检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Lu, Qin Li, Shuang Shi, Yueyan Xu, Jinchao Zhang, Xiajing Wu, Tao Zhou, Liang Guo, Jiachen Network and Information Center Shanghai Jiao Tong University School of Medicine Shanghai200025 China China Hospital Development Institute Shanghai Jiao Tong University Shanghai200025 China Collaborative Innovation Center Shanghai University of Medicine and Health Sciences Shanghai200025 China School of Health Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China School of Optical‐Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Jiading District Central Hospital Shanghai University of Medicine and Health Sciences Shanghai201899 China Biomedical Engineering Fusion Laboratory Jiangning Hospital Nanjing Medical University Jiangsu211166 China

Future wearable devices for health monitoring, robotics, and ultra-precise industrial positioning will require flexible optical systems. Flexible fiber optic sensors are important components of wearable smart devices that sense and respond to changes in physical quantities of the external environment. However, the sensitivity and response time of most sensors need to be further improved to detect humidity and temperature in relation to the human body. In this paper, a photonic bionic sensor based on strongly coupled fiber coated with carbomer polymer has been reported for the first time. The sensor itself adopts 2 × 2 coupler structure with waist diameter of 24 μm. The carbomer polymer film is coated in the strongly coupling area to increase the sensitivity and response time of the sensor. The thickness of the coating layer is about 1.5 μm. The sensitivity of the sensor is up to 0.017/%RH in the relative humidity range of 64 %RH - 84 %RH, and the temperature sensitivity is up to 0.016/°C in the range of 30°C - 45°C. Moreover, the photonic bionic sensor has a fast response time with a dynamic response of 1.2 s and a recovery of 1.8 s. Considering the excellent performance of the sensor, it can be utilized as the prototype of an ultra-sensitive flexible optical sensor, making it a suitable candidate for wearable medical devices aimed at both human and animal health monitoring. © 2024, The Authors. All rights reserved.

关键词： Bionics

来源：评论

学校读者我要写书评

暂无评论

Automatic Sleep Spindle Detection and Analysis in Patients with Sleep Disorders 1

引用

2nd International Workshop on Human Brain and Artificial Intelligence, HBAI 2020 held in Conjunction with IJCAI-PRICAI 2020

作者： Chen, Chao Zhu, Xuequan Belkacem, Abdelkader Nasreddine Lu, Lin Hao, Long You, Jia Shin, Duk Tan, Wenjun Huang, Zhaoyang Ming, Dong Academy of Medical Engineering and Translational Medicine Tianjin University Tianjin300072 China Key Laboratory of Complex System Control Theory and Application Tianjin University of Technology Tianjin300384 China Department of Computer and Network Engineering College of Information Technology UAE University Al Ain15551 United Arab Emirates Zhonghuan Information College Tianjin University of Technology Tianjin300380 China Department of Electronics and Mechatronics Tokyo Polytechnic University Atsugi243-0297 Japan School of Computer Science and Engineering Northeastern University Shenyang110189 China Department of Neurology Xuanwu Hospital Capital Medical University Beijing100088 China

ISBN: (数字)9789811612886

ISBN: (纸本)9789811612879

Nowadays, Sleep disorder is a common disease, and spindle spindles are important features of the second stage non-rapid eye movement (NREM) sleep. In this paper, we propose an improved automatic detection method of spindles based on wavelet transform. The spindles automatic detector is mainly composed of wavelet transform and clustering. We collected the electroencephalography (EEG) signals of six patients with sleep disorders all night for ten hours, and then preprocessed the data and other operations, and then used our improved method to detect the sleep EEG signals by spindles. By comparing with the previous automatic detection method not improved and another automatic detection method, the results show that the accuracy of sleep spindles detection can be effectively improved. The accuracy of the improved detector is 5.19% higher than before, and 9.7% higher than that of another method based on amplitude threshold. Finally, we made a simple comparison between people with sleep disorders and normal people. We found that there were significant differences in spindle density between people with sleep disorders and people without sleep disorders. The average spindle density in the normal population averaged 2.59 spindles per minute. People with sleep disorders had an average spindle density of 1.32 spindles per minute. In future research, our research direction is to improve the accuracy of spindles automatic detection by improving the spindles detector and study the difference of spindles between patients with sleep disorders and normal people in a large number of samples, so that the difference of spindles can be used as the basis for the diagnosis of sleep disorders. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Smart city governance through big data: Transformation towards sustainability

Smart city governance through big data: Transformation towar...

