检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Jiang, Weikang Wang, Jinxian Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Department of Computer Science and Technology Tongji University China

Single-cell RNA sequencing (scRNA-seq) enables researchers to analyze gene expression at single-cell level. One important task in scRNA-seq data analysis is unsupervised clustering, which helps identify distinct cell types, laying down the foundation for other downstream analysis tasks. In this paper, we propose a novel method called Cluster-aware Iterative Contrastive Learning (CICL in short) for scRNA-seq data clustering, which utilizes an iterative representation learning and clustering framework to progressively learn the clustering structure of scRNA-seq data with a cluster-aware contrastive loss. CICL consists of a Transformer encoder, a clustering head, a projection head and a contrastive loss module. First, CICL extracts the feature vectors of the original and augmented data by the Transformer-encoder. Then, it computes the clustering centroids by K-means and employs the student’s t-distribution to assign pseudo-labels to all cells in the clustering head. The projection-head uses a Multi-Layer Perceptron (MLP) to obtain projections of the augmented data. At last, both pseudo-labels and projections are used in the contrastive loss to guide the model training. Such a process goes iteratively so that the clustering result becomes better and better. Extensive experiments on 25 real-world scRNA-seq datasets show that CICL outperforms the state-of-the-art (SOTA) methods. Concretely, CICL surpasses the existing methods by from 14% to 280%, and from 5% to 133% on average in terms of performance metrics ARI and NMI respectively. Source code is available at https://***/Alunethy/CICL. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

BEVGGC:Biogeography-Based Optimization Expert-VGG for Diagnosis COVID-19 via Chest X-ray Images

引用

computer Modeling in Engineering & sciences 2021年第11期129卷 729-753页

作者： Junding Sun Xiang Li Chaosheng Tang Shixin Chen College of Computer Science and Technology Henan Polytechnic UniversityJiaozuo454000China Nursing Department The Fourth People’s Hospital of Huai’anHuai’an223001China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou215000China

Purpose:As to January 11,2021,coronavirus disease(COVID-19)has caused more than 2 million deaths *** diagnostic methods of COVID-19 are:(i)nucleic acid *** method requires high requirements on the sample testing *** collecting samples,staff are in a susceptible environment,which increases the risk of infection.(ii)chest computed *** cost of it is high and some radiation in the scan process.(iii)chest X-ray *** has the advantages of fast imaging,higher spatial recognition than chest computed ***,our team chose the chest X-ray images as the experimental dataset in this ***:We proposed a novel framework—BEVGG and three methods(BEVGGC-I,BEVGGC-II,and BEVGGC-III)to diagnose COVID-19 via chest X-ray ***,we used biogeography-based optimization to optimize the values of hyperparameters of the convolutional neural ***:The experimental results show that the OA of our proposed three methods are 97.65%±0.65%,94.49%±0.22%and 94.81%±0.52%.BEVGGC-I has the best performance of all ***:The OA of BEVGGC-I is 9.59%±1.04%higher than that of state-of-the-art methods.

关键词： Biogeography-based optimization convolutional neural networks depthwise separable convolution dilated

来源：评论

学校读者我要写书评

暂无评论

VAction: A Lightweight and Integrated VR Training System for Authentic Film-Shooting Experience 25

VAction: A Lightweight and Integrated VR Training System for...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Shaocong Wang Che Qu Minjing Yu Chao Zhou Yuntao Wang Yu-Hui Wen Yuanchun Shi Yong-Jin Liu Department of Computer Science and Technology Tsinghua University Beijing China Film & TV Technology Department Beijing Film Academy Beijing Beijing China College of Intelligence and Computing Tianjin University Tianjin China Human Computer Interaction Technology and Intelligent Information Processing Laboratory Institute of Software Chinese Acadamy of Sciences Beijing China School of Computer Science and Technology Beijing Jiaotong University Beijing China Department of Computer science and Technology Tsinghua University Beijing China Computer Science and Technology Tsinghua University Beijing Beijing China

ISBN: (纸本)9798400713941

The film industry exerts significant economic and cultural influence, and its rapid development is contingent upon the expertise of industry professionals, underscoring the critical importance of film-shooting education. However, this process typically necessitates multiple practice in complex professional venues using expensive equipment, presenting a significant obstacle for ordinary learners who struggle to access such training environments. Despite VR technology has already shown its potential in education, existing research has not addressed the crucial learning component of replicating the shooting process. Moreover, the limited functionality of traditional controllers hinder the fulfillment of the educational requirements. Therefore, we developed VAction VR system, combining high-fidelity virtual environments with a custom-designed controller to simulate the real-world camera operation experience. The system's lightweight design ensures cost-effective and efficient deployment. Experiment results demonstrated that VAction significantly outperforms traditional methods in both practice effectiveness and user experience, indicating its potential and usefulness in film-shooting education. © 2025 Copyright held by the owner/author(s).

