检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Andrew M. Childs Tongyang Li Jin-Peng Liu Chunhao Wang Ruizhe Zhang Joint Center for Quantum Information and Computer Science Department of Computer Science and Institute for Advanced Computer Studies University of Maryland Center on Frontiers of Computing Studies and School of Computer Science Peking University Simons Institute and Department of Mathematics UC Berkeley Department of Computer Science and Engineering Pennsylvania State University Department of Computer Science The University of Texas at Austin

ISBN: (纸本)9781713871088

Given a convex function f : ℝd → ℝ, the problem of sampling from a distribution ∝ e-f(x) is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc. In this work, we develop quantum algorithms for sampling log-concave distributions and for estimating their normalizing constants $\int_{\mathbb{R}^d}e^{-f(x)}\mathrm{d} x$. First, we use underdamped Langevin diffusion to develop quantum algorithms that match the query complexity (in terms of the condition number κ and dimension d) of analogous classical algorithms that use gradient (first-order) queries, even though the quantum algorithms use only evaluation (zeroth-order) queries. For estimating normalizing constants, these algorithms also achieve quadratic speedup in the multiplicative error e. Second, we develop quantum Metropolis-adjusted Langevin algorithms with query complexity Õ(κ1/2d) and Õ(κ1/2d3/2/ε) for log-concave sampling and normalizing constant estimation, respectively, achieving polynomial speedups in κ, d, ε over the best known classical algorithms by exploiting quantum analogs of the Monte Carlo method and quantum walks. We also prove a 1/ε1-o(1) quantum lower bound for estimating normalizing constants, implying near-optimality of our quantum algorithms in ε.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks

arXiv

引用

arXiv 2025年

作者： Khosrowshahli, Rasa Rahnamayan, Shahryar Ombuki-Berman, Beatrice Department of Computer Science Faculty of Mathematics and Science Brock University St. CatharinesONL2S 3A1 Canada lab Department of Engineering Brock University St. CatharinesONL2S 3A1 Canada

Deep neural networks suffer from storing millions and billions of weights in memory post-training, making challenging memory-intensive models to deploy on embedded devices. The weight-sharing technique is one of the popular compression approaches that use fewer weight values and share across specific connections in the network. In this paper, we propose a multi-objective evolutionary algorithm (MOEA) based compression framework independent of neural network architecture, dimension, task, and dataset. We use uniformly sized bins to quantize network weights into a single codebook (lookup table) for efficient weight representation. Using MOEA, we search for Pareto optimal k bins by optimizing two objectives. Then, we apply the iterative merge technique to non-dominated Pareto frontier solutions by combining neighboring bins without degrading performance to decrease the number of bins and increase the compression ratio. Our approach is model- and layer-independent, meaning the weights are mixed in the clusters from any layer, and the uniform quantization method used in this work has O(N) complexity instead of non-uniform quantization methods such as k-means with O(Nkt) complexity. In addition, we use the center of clusters as the shared weight values instead of retraining shared weights, which is computationally expensive. The advantage of using evolutionary multi-objective optimization is that it can obtain non-dominated Pareto frontier solutions with respect to performance and shared weights. The experimental results show that we can reduce the neural network memory by 13.72 ∼ 14.98× on CIFAR-10, 11.61 ∼ 12.99× on CIFAR-100, and 7.44 ∼ 8.58× on ImageNet showcasing the effectiveness of the proposed deep neural network compression framework. © 2025, CC BY.

关键词： Bins

来源：评论

学校读者我要写书评

暂无评论

Pose-Oriented Scene-Adaptive Matching for Abnormal Event Detection

SSRN

引用

SSRN 2024年

作者： Yang, Yuxing Xie, Leiyu Fu, Zeyu Naqvi, Syed Mohsen Intelligent Sensing and Communications Research Group Newcastle University Newcastle upon Tyne United Kingdom Department of Computer Science College of Engineering Mathematics and Physical Sciences University of Exeter Exeter United Kingdom

