检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yao, Jing Dou, Zhicheng Xie, Ruobing Lu, Yanxiong Wang, Zhiping Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China WeChat Search Application Department Tencent China Beijing Key Laboratory of Big Data Management and Analysis Methods Key Laboratory of Data Engineering and Knowledge Engineering MOE

Search and recommendation are the two most common approaches used by people to obtain information. They share the same goal - satisfying the user's information need at the right time. There are already a lot of Internet platforms and Apps providing both search and recommendation services, showing us the demand and opportunity to simultaneously handle both tasks. However, most platforms consider these two tasks independently - they tend to train separate search model and recommendation model, without exploiting the relatedness and dependency between them. In this paper, we argue that jointly modeling these two tasks will benefit both of them and finally improve overall user satisfaction. We investigate the interactions between these two tasks in the specific information content service domain. We propose first integrating the user's behaviors in search and recommendation into a heterogeneous behavior sequence, then utilizing a joint model for handling both tasks based on the unified sequence. More specifically, we design the Unified Information SEarch and Recommendation model (USER), which mines user interests from the integrated sequence and accomplish the two tasks in a unified way. Experiments on a dataset from a real-world information content service platform verify that our model outperforms separate search and recommendation baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm

arXiv

引用

arXiv 2023年

作者： Li, Jiatong Liu, Qi Wang, Fei Liu, Jiayu Huang, Zhenya Yao, Fangzhou Zhu, Linbo Su, Yu Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China School of Computer Science and Technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Hefei Normal University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

Personalized learner modeling using cognitive diagnosis (CD), which aims to model learners’ cognitive states by diagnosing learner traits from behavioral data, is a fundamental yet significant task in many web learning services. Existing cognitive diagnosis models (CDMs) follow the proficiency-response paradigm that views learner traits and question parameters as trainable embeddings and learns them through learner performance prediction. However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners’ cognitive states and the quality of web learning services. To address these problems, we propose an identifiable cognitive diagnosis framework (ID-CDF) based on a novel response-proficiency-response paradigm inspired by encoder-decoder models. Specifically, we first devise the diagnostic module of ID-CDF, which leverages inductive learning to eliminate randomness in optimization to guarantee identifiability and captures the monotonicity between overall response data distribution and cognitive states to prevent explainability overfitting. Next, we propose a flexible predictive module for ID-CDF to ensure diagnosis preciseness. We further present an implementation of ID-CDF, i.e., ID-CDM, to illustrate its usability. Extensive experiments on four real-world datasets with different characteristics demonstrate that ID-CDF can effectively address the problems without loss of diagnosis preciseness. Our code is available at https://***/CSLiJT/ID-CDF. Copyright © 2023, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Estimation Soil Organic Matter Using Airborne Hyperspectral Imagery

Estimation Soil Organic Matter Using Airborne Hyperspectral ...

引用

Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS

作者： Lihan Chen Kun Tan Xue Wang Chen Pan Key Laboratory for Land Environment and Disaster Monitoring of NASG China University of Mining and Technology Xuzhou China Key Laboratory of Geographic Information Science (Ministry of Education) East China Normal University Shanghai China Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities Ministry of Natural Resources East China Normal University Shanghai China School of Geographic Sciences East China Normal University Shanghai China Shanghai Municipal Institute of Surveying and Mapping Shanghai China

Soil organic matter (SOM) content plays an important part in soil environmental quality definition and should be estimated necessarily. The conventional methods for the SOM concentration assessment are mainly based on laboratory physicochemical analysis, which is costly and time consuming. Visible and near-infrared (Vis–NIR) spectroscopy offers the potential to quantify the SOM over large areas based on the soil spectral characteristics. Therefore, an innovative methodology using visible and near-infrared reflectance spectra are proposed in this work to monitoring the SOM rapidly and economically. A total of 91 soil samples and their spectral data collected in Yitong of China were utilized to characterize the relationship between the soil reflectance spectrum and SOM. First, continuum removal (CR) and competitive adaptive reweighted sampling (CARS) are introduced as the pretreatment method and wavebands selection method respectively, which can amplify the weak spectral characteristic. After the preprocessing phases, Partial Least Squares (PLS), Random Forest (RF) and XGBoost are carried out to estimate the SOM and the results show that XGBoost yields the best performance with R 2 of 0.9968 on training set and 0.6831 on testing set. Finally, the distribution trend of SOM in the whole study area is mapped using the optimal CR-CARS-XGBoost model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GIS Based FLMP Solving in Densely Populated City Areas: a Case Study in Singapore

