检索结果-内蒙古大学图书馆

A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Fubao Zhao, Jinyu Zhao, Chen Tang, Shaojie Nan, Jiaofen Li, Yanting Zhao, Zhongqiang Shi, Jianzhou Chen, Zenghong Jiang, Zhixin Zhou, Weihua School of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou450001 China Department of Applied Computing Michigan Technological University HoughtonMI49931 United States School of Automation Xi'an University of Posts and Telecommunications Shaanxi Xi'An710121 China Department of Cardiology The First Affiliated Hospital of Nanjing Medical University Jiangsu Provincial Hospital Nanjing210000 China Center for Biocomputing and Digital Health Institute of Computing and Cybersystems Health Research Institute Michigan Technological University HoughtonMI49931 United States

Background: The assessment of left ventricular (LV) function by myocardial perfusion SPECT (MPS) relies on accurate myocardial segmentation. The purpose of this paper is to develop and validate a new method incorporating deep learning with shape priors to accurately extract the LV myocardium for automatic measurement of LV functional parameters. Methods: A segmentation architecture that integrates a three-dimensional (3D) V-Net with a shape deformation module was developed. Using the shape priors generated by a dynamic programming (DP) algorithm, the model output was then constrained and guided during the model training for quick convergence and improved performance. An MPS dataset, including 31 subjects without or with mild ischemia, 32 subjects with moderate ischemia, and 12 subjects with severe ischemia, were retrospectively analyzed;myocardial contours were manually annotated as the ground truth. A stratified 5-fold cross-validation was used to train and validate our models. Left ventricular end-systolic volume (ESV), end-diastolic volume (EDV), ejection fraction (LVEF), and scar burden were measured from extracted myocardial contours to evaluate the clinical performance. Results: Results of our proposed method agree well with those from the ground truth. Our proposed model achieved a Dice similarity coefficient (DSC) of 0.9573±0.0244, 0.9821±0.0137, and 0.9903±0.0041, a Hausdorff distances (HD) of 6.7529±2.7334 mm, 7.2507±3.1952 mm, and 7.6121±3.0134 mm in extracting the endocardium, myocardium, and epicardium, respectively. The correlation coefficients between LVEF, ESV, EDV, stress scar burden, and rest scar burden measured from the optimal model in the stratified 5-fold cross-validation and those from the ground truth were 0.92, 0.958, 0.952, 0.972, and 0.958, respectively. Conclusion: Our proposed method achieved a high accuracy in extracting LV myocardial contours and assessing LV function. Future studies will further improve our method and investigate the

关键词： Image segmentation

Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Zihao Zhang, Lu Cao, Chao Yu, Xiaowei Dai, Haixing Ma, Chong Liu, Zhengliang Zhao, Lin Li, Gang Liu, Wei Li, Quanzheng Shen, Dinggang Li, Xiang Zhu, Dajiang Liu, Tianming School of Computing The University of Georgia Athens30602 United States Department of Computer Science and Engineering The University of Texas at Arlington Arlington76019 United States School of Automation Northwestern Polytechnical University Xi’an710072 China Department of Radiology and BRIC University of North Carolina Chapel Hill Chapel Hill27599 United States Department of Radiation Oncology Mayo Clinic Phoenix85054 United States Department of Radiology Massachusetts General Hospital Harvard Medical School Boston02115 United States School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200230 China Shanghai Clinical Research and Trial Center Shanghai201210 China

Recently, ChatGPT and GPT-4 have emerged and gained immense global attention due to their unparalleled performance in language processing. Despite demonstrating impressive capability in various open-domain tasks, their adequacy in highly specific fields like radiology remains untested. Radiology presents unique linguistic phenomena distinct from open-domain data due to its specificity and complexity. Assessing the performance of large language models (LLMs) in such specific domains is crucial not only for a thorough evaluation of their overall performance but also for providing valuable insights into future model design directions: whether model design should be generic or domain-specific. To this end, in this study, we evaluate the performance of ChatGPT/GPT-4 on a radiology NLI task and compare it to other models fine-tuned specifically © 2023, CC BY.

