检索结果-内蒙古大学图书馆

Advancing general robotic manipulation with multimodal foundation models: An embodied AI paradigm

science China Technological sciences 2025年第5期68卷 294-296页

作者： Shifeng HUANG He WANG Xing ZHOU Wenkai CHEN Haibin YANG Jianwei ZHANG Department of Mechanical and Aerospace Engineering Hong Kong University of Science and Technology Foshan Institute of Intelligent Equipment Technology Foshan Huashu Robot Co. Ltd. Center on Frontiers of Computing Studies (CFCS) School of Computer SciencePeking University Beijing Academy of Artificial Intelligence Department of Informatics Universit?t Hamburg

Can current robotic technologies truly replicate the full scope and intricacies of human labour? In practice, the adoption of robots remains limited, especially in open, unstructured environments commonly encountered in everyday scenarios such as services, healthcare, agriculture,construction, and numerous other fields. From the perspective of general robotic manipulation, the challenges arise from three factors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Translation-Invariant Quantum Algorithms for Ordered Search are Optimal

arXiv

引用

arXiv 2025年

作者： Carolan, Joseph Childs, Andrew M. Kovacs-Deak, Matt Schaeffer, Luke Department of Computer Science Institute for Advanced Computer Studies Joint Center for Quantum Information and Computer Science University of Maryland United States David R. Cheriton School of Computer Science Institute for Quantum Computing University of Waterloo Canada

Ordered search is the task of finding an item in an ordered list using comparison queries. The best exact classical algorithm for this fundamental problem uses [log2 n] queries for a list of length n. Quantum computers can achieve a constant-factor speedup, but the best possible coefficient of log2 n for exact quantum algorithms is only known to lie between (ln 2)/π ≈ 0.221 and 4/log2 605 ≈ 0.433. We consider a special class of translation-invariant algorithms with no workspace, introduced by Farhi, Goldstone, Gutmann, and Sipser, that has been used to find the best known upper bounds. First, we show that any exact, k-query quantum algorithm for ordered search can be implemented by a k-query algorithm in this special class. Second, we use linear programming to show that the best exact 5-query quantum algorithm can search a list of length 7265, giving an ordered search algorithm that asymptotically uses 5 log7265 n ≈ 0.390 log2 n quantum queries. © 2025, CC BY.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Correlating Time Series With Interpretable Convolutional Kernels

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3272-3283页

作者： Chen, Xinyu Cai, HanQin Liu, Fuqiang Zhao, Jinhua Massachusetts Institute of Technology Department of Urban Studies and Planning CambridgeMA02139 United States University of Central Florida Department of Statistics and Data Science Department of Computer Science OrlandoFL32816 United States McGill University Department of Civil Engineering MontrealQCH3A 0C3 Canada

This study addresses the problem of convolutional kernel learning in univariate, multivariate, and multidimensional time series data, which is crucial for interpreting temporal patterns in time series and supporting downstream machine learning tasks. First, we propose formulating convolutional kernel learning for univariate time series as a sparse regression problem with a non-negative constraint, leveraging the properties of circular convolution and circulant matrices. Second, to generalize this approach to multivariate and multidimensional time series data, we use tensor computations, reformulating the convolutional kernel learning problem in the form of tensors. This is further converted into a standard sparse regression problem through vectorization and tensor unfolding operations. In the proposed methodology, the optimization problem is addressed using the existing non-negative subspace pursuit method, enabling the convolutional kernel to capture temporal correlations and patterns. To evaluate the proposed model, we apply it to several real-world time series datasets. On the multidimensional ridesharing and taxi trip data from New York City and Chicago, the convolutional kernels reveal interpretable local correlations and cyclical patterns, such as weekly seasonality. For the monthly temperature time series data in North America, the proposed model can quantify the yearly seasonality and make it comparable across different decades. In the context of multidimensional fluid flow data, both local and nonlocal correlations captured by the convolutional kernels can reinforce tensor factorization, leading to performance improvements in fluid flow reconstruction tasks. Thus, this study lays an insightful foundation for automatically learning convolutional kernels from time series data, with an emphasis on interpretability through sparsity and non-negativity constraints. © 2025 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images for Crop Prediction using Machine and Deep Learning Models

Hyperspectral Images for Crop Prediction using Machine and D...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： R. Mahalakshmi K. Kumutha M. Sakthivanitha R. Bagavathi Lakshmi Mohamed Sirajudeen Sankar Padmanabhan Department of Computer Applications-PG Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India Department of Computer Applications-PG Vels Institute of Science Technology Advanced Studies Chennai Tamil Nadu India Department of Computer Application Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India Department of Information Technology Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India PG and Research Department of Computer Science Nilgiri College of Arts and Science The Nilgiris Tami Nadu India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data.

关键词： Support vector machines Radio frequency Deep learning Recurrent neural networks Accuracy Crops Spatial databases Convolutional neural networks Reliability Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

DLIoMT: Deep Learning Approaches for IoMT-Overview, challenges and the future

DLIoMT: Deep Learning Approaches for IoMT-Overview, challeng...

