检索结果-内蒙古大学图书馆

Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: From convolutional neural networks to visual transformers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Wanli Li, Chen Rahaman, Md Mamunur Jiang, Tao Sun, Hongzan Wu, Xiangchen Hu, Weiming Chen, Haoyuan Sun, Changhao Yao, Yudong Grzegorzek, Marcin Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang110169 China School of Control Engineering Chengdu University of Information Technology Chengdu610225 China Shengjing Hospital China Medical University Shenyang110001 China Suzhou Ruiguan Technology Company Ltd. Suzhou215000 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110169 China Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ07030 United States Institute of Medical Informatics University of Luebeck Luebeck Germany

Cervical cancer is a very common and fatal type of cancer in women. Cytopathology images are often used to screen for this cancer. Given that there is a possibility that many errors can occur during manual screening, a computer-aided diagnosis system based on deep learning has been developed. Deep learning methods require a fixed dimension of input images, but the dimensions of clinical medical images are inconsistent. The aspect ratios of the images suffer while resizing them directly. Clinically, the aspect ratios of cells inside cytopathological images provide important information for doctors to diagnose cancer. Therefore, it is difficult to resize directly. However, many existing studies have resized the images directly and have obtained highly robust classification results. To determine a reasonable interpretation, we have conducted a series of comparative experiments. First, the raw data of the SIPaKMeD dataset are pre-processed to obtain standard and scaled datasets. Then, the datasets are resized to 224 × 224 pixels. Finally, 22 deep learning models are used to classify the standard and scaled datasets. The results of the study indicate that deep learning models are robust to changes in the aspect ratio of cells in cervical cytopathological images. This conclusion is also validated via the Herlev dataset. Copyright © 2021, The Authors. All rights reserved.

关键词： Aspect ratio

Networked Model for Cooperative Adaptive Cruise control

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2019年第20期52卷 151-156页

作者： Philip E. Paré Ehsan Hashemi Raphael Stern Henrik Sandberg Karl Henrik Johansson Division of Decision and Control Systems at KTH Royal Institute of Technology Sweden Department of Mechanical and Mechatronics Engineering at University of Waterloo Canada Department of Informatics at the Technical University of Munich Germany

This paper proposes a cooperative adaptive cruise control model, adding a communication network structure to an existing model that has been shown to capture real commercial adaptive cruise control vehicle behavior. The proposed model is interesting because it only requires minimal information sharing, facilitating the creation of platoons comprised of vehicles from different manufacturers. We prove the stability of the model and discuss string stability. Algorithms for estimating the velocity of the vehicles locally and for estimating the velocities of all the vehicles in the platoon are presented. We simulate vehicle platoon control with the lead vehicle following an experimentally collected trajectory, showing that adding communication can cause a string unstable platoon to become stable.

关键词： Semi-autonomous vehicles Intelligent cruise control Networks Traffic control

Industry 4.0 in Germany, Austria and Hungary: Interpretation, strategies and readiness models 16

学校读者我要写书评

暂无评论

Industry 4.0 in Germany, Austria and Hungary: Interpretation...

16th IMEKO TC10 Conference 2019 on Testing, Diagnostics and Inspection as a Comprehensive Value Chain for Quality and Safety

作者： Nick, Gábor Gallina, Viola Szaller, Ádám Várgedő, Tamás Schumacher, Andreas Centre of Excellence in Production Informatics and Control Institute for Computer Science and Control Hungarian Academy of Sciences Budapest Hungary Fraunhofer Austria Research GmbH Wien Austria Széchenyi István University Research Center of Vehicle Industry Győr Hungary University of Technology and Economics Department of Manufacturing Science and Engineering Budapest Hungary

ISBN: (纸本)9789299008416

Global economy increasingly responds to trends of industrial digitization and start to develop their own digitalization strategies e.i. through application of Industry 4.0 concepts. Thereby, initiatives and developments are often carried out on a company-, industry- or country-level, which can result in a lack of international co-operation and utilization of synergy-effects. To analyse the Industry 4.0 development status on a macro level and to enhance transnational developments, in the first part of this study we introduce the national Industry 4.0 platforms of three EU member states – the frontrunner Germany, the solidly rising Austria and Hungary that is in the process of catching up. Our analysis are carried out in four dimensions: economic background, country-specific Industry 4.0 interpretation, and local platforms as well as initiatives. To analyse the actual Industry 4.0 development status of industrial enterprises and of development platforms, existing Industry 4.0 maturity models form all three countries are presented and compared. Our analysis helped to capture the different phases of digitization and Industry 4.0 in Germany, Austria and Hungary in regard to defined goals and strategies and further of resulting problems with respect to Industry 4.0. Building on our comparison-studies and captured problems, decision makers should be enabled to carry out transnational Industry 4.0 projects and initiatives more effectively. © 2019 International Measurement Confederation (IMEKO). All rights reserved.