关键词： Radiology

Correlating the Effect of Covid-19 Lockdown with Mobility Impacts: A Time Series Study Using Noise Sensors Data

学校读者我要写书评

暂无评论

Transportation Research Procedia 2022年 62卷 115-122页

作者： Antonio Pascale Simona Mancini Pedro M. d’Orey Claudio Guarnaccia Margarida C. Coelho Centre for Mechanical Technology and Automation Dept. of Mechanical Engineering University of Aveiro Campus Universitário de Santiago 3801-193 Aveiro Portugal Department of Information and Electric Engineering and Applied Mathematics University of Salerno Via Giovanni Paolo II 132 I-84084 Fisciano Italy Real-Time and Embedded Computing Systems Research Centre (CISTER) ISEP IPP Rua Dr. António Bernardino de Almeida 431 4200-072 Porto Portugal Dept. of Civil Engineering University of Salerno Via Giovanni Paolo II 132 I-84084 Fisciano Italy

The Covid-19 crisis forced governments around the world to rapidly enact several restrictions to face the associated health emergency. The Portuguese government was no exception and, following the example of other countries, established various limitations to flat the contagions curve. This led to inevitable repercussions on mobility and environmental indicators including noise. This research aims to assess the impact of the lockdown due to Covid-19 disease on the noise levels recorded in the city of Porto, Portugal. Data from four noise sensors located in strategic spots of the city were used to calibrate and validate Time Series Models, allowing to impute the missing values in the datasets and rebuild them. The trend and the cyclic information were extracted from the reconstructed datasets using decomposition techniques. Finally, a Spearman correlation analysis between noise levels values and traffic volumes (extracted from five inductive loop detectors, located nearby the noise sensors) was performed. Results show that the noise levels series present a daily seasonal pattern and the trends values decreased from 6.7 to 7.5 dBA during the first lockdown period (March-May 2020). Moreover, the noise levels tend to gradually rise after the removal of restrictions. Finally, there is a monotonic relationship between noise levels and traffic volumes values, as confirmed by the positive moderate-to-high correlation coefficients found, and the sharp drop of the former during March-May 2020 can be attributed to the strong reduction of road traffic flows in the city.

关键词： Traffic Noise Time Series Models Covid-19 Inductive Loops

Scaling Solar Photocatalytic Hydrogen Production in China: Integrated Geospatial-Meteorological Analysis

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Li, Yinan Li, Lanyu Yuan, Hongkuan He, Keji Chen, Hong Xie, Jianping Wang, Biao Wang, Xiaonan School of Physical Science and Technology Southwest University Chongqing400715 China Department of Chemical and Biomolecular Engineering National University of Singapore Singapore117585 Singapore Department of Chemical Engineering Tsinghua University Beijing100084 China China Oilfield Services Limited Yanjiao065201 China Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing101408 China School of Resources and Environment Institute of Fundamental and Frontier Science University of Electronic Science and Technology of China Chengdu611731 China Chongqing key Laboratory of Micro Nano Structure Optoelectronics School of Physical Science and Technology Southwest University Chongqing400715 China

Solar photocatalytic hydrogen production is considered a promising technology owing to its sustainable nature, while facing the challenges of improving and maintaining photocatalytic efficiency under prolonged variable weather conditions. Herein, we screen out the MoTe2/ZrS2 system with a theoretical solar-to-hydrogen conversion efficiency of 10.37%. To improve the actual efficiency among all 97,711 grid cells in China, we propose an original meteorological data-driven machine learning model to optimize photocatalytic H2 production and results show that the annual average STH efficiency gives a mean of 3.16% within a range of 0.44% – 4.91% . Incorporating geospatial data, we determine that China's photocatalytic H2 potential is about 216.65 Mt/year, which has been improved by almost sixfold compared to that without optimization, and the country’s 2060 hydrogen demand can be met by using 11.08% of its total land area. Compared with photovoltaic electrolysis, a photocatalyst cost of 23 USD/m2cat/103hrs would make photocatalysis economically competitive. Last, considering hydrogen production fluctuations, we explore optimal operation of hydrogen storage and utilization facilities to fulfil downstream demands. © 2024, The Authors. All rights reserved.

