检索结果-内蒙古大学图书馆

33rd ACM Web Conference, WWW 2024

作者： Tang, Yi-Kun Huang, Heyan Shi, Xuewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Data Science and Artificial Intelligence Dongbei University of Finance and Economics Liaoning Dalian China

ISBN: (纸本)9798400701719

Topic models that can take advantage of labels are broadly used in identifying interpretable topics from textual data. However, existing topic models tend to merely view labels as names of topic clusters or as categories of texts, thereby neglecting the potential causal relationships between supervised information and latent topics, as well as within these elements themselves. In this paper, we focus on uncovering possible causal relationships both between and within the supervised information and latent topics to better understand the mechanisms behind the emergence of the topics and the labels. To this end, we propose Causal Relationship-Aware Neural Topic Model (CRNTM), a novel neural topic model that can automatically uncover interpretable causal relationships between and within supervised information and latent topics, while concurrently discovering high-quality topics. In CRNTM, both supervised information and latent topics are treated as nodes, with the causal relationships represented as directed edges in a Directed Acyclic Graph (DAG). A Structural Causal Model (SCM) is employed to model the DAG. Experiments are conducted on three public corpora with different types of labels. Experimental results show that the discovered causal relationships are both reliable and interpretable, and the learned topics are of high quality comparing with eight start-of-the-art topic model baselines. © 2024 ACM.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

A novel approach for image retrieval in remote sensing using vision-language-based image caption generation

引用

Multimedia Tools and Applications 2025年第6期84卷 2985-3014页

作者： Yadav, Prem Shanker Tyagi, Dinesh Kumar Vipparthi, Santosh Kumar Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India School of Artificial Intelligence and Data Engineering Indian Institute of Technology Ropar Punjab Rupnagar140001 India

Recent advancements in satellite technologies have resulted in the emergence of Remote Sensing (RS) images. Hence, the primary imperative research domain is designing a precise retrieval model for retrieving the most pertinent images based on the query. Present Remote Sensing Image Retrieval (RSIR) systems use visual descriptors to characterize the primitives (such as various land-cover types) that are visible in the images. However, the visual descriptors are inadequate for defining the complicated content of RS images. To solve this problem, a new model is devised for image retrieval based on image captions. The goal is to generate textual illustrations with captions to define relations amongst objects precisely. Here, image captioning is attained based on the vision-language pre-training model. The image captions are utilized for generating features like term frequency-inverse document frequency (TF-IDF), length of text, and Bag of Words. Meanwhile, query text is utilized wherein features like TF-IDF, text length, and Bag of Words are obtained. The similarity between query text features and the image captions features has been computed on the basis of a hybrid similarity measure wherein weights are tuned with the proposed Honey Badger Political Optimizer (HBPO) to retrieve the image. The proposed HBPO provided enhanced efficiency with elevated precision of 93.3%, recall of 93.7%, F1-score of 93.5%, and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) of 0.441. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Emergency Vehicle Detection Using Deep ConvNet2D and computer Vision 2

Emergency Vehicle Detection Using Deep ConvNet2D and Compute...

引用

2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024

作者： Poongavanam, Elumalaivasan Prathik, A. Munirathinam, T. Kayalvizhi, V. Rajesh, R. Mahavishnu, C. Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai Kattankulathur India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Sona College of Technology Department of Information Technology Salem India School of Computer Science and Engineering and Information Science Presidency University Bangalore India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Shreenivasa Engineering College Department of Computer Science and Engineering Dharmapuri India

ISBN: (纸本)9798350328202

A surveillance system detects emergency vehicles stuck in traffic. This system helps manage traffic because the number of vehicles on the road has been increasing daily for years, causing congestion. This project implements Deep ConvNet2D (Convolutional Network 2D) and computer Vision emergency vehicle recognition. We propose a CNN-based real-time image processing model for emergency vehicle detection. The signal control unit can be set to terminate the round robin sequence when an emergency vehicle is detected. A CNN trained on Indian ambulance images solves the problem. Tensor Flow, a Python library, was used for training. Our method detects and classifies emergency cars well. Existing systems use ANN algorithm, which is inaccurate and inefficient. The system uses Deep ConvNet2D Algorithm. The proposed real-time system is accurate. The proposed system loads and executes faster than the existing system. The system is efficient, scalable, and enhanced for complex use cases. © 2024 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic community detection algorithm based on hyperbolic graph convolution

引用

International Journal of Intelligent Computing and Cybernetics 2024年第3期17卷 632-653页

作者： Weijiang Wu Heping Tan Yifeng Zheng College of Information Science and Engineering/College of Artificial Intelligence China University of Petroleum BeijingBeijingChina Beijing Key Laboratory of Petroleum Data Mining China University of Petroleum BeijingBeijingChina School of Computer Science Minnan Normal UniversityZhangzhouChina

