检索结果-内蒙古大学图书馆

Polychromatic full-polarization control in mid-infrared light

Light(Science & Applications) 2023年第5期12卷 894-904页

作者： Jin Chen Feilong Yu Xingsi Liu Yanjun Bao Rongsheng Chen Zengyue Zhao Jiuxu Wang Xiuxia Wang Wen Liu Yuzhi Shi Cheng-Wei Qiu Xiaoshuang Chen Wei Lu Guanhai Li State Key Laboratory of Infrared Physics Shanghai Institute of Technical PhysicsChinese Academy of Sciences500 Yu Tian RoadShanghai 200083China Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesNo.1 SubLane XiangshanHangzhou 310024China Shanghai Research Center for Quantum Sciences 99 Xiupu RoadShanghai 201315China University of Chinese Academy of Science No.19 Yuquan RoadBeijing 100049China Department of Electrical and Computer Engineering National University of Singapore4 Engineering Drive 3Singapore 117583Singapore Institute of Nanophotonics Jinan UniversityGuangzhou 511443China Center for Micro-and Nanoscale Research and Fabrication University of Science and Technology of ChinaHefei 230026China Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China National University of Singapore Suzhou Research Institute No.377 Linquan StreetSuzhouJiangsu 215123China

Objects with different shapes,materials and temperatures can emit distinct polarizations and spectral information in mid-infrared band,which provides a unique signature in the transparent window for object ***,the crosstalk among various polarization and wavelength channels prevents from accurate mid-infrared detections at high signal-to-noise ***,we report full-polarization metasurfaces to break the inherent eigen-polarization constraint over the wavelengths in *** recipe enables to select arbitrary orthogonal polarization basis at individual wavelength independently,therefore alleviating the crosstalk and efficiency degradation.A six-channel all-silicon metasurface is specifically presented to project focused mid-infrared light to distinct positions at three wavelengths,each with a pair of arbitrarily chosen orthogonal *** isolation ratio of 117 between neighboring polarization channels is experimentally recorded,exhibiting detection sensitivity one order of magnitude higher than existing infrared ***,the high aspect ratio~30 of our meta-structures manufactured by deep silicon etching technology at temperature−150℃ guarantees the large and precise phase dispersion control over a broadband from 3 to 4.5μ*** believe our results would benefit the noise-immune mid-infrared detections in remote sensing and space-to-ground communications.

关键词： polarization light noise

来源：评论

学校读者我要写书评

暂无评论

Instance Segmentation in the Dark

arXiv

引用

arXiv 2023年

作者： Chen, Linwei Fu, Ying Wei, Kaixuan Zheng, Dezhi Heide, Felix Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China Department of Computer Science Princeton University PrincetonNJ United States Department of Electrical and Computer Engineering McGill University Quebec Canada Algolux Rue Richardson Montreal Canada

Existing instance segmentation techniques are primarily tailored for high-visibility inputs, but their performance significantly deteriorates in extremely low-light environments. In this work, we take a deep look at instance segmentation in the dark and introduce several techniques that substantially boost the low-light inference accuracy. The proposed method is motivated by the observation that noise in low-light images introduces high-frequency disturbances to the feature maps of neural networks, thereby significantly degrading performance. To suppress this "feature noise", we propose a novel learning method that relies on an adaptive weighted downsampling layer, a smooth-oriented convolutional block, and disturbance suppression learning. These components effectively reduce feature noise during downsampling and convolution operations, enabling the model to learn disturbance-invariant features. Furthermore, we discover that high-bit-depth RAW images can better preserve richer scene information in low-light conditions compared to typical camera sRGB outputs, thus supporting the use of RAW-input algorithms. Our analysis indicates that high bit-depth can be critical for low-light instance segmentation. To mitigate the scarcity of annotated RAW datasets, we leverage a low-light RAW synthetic pipeline to generate realistic low-light data. In addition, to facilitate further research in this direction, we capture a real-world low-light instance segmentation dataset comprising over two thousand paired low/normal-light images with instance-level pixel-wise annotations. Remarkably, without any image preprocessing, we achieve satisfactory performance on instance segmentation in very low light (4 % AP higher than state-of-the-art competitors), meanwhile opening new opportunities for future research. Our code and dataset are publicly available to the community1 © 2023, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-omics graph convolutional networks for digestive system tumour classification and early-late stage diagnosis

