检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Wenlong Zhu, Qing Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (纸本)9798350368741

Video Character Social Relationship Recognition (VCSRR) requires a comprehensive consideration about spatio-temporal and multi-modal clues in videos. Most existing methods mainly focus on integrating multi-modal clues and modeling interactions among characters. However, they fail to discover key clues in the complex video data or fully understand the clues related to social relationships. In this article, we propose a novel Large Language Model Enhanced Key Clues Selection (LEKCS) framework to address the aforementioned issues. The core of LE-KCS is to mine multi-scale key clues from the perspectives of time, space and multi-modality, then transfer the knowledge about social relationships of the Large Language Model to VCSRR for understanding the selected clues. We evaluated LEKCS on the MovieGraphs dataset and the experimental results indicate that our proposed LE-KCS achieves state-of-the-art performance. © 2025 IEEE.

关键词： large language model Social relationship recognition video understanding

来源：评论

学校读者我要写书评

暂无评论

Wire- and powder-based direct energy deposition of NiTi-CuSn10-SS316L

引用

Materials and Manufacturing Processes 2025年第8期40卷 1049-1058页

作者： Otynshiyev, Yeldar Sariyev, Bakytzhan Golman, Boris Nie, Yi Spitas, Christos Department of Chemical and Materials Engineering School of Engineering and Digital Sciences Nazarbayev University Astana Kazakhstan Department of Computational and Data Sciences Astana IT University Astana Kazakhstan Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute University of Nottingham Ningbo China Ningbo China Department of Mechanical Materials and Manufacturing Engineering Faculty of Science and Engineering University of Nottingham Ningbo China

Additive manufacturing (AM) is a rapidly advancing method with the ability to produce complex geometries layer by layer. AM shows great promise for joining dissimilar metals. However, direct energy deposition (DED) of nitinol (NiTi) and 316 stainless steel (SS316L) encounters significant difficulties due to the development of brittle Fe-Ti intermetallic compounds. A copper alloy (CuSn10) interlayer was introduced to prevent their formation. This study utilizes a wire- and powder-based DED approach, eliminating the need for feedstock switching. Fine CuSn10 powder was specifically applied for the interlayer, resulting in distinct bonding mechanisms at the interfaces. Interdiffusion resulted in fishbone microstructures at the CuSn10-SS316L interface, whereas the NiTi-CuSn10 interface exhibited dendritic structures with evenly distributed elements. Microhardness analysis revealed a sharp variation across the layers, with the highest value observed at the NiTi-CuSn10 interface (529 HV0.2). This study shows the potential of using wire- and powder-based DED technology to join dissimilar metals. © 2025 Taylor & Francis Group, LLC.

关键词： Copper alloys

来源：评论

学校读者我要写书评

暂无评论

TIME-DOMAIN ITERATIVE RATIONAL KRYLOV METHOD

引用

SIAM Journal on Scientific Computing 2025年第3期47卷 A1628-A1651页

作者： Ackermann, Michael S. Gugercin, Serkan Department of Mathematics Virginia Tech BlacksburgVA24061 United States Department of Mathematics Division of Computational Modeling and Data Analytics Academy of Data Science Virginia Tech BlacksburgVA24061 United States

The Realization Independent Iterative Rational Krylov Algorithm (TF-IRKA) is a frequency-based data-driven reduced order modeling (DDROM) method that constructs H2 optimal DDROMs. However, as the H2 optimal approximation theory dictates, TF-IRKA requires repeated sampling of frequency data, that is, values of the system transfer function and its derivative, outside the unit circle. This repeated evaluation of frequency data requires repeated full model computations and may not be feasible. The data informativity framework for moment matching provides a method for obtaining such frequency data from a single time-domain simulation. However, this framework usually requires solving linear systems with prohibitively ill-conditioned matrices, especially when recovering frequency data from off the unit circle as required for optimality. In this paper, building upon our previous work with the data-informativity framework for moment matching, we provide a formula for the nonzero extreme eigenvalues of a symmetric rank-1 perturbation to an orthogonal projection, which then leads to an optimal scaling of the aforementioned linear systems. We also establish connections between the underlying dynamical system and conditioning of these linear systems. This analysis then leads to our algorithmic development, time-domain IRKA, which allows us to implement a time-domain variant of TF-IRKA, constructing H2 optimal DDROMs from a single time-domain simulation without requiring repeated frequency data evaluations. The numerical examples illustrate the effectiveness of the proposed algorithm. © 2025 Society for Industrial and Applied Mathematics.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

Joint Multi-Scale Contextual and Noise Suppression for Group Emotion Recognition

Joint Multi-Scale Contextual and Noise Suppression for Group...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Guo, Wangdong Zhu, Qing Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (纸本)9798350368741

Group Emotion Recognition (GER) seeks to identify emotional states within multi-person groups. The complexity of the environment and the reliance on a single group emotion label often result in noisy individuals with inconsistent emotional expressions, hampering accurate emotion classification. Mainstream GER networks attempt to downweight noisy individuals, but when their numbers are high and over-relying on a single group label, the negative impact of noise on individuals remains significant, further complicating classification and diminishing accuracy. To address these limitations, we propose the Multi-Scale Contextual and Noise Suppression Model (MCon-NSM), a novel framework that enhances GER by capturing fine-grained interaction contexts and collaboratively suppressing noise at both the individual and group label levels. Extensive experiments on the GAF series datasets demonstrate that our method achieves results comparable to state-of-the-art techniques, validating its effectiveness in mitigating noise in GER. © 2025 IEEE.

关键词： Emotion analysis Group emotion recognition Multi-Scale context learning Noise suppression

来源：评论

学校读者我要写书评

暂无评论

A genetic engineering algorithm for the generalized quadratic assignment problem

引用

Neural Computing and Applications 2025年 1-27页

作者： Sohrabi, Majid Fathollahi-Fard, Amir M. Gromov, Vasilii A. Dulebenets, Maxim A. School of Data Analysis and Artificial Intelligence National Research University Higher School of Economics 11 Pokrovsky Boulevard Moscow109028 Russia Laboratory for Models and Methods of Computational Pragmatics National Research University Higher School of Economics Moscow Russia Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology Taipa China College of Engineering 2035 E Paul Dirac Dr. Sliger Building Suite 275 TallahasseeFL32310 United States

The generalized quadratic assignment problem (GQAP) poses a significant challenge in optimization, known for its NP-hard complexity and wide-ranging applications in supply chain and manufacturing contexts. While various metaheuristic algorithms have addressed the GQAP, this paper introduces a novel modification of the genetic algorithm (GA), namely the genetic engineering algorithm (GEA). A traditional GA initializes the population of solutions randomly and refines these solutions iteratively through crossover and mutation operators. However, its reliance on randomness often leads to premature convergence, susceptibility to local optima, and suboptimal solutions at termination of the algorithmic run. To address these drawbacks, our research presents a modified GA framework inspired by genetic engineering principles. This framework introduces novel search mechanisms mimicking gene mining processes, targeting population enhancement through insertion, purification, and genetic material exchange from elite solutions. The GEA adds three search scenarios to the traditional GA framework to exhibit desired characteristics from chromosomes, enhancing solution quality and convergence speed. This GEA demonstrates a superior performance across various search scenarios against state-of-the-art algorithms and exact solutions for the benchmark instances of the GQAP. Additionally, this study conducts comprehensive sensitivity analyses on the search scenarios of the GEA. By employing gene mining strategies, the proposed GEA offers promising solutions for effectively addressing the NP-hard optimization challenges of the GQAP on large-scale datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Nature-Inspired Algorithms for Autism Spectrum Disorder Detection Using 3D Video dataset

arXiv

引用

arXiv 2025年

作者： Panchal, Aneesh Khan, Kainat Katarya, Rahul Department of Computational and Data Sciences Indian Institute of Science Karnataka Bangalore560012 India Big Data Analytics and Web Intelligence Laboratory Department of Computer Science & Engineering Delhi Technological University Delhi110042 India

Autism Spectrum Disorder (ASD) is a chronic neurodevelopmental disorder symptoms of which includes repetitive behaviour and lack of social and communication skills. Even though these symptoms can be seen very clearly in social but a large number of individuals with ASD remains undiagnosed. In this paper, we worked on a methodology for detection of ASD from 3-dimensional walking video dataset, utilizing supervised machine learning (ML) classification algorithms and using nature-inspired optimization algorithms for feature extraction from dataset. The proposed methodology involve the classification of ASD using supervised ML classification algorithm and extracting important and relevant features from the dataset using nature-inspired optimization algorithms. We also included the ranking coefficients for finding the initial leading particle. This selection of particle significantly reduces the computation time and hence, improving the total efficiency and accuracy for the ASD detection. To evaluate the efficiency of the proposed methodology, we deployed various combination of classification algorithm and nature-inspired algorithms resulting in an outstanding classification accuracy of 100% using random forest classification algorithm and gravitational search algorithm for feature selection. The application of the proposed methodology with different datasets would enhance the robustness and generalizability of the proposed methodology. Due to high accuracy and less total computation time, the proposed methodology will offer a significant contribution to the medical and academia fields, providing a foundation for future research and advancements in ASD diagnosis. Copyright © 2025, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

Leveraging Instruction-based Learning for Effective UAV Traf...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramya, R.S. Daniel, Keren Lois Rajkumar, S. Madhavan, Sruthi S. Akshya, J. Choudhry, Mani Deepak Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India KGiSL Institute of Technology Department of Computer Science and Business Systems Coimbatore India Sona College of Technology Department of Information Technology Salem India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Enhanced Bitcoin Price Prediction using RNN-GRU Algorithm with Optimized Parameters: Overcoming LSTM Ambiguities for Improved Accuracy and Efficiency 3

Enhanced Bitcoin Price Prediction using RNN-GRU Algorithm wi...