关键词： Film Production Education

来源：评论

学校读者我要写书评

暂无评论

Causal Discovery by Continuous Optimization with Conditional Independence Constraint: Methodology and Performance

Causal Discovery by Continuous Optimization with Conditional...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yewei Xia Hao Zhang Yixin Ren Jihong Guan Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University China Department of Computer Science & Technology Tongji University China

Discovering causal relationships from observational data is a challenging topic in artificial intelligence. Recent works formulate causal discovery as a continuous optimization problem with a differentiable acyclic constraint. Although these methods have achieved considerable performance improvement, they have two drawbacks: 1) they require a relatively large number of training samples; and 2) their performance will substantially deteriorate when facing heterogeneous noise. To address these problems, we first propose a low-order conditional independence (CI) constraint for the continuous optimization problem, and then design a soft version of the constraint by transforming it to a regularization term in the loss function of the continuous optimization problem. We show the convergence of continuous optimization with our constraint under some mild conditions, and the consistency of causal structure learning with the CI regularization. Extensive experiments on both synthetic and real-world datasets show that with our CI constraint or regularization, existing continuous optimization methods can achieve considerable performance improvement of causal discovery, especially when sample size is small.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Line-of-Sight Multipath Classification Method for BDS Using Convolutional Sparse Autoencoder with LSTM

引用

Tsinghua science and technology 2025年第1期30卷 68-86页

作者： Yahang Qin Zhenni Li Shengli Xie Bo Li Ming Liu Victor Kuzin School of Automation Guangdong University of Technologyand also with Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete ManufacturingGuangzhou 510006China School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Information Processing and System Integration of IoTMinistry of EducationGuangzhou 510006China Department of Electronic and Computer Engineering Hong Kong University of Science and TechnologHong Kong 999077China Academician of Russian Engineering Academy Moscow Moscow 125009Russia

Multipath signal recognition is crucial to the ability to provide high-precision absolute-position services by the BeiDou Navigation Satellite System(BDS).However,most existing approaches to this issue involve supervised machine learning(ML)methods,and it is difficult to move to unsupervised multipath signal recognition because of the limitations in signal *** by an autoencoder with powerful unsupervised feature extraction,we propose a new deep learning(DL)model for BDS signal recognition that places a long short-term memory(LSTM)module in series with a convolutional sparse autoencoder to create a new autoencoder ***,we propose to capture the temporal correlations in long-duration BeiDou satellite time-series signals by using the LSTM module to mine the temporal change patterns in the time ***,we develop a convolutional sparse autoencoder method that learns a compressed representation of the input data,which then enables downscaled and unsupervised feature extraction from long-duration BeiDou satellite series ***,we add an l_(1/2) regularizer to the objective function of our DL model to remove redundant neurons from the neural network while ensuring recognition *** tested our proposed approach on a real urban canyon dataset,and the results demonstrated that our algorithm could achieve better classification performance than two ML-based methods(e.g.,11%better than a support vector machine)and two existing DL-based methods(e.g.,7.26%better than convolutional neural networks).

关键词： convolutional sparse autoencoder BeiDou Navigation Satellite System(BDS) long short-term memory(LSTM) multipath classification

来源：评论

学校读者我要写书评

暂无评论

Descriptor: A Comprehensive Multimodal Dataset for Analyzing Maturity and Quality Indicators in Radish (Raphanus sativus)

IEEE Data Descriptions

引用

IEEE Data Descriptions 2024年 1卷 131-138页

作者： Ayan Sar Tanupriya Choudhury Tanmay Sarkar Faisal Imran School of Computer Science University of Petroleum and Energy Studies (UPES) Dehradun Uttarakhand India Department of Food Processing Technology Malda Polytechnic West Bengal State Council of Technical Education Government of West Bengal Malda India Department of Computer Science and Engineering International University of Business Agriculture and Technology (IUBAT) Dhaka Bangladesh

This work presents a novel multimodal dataset to address maturity and quality assessment in Radish ( Raphanus sativus). The analyzed dataset includes 360 images taken from five samples of radish that were photographed at three points—morning, afternoon, and evening on 24 subsequent days. Since the imaging process was intended to capture the visual growth in the presence of natural light, it offered a temporal resolution to the dataset. Consistent photos were taken each time to track the changes in texture, shape, and color of each sample. Besides the image data, this dataset contains comprehensive quality assessment records, where each radish sample's texture, shape, color, and overall appearance were scored between 1 and 10. These ratings were done based on just observations and touch sensations in an attempt to quantify some of the physical characteristics of the radish as it grew to maturity. Specific data needs are documented in an Excel file that incorporates timestamps, sample I.D.s, and ratings for each parameter for easy reference and to facilitate examination. It creates a platform to examine the relationship between environmental conditions and radish growth phases to apply machine learning algorithms and computer vision to evaluate the maturity and qualities of agricultural crops. This dataset may be useful for increasing the forecast accuracy of precision farming and for a better understanding of the dynamics of radish development. IEEE SOCIETY/COUNCIL Computational Intelligence Society (CIS) DATA TYPE/LOCATION Images (.jpg); Malda, West Bengal, India DATA DOI/PID 10.17632/cwxdmk8zhz.1

关键词： Crops Image color analysis Shape Visualization Quality assessment Monitoring Soil computer science Three-dimensional displays Pollution measurement

