检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shiyu Yu Lijian Gao Qirong Mao School of Computer Science and Communication Engineering Jiangsu University Zhenjiang 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: (数字)9798350368741

ISBN: (纸本)9798350368758

Sound Event Detection (SED) often employs pre-trained models to address data scarcity issues. However, existing systems usually treat the pretrained models as frozen feature extractors, resulting in suboptimal efficiency, or fully fine-tune the pretrained models, which requires substantial computational resources. To fully leverage the knowledge from pretrained models, we propose a novel Global Enhanced Frame Prompt Tuning (GE-FPT) framework, providing global and local insights tailored for SED tasks. Additionally, Frame Prompt Tuning (FPT) is proposed in our GE-FPT to effectively explore local temporal information, i.e., temporal details and context, which is essential for SED tasks, and in particular, for precise event boundary detection. Extensive experiments claim that our approach significantly outperforms full fine-tuning methods while substantially reducing computational costs. Our system achieves new state-of-the-art results, with PSDS1/PSDS2 scores of 0.628/0.845 on the DCASE2023 Challenge Task4 dataset. The source code is publicly available 1 .

关键词： Event detection Computational modeling Source coding Signal processing Feature extraction data models Acoustics Computational efficiency Speech processing Tuning

来源：评论

学校读者我要写书评

暂无评论

Key Clues Guided Video Character Social Relationship Recognition Enhanced by LLM

Key Clues Guided Video Character Social Relationship Recogni...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wenlong Dong Qing Zhu Qirong Mao 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: (数字)9798350368741

ISBN: (纸本)9798350368758

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 (LE-KCS) 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 LE-KCS on the MovieGraphs dataset and the experimental results indicate that our proposed LE-KCS achieves state-of-the-art performance.

关键词： Accuracy Large language models Speech recognition Signal processing Acoustics Character recognition Speech processing

来源：评论

学校读者我要写书评

暂无评论

Personalized Multimedia Recommendation Systems Using Higher-Order Tensor Singular-Value-Decomposition

引用

IEEE Transactions on Broadcasting 2024年第1期70卷 148-160页

作者： Chang, Shih Yu Wu, Hsiao-Chun Yan, Kun Chen, Xinjia Huang, Scott Chih-Hao Wu, Yiyan San Jose State University Department of Applied Data Science San JoseCA95192 United States Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for AI Applications Chungli32003 Taiwan Guilin University of Electronic Technology Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Department of Information and Telecommunication Guilin541004 China Northwestern State University Department of Engineering Technology NatchitochesLA71497 United States National Tsing Hua University Department of Electrical Engineering Hsinchu300 Taiwan Communications Research Centre Canada OttawaK2H 8S2 Canada

Because of rapid growth of multimedia data over the Internet, the infobesity has been emerging in recent years. Many recommender systems (RSs) have been proposed using a variety of techniques, including artificial intelligence, machine learning, statistical analysis, and data mining. Nowadays, E-commerce companies such as Amazon, eBay, Netflix, etc. have applied RSs conveniently to provide better customer services than before by enabling customized multimedia-content recommendations. It is well known that classical RSs are almost all based on the user-item attribute matrices. However, this two-fold user-item relationship should be extended to the emerging many-fold relationship among an arbitrary number of attribute groups so that the corresponding new RSs may lead to better performances. Therefore, in this paper, we introduce a novel personalized multimedia recommender system (PMRS) according to our proposed new parallel higher-order tensor singular-value-decomposition (PHOTSVD) algorithm. This PHOTSVD algorithm is capable of accommodating an arbitrary number of entities such as social-media channels, users, queries, webpages, etc. in a robust RS. Furthermore, we also investigate the cold start and data bias problems critical to RSs. Finally, we compare the performances of our proposed new PMRS and three other existing tensor-based RSs over realworld data with respect to the well-adopted metric, namely normalized root-mean-square error (NRMSE). Our proposed new PMRS greatly outperforms the other three existing tensor-based RSs in terms of NRMSE. © 1963-12012 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Method for Train Accident Prevention and Detection Using ResNet and Long Short-Term Memory Network

An Intelligent Method for Train Accident Prevention and Dete...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Jeyaselvi, M. Kavitha, V. Kalaiarasi, S. Sekhar, Savanam Chandra Girdharwal, Nitin Sindhu, K. Srm Institute of Science and Technology Department of Networking and Communications Chennai Kattankulathur India Vardhaman College of Engineering Department of Mathematics Hyderabad India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Data Science Chennai India Koneru Lakshmaiah Education Foundation Kl University Department of Bba Telangana Vijayawada India Faculty of Management Indore India M.Kumarasamy College of Engineering Master of Computer Applications Tamilnadu Karur India

