检索结果-内蒙古大学图书馆

32nd European Safety and Reliability Conference, ESREL 2022

作者： Zhang, Aibo Wu, Zhiying Wang, Yukun Xie, Min Center for Intelligent Multidimensional Data Analysis Hong Kong Science Park Shatin Hong Kong Department of Advanced Design and Systems Engineering City University of Hong Kong Hong Kong Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong School of Economics and Management Tianjin Chengjian University Tianjin300384 China

ISBN: (纸本)9789811851834

Most mechanical engineering systems experience deterioration due to several practical factors such as aging, usage etc. This results in the degradation of its performance. Although the deterioration is continuous in nature, it is not always practically possible to measure the deterioration especially in the case of subsea systems. In such cases the performance of these systems is represented by multiple finite states in their lifetimes where various levels of degradation are represented by these states. Generally, the degradation process is divided into two stages, i.e., the normal and defective stages. Thus, there are three possible states for the system: normal, defective, and failed. The Markov approach has been utilized heavily for reliability analysis of such systems. However, most of the Markov models rely on an accurately exponentially distributed transition rate, which is unrealistic in certain cases. In reality, there are some uncertainties in the transition rates thanks to the limits of prior knowledge. This paper presents a multi-phase Markov model-based performance evaluation model for a three-state system with uncertainties in transition rates. The transition rates are assumed following Beta distribution with known lower and upper bounds. The average system unavailability in a given life cycle is employed to quantify system performance. © 2022 ESREL2022 Organizers. Published by Research Publishing, Singapore.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Extracting Strong Policies for robotics Tasks from Zero-Order Trajectory Optimizers 9

Extracting Strong Policies for Robotics Tasks from Zero-Orde...

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Pinneri, Cristina Sawant, Shambhuraj Blaes, Sebastian Martius, Georg Autonomous Learning Group Max Planck Institute for Intelligent Systems Tübingen Germany Department of Computer Science ETH Zurich Switzerland Max Planck ETH Center for Learning Systems Department of Engineering Cybernetics NTNU Trondheim Norway

Solving high-dimensional, continuous robotic tasks is a challenging optimization problem. Model-based methods that rely on zero-order optimizers like the cross-entropy method (CEM) have so far shown strong performance and are considered state-of-the-art in the model-based reinforcement learning community. However, this success comes at the cost of high computational complexity, being therefore not suitable for real-time control. In this paper, we propose a technique to jointly optimize the trajectory and distill a policy, which is essential for fast execution in real robotic systems. Our method builds upon standard approaches, like guidance cost and dataset aggregation, and introduces a novel adaptive factor which prevents the optimizer from collapsing to the learner's behavior at the beginning of the training. The extracted policies reach unprecedented performance on challenging tasks like making a humanoid stand up and opening a door without reward shaping. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

Health Misinformation Detection: A Chunking Strategy Integrated to Retrieval-Augmented Generation 2

Health Misinformation Detection: A Chunking Strategy Integra...

引用

2nd Workshop on Artificial Intelligence for Perception and Artificial Consciousness, AIxPAC 2024

作者： Taib, Walid Saadallah, Idriss Ichou, Abdelali Hamdi, Abderrahmene Bruno, Alessandro Mazzeo, Pier Luigi Chetouani, Aladine Tliba, Marouane Kerkouri, Mohamed Amine Higher National School of Telecommunications and Information Technologies and Communications Es Senia Oran Algeria University of Orleans Orleans France Higher National School of Computer Science Oued Smar Algiers Algeria IULM University Department of Business Law Economics Consumer Behaviour -"Carlo A. Ricciardi" Via Carlo Bo 1 Milan20143 Italy ISASI Institute of Applied Sciences and Intelligent Systems-CNR Lecce73100 Italy University Sorbonne - Paris Nord Villetaneuse France

Generative AI (GenAI) and Natural Language Processing (NLP) have advanced significantly in recent years, exhibiting breakthroughs and pushing the bar of accuracy rates in text mining. Cascade effects have been observed in many application domains, spanning text analysis, question answering, classification, and new textual content generation. The latter has allowed many end-users to perceive AI as ready-to-go solutions to optimise their daily workflow. However, dark and bright sides lurk behind textual content generation, as trustworthy and unverified content can be effortlessly generated. That has fuelled a significant challenge in our society: fake news. Although fake news has existed for a while, it remains an unsolved issue. Generative AI has brought it to a new level by enabling the automated production of large volumes of high-quality, individually targeted fake content. Our work is part of the HeReFaNMi (Health-Related Fake News Mitigation) project, which focuses on health-related fake news mitigation by using NLP, Language Models, and a Retrieval-Augmented Generation (RAG) system. We propose a new chunking mechanism that streamlines the overall RAG framework pipeline. BERT and BERT+RAG have been compared on the health-related fake news classification task on a dataset of 2000 health-related articles equally split into two categories (’fake’ and’credible’). Preliminary experimental results reveal improvements in Accuracy, Recall, and F1-score. © 2024 Copyright for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage for Single-cell Omics Data

Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage...

引用

IEEE International Conference on Big Data

作者： Seth Wolfgang Skyler Ruiter Marc Tunnell Timothy Triche Erin Carrier Zachary DeBruine Department of Intelligent Systems Engineering University of Indiana Bloomington IN USA Department of Computer Science Purdue University West Lafayette IN USA Department of Epigenetics Van Andel Institute Grand Rapids MI USA College of Computing Grand Valley State University Allendale MI USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Genomics datasets, such as single-cell transcriptomics, are often very large and highly sparse, posing significant challenges for both storage and computation. As the scale of data generation accelerates, efficiently compressing these datasets becomes crucial. Current compression methods, like the popular Compressed Sparse Column (CSC) format, capitalize only on sparsity but overlook other properties like redundancy, which can offer additional opportunities for compression. Genomics data, especially single-cell assays, often exhibit high redundancy within columns, making traditional sparse formats inefficient for in-core computation. In this paper, we present two extensions to CSC: (1) Value-Compressed Sparse Column (VCSC) and (2) Index-and Value-Compressed Sparse Column (IVCSC). VCSC takes advantage of high redundancy within a column to further compress data up 1.9-fold over CSC on real data, without significant negative impact to performance characteristics. IVCSC extends VCSC by compressing index arrays through delta encoding and byte-packing, achieving up to a 4.4-fold decrease in memory usage over CSC on real data. Our benchmarks show that VCSC and IVCSC can be used in compressed form with little added computational cost. These formats represent a step forward in balancing the growing demands of data storage and processing in the era of large-scale genomics.

关键词： Redundancy Transcriptomics Memory Big Data Benchmark testing Encoding Computational efficiency Sparse matrices Indexes Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

arXiv

引用

arXiv 2024年

作者： Huo, Wei Liu, Changxin Ding, Kemi Johansson, Karl Henrik Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China

This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communication bottleneck. We introduce a federated learning algorithm called Differentially Private Federated Cubic Regularized Newton (DP-FCRN). By leveraging second-order techniques, our algorithm achieves lower iteration complexity compared to first-order methods. We also incorporate noise perturbation during local computations to ensure privacy. Furthermore, we employ sparsification in uplink transmission, which not only reduces the communication costs but also amplifies the privacy guarantee. Specifically, this approach reduces the necessary noise intensity without compromising privacy protection. We analyze the convergence properties of our algorithm and establish the privacy guarantee. Finally, we validate the effectiveness of the proposed algorithm through experiments on a benchmark dataset. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Little Chit-Chat Goes a Long Way: Design and Evaluation of Task-and Person-Oriented Styles for Social Robots

A Little Chit-Chat Goes a Long Way: Design and Evaluation of...

引用

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

Fenrir: Physics-Enhanced Regression for Initial Value Problems

arXiv

引用

arXiv 2022年

作者： Tronarp, Filip Bosch, Nathanael Hennig, Philipp Department of Computer Science University of Tübingen Tübingen Germany Max–Planck Institute for Intelligent Systems Tübingen Germany

We show how probabilistic numerics can be used to convert an initial value problem into a Gauss–Markov process parametrised by the dynamics of the initial value problem. Consequently, the often difficult problem of parameter estimation in ordinary differential equations is reduced to hyperparameter estimation in Gauss–Markov regression, which tends to be considerably easier. The method’s relation and benefits in comparison to classical numerical integration and gradient matching approaches is elucidated. In particular, the method can, in contrast to gradient matching, handle partial observations, and has certain routes for escaping local optima not available to classical numerical integration. Experimental results demonstrate that the method is on par or moderately better than competing approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Initial value problems

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Diabetes Type Using Random Forest Algorithm and SVM for Improving Accuracy 1

引用

International Conference on Advances in Communication Technology and computer Engineering, ICACTCE 2023

作者： Hai, Tao Zhou, Jincheng Olatunji, Timothy A. Ajoboh, Oluwakemi A. Chen, Lee Iwendi, Celestine Omeoga, Nkechi Sinha, Anurag School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun558000 China Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education Guizhou University Guizhou Guiyang550025 China School of Information and Artificial Intelligence Nanchang Institute of Science and Technology Nanchang China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Province Duyun558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Qiannan Duyun558000 China School of Creative Technologies University of Bolton BoltonBL3 5AB United Kingdom Manchester Metropolitan University Manchester United Kingdom Department of Computer Science and Information Technology IGNOU New Delhi India

