检索结果-内蒙古大学图书馆

1st International Conference in Advanced Innovation on Smart City, ICAISC 2023

作者： Kandpal, Meenakshi Sharma, Bhisham Barik, Rabindra K. Chowdhury, Subrata Patra, Sudhansu Shekhar Dhaou, Imed Ben KIIT Deemed to Be University School of Computer Engineering KIIT Deemed to Be University Bhubaneswar India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India KIIT Deemed to Be University School of Computer Applications Bhubaneswar India MCA Department AP Chittoor India Dar Al-Hekma University Hekma School of Engineering Computing and Informatics Department of Computer Science Jeddah Saudi Arabia

ISBN: (纸本)9781665472753

Due to the convergence of healthcare and smart cities, information and technology are employed in health and medical procedures worldwide. Residents of smart cities now enjoy better lives and healthier bodies because to integration. The advent of smart watch technology and deep learning techniques has engendered a potential increase in performance and accuracy of such tasks. Our paper explores the application of recurrent neural networks particularly LSTM for action recognition task using smart watch sensor data, i.e., gyroscope and accelerometer data. We have taken into consideration some general activities like standing, walking, sitting, etc. and implemented a LSTM network for the action recognition job using the time sequences sensor data. This model can be useful for other health-based applications which can monitor the health conditions of a user by keeping record of his activities. © 2023 IEEE.

关键词： Watches

来源：评论

学校读者我要写书评

暂无评论

Predicting Illnesses through Symptomatic Patterns through Ensemble Voting Regressor

Predicting Illnesses through Symptomatic Patterns through En...

引用

International Conference on Advances in Information technology (ICAIT)

作者： Prantik Ghosh Abhivesh Shukla Bibin Christopher V Fitri Yakub Computer Science and Engineering SRM Institute of Science And Technology Kattankulathur India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur India Japan International Institute of Technology University Technology Malaysia Kuala Lumpur

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

This paper utilizes the GitHub Collaborative Disease-Symptom Dataset enabling the identification of disease patterns through symptom analysis. Aimed at boosting the accuracy and efficiency of disease prediction systems, this initiative trains models like Logistic Regression, SVM, and KNN on a rich dataset of symptoms and diseases, seeking to provide personalized diagnostic insights for improved patient care. The methodolog capitalizes on this diverse dataset to uncover complex patterns, utilizing metrics such as precision, accuracy, and the F1 score for enhanced predictive performance. Results have shown significant progress in disease prediction, with confusion matrices revealing refined model predictions marked by high precision and accuracy in disease classification from reported symptoms. Ensemble Classifier yielded a record-breaking 98.96% accuracy, demonstrating the power of combining models for superior predictions. This endeavor highlights machine learning's transformative impact on healthcare diagnostics, offering data-driven insights for personalized medicine and targeted treatment strategies, thus emphasizing the critical role of sophisticated data analysis in elevating patient care and healthcare outcomes.

关键词： Support vector machines Accuracy Precision medicine Medical services Predictive models Vectors Robustness Regression tree analysis Diseases Software development management

来源：评论

学校读者我要写书评

暂无评论

Privacy Optimization in Sensors Based Networks With Industrial Processes Management 3

Privacy Optimization in Sensors Based Networks With Industri...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Siddiqui, Ahmed F. Mishra, Sushruta Jena, Mondeep M. Sharma, Vandana Al-Khasawneh, Mahmoud Ahmad Alkhayyat, Ahmed Kalinga Institute of Industrial Technology Deemed to Be University India Computer Science Department Delhi NCR India School of Computing Skyline University College University City Sharjah United Arab Emirates College of Technical Engineering The Islamic University Najaf Iraq

ISBN: (纸本)9798350343274

The Internet of Things (IoT) also known as IoT has the potential that is required to revolutionize industries, this has been discussed in this research article. Advancements in technology have made devices affordable, efficient and reliable. Different sectors have already started to incorporate these devices into their operations to boost productivity, to minimize failure and downtime. They also use it to optimize resource utilization which is also an important factor. However, the use of these devices also has some security challenges which need to be handled. This research paper proposes a security model specifically designed for process management in the industries. The goal of this model is to find the vulnerabilities, to minimize the risks and threats. Also ensuring integrity, confidentiality and availability of processes is a part of the goal. This paper gives evidence from its implementation and trial apart from its explanation. During the implementation phase, the sensitive data achieved a 100% encryption rate, for protection. Also, integrity checks were conducted on 99.8% of data to guarantee data integrity. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics

arXiv

引用

arXiv 2024年

作者： Wang, Jiahao Yang, Sikun Koeppl, Heinz Cheng, Xiuzhen Hu, Pengfei Zhang, Guoming School of Computer Science and Technology Shandong University China School of Computing and Information Technology Great Bay University China Department of Electrical Engineering and Information Technology Technische Universität Darmstadt Germany

Probabilistic approaches for handling count-valued time sequences have attracted amounts of research attentions because their ability to infer explainable latent structures and to estimate uncertainties, and thus are especially suitable for dealing with noisy and incomplete count data. Among these models, Poisson-Gamma Dynamical Systems (PGDSs) are proven to be effective in capturing the evolving dynamics underlying observed count sequences. However, the state-of-the-art PGDS still fails to capture the time-varying transition dynamics that are commonly observed in real-world count time sequences. To mitigate this gap, a non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time, and the evolving transition matrices are modeled by sophisticatedly-designed Dirichlet Markov chains. Leveraging Dirichlet-Multinomial-Beta data augmentation techniques, a fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance due to its capacity to learn non-stationary dependency structure captured by the time-evolving transition matrices. © 2024, CC BY.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Deep CNN based droplet deposition segmentation for spray distribution assessment 27

Deep CNN based droplet deposition segmentation for spray dis...

引用

27th International Conference on Automation and computing, ICAC 2022

作者： Chen, Tao Meng, Yanhua Su, Jinya Liu, Cunjia University of Essex School of Computer Science and Electronic Engineering Colchester United Kingdom Anyang Institute of Technology School of Mechanical Engineering Anyang China University of Aberdeen Department of Computing Science Aberdeen United Kingdom Loughborough University Department of Aeronautical and Automotive Engineering Loughborough United Kingdom

ISBN: (数字)9781665498074

ISBN: (纸本)9781665498074

Pesticides have been widely used in the cultivation of crops to enhance their production, however, incorrect application of pesticides will result in yield loss, product waste, environmental pollution among many others. Therefore, timely evaluating spray distribution of intelligent sprayers plays a pivotal role in the appropriate delivery of pesticides to the crop. The exiting approaches based on water-sensitive paper (WSP) either involve a relatively tedious and labor-intensive procedure, or have a high requirement on WSP image taking. So in this study we aim to conduct spray distribution assessment in the field based on mobile devices. To this end, the key issue of droplet deposition segmentation under natural imaging environments is addressed. WSPs with food dye droplets are first collected in the field by mobile phones. Then an image dataset on droplet deposition segmentation is created via thresholding approach with human supervision. Then four popular deep convolutional neural network (CNN) based segmentation algorithms are applied for droplet deposition segmentation so that spray distribution can be assessed. Comparative experiments show that UNeXt network is the best one in consideration of accuracy, inference time and network size. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Classification Using CNNs

Brain Tumor Classification Using CNNs

引用

International Conference on Power, Energy, Control and Transmission Systems (ICPECTS)

作者： D Saveetha Banu Priya Prathaban A Rashmi K. E. Purushothaman Department of Networking and Communication School of Computing College of Engineering and Technology SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai Tamil Nadu Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508852

Brain tumors are abnormal cell growths in the brain that can have a major negative impact on one's health. For efficient treatment planning, brain tumor classification must be precise. Convolutional Neural Networks (CNNs) have been an effective technique for the automated classification of brain tumors in recent years. Convolutional Neural Network (CNN) is the most popular neural network model for the image classification problem, which has attracted a lot of interest in recent years. In this paper, we suggest a CNN model for classifying brain tumors that performs quite well on a publicly accessible dataset. We contrast our model's performance with that of earlier research and talk about how our findings might have medical applications. Our findings demonstrate the need for more research in this field and show how well CNNs can classify brain tumors. The proposed CNN-based approach aims to accurately classify three major types of brain tumors, namely glioma, meningioma, and pituitary tumor. The results obtained from the experiments show promising results, with an accuracy of over 93%. The proposed CNN-based approach provides a reliable and efficient tool for the classification of brain tumors, which can aid in the accurate diagnosis and treatment planning of patients.

关键词： Accuracy Medical services Brain modeling Planning Convolutional neural networks Reliability Feeds Biological neural networks Optimization Image classification

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Framework to Classify and Generate Privacy-Preserving Explanations in Pornography Detection

An End-to-End Framework to Classify and Generate Privacy-Pre...

引用

International Conference of the Biometrics Special Interest Group (BIOSIG)

作者： Margarida Vieira Tiago Gonçalves Wilson Silva Ana F. Sequeira Faculty of Engineering University of Porto INESC TEC Porto Portugal Department of Information and Computing Sciences Department of Biology AI Technology for Life Utrecht University Utrecht The Netherlands

ISBN: (数字)9798350373714

ISBN: (纸本)9798350373721

The proliferation of explicit material online, particularly pornography, has emerged as a paramount concern in our society. While state-of-the-art pornography detection models already show some promising results, their decision-making processes are often opaque, raising ethical issues. This study focuses on uncovering the decision-making process of such models, specifically fine-tuned convolutional neural networks and transformer architectures. We compare various explainability techniques to illuminate the limitations, potential improvements, and ethical implications of using these algorithms. Results show that models trained on diverse and dynamic datasets tend to have more robustness and generalisability when compared to models trained on static datasets. Additionally, transformer models demonstrate superior performance and generalisation compared to convolutional ones. Furthermore, we implemented a privacy-preserving framework during explanation retrieval, which contributes to developing secure and ethically sound biometric applications.

