检索结果-内蒙古大学图书馆

Journal of Bionanoscience 2018年第1期12卷 100-108页

作者： Li, Ting Zhou, Changjun Wang, Bin Xiao, Boxiang Zheng, Xuedong Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China Beijing Key Laboratory of Digital Plant Beijing100097 China

With the accomplishment of the Human Genome Project, the significance of protein structure research becomes more outstanding. The prediction of protein structure is aimed at the study of amino acid molecules, and belongs to the field of Bio-Nano research. There are two kinds of methods to study protein structure: Experiment and theory. This paper adopts ab-initio prediction method which is one of theoretical methods. Based on the "thermodynamic hypothesis," there are many different models applied to the field. This paper selects 3D AB off-lattice model to solve this problem. ABC-PIO combines the characteristics of the diversity generated by artificial bee colony algorithm and the fast convergence speed of pigeon inspired optimization. At the end of this algorithm, Cauchy perturbation strategy is added to optimize the local optimum. Two functions are introduced to dynamically control two operators of the hybrid algorithm. In order to test the quality of ABC-PIO, ten real protein sequences from the Protein Data Bank have been selected. Compared with other four algorithms, the algorithm gets better result. To calculate the error between the predicted and the true protein structure RMSD is set. Comparisons are made not only in the convergence curves but also in the backbone drawings. © 2018 American Scientific Publishers.

关键词： Optimization

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jian Sun, Wei Yang, Hui Zeng, Zhiwen Liu, Chongpei Zheng, Jin Liu, Xingyu Rahmani, Hossein Sebe, Nicu Mian, Ajmal The National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China The School of Architecture and Art Central South University Changsha410082 China The Department of Automation Tsinghua University Beijing100084 China The School of Computing and Communications Lancaster University LA1 4YW United Kingdom The Department of Information Engineering and Computer Science University of Trento Trento38123 Italy The Department of Computer Science The University of Western Australia WA6009 Australia

Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted conventional algorithms reliant on engineered point pair features. Nevertheless, several challenges persist in contemporary methods, including their dependency on labeled training data, model compactness, robustness under challenging conditions, and their ability to generalize to novel unseen objects. A recent survey discussing the progress made on different aspects of this area, outstanding challenges, and promising future directions, is missing. To fill this gap, we discuss the recent advances in deep learning-based object pose estimation, covering all three formulations of the problem, i.e., instance-level, category-level, and unseen object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks, providing the readers with a holistic understanding of this field. Additionally, it discusses training paradigms of different domains, inference modes, application areas, evaluation metrics, and benchmark datasets, as well as reports the performance of current state-of-the-art methods on these benchmarks, thereby facilitating the readers in selecting the most suitable method for their application. Finally, the survey identifies key challenges, reviews the prevailing trends along with their pros and cons, and identifies promising directions for future research. We also keep tracing the latest works at Awesome-Object-Pose-Estimation. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

DNA logic circuits based on FokI enzyme regulation

学校读者我要写书评

暂无评论

New Journal of Chemistry 2020年第5期44卷 1931-1941页

作者： Sue Zhao Yuan Liu Bin Wang Changjun Zhou Qiang Zhang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian 116622 China School of Computer Science and Technology Dalian University of Technology Dalian 116024 China College of Computer Science and Engineering Dalian Minzu University Dalian China

In biomolecular programming, researchers have attempted to use DNA molecules as a new kind of highly reliable raw material, due to the high predictability and good programmability of DNA molecules, and construct DNA circuits that can realize logical calculation. In DNA circuits with a multi-step cascade, autonomy, and complex behavior, it is very important to be able to controllably activate and regulate toeholds. Therefore, we propose a strategy using an enzyme-assisted cleavage regulation system to solve the above problems. In this strategy, the DNA input strand regulates the recognition domain of FokI and initiates the activity of FokI due to the reconfiguration of programmable information. In addition, FokI induced conformational changes regulate the toehold-mediated strand displacement reaction, which optimizes the complex function and the signal transmission of logic circuits. In order to prove the feasibility of this strategy, we constructed a series of logic gates (YES, AND, and INHIBIT), and on this basis, we successfully implemented both a demultiplexer circuit and a multiplexer cascade circuit. The proposed enzyme-assisted cleavage regulation strategy provides a new approach for constructing more complex molecular computing systems, with applications in biosensors and medical detection systems.

关键词：

Efficient Pyramid Channel Attention Network for Pathological Myopia Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiaoqing Zhao, Jilu Li, Yan Wu, Hao Zhou, Xiangtian Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China National Clinical Research Center for Ocular Diseases Eye Hospital Wenzhou Medical University Wenzhou325027 China State Key Laboratory of Ophthalmology Optometry and Visual Science Eye Hospital Wenzhou Medical University Wenzhou325027 China Research Unit of Myopia Basic Research and Clinical Prevention and Control Chinese Academy of Medical Sciences Wenzhou325027 China Singapore Eye Research Institute 169856 Singapore

