forecasting accuracy. Secondly, sequence inputs are encoded in patches, improving the model's ability to process local sequence information. The proposed method is evaluated on a real deep cone thickener underflow concentration forecasting task and compared with state-of-The-Art time series forecasting methods, demonstrating superior performance. This study not only provides a more accurate model for CPS but also offers a framework for integrating control variables into predictive modeling. © 2024 IEEE.

关键词： Flexible manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

引用

IEEE Transactions on Circuits and systems for Video technology 2025年第6期35卷 5445-5460页

作者： Lin, Hui Li, Nan Yao, Pengjuan Dong, Kexin Guo, Yuhan Hong, Danfeng Zhang, Ying Wen, Congcong China Academy of Electronics and Information Technology Beijing100846 China China Meteorological Administration National Satellite Meteorological Center Innovation Center for FengYun Meteorological Satellite Beijing100081 China Tsinghua University State Key Laboratory of Hydroscience and Engineering Department of Hydraulic Engineering Beijing100084 China Chinese Academy of Sciences Aerospace Information Research Institute Beijing100094 China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China University of Science and Technology Beijing School of Automation and Electrical Engineering Beijing100083 China New York University Abu Dhabi Department of Electrical and Computer Engineering Abu Dhabi United Arab Emirates University of Science and Technology of China Anhui China

Object detection is a fundamental task in computer vision that involves accurately locating and classifying objects within images or video frames. In remote sensing, this task is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate more advanced approaches for effective object detection in such environments. While deep learning methods have achieved remarkable success in remote sensing object detection, they typically rely on large amounts of labeled data. Acquiring sufficient labeled data, particularly for novel or rare objects, is both challenging and time-consuming in remote sensing scenarios, limiting the generalization capabilities of existing models. To address these challenges, few-shot learning (FSL) has emerged as a promising approach, aiming to enable models to learn new classes from limited labeled examples. Building on this concept, few-shot object detection (FSOD) specifically targets object detection challenges in data-limited conditions. However, the generalization capability of FSOD models, particularly in remote sensing, is often constrained by the complex and diverse characteristics of the objects present in such environments. In this paper, we propose the Generalization-Enhanced Few-Shot Object Detection (GE-FSOD) model to improve the generalization capability in remote sensing FSOD tasks. Our model introduces three key innovations: the Cross-Level Fusion Pyramid Attention Network (CFPAN) for enhanced multi-scale feature representation, the Multi-Stage Refinement Region Proposal Network (MRRPN) for more accurate region proposals, and the Generalized Classification Loss (GCL) for improved classification performance in few-shot scenarios. GE-FSOD demonstrates superior robustness and accuracy in remote sensing FSOD tasks through these enhancements. Extensive experiments on the DIOR and NWPU VHR-10 datasets show that our

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Research on Target Encirclement Strategy of Amphibious Spherical Robots in 3D Underwater Environments 20

Research on Target Encirclement Strategy of Amphibious Spher...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Yang, Dan Shi, Liwei Guo, Shuxiang Feng, Shilong Beijing Institute of Technology School of Medical Technology Beijing100081 China Beijing Institute of Technology School of Life Science Beijing100081 China Key Laboratory of Convergence Medical Engineering System and Healthcare Technology Beijing Institute of Technology Ministry of Industry and Information Technology Beijing100081 China Southern University of Science and Technology The Department of Electronic and Electrical Engineering Guangdong Shenzhen518055 China

ISBN: (纸本)9798350320831

The cooperative trapping of multiple amphibious robots in a 3D underwater environment is a comprehensive research topic that mainly includes the generation of dynamic alliances for trapping and path planning. To address this problem, this paper first proposes a 'trap point occupancy strategy' to realize the generation of dynamic alliances among multiple robots during the trapping process. Secondly, based on this, an improved gray wolf algorithm is proposed in this paper to implement robot target guidance and adaptive obstacle avoidance functions, used for the path planning of the robot's arrival at the trapping point during the trapping process, thus completing the entire trapping task. Then, this paper conducts simulation experiments in a 3D underwater environment with static obstacles, and the results confirm that the proposed cooperative trapping algorithm has high efficiency and robustness. Finally, the innovations and all the work in the article are summarized, and prospects are put forward. © 2023 IEEE.

关键词： Motion planning

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：