Purpose:Community detection is a key factor in analyzing the structural features of complex ***,traditional dynamic community detection methods often fail to effectively solve the problems of deep network information loss and computational complexity in hyperbolic *** address this challenge,a hyperbolic space-based dynamic graph neural network community detection model(HSDCDM)is ***/methodology/approach:HSDCDM first projects the node features into the hyperbolic space and then utilizes the hyperbolic graph convolution module on the Poincare and Lorentz models to realize feature fusion and information *** addition,the parallel optimized temporal memory module ensures fast and accurate capture of time domain information over extended ***,the community clustering module divides the community structure by combining the node characteristics of the space domain and the time *** evaluate the performance of HSDCDM,experiments are conducted on both artificial and real ***:Experimental results on complex networks demonstrate that HSDCDM significantly enhances the quality of community detection in hierarchical *** shows an average improvement of 7.29%in NMI and a 9.07%increase in ARI across datasets compared to traditional *** complex networks with nonEuclidean geometric structures,the HSDCDM model incorporating hyperbolic geometry can better handle the discontinuity of the metric space,provides a more compact embedding that preserves the data structure,and offers advantages over methods based on Euclidean geometry ***/value:This model aggregates the potential information of nodes in space through manifoldpreserving distribution mapping and hyperbolic graph topology ***,it optimizes the Simple Recurrent Unit(SRU)on the hyperbolic space Lorentz model to effectively extract time series data in hyperbolic space,thereby enhancing computing efficiency by eliminating t

关键词： Complex networks Dynamic community detection Hyperbolic graph neural network

来源：评论

学校读者我要写书评

暂无评论

A Deepfake Image Classifier System for real and Doctored Image Differentiation 7

A Deepfake Image Classifier System for real and Doctored Ima...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Thomas, Juanith Mathew Ebenezer, V. Richard, Rohan Paul Karunya Institute of Technology And Sciences Division of Computer Science And Engineering Coimbatore India Karunya Institute of Technology And Sciences Division of Data Science And Cyber Security Coimbatore India

ISBN: (纸本)9798350359299

The sudden proliferation of deepfake technology has raised concerns about the authenticity and integrity of digital media. In response to these concerns, this paper presents a Deepfake image classifier system designed to differentiate between real and doctored images using "MesoNet"architecture which utilizes convolutional layers and builds a suitable neural network for classification. Making efficient use of Deep Learning strategies, this system aims to detect subtle manipulations indicative of deepfake alterations. The proposed model is trained on two distinct datasets: dataset I comprises authentic images while dataset II consists of images subjected to various levels of manipulation, making them deepfakes. Through extensive training using these images and their labels, we'll train the neural network to adequately predict the authenticity of an image. The model has been trained on exactly 7104 images and judging from the results, the predictions made by the model are fairly accurate. Results yield an accuracy of 88.81% and a precision of 87.93%. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Real-Time Traffic Flow Optimization using Adaptive IoT and data Analytics: A Novel DeepStreamNet Model 4

Real-Time Traffic Flow Optimization using Adaptive IoT and D...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Saranya, V.S. Subbarao, Garimidi Balakotaiah, Dega Bhavsingh, Maloth Babu, K. Suresh Dhanikonda, Srinivasa Rao School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chennai603 203 India India Department of Computer Science and Engineering India Ashok: Womens Engineering College Department of Computer Science and Engineering Andhra Pradesh Kurnool India Department of Computer Science and Engineering A.P Narasaraopet India Department of Artificial Intelligence and Data Science Telangana Hyderabad India

ISBN: (纸本)9798331540364

Thisstudy introduces the DeepStreamNet model, an advanced framework for enhancing real-time traffic management in urban environments using adaptive IoT and sophisticated big data analytics. Central to our approach is the integration of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) units, which synergize with IoT devices to facilitate dynamic adaptation to fluctuating traffic conditions. The model excels in operational performance, achieving a notable accuracy of 94.7% in congestion prediction with an exceptionally low latency of only 45 ms per decision cycle and the capability to process up to 50,000 data points per second. These technical achievements have marked significant improvements over traditional traffic management systems, enhancing traffic flow efficiency and reducing congestion effectively. The results underscore the transformative potential of the DeepStreamNet model in urban traffic management and public safety, offering actionable insights for intelligent transportation systems and setting the stage for more informed urban planning. Looking forward, we suggest extending the application of our model to areas such as logistics and broader smart city initiatives, highlighting its adaptability and broad utility in various urban contexts © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Quantum-enhanced Vehicle Detection and Speed Monitoring using OpenCV

Quantum-enhanced Vehicle Detection and Speed Monitoring usin...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Simonthomas, S. Naresh, B. Rohith, K. Aarupadai Veedu Institute of Technology Department of Computer Science and Engineering Chennai India Aarupadai Veedu Institute of Technology Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331541170