关键词： Biometrics Ethics Biological system modeling Heuristic algorithms Decision making Transformers Robustness Convolutional neural networks Context modeling

来源：评论

学校读者我要写书评

暂无评论

A Lightweight & Effective Public-Key System for IoT Applications Using DL Architecture 2

A Lightweight & Effective Public-Key System for IoT Applicat...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Marwaha, Pradeep Reena, R. Lohani, Manoj Chandra Menon, Soumya V. Aher, Vijaya N. Amudha, A. Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Information Technology Chennai127 India Graphic Era Hill University School of Computing Haldwani India Graphic Era Deemed to be University Uttarakhand Dehradun248002 India School of Sciences Chemistry and Biochemistry Karnataka Bangalore India Vishwakarma Institute of Technology Pune India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore641021 India

ISBN: (纸本)9798350388916

Online communication has grown in significance with advancements in computer network technology, and as a result, network complete solution has emerged as a means to guarantee dependable network communication. Keeping the internet secure is crucial in light of this. Most people use encryption. There are several encryption approaches that are constituted by different encryption algorithms. A novel algorithm, hyper-chaotic encryption, has evolved in the last few years. This forms the basis of an encryption system that may provide complete information security for networks and effectively thwart malicious network intrusions. Differential Privacy's main selling point is that it uses common numerical data types, which means it's compatible with the vast majority of machine learning libraries and hardware accelerators. This results in almost little overhead during implementation or runtime. Conversely, the accuracy of the model's forecasts is diminished when Differential Privacy is used. Instead of providing cryptographic assurances, Differential Privacy just provides a probability constraint on the likelihood of information leaking. The computer has become an integral part of people's daily lives, facilitating both education and daily living. Due to the multifaceted nature of the computer network environment, several variables might have an impact. Examining the safety of the computer network is the first and foremost step in making it more secure. Thus, there is a pressing need to use algorithms based on deep learning to assist programmers in developing a new system for computer internet security due to the high human and material expenses associated with maintaining this system and the inefficiency of conventional approaches. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Geometric Reconstruction in Modern Remote Sensing Techniques and Applications 4

Geometric Reconstruction in Modern Remote Sensing Techniques...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Temara, Sheetal Ravindran, Sindhu Sreevidya, Nelli Krishnmoorthi, Sathya Devarasu, Neelamegam Thota, Krishna Kishore University of the Cumberlands Department of Computer and Information Sciences United States Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India Sreenidhi Institute of Science and Technology Dept. of It Telangana Hyderabad India Kongu Engineering College Dept. of Artificial Intelligence TN Erode India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Dept. of Ece TN Chennai India AP Guntur India

ISBN: (纸本)9798350364729

This paper introduces a novel method for geometric reconstruction in remote sensing, combining LiDAR, SAR, deep lea0rning algorithms, and multi-sensor fusion. The proposed approach achieves a geometric reconstruction accuracy of 0.92, significantly higher than conventional methods, which average around 0.78. The method also reduces processing time to 28 seconds from the typical 45 seconds. By integrating LiDAR and SAR data, our approach enhances spatial feature extraction and reconstruction precision, making it highly effective for applications like urban planning, disaster response, and environmental monitoring. With an Intersection over Union (IoU) score of 0.88, the method demonstrates superior performance compared to traditional techniques. © 2024 IEEE.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

Composing Music Through Tile-based Games

Composing Music Through Tile-based Games

引用

2023 IEEE International Symposium on Multimedia, ISM 2023

作者： Laato, Samuli Rauti, Sampsa Espeseth, Alexander Sobke, Heinrich Hamari, Juho Buruk, Oguz 'Oz' Tampere University Gamification Group Tampere Finland University of Turku Department of Computing Turku Finland Kristiania University College School of Economics Innovation and Technology Kristiania Norway Faculty of Civil Engineering Bauhaus Universität Weimar Weimar Weimar Germany

ISBN: (纸本)9798350395761

In the realm of music we have multiple examples of successful rock stars, composers and producers who describe themselves as self-taught. This suggests there might be a demand in formal music education for learning technologies that support students' self-propelled discovery. In this theoretical work, we explore the design space of educational music composing games that would allow students to explore and learn music theory concepts at their leisure. We designed four unique tile-based music creation games based on popular contemporary video game genres, and evaluated them from the perspectives of learning and musical expression. This study opens up new avenues in music composing game design, and offers examples of some ways in which games can be harnessed as vehicles to learn music theory and composition. © 2023 IEEE.

关键词： Students

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：