For intelligent surveillance systems, abnormal event detection (AED) automatically analyses surveillance video sequences and detects abnormal objects or unusual human actions at the frame level. Due to the lack of labelled data, most approaches to AED are often semi-supervised based on reconstruction or prediction methods. However, these methods may not generalise well to unseen scene contexts. To address this issue, we present a novel self and mutual scene-adaptive matching method for abnormal event detection. In the framework, we propose synergistic pose estimation and object detection, which effectively integrates human pose and object detection information to improve pose estimation accuracy. Then, the poses are resized to reduce the spatial distance between the source and target domains. The improved pose sequences are further fed into a spatio-temporal graph convolutional network to extract the geometric features. Finally, the features are embedded in a clustering layer to classify action types and compute normality scores. The training data is taken from the training part of common video anomaly detection datasets: UCSD PED1 & PED2, CHUK Avenue, and ShanghaiTech Campus. The proposed framework is evaluated on video sequences with unseen scene contexts in the UCSD PED2 and ShanghaiTech Campus datasets. The detection accuracy and efficiency are also evaluated in detail, and the proposed method for AED achieves the highest AUC performance, 84.6%, on the ShanghaiTech Campus dataset and relatively high AUC performance, 96.9% and 74.8%, on UCSD PED2 & PED1 datasets. Compared with other state-of-the-art works, the performance analysis and results confirm the robustness and effectiveness of our proposed framework for cross-scene AED. © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Decision-Making for Electric Vehicle Selection Using AHP-MABAC-Fuzzy Integration

Decision-Making for Electric Vehicle Selection Using AHP-MAB...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： P. Poongothai C.D. Nandakumar R. Ponnusamy B.S.Abdur Rahman Crescent Institute of Science & Technology Vandalur Tamilnadu Department of Mathematics Chennai Institute of Technology Kanchipuram Tamilnadu Department of Mathematics and Actuarial Science B.S.Abdur Rahman Crescent Institute of Science & Technology Vandalur Tamilnadu Department of Computer Science and Engineering Chennai Institute of Technology Kundrathur Kanchipuram

The widespread adoption of electric vehicles (EVs) is pivotal for achieving sustainable and eco-friendly transportation systems. However, the selection of an optimal electric vehicle considering multiple criteria poses a complex decision-making challenge. This research proposes an integrated approach that combines the Analytic Hierarchy Process (AHP), Multi-Attributive Border Approximation Area Comparison (MABAC), and Fuzzy Logic to enhance the decision-making process for selecting the most suitable electric vehicle. The AHP is employed to structure the hierarchy of criteria and sub-criteria, capturing the diverse factors influencing EV selection, including cost, range, charging infrastructure, environmental impact, and performance. MABAC, a multi-criteria decision-making method, is utilized to calculate the relative rankings and weights of alternatives based on pairwise comparisons, considering both positive and negative *** account for the inherent uncertainties and vagueness in decision-making, fuzzy logic is integrated to handle linguistic assessments and subjective judgments. Fuzzy sets and membership functions are employed to model the imprecision in decision-makers preferences, providing a more realistic representation of the decision-making process. The proposed AHP-MABAC-Fuzzy integration is applied to a case study involving the selection of electric vehicles, considering a set of real-world criteria and sub-criteria. The results demonstrate the effectiveness of the integrated approach in handling the complexity and uncertainty associated with electric vehicle selection. This research contributes to the field of multi-criteria decision-making for sustainable transportation by providing a comprehensive and flexible methodology for electric vehicle selection. The integration of AHP, MABAC, and fuzzy logic offers a robust framework that can be adapted for decision-making in various domains where multiple conflicting criteria need to be considered.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WaveNet-SF: A Hybrid Network for Retinal Disease Detection Based on Wavelet Transform in the Spatial-Frequency Domain

arXiv

引用

arXiv 2025年

作者： Cheng, Jilan Long, Guoli Zhang, Zeyu Qi, Zhenjia Wang, Hanyu Lu, Libin Wang, Shuihua Zhang, Yudong Hong, Jin School of Information Engineering Nanchang University Nanchang330031 China School of Advanced Energy Sun Yat-sen University Shenzhen518107 China School of Mathematics and Computer Science Wuhan Polytechnic University Wuhan430023 China Department of Biological Sciences School of Science Xi'an Jiaotong Liverpool University Suzhou215123 China School of Computer Science and Engineering Southeast University Nanjing210096 China

Retinal diseases are a leading cause of vision impairment and blindness, with timely diagnosis being critical for effective treatment. Optical Coherence Tomography (OCT) has become a standard imaging modality for retinal disease diagnosis, but OCT images often suffer from issues such as speckle noise, complex lesion shapes, and varying lesion sizes, making interpretation challenging. In this paper, we propose a novel framework, WaveNet-SF, to enhance retinal disease detection by integrating spatial-domain and frequency-domain learning. The framework utilizes wavelet transforms to decompose OCT images into low- and high-frequency components, enabling the model to extract both global structural features and fine-grained details. To improve lesion detection, we introduce a multi-scale wavelet spatial attention (MSW-SA) module, which enhances the model's focus on regions of interest at multiple scales. Additionally, a high-frequency feature compensation block (HFFC) is incorporated to recover edge information lost during wavelet decomposition, suppress noise, and preserve fine details crucial for lesion detection. Our approach achieves state-of-the-art (SOTA) classification accuracies of 97.82% and 99. 58% on the OCT-C8 and OCT2017 datasets, respectively, surpassing existing methods. These results demonstrate the efficacy of WaveNet-SF in addressing the challenges of OCT image analysis and its potential as a powerful tool for retinal disease diagnosis. Copyright © 2025, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Optimizing Fuzzy System of Fuzzy Time Series for Hyper Spectral Image Classification

Optimizing Fuzzy System of Fuzzy Time Series for Hyper Spect...

引用

Optimization Computing and Wireless Communication (ICOCWC), International Conference on

作者： M.S. Nidhya Preeti Naval Ravindra Kumar Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Mathematics Vivekananda Global University Jaipur India

This research paper examines the capability of fuzzy time collection for hyperspectral photograph classification. Fuzzy time series (FTS) is a time series in which fuzzy standards are used to model the styles within the facts. FTS can be used to explain complex temporal styles in the records, and as a consequence making it possible to categorize photographs more extraordinarily accurately., this look proposes an optimization method primarily based on genetic seek techniques. The optimization algorithm is designed to discover the high-quality FTS parameters that yield first-rate type accuracy. The efficacy of the proposed technique is evaluated on hyperspectral facts set with extraordinary experimental scenarios. The results of the test display that the proposed method can enhance the accuracy of photo classification and the use of FTS considerably. Hence, the proposed method gives a promising technique that can be used to classify hyperspectral snapshots efficiently. The paper affords an optimized fuzzy machine of fuzzy time collection for the hyperspectral photograph category. The proposed device consists of 3 levels: pre-processing, version creation, and optimization. Throughout the pre-processing level, statistical and spectral analyses are executed to acquire the applicable attributes for developing the fuzzy time collection. The model construction degree then uses the bushy time series to extract between-class separability for the photo type. It is followed utilizing the optimization stage, related to the software of differential evolution, to minimize the complexity of the proposed machine while still enhancing the type accuracy. The proposed machine has been correctly carried out to a real-international hyperspectral dataset and demonstrates widespread upgrades in class accuracy over existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continuous Finite Element Subgrid Basis Functions for Discontinuous Galerkin Schemes on Unstructured Polygonal Voronoi Meshes

引用

Communications in Computational Physics 2022年第6期32卷 259-298页

作者： Walter Boscheri Michael Dumbser Elena Gaburro Department of Mathematics and Computer Science University of FerraraVia Machiavelli 3044121 FerraraItaly Department of Civil Environmental and Mechanical EngineeringUniversity of TrentoVia Mesiano 7738123 TrentoItaly Inria Univ.BordeauxCNRSBordeaux INPIMBUMR 5251200 Avenue de la Vieille Tour33405 Talence cedexFrance

We propose a new high order accurate nodal discontinuous Galerkin(DG)method for the solution of nonlinear hyperbolic systems of partial differential equations(PDE)on unstructured polygonal Voronoi *** than using classical polynomials of degree N inside each element,in our new approach the discrete solution is represented by piecewise continuous polynomials of degree N within each Voronoi element,using a continuous finite element basis defined on a subgrid inside each *** call the resulting subgrid basis an agglomerated finite element(AFE)basis for the DG method on general polygons,since it is obtained by the agglomeration of the finite element basis functions associated with the subgrid *** basis functions on each sub-triangle are defined,as usual,on a universal reference element,hence allowing to compute universal mass,flux and stiffness matrices for the subgrid triangles once and for all in a pre-processing stage for the reference element ***,the construction of an efficient quadrature-free algorithm is possible,despite the unstructured nature of the computational *** order of accuracy in time is achieved thanks to the ADER approach,making use of an element-local space-time Galerkin finite element *** novel schemes are carefully validated against a set of typical benchmark problems for the compressible Euler and Navier-Stokes *** numerical results have been checked with reference solutions available in literature and also systematically compared,in terms of computational efficiency and accuracy,with those obtained by the corresponding modal DG version of the scheme.

