检索结果-内蒙古大学图书馆

An Effective Tensor Regression with Latent Sparse Regularization

Journal of Data science 2022年第2期20卷 228-252页

作者： Chen, Ko-Shin Xu, Tingyang Liang, Guannan Tong, Qianqian Song, Minghu Bi, Jinbo Department of Computer Science and Engineering University of Connecticut United States Tencent AI Lab China Department of Biomedical Engineering University of Connecticut United States

As data acquisition technologies advance, longitudinal analysis is facing challenges of exploring complex feature patterns from high-dimensional data and modeling potential temporally lagged effects of features on a response. We propose a tensor-based model to analyze multidimensional data. It simultaneously discovers patterns in features and reveals whether features observed at past time points have impact on current outcomes. The model coefficient, a k-mode tensor, is decomposed into a summation of k tensors of the same dimension. We introduce a so-called latent F-1 norm that can be applied to the coefficient tensor to performed structured selection of features. Specifically, features will be selected along each mode of the tensor. The proposed model takes into account within-subject correlations by employing a tensor-based quadratic inference function. An asymptotic analysis shows that our model can identify true support when the sample size approaches to infinity. To solve the corresponding optimization problem, we develop a linearized block coordinate descent algorithm and prove its convergence for a fixed sample size. Computational results on synthetic datasets and real-life fMRI and EEG datasets demonstrate the superior performance of the proposed approach over existing techniques. © 2022 The Author(s).

关键词： longitudinal data quadratic inference function tensors

来源：评论

学校读者我要写书评

暂无评论

Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation

Adaptive Label Smoothing with Self-Knowledge in Natural Lang...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Lee, Dongkyu Cheung, Ka Chun Zhang, Nevin L. Department of Computer Science and Engineering HKUST Hong Kong NVIDIA AI Technology Center NVIDIA

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label smoothing smoothes target labels with a pre-defined prior label distribution;as a result, a model is learned to maximize the likelihood of predicting the soft label. Nonetheless, the amount of smoothing is the same in all samples and remains fixed in training. In other words, label smoothing does not reflect the change in probability distribution mapped by a model over the course of training. To address this issue, we propose a regularization scheme that brings dynamic nature into the smoothing parameter by taking model probability distribution into account, thereby varying the parameter per instance. A model in training self-regulates the extent of smoothing on the fly during forward propagation. Furthermore, inspired by recent work in bridging label smoothing and knowledge distillation, our work utilizes self-knowledge as a prior label distribution in softening target labels, and presents theoretical support for the regularization effect by knowledge distillation and the dynamic smoothing parameter. Our regularizer is validated comprehensively, and the result illustrates marked improvements in model generalization and calibration, enhancing robustness and trustworthiness of a model. © 2022 Association for Computational Linguistics.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Wireless Access Networks for IoT and E-Health-A Survey 3

Heterogeneous Wireless Access Networks for IoT and E-Health-...

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Salama, Ramiz Altrjman, Chadi Al-Turjman, Fadi Yadav, Satya Prakash Vats, Satvik Ai and Robotics Institute Research Center for Ai and IoT Near East University Department of Computer Engineering Near East Boulevard TRNC Mersin 10 Nicosia99138 Turkey Waterloo University Department of Chemical Engineering ONN2L 3G1 Canada Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept Mersin10 Nicosia Turkey Department of Computer Science and Engineering Greater Noida201306 India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350330724

In a heterogeneous wireless environment, there are many different radio access technologies (RATs), such as Wi-Fi and 2G, 3G, 4G, and 5G, which each have a different degree of coverage and processing power to meet various service requirements. A mobile user may have access to various access networks in such a situation. On the PC of each user, numerous programs with varied Quality of Service (QoS) requirements can operate simultaneously. It would be advantageous for a multi-interface terminal to use two or more interfaces simultaneously in order to improve performance. However, using multiple networks at once could use up more energy than just using one interface. Therefore, energy use must to be taken into account when analyzing the Flow/Interface Relationship (FIA). This paper presents a novel method for choosing the ideal FIA that achieves the best trade-off between all the characteristics taken into account, dubbed Smart Tabu Search (STS). STS considers user preferences, network circumstances, network expenses, application QoS specifications, and battery life of mobile devices. We use simulations and testbed experiments to validate our concept. Professionals are now able to diagnose and monitor patients remotely because to the growing use of healthcare monitoring devices. One of the most frequent occurrences that affects the reliability of information transmission in any network is congestion, which is defined as the unchecked increase in traffic relative to network capacity. With the use of a mesh network, wireless sensors, and some of the most significant models for vital signs, the article aims to provide a realistic simulation environment for a healthcare system. The simulator environment is a helpful tool for assessing the dependability and effectiveness of the healthcare system in a realistic setting. However, the system is not appropriate for real-time applications due to the sluggish network adaption caused by the end-to-end based traffic regulation deci

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach to Skin Color Segmentation Using Perceptually Uniform CIELab Color Model 11th

An Efficient Approach to Skin Color Segmentation Using Perce...

