检索结果-内蒙古大学图书馆

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Elie Saad Joost Broekens Mark A. Neerincx Department of Intelligent Systems Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft The Netherlands School of Engineering Holy Spirit University of Kaslik Jounieh Lebanon The Leiden Institute of Advanced Computer Science Leiden University Leiden The Netherlands The Netherlands Organization for Applied Scientific Research (TNO) Soesterberg The Netherlands

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Whereas the reception task is a promising application domain for social robots, knowledge is lacking about how to design the appropriate re-usable communication styles for a reception robot. This paper presents the use and evaluation of an iterative interaction-design (ID) method with which task- and person-oriented multi-modal communication styles have been designed for such a robot. First, we report on an evaluation study of the ID-method with Industrial Design students (N =13) who designed these two communication styles for a Pepper robot. This provided a set of distinct designs of the two styles, for which the differences in design parameters were in line with social science theory. The task-oriented style showed a more formal, shorter and less chatty communication. Second, we present findings from a Mechanical Turk study conducted to evaluate the perception of these style designs. Participants (N =301) were presented with videos showing the robot acting as a receptionist and were asked to rate their perception of the robot, the service experience and the orientation of the designs. Overall, the interaction with the robot was appreciated well. The robot with a person-oriented style was perceived to be more animate and likeable. Analysis showed that chit-chat was the main contributor to the perceived difference between the person-oriented and task-oriented styles. This is an important finding as it gives interaction designers a validated best-practice approach to make interaction style more or less personal.

关键词： Service robots Social robots Design tools Behavioral sciences Iterative methods Robots Videos

来源：评论

学校读者我要写书评

暂无评论

FLATTENING SINGULAR VALUES OF FACTORIZED CONVOLUTION FOR MEDICAL IMAGES

arXiv

引用

arXiv 2024年

作者： Feng, Zexin Zeng, Na Fang, Jiansheng Wang, Xingyue Lu, Xiaoxi Meng, Heng Liu, Jiang Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Guangzhou Native-Stone Intelligent-Brain Technology Co. Ltd. Guangzhou China Department of Neurology The First Affiliated Hospital of Jinan University Guangzhou China

Convolutional neural networks (CNNs) have long been the paradigm of choice for robust medical image processing (MIP). Therefore, it is crucial to effectively and efficiently deploy CNNs on devices with different computing capabilities to support computer-aided diagnosis. Many methods employ factorized convolutional layers to alleviate the burden of limited computational resources at the expense of expressiveness. To this end, given weak medical image-driven CNN model optimization, a Singular value equalization generalizer-induced Factorized Convolution (SFConv) is proposed to improve the expressive power of factorized convolutions in MIP models. We first decompose the weight matrix of convolutional filters into two low-rank matrices to achieve model reduction. Then minimize the KL divergence between the two low-rank weight matrices and the uniform distribution, thereby reducing the number of singular value directions with significant variance. Extensive experiments on fundus and OCTA datasets demonstrate that our SFConv yields competitive expressiveness over vanilla convolutions while reducing complexity. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Models

arXiv

引用

arXiv 2024年

作者： Carvalho, João Le, An T. Kicki, Piotr Koert, Dorothea Peters, Jan Intelligent Autonomous Systems Lab Computer Science Department Technical University of Darmstadt Germany Poznan University of Technology Poland IDEAS NCBR Warsaw Poland Centre for Cognitive Science Technical University of Darmstadt Germany Research Department: SAIROL Darmstadt Germany Hessian.AI Darmstadt Germany