引用

3rd International Conference on Intelligent data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Kathiravan, M. Meenakshi, M. Kaviya, M. Sreesubha, S. Sathyadurga, V. Neela Gandhi, V. Chennai India Department of CSE Department of Computational Intelligence SRM Institute of Science and Technology Kattangulathur Chennai India Department of Artificial Intelligence And Data Science Panimalar Engineering College Chennai India Department of AIML Rajalakshmi Engineering College Thandalam Chennai India Department of CSE Hindustan Institute of Technology and Science padur Chennai India Department of CSE Panimalar Engineering college Chennai India

ISBN: (纸本)9798331527549

Bitcoin's decentralised character and introduction in January 2009 can be mostly attributed to Satoshi Nakamoto, the unidentified designer of the digital money. Unlike regular money, Bitcoin has no value in and of itself and is not supported by any government or financial institution. The "mining" process consumes a lot of resources thus it cannot manage trades without a network of computers, often known as "nodes" or "miners." The Bitcoin blockchain, a catalogue of all the past transactions, is maintained by these nodes. Like equities, bitcoin is getting more and more well-known even if it is somewhat erratic as an investment. Its value varies greatly;hence it is difficult to predict when prices will adjust. Since Bitcoin is so erratic, automated approaches are growing more crucial for future projections regarding it. Often utilised for prediction, long short-term memory (LSTM) networks have constraints. LSTM focusses on short-term input and has a complex and occasionally ambiguous design, thus some claim it does not operate well when prior data is not significant to current forecasts. This has caused some to wonder if one can forecast Bitcoin's price using this approach. Made as a substitute for standard RNNs, the Gated Recurrent Unit (GRU) helps to prevent the fading gradient issue. Bitcoin price projections made by the GRU design are far more accurate than those derived from more antiquated methods. © 2025 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Hyper-parameter Tuning of CNN Using Improved Elephant Herding Optimisation for Detection of Skin Cancer 3rd

Hyper-parameter Tuning of CNN Using Improved Elephant Herdin...

引用

3rd International Conference on Computing and Communication Networks, ICCCN 2023

作者： Uma, N. Siva Shankar, G. Kavin, Balasubramanian Prabhu Dhanaraj, Rajesh Kumar New Horizon College of Engineering Ring Road Bellandur Post Bengaluru560103 India Department of Computational Intelligence College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chengalpattu District 603203 India Department of Data Science and Business Systems College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chengalpattu District 603203 India Pune India

ISBN: (纸本)9789819726707

Skin cancer is one of the top three tumours caused by DNA damage and has a dire prognosis. As a result of this injured DNA, cells start to grow out of control and are currently doubling in size. This study recommends using a hyper-parameter optimised convolution neural net to identify the kind of skin cancer. In this method, the improved elephant herding optimisation (IEHO) algorithm was used to optimise CNN's hyper-parameters. A nonlinear denoising method known as a bilateral filter can lessen noise while maintaining edges. In this study, we frequently use the bilateral filter to modify the texture and noise in skin cancer photo images. An improved elephant herding optimisation has been proposed (IEHO). When the separation operator was changed to the sine–cosine, opposition-based learning was incorporated. The proposed model, which is around 4 and 1% higher than other based models, may produce testing accuracy up to 99.33%, according to simulation results. The experimental findings unequivocally demonstrate that the recommended model outperforms other published models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Full-waveform inversion via the scaled boundary finite element method

arXiv

引用

arXiv 2025年

作者： Daneshyar, Alireza Kollmannsberger, Stefan Chair of Computational Modeling and Simulation Technical University of Munich Germany Data Science in Civil Engineering Bauhaus-Universität Weimar Germany

We begin by addressing the time-domain full-waveform inversion using the adjoint method. Next, we derive the scaled boundary semi-weak form of the scalar wave equation in heterogeneous media through the Galerkin method. Unlike conventional scaled boundary finite element formulations, the resulting system incorporates variable density and two additional terms involving its spatial derivative. As a result, the coefficient matrices are no longer constant over the elements but instead depend on the so-called radial coordinate, rendering the common solution methods such as low-frequency expansion and continued fractions—both of which assume that these matrices can be defined solely by boundary values—inapplicable. In this context, we introduce a radial discretization scheme for solving the transient scalar wave equation with spatially varying density within the framework of the scaled boundary finite element method. This approach begins with temporal discretization in the time domain, followed by spatial discretization along the radial coordinate. We employ the Newmark method for the former and a finite differencing scheme for the latter. However, the choices underlying our ansatz are made for demonstration purposes and remain flexible. Following these discretizations, we introduce an algorithmic condensation procedure to compute the dynamic stiffness matrices of the elements on the fly. Therefore, we maneuver around the need to introduce auxiliary unknowns into the global algebraic system. As a result, the optimization problem is structured in a two-level hierarchy. The higher level computes the nodal wavefields on a relatively coarse mesh, while the lower level provides the gradient of the cost function for a finely distributed set of model parameters. We obtain the Fréchet kernel by computing the zero-lag cross-correlations of the forward and adjoint wavefields, and solve the minimization problems iteratively by moving downhill on the cost function hypersurface throug

关键词： Cost functions

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：