关键词： Hydrogen production

ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhong, Tianyang Wei, Yaonai Yang, Li Wu, Zihao Liu, Zhengliang Wei, Xiaozheng Li, Wenjun Yao, Junjie Ma, Chong Li, Xiang Zhu, Dajiang Jiang, Xi Han, Junwei Shen, Dinggang Liu, Tianming Zhang, Tuo School of Automation Northwestern Polytechnical University Xi'An710072 China School of Computing The University of Georgia Athens30602 United States Department of Radiology Massachusetts General Hospital Harvard Medical School Boston02115 United States Department of Computer Science and Engineering The University of Texas at Arlington Arlington76019 United States School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200230 China Shanghai Clinical Research and Trial Center Shanghai201210 China School of life science and technology University of Electronic Science and Technology of China Chengdu611731 China

Large language models (LLMs) such as ChatGPT have recently demonstrated significant potential in mathematical abilities, providing valuable reasoning paradigm consistent with human natural language. However, LLMs currently have difficulty in bridging perception, language understanding and reasoning capabilities due to incompatibility of the underlying information flow among them, making it challenging to accomplish tasks autonomously. On the other hand, abductive learning (ABL) frameworks for integrating the two abilities of perception and reasoning has seen significant success in inverse decipherment of incomplete facts, but it is limited by the lack of semantic understanding of logical reasoning rules and the dependence on complicated domain knowledge representation. This paper presents a novel method (ChatABL) for integrating LLMs into the ABL framework, aiming at unifying the three abilities in a more user-friendly and understandable manner. The proposed method uses the strengths of LLMs' understanding and logical reasoning to correct the incomplete logical facts for optimizing the performance of perceptual module, by summarizing and reorganizing reasoning rules represented in natural language format. Similarly, perceptual module provides necessary reasoning examples for LLMs in natural language format. The variable-length handwritten equation deciphering task, an abstract expression of the Mayan calendar decoding, is used as a testbed to demonstrate that ChatABL has reasoning ability beyond most existing state-of-the-art methods, which has been well supported by comparative studies. To our best knowledge, the proposed ChatABL is the first attempt to explore a new pattern for further approaching human-level cognitive ability via natural language interaction with ChatGPT. © 2023, CC BY.

关键词： Semantics

A Kind of Lean Approach for Removing Wastes From Non-Manufacturing Process With Various Facilities

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 307-315页

作者： Guangyu Xiong Xiuqin Shang Gang Xiong Timo R.Nyberg IEEE the Silk Road Business School Sanya University the Department of Industrial Engineering and Management School of ScienceAalto University the State Key Laboratory for Management and Controlof Complex Systems Institute of AutomationChinese Academy of Sciences(CAS) Qingdao Academy of Intelligent Industries the Cloud Computing Center CAS the Beijing Engineering Research Center of Intelligent Systems and Technology Institute of AutomationCAS the School of Science at Aalto University

It is important to identify and remove the wastes not only from manufacturing process, but also from nonmanufacturing process. In the last several decades, significant research achievements and practice benefits have been achieved about removing wastes from manufacturing process. Since the1990 s, some researchers and lean practitioners have paid more attention to removing waste from non-manufacturing *** on the authors' research work and industrial practice, the paper introduces a kind of lean approach for removing waste from non-manufacturing process. In its case study, the order handling process in a value chain is described with respect to a factory and its downstream distribution centers(DCs). The paper proposes a lean approach solution for creating the improved order handling process, and analyze how great improvements in performance can be achieved. As a result, the significant achievement has created a win-win scenario for both the nonmanufacturing process in a factory and non-manufacturing facilities(like DCs) across the value chain. It demonstrates that improvements have been made by removing waste from the non-manufacturing process that takes place within a factory as well as with external participants through the whole value chain. Likewise, the proposed lean approach has helped the case companies to achieve greater levels of efficiency and more benefits. Finally, some conclusions are drawn.

关键词： Lean approach non-manufacturing process optimized order handling process removing wastes value chain win-win scenario

Model-free design of stochastic lqr controller from reinforcement learning and primal-dual optimization perspective

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Man Qin, Jiahu Zheng, Wei Xing Wang, Yaonan Kang, Yu Department of Automation University of Science and Technology of China Hefei230027 China School of Computing Engineering and Mathematics Western Sydney University SydneyNSW2751 Australia College of Electrical and Information Engineering Hunan University Changsha410082 China National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha410082 China