关键词： Industry 4.0

Towards Body Sensor Network Based Gait Abnormality Evaluation for Stroke Survivors 14th

学校读者我要写书评

暂无评论

Towards Body Sensor Network Based Gait Abnormality Evaluatio...

14th EAI International Conference on Body Area Networks, BodyNets 2019

作者： Qiu, Sen Guo, Xiangyang Zhao, Hongyu Wang, Zhelong Li, Qimeng Gravina, Raffaele Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China School of Control Science and Engineering Dalian University of Technology Dalian116024 China Department of Informatics Modeling Electronics and Systems University of Calabria Via P. Bucci RendeCS87036 Italy

ISBN: (纸本)9783030348328

Due to the technological advances of micro-electro-mechanical sensor and wireless sensor network, gait analysis has been widely adopted as an significant indicator of mobility impairment for stroke survivors. This paper aims to propose an wearable computing based gait impairment evaluation method with distribute inertial sensor unit (IMU) mounted on human lower limbs. Temporal-spacial gait metrics were evaluated on more than twenty post stroke patients and ten healthy control subjects in the 10-meters-walk-test. Experimental results shown that significant differences exist between stroke patients and healthy subject in terms of various gait metrics. The extracted gait metrics are consistent with clinical observations, and the position estimation accuracy has been validated by optical device. The proposed method has the potential to serve as an objective and cost-efficient tool for rehabilitation-assisting therapy for post stroke survivors in clinical practice. © 2019, ICST Institute for Computer Sciences, Social informatics and Telecommunications engineering.

关键词： Body sensor networks

Data-driven Algorithm for Scheduling with Total Tardiness

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bouška, Michal Novák, Antonín Sůcha, Přemysl Módos, István Hanzálek, Zdeněk Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Jugoslávských partyzánů 1580/3 Prague Czech Republic Czech Technical University in Prague Faculty of Electrical Engineering Department of Control Engineering Karlovo náměstí 13 Prague Czech Republic

In this paper, we investigate the use of deep learning for solving a classical N P-hard single machine scheduling problem where the criterion is to minimize the total tardiness. Instead of designing an end-to-end machine learning model, we utilize well known decomposition of the problem and we enhance it with a data-driven approach. We have designed a regressor containing a deep neural network that learns and predicts the criterion of a given set of jobs. The network acts as a polynomial-time estimator of the criterion that is used in a single-pass scheduling algorithm based on Lawler's decomposition theorem. Essentially, the regressor guides the algorithm to select the best position for each job. The experimental results show that our data-driven approach can efficiently generalize information from the training phase to significantly larger instances (up to 350 jobs) where it achieves an optimality gap of about 0.5%, which is four times less than the gap of the state-of-the-art NBR heuristic. Copyright © 2020, The Authors. All rights reserved.

关键词： Scheduling algorithms

On idle energy consumption minimization in production: Industrial example and mathematical model

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Benedikt, Ondřej Šůcha, Přemysl Hanzálek, Zdeněk Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Jugoslávských partyzánů 1580/3 Prague Czech Republic Czech Technical University in Prague Faculty of Electrical Engineering Department of Control Engineering Karlovo náměstí 13 Prague Czech Republic

This paper, inspired by a real production process of steel hardening, investigates a scheduling problem to minimize the idle energy consumption of machines. The energy minimization is achieved by switching a machine to some power-saving mode when it is idle. For the steel hardening process, the mode of the machine (i.e., furnace) can be associated with its inner temperature. Contrary to the recent methods, which consider only a small number of machine modes, the temperature in the furnace can be changed continuously, and so an infinite number of the power-saving modes must be considered to achieve the highest possible savings. To model the machine modes efficiently, we use the concept of the energy function, which was originally introduced in the domain of embedded systems but has yet to take roots in the domain of production research. The energy function is illustrated with several application examples from the literature. Afterward, it is integrated into a mathematical model of a scheduling problem with parallel identical machines and jobs characterized by release times, deadlines, and processing times. Numerical experiments show that the proposed model outperforms a reference model adapted from the literature. Copyright © 2020, The Authors. All rights reserved.