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

To improve the accuracy in the detection of diabetes-type diagnosis using Random Forest Algorithm and Support Vector Method. A dataset on diabetes was collected on ***. Support vector method analysis was performed on the data using kernel as linear, poly, and rbf with random state = 42 and test size = 0.2. The Random Forest Algorithm with n_estimators = 100 has the same accuracy as the support vector method with the kernel as rbf. When it comes to type diagnosis for a patient having diabetes, the Random Forest Algorithm and Support Vector Method with kernel rbf can be used, unlike another kernel of the Support Vector Method. The dataset was also visualized using power. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Hydrone: Modeling of a Hybrid Unmanned Aerial Underwater Vehicle Considering Trans-Media Dynamics

SSRN

引用

SSRN 2024年

作者： de Oliveira Evald, Paulo Jefferson Dias Brião, Stephanie Loi Aoki, Vivian Misaki da Silva, César Bastos dos Santos Cardoso, Dayana Pinheiro, Pedro Miranda de Oliveira, Felipe Gomes André Barbosa Cunha, Mauro Jorge Drews, Paulo Lilles Intelligent Systems and Control Group Federal University of Pelotas RS Pelotas Brazil Intelligent Robotics and Automation Group Federal University of Rio Grande RS Rio Grande Brazil Department of Computer Engineering and Industrial Automation State University of Campinas SP Campinas Brazil Federal Institute of Education Science and Technology in Rio Grande do Sul RS Pelotas Brazil Institute of Exact Sciences and Technology Federal University of Amazonas Itacoatiara AM Amazonas Brazil Brazil

Research in mobile robotics is growing into applications for difficult-to-access environments, such as in rescue and transport missions. Furthermore, autonomous vehicles can perform data collection in complex approach areas. Therefore, the study of hybrid unmanned vehicles is relevant for several areas, since these vehicles can act in different domains. The developed vehicle, called Hydrone, is designed in a quadrotor-type structure and equipped with a set of aerial and underwater propellers, which are fixed and independent between them. In this sense, this work presents the mathematical modeling of an unmanned hybrid vehicle, which can navigate underwater and aerial environments. Furthermore, the modeling considers the ground effect due to the influence on the vehicle’s trajectory change and the dynamics of the transition zone between water-air and air-water. These dynamics are important to evaluate the controller’s performance. Numerical simulations consider both transitions (water-air and air-water) and they are performed to discuss the influence of acting forces on the vehicle stability and position-tracking performance using a classical control system. © 2024, The Authors. All rights reserved.

关键词： Hybrid vehicles

来源：评论

学校读者我要写书评

暂无评论

A CNN-LSTM Based Model to Predict Trajectory of Human-Driven Vehicle

A CNN-LSTM Based Model to Predict Trajectory of Human-Driven...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Shehab Alsanwy Houshyar Asadi Mohammad Reza Chalak Qazani Shady Mohamed Saeid Nahavandi Institute of Intelligent Systems Research and Innovation (IISRI) Deakin University Geelong VIC Australia Department of Computer Science and Information Systems (CSIS) Murray State University Murray KY USA Swinburne University of Technology Hawthorn VIC Australia

Vehicle trajectory prediction is essential in ensuring the safe and efficient operation of advanced driver assistance systems (ADAS) and autonomous vehicles (AVs), as it enables highly efficient collision avoidance, path planning, and traffic control. However, existing models for vehicle trajectory prediction predominantly focus on limited driving scenarios, resulting in limited applicability. To address this limitation, we present a novel vehicle trajectory prediction approach that employs a Convolutional Long Short-Term Memory (CNN-LSTM) model, incorporating simulated environments and vehicle dynamic time series data, including longitudinal, vertical, and latitudinal position and acceleration. Our approach is distinguished by its ability to handle diverse urban driving scenarios, such as highways, roundabouts, intersections, and turns, which enhances its applicability and generalizability. We experimented and collected vehicle data from 17 drivers using a stationary driving simulator and the Euro Truck Simulator software. For the model implementation and validation, we utilized Python 3.9 and Google Colab, as well as the Scikit-learn library for Deep learning algorithms. The proposed CNN-LSTM model leverages a convolutional layer to learn local patterns and an LSTM layer to capture long-term temporal dependencies, improving performance in predicting vehicle trajectories. The experimental results demonstrate that the CNN-LSTM model provides more accurate predictions for longitudinal and lateral positions compared to traditional vehicle trajectory prediction methods that employ LSTM and Recurrent Neural Network (RNN). This research contributes to developing robust and reliable vehicle trajectory prediction systems vital for ADAS and AVs' safe and efficient operation. The proposed approach broadens the applicability of trajectory prediction models, enabling better-informed decision-making in various driving conditions and ultimately improving road safety and efficien

关键词：

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：