检索结果-内蒙古大学图书馆

Companion Proceedings of the ACM on Web Conference 2025

作者： Jun Li Xiangmeng Wang Yifei Yan Haoyang Li Hong Va Leong Nancy Xiaonan Yu Qing Li The Hong Kong Polytechnic University Hong Kong Hong Kong City University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798400713316

Despite significant advances in approaches to suicide detection on social media, predicting users' suicide risk in a subsequent state remains challenging. Even though existing works have identified various risk factors to improve detection performance, they often overlook the critical role of protective factors in suicide prevention. To address this limitation, we propose an approach that jointly learns both risk and protective factors to predict users' subsequent suicide risk. Recognizing that the effectiveness of these factors varies across different user patterns, we introduce a dynamic factor influence learning mechanism that captures user-dependent interactions with risk and protective factors. Our experiments demonstrate that the integrated approach significantly enhances suicide risk prediction performance compared to existing methods.

关键词： big data processing

来源：评论

学校读者我要写书评

暂无评论

Assessment and Prediction of Ecological Environment Vulnerability in China Under Rainstorm 24

Assessment and Prediction of Ecological Environment Vulnerab...

引用

Proceedings of the 2024 4th International Conference on Computational Modeling, Simulation and data Analysis

作者： Shiqi Shen Ruiqi Liu Shouhuai Yang Zijie Zhao National Key Laboratory of Transient Physics Nanjing University of Science and Technology Nanjing Jiangsu China

ISBN: (纸本)9798400711831

This paper deals with the prediction and assessment methods of flood disasters due to heavy rainfall, especially focusing on analyzing the extreme weather performance of ecologically fragile zones in China. Initial discussions are devoted to the discussion of the development of flood disaster prediction methods in and outside of the country, traditional methods taking support from depth loss curves together with modern applications in the realm of machine learning, remote sensing and GIS technologies. Based on that a vulnerability assessment system focusing on natural and anthropogenic factors was developed and subject to the analysis using data normalization and a random forest model. The analysis indicates that the rainfall is the most important factor affecting flooding into the disaster area, while natural factors such as forests reduce the risk of the disaster. In forecasting, the author applied a basic linear regression model along with an LSTM neural network for predicting the type of land use change and trends in rainfall in China for the next decade. Combining these predictions and a random forest model will allow for the establishment of the potential disaster-prone areas from 2025 to 2035. The predictions reveal that the southern and south-eastern coastal China are to be concerned as high-risk areas. With the integration of heat maps and model results, a multi-faceted analysis gives out the important insights into the spatial distribution characteristics of disaster-prone areas in China and its implications with respect to disaster risk assessment, management, and responsive strategies.

关键词： big data processing

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Oriented Privacy Protection of Sensitive data in the Internet of Vehicles

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第2期8卷 1057-1067页

作者： Xu, Cheng Wu, Hongjun Liu, Hongzhe Gu, Weihao Li, Ying Cao, Dongpu Beijing Union Univ Beijing Key Lab Informat Serv Engn Beijing 100101 Peoples R China Haomo AI Aobei Sci Pk Beijing 100089 Peoples R China Beijing Inst Technol Sch Mech Engn Beijing 100081 Peoples R China Tsinghua Univ Sch Vehicle & Mobil Beijing 100084 Peoples R China

The Internet of Vehicles is the specific instantiation of the Internet of Things in the field of transportation. Vehicle and driving data are often used to mine information about people's lifestyles and preferences. Without advanced data encryption and strict authorization measures, personal privacy and security are at great risk. To solve the problem that the relatively low security of vehicles connected to the Internet may threaten the privacy of users, a blockchain-based sensitive data privacy-protection scheme for vehicles connected to the Internet is proposed. First, association rules are used to mine big data in the Internet of Vehicles. Then, a data security aggregation protocol is established. Finally, an end-to-end encryption mechanism is created. The privacy protection of big data in the Internet of Vehicles is achieved through static and dynamic strategies. The experimental results show that the scheme can improve the hiding rate of sensitive data, the key generation time and encryption time are shorter than those of typical technologies, and the encryption ability is better. Therefore, in protecting the privacy of big data in the Internet of Vehicles, the blockchain proposed in this paper has better privacy protection and encryption abilities and is applicable to the protection of sensitive data in the Internet of Vehicles.