关键词： Scheduling

Global, regional, and national burden of diabetes from 1990 to 2021, with projections of prevalence to 2050: a systematic analysis for the Global Burden of Disease Study 2021

学校读者我要写书评

暂无评论

The Lancet 2023年第10397期402卷 203-234页

作者： Ong, Kanyin Liane Stafford, Lauryn K. McLaughlin, Susan A. Boyko, Edward J. Vollset, Stein Emil Smith, Amanda E. Dalton, Bronte E. Duprey, Joe Cruz, Jessica A. Hagins, Hailey Lindstedt, Paulina A. Aali, Amirali Abate, Yohannes Habtegiorgis Abate, Melsew Dagne Abbasian, Mohammadreza Abbasi-Kangevari, Zeinab Abbasi-Kangevari, Mohsen ElHafeez, Samar Abd Abd-Rabu, Rami Abdulah, Deldar Morad Abdullah, Abu Yousuf Md Abedi, Vida Abidi, Hassan Aboagye, Richard Gyan Abolhassani, Hassan Abu-Gharbieh, Eman Abu-Zaid, Ahmed Adane, Tigist Demssew Adane, Denberu Eshetie Addo, Isaac Yeboah Adegboye, Oyelola A. Adekanmbi, Victor Adepoju, Abiola Victor Adnani, Qorinah Estiningtyas Sakilah Afolabi, Rotimi Felix Agarwal, Gina Aghdam, Zahra Babaei Agudelo-Botero, Marcela Arriagada, Constanza Elizabeth Aguilera Agyemang-Duah, Williams Ahinkorah, Bright Opoku Ahmad, Danish Ahmad, Rizwan Ahmad, Sajjad Ahmad, Aqeel Ahmadi, Ali Ahmadi, Keivan Ahmed, Ali Ahmed, Luai A. Ahmed, Syed Anees Ajami, Marjan Akinyemi, Rufus Olusola Al Hamad, Hanadi Al Hasan, Syed Mahfuz AL-Ahdal, Tareq Mohammed Ali Alalwan, Tariq A. Al-Aly, Ziyad AlBataineh, Mohammad T. Alcalde-Rabanal, Jacqueline Elizabeth Alemi, Sharifullah Ali, Hassam Alinia, Tahereh Aljunid, Syed Mohamed Almustanyir, Sami Al-Raddadi, Rajaa M. Alvis-Guzman, Nelson Amare, Firehiwot Ameyaw, Edward Kwabena Amiri, Sohrab Amusa, Ganiyu Adeniyi Andrei, Catalina Liliana Anjana, Ranjit Mohan Ansar, Adnan Ansari, Golnoosh Ansari-Moghaddam, Alireza Anyasodor, Anayochukwu Edward Arabloo, Jalal Aravkin, Aleksandr Y. Areda, Demelash Arifin, Hidayat Arkew, Mesay Armocida, Benedetta Arnlov, Johan Artamonov, Anton A. Arulappan, Judie Aruleba, Raphael Taiwo Arumugam, Ashokan Aryan, Zahra Asemu, Mulu Tiruneh Asghari-Jafarabadi, Mohammad Askari, Elaheh Asmelash, Daniel Astell-Burt, Thomas Athar, Mohammad Athari, Seyyed Shamsadin Atout, Maha Moh'd Wahbi Avila-Burgos, Leticia Awaisu, Ahmed Azadnajafabad, Sina Darshan, B.B. Babamohamadi, Hassan Badar, Muhammad Badawi, Alaa Badiye, Ashish D. Baghcheghi, Nayereh Baghe Institute for Health Metrics and Evaluation School of Medicine General Medicine Service Department of Veterans Affairs Seattle WA United States Department of Health Metrics Sciences School of Medicine Faculty of Medicine France Department of Clinical Governance and Quality Improvement Aleta Wondo Hospital Aleta Wondo Ethiopia Department of Nursing Woldia University Woldia Ethiopia Department of Nursing Department of Orthopedic Surgery Orthopaedic Surgery Social Determinants of Health Research Center Non-communicable Diseases Research Center Epidemiology Department Evidence-Based Practice Center Community and Maternity Nursing Unit University of Duhok Duhok Iraq School of Planning Faculty of Environment Department of Public Health Sciences Penn State College of Medicine Pennsylvania State University Hershey PA United States Biocomplexity Institute Virginia Tech Blacksburg VA United States College of Medicine Department of Public Health Laboratory Technology Sciences Department Department of Family and Community Health University of Health and Allied Sciences Ho Ghana Research Center for Immunodeficiencies Department of Biosciences and Nutrition Karolinska University Hospital Huddinge Sweden Clinical Sciences Department Department of Surgery Department of Surgery Department of Obstetrics & Gynecology College of Graduate Health Sciences University of Tennessee Memphis TN United States Department of Obstetrics & Gynecology Department of Clinical and Psychosocial Epidemiology Department of Anesthesia and Critical Care Centre for Social Research in Health Quality and Systems Performance Unit Cancer Institute NSW Sydney NSW Australia Department of Public Health and Tropical Medicine HIV and Infectious Diseases Department Jhpiego Abuja Nigeria Adolescent Research and Care Department Adolescent Friendly Research Initiative and Care Ado Ekiti Nigeria Department of Epidemiology Department of Epidemiology and Medical Statistics Department of Family Medicine McMaster University