—The performance of optimization-based robot motion planning algorithms is highly dependent on the initial solutions, commonly obtained by running a sampling-based planner to obtain a collision-free path. However, these methods can be slow in high-dimensional and complex scenes and produce non-smooth solutions. Given previously solved path-planning problems, it is highly desirable to learn their distribution and use it as a prior for new similar problems. Several works propose utilizing this prior to bootstrap the motion planning problem, either by sampling initial solutions from it, or using its distribution in a maximum-a-posterior formulation for trajectory optimization. In this work, we introduce Motion Planning Diffusion (MPD), an algorithm that learns trajectory distribution priors with diffusion models. These generative models have shown increasing success in encoding multimodal data and have desirable properties for gradient-based motion planning, such as cost guidance. Given a motion planning problem, we construct a cost function and sample from the posterior distribution using the learned prior combined with the cost function gradients during the denoising process. Instead of learning the prior on all trajectory waypoints, we propose learning a lower-dimensional representation of a trajectory using linear motion primitives, particularly B-spline curves. This parametrization guarantees that the generated trajectory is smooth, can be interpolated at higher frequencies, and needs fewer parameters than a dense waypoint representation. We demonstrate the results of our method ranging from simple 2D to more complex tasks using a 7-dof robot arm manipulator. In addition to learning from simulated data, we also use human demonstrations on a real-world pick-and-place task. The experiments show that MPD achieves higher success rates compared to an uninformed prior, and a baseline that first samples from the diffusion prior and then optimizes the cost, while maintain

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Local topological signatures for network-based prediction of biological function

Local topological signatures for network-based prediction of...

引用

8th IAPR International Conference on Pattern Recognition in Bioinformatics, PRIB 2013

作者： Winterbach, Wynand Van Mieghem, Piet Reinders, Marcel J. T. Wang, Huijuan De Ridder, Dick Network Architectures and Services Group Delft University of Technology P.O. Box 5031 2600 GA Delft Netherlands Department of Intelligent Systems Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology P.O. Box 5031 2600 GA Delft Netherlands Netherlands Bioinformatics Center 6500 HB Nijmegen Netherlands Kluyver Centre for Genomics of Industrial Fermentation 2600 GA Delft Netherlands

ISBN: (纸本)9783642391583

In biology, similarity in structure or sequence between molecules is often used as evidence of functional similarity. In protein interaction networks, structural similarity of nodes (i.e., proteins) is often captured by comparing node signatures (vectors of topological properties of neighborhoods surrounding the nodes). In this paper, we ask how well such topological signatures predict protein function, using protein interaction networks of the organism Saccharomyces cerevisiae. To this end, we compare two node signatures from the literature - the graphlet degree vector and a signature based on the graph spectrum - and our own simple node signature based on basic topological properties. We find the connection between topology and protein function to be weak but statistically significant. Surprisingly, our node signature, despite its simplicity, performs on par with the other more sophisticated node signatures. In fact, we show that just two metrics, the link count and transitivity, are enough to classify protein function at a level on par with the other signatures suggesting that detailed topological characteristics are unlikely to aid in protein function prediction based on protein interaction networks. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Yeast

来源：评论

学校读者我要写书评

暂无评论

Polynomial-time hierarchy of computable reals

引用

Journal of Computational Information systems 2011年第4期7卷 1108-1115页

作者： Chen, Qingliang Su, Kaile Wu, Lijun Department of Computer Science Jinan University Guangzhou 510632 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Key Laboratory of High Confidence Software Technologies Ministry of Education Peking University Beijing China Institute for Integrated and Intelligent Systems Griffith University Brisbane Australia School of Computer Science and Engineering University of Electronic Science and Technology Chengdu 610054 China

In mathematics, various representations of real numbers have been investigated and all these representations are proved to be mathematically equivalent. Furthermore, it is known that all effective versions of these representations lead to the same class of "computable real numbers". However, when subrecursive (such as primitive recursive) is taken into account, these representations can lead to different notions of "computable real numbers". This paper will look into the polynomial-time version of the problem for computable real numbers under different representations. We will summarize the known results to exhibit the comprehensive hierarchy they form. Our goal is to clarify systematically how the polynomial-time computability depends on the representations of the real numbers. Copyright © 2011 Binary Information Press.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Prediction of Stroke Risk Within 7-Years Follow Up Using Machine Learning Models

Prediction of Stroke Risk Within 7-Years Follow Up Using Mac...

