检索结果-内蒙古大学图书馆

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Li, Jinyang Tong, Jiahui Gao, Guangyu Xu, Wenbin School of Computer Science and Technology Beijing Institute of Technology China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Optical Radiation Laboratory Beijing Institute of Environmental Characteristics Beijing100854 China

ISBN: (纸本)9781450398572

Traditional deep learning models firmly rely on a large amount of labeled data during pre-training. Whereas it lacks generalization in the face of unfamiliar categories. Recently, few-shot learning is a hot topic in computer vision to classify unseen classes with limited labels. A representative approach is to extract features from the support and query sets, respectively, and compare similarities via metric learning. However, convolutional neural networks often focus only on a local region and ignore the global region, which severely reduces the accuracy of the matching. Specifically, in this paper, we pile lightweight attention-based blocks in the embedding module, which combines an adaptive kernel size 2D convolutional network with a cross-channel attention mechanism to encode multi-scale features and implicitly increase the receptive field. The SE-relation module chooses to construct learnable non-linear comparators to compare the relationship utilizing channel information. Finally, we show experimental results on standard few-shot testing benchmarks such as mini-ImageNet and tiered-ImageNet to demonstrate effectiveness. © 2023 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Development of a Dempster-Shafer Model for Diagnosing Mental Health Disorders on Social Media 7

Development of a Dempster-Shafer Model for Diagnosing Mental...

引用

7th International Seminar on Research of Information Technology and Intelligent systems, ISRITI 2024

作者： Nasyuha, Ayahri Hadi Hadi Ilyas, Ananda Andriyani, Widyastuti Subagyo, Aloysius Agus Universitas Teknologi Digital Indonesia Faculty of Information Technology Dept. of Information System Yogyakarta Indonesia Universitas Dharmawangsa Faculty Of Engineering And Computer Science Dept. of Information System Medan Indonesia Universitas Teknologi Digital Indonesia Faculty of Information Technology Dept. of Master of Information Technology Yogyakarta Indonesia Universitas Teknologi Digital Indonesia Faculty of Information Technology Dept. of Accounting Information System Yogyakarta Indonesia

ISBN: (纸本)9798331519643

The rapid proliferation of social media has been paralleled by an increase in mental health concerns, often reflected in users' online behaviors and text posts. Traditional methods for diagnosing mental health disorders do not effectively leverage this vast amount of data, nor do they address the ambiguities and uncertainties inherent in natural language processing of social media content. A novel diagnostic model based on the Dempster-Shafer evidence theory is developed specifically for analyzing social media text. The model aims to enhance the precision of mental health disorder diagnoses by incorporating probabilistic reasoning and handling uncertainty in the data more effectively than traditional binary classification methods. It integrates linguistic cues, sentiment analysis, and behavioral indicators extracted from user posts to assess the likelihood of various mental health conditions. We collected a dataset comprising social media posts tagged with mental health keywords, verified by clinical annotations. The Dempster-Shafer model was trained with features derived from text analytics, including sentiment scores, thematic elements, and engagement metrics. The model's performance was evaluated against standard classification models through metrics such as accuracy, sensitivity, and specificity. The Dempster-Shafer model demonstrated superior capability in handling the uncertainty and imprecision of social media data, showing an improvement in diagnostic accuracy by 15% over traditional models. The findings suggest that applying Dempster-Shafer theory in mental health diagnostics can effectively utilize the nuanced and sparse data available on social media, offering a promising tool for early identification and intervention in mental health issues. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

The Innovation Development of Data Prediction and Clustered Compressive Sensing (CCS) in Environmental Application

The Innovation Development of Data Prediction and Clustered ...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Sonia Kukreja Garima Jain Department of Computer Science and Engineering Galgotias University Greater Noida India Department of Computer Science and Business System Noida Institute of Engineering and Technology Greater Noida India

Data prediction in environmental applications is a quickly evolving field that provides tremendous potential for improving environmental management and decision-making. By leveraging the power of data, predictive models can be developed to identify potential environmental risks, mitigate the impacts of climate change, and improve the efficiency of environmental management. Data prediction in environmental applications can be used to better understand the relationships between environmental phenomena and the environment. For instance, predictive models can be used to identify areas that are more likely to experience extreme weather events and inform the development of strategies for responding to such events. Predictive models can also be used to analyze the effects of changing climate on ecosystems and help inform decisions regarding the management of natural resources. Data prediction in environmental applications can also be used to develop more effective management strategies. Predictive models can be used to determine which areas are more likely to experience water scarcity or air pollution, and which areas are more likely to benefit from certain conservation practices. By leveraging data, predictive models can also help predict how certain management practices will affect the environment and inform decision-makers on how to best allocate resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Information Retrieval with a Language Model

Enhancing Medical Information Retrieval with a Language Mode...

