检索结果-内蒙古大学图书馆

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Jamil, Ishat Raihan Humaira, Mayeesha Department of Mechanical Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh

AHMERS, active health monitoring and emergency response system, is a mobile application-based system that wirelessly connects to a smartwatch to constantly monitor the human body and respond to sudden changes in vital data, in case of emergency. This app monitors heartbeat rate, blood oxygen saturation, body temperature, and compares them with pre-set normal values. If the data deviates or the user presses one of the emergency switches, the app immediately asks the person if he/she is ok. If the person fails to respond within a few seconds to the "Are you ok?" message, the app continues to send out distress signals to pre-set phone numbers and server along with the person's altitude, latitude and longitude, and current location on the map so that help can be sent quickly. It can determine whether a person is suffering from a health-related problem such as heart failure, Corona virus infection, hypothermia, etc. © 2023 The Authors. Published by Elsevier B.V.

关键词： Blood Oxygen Saturation Body Temperature Health Monitoring Heart Rate

来源：评论

学校读者我要写书评

暂无评论

Advancing Mars Exploration: Development of a Large-Scale Gravity Compensation System for Landers during Descent

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 6697-6710页

作者： Sun, Haining Tang, Xiaoqiang Ge, Shuzhi Sam Agency for Science Technology and Research Singapore Institute of Manufacturing Technology 138634 Singapore Tsinghua University State Key Laboratory of Tribology Department of Mechanical Engineering Beijing100084 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore

As space exploration advances, an increasing number of planets are becoming targets for landing missions. Before officially launching a lander, it is essential to conduct landing tests on Earth to verify the functionality of the lander. One key challenge is to simulate the target planet's gravity environment during the lander's descent. In this study, a large-scale gravity compensation system is developed to physically simulate the Martian gravity for the landing tests of a Mars lander. The system integrates a constant force mechanism and electronic control systems, working closely to ensure smooth transitions between working states during the landing tests. Based on the principle of minimum potential energy, an expression for the output force of the constant force mechanism is established, and the influence of factors such as mechanical parameters on the output force is analyzed. Experimental results show that the system can provide gravity compensation for a 720-kg Mars lander. It maintains a nearly constant output force even when the lander touches the ground and during the subsequent period, demonstrating its adaptability to transient collisions and sudden state changes. © 1965-2011 IEEE.

关键词： Space research

来源：评论

学校读者我要写书评

暂无评论

Precision autofocus in optical microscopy with liquid lenses controlled by deep reinforcement learning

引用

Microsystems & Nanoengineering 2024年第6期10卷 559-571页

作者： Jing Zhang Yong-feng Fu Hao Shen Quan Liu Li-ning Sun Li-guo Chen School of Mechanical and Electrical Engineering Soochow UniversityNo.8 Jixue RoadSuzhou CityJiangsu 215000China School of Computer Science and Technology Soochow UniversityNo.333 Ganjiang East RoadSuzhou CityJiangsu 215006China

Microscopic imaging is a critical tool in scientific research,biomedical studies,and engineering applications,with an urgent need for system miniaturization and rapid,precision autofocus ***,traditional microscopes and autofocus methods face hardware limitations and slow software speeds in achieving this *** response,this paper proposes the implementation of an adaptive Liquid Lens Microscope System utilizing Deep Reinforcement Learning-based Autofocus(DRLAF).The proposed study employs a custom-made liquid lens with a rapid zoom response,which is treated as an“agent.”Raw images are utilized as the“state”,with voltage adjustments representing the“actions.”Deep reinforcement learning is employed to learn the focusing strategy directly from captured images,achieving end-to-end *** contrast to methodologies that rely exclusively on sharpness assessment as a model’s labels or inputs,our approach involved the development of a targeted reward function,which has proven to markedly enhance the performance in microscope autofocus *** explored various action group design methods and improved the microscope autofocus speed to an average of 3.15 time ***,parallel“state”dataset lists with random sampling training are proposed which enhances the model’s adaptability to unknown samples,thereby improving its generalization *** experimental results demonstrate that the proposed liquid lens microscope with DRLAF exhibits high robustness,achieving a 79%increase in speed compared to traditional search algorithms,a 97.2%success rate,and enhanced generalization compared to other deep learning methods.