To further understand the underlying mechanism of various reinforcement learning (RL) algorithms and also to better use the optimization theory to make further progress in RL, many researchers begin to revisit the linear-quadratic regulator (LQR) problem, whose setting is simple and yet captures the characteristics of RL. Inspired by this, this work is concerned with the model-free design of stochastic LQR controller for linear systems subject to Gaussian noises, from the perspective of both RL and primal-dual optimization. From the RL perspective, we first develop a new model-free off-policy policy iteration (MF-OPPI) algorithm, in which the sampled data is repeatedly used for updating the policy to alleviate the data-hungry problem to some extent. We then provide a rigorous analysis for algorithm convergence by showing that the involved iterations are equivalent to the iterations in the classical policy iteration (PI) algorithm. From the perspective of optimization, we first reformulate the stochastic LQR problem at hand as a constrained non-convex optimization problem, which is shown to have strong duality. Then, to solve this non-convex optimization problem, we propose a model-based primal-dual (MBPD) algorithm based on the properties of the resulting Karush-Kuhn-Tucker (KKT) conditions. We also give a model-free implementation for the MB-PD algorithm by solving a transformed dual feasibility condition. More importantly, we show that the dual and primal update steps in the MB-PD algorithm can be interpreted as the policy evaluation and policy improvement steps in the PI algorithm, respectively. Finally, we provide one simulation example to show the performance of the proposed algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

Comparative evaluation of training schemes for the locally recurrent probabilistic neural network 28

学校读者我要写书评

暂无评论

Comparative evaluation of training schemes for the locally r...

28th International Scientific Conference Electronics, ET 2019 - Proceedings

作者： Dukov, Nikolay Tinkov Ganchev, Todor Dimitrov Department of Computer Science and Engineering Faculty of Computing and Automation Technical University of Varna 1 Studentska str. Varna9000 Bulgaria

ISBN: (纸本)9781728125749

In the present study we evaluate the performance of various training schemes for the locally recurrent probabilistic neural network and seek for advantageous tradeoffs between required training time and classification accuracy. Specifically, we consider training schemes which make use of a simple incremental procedure for adjusting sigma, as well as methods based on particle swarm optimization or differential evolution in different configurations. The experimental evaluation was carried out in common experimental protocol based on the Parkinson speech dataset. The experimental results show that with a proper training configuration a high accuracy can be achieved even with limited training data. © 2019 IEEE.

关键词： Particle swarm optimization (PSO)

Boosting Personalised Musculoskeletal Modelling with Physics-informed Knowledge Transfer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Jie Zhao, Yihui Bao, Tianzhe Li, Zhenhong Qian, Kun Frangi, Alejandro F. Xie, Sheng Quan Zhang, Zhi-Qiang The School of Electronic and Electrical Engineering University of Leeds LeedsLS2 9JT United Kingdom The School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China The School of Rehabilitation Sciences and Engineering University of Health and Rehabilitation Sciences Qingdao261000 China The School of Computing University of Leeds LeedsLS2 9JT United Kingdom The Alan Turing Institute LondonNW1 2DB United Kingdom The Department of Electrical Engineering KU Leuven Leuven3000 Belgium

Data-driven methods have become increasingly more prominent for musculoskeletal modelling due to their conceptually intuitive simple and fast implementation. However, the performance of a pre-trained data-driven model using the data from specific subject(s) may be seriously degraded when validated using the data from a new subject, hindering the utility of the personalised musculoskeletal model in clinical applications. This paper develops an active physics-informed deep transfer learning framework to enhance the dynamic tracking capability of the musculoskeletal model on the unseen data. The salient advantages of the proposed framework are twofold: 1) For the generic model, physics-based domain knowledge is embedded into the loss function of the data-driven model as soft constraints to penalise/regularise the data-driven model. 2) For the personalised model, the parameters relating to the feature extraction will be directly inherited from the generic model, and only the parameters relating to the subject-specific inference will be fine-tuned by jointly minimising the conventional data prediction loss and the modified physics-based loss. In this paper, we use the synchronous muscle forces and joint kinematics prediction from surface electromyogram (sEMG) as the exemplar to illustrate the proposed framework. Moreover, convolutional neural network (CNN) is employed as the deep neural network to implement the proposed framework, and the physics law between muscle forces and joint kinematics is utilised as the soft constraints. Results of comprehensive experiments on a self-collected dataset from eight healthy subjects indicate the effectiveness and great generalization of the proposed framework. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks