检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Böhm, Stefan Neumayer, Martin Kramer, Oliver Schiendorfer, Alexander Knoll, Alois Research & Development Department Technische Hochschule Rosenheim Rosenheim Germany Chair of Robotics Artificial Intelligence and Real-time Systems Technische Universität München München Germany Institut für nachhaltige Energieversorgung Rosenheim Germany Research Institute AImotion Bavaria Technische Hochschule Ingolstadt Ingolstadt Germany

Cutting and Packing problems are occurring in different industries with a direct impact on the revenue of businesses. Generally, the goal in Cutting and Packing is to assign a set of smaller objects to a set of larger objects. To solve Cutting and Packing problems, practitioners can resort to heuristic and exact methodologies. Lately, machine learning is increasingly used for solving such problems. This paper considers a 2D packing problem from the furniture industry, where a set of wooden workpieces must be assigned to different modules of a trolley in the most space-saving way. We present an experimental setup to compare heuristics, constraint optimization, and deep reinforcement learning for the given problem. The used methodologies and their results get collated in terms of their solution quality and runtime. In the given use case a greedy heuristic produces optimal results and outperforms the other approaches in terms of runtime. Constraint optimization also produces optimal results but requires more time to perform. The deep reinforcement learning approach did not always produce optimal or even feasible solutions. While we assume this could be remedied with more training, considering the good results with the heuristic, deep reinforcement learning seems to be a bad fit for the given use case. © 2021, CC BY.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

real-time Cell Sorting with Scalable In Situ FPGA-Accelerated Deep Learning

arXiv

引用

arXiv 2025年

作者： Islam, Khayrul Forelli, Ryan F. Han, Jianzhong Bhadane, Deven Huang, Jian Agar, Joshua C. Tran, Nhan Ogrenci, Seda Liu, Yaling Department of Mechanical Engineering Lehigh University BethlehemPA18015 United States Department of Electrical and Computer Engineering Northwestern University EvanstonIL60208 United States Coriell Institute for Medical Research CamdenNJ United States Department of Computer Science Lehigh University BethlehemPA18015 United States Cooper Medical School of Rowan University CamdenNJ08103 United States Center for Metabolic Disease Research Temple University Lewis Katz School of Medicine PhiladelphiaPA19122 United States Department of Mechanical Engineering and Mechanics Drexel University PhiladelphiaPA19104 United States Real-time Processing Systems Division Fermi National Accelerator Laboratory BataviaIL60510 United States Department of Bioengineering Lehigh University BethlehemPA18015 United States

Precise cell classification is essential in biomedical diagnostics and therapeutic monitoring, particularly for identifying diverse cell types involved in various diseases. Traditional cell classification methods such as flow cytometry depend on molecular labeling which is often costly, time-intensive, and can alter cell integrity. To overcome these limitations, we present a label-free machine learning framework for cell classification, designed for real-time sorting applications using bright-field microscopy images. This approach leverages a teacher-student model architecture enhanced by knowledge distillation, achieving high efficiency and scalability across different cell types. Demonstrated through a use case of classifying lymphocyte subsets, our framework accurately classifies T4, T8, and B cell types with a dataset of 80,000 preprocessed images, accessible via an open-source Python package for easy adaptation. Our teacher model attained 98% accuracy in differentiating T4 cells from B cells and 93% accuracy in zero-shot classification between T8 and B cells. Remarkably, our student model operates with only 0.02% of the teacher model’s parameters, enabling field-programmable gate array (FPGA) deployment. Our FPGA-accelerated student model achieves an ultra-low inference latency of just 14.5 µs and a complete cell detection-to-sorting trigger time of 24.7 µs, delivering 12x and 40x improvements over the previous state-of-the-art real-time cell analysis algorithm in inference and total latency, respectively, while preserving accuracy comparable to the teacher model. This framework provides a scalable, cost-effective solution for lymphocyte classification, as well as a new SOTA real-time cell sorting implementation for rapid identification of subsets using in situ deep learning on off-the-shelf computing hardware. © 2025, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-level feature fusion model-based real-time person re-identification for forensics

Multi-level feature fusion model-based real-time person re-i...

