检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Bandyopadhyay, Shaon Dutta, Dipankar Pratihar, Sanjoy Indian Institute of Information Technology Computer Science and Engineering Department West Bengal Kalyani KalyaniPIN 741235 India University Institute of Technology The University of Burdwan Computer Science and Engineering Department West Bengal BurdwanPIN 713104 India

ISBN: (纸本)9798350370249

In modern fast-paced society, the prevalence of fast food has spurred a surge in its consumption, emphasizing the need for accurate food identification systems. This study explores the efficacy of using the 'You Only Look Once' (YOLO) principles for classifying fast foods using the Food-101 dataset, which includes 1 0 1, 0 0 0 images across 101 food categories. Traditional machine learning (ML) methods, i.e., methods not using deep learning (DL), have struggled with the significant variation within classes and minimal distinction between classes characteristic of food images. In contrast, DL models, particularly convolutional neural networks (CNNs), have shown significant promise. This research leverages YOLO version 5 (YOLOv5), a cutting-edge object detection model, to achieve a classification accuracy of 8 0. 2 0 %. It outperforms other models such as Inceptionv3 and GoogLeNet. The study employs advanced techniques such as data augmentation, batch normalization, and sophisticated loss functions to optimize performance. The results underscore YOLOv5's superior capability in handling the complexities of fast-food classification. In the future, this can be useful for developing a robust solution for automated dietary monitoring and caloric intake assessment. © 2024 IEEE.

关键词： Convolutional Neural Networks Deep Learning Fast-Food Classification Food-101 Dataset YOLO

来源：评论

学校读者我要写书评

暂无评论

Blockchain inspired secure and reliable data exchange architecture for cyber-physical healthcare system 4.0

引用

Internet of Things and Cyber-Physical Systems 2023年第1期3卷 309-322页

作者： Kumar, Mohit Raj, Hritu Chaurasia, Nisha Gill, Sukhpal Singh Department of Information Technology National Institute of Technology Punjab Jalandhar India Department of Computer Science and Engineering National Institute of Technology Punjab Jalandhar India School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom

A cyber-physical system is considered to be a collection of strongly coupled communication systems and devices that poses numerous security trials in various industrial applications including healthcare. The security and privacy of patient data is still a big concern because healthcare data is sensitive and valuable, and it is most targeted over the internet. Moreover, from the industrial perspective, the cyber-physical system plays a crucial role in the exchange of data remotely using sensor nodes in distributed environments. In the healthcare industry, Blockchain technology offers a promising solution to resolve most securities-related issues due to its decentralized, immutability, and transparency properties. In this paper, a blockchain-inspired secure and reliable data exchange architecture is proposed in the cyber-physical healthcare industry 4.0. The proposed system uses the BigchainDB, Tendermint, Inter-Planetary-File-System (IPFS), MongoDB, and AES encryption algorithms to improve Healthcare 4.0. Furthermore, blockchain-enabled secure healthcare architecture for accessing and managing the records between Doctors and Patients is introduced. The development of a blockchain-based Electronic Healthcare Record (EHR) exchange system is purely patient-centric, which means the entire control of data is in the owner's hand which is backed by blockchain for security and privacy. Our experimental results reveal that the proposed architecture is robust to handle more security attacks and can recover the data if 2/3 of nodes are failed. The proposed model is patient-centric, and control of data is in the patient's hand to enhance security and privacy, even system administrators can't access data without user permission. © 2023 The Authors

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

On the Parameterized Complexity of Diverse SAT 35

On the Parameterized Complexity of Diverse SAT

引用

35th International Symposium on Algorithms and Computation, ISAAC 2024

作者： Misra, Neeldhara Mittal, Harshil Rai, Ashutosh Department of Computer Science and Engineering Indian Institute of Technology Gandhinagar India Department of Mathematics Indian Institute of Technology Delhi New Delhi India

ISBN: (纸本)9783959773546

We study the Boolean Satisfiability problem (SAT) in the framework of diversity, where one asks for multiple solutions that are mutually far apart (i.e., sufficiently dissimilar from each other) for a suitable notion of distance/dissimilarity between solutions. Interpreting assignments as bit vectors, we take their Hamming distance to quantify dissimilarity, and we focus on the problem of finding two solutions. Specifically, we define the problem Max Differ SAT (resp. Exact Differ SAT) as follows: Given a Boolean formula on n variables, decide whether has two satisfying assignments that differ on at least (resp. exactly) d variables. We study the classical and parameterized (in parameters d and n − d) complexities of Max Differ SAT and Exact Differ SAT, when restricted to some classes of formulas on which SAT is known to be polynomial-time solvable. In particular, we consider affine formulas, Krom formulas (i.e., 2-CNF formulas) and hitting formulas. For affine formulas, we show the following: Both problems are polynomial-time solvable when each equation has at most two variables. Exact Differ SAT is NP-hard, even when each equation has at most three variables and each variable appears in at most four equations. Also, Max Differ SAT is NP-hard, even when each equation has at most four variables. Both problems are W[1]-hard in the parameter n − d. In contrast, when parameterized by d, Exact Differ SAT is W[1]-hard, but Max Differ SAT admits a single-exponential FPT algorithm and a polynomial-kernel. For Krom formulas, we show the following: Both problems are polynomial-time solvable when each variable appears in at most two clauses. Also, both problems are W[1]-hard in the parameter d (and therefore, it turns out, also NP-hard), even on monotone inputs (i.e., formulas with no negative literals). Finally, for hitting formulas, we show that both problems can be solved in polynomial-time. © Neeldhara Misra, Harshil Mittal, and Ashutosh Rai.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