ISBN: (纸本)9798350300857

At unattended railroad crossings, numerous technologies have been developed to monitor trains, identify objects, and automatically open and close gates. In order to prevent accidents at the crossing, the currently planned systems may effectively close and open the gates upon the arrival and departure of trains. However, there are frequently incidents at railroad crossings caused by the unexpected arrival of trains. Indulging in headphone use is a leading cause of accidents on railroad tracks. The literature review revealed that no viable approach for preventing such mishaps had been developed. The purpose of this proposed system is to provide a comprehensive analysis of the current systems dedicated to the prevention of accidents in real time. Preprocessing, feature selection, and model performance evaluation are all used in the suggested method. The DWT method is used for preprocessing in the suggested method. PCA and LDA are used for feature selection. The suggested method employs ResNet LS TM to assess the efficiency of the model. Two conventional approaches, LSTM and GRU, are contrasted with the proposed methodology. The proposed method outperforms the other two. © 2023 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Innovative Artificial Intelligence-Based Internet of Things for Smart Cities and Smart Homes

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷 p1-3页

作者： Sung, Tien-Wen Lee, Chao-Yang Gaber, Tarek Nassar, Hamed Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Taiwan School of Science Engineering & Environment University of Salford Manchester United Kingdom Department of Computer Science Suez Canal University Ismailia Egypt

The integration of IoT systems and AI technology is very suitable for interconnected things to enhance intelligence, thus the artificial intelligence of things (AIoT), which enables the establishment of innovative IoT systems and applications for the modern smart city and smart home. The Internet of Things (IoT) consists of interconnected things with built-in and function-oriented sensors, essentially constituting a network of physical devices. The paper titled "Utilizing Artificial Intelligence and Lotus Effect in an Emerging Intelligent Drone for Persevering Solar Panel Efficiency" by F. A. Almalki et al. proposes a drone system with AI framework to help clean solar panels mounted on the top of buildings and enhance their efficiency. [Extracted from the article]

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer-Enhanced Dilated Convolutional Networks for Early Detection of Neurological Disorders

Transformer-Enhanced Dilated Convolutional Networks for Earl...

引用

Artificial Intelligence and Machine Learning applications Theme: Healthcare and Internet of Things (AIMLA), International Conference on

作者： A. Syed Musthafa R. Mekala G. Jenifa Vignesh Janarthanan T. Vadivel H. Fathima Department of Information Technology M. Kumarasamy College of Engineering Karur Tamil Nadu India Department of Artificial Intelligence and Data Science Akshaya College of Engineering and Technology Coimbatore Tamil Nadu India Computer Science and Engineering (AI) Madanapalle Institute of Technology and Science Madanapalle Andhra Pradesh India SIMATS Engineering Saveetha University Chennai Department of Computer Applications K S Rangasamy College of Arts and Science Tiruchengode Tamil Nadu

ISBN: (数字)9798331538965

ISBN: (纸本)9798331538972

In The fusion of Transformer networks with convolutional architecture's has been very fruitful in launching the push for the early detection of neurological disorders. The current study introduces the Transformer Enhanced Dilations (TEDCN) in which it processes clinical records and past medical history to detect patterns characteristic of neurological conditions. The proposed model stands on the ability of Transformers to capture the long-range dependencies of the data, together with dilated convolutions that reinforce the receptive field without losing the resolution. The TEDCN model is an outcome of a research approach, which is based on the use of the Transformer network and dilated convolutions for better receptive field coverage with maximum resolution. Furthermore, data porosity can be met through the three diverse types of information, i.e., clinical data, medical histories, and diagnostics. The TEDCN can solve the massive, complex datasets and as a result, it can detect the disease early with high accuracy. The accuracy of the model to detect the slightest of the relationships amongst the previous records of a patient and disorders becomes a valid way of starting intervention and therefore healthcare management turns out to be benefitted. In the meantime, the proposed method has proved to be effective in early determination of neurological disorders after a thorough examination of various clinical data, thus shortening the gap between the detection and the treatment.

关键词： Neurological diseases Hypertension Heart rate Anxiety disorders Transformers data models Glucose Diabetes History Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

A Smart Air Pollutants Monitoring System Using IOT Technologies

A Smart Air Pollutants Monitoring System Using IOT Technolog...