引用

2025 International Conference on computer, Electrical and Communication Engineering, ICCECE 2025

作者： Harshni, V. Singh, Satyendr Indhumathi, R. Kumar, Neelam Sanjeev Chowdhury, Subrata Patra, Sudhansu Shekhar Srm Institute of Science and Technology Department of Bme Ramapuram campus Chennai India Bml Munjal University Computer Science & Engg Department Gurugram India Vadapalani Campus Chennai India Sreenivasa Institute of Technology and Management Studies Department of Computer Science and Engineering Andra Pradesh Chittoor India Deemed to be University School of Compter Applications Odisha Bhubaneswar India

ISBN: (纸本)9798331513894

An artificial intelligence (AI) system works by combining a computer program and algorithms to make a device more efficient and intelligent for tasks that are typically performed by humans. Deep learning, machine learning, conventional neural networks, recognition, and fuzzy logic are a few of the subsets of AI with unique capabilities and functions that can enhance modern medical science. Such innovations simplify human interference in clinical diagnostic procedures, decision making, and medical imaging. To improve human health, connected biomedical network devices and software applications are interconnected to form the Internet of Medical Things (IoMT), the next generation of bioanalytical tools. This review paper provides in-depth analysis of the IoMT encasing its definition, technologies, applications, challenges, and future prospects. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Text-Based Sentiment Analysis: Experimentation with CNN and Basic Machine-Learning Approaches

Text-Based Sentiment Analysis: Experimentation with CNN and ...

引用

International Conference on Smart Systems and Wireless Communication, SSWC 2024

作者： Agrawal, Umang Kumar Das, Debashreet Ramana, B.V. Panda, Nibedan School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar India Department of Computer Science and Engineering Centre for UG and PG Studies BPUT Odisha Rourkela India Department of Information Technology Aditya Institute of Technology and Management Andhra Pradesh Tekkali India

ISBN: (纸本)9789819613472

Sentiment analysis, a burgeoning sector within natural language processing (NLP) plays a crucial role in discerning and perceiving attitudes, emotions and opinions expressed in the form of textual data in the social media platform. With the growing proliferation of social networks, sentiment analysis has become indispensable for the government, firms, and researchers, providing beneficial insights into customer feedback, public perception and new actuality. Over the years, Convolutional Neural Networks (CNN) have emerged as the most influential approach in NLP to implement text classification. In this article, we have incorporated Deep Neural Network (DNN) namely CNN in contrast with various basic supervised machine-learning (ML) approaches evaluated on the IMDB Movie Review Dataset. We have analyzed the pros and cons of each approach, simplifying their efficiency in analyzing the sentiments to compel the manifest model into a prolific and reliable approach for better text classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient and Privacy-Preserving Authentication for Federated Learning in Industrial Internet of Things Data Sharing Application

引用

IEEE Internet of Things Journal 2025年第9期12卷 11652-11663页

作者： Huang, Yongfei Xu, Guangxia Wang, Qiuyan Song, Xiaoling Wang, Xinhui Hengyang Normal University College of Computer Science and Technology Hengyang421002 China Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China Peng Cheng Laboratory Department of New Networks Shenzhen518000 China Chongqing University of Posts and Telecommunications School of Software Engineering Chongqing400065 China Hunan Institute of Technology School of Electrical and Information Engineering Hengyang421002 China

Federated learning (FL) has emerged as a promising approach for collaborative machine learning while respecting data privacy. However, directly aggregating local models during FL training can expose sensitive information, as adversaries may analyze model parameters to infer the underlying raw data. To address this concern, implementing a robust identity authentication mechanism can verify the integrity of local models and confirm their sources. However, many existing authentication schemes are computationally intensive, which can hinder performance. In this article, we present a lightweight authentication scheme for FL called EPPAFL. This innovative approach is compatible with all machine learning algorithms, maintains data utility, and ensures strong privacy protection. Additionally, it can be integrated with detection mechanisms to defend against data poisoning and free-rider attacks. Specifically, we first design a certificateless signature scheme based on the elliptic curve cryptography (ECC) and then propose an anonymous and efficient authentication protocol based on the Chinese remainder theorem (CRT), which supports batch verification, dynamic updates, and revocations of group keys. Moreover, participants interact anonymously to achieve secure communication, and trusted authority (TA) can track and recover the real identities of participants in case of malicious activities. We provide formal security proofs and analyses to demonstrate the achieved security properties. Performance evaluations demonstrate that our proposed protocol significantly reduces the costs associated with signature generation and verification, outperforming the existing schemes in both communication and computational efficiency. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Impact of Physical Configuration and Lead Time on WRF Forecasting of an Extreme Wind Event

引用

Journal of Meteorological Research 2025年第1期39卷 154-171页

作者： Rocío OTERO Matías SUAREZ Edgardo PIEROBON Leandro MATURANO Ignacio MONTAMAT Juan Ezequiel SANCHEZ Lucia SANDALIO Andrés RODRIGUEZ Denis POFFO Hydrometeorology Laboratory Department of ExactPhysical and Natural SciencesNational University of CordobaCórdobaX5016GCAArgentina Institute for Advanced Studies in Engineering and Technology National Scientific and Technical Research CouncilCordobaX5016GCAArgentina Radar and Remote Sensing Laboratory Department of MathematicsAstronomyPhysics and Computer ScienceNational University of CordobaCordobaX5016HUAArgentina