Background: Diabetes is one of the leading causes of death and disability worldwide, and affects people regardless of country, age group, or sex. Using the most recent evidentiary and analytical framework from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD), we produced location-specific, age-specific, and sex-specific estimates of diabetes prevalence and burden from 1990 to 2021, the proportion of type 1 and type 2 diabetes in 2021, the proportion of the type 2 diabetes burden attributable to selected risk factors, and projections of diabetes prevalence through 2050. Methods: Estimates of diabetes prevalence and burden were computed in 204 countries and territories, across 25 age groups, for males and females separately and combined;these estimates comprised lost years of healthy life, measured in disability-adjusted life-years (DALYs;defined as the sum of years of life lost [YLLs] and years lived with disability [YLDs]). We used the Cause of Death Ensemble model (CODEm) approach to estimate deaths due to diabetes, incorporating 25 666 location-years of data from vital registration and verbal autopsy reports in separate total (including both type 1 and type 2 diabetes) and type-specific models. Other forms of diabetes, including gestational and monogenic diabetes, were not explicitly modelled. Total and type 1 diabetes prevalence was estimated by use of a Bayesian meta-regression modelling tool, DisMod-MR 2.1, to analyse 1527 location-years of data from the scientific literature, survey microdata, and insurance claims;type 2 diabetes estimates were computed by subtracting type 1 diabetes from total estimates. Mortality and prevalence estimates, along with standard life expectancy and disability weights, were used to calculate YLLs, YLDs, and DALYs. When appropriate, we extrapolated estimates to a hypothetical population with a standardised age structure to allow comparison in populations with different age structures. We used the comparative r

关键词：

Dynamic Resilient Network Games with Applications to Multi-Agent Consensus

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Nugraha, Yurid Cetinkaya, Ahmet Hayakawa, Tomohisa Ishii, Hideaki Zhu, Quanyan Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo152-8552 Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo101-8430 Japan Department of Computer Science Tokyo Insitute of Technology Yokohama226-8502 Japan Department of Electrical and Computer Engineering New York University BrooklynNY11201 United States

A cyber security problem in a networked system formulated as a resilient graph problem based on a game-theoretic approach is considered. The connectivity of the underlying graph of the network system is reduced by an attacker who removes some of the edges whereas the defender attempts to recover them. Both players are subject to energy constraints so that their actions are restricted and cannot be performed continuously. For this two-stage game, which is played repeatedly over time, we characterize the optimal strategies for the attacker and the defender in terms of edge connectivity and the number of connected components of the graph. The resilient graph game is then applied to a multi-agent consensus problem. We study how the attacks and the recovery on the edges affect the consensus process. Finally, we also provide numerical simulation to illustrate the results. Copyright © 2020, The Authors. All rights reserved.

关键词： Multi agent systems

Dexterous Manipulation through Imitation Learning: A Survey

学校读者我要写书评

暂无评论

arXiv 2025年

作者： An, Shan Meng, Ziyu Tang, Chao Zhou, Yuning Liu, Tengyu Ding, Fangqiang Zhang, Shufang Mu, Yao Song, Ran Zhang, Wei Hou, Zeng-Guang Zhang, Hong School of Electrical and Information Engineering Tianjin University Tianjin300072 China School of Control Science and Engineering Shandong University Jinan250061 China State Key Laboratory of General Artificial Intelligence Beijing100086 China Department of Mechanical and Process Engineering ETH Zurich Zurich8092 Switzerland Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China School of Informatics University of Edinburgh EH8 9AB United Kingdom Department of Computer Science University of Hong Kong 999077 Hong Kong State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China CASIA-MUST Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology 999078 China

Dexterous manipulation, which refers to the ability of a robotic hand or multi-fingered end-effector to skillfully control, reorient, and manipulate objects through precise, coordinated finger movements and adaptive force modulation, enables complex interactions similar to human hand dexterity. With recent advances in robotics and machine learning, there is a growing demand for these systems to operate in complex and unstructured environments. Traditional model-based approaches struggle to generalize across tasks and object variations due to the high-dimensionality and complex contact dynamics of dexterous manipulation. Although model-free methods such as reinforcement learning (RL) show promise, they require extensive training, large-scale interaction data, and carefully designed rewards for stability and effectiveness. Imitation learning (IL) offers an alternative by allowing robots to acquire dexterous manipulation skills directly from expert demonstrations, capturing fine-grained coordination and contact dynamics while bypassing the need for explicit modeling and large-scale trial-and-error. This survey provides an overview of dexterous manipulation methods based on imitation learning (IL), details recent advances, and addresses key challenges in the field. Additionally, it explores potential research directions to enhance IL-driven dexterous manipulation. Our goal is to offer researchers and practitioners a comprehensive introduction to this rapidly evolving domain. Copyright © 2025, The Authors. All rights reserved.

关键词： Grippers