检索结果-内蒙古大学图书馆

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Usha, R. Devi, G. Vasundhara Basi Reddy, A. Divya, B. Selvan, R. Senthamil Mits Madanapalle Department of Computer Science and Engineering Madanapalle India School of Computing Mohan Babu University Department of Computer Science and Engineering Tirupati India Gurunanak Institute of Technical Campus Department of Computer Science and Engineering Ibrahimpatnam India Annamacharya Institute of Technology and Sciences Department of Electronics and Communication Engineering Tirupati India

ISBN: (纸本)9798350330724

Key technological tools driving the fast growth of integrated manufacturing may be found in information technologies including big data, deep learning, cloud computing, and the Iot. Recent years have seen significant progress in the application of deep learning to the analysis of large datasets. This work focuses on the automated comprehension of human motions in free gymnastics movies as part of the research of a high-precision classification model for sports footage. This work uses deep learning and large-data-based computer imagery to identify and represent human motions in videos. Sports footage is classified using an independent narrative based on long- and short-term memory associations. Short-term and long-term memory networks learn the map relationship between word sequences and video frame sequences in S2VT. We recommend stressing freestyle gymnastics' building blocks. This study creates a competitive freestyle gymnastics routine database. Using predicted sampling and data and custom-built dataset evaluation, we can narrow training decoder-prediction decoder disparities. This research found rethinking sports footage categorization better. Deep learning video categorization with big data enhances user experience by classifying videos more correctly. Feature extraction networks automate free gymnastics movement descriptions and compare feature extraction results to classify lifting sports models. © 2023 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Novel Analysis and Detection of Autism Spectrum Disorder in Artificial Intelligence Using Hybrid Machine Learning

A Novel Analysis and Detection of Autism Spectrum Disorder i...

引用

2023 IEEE International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2023

作者： Senthil, G.A. Prabha, R. Nithyashri, J. Suganthi, P. Thamarai, I. Sridevi, S. Agni College of Technology Department of Information Technology Chennai India Sri Sai Ram Institute of Technology Department of Electronics and Communication Engineering Chennai India School of Computing SRM Institute of Science and Technology Kattankulathur Dept. of Computing Technologies Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai City Campus Chennai India Sri Ramachandra Engineering and Technology Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397208

Heart Disease or Cardiovascular Disease refers to the range of heart conditions like cardiac arrest, coronary artery disease. Heart disease can be very well hindered through certain lifestyle changes. There is a significant increase in the mortality rate recently due to the distinctive heart diseases. Machine learning uses mathematical models to work efficiently with the enormous amount of data. It plays a crucial role in medical science in the prediction of distinctive diseases. Cardiologists inspects the heart functionality using electrocardiography, computed tomography. These tests are quite expensive for a common man. Recent times, the life span of a human is guaranteed only with the support of medications. As prevention is better than the cure, machine learning helps to predict the vulnerability of a heart disease with few elemental symptoms and health factors. It is been fed by the basic data of the patients like age and sex. Machine learning helps to predict the vulnerability in advance which provides the cardiologists with great acumen for the adaption of the treatment. Machine learning algorithms have proven to produce reliable and accurate output with the help of the inputs. The algorithms used in the article include K-Nearest Neighbour (KNN) and decision tree classifier which is compared to yield the desired and efficient output. © 2023 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Security of Images Using DNA Encryption and Lorenz System in Cloud Storage 7th

Security of Images Using DNA Encryption and Lorenz System in...

引用

7th International Conference on Soft computing and Signal Processing, ICSCSP 2024

作者： Gupta, Raghav Gullapalli, Manasa Suseela, G. Department of Networking and Communications School of Computing Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Networking and Communications Faculty of Engineering and Technology School of Computing Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9789819799251

Images are the most valuable yet susceptible type of data since they may be used to track user activity, exploited by hackers, and utilized for fraud and identity theft. Storing images in local storage, on a device’s disk, within a web browser’s local storage, or on a server’s file system can introduce several vulnerabilities and risks, particularly regarding security and data integrity. Using image encryption as a security solution provides a reliable means of protecting sensitive visual data from unauthorized access and potential security threats. The convenience of cloud-based systems, however, comes with the responsibility of protecting data against cyber threats. The widespread usage of cloud storage has led to concerns about the security of images stored there. Addressing the challenges associated with securing images in the cloud, this project brings a novel approach that blends cryptographic techniques, such as DNA encryption, with the dynamism of chaotic systems like the Lorenz system. Such integrative methodologies aim to meet current security demands for image storage and transmission in the digital age. This dual-layer encryption approach ensures that images encrypted and stored in cloud storage are safeguarded with a security measure that is currently unparalleled, making unauthorized access and decryption practically impossible without the specific, uniquely generated decryption key. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics

引用

IEEE Transactions on Mobile computing 2025年

作者： Chen, Yile Li, Xiucheng Cong, Gao Bao, Zhifeng Long, Cheng Nanyang Technological University School of Computer Science and Engineering Singapore School of Computer Science and Technology Guangdong Shenzhen China RMIT University School of Computing Technologies MelbourneVIC Australia