关键词： Intelligent vehicles Production facilities Physical layer Blockchains Automobiles Internet of Vehicles blockchain big data processing privacy protection sensitive data

来源：评论

学校读者我要写书评

暂无评论

Improved PSO Algorithm Integrated With Opposition-Based Learning and Tentative Perception in Networked data Centres

引用

IEEE ACCESS 2020年 8卷 55872-55880页

作者： Zhou, Zhou Li, Fangmin Abawajy, Jemal H. Gao, Chaochao Changsha Univ Dept Math & Comp Sci Changsha 410083 Peoples R China Deakin Univ Sch Informat Technol Geelong Vic 3217 Australia Hunan Normal Univ Sch Informat Sci & Engn Changsha 410006 Peoples R China

Particle swarm optimization (PSO) algorithms have low-quality initial particle swarm, which is generated by a random method when handling the problem of task scheduling in networked data centres. Such algorithms also fall easily into local optimum when searching for the optimal solution. To address these problems, this study proposes combining opposition-based learning (OBL) and tentative perception (TP) with PSO;the proposed method is called OBL & x2013;TP & x2013;PSO. This algorithm uses reverse learning to generate the initial population, such that the quality of the initial particle swarm can be improved. Before the particle speed and location are updated, the TP method is used to search for the individual optimum around each particle, thereby reducing the possibility of missing the potential optimal solution during the process of searching. In this manner, the problem in which the PSO algorithm easily falls into the local optimal is effectively solved. To evaluate the performance of the proposed algorithm, simulation experiments are performed on CloudSim toolkit. Experimental results show that in comparison with other algorithms (namely, Min-Min, Max-Min and PSO algorithm), the proposed OBL & x2013;TP & x2013;PSO algorithm has better performance in terms of the total execution time, load balancing and quality of service.

关键词： big data processing high-performance data processing networked data centre opposition-based learning tentative perception

来源：评论

学校读者我要写书评

暂无评论

Enhancing random forest classification with NLP in DAMEH: A system for data Management in eHealth Domain

引用

NEUROCOMPUTING 2020年 444卷 79-91页

作者： Amato, Flora Coppolino, Luigi Cozzolino, Giovanni Mazzeo, Giovanni Moscato, Francesco Nardone, Roberto Univ Naples Federico II DIETI Naples Italy Univ Naples Parthenope DI Naples Italy Univ Salerno DIEM Fisciano Italy Univ Mediterranea Reggio Calabria DIIES Reggio Di Calabria Italy

The use of pervasive IoT devices in Smart Cities, have increased the Volume of data produced in many and many field. Interesting and very useful applications grow up in number in E-health domain, where smart devices are used in order to manage huge amount of data, in highly distributed environments, in order to provide smart services able to collect data to fill medical records of patients. The problem here is to gather data, to produce records and to analyze medical records depending on their contents. Since data gathering involve very different devices (not only wearable medical sensors, but also environmental smart devices, like weather, pollution and other sensors) it is very difficult to classify data depending their contents, in order to enable better management of patients. data from smart devices couple with medical records written in natural language: we describe here an architecture that is able to determine best features for classification, depending on existent medical records. The architecture is based on pre filtering phase based on Natural Language processing, that is able to enhance Machine learning classification based on Random Forests. We carried on experiments on about 5000 medical records from real (anonymized) case studies from various health-care organizations in Italy. We show accuracy of the presented approach in terms of Accuracy-Rejection curves. (c) 2021 Elsevier B.V. All rights reserved.