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1572-1586页

作者： Lin Zhou Zhengzhi Zhu Hongbo Gao Chunyu Wang Muhammad Attique Khan Mati Ullah Siffat Ullah Khan School of Information Science and Technology University of Science and Technology of ChinaHefeiAnhuiChina Anhui Engineering Research Center on Information Fusion and Control of Intelligent Robot WuhuAnhuiChina Department of Breast Center West District of The Affiliated Hospital of University of Science and Technology of ChinaDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefeiAnhuiChina Institute of Advanced Technology University of Science and Technology of ChinaHefeiAnhuiChina School of Electrical and Electronic Engineering Nanyang Technological UniversitySingaporeSingapore School of Biological and Environmental Engineering Chaohu UniversityChaohu Regional Collaborative Technology Service Center for Rural RevitalizationHefeiChina Department of Artificial Intelligence College of Computer Engineering and SciencePrince Mohammad Bin Fahd UniversityAl-KhobarSaudi Arabia School of Automation Northwestern Polytechnical UniversityXi'anShaanxiChina Institute of Engineering and Computing Science University of Science and Technology of BannuKPKBannuPakistan

The prevalence of digestive system tumours(DST)poses a significant challenge in the global crusade against *** neoplasms constitute 20%of all documented cancer diagnoses and contribute to 22.5%of cancer-related *** accurate diagnosis of DST is paramount for vigilant patient monitoring and the judicious selection of optimal *** this challenge,the authors introduce a novel methodology,denominated as the Multi-omics Graph Transformer Convolutional Network(MGTCN).This innovative approach aims to discern various DST tumour types and proficiently discern between early-late stage tumours,ensuring a high degree of *** MGTCN model incorporates the Graph Transformer Layer framework to meticulously transform the multi-omics adjacency matrix,thereby illuminating potential associations among diverse samples.A rigorous experimental evaluation was undertaken on the DST dataset from The Cancer Genome Atlas to scrutinise the efficacy of the MGTCN *** outcomes unequivocally underscore the efficiency and precision of MGTCN in diagnosing diverse DST tumour types and successfully discriminating between early-late stage DST *** source code for this groundbreaking study is readily accessible for download at https://***/bigone1/MGTCN.

关键词： digestive system tumors early-late stage multi-omics tumor types

来源：评论

学校读者我要写书评

暂无评论

Using NSCTS and DCNN, Rapid Prediction and Forecasting of Breast Cancer

Using NSCTS and DCNN, Rapid Prediction and Forecasting of Br...

引用

Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE), International Conference on

作者： K. Seethalakshmi A. Bhagyalakshmi A. Sangeetha S. Vijitha P. Suhas Palukuri Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.K. College of Engineering and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India

Utilizing the CAD system, which aids radiologists in various diagnostic procedures, a recent study has been conducted on the early identification of breast cancer. Next to lung cancer, breast cancer ranks among the most deadly diseases. Initially, detection is done based on screening tests done through Magnetic resonance imaging (MRI), subsequently Infrared thermography, and digital mammography (DM). Whenever a suspicion is raised, these tests might be recommended by the specialist. Region-based segmentation is used for the test picture in this work, while NSCTS (Non-subsample Contourlet transform segmentation) is used for preprocessing. ResNet-164 DCNN architecture performs feature extraction and classification between normal and aberrant tumor pictures. The diagnosis system adopts the deep learning technology to increase its performance rate. The approach to prediction starts with screening test photos, then preprocessing to enhance the image quality, ROI detection, ROI segmentation, and classification. The resulting images are examined using a variety of evaluation measures, including performance rate, sensitivity, specificity, and accuracy. When compared to other recent work, the outcome is exceptional. The obtained accuracy, sensitivity of the proposed system is 98.58% and 98.78%. The application takes advantage of the MIAS mammography image dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Jointly Optimizing Terahertz based Sensing and Communications in Vehicular Networks: A Dynamic Graph Neural Network Approach

arXiv

引用

arXiv 2024年

作者： Li, Xuefei Chen, Mingzhe Hu, Ye Zhang, Zhilong Liu, Danpu Mao, Shiwen The Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States The Department of Electrical and Computer Engineering Auburn University AuburnAL36849 United States

In this paper, the problem of vehicle service mode selection (sensing, communication, or both) and vehicle connections within terahertz (THz) enabled joint sensing and communications over vehicular networks is studied. The considered network consists of several service provider vehicles (SPVs) that can provide: 1) only sensing service, 2) only communication service, and 3) both services, sensing service request vehicles, and communication service request vehicles. Based on the vehicle network topology and their service accessibility, SPVs strategically select service request vehicles to provide sensing, communication, or both services. This problem is formulated as an optimization problem, aiming to maximize the number of successfully served vehicles by jointly determining the service mode of each SPV and its associated vehicles. To solve this problem, we propose a dynamic graph neural network (GNN) model that selects appropriate graph information aggregation functions according to the vehicle network topology, thus extracting more vehicle network information compared to traditional static GNNs that use fixed aggregation functions for different vehicle network topologies. Using the extracted vehicle network information, the service mode of each SPV and its served service request vehicles will be determined. Simulation results show that the proposed dynamic GNN based method can improve the number of successfully served vehicles by up to 17% and 28% compared to a GNN based algorithm with a fixed neural network model and a conventional optimization algorithm without using GNNs. Copyright © 2024, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Cloud-based Decentralized Smart Healthcare for Patient Monitoring on Deep Learning 2