The Large Language Models on Biomedical Data Analysis: A Survey

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4486-4497页

作者： Lan, Wei Tang, Zhentao Liu, Mingyang Chen, Qingfeng Peng, Wei Chen, Yiping Phoebe Pan, Yi Guangxi University School of Computer Electronic and Information Nanning530004 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China La Trobe University Department of Computer Science and Information Technology MelbourneVIC3086 Australia Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen518055 China

With the rapid development of Large Language Model (LLM) technology, it has become an indispensable force in biomedical data analysis research. However, biomedical researchers currently have limited knowledge about LLM. Therefore, there is an urgent need for a summary of LLM applications in biomedical data analysis. Herein, we propose this review by summarizing the latest research work on LLM in biomedicine. In this review, LLM techniques are first outlined. We then discuss biomedical datasets and frameworks for biomedical data analysis, followed by a detailed analysis of LLM applications in genomics, proteomics, transcriptomics, radiomics, single-cell analysis, medical texts and drug discovery. Finally, the challenges of LLM in biomedical data analysis are discussed. In summary, this review is intended for researchers interested in LLM technology and aims to help them understand and apply LLM in biomedical data analysis research. © 2013 IEEE.

关键词： Data consistency

来源：评论

学校读者我要写书评

暂无评论

A Self-Labeling Method for Adaptive Machine Learning by Interactive Causality

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2093-2102页

作者： Ren, Yutian Yen, Aaron Haohua Li, Guann-Pyng University of California Irvine Department of Electrical Engineering and Computer Science The California Institute for Telecommunications and Information Technology IrvineCA92697 United States

Learning from unlabeled data or self-learning, can substantially reduce the complexity of machine learning (ML) utilization in real-time deployment. While the development of un/semisupervised algorithms shows promising results in learning with reduced labels, the fundamental assumption of data smoothness restricts its scope of application, especially with nonstationary data distributions in different domains. Leveraging transdomain invariant causal relationships, causality has recently been employed to foster robust ML. In this article, we have developed a generic method for self-labeling data that relies on known causality among interactive objects and learned temporal relations among causal events for identifying and associating labels and input data. The causal time-interval between asynchronous cause and effect events is studied to achieve self-labeling. We utilize dynamical system theory in a 1-d setting to demonstrate that our proposed method outperforms traditional feature similarity-based semisupervised learning. A computer simulation experiment was conducted to generate high-dimensional data, and the comprehensive results reveal the potential of learning adaptation in dynamic environments to improve ML robustness against shifts in data distribution. © 2023 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Heuristic Data Placement in Distributed Hierarchical Storage Network Using Deep Reinforcement Learning 22

Heuristic Data Placement in Distributed Hierarchical Storage...

引用

22nd IEEE Consumer Communications and Networking Conference, CCNC 2025

作者： Kaler, Ravi Toshniwal, Durga Indian Institute of Technology Roorkee Computer Science and Engineering Department Uttarakhand India

ISBN: (纸本)9798331508050

Intelligent data placement in hierarchical distributed storage networks (DSNs) has become crucial due to advancements in storage devices, an increase in big data applications, and strict time constraints. Inefficient data placement can lead to significant delays in data movement and increased service latency, impacting the overall performance of a distributed environment. It is a complex online decision-making problem due to its varying access patterns, dynamic network conditions, and ever-changing distributed environment, which traditional network optimization techniques fail to address efficiently. Reinforcement learning is best suited to address this problem as it learns from the environment dynamically and performs action. This paper presents a novel deep reinforcement learning (DRL) framework, soft actor-critic-2 (SAC-2), for heuristic data placement in the distributed network, leveraging the state-of-the-art SAC technique to improve efficiency, reduce latency, and subsequently minimize storage costs. We formulate the problem as a Markov Decision Process (MDP) model and incorporate a prioritized replay buffer for efficient learning. The heuristic data placement technique improves distributed hierarchical storage system efficiency compared to baseline strategies, as demonstrated by extensive experiments on Microsoft Research Cambridge (MSR) network traces. © 2025 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Labor Safety Analysis Using Object Recognition and Deep Learning 1