引用

Cognitive Robotics and Intelligent systems (ICC - ROBINS), International Conference on

作者： Yuvaraj Natarajan Sri Preethaa K.R Sasikumar Pandian Shruti Umapathi Geetha Sujadharshini Senthilkumar Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore Department of Robot and Smart System Engineering Kyungpook National University Daegu Republic of Korea

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

In this ever-evolving healthcare landscape, with the integration of cutting-edge technology, this study has exemplified a medical chatbot by harnessing the advanced Llama2 model. This chatbot places significant emphasis on instance training by changing and adding the meta, which enables it to continuously adapt and stay updated with the latest medical developments. Its adaptability also encompasses capabilities such as question-answering and mining knowledge from an extensive meta dataset. By leveraging its extensive ability to learn medical terminology, the chatbot provides precise and real-time responses to medical inquiries by establishing itself as a reliable information source. Access to a specially collected meta dataset further enhances its ability to deliver comprehensive medical insights while self-supervised learning techniques enhance the model efficacy. Consequently, this chatbot reshapes the way individuals access precise medical information by enabling a new era of advanced digital healthcare assistants in the digital age.

关键词： Training Adaptation models Terminology Self-supervised learning Chatbots Information age Real-time systems

来源：评论

学校读者我要写书评

暂无评论

K-means Clustering Powered Context Aware Food Recommender system

K-means Clustering Powered Context Aware Food Recommender Sy...

引用

2023 International Conference on Integrated Intelligence and Communication systems, ICIICS 2023

作者： Panwar, Minakshi Sharma, Ashish Mahela, Om Prakash Khan, Baseem Maulana Azad University Jodhpur Department of Computer Science Rajasthan India Rajasthan Rajya Vidyut Prasaran Nigam Ltd Power System Planning Division Jaipur India Hawassa University Department of Electrical Engineering Ethiopia

ISBN: (纸本)9798350315455

This paper designed a K-means clustering powered context aware food recommender system (CAFRS). The CAFRS is based on dividing the food data sets into clusters to minimize the error between the user input and available data by computing the distance between the cluster centroid and available food data in the data set of CAFRS. Recommended food has the minimum distance from the K-means clustering (KMC) centroid. Root mean square error (RMSE) and mean absolute error (MAE) are computed to evaluate requirement of the repeat orders to meet energy demand of the user. Proposed CAFRS is effective to recommend a suitable recipe for the user and RMSE and MAE are effective to estimate the requirement of repeat order. Performance of the proposed CAFRS is superior compared to a rule based food recommender system (RBFRS). This study is performed in MATLAB environment. © 2023 IEEE.

关键词： Context aware food recommender system Food preference K-means clustering Mean absolute error Root mean square error

来源：评论

学校读者我要写书评

暂无评论

Multimodal Remote Sensing Image Registration Based on Local Phase Congruency and Keypoint Filtering

Multimodal Remote Sensing Image Registration Based on Local ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Ma, Tao Huang, Weijian Du, Linlin Wang, Chun Ge, Shuangquan Liu, Yunfei Yu, Kun China Academy of Engineering Physics Institute of Computer Application Mianyang China Naval University of Engineering National Key Laboratory of Science and Technology on Vessel Integrated Power System Wuhan China

ISBN: (纸本)9781665465335

Robust registration is able to register the complementary information captured by multimodal images. Owning to the nonlinear intensity differences and repeating patterns in multimodal images, many classic descriptors are unable to achieve good performance. Aiming at this problem, a remote sensing image registration method based on key point description and filtering is proposed. First, this work utilizes a new keypoint descriptor with Log-Gabor filters to characterize the oriented phase congruency information in multimodal images. Then, a keypoint filtering is performed on all descriptors by mean-shift clustering to remove the repeating patterns. This approach is evaluated on three commonly used data sets, which are used for structure map construction and image registration comparisons. The experimental results show that the proposed method is able to preserve highly similar structure features and remove most repeating keypoints in multimodal images, which indicates this method is efficient and can achieve good registration performance. © 2022 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

A study of the Architecture Design of digital software for Transportation Infrastructure 7

A study of the Architecture Design of digital software for T...

引用

7th IEEE International Conference on Transportation Information and Safety, ICTIS 2023

作者： Zou, Xinxin Chen, Xianqiao Gao, Song Zhou, ZhongLiang Wu, Chaozhong Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan China Wuhan University of Technology National Engineering Research Center for Water Transport Safety Intelligent Transport System Research Center Wuhan China

ISBN: (纸本)9798350308532

The digital software of transportation infrastructure is the foundation of digital transportation. With the development of information technology, its software technology architecture is also evolving iteratively. Based on the status quo in the field of transportation infrastructure engineering, the core basic capabilities of the software are determined, including data aggregation and storage, data analysis and processing, engineering data delivery, engineering visualization, system integration expansion, application customization development, etc. The characteristics of the existing software architecture are studied, and the logical architecture of the transport infrastructure data software system is designed, including operation support layer, convergence storage layer, data service layer, and application service layer. In addition, the technical reference architecture and operation architecture of digital software for transport infrastructure are emphatically introduced, and the development trend of digital software architecture for transport infrastructure has been prospected. © 2023 IEEE.

关键词： Software architecture

来源：评论

学校读者我要写书评

暂无评论

Overview of Data Management Technology for Transportation Infrastructure based on BIM 7

Overview of Data Management Technology for Transportation In...