The central region of Argentina is known to be a source of some most extreme weather events in the world,which are partially associated with the passage of cold fronts accompanied often by extreme wind *** may cause severe property damage and even loss of human ***,there is a lack of studies that evaluate the performance of the numerical weather prediction(NWP)models such as weather research and forecasting(WRF)model in anticipating this type of weather in the *** study compares the performance of the operational WRF in Argentina using four combinations of various planetary boundary layer(PBL)and microphysics parameterization schemes under varied lead times in predicting an extreme wind event(gusts>30 m s^(-1))in Central *** results demonstrate that the WRF model is capable of providing an acceptable prediction of wind speed during an extreme *** is found that no single combination outperforms the others,although there is a slight tendency for Combination A,which utilizes the Mellor-Yamada-Janjic(MYJ)parameterization for the PBL and the Eta similarity parameterization for the surface layer,to more accurately capture the extreme wind *** with wind gust observations at five weather stations,the wind gust parameterization predicted the intensity and occurrence time of the peak wind,with an acceptable bias(time of peak<±1 h).Analysis of grid configurations(resolutions of 4 vs 9/3/1 km)revealed that higher resolution does not imply an improvement in the wind gust forecast for this particular *** regard to lead time,a shorter lead time does not necessarily result in more accurate ***,it is beneficial to conduct multiple sensitivity runs in order to obtain and understand the dispersion of forecasted wind speeds.

关键词： extreme wind wind event weather research and forecasting(WRF)model wind gust forecast cold front lead time

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Telegram App Reviews Using Text Classification Models 4

Sentiment Analysis of Telegram App Reviews Using Text Classi...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Thomas, Lijo P Thomas, Juby Menon, Vishnu Achutha Sateesh Kumar, T.K. Kristu Jayanti College Department of Computer Science Bengaluru India Kristu Jayanti College Department of Media Studies Bengaluru India Institute for Educational and Developmantal Studies Deparment of Communication and International Studies Noida India Kristu Jayanti College Department of Commerce Bengaluru India

ISBN: (纸本)9798331523923

This study explores sentiment analysis of Telegram app reviews using four machine learning-models: Naive Bayes, Random Forest, Logistic-Regression and Neural Networks. A dataset of 76,500 reviews was analyzed, and the models were evaluated based on precision, recall, F1-score, and accuracy across three sentiment categories: Negative, Neutral, and Positive. Among the models, random -forest achieved the highest accuracy of 75% but struggled with Neutral sentiment classification, a challenge shared by the other models. Logistic Regression and Naive Bayes both delivered 74% accuracy, with slightly better precision and recall for Negative and Positive sentiments. Neural Networks achieved 72% accuracy but faced difficulties in identifying Neutral sentiments. The use of 'Natural Language Processing' (NLP) techniques, such as text preprocessing and feature extraction, proved crucial for improving performance. © 2025 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Detection of Neurogenic Voice Disorders Using the Fisher Vector Representation of Cepstral Features

引用

Journal of Voice 2025年第3期39卷 757-763页

作者： Yagnavajjula, Madhu Keerthana Alku, Paavo Rao, Krothapalli Sreenivasa Mitra, Pabitra Department of Signal Processing and Acoustics Aalto University Espoo Finland Advanced Technology Development Centre Indian Institute of Technology Kharagpur West Bengal Kharagpur India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal Kharagpur India

Neurogenic voice disorders (NVDs) are caused by damage or malfunction of the central or peripheral nervous system that controls vocal fold movement. In this paper, we investigate the potential of the Fisher vector (FV) encoding in automatic detection of people with NVDs. FVs are used to convert features from frame level (local descriptors) to utterance level (global descriptors). At the frame level, we extract two popular cepstral representations, namely, Mel-frequency cepstral coefficients (MFCCs) and perceptual linear prediction cepstral coefficients (PLPCCs), from acoustic voice signals. In addition, the MFCC features are also extracted from every frame of the glottal source signal computed using a glottal inverse filtering (GIF) technique. The global descriptors derived from the local descriptors are used to train a support vector machine (SVM) classifier. Experiments are conducted using voice signals from 80 healthy speakers and 80 patients with NVDs (40 with spasmodic dysphonia (SD) and 40 with recurrent laryngeal nerve palsy (RLNP)) taken from the Saarbruecken voice disorder (SVD) database. The overall results indicate that the use of the FV encoding leads to better identification of people with NVDs, compared to the defacto temporal encoding. Furthermore, the SVM trained using the combination of FVs derived from the cepstral and glottal features provides the overall best detection performance. © 2022 The Authors

关键词： Fisher vector Glottal features MFCC Neurogenic voice disorders Perceptual linear prediction Support vector machine

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：