Pathological myopia (PM) is the leading ocular disease for impaired vision worldwide. Clinically, the characteristic of pathology distribution in PM is global-local on the fundus image, which plays a significant role in assisting clinicians in diagnosing PM. However, most existing deep neural networks focused on designing complex architectures but rarely explored the pathology distribution prior of PM. To tackle this issue, we propose an efficient pyramid channel attention (EPCA) module, which fully leverages the potential of the clinical pathology prior of PM with pyramid pooling and multi-scale context fusion. Then, we construct EPCA-Net for automatic PM recognition based on fundus images by stacking a sequence of EPCA modules. Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters. In addition, we construct a PM recognition benchmark termed PM-fundus by collecting fundus images of PM from publicly available datasets. The comprehensive experiments demonstrate the superiority of EPCA-Net over state-of-the-art methods in the PM recognition task. For example, EPCA-Net achieves 97.56% accuracy and outperforms ViT by 2.85% accuracy on the PM-fundus dataset. The results also show that our method based on the pretraining-and-finetuning paradigm achieves competitive performance through comparisons to part of previous methods based on traditional fine-tuning paradigm with fewer tunable parameters, which has the potential to leverage more natural image foundation models to address the PM recognition task in limited medical data regime. Copyright © 2023, The Authors. All rights reserved.

关键词： Pathology

EXTRACTING ABSTRACTION DIMENSIONS BY IDENTIFYING SYNTAX PATTERN FROM TEXTS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhou, Jian Li, Jiazheng Zhuge, Sirui Zhuge, Hai Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China King’s College London United Kingdom Publicis Sapient United Kingdom School of Computing and Information Technology Great Bay University Dongguan China Great Bay Institute for Advanced Study Dongguan China

This paper proposed an approach to automatically discovering subject dimension, action dimension, object dimension and adverbial dimension from texts to efficiently operate texts and support query in natural language. The high quality of trees guarantees that all subjects, actions, objects and adverbials and their subclass relations within texts can be represented. The independency of trees ensures that there is no redundant representation between trees. The expressiveness of trees ensures that the majority of sentences can be accessed from each tree and the rest of sentences can be accessed from at least one tree so that the tree-based search mechanism can support querying in natural language. Experiments show that the average precision, recall and F1-score of the abstraction trees constructed by the subclass relations of subject, action, object and adverbial are all greater than 80%. The application of the proposed approach to supporting query in natural language demonstrates that different types of question patterns for querying subject or object have high coverage of texts, and searching multiple trees on subject, action, object and adverbial according to the question pattern can quickly reduce search space to locate target sentences, which can support precise operation on *** Codes 68T50 (Primary) 91F20 (Secondary) © 2025, CC BY.

关键词： Question answering

Half adder and half subtractor logic gates based on nicking enzymes

学校读者我要写书评

暂无评论

Molecular Systems design and Engineering 2019年第6期4卷 1103-1113页

作者： Zhao, Yunbin Liu, Yuan Zheng, Xuedong Wang, Bin Lv, Hui Zhou, Shihua Zhang, Qiang Wei, Xiaopeng Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian 116622 China School of Computer Science and Technology Dalian University of Technology Dalian 116024 China College of Computer Science Shenyang Aerospace University Shenyang 110136 China

The excellent specificity and predictability of DNA pairing and its natural ability to interact with other biomolecules make DNA an ideal material for building molecular logic devices (MLDs). However, there are still many challenges in the process of building such devices, including their complex structures, potentially harsh reaction conditions, long reaction times and so on. Thus, the parallel nature of DNA and other biomolecules needs to be developed before MLDs based on DNA can be exploited to a greater extent. In order to solve this problem, herein, we carefully selected two enzymes, *** and ***, that were both persistent and compatible, and used them to build a nicking enzyme platform. Based on this enzyme platform, we constructed a novel XOR logic gate with flexible internal signaling. Furthermore, AND and INHIBIT logic gates were also modified to use the same enzymes as the XOR logic gate as their inputs. As a result, the algorithm process of half adder and half subtractor was realized by this work. This study provides a new approach for typical DNA-based arithmetic operations and promotes the development of advanced MLDs. © 2019 The Royal Society of Chemistry.

关键词：

SPFCN: Select and Prune the Fully Convolutional Networks for Real-time Parking Slot Detection

学校读者我要写书评

暂无评论

SPFCN: Select and Prune the Fully Convolutional Networks for...

IEEE Symposium on intelligent Vehicle

作者： Zhuoping Yu Zhong Gao Hansheng Chen Yuyao Huang Institute of Intelligent Vehicles School of Automotive Studies Tongji University Shanghai China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body China

ISBN: (数字)9781728166735

ISBN: (纸本)9781728166742

For vehicles equipped with the automatic parking system, the accuracy and speed of the parking slot detection are crucial. But the high accuracy is obtained at the price of low speed or expensive computation equipment, which are sensitive for many car manufacturers. In this paper, we proposed a detector using CNN (convolutional neural networks) for faster speed and smaller model size while keeps accuracy. To achieve the optimal balance, we developed a strategy to select the best receptive fields and prune the redundant channels automatically after each training epoch. The proposed model is capable of jointly detecting corners and line features of parking slots while running efficiently in real time on average processors. The model has a frame rate of about 30 FPS on a 2.3 GHz CPU core, yielding parking slot corner localization error of 1.51±2.14 cm (std. err.) and slot detection accuracy of 98%, generally satisfying the requirements in both speed and accuracy on onboard mobile terminals.