引用

Journal of Geodesy and Geoinformation Science 2022年第2期5卷 111-123页

作者： Yu Ning Hazel ANG Kai CAO Department of Geography National University of SingaporeSingapore 139649Singapore School of Geographic Sciences East China Normal UniversityShanghai 200241China Key Laboratory of Geographic Information Science(Ministry of Education) East China Normal UniversityShanghai 200241China Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities(Ministry of Natural Resources) Shanghai 200241China

With continual population growth in the densely populated cities,e.g.,Singapore,traffic congestion is the main transportation *** such,Public Transport is deemed as the most sustainable mode of ***,pubic transport is often plagued with the First and Last Mile Problem(FLMP),reducing its appeal especially in the densely populated city *** FLMP leads to a wide range of complications,in particular,human congestion in public *** this research,after a comprehensive discussion of FLMP problem in densely populated city areas,a case study in Singapore,i.e.,the Kent Ridge Campus of National University of Singapore(KRC-NUS),has been conducted based on the survey and spatio-temporal *** addition to the investigation of FLMP status in the case study area,a new campus shuttle bus route from an alternative MRT station(Haw Par Villa Station)has also been proposed based on the Tabu Search to alleviate the human congestion and current FLMP status for *** research not only has successfully addressed the FLMP in the case study area,but also can be a good reference for other areas in densely populated cities to help mitigate FLMPs.

关键词： GIS First and Last Mile Problem Tabu Search Public Transport Singapore

来源：评论

学校读者我要写书评

暂无评论

A review of big data technology and its application in cancer care

引用

Computers in Biology and Medicine 2024年 176卷 108577-108577页

作者： Xiao, Tianyun Kong, Shanshan Zhang, Zichen Hua, Dianbo Liu, Fengchun Hebei Key Laboratory of Data Science and Application North China University of Science and Technology Hebei Tangshan063210 China The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and Technology Hebei Tangshan063210 China College of Science North China University of Science and Technology Hebei Tangshan063210 China Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and Technology Hebei Tangshan China Tangshan Intelligent Industry and Image Processing Technology Innovation Center North China University of Science and Technology Hebei Tangshan China Beijing Sitairui Cancer Data Analysis Joint Laboratory Beijing101149 China

The development of modern medical devices and information technology has led to a rapid growth in the amount of data available for health protection information, with the concept of medical big data emerging globally, along with significant advances in cancer care relying on data-driven approaches. However, outstanding issues such as fragmented data governance, low-quality data specification, and data lock-in still make sharing challenging. Big data technology provides solutions for managing massive heterogeneous data while combining artificial intelligence (AI) techniques such as machine learning (ML) and deep learning (DL) to better mine the intrinsic connections between data. This paper surveys and organizes recent articles on big data technology and its applications in cancer, dividing them into three different types to outline their primary content and summarize their critical role in assisting cancer care. It then examines the latest research directions in big data technology in cancer and evaluates the current state of development of each type of application. Finally, current challenges and opportunities are discussed, and recommendations are made for the further integration of big data technology into the medical industry in the future. © 2024 Elsevier Ltd

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Real-Time Chaotic Video Encryption Based on Multi-Threaded Parallel Confusion and Diffusion

SSRN

引用

SSRN 2023年

作者： Jiang, Dong Yuan, Zhen Li, Wen-Xin Wang, Hai-Tao Lu, Liang-Liang School of Internet Anhui University Hefei230039 China National Engineering Research Center of Agro-Ecological Big Data Analysis and Application Anhui University Hefei230601 China Key Laboratory of Optoelectronic Technology of Jiangsu Province Nanjing Normal University Nanjing210023 China National Laboratory of Solid State Microstructures Nanjing University Nanjing210093 China Hefei National Laboratory Hefei230088 China

