检索结果-内蒙古大学图书馆

6th Parul International Conference on engineering and technology, PICET 2024

作者： Barhate, Aditya Kumar, Praveen Verma, Prateek Jikar, Nayan Tale, Abhay Hikre, Vaibhav Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India Department of Computer Science and Medical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Maharashtra Wardha India

ISBN: (纸本)9798350369748

Smart healthcare employs cloud computing, the Internet of Things (IoT), and supercomputers to manage the healthcare system. Medical data storage volume is increasing, necessitating the adoption of Machine Learning (ML) models for predicting outcomes, particularly in the treatment of chronic illnesses. The trend of care personalization and technological integration is highlighted by the development of ML applications for clinical decision support systems, including real-time predictive analytics. Predictive analytics applications employ ML and artificial intelligence (AI) to forecast patient risks, outcomes, and treatment responses. Predictive analytics is more important in healthcare when it comes to detecting Alzheimer's disease, cardiovascular events, radiology, and other conditions. Therefore, the current study highlights the change in illness identification, medical imaging, and personalized medication brought about by ML and Predictive Analytics in Precision Medicine (PM). However, ethical concerns and the deployment of transparent AI models still need more research. This study anticipates a time when healthcare will be quicker, better informed, and more patient-centered by using the insights provided by intelligent healthcare data. By effectively saving patient lives, the use of ML in healthcare ushers in a new era for the industry. © 2024 IEEE.

关键词： Disease Detection Machine Learning Medical Imaging Predictive Analytics Smart Healthcare

来源：评论

学校读者我要写书评

暂无评论

Research on Improved TDOA Algorithm for Shallow Water Underwater Positioning 16

Research on Improved TDOA Algorithm for Shallow Water Underw...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Shen, Biyue Rong, Shaowei Ji, Lingxian Wu, Kaiyuan Li, Jiaju Deng, Xiangyu Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Faculty of Artificial Intelligence Industry Kunming University of Science and Technology Kunming650500 China

ISBN: (纸本)9781510689251

Accurate positioning in shallow water regions is crucial for various underwater applications. TDOA algorithms estimate the signal source location by measuring the time differences of signal arrival at multiple receivers. However, these methods often suffer from Non-Line-of-Sight (NLOS) errors and noise, leading to reduced positioning accuracy in shallow water environments. This research proposes an improved TDOA estimation algorithm that utilizes cross-correlation techniques to mitigate NLOS errors and combines the strengths of the Chan and Taylor algorithms to enhance positioning precision. The proposed algorithm addresses challenges such as time ambiguity and alpha-stable noise, offering advantages in TDOA modeling for underwater positioning. Implementation details are provided, including the design of matching basis functions, time delay matching procedures, algorithm flow, and computational steps. Simulation tests validate the effectiveness of the algorithm, demonstrating significant improvements in positioning accuracy. The computational complexity is also analyzed to assess the algorithm's practicality. Finally, the research findings are summarized, and directions for future work are discussed. © 2025 SPIE.

关键词： Time difference of arrival

来源：评论

学校读者我要写书评

暂无评论

Wearable Biosensors: Transformative Innovations and Future Pathways for Continuous Health Monitoring 2

Wearable Biosensors: Transformative Innovations and Future P...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Thute, Trupti Gudadhe, Amit Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Department of Artificial Intelligence and Data Science Maharashtra Wardha India Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Department of Computer Science and Design Maharashtra Wardha India

ISBN: (纸本)9798331505745

Wearable biosensors are revolutionizing healthcare by enabling continuous monitoring of health status, transforming it from an event-based process to an ongoing one. When integrated with AI, nanotechnology, and IoMT (Internet of Medical Things), these devices enhance precision care, telediagnosis, and chronic disease management. Advancements in electrochemical, optical, and biochemical sensors, along with innovations in energy harvesting and miniaturized flexible materials, improve both the performance and comfort of these devices. Wearable biosensors are now crucial for everyday fitness, disease prediction, and the seamless exchange of data between m-health apps and EHRs. Despite these advancements, challenges remain, such as data security, system integration, and user incentives. Addressing these concerns through enhanced security features, standardized protocols, and user-focused designs is critical. The future development of wearable biosensors is aimed at leveraging cost-effective energy sources, utilizing AI for data analysis, and improving user convenience, making significant strides in preventive and personalized healthcare. © 2025 IEEE.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection in IoT Environment Using Crystal Optimized Deep Neural Network 1st

DDoS Attack Detection in IoT Environment Using Crystal Optim...