引用

2021 International Conference of Women in Data science at Taif University, WiDSTaif 2021

作者： Sarker, Md Nazirul Islam Kamruzzaman, M.M. Huq, Md Enamul Zaman, Roksana Hossain, Babul Khurshid, Sumaira School of Political Science and Public Administration Neijiang Normal University Neijiang614112 China Department of Computer and Information Science Jouf University Sakaka Al-Jouf Saudi Arabia State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China School of Electrical Engineering and Information Southwest Petroleum University Chengdu China Research Center for Environment and Society Hohai University Nanjing China School of Education and Science Neijiang Normal University Neijiang China

ISBN: (纸本)9781665449489

Smart city governance (SCG) is a new paradigm of urban policy, planning, and management that able to solve emerging challenges of urban areas along with ensuring urban sustainability. Data-driven technology provides an opportunity to transform the conventional practices into smart practices at all levels of urban actors. This study assesses the suitability of big data approaches for ensuring SCG. A systematic desk review has been conducted under the framework of PRISMA. This study reveals a difference among the opinions of scholars on SCG, such as, a group of scholars emphasizes on smart characteristics of technology, people, and their integration, while other group focuses on the digital transformation of urban management practices of key actors like public, private and community. This study argues that SCG is a combined function of public, private, and community that adapted advanced technology like big data in their practices for transformation from conventional one for ensuring urban sustainability. This study offers a number of indicators for the concerned authorities to understand the SCG and take priority-based decisions from systemic data and information. © 2021 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Conceptualising a channel-based overlapping CNN tower architecture for COVID-19 identification from CT-scan images

引用

Scientific Reports 2022年第1期12卷 1-15页

作者： Tiwari, Ravi Shekhar D, Lakshmi Das, Tapan Kumar Srinivasan, Kathiravan Chang, Chuan-Yu Artificial Intelligence Engineering Chadura Tech Bangalore India School of Computing Science and Engineering VIT Bhopal University Bhopal India School of Information Technology and Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Douliu City 64002 Taiwan Service Systems Technology Center Industrial Technology Research Institute Hsinchu Taiwan

Convolutional Neural network (CNN) has been employed in classifying the COVID cases from the lungs’ CT-Scan with promising quantifying metrics. However, SARS COVID-19 has been mutated, and we have many versions of the virus B.1.1.7, B.1.135, and P.1, hence there is a need for a more robust architecture that will classify the COVID positive patients from COVID negative patients with less training. We have developed a neural network based on the number of channels present in the images. The CNN architecture is developed in accordance with the number of the channels present in the dataset and are extracting the features separately from the channels present in the CT-Scan dataset. In the tower architecture, the first tower is dedicated for only the first channel present in the image;the second CNN tower is dedicated to the first and second channel feature maps, and finally the third channel takes account of all the feature maps from all three channels. We have used two datasets viz. one from Tongji Hospital, Wuhan, China and another SARS-CoV-2 dataset to train and evaluate our CNN architecture. The proposed model brought about an average accuracy of 99.4%, F1 score 0.988, and AUC 0.99. © 2022, The Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Easy Begun is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout

arXiv

引用

arXiv 2022年

作者： Wang, Hongjun Chen, Jiyuan Pan, Tong Fan, Zipei Zhang, Boyuan Jiang, Renhe Zhang, Lingyu Xie, Yi Wang, Zhongyi Song, Xuan SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and Engineering Southern University of Science and Technology China Research Institute of Trustworthy Autonomous Systems SUSTech Department of Physics The Chinese University of Hong Kong Hong Kong Center for Spatial Information Science University of Tokyo Japan Information Technology Center University of Tokyo Japan Huawei Technologies CO.LTD China

Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area. However, for the nodes in graph, their ST patterns can vary greatly in difficulties for modeling, owning to the heterogeneous nature of ST data. We argue that unveiling the nodes to the model in a meaningful order, from easy to complex, can provide performance improvements over traditional training procedure. The idea has its root in Curriculum Learning (Bengio et al. 2009) which suggests in the early stage of training models can be sensitive to noise and difficult samples. In this paper, we propose ST-Curriculum Dropout, a novel and easy-to-implement strategy for spatial-temporal graph modeling. Specifically, we evaluate the learning difficulty of each node in high-level feature space and drop those difficult ones out to ensure the model only needs to handle fundamental ST relations at the beginning, before gradually moving to hard ones. Our strategy can be applied to any canonical deep learning architecture without extra trainable parameters, and extensive experiments on a wide range of datasets are conducted to illustrate that, by controlling the difficulty level of ST relations as the training progresses, the model is able to capture better representation of the data and thus yields better generalization. © 2022, CC BY.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

