检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Kaji, Hotaka Mori, Fumito Ito, Hiroshi Faculty of Design Kyushu University Fukuoka Japan Education and Research Center for Mathematical and Data Science Kyushu University Fukuoka Japan

Circadian rhythms are biological rhythms of approximately 24 h that persist even under constant conditions without environmental daily cues. The molecular circadian clock machinery generates the physiological rhythms, which can be transmitted into the downstream output system. Owing to the stochastic nature of the biochemical reactions, the oscillation period of circadian rhythms exhibited by individual organisms or cells is not constant on a daily basis with variations as high as 10 % in terms of the coefficient of variation. Although the fluctuations in circadian rhythm is measured through a reporter such as bioluminescence or fluorescence, experimentally confirming whether the fluctuations found in the reporter system are the same as those in the clock itself is challenging. This study numerically and analytically investigated a coupled system of a circadian clock and its output system, and then compared the fluctuations in the oscillation period of the two systems. We found that the amount of fluctuation in the output system is smaller than that in the circadian clock when the degradation rate of the molecules responsible for the output system was at typical values. The results obtained imply that the output system improves the accuracy of the circadian rhythm without the need for any special denoising processes. © 2022, CC BY.

关键词： Machinery

来源：评论

学校读者我要写书评

暂无评论

Prediction of Heart Disease Using Machine Learning Algorithms

Prediction of Heart Disease Using Machine Learning Algorithm...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Rushikesh Burle Sanskruti Gaurkhede Leelkanth Dewangan Utkarsha Pacharaney Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Computer Science And Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

In India, heart disease claims the lives of about one person every day. The human body's most vital organ is the heart. The heart has two primary purposes: first, it gathers blood from body tissues and pumps it to the lungs; second, it gathers blood from the lungs and pumps it to all body *** disease has claimed the lives of many people. Predicting that disease at the appropriate moment is crucial, for this reason. Making use of machine learning Additionally, illnesses are easily identified and anticipated. It also covers the use of many algorithms on the Heart Disease dataset. The dataset used in this research was obtained from Kaggle. Analyzing fundamental machine learning algorithms for the prediction of heart disease, such as Random Forest, K-Nearest Neighbours, Decision Tree Classifier, and Support Vector Machine, is the primary goal of this study. Our Acquired Model for The Decision Tree Classifier has a score of 79.0%. And the Random Forest Classifier has an 84.0% score. With a linear kernel, the Support Vector Classifier scores 83.0%. Next, K Neighbours Classifier~ outperformed all previously employed methods, achieving the maximum score of {87%} with ~8 nearest result. RF (Random Forest), K-Nearest Neighbours Algorithm, and Decision Tree, together with Python programming and Visual Studio, which excels at both data and code.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Parkinson's Disease Detection Through Machine Learning Techniques

A Comprehensive Study on Parkinson's Disease Detection Throu...

引用

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： Rushikesh Burle Sanskruti Gaurkhede Bhushan Fulkar Swapnil Gundewar Utkarsha Pacharaney Prateek Verma Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Computer science And Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Mahartashtra India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

One of the biggest issues with worldwide public health is Parkinson's disease (PD). It is usually known that about are around one million Americans who have Parkinson's disease, whereas there are approximately five million cases of the condition globally. As a result, it's critical to identify Parkinson's disease early on and make the appropriate treatment plans. These days, machine learning is essential for analysing problems in real time and offering answers thanks to its widely used algorithms. These days, machine learning algorithms are used in the healthcare industry to identify patients' health problems. This research went into great detail about the methods used using algorithms that use machine learning to classify Parkinson's disease. A fault in the brain cells that generate dopamine, a necessary chemical for synapses to connect with one another, is the cause of Parkinson's disease. The brain's dopamine-producing neurons are in charge of control, flexibility, and event familiarity. When 60–80% of these cells disappear, inadequate dopamine is produced, which causes Parkinson's disease symptoms to manifest. In this case, the Random Forest, Decision Tree, K-Nearest Neighbours, and Support Vector Machine techniques were used to identify the illness. Compared to Decision Tree and Support Vector Machine, Random Forest and K-Nearest Neighbours offer the best performance.