来源：评论

学校读者我要写书评

暂无评论

Disk Failure Prediction Based on SW-Disk Feature Engineering 8

Disk Failure Prediction Based on SW-Disk Feature Engineering

引用

8th IEEE International Conference on Big Data Security on Cloud, 8th IEEE International Conference on High Performance and Smart Computing, and 8th IEEE International Conference on Intelligent Data and Security, BigDataSecurity/HPSC/IDS 2022

作者： Liang, Chenjun Deng, Li Zhu, Jincan Cao, Zhen Li, Chao College of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Hubei University Department of Information Development and Management Wuhan China

ISBN: (纸本)9781665480697

With the rapid development of cloud storage, the number of disks has increased dramatically, and the absolute number of failed disks has also continued to increase. Since the impact of these failures on the quality of cloud services cannot be ignored, the demand for disk failure prediction is also increasing. In addition, the accuracy of the disk failure prediction algorithm largely depends on the input data set. Therefore, according to the large difference in the feature morphology in the disk tracking dataset, we analyze the change trend of features in different dimensions, and propose a new method. The SW-Disk feature engineering method for disk failure prediction constructs features from both horizontal and vertical dimensions. Including feature crossover between indicators and indicators to construct higher-order features. In the time dimension, the time series features under the multi-scale sliding window are constructed. We use the random forest prediction model to predict whether the disk will fail in the next 30 days, so as to reserve more time to take measures on the disk to achieve the purpose of improving the reliability of the cloud storage system. We validated our SW-Disk feature engineering method and prediction model on the Backblaze2019 disk dataset, and the experimental results demonstrate the effectiveness and superiority of our proposed method. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Cloud Storage I/O Load Prediction Based on XB-IOPS Feature Engineering 8

Cloud Storage I/O Load Prediction Based on XB-IOPS Feature E...

引用

ISBN: (纸本)9781665480697

With the popularization of cloud computing and the deepening of its application, more and more cloud block storage systems have been put into use. The performance optimization of cloud block storage systems has become an important challenge facing today, which is manifested in the reduction of system performance caused by the unbalanced resource load of cloud block storage systems. Accurately predicting the I/O load status of the cloud block storage system can effectively avoid the load imbalance problem. However, the cloud block storage system has the characteristics of frequent random reads and writes, and a large amount of I/O requests, which makes prediction difficult. Therefore, we propose a novel I/O load prediction method for XB-IOPS feature engineering. The feature engineering is designed according to the I/O request pattern, I/O size and I/O interference, and realizes the prediction of the actual load value at a certain moment in the future and the average load value in the continuous time interval in the future. Validated on a real dataset of Alibaba Cloud block storage system, the results show that the XB-IOPS feature engineering prediction model in this paper has better performance in Alibaba Cloud block storage devices where random I/O and small I/O dominate. The prediction performance is better, and the prediction time is shorter than other prediction models. © 2022 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Face Deepfakes - A Comprehensive Review

arXiv

引用

arXiv 2025年

作者： Fernando, Tharindu Priyasad, Darshana Sridharan, Sridha Ross, Arun Fookes, Clinton Signal Processing Artificial Intelligence & Vision Technologies Queensland University of Technology Australia Michigan State University Department of Computer Science and Engineering United States

In recent years, remarkable advancements in deepfake generation technology have led to unprecedented leaps in its realism and capabilities. Despite these advances, we observe a notable lack of structured and deep analysis deepfake technology. The principal aim of this survey is to contribute a thorough theoretical analysis of state-of-the-art face deepfake generation and detection methods. Furthermore, we provide a coherent and systematic evaluation of the implications of deepfakes on face biometric recognition approaches. In addition, we outline key applications of face deepfake technology, elucidating both positive and negative applications of the technology, provide a detailed discussion regarding the gaps in existing research, and propose key research directions for further investigation. Copyright © 2025, 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

Balance Multi-Head Attention based on Software and Hardware Co-design 9

Balance Multi-Head Attention based on Software and Hardware ...

引用

9th IEEE International Conference on Cyber Security and Cloud Computing and 8th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2022

作者： Xu, Dian Hu, Wei Liu, Fang Fan, Zimeng Shi, Qingsong Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System College of Computer Science Wuhan China Wuhan University Department of Information Engineering Wuhan Institute of City School of Computer Science Wuhan China Zhejiang University College of Computer Science Hangzhou China

ISBN: (数字)9781665480666

ISBN: (纸本)9781665480666

Recently, the Transformer-based models have achieved leading results in many research areas such as natural language processing and computer vision. However, since Transformer-based models have a huge computational complexities, optimization for Transformer is the focus of current research. the core of Transformer models is the attention module, and in this paper we propose a software and hardware co-designed attention module, which reduces the computational units of the multi-head attention module by balancing the The inference time of the attention module is reduced by balancing the computational units of multiple attention modules. At the same time, we design the corresponding structure on FPGA, which accelerate 14.6x inference time in comparison with the original attention module implementation on GPU. We applied this attention module to multiple visual Transformer models and tested the accuracy difference between the balanced multi-head attention module-based model and the original model on CIFAR-10, and obtained a result of 80.46%, which lower from the original version by 0.18%. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

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：