引用

作者： Wang, Shiqin Xu, Xin Liu, Lei Tian, Jing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China Artificial Intelligence Institute Wuhan University of Science and Technology Wuhan430065 China Institute of Systems Science National University of Singapore Singapore119615 Singapore

Person forensics aims to retrieve the specified person across non-overlapping cameras. It is difficult owing to the appearance variations caused by occlusion, human pose change, background clutter, illumination variation, etc. In this scenario, current models face great challenges in extracting effective features. Recent deep learning models mainly focus on extracting representative deep features to cope with appearance variations, while handcrafted features are not fully explored. In this paper, a multi-level feature fusion model (MFFM) is designed to combine both deep features and handcrafted features in real time. MFFM is first utilized to describe person appearance. Then, local binary pattern (LBP) and histogram of oriented gradient (HOG) are extracted to cope with geometric change and illumination variance. Using LBP and HOG, 11.89% on the CUHK03, 15.30% on the Market-1501 and 8.25% on the VIPeR top-1 recognition accuracy improvement for the proposed method are achieved with only 9.66%, 4.90%, and 7.59% extra processing time. Experimental results indicate MFFM can achieve the best performance compared to the state-of-the-art models on the Market1501, CUHK03, and VIPeR datasets. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Development of a Cloud- and Edge-Architecture for adaptive model weight optimization of a CNN exemplified by optical detection of hairpin welding

Development of a Cloud- and Edge-Architecture for adaptive m...

引用

International Electric Drives Production Conference (EDPC)

作者： Johannes Vater Maximilian Kirschning Dominik Scheurenberg Dirk Abel Alois Knoll Planning and Production of Electrified Powertrains BMW Group Munich Germany Chair of Robotics Artificial Intelligence and Real-time Systems Technical University Munich Munich Germany Institute of Automatic Control RWTH Aachen University Aachen Germany

ISBN: (数字)9781728184586

ISBN: (纸本)9781728196145

The beginning of a global reorientation towards an increasingly conscientious approach to nature and the human habitat has been accompanied by changes in industry and society. The automotive industry, where a transition from combustion to electrically powered vehicles is currently underway, is also concerned with this change. In addition to increasing the capacity of the battery, improving the efficiency of the electric motor is essential. To achieve these goals, however, new technologies such as hairpins for the stator are needed. An important process step involves the welding of two pairs of hairpins, which often leads to welding defects. Nevertheless, expert knowledge in this field is limited. Optical monitoring of the welding process with the help of a convolutional neural network (CNN) is a good approach. This approach can compensate for the low level of expert knowledge and detects and classifies welding defects directly in the production line. However, the disadvantage of optical monitoring is that production conditions and the surrounding environment change over time. This has an impact on optical detection and can negatively affect the accuracy of a CNN. For example, the camera perspective can change, which has a negative effect on optical quality monitoring. Therefore, this paper presents an approach for monitoring and evaluating the quality of a CNN in a cloud instance online. If a deteriorating quality is detected, the CNN in the cloud is re-trained by continuously collected data and then automatically deployed to the production line. This allows the CNN to adapt to the changing environmental conditions. The present approach is demonstrated and validated with real data of the stator production process. Compared with the current state-of-the-art, this control loop is highly automated and requires a minimum of human intervention.

关键词： Industries Welding Production Optical computing Stators Monitoring Optimization

来源：评论

学校读者我要写书评

暂无评论

Event-based robotic grasping detection with neuromorphic vision sensor and event-stream dataset

arXiv

引用

arXiv 2020年

作者： Li, Bin Cao, Hu Qu, Zhongnan Hu, Yingbai Wang, Zhenke Liang, Zichen JingDong Group Beijing China Tongji University Shanghai China Chair of Robotics Artificial Intelligence and Real-time Systems Technische Universität München München Germany Computer Eng. and Networks Lab ETH Zurich Switzerland

Robotic grasping plays an important role in the field of robotics. The current state-of-the-art robotic grasping detection systems are usually built on the conventional vision, such as RGB-D camera. Compared to traditional frame-based computer vision, neuromorphic vision is a small and young community of research. Currently, there are limited event-based datasets due to the troublesome annotation of the asynchronous event stream. Annotating large scale vision dataset often takes lots of computation resources, especially the troublesome data for video-level annotation. In this work, we consider the problem of detecting robotic grasps in a moving camera view of a scene containing objects. To obtain more agile robotic perception, a neuromorphic vision sensor (DAVIS) attaching to the robot gripper is introduced to explore the potential usage in grasping detection. We construct a robotic grasping dataset named Event-Stream Dataset with 91 objects. A spatio-temporal mixed particle filter (SMP Filter) is proposed to track the led-based grasp rectangles which enables video-level annotation of a single grasp rectangle per object. As leds blink at high frequency, the Event-Stream dataset is annotated in a high frequency of 1 kHz. Based on the Event-Stream dataset, we develop a deep neural network for grasping detection which consider the angle learning problem as classification instead of regression. The method performs high detection accuracy on our Event-Stream dataset with 93% precision at object-wise level. This work provides a large-scale and well-annotated dataset, and promotes the neuromorphic vision applications in agile robot. Copyright © 2020, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Design and control of a highly redundant rigid–flexible coupling robot to assist the COVID-19 oropharyngeal-swab sampling