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Sathish, B.S. Jerry Alexander, T. Padmavathy, B. Leo Joseph, L.M.I. Ganesan, P. Sajiv, G. Murugesan, R. Department of Computer Science Engineering AI Sri Venkateshwara College of Engineering Bengaluru India Department of ECE Swarnandhra College of Engineering and Technology Andhra Pradesh Narsapur India Department of Computer Science Engineering Sri Venkateshwara College of Engineering Bengaluru India Department of ECE SR University Telangana Warangal India Department of ECE Vidya Jyothi Institute of Technology Hyderabad India Saveetha School of Engineering SIMATS Chennai India Department of ECE Narshima Reddy Engineering College Secunderabad India

ISBN: (纸本)9789819717231

The skin segmentation is one of the most crucial steps in many applications such as face detection, human identification, and video conferencing. However, it is not straightforward to classify the skin pixels because the skin tone is extensively changing from darkest to lightest due to the divergence in the quantity of melanin (pigmentation). The proposed work focused on the segmentation of skin pixels using the device independent and perceptually uniform CIELab color model. In the proposed method, all the three components of the CIELab model are independently applied for skin segmentation. The outcome of the CIELab-based skin segmentation is compared to the result of RGB-based segmentation to exhibit the preeminence of the proposed method. The investigational outcome clearly exemplified that the chrominance components ‘a’ and ‘b’ precisely classified skin pixels in all test images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Application for Identifying Cavities in Dentistry: Utilizing Smartphone-Taken Intraoral Photos 5

A Deep Learning Application for Identifying Cavities in Dent...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Mahaveerakannan, R. Nair, Sreerengan V R Rohini, M.S. Vinoth Kumar, M. Rajakumar, B. Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Tamil Nadu Chennai India Bengaluru India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India JNN Institute of Engineering Chennai Periyapalayam Highway Department of AI & DS Tamil Nadu Chennai601102 India

ISBN: (纸本)9798331530013

The potential of digital examinations and advanced tele-dentistry applications remains limited due to the lack of universal access to dental care, particularly in remote regions with scarce financial resources. This study aims to standardize the use of digital dental cavity evaluation and progression tracking through image-based techniques. The primary objective of this research was to design an innovative, cost-effective virtual tool capable of predicting dental cavitation from non-standardized images with clinically acceptable reliability. A dataset comprising 1,903 photographs of flattened tooth surfaces, captured using an iPhone 7 by 696 participants, was utilized. The study evaluated four deep learning strategies: YOLOv3, Faster R-CNN, RetinaNet, and Single-Shot Multi-Box Detector (SSD), to detect early cavities and dental infections. The benchmark was set against dentists' evaluations based on image inspections aligned with the Global Cavities Classification and Oversight Method. Among the models, YOLOv3 and Faster R-CNN demonstrated the highest sensitivity for cavitated caries, achieving 88.5% and 72.5%, respectively. However, their sensitivity for visually non-cavitated lesions was lower, at 37.9% and 27%, respectively. All four models achieved specificity levels exceeding 86% for cavitated cavities and over 72% for visually non-cavitated lesions. This research integrates model-based categorization, test-time enhancement, and portable deep learning techniques into a virtual ai-driven system capable of predicting dental cavities from irregular images with adequate clinical reliability. The proposed framework has the potential to enhance access to oral healthcare in underserved and resource-constrained areas, supporting automated diagnoses and advancing tele-dentistry application. © 2024 IEEE.

关键词： Cavitation

来源：评论

学校读者我要写书评

暂无评论

Fast Vocabulary Transfer for Language Model Compression

Fast Vocabulary Transfer for Language Model Compression

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Gee, Leonidas Zugarini, Andrea Rigutini, Leonardo Torroni, Paolo Expert.ai Italy University of Siena Department of Computer Science and Engineering University of Bologna

ISBN: (纸本)9781952148255

Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance. © 2022 Association for Computational Linguistics.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Context is King: Rethinking Query Expansion in Modern Search Engines

Context is King: Rethinking Query Expansion in Modern Search...

