检索结果-内蒙古大学图书馆

1st International Conference on Sustainable Energy Technologies and Computational Intelligence, SETCOM 2025

作者： Varshney, Shreekant Raval, Jainit Priyadarshi, Rahul Manek, Vidhi Dadheech, Yash Shah, Manthan Pandit Deendayal Energy University School of Technology Department of Mathematics Gujarat Gandhinagar382426 India Pandit Deendayal Energy University School of Energy Technology Department of Electrical Engineering Gujarat Gandhinagar382426 India Symbiosis International University Symbiosis Institute of International Business Hinjewadi Maharashtra Pune411057 India New York University Center for Data Science Department of Center for Data Science New YorkNY United States Pandit Deendayal Energy University School of Technology Department of Computer Science and Engineering Gujarat Gandhinagar382426 India Pandit Deendayal Energy University School of Technology Department of Mechanical Engineering Gujarat Gandhinagar382426 India

ISBN: (纸本)9798331520540

This paper presents a stochastic model for addressing a single-server service station offering both EV charging and battery swapping services, considering the realistic retrial-based queueing behavior of the waiting individuals. A computationally efficient method is proposed for determining the steady-state probability distribution of the charging network. The approach involves analyzing the governing differential-difference equations and employing a matrix method to derive the steady-state probability distribution. Further, straightforward formulae are derived for critical system performance indicators, considering both server and system characteristics. Numerical results are visualized in the form of different graphical representations to demonstrate the influence of various parameters on system performance. Finally, the paper concludes with significant findings and future research directions to apprise researchers, decision-makers, and system designers in optimizing combined charging/swapping infrastructure. © 2025 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Age of Gossip in Random and Bipartite Networks

arXiv

引用

arXiv 2024年

作者： Maranzatto, Thomas J. Department of Mathematics Statistics and Computer Science University of Illinois Chicago ChicagoIL United States

In this paper we study gossip networks where a source observing a process sends updates to an underlying graph. Nodes in the graph communicate to their neighbors by randomly sending updates. Our interest is studying the version age of information (vAoI) metric over various classes of networks. It is known that the version age of Kn is logarithmic, and the version age of Kn is linear. We study the question 'how does the vAoI evolve as we interpolate between Kn and Kn' by studying Erdős-Reyni random graphs, random d-regular graphs, and bipartite networks. Our main results are proving the existence of a threshold in G(n, p) from rational to logarithmic average version age, and showing G(n, d) almost surely has logarithmic version age for constant d. We also characterize the version age of complete bipartite graphs KL,R when we let L vary from O(1) to O(n). © 2024, CC BY.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Novel Resilient Model Risk Forecasts Based on Neuro Volatility Models

Novel Resilient Model Risk Forecasts Based on Neuro Volatili...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Md Erfanul Hoque Sulalitha Bowala Avanthi Saumyamala Aerambamoorthy Thavaneswaran Ruppa Thulasiram Department of Mathematics and Statistics Thompson Rivers University Kamloops Canada Department of Statistics University of Manitoba Winnipeg Canada Department of Computer Science University of Manitoba Winnipeg Canada

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Recently, there has been a growing interest in using neuro volatility models in fuzzy forecasting and fuzzy option pricing. Neuro volatility models are used to model and predict financial market volatility by extending the neural network autoregressive (NNAR) model for nonlinear nonstationary times series data. In financial risk forecasting, various risk forecasting models for volatility are used to obtain the volatility forecasts, and the model risk ratio based on all the models is calculated to assess the stability of the financial system. However, the recently proposed neuro volatility models (based on neural networks such as LSTM, NNAR, etc.) are not used in evaluating the model risk. In this paper, novel 'neuro model risk forecasts' are obtained by including recently proposed neuro volatility models, and the resiliency of the financial system is studied. Unlike the existing model risk ratio forecasting based on linear volatility models, the driving idea is to use more appropriate nonlinear nonstationary neuro volatility forecasting models to obtain the model risk forecasts. The proposed model risk forecasts in this paper have been evaluated through extensive experiments, and it is shown that the model risk ratio can effectively serve as a metric for assessing the resilience and stability of the targeted financial system.