关键词： Continuous finite element subgrid basis for DG schemes high order quadraturefree ADER-DG schemes unstructured Voronoi meshes comparison of nodal and modal basis compressible Euler and Navier-Stokes equations

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Potential of Large Language Models in Modern Marketing Management: Applications, Future Directions, and Strategic Recommendations

arXiv

引用

arXiv 2025年

作者： Aghaei, Raha Kiaei, Ali A. Boush, Mahnaz Vahidi, Javad Zavvar, Mohammad Barzegar, Zeynab Rofoosheh, Mahan School of Mathematics and Computer Science Iran University of Science & Technology Tehran Iran Department of Artificial Intelligence in Medicine Faculty of Advanced Technologies in Medicine Iran University of Medical Sciences Tehran Iran Cellular and Molecular Biology Research Center Shahid Beheshti University of Medical Sciences Tehran Iran Department of Computer Engineering Sari Branch Islamic Azad University Sari Iran Computer engineering group Alborz Vocational Technical University Alborz Iran

Large Language Models (LLMs) have revolutionized the process of customer engagement, campaign optimization, and content generation in marketing management. In this paper, we explore the transformative potential of LLMs along with the current applications, future directions, and strategic recommendations for marketers. In particular, we focus on LLMs major business drivers such as personalization, real-time-interactive customer insights, and content automation, and how they enable customers and business outcomes. For instance, the ethical aspects of AI with respect to data privacy, transparency, and mitigation of bias are also covered, with the goal of promoting responsible use of the technology. Through best practices and the use of new technologies businesses can tap into the LLM potential, which help growth and stay one step ahead in the turmoil of digital marketing. This article is designed to give marketers the necessary guidance by using best industry practices to integrate these powerful LLMs into their marketing strategy and innovation roadmap without compromising on the ethos of their brand. Copyright © 2025, The Authors. All rights reserved.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Performance of Online Adaptive Clustering for Time Series with Head-Based Aggregation

Analyzing the Performance of Online Adaptive Clustering for ...

引用

Optimization Computing and Wireless Communication (ICOCWC), International Conference on

作者： Ankita Agarwal Murli Manohar Gour Karthikeyan M P Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Mathematics Vivekananda Global University Jaipur India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India

This paper presents an analytical examine the present day, an internet adaptive clustering technique for time collection statistics with Head-primarily based Aggregation (HBA). Using a Markov chain technique, the authors analyze the asymptotic overall performance of cutting-edge global clustering blunders, which consist of the sum of present-day misclassification and the clustering structure errors. They offer a closed-shape expression new to the predicted global error rate and show its conduct quantitatively beneath distinct eventualities. Thru massive experiments on both synthetic and actual datasets, they show the effectiveness of the proposed method compared to the conventional okay-approach clustering and a few online clustering algorithms. The effects show that the proposed method can successfully seize time collection clustering shape.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flower automata pattern-based discrimination of fibromyalgia from control subjects using fusion of sleep EEG and ECG signals

引用

IEEE Access 2025年 13卷 99032-99047页

作者： Barua, Prabal Datta Kobayashi, Makiko Dogan, Sengul Baygin, Mehmet Tuncer, Turker Paul, Jose Kunnel Iype, Thomas Acharya, U.R. Australia Kumamoto University Graduate School of Science and Technology Kumamoto860-8555 Japan Kumamoto860-8555 Japan Firat University Technology Faculty Department of Digital Forensics Engineering Elazig Turkey Erzurum Technical University Faculty of Engineering and Architecture Department of Computer Engineering Erzurum Turkey Government Medical College Department of Neurology Kerala Thiruvananthapuram India University of Southern Queensland School of Mathematics Physics and Computing Springfield Australia

Electroencephalogram (EEG) and electrocardiogram(ECG) signals provide vital insights into brain and heart activity and are widely used in automated medical diagnostics. This study introduces a novel, multimodal fibromyalgia detection system developed by the fusion of EEG and ECG signals recorded during sleep stages 2 and 3. The novelty of the model is the use of dynamic and interpretable feature engineering framework comprising of two innovations: (i) Flower Automata Pattern (FAP) for self-organized pattern-based feature extraction, and (ii) Attention-Driven Wavelet Transform and Absolute Maximum Pooling (ADWTAMP) method for signal decomposition and compression. Three feature selection strategies—Neighborhood Component Analysis (NCA), Chi2, and the intersection of NCA and Chi2 (NCA˄Chi2) —are employed to generate robust feature vectors, which are classified using k-nearest neighbors (kNN) and support vector machine (SVM) under the leave-one-record-out cross-validation (LORO CV) scheme. The final decision is derived through an iterative voting and greedy fusion approach. The proposed model achieved classification accuracies of 99.36% and 98.37% for sleep stages 2 and 3, respectively. Key advantages of the model include its high accuracy, low computational requirements (CPU-only execution), and explainable architecture. To the best of our knowledge, this is the first multimodal automata-based classification framework designed for fibromyalgia detection. © 2013 IEEE.

关键词： Electrocardiography

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：