引用

1st International Conference on artificial intelligence of Things, ICAIoT 2023

作者： Karpagavalli, C. Suganya, R. Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam India Department of Information Technology Thiagarajar College of Engineering Madurai India

ISBN: (纸本)9783031487736

Internet of Things (IoT) is the interconnection of many devices through the internet for different real-time applications. One of the major issues of IoT is Distributed Denial of Service attack(DDoS) and many research works have been carried out to circumvent the DDoS attack;however, they failed to attain the accurate classification of DDoS and normal traffic. In context with this, we propose a novel Deep Neural Network (DNN) based Crystal Search algorithm (CSA) (DNN-CSA). The modified Multilayer Preceptor (MLP) based DNN enhances the classification outcomes. Prior to classification the data are collected by sniffer tool and preprocessed using the min-max approach. Experimental analyses are carried out to analyze the performance of our proposed approach and the results are compared with other state-of-art works. The proposed methodology offers better detection accuracy, precision, recall, and F1-score for DDoS attack detection and also effective results in terms of throughput, energy consumption, and memory utilization. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

REAL-TIME GLUCOSE MONITORING SYSTEM AND DIETARY RECOMMENDATIONS FOR DIABETES MELLITUS USING FOG COMPUTING

引用

Telecommunications and Radio engineering (English translation of Elektrosvyaz and Radiotekhnika) 2025年第5期84卷 55-67页

作者： Sathish, N. Elangovan, D. Nagalakshmi, R. Suresh, G. Chitra, Devi D. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Information Technology Saveetha Engineering College Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Artificial Intelligence and Data Science Kings Engineering College Sriperumbudur India Department of Computer Science And Engineering S.A. Engineering College Chennai India

This systematic review gave special attention to diabetes and the advancements in food and nutrition needed to prevent or manage diabetes in all its forms. There are two main forms of diabetes mellitus: Type 1 (T1D) and Type 2 (T2D). The loss of beta cells brought on by an autoimmune reaction causes the pancreas to be unable to produce enough insulin, which leads to Type 1 diabetes. A deficiency of insulin could arise as the illness worsens. The most frequent cause is a combination of excessive body weight and inadequate exercise. Currently, 90–95% of patients have Type 2 diabetes mellitus (T2DM). Age-specific normal blood sugar ranges exist and knowing them is crucial for determining a target blood sugar level that is both healthy and appropriate. The main takeaway is that diet regimens ought to be tailored to the patient’s requirements and should account for their capacity for change. Carbohydrates are the nutrients that have the biggest impact on the rise in blood glucose. In this paper, we have proposed a novel method for glucose monitoring and diet recommendations for diabetic patients using fog computing. A paradigm known as fog computing makes use of the benefits that come from using both cloud and edge devices to support modern computing systems by offering high-quality services, cutting latency, facilitating mobility, supporting multi-tenancy, and many other features. © 2025 by Begell House, Inc.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Improving AI-Based Skin Disease Classification with StyleGAN3 for Minority Skin Tone Generation 16

Improving AI-Based Skin Disease Classification with StyleGAN...

引用

16th Biomedical engineering International Conference, BMEiCON 2024

作者： Tanantong, Tanatorn La-Or-On, Pangon Srijiranon, Krittakom Thammasat University Research Thammasat University Unit in Data Innovation and Artificial Intelligence Faculty of Science and Technology Department of Computer Science Pathum Thani Thailand

ISBN: (纸本)9798331505431

Skin diseases are prevalent in Thailand due to the hot temperatures, humid climate, and increasing diversity of skin tones, which complicates diagnosis. artificial intelligence (AI) has improved skin disease detection through deep learning models, aiding faster diagnoses and reducing the workload on dermatologists. However, AI models often struggle with underrepresentation of darker skin tones in training datasets, affecting performance. To address this imbalance, data augmentation techniques like generative models are recommended. This research enhances skin disease classification using StyleGAN3 for data augmentation to balance minority skin tone classes. The Fitzpatrick17k dataset focusing on Acne, Psoriasis, and Vitiligo is used. The Fitzpatrick Skin Type Scale is reduced from six to three levels due to image availability. VGG16 is applied to classify skin tone classes. Two additional datasets, the original and traditionally augmented datasets, are used for comparison against the StyleGAN3-augmented dataset. Results show that the StyleGAN3-augmented dataset achieves the best performance with F1-scores of 0.7193, 0.7446, and 0.7543 and accuracy scores of 0.7200, 0.7368, and 0.7419 for Acne, Psoriasis, and Vitiligo respectively. The obtained results demonstrate that utilizing the StyleGAN3-augmented dataset for skin disease classification in minority skin tone classes yields the highest performance, with F1-scores increasing by 19.25%, 19.77%, and 25.94 % for Acne, Psoriasis, and Vitiligo, respectively. These findings highlight the effectiveness of StyleGAN3 in improving model performance for underrepresented skin tones in skin disease classification. © 2024 IEEE.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

YouTube Video Summarizer in Regional Language 3

YouTube Video Summarizer in Regional Language

引用

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Jadhav, Ranjana Damre, Prajwal Hire, Atharva Gosavi, Priti Deshmukh, Sanskruti Vishwakarma Institiute of Technology Department of Multidisciplinary Engineering Pune India Vishwakarma Institiute of Technology Department of Artificial Intelligence and Data Science Pune India