关键词： Measurement Computational modeling Time series analysis Predictive models data models Stability analysis Forecasting

来源：评论

学校读者我要写书评

暂无评论

Classification of Gender in Celebrity Cartoon Images 6th

Classification of Gender in Celebrity Cartoon Images

引用

6th International Conference on computer Vision and Image Processing, CVIP 2021

作者： Prajna, S. Vinay Kumar, N. Guru, D.S. Department of Studies in Computer Science Manasagangotri University of Mysore Mysuru570006 India NTT Data Services Bangalore India

ISBN: (纸本)9783031113451

This paper presents a model by integrating deep architecture-based feature extraction with classical learning algorithms for the effective gender classification of celebrity cartoon images. The proposed model makes use of colored celebrity cartoon images. For face representation, we have extracted features using various conventional approaches such as Scale-Invariant Feature Transform (SIFT), Fast Fourier Transform (FFT), and Discrete Cosine Transform (DCT), and the deep approach using deep features from a pre-trained architecture. After extracting the features to classify the gender of celebrity cartoon images, we have used conventional classifiers. Here in this work, we have recommended the integration of random forest (RF) with deep features extracted from FaceNet pre-trained architecture. We have used an existing dataset, the Cartoon Faces in the wild (IIIT-CFW) database of celebrity cartoon faces consisting of 8928 cartoon images. At the same time, we segregate it into two distinct classes, male and female, comprising 4594 and 2073, respectively. There is an imbalance in the proportion of the dataset;we have attempted to balance the unbalanced data using the SMOTE technique. Lastly, to classify the gender of celebrity cartoon images, we have adopted distinct supervised conventional learning models. The classification results are validated using classification metrics such as accuracy, precision, recall, f-measure. We show that our approach model establishes a state-of-the-art F1-score of 95% on the task of gender recognition of cartoons faces. The model has been compared against other existing contemporary models for its effectiveness. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Hybrid GAN-CNN Framework for Low-Light Image Enhancement Combining Structural Noise Reduction and Perceptual Quality

A Hybrid GAN-CNN Framework for Low-Light Image Enhancement C...

引用

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

作者： Gobinath, R. Boopathi, R. Vijayalakshmi, S. Disney, D. Anu Priyadharshini, P. Nirmala Maheshwari, K. E.G.S. Pillay Engineering College Nagapattinam611002 India Karpaga Vinayaga College of Engineering and Technology Department of Electrical and Electronic Engineering Tamilnadu 603308 India Sona College of Technology Department of Electronics and communication Engineering Tamilnadu Salem636005 India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai600119 India Adithya Institute of Technology Department of Information Technology Coimbatore641107 India Sir Issac Newton College of Engineering and Technology Department of Artificial Intelligence and Data Science Nagapattinam611 102 India

ISBN: (纸本)9798331509828

Low light region is one of the difficult scenarios for surveillance system, especially noisy, low-quality images may lead to poor object detection and scene analysis. To tackle this problem, we introduce a hybrid GAN - CNN framework for low light image denoising and quality enhancement. We develop a framework that combines the strengths of Generative Adversarial Networks (GANs) for photorealistic image generation and Convolutional Neural Networks (CNNs) for robust noise reduction. First denoising and feature extraction is done by the CNN module, and the GAN part further refines the denoised output to improve the perceptual quality of the generated images. We train and validate the proposed model in standard low light image dataset and show superior PSNR, SSIM, and visual clarity compared to state of art methods. We show that the hybrid GAN-CNN model successfully trades between image denoising accuracy and visual realism, thereby providing a viable alternative for enhancing surveillance performance in lowlight conditions. Keywords: Image denoising, GAN-CNN hybrid, low-light enhancement, PSNR, SSIM, surveillance systems. © 2025 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

POLYNOMIAL FOURIER DECAY FOR PATTERSON-SULLIVAN MEASURES

arXiv

引用

arXiv 2024年

作者： Khalil, Osama Department of Mathematics Statistics and Computer Science University of Illinois Chicago ChicagoIL United States

We show that the Fourier transform of Patterson-Sullivan measures associated to convex cocompact groups of isometries of real hyperbolic space decays polynomially quickly at infinity. The proof is based on the L2-flattening theorem obtained in [16] combined with a method based on dynamical self-similarity for ruling out the sparse set of potential frequencies where the Fourier transform can be large. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dimension-free Private Mean Estimation for Anisotropic Distributions

arXiv

引用

arXiv 2024年

作者： Dagan, Yuval Jordan, Michael I. Yang, Xuelin Zakynthinou, Lydia Zhivotovskiy, Nikita School of Computer Science Tel Aviv University Department of Electrical Engineering and Computer Science University of California Berkeley United States Department of Statistics University of California Berkeley United States