The widespread adoption of mobile devices and positioning technology has resulted in the generation of massive urban data, offering great opportunities to improve analytical abilities for urban infrastructure components. In this study, we introduce a novel framework called Toast for learning general-purpose representations of road networks, along with its advanced counterpart DyToast, designed to enhance the integration of temporal dynamics to boost the performance of various time-sensitive downstream tasks. Specifically, we propose to encode two pivotal semantic characteristics intrinsic to road networks: traffic patterns and traveling semantics. To achieve this, we refine the skip-gram module by incorporating auxiliary objectives aimed at predicting the traffic context associated with a target road segment. Moreover, we leverage mobile trajectory data and design pre-training strategies based on Transformer to distill traveling semantics on road networks. DyToast further augments this framework by employing unified trigonometric functions characterized by their beneficial properties, enabling the capture of temporal evolution and dynamic nature of road networks more effectively. With these proposed techniques, we can obtain representations that encode multi-faceted aspects of knowledge within road networks, applicable across both road segment-based applications and trajectory-based applications. Extensive experiments on two real-world datasets across three tasks demonstrate that our proposed framework consistently outperforms the state-of-the-art baselines by a significant margin. © 2002-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Large Language Models for Data Annotation and Synthesis: A Survey

Large Language Models for Data Annotation and Synthesis: A S...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Tan, Zhen Li, Dawei Wang, Song Beigi, Alimohammad Jiang, Bohan Bhattacharjee, Amrita Karami, Mansooreh Li, Jundong Cheng, Lu Liu, Huan School of Computing and Augmented Intelligence Arizona State University United States Department of Electrical and Computer Engineering the University of Virginia United States Department of Computer Science University of Illinois Chicago United States

ISBN: (纸本)9798891761643

Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. The process, however, is labor-intensive and costly. The emergence of advanced Large Language Models (LLMs), exemplified by GPT-4, presents an unprecedented opportunity to automate the complicated process of data annotation and synthesis. While existing surveys have extensively covered LLM architecture, training, and general applications, we uniquely focus on their specific utility for data annotation. This survey contributes to three core aspects: LLM-Based Annotation Generation, LLM-Generated Annotations Assessment, and LLM-Generated Annotations Utilization. Furthermore, this survey includes an in-depth taxonomy of data types that LLMs can annotate, a comprehensive review of learning strategies for models utilizing LLM-generated annotations, and a detailed discussion of the primary challenges and limitations associated with using LLMs for data annotation and synthesis. Serving as a key guide, this survey aims to assist researchers and practitioners in exploring the potential of the latest LLMs for data annotation, thereby fostering future advancements in this critical field. © 2024 Association for Computational Linguistics.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Assessing the Participation of Villagers in a Participatory Rural Appraisal Based Study: An Amrita Live-In-Labs® Project Case Study 4

Assessing the Participation of Villagers in a Participatory ...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Anoop, S. Adwaith, A. Aswin, A. Raja, S.K. Tejasvin, V. Nayan, M.K. Nithin, P.M. Amrita Vishwa Vidyapeetham Department of Electrical and Electronics Engineering Amritapuri India Amrita Vishwa Vidyapeetham Department of Electronics and Communication Engineering Amritapuri India Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Amritapuri India Amrita Vishwa Vidyapeetham Amrita School For Sustainable Futures Amritapuri India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518981

Participatory Rural Appraisal (PRA) is a key methodology in the socially inclusive development of Indian rural communities. Even though there are various organizations and government agencies involved in the 'real' implementation of PRA for identifying the root causes and solutions of poverty, health issues, societal imbalance, and so on, the actual participation of the beneficiaries in the process is still a question mark. In this paper, we try to analyse the effect of actual participation of the people from the local community in the application of some PRA tools to do surveys and identify the root cause of the economic backwardness, and societal imbalance in a rural village in the state of Maharashtra, India. Most of the similar projects are done by management or social science students/researchers/scientists. In this paper, the analysis is done and presented from an engineer's perspective. This project is part of the Live-in-Labs® project of Amrita Vishwa Vidyapeetham to encourage students to live and interact with society and to learn and solve the community's problems. In this paper, we try to explain the various levels of complexities faced during the study, with an emphasis on both failed and succeeded steps. We believe this paper supports practitioners and policymakers who are working towards improving the methodologies and approaches involved in PRA to ensure an inclusive and holistic community integrated development in rural India. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Data Bias Recognition in Museum Settings: Framework Development and Contributing Factors 25

Data Bias Recognition in Museum Settings: Framework Developm...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI 2025

作者： Quinto Lima, Stella Buraglia, Gabriela Kam-Kwai, Wong Roberts, Jessica School of Interactive Computing Georgia Institute of Technology AtlantaGA United States Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong Interactive Computing Georgia Institute of Technology AtlantaGA United States