关键词： Support vector machines Machine learning algorithms Parkinson's disease Vectors Real-time systems Classification algorithms Decision trees

来源：评论

学校读者我要写书评

暂无评论

The Impact of 5G Technology on the Functionality and Performance of Internet of Things (IoT) Devices

The Impact of 5G Technology on the Functionality and Perform...

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Prajyot Yesankar Palash Gourshettiwar Pradnyawant Gote Moses Makuei Jiet Ayush Gadkari Department of Computer Science & Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Wardha Maharashtra India Department of Computer Science & Medical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Wardha Maharashtra India Department of Artificial Intelligence & Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Wardha Maharashtra India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

The design of wireless mobile devices of the next generation 5G promises to address the demands of complex IOT designs in terms of connectivity technologies. This The study illuminates the architecture, benefits, and needs that5G can satisfy. drawbacks of the 5G network. Numerous sites throughout the world have conducted extensive analyses of IOT devices with 5G capabilities and research on this kind of network. A new era of communication has begun with the introduction of 5G technology, which promises unheard of velocity, low latency, and enormous capacity. The significant effects of 5G on the operation and efficiency of connected Internet of Things (IoT) gadgets are examined in this research. IoT devices stand to gain from improved communication capabilities as 5G networks proliferate, opening the door for creative applications in a variety of industries. The first section of the article gives a summary of the main characteristics of 5G technology, highlighting how it has the potential to completely change how Internet of Things devices interact and communicate. Real-time data transfer is made possible by 5G networks far lower latency and higher capacity, which open up possibilities for faster and smooth interactions between IoT *** report also explores how 5G may affect how much electricity Internet of Things devices use. 5G has the ability to solve a long-standing issue in the IoT ecosystem by extending the life of the batteries of IoT devices with the adoption of cost-effective communication protocols and increased network efficiency. A solution that can efficiently handle enormous volumes of information being transferred at very high capacity is required as the Internet of Things gains popularity One of the main demands or goals that need to be reached in the near future, or the next generation of IOT devices, is more capacity, a faster data transfer speed and less delay.

关键词： Wireless communication Performance evaluation Protocols 5G mobile communication data transfer Real-time systems Mobile handsets Internet of Things Low latency communication Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Brain Connectivity Using Deep Learning Algorithms

Brain Connectivity Using Deep Learning Algorithms

引用

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Moses Makuei Jiet Aahash Kamble Chetan Gajanan Puri Prateek Verma Department of Computer Science & Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Wardha Maharashtra India Department of Artificial Intelligence & Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Wardha Maharashtra India

The integration of deep learning into the examination of brain connectivity marks a transformative era in understanding neural networks. This article provides a concise overview of the burgeoning field of deep learning in brain connectivity analysis. It defines the concept, explores functional and structural connectivity, outlines practical applications, delves into the algorithms involved, compares traditional methods vs advanced deep learning approaches for brain connectivity and highlights its revolutionary impact in clinical practice. In deep learning, brain connectivity investigates neural links using advanced artificial intelligence. Functional connectivity, powered by deep neural networks, reveals patterns in brain activity linked to cognition, emotion, and decision-making. Structural connectivity, often utilizing graph neural networks, reconstructs intricate neural pathways. This technology shows significant progress in diagnosing conditions like Alzheimer's, schizophrenia, and autism. As it evolves, its clinical importance becomes evident, offering early disease detection, tailored treatments, and a deeper understanding of neurological disorders. Beyond clinical applications, deep learning in brain connectivity opens avenues for advancements in brain-computer interfaces, enhanced rehabilitation therapies, and precise interventions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regression models for the prediction of the influence of magnesium ions on primary endothelial cell (HUVEC) proliferation and migration