Quantum based vehicle detection is the innovative integration of Quantum Machine Learning (QML) techniques with classical computer vision methods to enhance vehicle detection and speed tracking systems using OpenCV. Traditional approaches in vehicle detection and speed tracking are often hindered by computational inefficiencies and accuracy limitations in complex traffic scenarios. Our proposed hybrid quantum-classical framework aims to overcome these complications by exploiting the computational advantages of quantum computing. In this study, we employ Quantum Principal Component Analysis (QPCA) for feature extraction and data dimensionality reduction, optimizing the input data for improved processing efficiency. The core detection mechanism integrates Quantum Neural Networks (QNNs) with classical Convolutional Neural Networks (CNNs), enhancing the model's accuracy in identifying vehicles within video frames. For speed tracking, we apply quantum optimization techniques to refine the tracking of vehicle positions across consecutive frames, ensuring precise speed calculation. Using OpenCV for real-time video processing and Qiskit for quantum computations, the findings from the experiments indicate significant improvements in both detection a precision, accuracy and computational efficiency. The hybrid quantum-classical model showcases the potential of quantum computing in advancing computer vision applications, particularly in intelligent transportation systems. This research highlights the transformative impact of QML techniques on practical applications and paves the way for further advancements in quantum-enhanced vehicle detection and speed tracking. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Assessing Algorithmic Bias in Machine Learning Classifiers: A Fairness Evaluation

Assessing Algorithmic Bias in Machine Learning Classifiers: ...

引用

2024 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2024

作者： Hamdan, S. Wagle, S. Poudel, S. Zhou, Y. Poudel, K. Middle Tennessee State University Computer Science MurfreesboroTN United States Middle Tennessee State University Computational And Data Science MurfreesboroTN United States

ISBN: (纸本)9798350388572

In the realm of healthcare, AI stands as an invaluable tool that significantly contributes to streamlining healthcare records [1]. It excels in organizing medical documentation, enabling remote patient monitoring, and extracting critical information from EHR systems. Furthermore, AI profoundly influences drug discovery and development by predicting patient responses to medications and identifying those who will benefit most from specific treatments [2]. This technological advancement also enhances the efficacy of personalized medicine by tailoring treatments to patients based on their medical histories. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Privacy Preservation Fully Homomorphic Encryption for Cloud-assisted Biometric Identification with Multi-key

Privacy Preservation Fully Homomorphic Encryption for Cloud-...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Peng, Shenghui Jia, Peiheng Xiong, Jinbo Zhu, Liehuang Liu, Ximeng Beijing Institute of Technology School of Cyberspace Science and Technology Beijing China Fujian Normal University College of Computer and Cyber Security Fuzhou China Fuzhou University College of Computer and Data Science Fuzhou China

ISBN: (纸本)9798350351255

Biometrics is a technology that utilizes individual physiological or behavioral characteristics for identity authentication and identification, ensuring secure and accurate identity verification by comparing biometric information with samples in a database. However, traditional biometric technology raises concerns about privacy leakage, which has led to the emergence of privacy-preserving biometric technology. This study introduces a cloud-assisted privacy-preserving biometric authentication system based on multi-key full homomorphic encryption. Our scheme employs a TFHE encryption scheme to encrypt user biometrics and utilizes a cloud server to assist in computation. We design secure computing protocols based on multi-key TFHE and develop a privacy-preserving biometric system based on a single cloud server. Privacy analysis and performance evaluation demonstrate that the proposed solution is efficient and feasible. Our experimental findings indicate that the proposed scheme exhibits a superior accuracy rate to current schemes. Compared to the best solution, our method has increased the iris recognition accuracy by approximately 68.42%. Although the experimental results demonstrate high accuracy and feasibility, implementing TFHE in biometric models could be improved by its execution time, presenting challenges for broad adoption. Nevertheless, through optimization and technological advancements, this protocol is anticipated to elevate privacy protection standards in practical biometric recognition systems moving forward. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning from Purified Demonstrations 41

Imitation Learning from Purified Demonstrations

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yunke Dong, Minjing Zhao, Yukun Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan Institute of Data Intelligence Wuhan University China Department of Computer Science City University of Hong Kong Hong Kong School of Computer Science Faculty of Engineering The University of Sydney Australia

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often imperfect, leading to challenges in the effectiveness of imitation learning. While existing research has focused on optimizing with imperfect demonstrations, the training typically requires a certain proportion of optimal demonstrations to guarantee performance. To tackle these problems, we propose to purify the potential noises in imperfect demonstrations first, and subsequently conduct imitation learning from these purified demonstrations. Motivated by the success of diffusion model, we introduce a two-step purification via diffusion process. In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise. Subsequently, a reverse generative process is utilized to recover the optimal demonstration from the diffused ones. We provide theoretical evidence supporting our approach, demonstrating that the distance between the purified and optimal demonstration can be bounded. Empirical results on MuJoCo and RoboSuite demonstrate the effectiveness of our method from different aspects. Copyright 2024 by the author(s)

关键词： Contrastive Learning

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：