Cloud-based Decentralized Smart Healthcare for Patient Monit...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Arunachalam, Sripriya Shanthi, H.J. Sivagurunathan, G. Das, Shyamali Anand, D. Raj M, Thanga School of Computing Sciences Vels Institute of Science Technology & Advanced Studies - Vistas Computer Applications- Pg India Amet University Ecr Kanathur India St. Joseph's College of Engineering Omr Department of Electronics and Communication Engineering Chennai600119 India Cmr Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Koneru Lakshmaiah Education Foundation Department of Cse AP Vaddeswaram India Persistent Systems Limited Pune India

ISBN: (纸本)9781665456302

Over the past few years, there has been a meteoric surge in the quantity of digital information available online for instantaneous sharing, persistent archiving, and inquiring. It has expanded the possibilities for using digital data that is both decentralised and ad hoc in order to make decisions quickly. At present, e-Healthcare is among the most sought-after sectors for EHR and telemedicine communication. Securing electronic health records (EHR) has become a topic of intense interest in recent years, with previous works employing a wide range of methods to better ensure the confidentiality and security of EHR at a reasonable price. There are a number of serious problems with the current research, including computational complexity, increased process time, information leakage, vulnerability to various assaults, scalability difficulty, etc. Clinical data analysis presents several difficulties, but disease prediction is one of the most significant ones. The suggested study aims to apply deep learning (DL) classification algorithms for disease prediction. A technique that utilises cloud computing, fog computing, and IoMT more recently has been presented for diagnosing illness. Fast DL classification analysis is performed in the fog layer. When compared to the alternative proposed model Bi-CNN, the healthcare model's efficiency in the Bi-LSTM simulation yields significantly better results: 97.31% of accuracy, 97.58% of recall, 96.90% of precision, 94.90% of F1-measure, 97.25% of specificity, and 94.80% of G-mean. © 2023 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Epidermal piezoresistive structure with deep learning-assisted data translation

引用

npj Flexible Electronics 2022年第1期6卷 672-680页

作者： Changrok So Jong Uk Kim Haiwen Luan Sang Uk Park Hyochan Kim Seungyong Han Doyoung Kim Changhwan Shin Tae-il Kim Wi Hyoung Lee Yoonseok Park Keun Heo Hyoung Won Baac Jong Hwan Ko Sang Min Won Department of Electrical and Computer Engineering Sungkyunkwan University(SKKU)Suwon 16419Republic of Korea School of Chemical Engineering Sungkyunkwan University(SKKU)Suwon 16419Republic of Korea Querrey Simpson Institute for Bioelectronics Northwestern UniversityEvanstonIL 60208USA Department of Mechanical Engineering Ajou UniversitySuwon 16499Republic of Korea School of Electrical Engineering Korea UniversitySeoul 02841Republic of Korea Biomedical Institute for Convergence(BICS) Sungkyunkwan University(SKKU)Suwon 16419Korea Department of Organic and Nano System Engineering Konkuk UniversitySeoul 05029Republic of Korea Department of Advanced Materials Engineering for Information and Electronics Kyung Hee UniversityYongin 17104Republic of Korea School of Semiconductor and Chemical Engineering Jeonbuk National UniversityJeonju 54896Republic of Korea

Continued research on the epidermal electronic sensor aims to develop sophisticated platforms that reproduce key multimodal responses in human skin,with the ability to sense various external stimuli,such as pressure,shear,torsion,and *** development of such applications utilizes algorithmic interpretations to analyze the complex stimulus shape,magnitude,and various moduli of the epidermis,requiring multiple complex equations for the attached *** this experiment,we integrate silicon piezoresistors with a customized deep learning data process to facilitate in the precise evaluation and assessment of various stimuli without the need for such *** the ability to surpass conventional vanilla deep regression models,the customized regression and classification model is capable of predicting the magnitude of the external force,epidermal hardness and object shape with an average mean absolute percentage error and accuracy of<15 and 96.9%,*** technical ability of the deep learning-aided sensor and the consequent accurate data process provide important foundations for the future sensory electronic system.

关键词： utilize attached precise

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Neuro-Fuzzy Control Approach for Robot's Trajectory Tracking 7

Design and Implementation of Neuro-Fuzzy Control Approach fo...