关键词： big data processing E-health Machine learning Random forests Multi-classification schema

来源：评论

学校读者我要写书评

暂无评论

Action recognition using optimized deep autoencoder and CNN for surveillance data streams of non-stationary environments

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2019年 96卷 386-397页

作者： Ullah, Amin Muhammad, Khan Ul Haq, Ijaz Baik, Sung Wook Sejong Univ Digital Contents Res Inst Intelligent Media Lab Seoul South Korea Sejong Univ Dept Software Seoul South Korea

Action recognition is a challenging research area in which several convolutional neural networks (CNN) based action recognition methods are recently presented. However, such methods are inefficient for real-time online data stream processing with satisfied accuracy. Therefore, in this paper we propose an efficient and optimized CNN based system to process data streams in real-time, acquired from visual sensor of non-stationary surveillance environment. Firstly, frame level deep features are extracted using a pre-trained CNN model. Next, an optimized deep autoencoder (DAE) is introduced to learn temporal changes of the actions in the surveillance stream. Furthermore, a non-linear learning approach, quadratic SVM is trained for the classification of human actions. Finally, an iterative fine-tuning process is added in the testing phase that can update the parameters of trained model using the newly accumulated data of non-stationary environment. Experiments are conducted on benchmark datasets and results reveal the better performance of our system in terms of accuracy and running time compared to state-of-the-art methods. We believe that our proposed system is a suitable candidate for action recognition in surveillance data stream of non-stationary environments. (C) 2019 Elsevier B.V. All rights reserved.

关键词： big data processing Action recognition Online data stream analysis Optimized deep autoencoder Convolutional neural network Machine learning Non-stationary environment

来源：评论

学校读者我要写书评

暂无评论

big data Driven Map Reduce Framework for Automated Flood Disaster Detection Based on Heuristic-Based Ensemble Learning

引用

CYBERNETICS AND SYSTEMS 2024年第7期55卷 1757-1791页

作者： Shatat, Abdallah Saleh Ali Akhtar, Md. Mobin Zamani, Abu Sarwar Dilshad, Sara Samdani, Faizan Appl Sci Univ Coll Adm Sci Dept Management Informat Syst East Al Ekir Bahrain Riyadh Elm Univ REU Coll Appl Med Sci Dept Basic Sci Riyadh Saudi Arabia Prince Sattam bin Abdulaziz Univ Dept Comp & Self Dev Preparatory Year Deanship Al Kharj Saudi Arabia Aligarh Muslim Univ Dept Stat & Operat Res Aligarh India Asia Pacific Univ Dept Comp Engn Kuala Lumpur Malaysia

Flooding disaster causes huge impacts on the socio-economic world. In the inundated area, some geo-referenced images are shared through some media posts, which assist in providing alertness to the critical volunteers and managing the financial loss crisis. In this work, the Adaptive Billiards-Inspired Optimization (A-BIO) and Optimized Ensemble-learning-based detection (OED) with map reduce framework is proposed for flood disaster detection. Initially, the big data is gathered and processed for detection. During the map phase, data preprocessing is performed to enhance the performance of the data, which helps in removing the noise or unwanted attributes. Furthermore, the reduction phase can be done through weighted feature selection, where the features to be selected and the weight is optimized through A-BIO, which assists in getting the most significant features for improving the performance and reducing the complexity of the designed model. Finally, OED is performed by a set of classifiers like Convolutional Neural Networks, Adaboost, XGBoost, Long Short-Term Memory, and Deep Neural Networks, where the parameters of ensemble learning classifiers are optimized by A-BIO algorithm. Finally, through the performance analysis, this detection model can provide high accuracy and better detection performance to avoid the huge impacts of flood disasters.