引用

7th IEEE International Conference on Transportation Information and Safety, ICTIS 2023

作者： Zhou, ZhongLiang Chen, Xianqiao Gao, Song Zou, Xinxin Wu, Chaozhong Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan China Wuhan University of Technology National Engineering Research Center for Water Transport Safety Intelligent Transport System Research Center Wuhan China

ISBN: (纸本)9798350308532

The application of BIM (Building Information Modeling) technology in the field of transportation infrastructure digitization is the current development trend. However, the practical implementation of BIM in transportation infrastructure faces challenges such as inconsistent data standards, low information transfer efficiency, and fragmented information across different life cycles. This paper summarizes the current status and hot spots of BIM data management research through an in-depth literature review, analyzes the problems and shortcomings of existing different forms of BIM data management technology, and a prospect for its future development was proposed in the discussion. The study shows that the file-based BIM data management solutions can hardly meet the BIM data access requests of today's transportation infrastructure conveniently, securely, and efficiently, and the management solutions based on a single type of database can hardly have good performance while compatible with BIM data of multiple structures due to the heterogeneity of data sources. Therefore, future BIM data management must be based on unified data standards (such as Industry Foundation Classes), combined with NewSql-related technologies to achieve high-performance and highly scalable BIM data management to share and exchange data more conveniently and efficiently. © 2023 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic with Deep Learning Enabled Biomedical Bone Age Assessment and Classification Model

引用

computers, Materials & Continua 2022年第12期73卷 5473-5489页

作者： Mesfer Al Duhayyim Areej A.Malibari Marwa Obayya Mohamed K.Nour Ahmed S.Salama Mohamed I.Eldesouki Abu Sarwar Zamani Mohammed Rizwanullah Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Electrical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The skeletal bone age assessment(BAA)was extremely implemented in development prediction and auxiliary analysis of medicinal issues.X-ray images of hands were detected from the estimation of bone age,whereas the ossification centers of epiphysis and carpal bones are important *** typical skeletal BAA approaches remove these regions for predicting the bone age,however,few of them attain suitable efficacy or *** BAA techniques with deep learning(DL)methods are reached the leading efficiency on manual and typical ***,this study introduces an intellectual skeletal bone age assessment and classification with the use of metaheuristic with deep learning(ISBAAC-MDL)*** presented ISBAAC-MDL technique majorly focuses on the identification of bone age prediction and classification *** attain this,the presented ISBAAC-MDL model derives a mask Region-related Convolutional Neural Network(Mask-RCNN)with MobileNet as baseline model to extract *** by,the whale optimization algorithm(WOA)is implemented for hyperparameter tuning of the MobileNet *** last,Deep Feed-Forward Module(DFFM)based age prediction and Radial Basis Function Neural Network(RBFNN)based stage classification approach is *** experimental evaluation of the ISBAAC-MDL model is tested using benchmark dataset and the outcomes are assessed over distinct *** experimental outcomes reported the better performances of the ISBAACMDL model over recent approaches with maximum accuracy of 0.9920.

关键词： Biomedical images bone age assessment age prediction computer vision deep learning image classification

来源：评论

学校读者我要写书评

暂无评论

Blockchain Enabled Intelligent Digital Forensics system for Autonomous Connected Vehicles

Blockchain Enabled Intelligent Digital Forensics System for ...

引用

2022 International Conference on Communication, Computing and Internet of Things, IC3IoT 2022

作者： Tyagi, Ranu Sharma, Sachin Mohan, Seshadri Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun India University of Arkansas at Little Rock System Engineering Department Little RockAR United States

ISBN: (纸本)9781665479950

Autonomous connected vehicles are revolutionizing the automotive industry vision and impacting their business model. This trend will likely impact other related industries and their business model such as automotive insurance companies, tier-II automotive manufactures, and automotive maintenance service companies. The growing number of connected vehicles will require new policy formulation by the government about privacy and security issues in the era of massive digitalization and automation. Organizations such as 3GPP and IEEE are evolving standards that address security issues for connected vehicles. However, since Artificial Intelligence (AI) and Machine Learning (ML) will play a significant role in 5G networks and beyond, we address the privacy and security issues with a blockchain-based intelligent digital forensics system for autonomous connected vehicles (ACVs) in a connected smart world incorporating artificial intelligence. The proposed system includes a novel algorithm for the autonomous connected vehicles and the users' security and privacy. We utilize short randomizable signatures to anonymously authenticate witness's identities and to protect the witnesses' privacy. Then, we leverage fine-grained access control based on ciphertext-policy attribute-based encryption for evidence access and evaluate the feasibility of the proposed system by simulating the proposed model, its computational costs and communication overhead by implementing a prototype on a local Ethereum blockchain network platform. The simulation results show the proof-of-concept of the proposed system. We envision the application of the proposed system to ensure security and privacy of ACVs and their security applications for use with 5G-V2X and future XG-V2X networks. © 2022 IEEE.

关键词： Blockchain

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：