引用

2nd International Conference on Human-Centric Smart Computing, ICHCSC 2023

作者： Evangeline, D. Jatin, B. Manoj, S. Pannaga, N. Sanjeev, G. Parkavi, A. Department of Information Science and Engineering Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering Ramaiah Institute of Technology Bangalore India

ISBN: (数字)9789819977116

ISBN: (纸本)9789819977109

Occupational safety is a major concern in any industry or workplace, and the use of advanced technologies such as object recognition and deep learning can greatly enhance safety measures. This paper proposes a labor safety analysis system that utilizes object recognition and deep learning algorithms to detect potential hazards and ensure safe working conditions. The proposed system can recognize various types of safety gear and analyze their positions and movements to detect potential safety in real time. The system can also provide alerts and warnings to workers and supervisors in case of the absence of safety gear. Experimental results demonstrate the effectiveness and efficiency of the proposed work. This can significantly improve the safety and productivity of the workplace. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Centralized Platform for Sensor Integration and AI Models in Precision Agriculture 2

Centralized Platform for Sensor Integration and AI Models in...

引用

2nd IEEE International Conference on Networks, Multimedia and information technology, NMITCON 2024

作者： Chowdary, Ch Srinivasa Akshith Likith, S. Maya, B.S. Lokesh, S.V. Manish, Y. Asha, T. Bangalore Institute of Technology Department of Computer Science and Engineering Bengaluru India Bangalore Institute of Technology Department of Information Science and Engineering Bengaluru India

ISBN: (纸本)9798350372892

A centralized platform for integrating various sensors and AI models in precision agriculture. The platform connects soil moisture sensors with AI models to generate crop recommendations and irrigation alerts, aiming to enhance resource utilization and crop yield. Key outcomes include real-time monitoring, actionable insights, and data-driven decision support for farmers. The practical implications for farmers and the agricultural industry are profound, as this system enables them to adopt precision agriculture techniques, reducing waste, increasing efficiency, and ultimately improving profitability © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation

引用

Research 2024年第2期6卷 29-40页

作者： Jiawen Deng Zhuang Chen Hao Sun Zhexin Zhang Jincenzi Wu Satoshi Nakagawa Fuji Ren Minlie Huang The CoAl group DCSTInstitute for Artificial InteligenceState Key Lab of Intelligent Technology and SystemsBeijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Graduate School of Information Science&Technology The University of Tokyo.Tokyo 1138654Japan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengduSichuan611731China

Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language *** data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English *** significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain *** alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language Dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model ***,we employ a multiteacher distillation framework to enhance detection performance with unsupervised *** is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to *** soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive *** conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.

关键词： COLD dealing limitations

来源：评论

学校读者我要写书评

暂无评论

A Fruit and Vegetable Detection Based on Pytorch Machine Learning Frame Work Model 2

A Fruit and Vegetable Detection Based on Pytorch Machine Lea...

引用

2nd International Conference on Emerging Trends in information technology and engineering, ic-ETITE 2024

作者： Priyadharshini, U. Vijayan, R. School of Advanced Science Vellore Institute of Information Technology Vellore India School of Computer Science Engineering and Information System Vellore Institute of Information Technology Vellore India

ISBN: (纸本)9798350328202

Today, Agricultures has become a significant element of people's life. Among them fruits and vegetables are a great thing for healthy lives. Classification of fruits and vegetable are difficult for normal person because of some same similarities like shape and color. Also, Fruits and Vegetables classification is an important process in industries applications as well as local market. Lots of similarities available between fruits like apples, pears and peaches, and that kinds of fruits are generally used in daily routine. As well as some vegetables are same in shape, so it will be difficult to differentiate in this type of situation for old persons. The previous research for solution of this type of problem for classification of fruits CNN is used but the problem in this research is when they use the self-made datasets then their accuracy decreases as compare to public datasets accuracy increases. To solve this type of problem, here produce a kind of algorithms in the paper to classify fruits and vegetable, using deep leaning technique such as VGG16 and DenseNet169 model have capability to extract the feature of images very deeply using various small filters so it provide a better result. On this premise, it was used to classify fruit kinds against a complex background and integrated with data improvement technology for future usage. It might be helpful for human for automatic differentiate the both categories. This project is implemented in the python programming language and the dataset used Fruits and Vegetables Image Recognition Dataset for the classification. Which will help to differentiate between Fruits and Vegetables with high accuracy rate. For the implementation of this project used Python programming and this implementation using the tool like Jupiter and Kaggle Notebook and used GPU for highspeed execution. © 2024 IEEE.

关键词： Fruits

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：