arXiv

引用

arXiv 2021年

作者： Hu, Yingbai Li, Jian Chen, Yongquan Wang, Qiwen Chi, Chuliang Zhang, Heng Gao, Qing Lan, Yuanmin Li, Zheng Mu, Zonggao Sun, Zhenglong Knoll, Alois Robotics and Intelligent Manufacturing & School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society 518129 China Chair of Robotics Artificial Intelligence and Real-time Systems Technische Universität München München85748 Germany Department of surgery Chow Yuk Ho Technology Centre for Innovative Medicine The Chinese University of Hong Kong Hong Kong School of Mechanical Engineering Shandong University of Technology Zibo255000 China Longgang District People’s Hospital of Shenzhen 518172 China

The outbreak of novel coronavirus pneumonia (COVID-19) has caused mortality and morbidity worldwide. Oropharyngeal-swab (OP-swab) sampling is widely used for the diagnosis of COVID-19 in the world. To avoid the clinical staff from being affected by the virus, we developed a 9-degree-of-freedom (DOF) rigid–flexible coupling (RFC) robot to assist the COVID-19 OP-swab sampling. This robot is composed of a visual system, UR5 robot arm, micro-pneumatic actuator and force-sensing system. The robot is expected to reduce risk and free up the clinical staff from the long-term repetitive sampling work. Compared with a rigid sampling robot, the developed force-sensing RFC robot can facilitate OP-swab sampling procedures in a safer and softer way. In addition, a varying-parameter zeroing neural network-based optimization method is also proposed for motion planning of the 9-DOF redundant manipulator. The developed robot system is validated by OP-swab sampling on both oral cavity phantoms and volunteers. Copyright © 2021, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A realistic simulation environment as a teaching aid in educational robotics

A realistic simulation environment as a teaching aid in educ...

引用

IEEE Latin American robotics Symposium, LARS

作者： José Lima Rebeca B. Kalbermatter João Braun Thadeu Brito Guido Berger Paulo Costa Research Centre in Digitalization and Intelligent Robotics (CeDRI) Instituto Politécnico de Bragança (IPB) Bragança Portugal Laboratório para a Sustentabilidade e Tecnologia em Regiões de Montanha (SusTEC) Instituto Politécnico de Bragança (IPB) Bragança Portugal Centre for Robotic in Industry and Intelligent Systems Institute for Systems and Computer Engineering Technology and Science (INESC-TEC) Porto Portugal Faculdade de Engenharia Universidade do Porto Porto Portugal Universidade de Trás-os-Montes e Alto Douro Vila Real Portugal

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

The experimental component is an essential method in Engineering education. Sometimes the availability of laboratories and components is compromised, and the COVID-19 pandemic worsened the situation. Resorting to an accurate simulation seems to help this process by allowing students to develop the work, program, test, and validate it. Moreover, it lowers the development time and cost of the prototyping stages of a robotics project. As a multidisciplinary area, robotics requires simulation environments with essential characteristics, such as dynamics, connection to hardware (embedded systems), and other applications. Thus, this paper presents the Simulation environment of SimTwo, emphasizing previous publications with models of sensors, actuators, and simulation scenes. The simulator can be used for free, and the source code is available to the community. Proposed scenes and examples can inspire the development of other simulation scenes to be used in electrical and mechanical Engineering projects.

关键词： Mechanical sensors Embedded systems Pandemics Source coding Laboratories Sensor phenomena and characterization Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Next-generation smart homes: CO 2 monitoring with Matter protocol to support indoor air quality

Internet of Things

引用

Internet of Things 2025年 32卷

作者： Afonso Mota Carlos Serôdio Ana Briga-Sá Antonio Valente Department of Engineering School of Sciences and Technology Universidade de Trás-os-Montes e Alto Douro (UTAD) 5000-801 Vila Real Portugal Center ALGORITMI Universidade do Minho Campus de Azurém Guimarães 4800-058 Portugal CQ-VR (Center of Chemistry of Vila Real) Universidade de Trás-os-Montes e Alto Douro 5000-801 Vila Real Portugal CRIIS (Centre for Robotics in Industry and Intelligent Systems) INESC-TEC—Institute for Systems and Computer Engineering Technology and Science Campus da FEUP Porto 4200-465 Portugal

Humans spend most of their time indoors, where air quality and comfort are crucial to health and well-being. Elevated CO 2 levels in buildings can reduce cognitive function, discomfort, and health issues. Indoor CO 2 monitoring has emerged as a key focus in the literature, particularly in residential buildings, as it can play a vital role in helping to maintain adequate ventilation rates. The growing smart home market demands seamless integration and control, which are essential for implementing IAQ sensing devices. However, interoperability barriers between platforms and devices continue to hinder smart home adoption. To address these challenges, Matter protocol is starting to appear in the market. In this work, a wireless CO 2 sensor is developed based on ESP32-C6 and SCD40 and integrated into a created Matter-enabled ecosystem formed with the Home Assistant open-source platform. The utilized hardware and software enable the usage of two different wireless communication technologies, WiFi and Thread, enhancing compatibility. The study highlights the rapid and seamless onboarding of the developed CO 2 monitoring device into smart home ecosystems using the Matter protocol. As a result, once the device is successfully added to the ecosystem, the measurements can be accessed and analyzed through a mobile application, forming an IoT environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benchmark of Automated Machine Learning with State-of-the-Art Image Segmentation Algorithms for Tool Condition Monitoring

引用

Procedia Manufacturing 2020年 51卷 215-221页

作者： B. Lutz R. Reisch D. Kisskalt B. Avci D. Regulin A. Knoll J. Franke Siemens AG Otto-Hahn-Ring 6 81739 München Germany Institute for Factory Automation and Production Systems Friedrich-Alexander University Erlangen-Nürnberg Egerlandstr. 9 91058 Erlangen Germany Chair of Robotics Artificial Intelligence and Real-time Systems Technical University of Munich Boltzmannstraße 3 85748 Garching at Munich Germany

In condition monitoring of cutting inserts for machine tools, vision-based solutions enable detailed wear pattern analysis. Besides the main failure modes of flank wear and tool breakage, other defects, such as chipping, grooves, and build-up-edges, can be detected and quantified. However, manual analysis of the images is time consuming and traditional machine vision systems have limited capabilities adapting to changing situations, such as different insert types. As a result, robust machine learning techniques are researched to support the process of classifying images and detecting defects through image segmentation. For the latter, a variety of highly optimized networks exists. Still, these networks require tuning by machine learning experts. In contrast, automated machine learning is a recent trend that greatly reduces these efforts through automated network selection and hyperparameter optimization. In this study, automated machine learning is compared with manually trained segmentation networks on the example of tool condition monitoring. To achieve this, a heterogeneous dataset of over 200 industrial cutting tool images is recorded and evaluated. Comparing the manually trained segmentation networks to the automated machine learning framework, it is determined that the automated machine learning solution is easier to handle, faster to train and achieves better accuracies than other approaches.

关键词： Tool Condition Monitoring Image Segmentation Machine Learning Automated Machine Learning

来源：评论

学校读者我要写书评

暂无评论

A General Gray Code Quantized Method of Binary Feature Descriptors for Fast and Efficient Keypoint Matching

A General Gray Code Quantized Method of Binary Feature Descr...

引用

International Conference on Intelligent Autonomous systems (ICoIAS)

作者： Yunhan Lin Yalan Sun Huasong Min College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial Systems Wuhan China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan China

In this paper, a general Gray code quantized method of binary feature descriptors is proposed for fast and efficient keypoint matching on 3D point clouds. In our method, it includes 2 variable L and N. L is rule variable which can be used to set the encoding group length according to the feature of the real-valued descriptor, and N is bits variable which can be used to set the number of Gray code bits according to the actual system requirements. Be different from the exist method, such as B-SHOT, our proposed method has the advantages of reasonable and flexible. As an example, our method is applied on the feature descriptor SHOT and tested in a standard benchmark dataset, different variable combinations of L and N are tested in the Gray code quantized processes, the best combination of L and N is dubbed as GRAY-SHOT through performance comparison. At last, GRAY-SHOT is compared with the state-of-the-art binary 3D feature descriptor B-SHOT, experimental evaluation result shows that GRAY-SHOT offers better keypoint matching performances to B-SHOT on a standard benchmark dataset with a slight more memory footprint and time consumption.

关键词： Three-dimensional displays Reflective binary codes Encoding Histograms Feature extraction Standards Benchmark testing

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：