检索结果-内蒙古大学图书馆

PcdGS: A point cloud densification method for Gaussian Splatting

computers & Graphics 2025年 130卷

作者： Jing Zhao Chenxi Li Shuhui Zhang Feng Wang Ying Yin Yuhan Liu School of Information Science and Engineering Yanshan University Qinhuangdao 066000 Hebei China Hebei Key Laboratory of Computer Virtual Technology and System Integration Qinhuangdao Hebei China

Novel view synthesis (NVS) from limited observations continues to be an important and persistent challenge. Currently, methods based on Neural Radiance Fields (NeRF) are not very efficient, and although methods based on 3D Gaussian Splatting (3DGS) outperform NeRF in terms of rendering quality and speed, they still lack sufficient details. To tackle these issues, we introduce a new method for densifying the point cloud, which enhances the rendering effect of 3DGS-based techniques under sparse view conditions. First, we introduce a mask-based densification technique to improve rendering details under limited input views. Second, We propose a monocular pixel depth-based mapping method that leverages a pre-trained model to predict depth, effectively normalizing point locations within the resulting point cloud. Lastly, we implement a filtering method based on depth and RGB color to minimize noise introduced by the additional data. We conduct comparative experiments on the LLFF, Mip-NeRF 360, and Blender datasets, demonstrating that our method outperforms existing approaches in both evaluation metrics and visual quality, thereby validating its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Examining the Fourier Spectrum of Speech Signal from a Time-Frequency Perspective for Automatic Depression Level Prediction

引用

IEEE Transactions on Affective Computing 2025年

作者： Niu, Mingyue Tao, Jianhua He, Yongjun Zhang, Shiqing Li, Ming YanShan University School of Information Science and Engineering Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Taizhou University Institute of Intelligent Information Processing Taizhou318000 China Zhejiang Normal University Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua321004 China Zhejiang Institute of Optoelectronics Jinhua321004 China

Currently, many studies use Fourier amplitude spectra of speech signals to predict depression levels. However, those works often treat Fourier amplitude spectra as images or sequences to capture depression cues using convolutional neural networks or multilayer perceptrons. Therefore, they ignore the complex element composition and time-frequency attributes of Fourier spectra, which is not conducive to capturing the differences among individuals with different depression levels. For this reason, we construct a Time-Frequency Self-Embedding (TFSE) module, which not only stores the correlation relationship among real (imaginary) parts of Fourier spectra of different subjects from the time-frequency perspective, but also maintain the physical properties of data through the weight embedding process. Besides, Global Average Pooling (GAP) or linear layers are difficult to balance both temporal and frequency dimensions in the vectorization process. Therefore, we construct a Time-Frequency Tensor Vectorization (TFTV) module, which summarizes each channel along time and frequency dimensions, and then generates the vectorization result by integrating various channels. In this way, we combine TFSE and TFTV modules to form our SpectrumFormer model for predicting depression levels. Evaluation indicators on AVEC 2013 and AVEC 2014 depression databases imply the progressiveness of our model. © 2010-2012 IEEE.

关键词： Depression level prediction Real and imaginary parts Tensor vectorization Time-frequency attributes

来源：评论

学校读者我要写书评

暂无评论

Fast Smallest Lowest Common Ancestor Computation Based on Stable Match

引用

Journal of computer Science & technology 2013年第2期28卷 366-381页

作者：周军锋蓝国翔陈子阳汤显 School of Information Science and Engineering Yanshan University Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University School of Economics and Management Yanshan University

In this paper, we focus on efficient processing of XML keyword queries based on smallest lowest common ancestor （SLCA） semantics. For a given query Q with m keywords, we propose to use stable matches as the basis for SLCA computation, where each stable match M consists of m nodes that belong to the m distinct keyword inverted lists of Q. M satisfies that no other lowest common ancestor （LCA） node of Q can be found to be located after the first node of M and be a descendant of the LCA of M, based on which the operation of locating a stable match can skip more useless nodes. We propose two stable match based algorithms for SLCA computation, i.e., BSLCA and HSLCA. BSLCA processes two keyword inverted lists each time from the shortest to the longest, while HSLCA processes all keyword inverted lists in a holistic way to avoid the problem of redundant computation invoked by BSLCA. Our extensive experimental results verify the performance advantages of our methods according to various evaluation metrics.

关键词： XML keyword search smallest lowest common ancestor

来源：评论

学校读者我要写书评

暂无评论

Integrating a weighted-average method into the random walk framework to generate individual friend recommendations

引用

Science China(Information Sciences) 2017年第11期60卷 43-64页

作者： Jibing GONG Xiaoxia GAO Hong CHENG Jihui LIU Yanqing SONG Mantang ZHANG Yi ZHAO School of Information Science and Engineering Yanshan University The Key Lab for Computer Virtual Technology and System Integration Yanshan University State Key Lab of Mathematical Engineering and Advanced Computing Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong

Friend recommendation is a fundamental service in both social networks and practical applications,and is influenced by user behaviors such as interactions, interests, and activities. In this study, we first conduct in-depth investigations on factors that affect recommendation results. Next, we design Friend++, a hybrid multi-individual recommendation model that integrates a weighted average method(WAM) into the random walk(RW) framework by seamlessly employing social ties, behavior context, and personal information. In Friend++, the first plus signifies recommending a new friend through network features, while the second plus stands for using node features. To verify our method, we conduct experiments on three social datasets crawled from the Sina microblog system(Weibo). Experimental results show that the proposed method significantly outperforms six baseline methods in terms of recall, precision, F1-measure, and MAP. As a final step, we describe a case study that demonstrates the scalability and universality of our method. Through discussion, we reach a meaningful conclusion: although common interests are more important than user activities in making recommendations, user interactions may be the most important factor in finding the most appropriate potential friends.

关键词： multi-individual friend recommendation architecture behavior context analysis Intimacy degree random walk framework social networks

来源：评论

学校读者我要写书评

暂无评论

iBole： A Hybrid Multi-Layer Architecture for Doctor Recommendation in Medical Social Networks

引用

Journal of computer Science & technology 2015年第5期30卷 1073-1081页

作者：宫继兵王立立孙胜涛彭思维 School of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao 066004 China

In this paper, we try to systematically study how to perform doctor recommendation in medical social net- works （MSNs）. Specifically, employing a real-world medical dataset as the source in our work, we propose iBole, a novel hybrid multi-layer architecture, to solve this problem. First, we mine doctor-patient relationships/ties via a time-constraint probability factor graph model （TPFG）. Second, we extract network features for ranking nodes. Finally, we propose RWR- Model, a doctor recommendation model via the random walk with restart method. Our real-world experiments validate the effectiveness of the proposed methods. Experimental results show that we obtain good accuracy in mining doctor-patient relationships from the network, and the doctor recommendation performance is better than that of the baseline algorithms： traditional Ranking SVM （RSVM） and the individual doctor recommendation model （IDR-Model）. The results of our RWR-Model are more reasonable and satisfactory than those of the baseline approaches.

关键词： doctor recommendation architecture random walk with restart doctor-patient tie mining time-constraintprobability factor graph model medical social network

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of an enhanced Ethernet energy saving mechanism in IEEE 802.3az

引用

Journal of Information and Computational Science 2014年第5期11卷 1605-1613页

作者： Zhi, Shengyang Jin, Shunfu Meng, Chao College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004 China

In order to reduce the energy consumption and improve the response performance, by introducing the strategies of sleep-delay, pre-awake and split timing to IEEE 802.3az, an enhanced Ethernet energy saving mechanism is proposed. Considering the digital nature of modern communications, a discrete-time queueing model with multiple-vacation and N-strategy is built. With the method of an embedded Markov chain, we evaluate the energy saving efficiency of the system and the response performance of the data frames mathematically. Numerical experiments and simulation results show that, in the enhanced Ethernet energy saving mechanism, the average packet latency is reduced, while the energy saving ratio is satisfactory. © 2014 by Binary Information Press.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Detection Method for Shilling Attacks Based on Features of Automatic Extraction

引用

China Communications 2019年第8期16卷 130-146页

作者： Yaojun Hao Fuzhi Zhang Jinbo Chao School of Information Science and Engineering Yanshan UniversityQinhuangdao 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004China Department of Computer Science and Technology Xinzhou Teachers UniversityXinzhou 034000China

Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.

关键词： shilling attack ensemble detection features of automatic extraction marginalized linear denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Commodity dynamic pricing and inventory joint decision-making model based on specific power demand function

引用

Revista Tecnica de la Facultad de Ingenieria Universidad del Zulia 2016年第4期39卷 74-81页

作者： Sun, Dejie Liu, Wenyuan Zhang, Jie School of Information Science and Engineering Yanshan University Qinhuangdao Hebei066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao Hebei066004 China

Dynamic pricing and inventory play a respective role. The purpose of inventory is to try best to maintain an even production speed and efficiently ease supply-and-demand contradiction during the production process and among enterprises in the supply chain. However, dynamic pricing aims at maximizing revenues by setting commodities or services at different price levels according to diversified demands of consumers and different commodity or service price evaluation by consumers in different periods. Therefore, it is important for enterprises to optimize their dynamic pricing strategies and commodity inventory so as to maximize value of researches. However, demands for tangible commodities are uncertain. Generally speaking, the commodity demand volume should first be confirmed before any specific analysis. Therefore, this paper focuses on introducing the commodity demand function and relevant factors influencing the commodity demand volume. The utility function describing consumers' demands for a single commodity is analyzed. The specific power demand function model based on utility maximization is built through the utility function. At last, we conduct an in-depth analysis and simulation of the model.

关键词： Economics

来源：评论

学校读者我要写书评

暂无评论

Data stream clustering algorithm based on spatial directed graph

引用

Advances in Information Sciences and Service Sciences 2012年第20期4卷 241-249页

作者： Ren, Jiadong Yuan, Xuemei Dong, Jun College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China

Recently, the grid-density based clustering has become one of the major issues among all of the clustering approaches, it has special advantages over other clustering algorithms, such as less computation and the ability of clustering with arbitrarily shape, which are particularly useful for the data stream clustering. This paper defines a spatial directed graph named Grid-Based Graph (GBG) to store the non-empty grids in data space, and proposes a data stream clustering algorithm based on spatial directed graph GBGSClu (Grid-Based Graph Stream Clustering). GBG graph composes of vertices and directed edges, if a vertex A has a neighboring dense vertex B, and then there is a directed edge from vertex B to A in GBG. The algorithm maps the data stream into the non-empty vertices online, updates the vertices' feature vectors with the arriving of data stream, deletes the sparse vertices every gap time, generates GBG graph when the clustering quest coming and finally clusters on the current structure. The eventual clustering results can be obtained by only checking the vertices' in-degree which can reduce the computation needed in clustering. The validity and efficiency of GBGSClu algorithm have been tested and verified by clustering on real and synthetic datasets.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Efficient subtree results computation for XML keyword queries

引用

Frontiers of computer Science 2015年第2期9卷 253-264页

作者： Ziyang CHEN School of Information Science and Engineering Yanshan University Hebei 066004 China Environmental Management College of China Hebei 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of HeBei Province Yanshan University Hebei 066004 China

In this paper, we focus on efficient construction of restricted subtree （RSubtree） results for XML keyword queries on a multicore system. We firstly show that the perfor- mance bottlenecks for existing methods lie in 1） computing the set of relevant keyword nodes （RKNs） for each subtree root node, 2） constructing the corresponding RSubtree, and 3） parallel execution. We then propose a two-step generic top-down subtree construction algorithm, which computes SLCA/ELCA nodes in the first step, and parallelly gets RKNs and generates RSubtree results in the second step, where generic means that 1） our method can be used to compute dif- ferent kinds of subtree results, 2） our method is independent of the query semantics; top-down means that our method con- structs each RSubtree by visiting nodes of the subtree con- structed based on an RKN set level-by-level from left to right, such that to avoid visiting as many useless nodes as possible. The experimental results show that our method is much more efficient than existing ones according to various metrics.

关键词： XML SLCA/ELCA RSubtree RKNs parallel

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：