引用

2023 IEEE EMBS Special Topic Conference on Data science and Engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Tsarapatsani, Konstantina-Helen Sakellarios, Antonis Tsakanikas, Vasilis D. Rudolf, Henrik Trampisch, Hans J. Pezoulas, Vasileios C. Matsopoulos, George K. Fotiadis, Dimitrios I. University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering IoanninaGR 45110 Greece Biomedical Research Institute Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany Ruhr University Bochum Department of Medical Informatics Biometry and Epidemiology Bochum Germany National Technical University of Athens School of Electrical and Computer Engineering Athens Greece

ISBN: (纸本)9798350383386

A stroke, also known as brain attack, occurs when blood supply to your brain is interrupted. Primary prevention relies on prompt prediction of a stroke. While currently there are several clinical risk scores, machine learning (ML) models seems to be more suitable tools for accurate prediction of stroke events. Therefore, this work focuses on the prediction of stroke within 7 years follow-up in patients who have not suffered from a stroke or TIA event at baseline. LightGBM (LGBM), Extreme Grading Boosting (XGBoost), Support Vector Machine (SVM) and Decision Tree were employed in the getABI dataset, which includes 5,897 participants. The performance of models was calculated by Accuracy (ACC), Sensitivity (SENS), Specificity (SPE) and area under the receiver operating characteristic curve (AUC) of each model. According to the comparison analysis's results, LGBM has been shown to be the most trustworthy algorithm, with accuracy 68 %. Moreover, sex, age, status of peripheral artery disease (PAD), history of myocardial infarction, angina pectoris, amputation and diabetes and pulse status of different arteries can be used as a simple and cost-effective way to predict *** Relevance: A fatal medical emergency, stroke may be anticipated using artificial intelligence, and the sooner it is predicted, the more cerebrovascular disease occurrences can be avoided. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Pointwise Logic on Completely Distributive Lattices and Approximate Reasoning

Pointwise Logic on Completely Distributive Lattices and Appr...

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Yalin Zheng Guang Yang Jing Zheng Jinsheng Xing State Key Laboratory for Intelligent Technology and Systems Department of Automation Faculty of Information Science and Technology Tsinghua University Beijing China Research Center of Intelligent Information Technology Department of Computer Science and Technology Faculty of Software Dongguan University of Science and Technology Dongguan China Research Center of Dongguan Economy Department of Economy and Commerce Dongguan University of Science and Technology Dongguan China Faculty of Mathematics and Computer Science Shanxi Normal University Linfen China Research Center of System Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University Xi'an China

In this paper, we propose the basic framework of point- wise topological logic on completely distributive lattices and explore approximate reasoning in it. The logic of this paper is based on pointwise characterization, therefore the pointwise conception is pervasive. We explore approximate reasoning in abstract logical framework Fl on completely distributive lattice L. We propose the structure of point- wise topological logic F TL , the structure of matching function sigma. and the structure of matching neighborhood group. We investigate approximate reasoning in pointwise topological logic F TL with matching function sigma, develop pointwise topological algorithm of simple approximate reasoning, introduce the essential characteristics of this scheme.

关键词： Lattices Fuzzy logic computer science Knowledge engineering Fuzzy systems Information technology Laboratories intelligent systems Automation Information science

来源：评论

学校读者我要写书评

暂无评论

A low-power CMOS neural amplifier with amplitude measurements for spike sorting

A low-power CMOS neural amplifier with amplitude measurement...

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： T. Horiuchi T. Swindell D. Sander P. Abshier Institute for Systems Research Neuroscience and Cognitive Science Program University of Maryland College Park MD USA Electrical and Computer Engineering Department University of Maryland College Park MD USA Electrical and Computer Engineering Department Electrical Engineering Department Pennsylvania State University State College PA USA

Integrated, low-power, low-noise CMOS neural amplifiers have recently grown in importance as large microelectrode arrays have begun to be practical. With an eye to a future where thousands of signals must be transmitted over a limited bandwidth link or be processed in situ, we are developing low-power neural amplifiers with integrated pre-filtering and measurements of the spike signal to facilitate spike-sorting and data reduction prior to transmission to a data-acquisition system. We have fabricated a prototype circuit in a commercially-available 1.5 /spl mu/m, 2-metal, 2-poly CMOS process that occupies approximately 91,000 square /spl mu/m. We report circuit characteristics for a 1.5 V power supply, suitable for single cell battery operation. In one specific configuration, the circuit bandpass filters the incoming signal from 22 Hz to 6.7 kHz while providing a gain of 42.5 dB. With an amplifier power consumption of 0.8 /spl mu/W, the rms input-referred noise is 20.6 /spl mu/V.

