检索结果-内蒙古大学图书馆

Path Planning for Autonomous Robot Navigation: Present Approaches 1

学校读者我要写书评

暂无评论

3rd International Conference on Futuristic Trends in Network and Communication Technologies, FTNCT 2020

作者： Verma, Shagun Kumar, Neerendra Department of Computer Science IT Central University of Jammu Jammu181143 India Doctoral School of Applied Informatics and Applied Mathematics Óbuda University Budapest Hungary

ISBN: (数字)9789811614835

ISBN: (纸本)9789811614828

An intelligent autonomous robot is in demand for robotic operations in the fields such as industry, medical, bionics, military. For any machine, designed to follow a precise sequence of instructions, self-positioning, path framing, map architecture, and obstacle prevention are the prerequisites of navigation. This paper presents a survey about the key navigation approaches explored by various authors in the last decade. The survey has a brief insight into the various approaches used for robot navigation concerning to the variable and invariable nature of the vicinity and the obstacle. The comprehensive look-over presented in this paper provides an in-depth analysis and assessment of the discrete classical and heuristic approaches used by the researchers. The research assessment is finally concluded by aggregating the complete knowledge of the various path planning techniques by reviewing the literature. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Motion planning

Understanding the learning mechanism of convolutional neural network applied to fluorescence spectra 4

学校读者我要写书评

暂无评论

Understanding the learning mechanism of convolutional neural...

AI and Optical Data sciences IV 2023

作者： Venturini, Francesca Michelucci, Umberto Sperti, Michela Gucciardi, Arnaud Deriu, Marco A. Institute of Applied Mathematics and Physics Zurich University of Applied Sciences Technikumstrasse 9 Winterthur8401 Switzerland TOELT llc Machine Learning Research and Development Birchlenstr. 25 Dübendorf8600 Switzerland Lucerne University of Applied Sciences and Arts Computer Science Department Lucerne Switzerland PolitoBIOMed Lab Department of Mechanical and Aerospace Engineering Politecnico di Torino Turin Italy Artificial Intelligence Laboratory University of Ljubljana Ljubljana Slovenia

ISBN: (纸本)9781510659810

The power of artificial neural networks to determine the quality and properties of olive oil was proven by several studies in the last years. Less clear is, however, how the neural network is able to extract useful information from the input data. This work investigates the learning mechanism of one-dimensional convolutional neural networks (1D-CNNs) trained to predict the physicochemical properties of olive oil from single fluorescence spectra. Such a 1D-CNN can successfully predict the parameters relevant to the quality assessment: acidity, peroxide value, and UV absorbance. To go beyond a simple quality assessment algorithm, it is important to identify which spectral features in the measured spectra are correlated with each chemical parameter and therefore with the quality of olive oil. To obtain this information, explainability techniques can be used by studying the latent feature space generated by the intermediate layers of the one-dimensional trained convolutional neural network. This work analyses in detail the common features that are used by the 1D-CNN to predict the two physicochemical parameters: acidity and K232 © 2023 SPIE.

关键词： Olive oil

Second-order nonstandard finite difference schemes for a class of models in bioscience

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Anguelov, Roumen Lubuma, Jean M.-S. Department of Mathematics and Applied Mathematics University of Pretoria Pretoria South Africa School of Computer Science and Applied Mathematics University of the Witwatersrand Johannesburg South Africa

We consider a dynamical system, defined by a system of autonomous differential equations, on Ω ⊂ Rn. By using Mickens' rule on the nonlocal approximation of nonlinear terms, we construct an implicit Nonstandard Finite Difference (NSFD) scheme that, under an existence and uniqueness condition, is an explicit time reversible scheme. Apart from being elementary stable, we show that the NSFD scheme is of second-order and domain-preserving, thereby solving a pending problem on the construction of higher-order nonstandard schemes without spurious solutions, and extending the tangent condition to discrete dynamical systems. It is shown that the new scheme applies directly for mass action-based models of biological and chemical *** Codes 65L05 © 2022, CC BY.

关键词： Dynamical systems

An Assessment of the Supremizer and Aggregation Methods of Stabilization for Reduced-Order Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Davie, Kayla D. Elman, Howard C. Applied Mathematics & Statistics Scientific Computation Program University of Maryland College ParkMD20742 United States Department of Computer Science Institute for Advanced Computer Studies University of Maryland College ParkMD20742 United States

MSC Codes 65N22, 65K10, 65F45We explore the features of two methods of stabilization, aggregation and supremizer methods, for reduced-order modeling of parametrized optimal control problems. In both methods, the reduced basis spaces are augmented to guarantee stability. For the aggregation method, the reduced basis approximation spaces for the state and adjoint variables are augmented in such a way that the spaces are identical. For the supremizer method, the reduced basis approximation space for the state-control product space is augmented with the solutions of a supremizer equation. We implement both of these methods for solving several parametrized control problems and assess their performance. Results indicate that the number of reduced basis vectors needed to approximate the solution space to some tolerance with the supremizer method is much larger, possibly double, that for aggregation. There are also some cases where the supremizer method fails to produce a converged solution. We present results to compare the accuracy, efficiency, and computational costs associated with both methods of stabilization which suggest that stabilization by aggregation is a superior stabilization method for control problems. © 2023, CC BY.

关键词： Stabilization

Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation 39

学校读者我要写书评

暂无评论

Harnessing Multimodal Large Language Models for Multimodal S...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Yuyang Zheng, Zhi Shen, Yishan Wang, Tianshu Zhang, Hengruo Zhu, Peijun Yu, Runlong Zhang, Kai Xiong, Hui Department of Management Science and Information Systems Rutgers University United States School of Data Science University of Science and Technology of China China Department of Applied Mathematics and Computational Science University of Pennsylvania United States Bytedance Inc. China School of Computer Science Georgia Institute of Technology United States Department of Computer Science University of Pittsburgh United States China

ISBN: (纸本)157735897X

Recent advances in Large Language Models (LLMs) have demonstrated significant potential in the field of Recommendation Systems (RSs). Most existing studies have focused on converting user behavior logs into textual prompts and leveraging techniques such as prompt tuning to enable LLMs for recommendation tasks. Meanwhile, research interest has recently grown in multimodal recommendation systems that integrate data from images, text, and other sources using modality fusion techniques. This introduces new challenges to the existing LLM-based recommendation paradigm which relies solely on text modality information. Moreover, although Multimodal Large Language Models (MLLMs) capable of processing multi-modal inputs have emerged, how to equip MLLMs with multi-modal recommendation capabilities remains largely unexplored. To this end, in this paper, we propose the Multimodal Large Language Model-enhanced Sequential Multimodal Recommendation (MLLM-MSR) model. To capture the dynamic user preference, we design a two-stage user preference summarization method. Specifically, we first utilize an MLLM-based item-summarizer to extract image feature given an item and convert the image into text. Then, we employ a recurrent user preference summarization generation paradigm to capture the dynamic changes in user preferences based on an LLM-based user-summarizer. Finally, to enable the MLLM for multi-modal recommendation task, we propose to fine-tune a MLLM-based recommender using Supervised Fine-Tuning (SFT) techniques. Extensive evaluations across various datasets validate the effectiveness of MLLM-MSR, showcasing its superior ability to capture and adapt to the evolving dynamics of user preferences. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

Real-Time Credit Card Fraud Detection Surveillance System 2

学校读者我要写书评

暂无评论

Real-Time Credit Card Fraud Detection Surveillance System

2nd International Conference on Cybernetics and Innovations, ICCI 2023

作者： Thongthawonsuwan, Pattarawan Ganokratanaa, Thittaporn Pramkeaw, Patiyuth Chumuang, Narumol Ketcham, Mahasak King Mongkut's University of Technology North Bangkok Department of Information Technology Management Bangkok Thailand King Mongkut's University of Technology Thonburi Applied Computer Science Program Bangkok Thailand King Mongkut's University of Technology Thonburi Media Technology Program Bangkok Thailand Department of Digital Media Technology Thailand Media Technology Program King Mongkut s University of Technology Thonburi Bangkok Thailand

ISBN: (纸本)9798350336573

In this research, the system that detects administrative behavior, credit card and developing corruption from credit cards through LINE applications. The objective of this research 1) To develop a risk notification system or suspect to be corruption of credit cards through the connection channels of LINE application 2) to measure the accuracy of the system developed. As for the notification to prevent the risk of credit card corruption The research methods are divided into 5 steps, namely Step 1, Step System analysis. Is a study and analysis to determine the needs of steps 2 steps, system design Is the process of designing tools used in research. Step 3 System development Is the process of developing the tools used in research. Step 4, the process of testing and correcting the system. Is the process of testing the tools used in research. Step 5 Summary Discuss results and suggestions. The research results are summarized as follows The results of the measurement and completeness of the data are very good as 86.67 percent. The results of the measurement of the correct conditions are as good as 80 percent and the performance measurement of time is in The criteria is as good as 86.67 percent. In conclusion, the corruption system from credit cards through the application alert. LINE can be used appropriately. © 2023 IEEE.

关键词： Systems analysis

INVERSION SETS AND QUOTIENT ROOT SYSTEMS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dimitrov, Ivan Gigliotti, Cole Ossip, Etan Paquette, Charles Wehlau, David Department of Mathematics and Statistics Queen’s University United Kingdom Department of Mathematics University of British Columbia Canada Faculty of Engineering and Applied Science Queen’s University United Kingdom Department of Mathematics and Computer Science Royal Military College of Canada Canada

We provide a recursive description of all decompositions of the positive roots R+ of a quotient root system R into disjoint unions of inversion sets. Our description is type-independent and generalizes the analogous result for type A root systems in [USRA]. The main tool is the notion of an inflation of a subset of a quotient root system. This new notion allows us to treat all root systems (and their quotients) uniformly. We also obtain some numerical results about the number of special decompositions. The new sequences we obtain may be considered as extensions of Catalan *** Codes 17B22 © 2023, CC BY.

关键词：

Finite groups in which generalized normality is a transitive relation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Safonova, Inna N. Skiba, Alexander N. Department of Applied Mathematics and Computer Science Belarusian State University Minsk220030 Belarus Department of Mathematics and Technologies of Programming Francisk Skorina Gomel State University Gomel246019 Belarus

In this paper, we discuss some well-known results and some open problems of the theory of σ-properties of a group related to the study of generalized *** Codes 20D10, 20D15, 20D30 Copyright © 2023, The Authors. ...

关键词：

EFFICIENT NONLINEAR MULTISCALE SPECTRAL GFEM applied TO COMPOSITE AEROSPACE STRUCTURES 23

学校读者我要写书评

暂无评论

EFFICIENT NONLINEAR MULTISCALE SPECTRAL GFEM APPLIED TO COMP...

23rd International Conference on Composite Materials, ICCM 2023

作者： Bénézech, J. Seelinger, L. Reinarz, A. Dodwell, T.J. Butler, R. Scheichl, R. Material & Structure Research Centre University of Bath Bath United Kingdom Interdisciplinary Center for Scientific Computing Institute for Applied Mathematics Heidelberg University Heidelberg Germany Department of Computer Science Durham University Durham United Kingdom Institute of Data Science and AI University of Exeter Exeter United Kingdom DigiLab Exeter United Kingdom