Due to the strong correlation among adjacent pixels, image encryption schemes typically perform multiple rounds of confusion and diffusion to protect images against various attacks, which is time-consuming and cannot meet the real-time requirements for video encryption. Existing works, therefore, realize video encryption by simplifying encryption process or selectively encrypting specific pixels, resulting in lower security compared to image encryption. This paper proposes a real-time chaotic video encryption strategy based on parallel computing. It splits video frame into sub-frames, creates a set of threads to concurrently perform confusion and diffusion operations on corresponding sub-frames, and efficiently outputs encrypted frames. To assess its performance, two cryptosystems are implemented using different chaotic systems. Encryption speed evaluation demonstrates a significant acceleration in byte generation, confusion, and diffusion phases, enabling real-time encryption on different X86 platforms. The average encryption time is less than 42ms, despite performing five rounds of confusion and diffusion operations on each frame. Statistical and security analysis prove that the deployed cryptosystems exhibit exceptional statistical properties and provide resistance to different attacks. Moreover, our method is adopted to implement a multi-user, real-time mobile video communication system using embedded systems, validating the feasibility of the proposed strategy for various application scenarios. © 2023, The Authors. All rights reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Taxi travel time based Geographically Weighted Regression Model (GWR) for modeling public housing prices in Singapore 29

Taxi travel time based Geographically Weighted Regression Mo...

引用

29th International Conference on Geoinformatics, Geoinformatics 2022

作者： Wang, Yi'an Cai, Fangyi Cheng, Shih-Fen Wu, Bo Cao, Kai School of Geographic Sciences East China Normal University Shanghai China East China Normal University Key Laboratory of Geographic Information Science Ministry of Education Shanghai China East China Normal University Key Lab. of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities Ministry of Natural Resources Shanghai China National University of Singapore Department of Geography Singapore School of Computing and Information Systems Singapore Management University Singapore School of Geography and Environment Jiangxi Normal University Jiangxi Nanchang China

ISBN: (数字)9798350309881

ISBN: (纸本)9798350309881

In this research, a taxi travel time based Geographically Weighted Regression model (GWR) is proposed and utilized to model the public housing price in the case study of Singapore. In addition, a comparison between the proposed taxi data driven GWR and other models, such as ordinary least squares model (OLS), GWR model based on Euclidean distance and GWR model based on public transport travel time, have also been carried out. Results indicates that taxi travel time based GWR model has better fitting performance than the OLS model, and slightly better than the Euclidean distance-based GWR model, however, it is not as good as the GWR model based on public transport travel time according to the metric of Adjusted R2. These experiments indicate that the public transport travel time may has a major part to play in modeling the public housing resale prices compared to taxi travel time or driving time, and both the taxi travel time and public transport travel time can better explain the public housing resale prices in Singapore compared to Euclidean distance in the GWR modeling. © 2022 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Pioneering case: Robot-assisted remote radical distal gastrectomy for gastric cancer based on 5G communication technology

引用

Intelligent Surgery 2024年第1期7卷 22-26页

作者： Honghai Guo Yuan Tian Jia Shi Peigang Yang Jiaxuan Yang Pingan Ding Xuefeng Zhao Zhidong Zhang Qun Zhao The Third Department of Surgery The Fourth Hospital of Hebei Medical University Shijiazhuang Hebei 050011 China Hebei Provincial Key Laboratory of Precision Diagnosis and Comprehensive Treatment of Gastric Cancer Shijiazhuang Hebei 050011 China Big Data Analysis and Mining Application for Accurate Diagnosis and Treatment of Gastric Cancer Hebei Provincial Engineering Research Center Shijiazhuang Hebei 050011 China Department of Academic Research The First Affiliated Hospital of Shandong First Medical University Jinan Shandong 250014 China