关键词： Kernel Convolution Feature extraction Training Heating systems Task analysis Real-time systems

Research on Logistics Simulation and Optimization of Die Forging Production Line Based on Flexsim

学校读者我要写书评

暂无评论

Research on Logistics Simulation and Optimization of Die For...

作者： Qiang Cheng Hongchao Shen Hongyan Chu Zhifeng Liu Caixia Zhang Jiaxiang Ren Institute of Advanced Manufacturing and Intelligent Technology Beijing University of Technology Beijing Key Laboratory of Advanced Manufacturing Technology Beijing University of Technology Mechanical Industry Key Laboratory of Heavy Machine Tool Digital Design and Testing Beijing University of Technology

Long forging production cycle and low equipment utilization are the important problems currently facing domestic die forging ring production lines. To solve this problem, a simulation optimization method for die forging production line based on Flexsim was proposed. Firstly, the ECRS theory method was used to analyze the bottleneck process of the production line. Then, built a logistics simulation model of die forging production line based on Flexsim, The parallel and cycle processing steps was set reasonable parameters and simulated. Next, through logic analysis, methods such as adding processing equipment, improving equipment efficiency and balancing equipment handling tasks were used to optimize and improve the production line. Finally, compared and analyzed the original and optimized model. The simulation results show that the optimized production line equipment task allocation tends to be rationalized, the equipment utilization rate is increased by 4.34%, and the product cycle time is reduced by 27.65%, and optimized planning and design are achieved.

关键词： Production logistics Parallel processing Cyclic processing Flexsim, Modeling Simulation optimization

Mechanisms of strain rate effect on pure Ti deformation: Application in the bipolar plates forming process

学校读者我要写书评

暂无评论

Journal of Materials Processing Technology 2025年 342卷

作者： Guodong Pang Da Cai Hao Jiang Junjia Cui Guangyao Li Y.C. Lin State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan University Changsha 410082 China Shenzhen Automotive Research Institute Beijing Institute of Technology Shenzhen 518119 China Shenzhen Huashun Intelligent Equipment Co. Ltd Shenzhen 518119 China State Key Laboratory of Precision Manufacturing for Extreme Service Performance Central South University Changsha 410083 China

In the present research, the mechanical behavior of pure Ti was analyzed at room temperature under low strain rates (LSRs, 0.001 s −1 , 0.01 s −1 and 0.1 s −1 ) and high strain rates (HSRs, 1160 s −1 , 1670 s −1 and 2310 s −1 ). The results demonstrated that as the strain rate increased from 0.001 s −1 to 2310 s −1 , the elongation increased significantly by 27 %. The underlying mechanisms governing the strain rate dependence of plasticity were elucidated through microstructural analysis. The frequency of deformation twinning increased notably with strain rate. This effect was especially obvious during the transition from LSR to HSR. Deformation twinning inhibited dislocation motion and enhanced the work hardening capacity. Simultaneously, hard oriented grains (HOG) were found to play a significant role in the plastic deformation under HSR loading, enhancing the deformation coordination between grains and improving material deformation uniformity. This improvement in deformation uniformity mitigated premature localized strain and necking. Further, based on the plasticity-strengthening mechanism induced by HSR loading, an electro-hydraulic forming (EHF) method for the fabrication of pure titanium bipolar plates (Ti-BPPs) at room temperature. In comparison to the conventional LSR loading rubber pad forming (RPF) method, the EHF process significantly improved formability and addressed manufacturing challenges associated with pure Ti-BPPs. The proposed method successfully achieved the formation of complete flow channels with dimensional accuracy within a ± 10 μm tolerance. Additionally, the average thickness reduction in corner regions decreased from 34.2 % to 15.7 %. These findings provide theoretical insights that could guide the manufacturing of pure Ti-BPPs with thin walls and small structural sizes in industrial application.

关键词：

SPFCN: Select and prune the fully convolutional networks for real-time parking slot detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yu, Zhuoping Gao, Zhong Chen, Hansheng Huang, Yuyao Institute of Intelligent Vehicles School of Automotive Studies Tongji University Shanghai China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body China

For vehicles equipped with the automatic parking system, the accuracy and speed of the parking slot detection are crucial. But the high accuracy is obtained at the price of low speed or expensive computation equipment, which are sensitive for many car manufacturers. In this paper, we proposed a detector using CNN(convolutional neural networks) for faster speed and smaller model size while keeps accuracy. To achieve the optimal balance, we developed a strategy to select the best receptive fields and prune the redundant channels automatically after each training epoch. The proposed model is capable of jointly detecting corners and line features of parking slots while running efficiently in real time on average processors. The model has a frame rate of about 30 FPS on a 2.3 GHz CPU core, yielding parking slot corner localization error of 1.51±2.14 cm (std. err.) and slot detection accuracy of 98%, generally satisfying the requirements in both speed and accuracy on on-board mobile terminals. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution