检索结果-内蒙古大学图书馆

9th International Conference on Cyber Security and Information Engineering, ICCSIE 2024

作者： Wu, Jing Guo, Zhenxin Wang, Zhicheng Zhang, Haotian Kang, Xaolin Ma, Xiaoguang Department of Computer and Information Science Qinghai Institute of Technology China Foshan Graduate School Northeastern University China School of Computer Science and Application Qinghai University China

ISBN: (纸本)9798400718137

The application of big data technology has brought new impetus and possibilities to the development of tourism. The design of an embedded Q&A robot system for Qinghai tourism customer service based on ChatGPT system aims to provide an intelligent customer service solution to help users obtain information about Qinghai tourism and answer questions. The system uses ChatGPT as the core dialogue model, combines the knowledge and data in the field of Qinghai tourism, and realizes the intelligent answer to user questions. This study application in the field of natural language processing, and analyzes the design requirements and implementation scheme of embedded travel question answering system in detail. The function module includes user login and registration, travel tickets, hotel information query, scenic spot ticket price query and other essential basic function modules of the tourism website. Whether the design is reasonable or not will also directly affect the user experience. The results show that ChatGPT embedded in Qinghai tourism Q&A system can not only provide more intelligent and accurate answers, but also enhance the interactivity and practicability of the system, and provide users with more convenient and personalized tourism information services. © 2024 Copyright held by the owner/author(s).

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Vibration-induced bias error reduction using loop gain compensation for high-precision fiber optic gyroscopes

引用

Journal of Systems Engineering and Electronics 2025年第1期36卷 224-232页

作者： CHEN Heyu QIN Xuexin XIE Huan KONG Linghai ZHENG Yue School of Instrumentation Science and Opto-Electronics Engineering Beihang UniversityBeijing 100191China Beijing Institute of Computer Technology and Application Beijing 100854China Hunan Shuaiwei Control Technology Co. LTDChangsha 421000China Beijing Institute of Control and Electronic Technology Beijing 100038China

Vibration-induced bias deviation,which is generated by intensity fluctuations and additional phase differences,is one of the vital errors for fiber optic gyroscopes(FOGs)operating in vibration environment and has severely restricted the applications of high-precision *** conventional methods for suppressing vibration-induced errors mostly concentrate on reinforcing the mechanical structure and optical path as well as the compensation under some specific operation parameters,which have very limited effects for high-precision FOGs maintaining performances under *** this work,a technique of suppressing the vibration-induced bias deviation through removing the part related to the varying gain from the rotation-rate output is put ***,the loop gain is extracted out by adding a gain-monitoring *** demodulating the loop gain and the rotation rate simultaneously under distinct frequencies and investigating their quantitative relationship,the vibrationinduced bias error is compensated without limiting the operating parameters or environments,like the applied modulation *** experimental results show that the proposed method has achieved the reduction of bias error from about 0.149°/h to0.014°/h during the random vibration with frequencies from20 Hz to 2000 *** technique provides a feasible route for enhancing the performances of high-precision FOGs heading towards high environmental adaptability.

关键词： vibration-induced error fiber optic gyroscope(FOG) loop gain

来源：评论

学校读者我要写书评

暂无评论

A Livestock Recognition and Detection Algorithm based on Improved YOLOv5s

A Livestock Recognition and Detection Algorithm based on Imp...

引用

International Conference on computer Vision, Robotics, and Automation Engineering, CRAE 2024

作者： Niu, Jiajun Li, Chunmei Fang, Chengwu College of Computer Technology and Applications Qinghai University Xining810016 China Intelligent Computing and Application Laboratory of Qinghai Province China

ISBN: (纸本)9781510682283

As the largest natural reserve in China, the Three-River-Source Region possesses abundant grassland resources. However, in recent years, the grasslands in this area have been facing severe degradation issues. Overgrazing by livestock, mainly cattle and sheep, who are the primary livestock of the local herdsmen, has led to excessive grassland depletion. Addressing this phenomenon, this paper aims to provide technical support for grassland workers to explore the relationship between livestock grazing and grassland degradation by accurately identifying the number of cattle and sheep. This will enable the formulation of more effective grazing management strategies. This study involved field data collection and manual annotation to construct a dataset comprising 10,000 images of cattle and sheep. Building upon the original YOLOv5 model, optimizations were made by integrating compression techniques and the Squeeze-and-Excitation (SE) module, as well as enhancing the small object detection stage. Following these optimizations, the model achieved performance improvements of 1.2% in precision, 4.03% in recall, and 3.6% in mAP0.5 (mean average precision at an IoU threshold of 0.5) compared to the original model. These enhancements provide efficient and accurate technical means for livestock counting in the Three-River-Source Region. © 2024 SPIE.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

Lifestyle Classification Amidst Psychological Impact of COVID: A Machine Learning Approach 7

Lifestyle Classification Amidst Psychological Impact of COVI...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Agrawal, Alok Kumar Ahmed, Bilal Jakhar, Yogesh Kumar Bajaj, Karan Kumar, Girish Kumar, Mukesh Chitkara University School of Engineering & Technology Chitkara University Himachal Pradesh India School of Computer Application Lovely Professional University India University of Engineering & Management Department of Computer Application Jaipur India

ISBN: (纸本)9798350340600

The COVID pandemic has caused significant social changes, affecting not just physical health but also individuals' psychological well-being. This study investigates the complex interaction between lifestyle choices and the psychological impact of the pandemic, using a Machine Learning (ML) technique to categorise and assess distinct lifestyle patterns in the context of COVID. In this study, a significant data from a variety of sources, including questionnaires, social media, and healthcare records, to get insight into how the pandemic has affected lifestyle characteristics such as exercise, food, social connections, work habits, and leisure activities. This study has analysed the psychological effects of these lifestyle changes, including stress, anxiety, sadness, and overall mental health. This research article implements the basic classification models like (Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbors, and XGBoost), which can classify various lifestyle changes among individuals based on their pandemic-related behaviours. The impact of these lifestyle changes on mental health outcomes is investigated, offering light on the intricate interplay between personal decisions and psychological well-being during times of crisis. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

African Bison Optimization Algorithm:A New Bio-Inspired Optimizer with Engineering applications

引用

computers, Materials & Continua 2024年第10期81卷 603-623页

作者： Jian Zhao Kang Wang Jiacun Wang Xiwang Guo Liang Qi School of Science University of Science and Technology LiaoningAnshan114051China Team of Artificial Intelligence Theory and Application University of Science and Technology LiaoningAnshan114051China Department of Computer Science and Software Engineering Monmouth UniversityWest Long BranchNJ 07764USA Information and Control Engineering College Liaoning Petrochemical UniversityFushun113000China Department of Computer Science and Technology Shandong University of Science and TechnologyQingdao266590China

This paper introduces the African Bison Optimization(ABO)algorithm,which is based on biological *** is inspired by the survival behaviors of the African bison,including foraging,bathing,jousting,mating,and *** foraging behavior prompts the bison to seek a richer food source for *** bison find a food source,they stick around for a while by bathing *** jousting behavior makes bison stand out in the population,then the winner gets the chance to produce offspring in the mating *** eliminating behavior causes the old or injured bison to be weeded out from the herd,thus maintaining the excellent *** above behaviors are translated into ABO by mathematical *** assess the reliability and performance of ABO,it is evaluated on a diverse set of 23 benchmark functions and applied to solve five practical engineering problems with *** findings from the simulation demonstrate that ABO exhibits superior and more competitive performance by effectively managing the trade-off between exploration and exploitation when compared with the other nine popular metaheuristics algorithms.

关键词： Optimization metaheuristics African bison optimization engineering problems

来源：评论

学校读者我要写书评

暂无评论

Electroencephalography (EEG) Based Prediction of Learning and Responsiveness among Students 7

Electroencephalography (EEG) Based Prediction of Learning an...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

ISBN: (纸本)9798350340600

The constructivist method of teaching has been shown to have a major influence on the learning outcomes of students. In order to improve classroom instruction, it is essential to evaluate students' levels of involvement and attentiveness while they are being taught. Electroencephalography (EEG) can now be used to assess students' attentiveness in real time thanks to recent neuro-engineering breakthroughs and mobile brainwave sensors' availability. The purpose of this study is to provide an overview of EEG-based techniques with the intention of predicting constructivism and engagement among students of varying levels. The purpose of this study is to evaluate the efficacy of these approaches and to determine the extent to which they have the potential to enhance the design of future learning systems. This survey analyzes whether or not approaches based on EEG may be used to determine the level of constructivism and involvement displayed by pupils. The findings provide helpful insights that can be used to develop tailored teaching strategies and improve education's overall efficiency. However, some obstacles need to be overcome in order for EEG-based predictions to be accurate. Some of these obstacles include data quality and variability, individual differences, interpretability, generalization, and ethical considerations. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Identification of Pneumonia: A CNN Approach 2

Deep Learning Techniques for Identification of Pneumonia: A ...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Das, Ruchika Nayak, Debasish Swapnesh Kumar Rout, Chinmayee Priyadarshini Jena, Lambodar Swarnkar, Tripti Siksha 'o' Anusandhan University Department of Computer Science and Engineering Bhubaneswar India Nalanda Institute of Technology Department of Computer Application Bhubaneswar India Siksha 'O Anusandhan University Department of Data Science Bhubaneswar India Siksha 'o' Anusandhan University Department of Computer Application Bhubaneswar India

ISBN: (纸本)9798350370188

Pneumonia is an inflammatory lung disease that mostly affects the tiny air sacs known as alveoli in human bodies. Pneumonia may be caused by bacteria, viruses, or fungi. Mild to severe symptoms may include a mucus-producing cough and a fever, appals, and difficulty to breath. The approach most usually used to diagnose pneumonia is chest X-ray (CXR) imaging. Images from a CXR screening can be used as an alternative or confirmation method because they are simple and affordable to acquire. Examining the chest X-rays however is a hard task that might be vulnerable to subjective variation. We used a deep learning technique in this investigation. Convolutional neural networks (CNNs) for deep learning were employed in this paper. In his work, the proposed model is applied to the original CXR image dataset and the augmented image dataset. We generated the augmented images from the existing CXR image dataset and deployed VGG-19, a component of the CNN model to create an autonomous Pneumonia detection system. The suggested techniques that have been employed include scaling the image, adding extra information, deep learning using Keras, batch normalization, and finally using weights from the pre-trained Keras model (VGG19). Finding pneumonia sickness is difficult and takes time. In this study, we address the issue and demonstrate how to detect pneumonia disease more quickly and accurately. Our proposed model shows an accuracy of 95% on the augmented CXR image dataset. © 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

Weakly Supervised Object Localization with Background Suppression Erasing for Art Authentication and Copyright Protection

引用

Machine Intelligence Research 2024年第1期21卷 89-103页

作者： Chaojie Wu Mingyang Li Ying Gao Xinyan Xie Wing W.Y.Ng Ahmad Musyafa School of Computer Science and Engineering South China University of TechnologyGuangzhou 511442China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's HospitalGuangzhou 510180China

The problem of art forgery and infringement is becoming increasingly prominent,since diverse self-media contents with all kinds of art pieces are released on the Internet every *** art paintings,object detection and localization provide an efficient and ef-fective means of art authentication and copyright ***,the acquisition of a precise detector requires large amounts of ex-pensive pixel-level *** alleviate this,we propose a novel weakly supervised object localization(WSOL)with background su-perposition erasing(BSE),which recognizes objects with inexpensive image-level ***,integrated adversarial erasing(IAE)for vanilla convolutional neural network(CNN)dropouts the most discriminative region by leveraging high-level semantic ***,a background suppression module(BSM)limits the activation area of the IAE to the object region through a self-guidance ***,in the inference phase,we utilize the refined importance map(RIM)of middle features to obtain class-agnostic loc-alization *** experiments are conducted on paintings,CUB-200-2011 and ILSVRC to validate the effectiveness of our BSE.

关键词： Weakly supervised object localization erasing method deep learning computer vision art authentication and copyright protection

来源：评论

学校读者我要写书评

暂无评论

Cross-Guided Attention and Combined Loss for Optimizing Gastrointestinal Visual Question Answering

Cross-Guided Attention and Combined Loss for Optimizing Gast...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Yang, Qian Liu, Lijun Yang, Xiaobing Liu, Li Peng, Wei Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Yunnan Key Laboratory of Computer Technology Application Kunming650500 China

ISBN: (纸本)9798350386226

Medical Visual Question Answering (Med-VQA) aims at answering clinical questions related to medical imaging, providing important reference for medical imaging diagnosis. Gastrointestinal visual question answering can deeply understand and analyze gastrointestinal medical images, provides supporting information to answer questions about the diagnostic process, and improves diagnostic accuracy and efficiency. However, most existing Med-VQA can only handle simple and general questions, struggling to tackle visual question answering related to complex diseases. Therefore, this paper proposes a Med-VQA model called CACL, which uses cross-guidance and improved combined loss. The model focuses on gastrointestinal image analysis and achieves efficient and accurate feature extraction for gastrointestinal images. A cross-guided attention module is also designed to enhance the model's reasoning ability when dealing with complex cross-modal tasks. In addition, a multi-task composite loss function is designed to balance the loss of segmentation task and classification task, and improve the overall performance. Experimental results show that the proposed method can effectively improve the accuracy of gastrointestinal visual question answering. © 2024 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Cloud-based technology in Automotive Supply Chain 5

Blockchain and Cloud-based Technology in Automotive Supply C...

引用

5th International Conference on Smart Systems and Inventive technology, ICSSIT 2023

作者： Yasmin, S. Devi, G. Shree B.S.Abdur Rahman Crescent Institute of Science and Technology Department of Computer Application India

ISBN: (纸本)9781665474672

The study focuses on the utilization of Blockchain and Cloud based technologies in the automotive supply chain in India. It is based on a questionnaire-based survey conducted through a Google Form based questionnaire over 75 company executives of automobile sector having any idea on Blockchain. Among the participants, 73% was Male& 27% was Female. 32% Executives with Job experience 2-5 years, 27% with 5-10 years and 41% with More than 10 years. In terms of working profile, 41% Production Manager, 17% Tech Manager and 32% Supply Manager were *** study uses a 5-point Likert scale questionnaire to assess the three broad parameters: Blockchain technology Adoption (BTA), Supply Chain Integration (SC1) with Internal Integration, Customer Integration and Supplier Integration as sub-items and Sustainable Supply Chain Performance (SSCP). It has found that the company executives perceive that the blockchain is well integratedin the supply chain from both supplier and customer's perspective and also perceive that the blockchain is well integrated in the supply chain from both supplier and customer's perspective. organizationsalso has the capability of achieving sustainability in embracing Blockchain technology. Not only in the mainstream production process, but also in the supply chain encompassing the suppliers and transporters, the usage of blockchain technology is widespread acknowledged. The Customer services also embrace Cloud-based Blockchain services to a greater extent. It has been observed that the adoption of blockchain and cloud technologies improve supply chain sustainability and coordination among different units in supply chain. However, the blockchain-based customer services such as vehicle monitoring, theft prevention, insurance scrutiny need to be focused more as the automotive sector in India is inclined to the Blockchain technology towards the backward linkages up the supply chain rather than the forward linkages downward. The cloud integration in the

关键词： Supply chains

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：