引用

Intelligent Systems for Communication, IoT and Security (ICISCoIS), International Conference on

作者： M Pyingkodi N R Wilfred Blessing K Thenmozhi K Kanimozhi L Pavithira P K Sandhya Balakrishnan Department of Computer Applications Kongu Engineering College Erode India IT Department College of Computing and Information Sciences University of Technology and Applied Sciences-Ibri(Government) Oman Department of Computer Science Kristu Jayanti College Bengaluru India Department of Information Technology Sri Krishna Adithya College of Arts and Science Coimbatore Department of Computer Science with Data Analytics PSG college of Arts & Science College Coimbatore Department of Computer Science CMS College of Science and Commerce Coimbatore

On international basis, one in all our century's essential problems is air pollutants. Every year, the range of individuals killed via way of means of pollutants climbs, with air pollutants being the main cause. The Internet of Things (IoT) is used worldwide community of “inventive gadgets” which could sense, and join to, and have interaction with different humans and systems. The solution is furnished via way of means of a sensor-primarily based totally hardware module that can be deployed anywhere. These gadgets, which can be hooked up on mild poles, homes, and different structures, wirelessly speak air pleasant facts to a far flung server. The microprocessor collects facts from IoT sensing gadgets and sends it to a cloud server for processing. These facts can be used to expecting while the vicinity is maximum polluted. The machine additionally gives air pleasant statistics through a cell application, permitting clients to choose alternatives wherein the air pleasant is great. It is likewise a totally less expensive device.

关键词： Cloud computing Microprocessors Air pollution Hardware Sensors Servers Internet of Things

来源：评论

学校读者我要写书评

暂无评论

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Learning as a Service 19

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Le...

引用

19th IEEE International Conference on e-science, e-science 2023

作者： Li, Zilinghan He, Shilan Chaturvedi, Pranshu Hoang, Trung-Hieu Ryu, Minseok Huerta, E.A. Kindratenko, Volodymyr Fuhrman, Jordan Giger, Maryellen Chard, Ryan Kim, Kibaek Madduri, Ravi Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Department of Computer Science University of Illinois at Urbana-Champaign UrbanaIL61801 United States National Center for Supercomputing Applications University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL61801 United States School of Computing and Augmented Intelligence Arizona State University TempeAZ85281 United States Department of Physics University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Computer Science The University of Chicago ChicagoIL60637 United States University of Chicago Consortium for Advanced Science and Engineering ChicagoIL60637 United States Mathematics and Computer Science Division Argonne National Laboratory LemontIL60439 United States

ISBN: (纸本)9798350322231

Cross-silo privacy-preserving federated learning (PPFL) is a powerful tool to collaboratively train robust and generalized machine learning (ML) models without sharing sensitive (e.g., healthcare of financial) local data. To ease and accelerate the adoption of PPFL, we introduce APPFLx, a ready-to-use platform that provides privacy-preserving cross-silo federated learning as a service. APPFLx employs Globus authentication to allow users to easily and securely invite trustworthy collaborators for PPFL, implements several synchronous and asynchronous FL algorithms, streamlines the FL experiment launch process, and enables tracking and visualizing the life cycle of FL experiments, allowing domain experts and ML practitioners to easily orchestrate and evaluate cross-silo FL under one platform. APPFLx is available online at https://*** © 2023 IEEE.

关键词： Privacy-preserving techniques

来源：评论

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for Speech Source Separation

arXiv

引用

arXiv 2025年

作者： Dong, Jinwei Wang, Xinsheng 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 Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi’an China

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method’s superior performance over existing diffusion and discriminative models, validating its efficacy. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

LECF: recommendation via learnable edge collaborative filtering

引用

science China(Information sciences) 2022年第1期65卷 116-130页

作者： Shitao XIAO Yingxia SHAO Yawen LI Hongzhi YIN Yanyan SHEN Bin CUI School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications School of Information Technology and Electrical Engineering The University of Queensland Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Computer Science and Technology Peking University National Engineering Laboratory for Big Data Analysis and Applications Peking University

The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simple relationships between objects, e.g., user-item, item-item, or user-user. They always rely on a single type of object-object relationship, ignoring other useful relationship information in data. In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering(LECF). LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data. Specifically, we first adopt the concept of line graph where each node represents an interaction edge; then calculate a weighted sum of similarity between the query edge and the observed edges(i.e., historical interactions) that are selected from the neighborhood of query edge in the line graph for a recommendation. In addition, we design an efficient propagation algorithm to speed up the training and inference of LECF. Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods.

关键词： collaborative filtering recommender system implicit feedback edge-edge similarity line graph

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：