检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Fan Ji, Naye Gao, Fuxing Zhao, Siyuan Wang, Zhaohan Li, Shunman The Faculty of Humanities and Arts Macau University of Science and Technology China The College of Media Engineering Communication University of Zhejiang China Research Center for Artificial Intelligence and Fine Arts Zhejiang Lab Zhejiang China The School of Animation and Digital Arts Communication University of China Beijing China Zhejiang Institute of Economics and Trade Zhejiang China

The generation of co-speech gestures for digital humans is an emerging area in the field of virtual human creation. Prior research has made progress by using acoustic and semantic information as input and adopting classify method to identify the person’s ID and emotion for driving co-speech gesture generation. However, this endeavour still faces significant challenges. These challenges go beyond the intricate interplay between co-speech gestures, speech acoustic, and semantics;they also encompass the complexities associated with personality, emotion, and other obscure but important factors. This paper introduces "diffmotionv2," a speech-conditional diffusion-based and non-autoregressive transformer-based generative model with WavLM pre-trained model. It can produce individual and stylized full-body co-speech gestures only using raw speech audio, eliminating the need for complex multimodal processing and manually annotated. Firstly, considering that speech audio not only contains acoustic and semantic features but also conveys personality traits, emotions, and more subtle information related to accompanying gestures, we pioneer the adaptation of WavLM, a large-scale pre-trained model, to extract low-level and high-level audio information. Secondly, we introduce an adaptive layer norm architecture in the transformer-based layer to learn the relationship between speech information and accompanying gestures. Extensive subjective evaluation experiments are conducted on the Trinity, ZEGGS, and BEAT datasets to confirm the WavLM and the model’s ability to synthesize natural co-speech gestures with various styles. © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Water Management and Monitoring System in Residential Building

Mobile Application for Water Management and Monitoring Syste...

引用

International Conference on Futuristic Technologies (INCOFT)

作者： Nalla Akhila Aswadhati Sirisha P. Dass P M Dinesh T Sujatha Amit Kamalakar Gaikwad Computer Science and Engineering Aditya Engineering College Surampalem Jawaharlal Nehru technological university Kakinada Kakinada East Godavari district Information Technology (IT) Department Vignans institute of information technology (A) Duvvada India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Department of ECE Sona College of Technology Salem Department of Artificial Intelligence and Data Science Sri Krishna College of Engineering and Technology Coimbatore Department of Computer Science G.H.Raisoni University Amravati Maharashtra

Water scarcity is one of the major threats to human society. Though there are many reasons for water scarcity like water pollution, drought and global warming, overuse of domestic water is one of the major causes of water scarcity. More than one billion people are deprived of clean drinking water and water for other purposes. One of the main solutions that were found to this problem is rainwater harvesting. Many countries encouraged the citizens to collect the rainwater for further uses. Though the rainwater is preserved, another issue named water over usage comes into existence. Most of the time, the water supplied for domestic reasons may undergo several preprocessing like filtration, osmosis, etc. to ensure the cleanliness of the water. When this water is wasted for petty reasons like washing dishes and watering plants, it may lead to the shortage of freshwater for necessary needs like cattle feeding, food production, farming, etc. Many researchers and scientists have found a lot of techniques and processes to minimize the usage of fresh water in households. This project aims the development of a mobile application that constantly monitors the water usage by a house in a community. There will be a prefixed value for the amount of water each house can use. If the water usage exceeds the prefixed value, the inmates of the house are asked to pay a certain fine amount which is calculated by the number of extra liters used and the prefixed fine amount for each liter. If the fine amount was not paid, the water supply to that particular house will be blocked. All of the above-mentioned processes are monitored by this application. Hardware components like multiple sensors, adaptors, motors are used for this purpose. The whole working of the hardware is controlled by a microcontroller namely Arduino Uno. This application helps in the control of the over usage of water in residential buildings. This can be equipped in apartments, community houses, quarters, etc. to constan

关键词： Microcontrollers Buildings Production Water pollution Hardware Osmosis Sensors

来源：评论

学校读者我要写书评

暂无评论

Fashionable Four Wheeler Parking to Reduce the Human Intervention and to Enhance the Flexibility in Parking System Using IoT

Fashionable Four Wheeler Parking to Reduce the Human Interve...