ISBN: (纸本)9798400713941

Critical thinking skills are increasingly important for comprehending our data-rich society. While museums provide data for discussion, visitors may not naturally question data in such displays due to the inherent authority of a museum. To investigate what factors can help visitors recognize bias in data, we interviewed visitors after they interacted with an augmented reality data map in an interactive data exhibition. Here, we present a qualitative analysis of fifteen semi-structured interviews with visitors who engaged with mapped data from the citizen science platform iNaturalist. The study revealed that 47% of participants were able to recognize bias, and familiarity was found to be a significant factor in this ability. We propose a three-layer framework to understand the cognitive processes of bias recognition in informal learning settings and apply this framework to our data to inform future work for designing displays to promote critical engagement with data in free-choice learning contexts. © 2025 Copyright held by the owner/author(s).

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Advancements in Sustainable Charging Infrastructure: Integrating Solar Energy and IoT for Smart E-Vehicle Charging Stations

Advancements in Sustainable Charging Infrastructure: Integra...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Sivasankar, C. Saravanan, G. Pradeepa, H. Arun, V. Ganesh, E.N. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Sairam Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Thiagarajar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Madurai India School of Computing Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computing Technologies Tamil Nadu Chennai India Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350313987

An effective and environmentally friendly charging infrastructure is essential due to the rising popularity of Electric Vehicles (EVs). The proposed system offers an efficient approach to this problem by suggesting a solar charging station for EV incorporating the Internet of Things (IoT). In order to encourage the use of renewable energy and lessen the environmental impact, the system uses solar energy to power EV charging stations. IoT technologies improve the charging station's performance by allowing realtime monitoring and control, remote access and data analytics. Considerations for solar panel layout optimization and energy storage are central to this study's emphasis on the design and execution of a solar-powered EV charging station. In addition, the station can easily respond to changes in demand and grid circumstances thanks to dynamic load control made possible by IoT. This research proves the feasibility and efficiency of the proposed Solar with IoT Charging Station for Electric Vehicles via practical assessment and simulations. The results provide a scalable and long-term answer that promotes a cleaner and greener transportation environment by aiding the development of electric mobility and integrating renewable energy. © 2023 IEEE.

关键词： Charging Station Dynamic Load Management Electric Vehicle Internet of Things Solar Energy

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Deep Learning and Machine Learning models for Network Intrusion Detection 14

Comparative Analysis of Deep Learning and Machine Learning m...

引用

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Dharaneish, V.C. Nithin Kumar, S. Hari Varsha, V. Senthil Kumar, T. Gireesh Kumar, T. Vajipayajula, Sulakshan Coimbatore Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering India Coimbatore Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of Electrical and Electronics Engineering India Ibm India Pvt Ltd Ibm Security Bengaluru India

ISBN: (纸本)9798350335095

The increasing prevalence of security breaches and malicious software attacks is a major concern in the digital landscape, sparking continued interest in malware detection. Malware attacks have a significant impact on computer users, networks, businesses, organizations, and governments. Despite the development of multiple intrusion detection systems aimed at protecting data and resources from attacks, the frequent emergence of new threats and attacks poses a challenge for these systems to detect and prevent them from penetrating the network. One such attack is Advanced Persistent Threats (APTs) which can cause significant damage to computer network and organizations. To handle these attacks, the study has developed an APT detection system that uses various Machine learning (ML) and Deep Learning (DL) based classifiers, which can more effectively extract data features from huge amounts of complex data and understand patterns to detect anomalies and potential threats. This study compares and evaluate their performance and efficiency on NSL-KDD dataset. By evaluating using various evaluation metrics, it was found that Extreme Gradient Boosting (XGBoost) is the most effective model among all models, followed by Multi-Layer Perceptron (MLP) and Convolutional Neural Networks (CNN). © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Joint Learning Based on Discriminant Representation and Group Collaborative Measurement for Image Set Classification 2nd

Joint Learning Based on Discriminant Representation and Grou...

引用

2nd International Conference on Image, Vision and Intelligent Systems, ICIVIS 2022

作者： Liu, Xingrui Feng, Zeming Gao, Xizhan School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9789819909223

In daily life, it is easy to obtain a large number of images in the form of sets. How to extract discriminative information from a wide range of images become very important. Most of the existing image set classification methods based on collaborative representation assume that the images in the same set can affect each other, ignoring the interaction between sets. In order to solve the above problems, a joint learning based on discriminative representation and group collaborative measurement (DRGCM) is proposed. Through the deep subspace clustering algorithm, the set is accurately divided, and multiple local models are found to form a dictionary. In the training stage, a global projection matrix learning model is designed to make the dictionary have stronger representation ability of prototype points in the embedded space. In the testing phase, a class-specific projection matrix model is constructed around the test set to make the dictionary more discriminative to the test set in a specific embedding space. Finally, the excellent performance on Honda, Mobo and other database proves the effectiveness of the algorithm. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

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：