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2711-2718页

作者： Heike Helmholz Redon Resuli Marius Tacke Jalil Nourisa Sven Tomforde Roland Aydin Regine Willumeit-Römer Berit Zeller-Plumhoff Institute of Metallic Biomaterials Helmholz-Zentrum Hereon Geesthacht Germany Institute of Material Systems Modeling Helmholz-Zentrum Hereon Geesthacht Germany Department of Computer Science Faculty of Engineering Kiel University Kiel Germany Institute for Continuum and Material Mechanics Hamburg University of Technology Hamburg Germany Kiel Nano Surface and Interface Science - KiNSIS Kiel University Germany Data-driven Analysis and Design of Materials Faculty of Mechanical Engineering and Marine Technologies University of Rostock Germany Department Life Light & Matter Interdisciplinary Faculty University of Rostock Germany

Angiogenesis is one of the first stages in fracture healing and bone repair. Therefore, numerous studies evaluating the effect of Mg as a promising degradable, metallic biomaterial on the proliferation and function of endothelial cells have been performed. However, these studies lack methodological homogeneity and therefore differ in fundamental conclusions. Here, Mg-concentration-, donor- and cell age- dependent relations to primary human umbilical cord vein endothelial cells (HUVEC) proliferation and migration were investigated systematically. The generated data were utilized to develop regression models in order to assess and predict the cell response on Mg exposition in a concentration range of 2–20 mM Mg in cell culture medium extract. A concentration of > 2 mM already induced a detrimental effect in the sensitive primary HUVECs. Molecular data quantifying angiogenesis markers supported this finding. An increased migration capacity has been observed at a concentration of 10 mM Mg. We compared linear regression, random forests, support vector machines, neural networks and large language models for the prediction of HUVEC proliferation for a number of scenarios. Using these machine learning methods, we were able to predict the proliferation of HUVECs for missing Mg concentrations and for missing passages with mean absolute errors below 10 % and as low as 8.5 %, respectively. Due to strong differences between the cell behaviour of different donors, information for missing donors can be predicted with mean absolute errors of 15.7 % only. Support vector machines with linear kernel performed best on the tested data, but large language models also showed promising results.

关键词： Regression models HUVEC Cell proliferation Large Language Model

来源：评论

学校读者我要写书评

暂无评论

Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Test

arXiv

引用

arXiv 2023年

作者： Khojasteh, Behnam Solowjow, Friedrich Trimpe, Sebastian Kuchenbecker, Katherine J. Stuttgart Germany The Faculty of Engineering Design Production Engineering and Automotive Engineering University of Stuttgart Stuttgart Germany The Institute for Data Science in Mechanical Engineering RWTH Aachen University Aachen Germany MPI-IS Stuttgart Germany

Machine learning and deep learning have been used extensively to classify physical surfaces through images and time-series contact data. However, these methods rely on human expertise and entail the time-consuming processes of data and parameter tuning. To overcome these challenges, we propose an easily implemented framework that can directly handle heterogeneous data sources for classification tasks. Our data-versus-data approach automatically quantifies distinctive differences in distributions in a high-dimensional space via kernel two-sample testing between two sets extracted from multimodal data (e.g., images, sounds, haptic signals). We demonstrate the effectiveness of our technique by benchmarking against expertly engineered classifiers for visual-audio-haptic surface recognition due to the industrial relevance, difficulty, and competitive baselines of this application;ablation studies confirm the utility of key components of our pipeline. As shown in our open-source code, we achieve 97.2% accuracy on a standard multi-user dataset with 108 surface classes, outperforming the state-of-the-art machine-learning algorithm by 6% on a more difficult version of the task. The fact that our classifier obtains this performance with minimal data processing in the standard algorithm setting reinforces the powerful nature of kernel methods for learning to recognize complex patterns. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning In Autonomous Cars To Preventing Road Accident

Deep Reinforcement Learning In Autonomous Cars To Preventing...

引用

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Rushikesh Thote Aditya Barhate Abhay Tale Prateek Verma Department of Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

The integration of autonomous vehicles (AVs) into modern transportation systems presents both unprecedented opportunities and challenges, particularly in ensuring road safety and reducing accidents. This paper explores the application of Deep Reinforcement Learning (DRL) techniques to enhance decision-making processes in AVs, aiming to proactively prevent road accidents. By simulating complex driving environments, DRL algorithms enable AVs to learn optimal driving strategies through continuous interaction and feedback. We introduce a DRL-based framework that incorporates sensor data fusion, real-time environment analysis, and adaptive control mechanisms. Experimental results from simulated urban and highway scenarios demonstrate a significant reduction in collision rates and improved response to unforeseen obstacles compared to traditional rule-based systems. The findings underscore the potential of DRL in fortifying the reliability and safety of autonomous driving technologies.

关键词： Road accidents Reviews Decision making Transportation Transforms Deep reinforcement learning Road safety Safety Reliability Stress

来源：评论

学校读者我要写书评

暂无评论

Robust AI-Synthesized Image Detection via Multi-feature Frequency-aware Learning

arXiv

引用

arXiv 2025年

作者： Cai, Hongfei Liu, Chi Shen, Sheng Qu, Youyang Gui, Peng Faculty of Data Science City University of Macau China Design and Creative Technology Vertical Torrens University Australia NSW Australia Shandong Provincial Key Laboratory of Computer Networks Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

The rapid progression of generative AI (GenAI) technologies has heightened concerns regarding the misuse of AI-generated imagery. To address this issue, robust detection methods have emerged as particularly compelling, especially in challenging conditions where the targeted GenAI models are out-of-distribution or the generated images have been subjected to perturbations during transmission. This paper introduces a multi-feature fusion framework designed to enhance spatial forensic feature representations with incorporating three complementary components, namely noise correlation analysis, image gradient information, and pretrained vision encoder knowledge, using a cross-source attention mechanism. Furthermore, to identify spectral abnormality in synthetic images, we propose a frequency-aware architecture that employs the Frequency-Adaptive Dilated Convolution, enabling the joint modeling of spatial and spectral features while maintaining low computational complexity. Our framework exhibits exceptional generalization performance across fourteen diverse GenAI systems, including text-to-image diffusion models, autoregressive approaches, and post-processed deepfake methods. Notably, it achieves significantly higher mean accuracy in cross-model detection tasks when compared to existing state-of-the-art techniques. Additionally, the proposed method demonstrates resilience against various types of real-world image noise perturbations such as compression and blurring. Extensive ablation studies further corroborate the synergistic benefits of fusing multi-model forensic features with frequency-aware learning, underscoring the efficacy of our approach. © 2025, CC BY-NC-SA.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Open Government data (OGD) Framework for Sustainable Development

Open Government Data (OGD) Framework for Sustainable Develop...

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Maria Fasli Amani Yousef Owda Tufail Abbasi Majdi Owda Lampros Stergioulas Bhanu Neupane University of Essex School of Computer Science and Electronic Engineering Colchester UK Faculty of Graduate Studies Arab American University Ramallah West Bank Palestine Faculty of IT & Design The Hague University of Applied Sciences The Hague The Netherlands Faculty of Data Science Arab American University Ramallah West Bank Palestine UNESCO Information and ICT & Sciences Paris France

In the last few years, we have seen the production of data via companies, organizations, or even directly by citizens/consumers increase exponentially. In this new era where almost every aspect of human activity entails the production and consumption of data, Governments play a key role in leading the way to opening up data to stimulate innovation, but also to facilitate transparency and accountability. In this paper, we advocate for this critical role that Governments have to play and the need for a concerted effort in providing a guiding framework to support the opening up of Government data for the wider benefit of society, but in particular to support the Sustainable Development Goals (SDGs). The SDGs, a universal call to action to end poverty, safeguard the planet, and promote prosperity for everyone, are inextricably linked to the appropriate use and dissemination of data. By using the potential of accessible government data, we not only advance the SDGs but also create a more fair and sustainable future for all.

关键词：

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：