关键词： Adaboost adaptive billiards-inspired optimization algorithm automated flood detection big data processing convolutional neural network deep neural network long short-term memory map reduce framework optimized ensemble-learning-based detection XGBoost

来源：评论

学校读者我要写书评

暂无评论

big data analytics - enabled cyber-physical system: model and applications

引用

INDUSTRIAL MANAGEMENT & data SYSTEMS 2019年第5期119卷 1072-1088页

作者： Luo, Shuai Liu, Hongwei Qi, Ershi Tianjin Univ Coll Management & Econ Tianjin Peoples R China

Purpose - The purpose of this paper is to propose a comprehensive framework for integrating big data analytics (BDA) into cyber- physical system (CPS) solutions. This framework provides a wide range of functions, including data collection, smart data preprocessing, smart data mining and smart data visualization. Design/methodology/approach - The architecture of CPS was designed with cyber layer, physical layer and communication layer from the perspective of big data processing. The BDA model was integrated into a CPS that enables managers to make sound decisions. Findings - The effectiveness of the proposed BDA model has been demonstrated by two practical cases the prediction of energy output of the power grid and the estimate of the remaining useful life of the aeroengine. The method can be used to control the power supply system and help engineers to maintain or replace the aero- engine to maintain the safety of the aircraft. Originality/value - The communication layer, which connects the cyber layer and physical layer, was designed in CPS. From the communication layer, the redundant raw data can be converted into smart data. All the necessary functions of data collection, data preprocessing, data storage, data mining and data visualization can be effectively integrated into the BDA model for CPS applications. These findings show that the proposed BDA model in CPS can be used in different environments and applications.

关键词： big data analytics big data processing Communication layer Cyber-physical system Smart data

来源：评论

学校读者我要写书评

暂无评论

MapReduce-Based Improved Random Forest Model for Massive Educational data processing and Classification

引用

MOBILE NETWORKS & APPLICATIONS 2021年第1期26卷 191-199页

作者： Xu, Wei Hoang, Vinh Truong Xian Univ Finance & Econ Business Sch Xian 710100 Shaanxi Peoples R China Ho Chi Minh City Open Univ Fac Comp Sci Ho Chi Minh City 70000 Vietnam

This paper takes education data mining as the research theme, mine the existing massive education big data, compares the analysis methods of existing data models, and proposes an improved random forest reference model. The information gain of various features is calculated by introducing the feature weighting system, and the evaluation index is used to improve the existing data analysis. The simulation results show that the improved model is highly efficient as compared to the existing models for classification. In order to resolve the performance bottleneck of a single node in multiple data classification tasks in the era of big data, a classification and prediction model of graduates' large-scale employment data, based on distributed improved RF algorithm, is proposed. The MapReduce distributed computing framework is used to complete the serial writing and deserialization loading of the training model between the local disk and the distributed file system, and realizing the distributed expansion of the large-scale data classification model based on the improved RF model.

关键词： Machine learning data classification model big data processing MapReduce

来源：评论

学校读者我要写书评

暂无评论

An efficient architecture for processing real-time traffic data streams using apache flink

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第13期83卷 37369-37385页

作者： Deepthi, B. Gnana Rani, K. Sandhya Krishna, P. Venkata Saritha, V. Sri Padmavati Mahila Visvavidyalayam Dept Comp Sci & Engn Tirupati India

big data technologies emerging day by day and are making drastic changes in various real-world applications. Traditional data mining tools adequate to process volumes of data but from past decades the rapid growth in data becomes difficult for processing. Due to continuous flow of data, data streams require additional computational processing than the traditional one. big data stream processing considers different features of the data streams heterogeneity, scalability, fault tolerance and query optimization. Efficient implementation of these features in real-world applications using big data analytics is a challenging job during data storage, processing, and analysis phases. Therefore, the proposed model FRTSPS is a generic architecture which is influenced by popular big data processing Lambda architecture, based on distributed computing platform. The architecture using open-source platform Apache Flink for doing data processing. Flink is a popular platform for processing historical and stream data flows at once parallelly. Its stateful streaming can obtain more scalability and flexibility along with high throughput and low latency than the remaining stream processing programming models.

关键词： big data big data processing Stream Computing Apache Flink

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：