Background The aim of this study is to describe technical considerations and short-term outcomes of the first officially published robot-assisted remote radical distal gastrectomy for gastric cancer with 5G technology. Methods A 51-year-old gastric cancer patient with clinical stage T2N0M0 underwent 5G-enabled robot-assisted remote radical distal gastrectomy on September 11, 2023 at the Third Department of Surgery, the Fourth Hospital of Hebei Medical University. Results The surgery procedure was successfully performed with an average total intraoperative delay of 225 ms, average round-trip delay of 30 ms and no packet loss rate. The operative time was 140 min and intraoperative blood loss was 20 ml. The patient was discharged on postoperative day 6 without any postoperative complications. Conclusion This case has preliminarily verified the feasibility and safety of 5G-enabled robot-assisted remote radical distal gastrectomy for patients with gastric cancer. The initial study fills in the gaps in related fields and lays a solid foundation for subsequent research. To verify its superior operative outcomes, further clinical trials are needed.

关键词： 5G technology Robotic surgery Radical gastrectomy Remote surgery

来源：评论

学校读者我要写书评

暂无评论

Internal drivers of the global pandemic of the Omicron variants of SARS-CoV-2

Medicine Advances

引用

Medicine Advances 2024年第3期2卷 262-273页

作者： Yilin Niu Wuxiu Quan Yunyi Li Ziying Chen Yunfei Gao School of Public Health Southern Medical University Guangzhou Guangdong China Medical Big Data Center Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou Guangdong China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou Guangdong China School of Software Engineering South China University of Technology Guangzhou Guangdong China

Background The high transmissibility of the Omicron variants of severe acute respiratory syndrome coronavirus 2 continues to impose a significant burden on public health systems worldwide. Continuous mutations in the virus challenge the efficacy of vaccines and prior immunity from other variants, posing a severe threat to human health. Therefore, there is an urgent need to predict mutations of the Omicron variants and identify key factors influencing their spread. This study investigated critical amino acid mutations of the Omicron variants using epidemiological data and the mechanisms underlying their transmission. The aim was to understand the key factors driving the spread of the Omicron variants and provide insights for effective control and prevention strategies. Methods A total of 488,646 Omicron cases recorded between December 2021 and February 2023 were analyzed using a sliding time window and the Epi Score model, which has high accuracy for the identification of mutation sites. MutPred2, PolyPhen2 and VarSite tools were used to predict future mutations and identify factors driving the prevalence of the Omicron variants. Results Epi Scores showed fluctuating patterns at mutation sites, highlighting N969K, Y505H, N764K, T478K, and S371F mutations on the spike protein as significant for future prevention efforts. The spread of the Omicron variants was linked to changes in the viral entry pathway and improved angiotensin-converting enzyme 2 (ACE2) binding and immune evasion tactics. Conclusions The findings of this study reveal trends in the evolution of the Omicron variants, including altered cell entry, increased affinity for ACE2, and evasion of the immune system. These factors are critical for understanding the global spread of the Omicron variants and developing effective control strategies.

关键词： amino acids coronavirus immune evasion mutation public health SARS-CoV-2 spike glycoprotein

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Graph Transformer with Adaptive Node Sampling

arXiv

引用

arXiv 2022年

作者： Zhang, Zaixi Liu, Qi Hu, Qingyong Lee, Chee-Kong Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong Tencent America United States

The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision. However, when it comes to graph-structured data, transformers have not achieved competitive performance, especially on large graphs. In this paper, we identify the main deficiencies of current graph transformers: (1) Existing node sampling strategies in Graph Transformers are agnostic to the graph characteristics and the training process. (2) Most sampling strategies only focus on local neighbors and neglect the long-range dependencies in the graph. We conduct experimental investigations on synthetic datasets to show that existing sampling strategies are sub-optimal. To tackle the aforementioned problems, we formulate the optimization strategies of node sampling in Graph Transformer as an adversary bandit problem, where the rewards are related to the attention weights and can vary in the training procedure. Meanwhile, we propose a hierarchical attention scheme with graph coarsening to capture the long-range interactions while reducing computational complexity. Finally, we conduct extensive experiments on real-world datasets to demonstrate the superiority of our method over existing graph transformers and popular GNNs. Our code is open-sourced at https://***/zaixizhang/ANS-GT. © 2022, CC BY-SA.

关键词： Graph theory

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：