引用

Innovative Practices in technology and Management (ICIPTM), International Conference on

作者： Manoj P Varun C M Keerthi Kumar N Pradip Padhye K. Aruna Kumari Puja Das Swagata Sarkar Department of Civil Engineering Vidyavardhaka College of Engineering Mysore India Department of Computer Science and business system R.M.K. Engineering College Kavaraipettai India Department of Mechanical Engineering BMS Institute of Technology and Management Bengaluru India School of Management Dr. Vishwanath Karad MIT World Peace University Pune India Department of Mathematics Gitam University Visakhpatanam India Department of Computer science Hiralal Mazumder Memorial college for Women Kolkata India Department of Artificial Intelligence and Data Science Sri Sai Ram Engineering College Chennai India

Due to the lack of a mechanism in place to check online for parking availability, it is now quite difficult to find a parking spot in congested regions. Imagine being able to access information about parking slot availability on your phone and not having to move around to do so. The cutting-edge parking system powered by IoT can overcome this issue. The IoT-based parking system makes it simple to check the availability of parking spaces online. With the aid of this device, the parking system might be fully automated. You might have automatic admission, payment, and exit processes. A NodeMCU-based IOT-based car parking system is being created using five IR sensors, two servo motors, and NodeMCU. Three IR sensors are utilised to determine whether parking spaces are available, and two IR sensors are used at the entry and exit gates to identify vehicles. Based on the sensor value, servo motors control the gates' opening and closing. In this part, we'll show you how to upload data to the cloud that is reachable from anywhere using the Adafruit IO platform.

关键词： Space vehicles Technological innovation Motor drives Cloud computing Costs Logic gates Sensor systems

来源：评论

学校读者我要写书评

暂无评论

Sliding Flexoelectricity in Two-Dimensional van der Waals Systems

arXiv

引用

arXiv 2024年

作者： He, Ri Wang, Hua Deng, Fenglin Gao, Yuxiang Zhang, Binwen Shi, Yubai Li, Run-Wei Zhong, Zhicheng Key Laboratory of Magnetic Materials Devices Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China Center for Quantum Matter School of Physics Zhejiang University Hangzhou310058 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China Fujian Key Laboratory of Functional Marine Sensing Materials Center for Advanced Marine Materials and Smart Sensors College of Material and Chemical Engineering Minjiang University Fuzhou350108 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China School of Future Technology University of Chinese Academy of Sciences Beijing100049 China School of Artificial Intelligence and Data Science University of Science and Technology of China Suzhou215123 China

Two-dimensional sliding ferroelectrics, with their unique stacking degrees of freedom, offer a different approach to manipulate polarization by interlayer sliding. Bending sliding ferroelectrics inevitably leads to interlayer sliding motion, thus altering stacking orders and polarization properties. Here, by using machine-learning force field, we investigate the effects of bending deformation on geometries, stackings, energies, and polarizations in sliding ferroelectric bilayer h-BN and 3R-MoS2. We predict that bent ferroelectric bilayer forms irreversible kinks instead of arc when the bending angle exceeds a critical value. We demonstrate that the kinks originate from the competition between bending energy and interlayer van der Waals energy. The kink contains a ferroelectric domain wall that reverses the polarization, effectively inducing a flexoelectric effect. We term this phenomenon "sliding flexoelectricity" to distinguish it from conventional strain-gradient-induced flexoelectricity. Copyright © 2024, The Authors. All rights reserved.

关键词： Van der Waals forces

来源：评论

学校读者我要写书评

暂无评论

Exploring Nanoscale Perovskite Materials for Next‑Generation Photodetectors:A Comprehensive Review and Future Directions

引用

Nano-Micro Letters 2025年第2期17卷 46-108页

作者： Xin Li Sikandar Aftab Maria Mukhtar Fahmid Kabir Muhammad Farooq Khan Hosameldin Helmy Hegazy Erdi Akman State Key Laboratory of Pulsed Power Laser Technology National University of Defense TechnologyHefei 230037AnhuiPeople’s Republic of China Anhui Laboratory of Advanced Laser Technology Hefei 230037AnhuiPeople’s Republic of China Nanhu Laser Laboratory Changsha 410015HunanPeople’s Republic of China Department of Semiconductor Systems Engineering and Clean Energy Sejong UniversitySeoul 05006Republic of Korea Department of Artificial Intelligence and Robotics Sejong UniversitySeoul 05006Republic of Korea School of Engineering Science Simon Fraser UniversityBurnabyBC V5A 1S6Canada Department of Electrical Engineering Sejong UniversitySeoul 05006South Korea Department of Physics Faculty of ScienceKing Khalid UniversityP.O.Box 9004AbhaSaudi Arabia Central Labs King Khalid UniversityAlQura’aP.O.Box 96061413 AbhaSaudi Arabia Scientific and Technological Research and Application Center Karamanoglu Mehmetbey University70100 KaramanTurkey

The rapid advancement of nanotechnology has sparked much interest in applying nanoscale perovskite materials for photodetection *** materials are promising candidates for next-generation photodetectors(PDs)due to their unique optoelectronic properties and flexible synthesis *** review explores the approaches used in the development and use of optoelectronic devices made of different nanoscale perovskite architectures,including quantum dots,nanosheets,nanorods,nanowires,and *** a thorough analysis of recent literature,the review also addresses common issues like the mechanisms underlying the degradation of perovskite PDs and offers perspectives on potential solutions to improve stability and scalability that impede widespread *** addition,it highlights that photodetection encompasses the detection of light fields in dimensions other than light intensity and suggests potential avenues for future research to overcome these obstacles and fully realize the potential of nanoscale perovskite materials in state-of-the-art photodetection *** review provides a comprehensive overview of nanoscale perovskite PDs and guides future research efforts towards improved performance and wider applicability,making it a valuable resource for researchers.

关键词： Nanoscale perovskites Photodetectors Nanosheets Nanorods Nanowires Quantum dots Nanocrystals

来源：评论

学校读者我要写书评

暂无评论

IoT based on Smart Traffic Lights and Streetlight System

IoT based on Smart Traffic Lights and Streetlight System

引用

International Conference on Edge Computing and Applications (ICECAA)

作者： Shobana S Shakunthala M C. Vimala Josphine M. Theodore Kingslin S. Sivarajan Chairma Lakshmi K R Department of Information Technology R.M.K Engineering College Chennai India Department of Electronics and Communication Engineering R.M.D Engineering College Chennai Department of Artificial Intelligence and Data Science R.M.K Engineering College Chennai Department of Electronics and Communication Engineering R.M.K College of Engineering College & Technology Department of Electrical and Electronics Engineering Veltech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Department of Electronics and Instrumentation Engineering R.M.K. Engineering College Chennai India

Energy wastage, traffic jams, and traffic monitoring are the three main problems the world's population is confronting. The traditional roadway management method is ineffective at controlling the flow of traffic when one lane has significantly more traffic than the others. Additionally, the present street light controller uses lights that are not turned off in the morning even though it is sufficiently light outside and that are turned on in the late afternoon before even the sun sets, which causes some power loss. This proposed system will offer an advanced smart traffic management system and intelligent street lighting system to bring a standardized approach to solving this issue. The enhanced smart traffic control system is accomplished by modifying the signal timings based on the comparison of the densities on all roads, i.e., when a specific lane has much more density compared to the other lanes, that specific lane is modified to a green signal for a specified length of time. By computerizing solar-powered street lights with IoT, energy wastage in the traditional street lighting system is prevented. The street lights are activated whenever an item moves, or they remain off otherwise. This proposed method reduces traffic issues, and energy wastage and improves the traffic monitoring process also.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge Enhancement using Question Generation for Images and Chart data Input

Knowledge Enhancement using Question Generation for Images a...

引用

artificial intelligence and Speech technology (AIST), International Conference on

作者： Devendra Kumar Tayal Amita Jain Nikita Shrivastava Akshita Jain Hunny Gaur Department of Computer Science & Engineering Indira Gandhi Delhi Technical University for Women Delhi India Department of Computer Science & Engineering Netaji Subhash University of Technology Delhi India Department of Artificial Intelligence & Data Science Indira Gandhi Delhi Technical University for Women Delhi India Department of Computer Science St. Stephen’s College University of Delhi Delhi India

In the current era, pictorial representation of data in the form of patterns, charts, graphs and trends are gaining a lot of attention in the fields of finance and science. Deep and correct study of the trends going on is necessary to better one's financial and general knowledge and helps reading and comparing the patterns over a period of time. Correct understanding of the pictorial representation of data in the form of line charts, bar charts or any textual representation is a major task. Hence, the proposed method aims at reading these charts and images, converting them into text and generating questions and then using sentiment analysis to determine positive or negative trends. This is followed by generating commonly asked questions based on the extracted text and providing more context and information on this text using web crawling, which helps provide greater dimensionality and understanding of the problem at hand.

关键词： Sentiment analysis Finance Speech enhancement Market research data mining Task analysis artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Cloud-Driven Autonomous Drones for Dynamic Emergency Medical Response Using Convolutional Neural Networks

Cloud-Driven Autonomous Drones for Dynamic Emergency Medical...

引用

Smart Technologies for Sustainable Development Goals (ICSTSDG), International Conference on

作者： P. Karthikeyani D. David Neels Ponkumar S. Hemalatha M. Tamilselvam M. Muthulekshmi C. Dhanesh Department of Computer Science Thanthai Hans Roever College (Autonomous) Perambalur Tamil Nadu India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Tagore Engineering College Chennai India Department of Civil Engineering Vinayaka Mission's Kirupananda Variyar Engineering College Vinayaka Mission's Research Foundation (Deemed to be University) Salem Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Mechanical Engineering S.A. Engineering College (Autonomous) Chennai Tamil Nadu India

ISBN: (数字)9798331516284

ISBN: (纸本)9798331516291

This research presents an innovative method for improving emergency medical response by using autonomous drones powered by Convolutional Neural Networks (CNNs) and controlled by cloud computing. The proposed system incorporates advanced technology to speed up help delivery in emergency conditions requiring rapid medical intervention. Using CNNs, drones can detect and recognize objects in real-time, vital for quickly diagnosing life-threatening medical emergencies. Drones can make quick decisions and navigate themselves using the vast computer capacity made available by cloud computing. The system uses dynamic routing algorithms to maximize drone deployment and respond quickly to changing emergency dynamics. The experimental results demonstrate the framework's effectiveness and scalability, highlighting its capacity to transform emergency medical care. The system's seamless integration image processing shows an enormous step forward in enhancing emergency response capabilities. Drones may now effectively provide lifesaving help by navigating complicated situations autonomously, made possible by the combination of advanced technology. It presents a viable route for improving outcomes in critical conditions by employing AI-driven drones for dynamic emergency medical intervention.

关键词： Measurement Cloud computing Navigation Heuristic algorithms Medical services Routing Real-time systems Convolutional neural networks Medical diagnostic imaging Drones

来源：评论

学校读者我要写书评

暂无评论

HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN

arXiv

引用

arXiv 2023年

作者： Islam, Md Shofiqul Hasan, Khondokar Fida Sultana, Sunjida Uddin, Shahadat Lio', Pietro Quinn, Julian M.W. Moni, Mohammad Ali Faculty of Computing Universiti Malaysia Pahang Gambang Pahang Kuantan26300 Malaysia Lebuhraya Tun Razak Gambang Pahang Kuantan26300 Malaysia 2 George Street Brisbane4000 Australia Department of Computer Science and Engineering Islamic University Kushtia7600 Bangladesh School of Project Management Faculty of Engineering The University of Sydney Sydney Australia Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Bone Research Group The Garvan Institute of Medical Research DarlinghurstNSW Australia Artificial Intelligence & Data Science School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St LuciaQLD4072 Australia

Deep learning-based models have achieved significant success in detecting cardiac arrhythmia by analyzing ECG signals to categorize patient heartbeats. To improve the performance of such models, we have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. This solves problems that arise when traditional dilated convolutional neural network (CNN) models disregard the correlation between contexts and gradient dispersion. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU-BiLSTM) architecture to generate fusion features. As a result of incorporating both local and global feature information and an attention mechanism, the model's performance for prediction is improved. By combining the fusion features with a dilated CNN and a hierarchical attention mechanism, the trained HARDC model showed significantly improved classification results and interpretability of feature extraction on the PhysioNet 2017 challenge dataset. Sequential Z-Score normalization, filtering, denoising, and segmentation are used to prepare the raw data for analysis. CGAN (Conditional Generative Adversarial Network) is then used to generate synthetic signals from the processed data. The experimental results demonstrate that the proposed HARDC model significantly outperforms other existing models, achieving an accuracy of 99.60%, F1 score of 98.21%, a precision of 97.66%, and recall of 99.60% using MIT-BIH generated ECG. In addition, this approach substantially reduces run time when using dilated CNN compared to normal convolution. Overall, this hybrid model demonstrates an innovative and cost-effective strategy for ECG signal compression and high-performance ECG recognition. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise. © 2023, CC BY.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Generic ESD Generator Model using artificial Neural Network

Generic ESD Generator Model using Artificial Neural Network

引用

EMC/SI/PI and EMC Europe Symposium, IEEE International Joint

作者： Jawad Yousaf Kamran Javed Mohammed Ghazal Abu Dhabi University Abu Dhabi United Arab Emirates Saudi Data and Artificial Intelligence Authority (SDAIA) National Centre for Artificial Intelligence (NCAI) Riyadh Saudi Arabia Faculty of Computer Sciences and Engineering Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Topi Pakistan

Different commercial ESD gun models, although complying with the standard ESD waveform requirements in terms of rise time and current values for standard Pellegrini target, produce different ESD waveforms. The variations of the ESD source and target impedance in real-time with the change in the gun model affects the ESD susceptibility compliance testing results and immunity analysis for the estimation of possible ESD failure in a product. This study presents, for the first time, a novel generic ESD generator model using artificial neural network (ANN) based deep learning techniques. The developed deep learning model incorporates the characteristics of the real-time generated ESD waveforms by various commonly used commercial ESD gun models with different target load impedances. The presented model could be used as a generic ESD source for fast ESD susceptibility and immunity testing’s at the design stage of a product using numerical or circuit-analysis-based tools.

关键词： Deep learning artificial neural networks Immunity testing Electrostatic discharges Generators Real-time systems Numerical models

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：