关键词： Deep hardware generalization

来源：评论

学校读者我要写书评

暂无评论

HCCL: Hierarchical Channels and Contrastive Learning for Drug-Gene Multi-Relation Prediction

HCCL: Hierarchical Channels and Contrastive Learning for Dru...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Shang, Yizhe Chen, Jianrui Lei, Xiujuan Wu, Fang-Xiang Shaanxi Normal University School of Computer Science Xi'an China University of Saskatchewan Department of Mechanical Engineering Division of Biomedical Engineering Department of Computer Science SaskatoonS7N 5A9 Canada

ISBN: (纸本)9798350386226

Drug-gene interaction plays a crucial role in drug discovery and personalized medicine. Although existing methods have improved the accuracy of exploring multiple relationships between drugs and genes, there are still some limitations, such as susceptibility to data sparsity and poor generalization, which pose some challenges for practical applications. To address these challenges, we propose a novel Hierarchical Channels and Contrastive Learning (HCCL) framework in which drug feature extractor captures structural information of drug molecules from atom and bond channels. After obtaining the initial features of drugs and genes, we employ high-low-order channels to update them, where the low-order channel adopts graph convolutional networks while the high-order channel leverages hypergraph structures for message propagation. Finally, we adopt contrastive learning and inter-channel attention to fuse high-low-order features, which improves the robustness of the model and prevents feature information loss. Experimental results demonstrate the superior performance of HCCL. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Transforming dentistry using artificial intelligence based innovations for advanced diagnostics and sustainable healthcare 3

Transforming dentistry using artificial intelligence based i...

引用

3rd International Conference on Computational Modelling, Simulation and Optimization, ICCMSO 2024

作者： Chhabra, Deepak Kumar Dhingra, Ashwani Kaushik, Ashish Dhingra, Sunita Kumar Sahdev, Ravinder Dhingra, Sunil Maharshi Dayanand University Department of Mechanical Engineering UIET Rohtak India Deenbandhu Chhotu Ram University of Science and Technology Department of Mechanical Engineering Sonipat India Maharshi Dayanand University Department of Computer Science and Engineering UIET Rohtak India University Institute of Engineering and Technology Kurukshetra University Department of Mechanical Engineering Haryana Kurukshetra India

ISBN: (纸本)9798350361391

Modernizing and enhancing primary dental health care is imperative to address the growing demands of patients suffering from oral diseases to achieve the sustainable development goal of ensuring healthy lives and promoting well-being. Artificial intelligence (AI) is one such emerging technology that can radically transform dental practices by providing AI-driven imaging solutions, advanced diagnostic capabilities, and accurate treatment planning. This study explores the current state of artificial intelligence in dentistry using bibliometric analysis, along with an in-depth discussion on widely used artificial intelligence techniques for minimally invasive dentistry. Furthermore, several applications of AI in dentistry, along with benefits and current challenges, are also described. The study found that AI-powered tools are demonstrably enhancing diagnostic accuracy, streamlining workflows, and offering personalized treatment options. © 2024 IEEE.

关键词： Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced LSB Steganography Interface: Concealed Data Embedding Framework 9

AI-Enhanced LSB Steganography Interface: Concealed Data Embe...

引用

9th IEEE International Conference on Smart Structures and Systems, ICSSS 2023

作者： Raja Rajeswari, N. Meenadshi, M. Saveetha Engineering College Department of Mechanical Engineering Chennai India Saveetha Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350384208

Steganography involves concealing text-based secret data within non-text files such as image, audio, or video files, with the extraction of the hidden data taking place at its destination. This avoids detection. Therefore, it becomes challenging for anyone to detect the presence of a concealed message within the image, highlighting the increasing importance of data privacy in contemporary times. The primary objective of Steganography is to enable clandestine communication between two individuals, typically involving the processes of encoding and decoding. This project specifically focuses on image Steganography, allowing the encoding and decoding of data within an image file. Through the utilization of steganography, an individual can conceal a substantial amount of text, comprising thousands of words, within a standard-sized image. To implement this Steganography approach, Python Image Library (PIL) is employed in conjunction with the Tkinter framework. LSB (Least Significant Bit) steganography techniques are applied for encryption and decryption functionalities. The primary goal is to create an application that employs LSB insertion to encode data within a cover image and, in a user-friendly manner, decode the original message from the embedded image. Additionally, AI-based encryption methodologies are integrated to enhance data security and fortify the concealment of information within the images, showcasing the synergy between advanced encryption techniques and traditional steganographic methods. © 2023 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Imaging and structure analysis of ferroelectric domains,domain walls,and vortices by scanning electron diffraction

引用

npj Computational Materials 2024年第1期10卷 2154-2161页

作者： Ursula Ludacka Jiali He Shuyu Qin Manuel Zahn Emil Frang Christiansen Kasper A.Hunnestad Xinqiao Zhang Zewu Yan Edith Bourret István Kézsmárki Antonius T.Jvan Helvoort Joshua Agar Dennis Meier Department of Materials Science and Engineering NTNU Norwegian University of Science and TechnologyTrondheimNorway Department of Computer Science and Engineering Lehigh UniversityBethlehemPAUSA Department of Mechanical Engineering and Mechanics Drexel UniversityPhiladelphiaPAUSA Experimental Physics V University of AugsburgAugsburgGermany Department of Physics NTNU Norwegian University of Science and TechnologyTrondheimNorway Department of Physics ETH ZurichZürichSwitzerland Materials Sciences Division Lawrence Berkeley National LaboratoryBerkeleyCAUSA

Direct electron detectors in scanning transmission electron microscopy give unprecedented possibilities for structure analysis at the *** electronic and quantum materials,this new capability gives access to,for example,emergent chiral structures and symmetry-breaking distortions that underpin functional *** nanoscale structural features with statistical significance,however,is complicated by the subtleties of dynamic diffraction and coexisting contrast mechanisms,which often results in a low signal-to-noise ratio and the superposition of multiple signals that are challenging to deconvolute.

关键词： properties structure ferroelectric

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Sleep Stage Classification With Two-Stream Encoder-Decoder

引用

IEEE Transactions on Neural Systems and Rehabilitation engineering 2024年 32卷 2096-2105页

作者： Zhang, Zhao Lin, Bor-Shyh Peng, Chih-Wei Lin, Bor-Shing Wuyi University College of Mechanical and Electrical Engineering Fujian Wuyishan354300 China National Taipei University College of Electrical Engineering and Computer Science Department of Computer Science and Information Engineering New Taipei City237303 Taiwan Institute of Imaging and Biomedical Photonics National Yang Ming Chiao Tung University Tainan71150 Taiwan Taipei Medical University School of Biomedical Engineering College of Biomedical Engineering School of Gerontology and Long-Term Care College of Nursing Taipei11031 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan

Sleep staging serves as a fundamental assessment for sleep quality measurement and sleep disorder diagnosis. Although current deep learning approaches have successfully integrated multimodal sleep signals, enhancing the accuracy of automatic sleep staging, certain challenges remain, as follows: 1) optimizing the utilization of multi-modal information complementarity, 2) effectively extracting both long- and short-range temporal features of sleep information, and 3) addressing the class imbalance problem in sleep data. To address these challenges, this paper proposes a two-stream encode-decoder network, named TSEDSleepNet, which is inspired by the depth sensitive attention and automatic multi-modal fusion (DSA2F) framework. In TSEDSleepNet, a two-stream encoder is used to extract the multiscale features of electrooculogram (EOG) and electroencephalogram (EEG) signals. And a self-attention mechanism is utilized to fuse the multiscale features, generating multi-modal saliency features. Subsequently, the coarser-scale construction module (CSCM) is adopted to extract and construct multi-resolution features from the multiscale features and the salient features. Thereafter, a Transformer module is applied to capture both long- and short-range temporal features from the multi-resolution features. Finally, the long- and short-range temporal features are restored with low-layer details and mapped to the predicted classification results. Additionally, the Lovász loss function is applied to alleviate the class imbalance problem in sleep datasets. Our proposed method was tested on the Sleep-EDF-39 and Sleep-EDF-153 datasets, and it achieved classification accuracies of 88.9% and 85.2% and Macro-F1 scores of 84.8% and 79.7%, respectively, thus outperforming conventional traditional baseline models. These results highlight the efficacy of the proposed method in fusing multi-modal information. This method has potential for application as an adjunct tool for diagnosing sleep disorde

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Robust Car-Following Control of Connected and Autonomous Vehicles: A Stochastic Model Predictive Control Approach

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-14页

作者： Zhang, Peiyu Tian, Daxin Zhou, Jianshan Chang, Mai Duan, Xuting Zhao, Dezong Cao, Dongpu Leung, Vicor C.M. Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing China James Watt School of Engineering University of Glasgow Glasgow U.K Department of Mechanical and Mechatronics Engineering University of Waterloo Waterloo ON Canada Computer Science and Software Engineering Shenzhen University Shenzhen China

Vehicle platooning has attracted growing attention for its potential to enhance traffic capacity and road safety. This paper proposes an innovative distributed Stochastic Model Predictive Control (SMPC) for a vehicle platoon system to enhance the robustness and safety of the vehicles in uncertain traffic environments. In particular, considering the similarity between the acceleration or deceleration behaviour of neighbouring vehicles and the spring-scale properties, we use a two-mass spring system for the first time to construct an uncertain dynamic model of a formation system. In the presence of uncertain perturbations with known distributional attributes (expectation, variance), we propose an objective function in the form of expectation along with probabilistic chance constraints. Subsequently, a state feedback control mechanism is devised accordingly. Under the cumulative probability distribution function of stochastic perturbations, we theoretically derive a computationally tractable equivalent of the SMPC model. Finally, simulation experiments are designed to validate the control performance of the SMPC platoon controllers, along with an analysis of the stability performance under varying probabilities. The experimental findings demonstrate that the model can be efficiently solved in real-time with appropriately chosen prediction horizon lengths, ensuring robust and safe longitudinal vehicle formation control. IEEE

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Design,simulation,and testing of a tunable MEMS multi-threshold inertial switch

引用

Microsystems & Nanoengineering 2024年第2期10卷 37-46页

作者： Qiu Xu Rodrigo T.Rocha Yousef Algoos Eric Feron Mohammad I.Younis Faculty of Electronic Information Engineering Huaiyin Institute of TechnologyHuai’an223003PR China Computer Electrical and Mathematical Science and Engineering DivisionKing Abdullah University of Science and TechnologyThuwal23955-6900Saudi Arabia Piezoelectric Microsystem Technologies Silicon Austria LabsVillach9524Austria Physical Sciences and Engineering Division King Abdullah University of Science and TechnologyThuwal23955Saudi Arabia Mechanical Engineering Department State University of New YorkBinghamtonNY13902USA

This paper presents a tunable multi-threshold micro-electromechanical inertial switch with adjustable threshold *** demonstrated device combines the advantages of accelerometers in providing quantitative acceleration measurements and g-threshold switches in saving power when in the inactive state upon experiencing acceleration below the *** designed proof-of-concept device with two thresholds consists of a cantilever microbeam and two stationary electrodes placed at different positions in the sensing *** adjustable threshold capability and the effect of the shock duration on the threshold acceleration are analytically investigated using a nonlinear beam *** are shown for the relationships among the applied bias voltage,the duration of shock impact,and the tunable *** fabricated prototypes are tested using a shock-table *** analytical results agree with the experimental *** designed device concept is very promising for the classification of the shock and impact loads in transportation and healthcare applications.

关键词： tunable acceleration testing

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：