关键词： Sorting Signal processing Low-noise amplifiers Microelectrodes Bandwidth Integrated circuit measurements Prototypes CMOS process Power supplies Batteries

来源：评论

学校读者我要写书评

暂无评论

Optimizing One-Stage Object Detection for URLLC: A Two-Stage Pipeline with Oculi SPU

Optimizing One-Stage Object Detection for URLLC: A Two-Stage...

引用

Information Technology (ACIT)

作者： Adam Bou Moghlebey Abdallah Moubayed MohammadNoor Injadat Electrical & Computer Engineering Department Lebanese American University Byblos Lebanon Computer Engineering Department and Interdisciplinary Research Center for Intelligent Secure Systems King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia Data Science & Artificial Intelligence Department Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Pedestrian-related accidents account for an estimated 20-25% of the approximately 1.19 million road fatalities occurring annually, highlighting the urgent need for enhanced detection systems in surveillance and smart transportation to mitigate such incidents. The escalating demand for Ultra-Reliable Low-Latency Communications (URLLC) in modern surveillance and transportation systems has become a solution to that problem but highlighted significant challenges in reducing inference times of machine learning models, particularly on constrained hardware. The maximum permissible latency for most vehicular applications ranges from 6 to 20 milliseconds based on the application. When tested on an 8GB RAM setup using the NTU, LLVIP, and VIRAT datasets, YOLOv8n achieved a minimum inference time of approximately 200 milliseconds per frame, making it unsuitable for URLLC applications despite 8GB RAM being an adequate hardware setup for edge devices. This research introduces a new two-stage pipeline that integrates Oculi’s Sensing and Processing Unit (SPU) simulation with the YOLOv8n one-stage object detection model to enhance pedestrian detection, thereby addressing these challenges. By leveraging Regions of Interest (ROIs) generated by Oculi’s SPU, our approach optimizes the input data for the YOLO model, substantially reducing computational overhead and thus making it suitable for URLLC applications. This integration can lead to a reduction in inference time by up to 93% in the tested frames when being compared to YOLOv8n pre-trained model.

关键词： YOLO Pedestrians Computational modeling Surveillance Pipelines Random access memory Ultra reliable low latency communication Hardware Smart transportation Sensors

来源：评论

学校读者我要写书评

暂无评论

Finger-Knuckle-Print Identification Based on Histogram of Oriented Gradients and SVM classifier

Finger-Knuckle-Print Identification Based on Histogram of Or...

引用

International Conference on New Technologies of Information and Communication

作者： Abdallah Meraoumia Maarouf Korichi Salim Chitroub Ahmed Bouridane Univ Ouargla Fac. des nouvelles technologies de l'information et de la communication Lab. de Genie Electrique Laboratory of Intelligent and Communication Systems Engineering (LISIC) Electronics and Computer Science Faculty USTHB Department of Computer Science and Digital Technologies North Umbria University Newcastle

ISBN: (纸本)9781467366861

Recently, a wide variety of applications require reliable personal recognition systems to either confirm or determine the identity of an individual requesting their services. So, a reliable identity recognition system is a critical part in these applications that render their services only to genuine users. Thus, biometrics is an emerging technology that utilizes distinct behavioral or physiological traits in order to determine or verify the identity of an individual. In this context, the present paper attempts to design an effectively biometric system by using Finger-Knuckle-Print (FKP) traits. In this study, the feature vector of each segmented FKP is extracted using Histogram of Oriented Gradients (HOG). In addition, a multi-class Support Vector Machine (SVM) based learning algorithm is used to train the system using the extracted features vectors. From the test results, using PolyU FKP database with 165 persons, it is evident that our scheme has higher identification rate and very less classification error compared to several existing methods.

关键词： Security Biometrics Identification FKP HOGSVM Data fusion

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：