引用

7th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2023

作者： Kiruba Sandou, D. Sunad Kumara, A.N. Choudhary, Binod Kumar Gurpur, Shashikala Sarishma Natrayan, L. Sivaramkumar, M. Manakula Vinayagar Institute of Technology Department of Robotics and Automation Pondicherry605107 India BGS Institute of Technology Department of Computer Science and Engineering Adichunchanagiri University Karnataka Mandya571448 India ARKA Jain University Department of Electrical and Electronics Engineering Jharkhand Jamshedpur832108 India Maharashtra Pune411014 India Graphic Era Deemed to Be University Department of Management Studies Uttarakhand Dehradun India Saveetha School of Engineering SIMATS Department of Mechanical Engineering Tamilnadu Chennai602105 India Karpagam Academy of Higher Education Department of EEE Tamiinadu Coimbatore India

ISBN: (纸本)9798350340600

Achieving precise trajectory tracking while minimizing errors, reducing settling time, and curbing overshoot presents a significant challenge in the domain of robot-manipulator control. In response, this paper proposes a novel controller design for robot manipulators, incorporating two distinct approaches: a conventional fuzzy controller and an advanced Neuro-Fuzzy controller. These controllers are tailored to elevate trajectory tracking performance by simultaneously optimizing time characteristics in robot manipulator responses. To assess their efficacy, a range of test scenarios is devised, encompassing different trajectory types, including linear and nonlinear paths. Upon comparative analysis, the results highlight an intriguing contrast: while the fuzzy controller exhibits higher maximum overshoot and longer settling times in the robot's response, the Neuro-Fuzzy controller consistently demonstrates superior performance. The comprehensive error analysis such as Integral Square Error (ISE) and Integral Absolute Error (IAE) further underscores the capability of the Neuro-Fuzzy-based robot manipulator in delivering trajectory tracking precision. This study contributes to the advancement of trajectory control techniques for robot manipulators, paving the way for enhanced automation and performance across various applications. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

AL-Annotator: An Active Learning-based Cervical Cell Annotation System 29

AL-Annotator: An Active Learning-based Cervical Cell Annotat...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Jiang, Yangbo Zhang, Shuting Wu, Jinggen Zhu, Xumei Liu, Xiao Zheng, Nenggan Zhejiang University Qiushi Academy for Advanced Studies College of Computer Science and Technology Hangzhou China Zhejiang Sci-Tech University College of Information Science and Engineering Hangzhou China Zhejiang University Women's Hospital School of Medicine Hangzhou China Zhejiang Institute of Mechanical and Electrical Engineering College of Continuing Education Hangzhou China Beijing Huawei Digital Technology Co. Ltd. Beijing China

ISBN: (纸本)9798350330717

When deep learning is applied to cervical cell screening, it encounters challenges related to the inefficient labeling of data and a shortage of annotators. To mitigate these challenges, this study introduces AL-Annotator, an active learning-based cervical cell annotation system. This system consists of three key components: an interactive interface designed for efficient pathologists' review, a front-end and back-end separated cervical cell annotation system, and an active learning-based annotation method. Compared to traditional classification-based annotation methods, our annotation system achieves a 17.74% reduction in annotation quantity while improving the accuracy by 1.92%. This annotation system is crucial for developing and testing new machine learning and artificial intelligence algorithms for cervical screening, thereby facilitating advancements in diagnostic tools and methodologies. © 2023 IEEE.

关键词： active learning annotation system cervical cell classification system architecture

来源：评论

学校读者我要写书评

暂无评论

A Novel Model for Driver Lane Change Prediction in Cooperative Adaptive Cruise Control Systems

arXiv

引用

arXiv 2023年

作者： Qasemabadi, Armin Nejadhossein Mozaffari, Saeed Rezaei, Mahdi Ahmadi, Majid Alirezaee, Shahpour Electrical and Computer Engineering Department University of Windsor Windsor Canada Mechanical Automotive and Material Engineering Department University of Windsor Windsor Canada Institute for Transport Studies University of Leeds United Kingdom

Accurate lane change prediction can reduce potential accidents and contribute to higher road safety. Adaptive cruise control (ACC), lane departure avoidance (LDA), and lane keeping assistance (LKA) are some conventional modules in advanced driver assistance systems (ADAS). Thanks to vehicle-to-vehicle communication (V2V), vehicles can share traffic information with surrounding vehicles, enabling cooperative adaptive cruise control (CACC). While ACC relies on the vehicle's sensors to obtain the position and velocity of the leading vehicle, CACC also has access to the acceleration of multiple vehicles through V2V communication. This paper compares the type of information (position, velocity, acceleration) and the number of surrounding vehicles for driver lane change prediction. We trained an LSTM (Long Short-Term Memory) on the HighD dataset to predict lane change intention. Results indicate a significant improvement in accuracy with an increase in the number of surrounding vehicles and the information received from them. Specifically, the proposed model can predict the ego vehicle lane change with 59.15% and 92.43% accuracy in ACC and CACC scenarios, respectively. © 2023, CC BY.

关键词： Adaptive cruise control

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：