ISBN: (纸本)9798350396157

The idea and features of the proposed You Tube video summarizer tool created especially for regional languages is presented in this research study. Generally, it is a challenging task for viewers, who prefer regional languages to access and understand videos that are primarily available in a different language in YouTube. The proposed You Tube video summarizer in regional language attempts to overcome this challenge by offering a service to summarize videos in regional languages, making them easier for viewers who might not understand the original language of the video to access and comprehend. The developed program analyses and extracts important information from the video's audio or subtitles using natural language processing (NLP) and machine learning algorithms. This YouTube video summarizer in local languages has a wide range of potential uses. It can improve non-English speakers' access to information, improve video browsing, and promote effective content consumption in localized language groups. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Vision Transformer with Lion Optimizer for Accurate Classification of Monkeypox Skin Images 4

Enhanced Vision Transformer with Lion Optimizer for Accurate...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Bhatnagar, Roheet Hassan, Esraa Saber, Abeer Shams, Mahmoud Y. Elbedwehy, Samar Manipal University Jaipur Department of Computer Science and Engineering Rajasthan India Kafrelsheikh University Faculty of Artificial Intelligence Dept. of Machine Learning Kafrelsheikh33516 Egypt Damietta University Faculty of Computers and Artificial Intelligence Information Technology Dept. Damietta34517 Egypt Kafrelsheikh University Faculty of Artificial Intelligence Dept. of Data Science Kafrelsheikh33511 Egypt

ISBN: (纸本)9798350387490

Monkeypox is a contagious viral infection caused by the monkeypox virus (Mpoxvirus). Characterized by skin lesions, fever, respiratory difficulties, swollen lymph nodes, and neurological complications, MPX can be fatal. Recent outbreaks have spread the disease across Europe, Australia, the United States, and Africa. Traditionally diagnosed through PCR testing of skin lesions, this process poses significant risks to medical personnel due to potential exposure to the highly contagious virus. However, the usage artificial intelligence (AI) is revolutionizing diagnostics, providing a safer and more efficient approach to MPX detection. In this paper, a new AI technique based on vision transformer and lion optimizer for classifying Monkeypox Skin Images. The presented model used for classifying the dataset and results reached accuracy of 99.6%. © 2024 IEEE.

关键词： Classification Deep Learning Diagnosis Monkeypox

来源：评论

学校读者我要写书评

暂无评论

A Real TimeVehicle Detection Based on Modified Convolutional Neural Networks in Different Climate

A Real TimeVehicle Detection Based on Modified Convolutional...

引用

2023 IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： Johnson, Sandra Laxmi, B Prathusha R.M.K. Engineering College Department of Artificial Intelligence and Data Science Chennai India R.M.K. College of Engineering and Technology Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9781665462631

In order to effectively manage and monitor traffic on the roads, intelligent technologies must be able to detect and tally the number of cars on the road. The technology may be used for controlling and monitoring traffic in both urban areas and on highways, especially in times of heavy congestion or bad weather. It has traditionally been accomplished using sensor data and the standard toolkit for image processing. Recently however, with the help of deep learning-based smart computer vision systems, this process has become highly scalable and dependable. For intelligent traffic monitoring and management of issues like traffic congestion, the information gathered from various surveillance cameras may be utilized to train models that can recognize and track on-road cars, even in low-light and blurry situations brought on by bad weather. Although they all aim to solve the same problem, vehicle identification algorithms all have to deal with one or two very distinct cases. Vehicle detection under haze, dust, sandstorms, snow, and rain, as well as daytime and nocturnal conditions, is the focus of this study. The suggested design is based on the CNN architecture as a starting point, but it adds a spatial pyramid pooling layer and removes several of the Batch Normalization levels. During training, the system achieved an average accuracy of 81% and was able to identify even the tiniest vehicles in the scene. © 2023 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Harnessing Long Short Term Memory Networks for Stock Market Forecasts

Harnessing Long Short Term Memory Networks for Stock Market ...

引用

2024 International Conference on engineering and Computing, ICECT 2024

作者： Faheem, Alishba Arshad, Usama Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Faculty of Computer Science and Engineering Department of Artificial Intelligence Topi Pakistan

ISBN: (纸本)9798350349719

Stock market trend prediction is a classical re-gression problem with effects on stock exchange. This research is presenting a detailed exploration of how Long Short Term Memory (LSTM) networks may be used for predicting stock market trends. The LSTM model was employed instead of the conventional Recurrent Neural Networks (RNNs), to learn from historical financial data. The study examines the operations of the LSTM model and the optimization of hyper parameters that lead to accurate prediction outcomes from the given dataset. Our model gave encouraging results that underlined the LSTM model's prowess in capturing intricate temporal dependencies in data. The model's result were in a low Root Mean Square Error (RMSE) score and an impressively high accuracy level that were good indicators of the model's adaptability at trend identification. Our study amplifies the need for advanced machine learning algorithms like LSTM that increase prediction accuracy while offering insights into decision-making processes for both investors and financial analysts at the same time. Further, it also hints at the potential of deep learning within the stock market. The paper concludes by discussions on all possible improvements to the existing model, future directions, and how incorporating additional data types can increase our predictive accuracy. This research primarily underscores the significant role LSTM plays in deciphering complex financial data trends accurately. © 2024 IEEE.

关键词： Long short-term memory

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：