引用

Artificial Intelligence and Data engineering (aiDE), International Conference on

作者： Krishnan Batri S Lakshmi S Ramesh N Sangeetha S. Annamalai School of Computer Science and Engineering Jain(Deemed-to-be-University) Bengaluru India Electronics and Communication Engineering Jain(Deemed-to-be-University) Bengaluru India Department of AI&ML City Engineering College Bengaluru India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

In the era of digital information overload, search engines have evolved beyond simple keyword matching to embrace context-aware methodologies. However, the task of accurately interpreting user intent remains a critical challenge, with traditional query expansion techniques often falling short of capturing semantic and contextual nuances. This paper critically examines the evolution of query expansion strategies, highlighting their limitations and exploring state-of-the-art techniques such as machine learning models, knowledge graphs, and transformer-based systems like BERT and GPT. Experimental results compare traditional methods like synonym expansion with modern approaches, demonstrating the superior relevance and diversity of results from context-aware systems. The study underscores the importance of integrating real-time contextual signals and dynamic user preferences to enhance search engine performance, paving the way for more personalized and accurate retrieval systems.

关键词： Adaptation models Quantum computing Biological system modeling Semantics Machine learning Knowledge graphs Search engines Transformers Real-time systems Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Overview of Energy Harvesting and Sustainability in Smart Cities 3

Overview of Energy Harvesting and Sustainability in Smart Ci...

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

ISBN: (纸本)9798350330724

Sustainability is a key factor in the context of smart cities. In smart cities, promoting sustainable energy is one strategy for achieving sustainability and lowering greenhouse gas emissions. Different energy sources are needed to meet the need for affordable and dependable electrical energy, where the environmental impact typically outweighs the cost of generation. In order to increase sustainability in the electrical industry, smart cities are examined in this article. The methodological strategy for this involved conducting a systematic literature review utilizing the PRISMA procedure. 154 journal articles were examined in-depth for this review. Energy efficiency, renewable energy, and energy and urban planning were the themes that the results were organized into. The results of the study showed that: (a) there is a global academic publication landscape for research on smart cities and energy sustainability;(b) publications are unbalanced when comparing the results of studies on the energy use intensity of different continents to those on the energy sustain ability of smart cities;and (c) there is a strong focus on technology-related issues related to energy sustainability, efficiency, and renewables topics in the literature, but much less attention is given to these issues. Urban and energy authorities are informed by the insights produced, and scholars are given ideas for future research directions. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

PVT v2:Improved baselines with Pyramid Vision Transformer

引用

Computational Visual Media 2022年第3期8卷 415-424页

作者： Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo Ling Shao Shanghai AI Laboratory Shanghai 200232China Department of Computer Science and Technology NanjingUniversityNanjing 210023China Department of Computer Science the University ofHong KongHong Kong 999077China School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210014China Computer Vision Lab ETH ZurichZurich 8092Switzerland SenseTime Beijing 100080China Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Transformers have recently lead to encouraging progress in computer *** this work,we present new baselines by improving the original Pyramid Vision Transformer(PVT v1)by adding three designs:(i)a linear complexity attention layer,(ii)an overlapping patch embedding,and(iii)a convolutional feed-forward *** these modifications,PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification,detection,and *** particular,PVT v2 achieves comparable or better performance than recent work such as the Swin *** hope this work will facilitate state-ofthe-art transformer research in computer *** is available at https://***/whai362/PVT.

关键词： transformers dense prediction image classification object detection semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient Leverage Score Sampling for Tensor Train Decomposition 38

Efficient Leverage Score Sampling for Tensor Train Decomposi...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bharadwaj, Vivek Rakhshan, Beheshteh T. Malik, Osman Asif Rabusseau, Guillaume Electrical Engineering and Computer Science Department UC Berkeley United States Encube Technologies United States Mila & DIRO Université de Montréal Canada CIFAR AI Canada

Tensor Train (TT) decomposition is widely used in the machine learning and quantum physics communities as a popular tool to efficiently compress high-dimensional tensor data. In this paper, we propose an efficient algorithm to accelerate computing the TT decomposition with the Alternating Least Squares (ALS) algorithm relying on exact leverage scores sampling. For this purpose, we propose a data structure that allows us to efficiently sample from the tensor with time complexity logarithmic in the tensor size. Our contribution specifically leverages the canonical form of the TT decomposition. By maintaining the canonical form through each iteration of ALS, we can efficiently compute (and sample from) the leverage scores, thus achieving significant speed-up in solving each sketched least-square problem. Experiments on synthetic and real data on dense and sparse tensors demonstrate that our method outperforms SVD-based and ALS-based algorithms. © 2024 Neural information processing systems foundation. All rights reserved.

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：