The Lithium-Ions Storage Behavior of Flexible and Binder-Free Multilayer Defective Graphene

SSRN

引用

SSRN 2024年

作者： Yang, Ying Zhang, Xuefu Zhao, Ruirui Chen, Yong P. Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology Av. Wai Long 999078 China Institute of New Energy for Vehicles School of Materials Science and Engineering Tongji University Shanghai201804 China National Key Laboratory of Materials for Integrated Circuits Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai200050 China Tohoku University Sendai980-8577 Japan Department of Physics and Astronomy Elmore Family School of Electrical and Computer Engineering Birck Nanotechnology Center Purdue Quantum Science and Engineering Institute Purdue University West LafayetteIN47907 United States Institute of Physics and Astronomy Villum Center for Hybrid Quantum Materials and Devices Aarhus University Aarhus-C 8000 Denmark

Graphene, a two-dimensional material made up of a single layer of carbon atoms, shows extraordinary electrical conductivity, exceptionally high specific surface area, and robust mechanical integrity, positioning graphene as an ideal anode material for lithium-ion batteries (LIBs). However, investigations of the utilization of pure multilayer graphene in lithium-ion batteries remain relatively scarce. Herein, multilayer graphene was fabricated by a scalable and common chemical vapor deposition (CVD) approach. Defects were formed during growth process, resulting in irregular local electron distributions in graphene. Using CVD growth graphene (CVD-graphene) as a free-standing and flexible anode for lithium-ion battery, it delivers a reversible areal capacity of 142 mAh cm−2 at a current of 0.1 μA and good cycle stability. The result demonstrates that surface pseudo-capacitance contribution mainly affects lithium-ion storage behaviors. The application of CVD-graphene for LIBs provides a promising way to develop lightweight and small electronic devices. © 2024, The Authors. All rights reserved.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Optimization for Amortized Inverse Problems

arXiv

引用

arXiv 2022年

作者： Liu, Tianci Yang, Tong Zhang, Quan Lei, Qi School of Electrical and Computer Engineering Purdue University United States Center of Data Science Peking University China Department of Accounting and Information Systems Michigan State University United States Courant Institute of Mathematical Sciences Center for Data Science New York University United States

Incorporating a deep generative model as the prior distribution in inverse problems has established substantial success in reconstructing images from corrupted observations. Notwithstanding, the existing optimization approaches use gradient descent largely without adapting to the non-convex nature of the problem and can be sensitive to initial values, impeding further performance improvement. In this paper, we propose an efficient amortized optimization scheme for inverse problems with a deep generative prior. Specifically, the optimization task with high degrees of difficulty is decomposed into optimizing a sequence of much easier ones. We provide a theoretical guarantee of the proposed algorithm and empirically validate it on different inverse problems. As a result, our approach outperforms baseline methods qualitatively and quantitatively by a large margin. Copyright © 2022, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Enhancement of sensitivity near exceptional points in dissipative qubit-resonator systems

arXiv

引用

arXiv 2025年

作者： Han, Pei-Rong Wu, Fan Huang, Xin-Jie Wu, Huai-Zhi Zou, Chang-Ling Yi, Wei Zhang, Mengzhen Li, Hekang Xu, Kai Zheng, Dongning Fan, Heng Wen, Jianming Yang, Zhen-Biao Zheng, Shi-Biao School of Physics and Mechanical and Electrical Engineering Longyan University Longyan364012 China Fujian Key Laboratory of Quantum Information and Quantum Optics College of Physics and Information Engineering Fuzhou University Fuzhou350108 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei230026 China Pritzker School of Molecular Engineering University of Chicago ChicagoIL60637 United States Institute of Physics Chinese Academy of Sciences Beijing100190 China CAS Center for Excellence in Topological Quantum Computation University of Chinese Academy of Sciences Beijing100190 China Department of Electrical and Computer Engineering Binghamton University BinghamtonNY13902 United States Department of Physics Kennesaw State University MariettaGA30060 United States

Dissipation usually plays a negative role in quantum metrological technologies, which aim to improve measurement precision by leveraging quantum effects that are vulnerable to environment-induced decoherence. Recently, it has been demonstrated that dissipation can actually be used as a favorable resource for enhancing the susceptibility of signal detection. However, demonstrations of such enhancement for detecting physical quantities in open quantum systems are still lacking. Here we propose and demonstrate a protocol for realizing such non-Hermitian quantum sensors for probing the coupling between a qubit and a resonator subjecting to energy dissipations. The excitation-number conversion associated with the no-jump evolution trajectory enables removal of the noisy outcomes with quantum jumps, implementing the exceptional point (EP), where the Rabi splitting exhibits a divergent behavior in response to a tiny variation of the effective coupling. The sensitivity enhancement near the EP is confirmed by both theoretical calculation and experimental measurement. Copyright © 2025, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Application Level Trust Authority (APPLETA) for Resource-Constrained Edge Devices in IoT and 6G

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Mahmood, Shahid Gohar, Moneeb Koh, Seok-Joo Tariq, Muhammad Usman Ghani, Anwar Department of Computer Science Bahria University Shangrilla Road E-8/1 Islamabad Pakistan School of Computer Science and Engineering Kyungpook National University Korea Republic of Marketing Operations Information Systems Abu Dhabi University United Arab Emirates Department of Computer Science International Islamic University Department of Computer Science International Islamic University Islamabad Pakistan Big Data Research Center Department of Computer Engineering Jeju National University Korea Republic of Department of Computer Science School of Engineering and Digital Sciences Nazarbayev University Astana010000 Kazakhstan

The rapid growth of the internet and edge devices has greatly increased the risk of cyber-attacks at the edge layer of computer networks. The rise of edge devices has driven extensive research into their cybersecurity challenges. These devices require robust protection to counter possible cyberattacks. Trust is a key security parameter used to determine the level of protection required for a device.. Trustworthiness gives confidence to other devices before they offer or request a service. The trust value indicates the probability of risk that a device may incur while engaging with another device. There are various solutions, but many fail due to the diversity of edge devices in the Internet of Things. In this paper, an efficient trust management framework, APPLETA, has been proposed. It computes the trust value based on routine application transactions and authentication behaviours without additional overhead. Simulation results show that the trust value is computed more efficiently, using only one application transaction trust parameter. APPLETA has demonstrated better results against good and bad-mouthing attacks with two parameters: application transaction and authentication. This scheme can effectively segregate malicious and harmless nodes. This segregation can further assist in the precise detection of malicious nodes. © 1975-2011 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Plant Disease Detection: A Novel CNN-Based Approach with Tensor Subspace Learning and HOWSVD-MD

arXiv

引用

arXiv 2024年

作者： Ouamane, Abdelmalik Chouchane, Ammar Himeur, Yassine Debilou, Abderrazak Amira, Abbes Atalla, Shadi Mansoor, Wathiq Al Ahmad, Hussain Laboratory of LI3C University of Biskra Algeria Algeria University Center of Barika Amdoukal Road Barika05001 Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Department of Computer Science University of Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom

Machine learning has revolutionized the field of agricultural science, particularly in the early detection and management of plant diseases, which are crucial for maintaining crop health and productivity. Leveraging advanced algorithms and imaging technologies, researchers are now able to identify and classify plant diseases with unprecedented accuracy and speed. Effective management of tomato diseases is crucial for enhancing agricultural productivity. The development and application of tomato disease classification methods are central to this objective. This paper introduces a cutting-edge technique for the detection and classification of tomato leaf diseases, utilizing insights from the latest pretrained Convolutional Neural network (CNN) models. We propose a sophisticated approach within the domain of tensor subspace learning, known as Higher-Order Whitened Singular Value Decomposition (HOWSVD), designed to boost the discriminatory power of the system. Our approach to Tensor Subspace Learning is methodically executed in two phases, beginning with HOWSVD and culminating in Multilinear Discriminant Analysis (MDA). The efficacy of this innovative method was rigorously tested through comprehensive experiments on two distinct datasets, namely PlantVillage and the Taiwan dataset. The findings reveal that HOWSVD-MDA outperforms existing methods, underscoring its capability to markedly enhance the precision and dependability of diagnosing tomato leaf diseases. For instance, up to 98.36% and 89.39% accuracy scores have been achieved under PlantVillage and the Taiwan datasets, respectively. © 2024, CC BY.

关键词： Singular value decomposition

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：