We present differentially private algorithms for high-dimensional mean estimation. Previous private estimators on distributions over d suffer from a curse of dimensionality, as they require Ω(d1/2) samples to achieve non-trivial error, even in cases where O(1) samples suffice without privacy. This rate is unavoidable when the distribution is isotropic, namely, when the covariance is a multiple of the identity matrix, or when accuracy is measured with respect to the affine-invariant Mahalanobis distance. Yet, real-world data is often highly anisotropic, with signals concentrated on a small number of principal components. We develop estimators that are appropriate for such signals—our estimators are (Ε,δ)-differentially private and have sample complexity that is dimension-independent for anisotropic subgaussian distributions. Given n samples from a distribution with known covariance-proxy Σ and unknown mean μ, we present an estimator μˆ that achieves error in Euclidean distance, ⃦μˆ − μ ⃦2 ≤ α, as long as n tr(Σ)/α2 + tr(Σ1/2)/(αΕ). In particular, when σ2 = (σ12, . . .,σd2) are the singular values of Σ, we have tr(Σ) = ⃦σ ⃦22 and tr(Σ1/2) = ⃦σ ⃦1, and hence our bound avoids dimension-dependence when the signal is concentrated in a few principal components. We show that this is the optimal sample complexity for this task up to logarithmic factors. Moreover, for the case of unknown covariance, we present an algorithm whose sample complexity has improved dependence on the dimension, from d1/2 to d1/4 Copyright © 2024, The Authors. All rights reserved.

关键词： Anisotropy

来源：评论

学校读者我要写书评

暂无评论

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers

arXiv

引用

arXiv 2024年

作者： Chen, Siyu Sheen, Heejune Wang, Tianhao Yang, Zhuoran Department of Statistics and Data Science Yale University United States Toyota Technological Institute at Chicago United States

In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architectures. In particular, most existing work only theoretically explains how the attention mechanism facilitates ICL under certain data models. It remains unclear how the other building blocks of the transformer contribute to ICL. To address this question, we study how a two-attention-layer transformer is trained to perform ICL on n-gram Markov chain data, where each token in the Markov chain statistically depends on the previous n tokens. We analyze a sophisticated transformer model featuring relative positional embedding, multi-head softmax attention, and a feed-forward layer with normalization. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model that performs a generalized version of the "induction head" mechanism with a learned feature, resulting from the congruous contribution of all the building blocks. In the limiting model, the first attention layer acts as a copier, copying past tokens within a given window to each position, and the feed-forward network with normalization acts as a selector that generates a feature vector by only looking at informationally relevant parents from the window. Finally, the second attention layer is a classifier that compares these features with the feature at the output position, and uses the resulting similarity scores to generate the desired output. Our theory is further validated by experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Detecting Food Items with Possible Allergens Using Deep Neural Network

Detecting Food Items with Possible Allergens Using Deep Neur...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Kannapak Yudeepanao Kittiphop Sakkato Pornthanwa Tosaman Pokpong Songmuang Rachada Kongkachandra Data Science and Innovation College of Interdisciplinary Studies Thammasat University Thailand Department of Computer Science Faculty of Science and Technology Thammasat University Thailand

ISBN: (数字)9798350370096

ISBN: (纸本)9798350370102

Food allergies are a significant concern for the community as they can have adverse effects on human health. Even a small amount of certain food items can trigger allergic reactions in the body, ranging from mild symptoms like hives or itchiness to severe and life-threatening anaphylaxis. However, these reactions can often be prevented by being aware of the specific allergen-based food items and avoiding their consumption. Our research aims to address this issue by utilizing a Convolutional Neural Network-based object. This model, belonging to the realm of deep learning techniques, is utilized to identify food items present in images. The primary objective behind this recognition process is to facilitate the development of a system that can effectively identify ingredients capable of triggering allergic reactions. This study explored three deep learning techniques for the classification of food images. The effectiveness of three distinct deep learning models, namely MobilenetV2, EfficientNetB0 and Resnet50v2, was examined. Notably, the EfficientNetB0 classifier outperformed the others, achieving an impressive accuracy score of 97%.

关键词： Deep learning Privacy Adaptation models Technological innovation Transfer learning data models Safety

来源：评论

学校读者我要写书评

暂无评论

Practical equivariances via relational conditional neural processes 23

Practical equivariances via relational conditional neural pr...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Daolang Huang Manuel Haussmann Ulpu Remes ST John Grégoire Clarté Kevin Sebastian Luck Samuel Kaski Luigi Acerbi Department of Computer Science Aalto University Finland Department of Mathematics and Statistics University of Helsinki Department of Computer Science University of Helsinki Department of Electrical Engineering and Automation (EEA) Aalto University Finland and Department of Computer Science Vrije Universiteit Amsterdam The Netherlands Department of Computer Science Aalto University Finland and Department of Computer Science University of Manchester

Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as in spatiotemporal modeling, Bayesian Optimization and continuous control, inherently contain equivariances - for example to translation - which the model can exploit for maximal performance. However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions. In this work, we propose Relational Conditional Neural Processes (RCNPs), an effective approach to incorporate equivariances into any neural process model. Our proposed method extends the applicability and impact of equivariant neural processes to higher dimensions. We empirically demonstrate the competitive performance of RCNPs on a large array of tasks naturally containing equivariances.

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：