检索结果-内蒙古大学图书馆

distributed data collection and web-based integration for more efficient and informative groundwater pollution risk assessment

引用

ENVIRONMENTAL MODELLING & SOFTWARE 2018年 100卷 278-290页

作者： Sege, Jon Ghanem, Marwan Ahmad, Waseem Bader, Hanadi Rubin, Yoram Univ Calif Berkeley Dept Civil & Environm Engn Berkeley CA 94720 USA Birzeit Univ Geog Dept POB 14 Birzeit Palestine

We present a web-based software platform for assimilation of field data on groundwater vulnerability and assessment of groundwater pollution risk. Groundwater vulnerability and risk assessments couple hydrogeologic characterization and pollution source information to provide a relative measure of risk to a groundwater supply. Vulnerability is based solely on hydrogeologic factors, while risk also considers pollution hazards. Previous studies have identified two key limitations in the collection of pollution hazards information: detailed investigations throughout a study area are extremely time-consuming, and pollution inventories are not regularly updated to reflect changes in land use. This paper presents a methodology to address these two limitations by allowing broad-based effort to collect pollution hazard parameters in the field using GPS-tagged smartphone forms and incorporating the new information rapidly into a web-based risk modelling framework. To demonstrate this approach, a case-study is presented from the Natuf Basin in the Ramallah-Al Bireh Governorate of Palestine. (c) 2017 Elsevier Ltd. All rights reserved.

关键词： distributed data collection Web-based GIS Risk assessment Groundwater Pollution

来源：评论

学校读者我要写书评

暂无评论

distributed data collection in Large-Scale Asynchronous Wireless Sensor Networks Under the Generalized Physical Interference Model

引用

IEEE-ACM TRANSACTIONS ON NETWORKING 2013年第4期21卷 1270-1283页

作者： Ji, Shouling Cai, Zhipeng Georgia State Univ Dept Comp Sci Atlanta GA 30303 USA

Wireless sensor networks (WSNs) are more likely to be distributed asynchronous systems. In this paper, we investigate the achievable data collection capacity of realistic distributed asynchronous WSNs. Our main contributions include five aspects. First, to avoid data transmission interference, we derive an R-0-proper carrier-sensing range (R-0 - PCR) under the generalized physical interference model, where R-0 is the satisfied threshold of data receiving rate. Taking R-0 - PCR as its carrier-sensing range, any sensor node can initiate a data transmission with a guaranteed data receiving rate. Second, based on R-0 - PCR, we propose a distributed data collection (DDC) algorithm with fairness consideration. Theoretical analysis of DDC surprisingly shows that its achievable network capacity is order-optimal and independent of network size. Thus, DDC is scalable. Third, we discuss how to apply R-0 - PCR to the distributed data aggregation problem and propose a distributed data Aggregation (DDA) algorithm. The delay performance of DDA is also analyzed. Fourth, to be more general, we study the delay and capacity of DDC and DDA under the Poisson node distribution model. The analysis demonstrates that DDC is also scalable and order-optimal under the Poisson distribution model. Finally, we conduct extensive simulations to validate the performance of DDC and DDA.

关键词： Capacity analysis delay analysis distributed data aggregation distributed data collection wireless sensor networks (WSNs)

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserved distinct content collection in human-assisted ubiquitous computing systems

引用

INFORMATION SCIENCES 2019年 493卷 91-104页

作者： Zheng, Xu Chen, Aiguo Luo, Guangchun Tian, Ling Cai, Zhipeng Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Sichuan Peoples R China Georgia State Univ Dept Comp Sci Atlanta GA 30303 USA

Human beings with smart devices have dramatically facilitated the knowledge acquisition in ubiquitous computing systems. However, the collected contents also severely threat the security and privacy for individuals, as these contents achieve a fine-grained coverage of one's behaviors and movements. Local differential privacy, as one of the widely accepted properties, enables individuals to contribute to data collection while remaining indistinguishable against adversaries. However, existing solutions and mechanisms fail to capture the contents with relatively low frequency, e.g., the temperature in local regions visited by very few people. Therefore, this work proposes a novel framework for distinct content estimation under local differential privacy. We propose a hash function and random response based framework for the estimation. The framework allows individuals in the ubiquitous computing system to participate with flexible bandwidth, and properly assigns the given bandwidth to improve estimated results. We prove the optimization problem of assignment in our framework to be NP-complete, and provides an effective heuristic algorithm. Our framework is also proved to guarantee an unbiased estimation for distinct contents, and achieves local differential privacy for users. Meanwhile, we also propose a randomized algorithm designed for more general cases, where the preposed knowledge for the first algorithm is unavailable. Finally, we evaluate both algorithms on real world datasets, and the results reveal that our algorithms outperform existing methods. (C) 2019 Elsevier Inc. All rights reserved.

关键词： Local differential privacy Distinct value estimation distributed data collection Security

来源：评论

学校读者我要写书评

暂无评论

A Robust Framework for Multimodal Sentiment Analysis with Noisy Labels Generated from distributed data Annotation

引用

Computer Modeling in Engineering & Sciences 2024年第6期139卷 2965-2984页

作者： Kai Jiang Bin Cao Jing Fan School of Computer Science and Technology Zhejiang University of TechnologyHangzhou310023China

Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s *** the advent of distributed data collection and annotation,we can easily obtain and share such multimodal ***,due to professional discrepancies among annotators and lax quality control,noisy labels might be *** research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the *** address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities ***,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network ***,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy *** conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.

关键词： distributed data collection multimodal sentiment analysis meta learning learn with noisy labels

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient distributed Mobile Crowd Sensing: A Deep Learning Approach

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2019年第6期37卷 1262-1276页

作者： Liu, Chi Harold Chen, Zheyu Zhan, Yufeng Beijing Inst Technol Sch Comp Sci & Technol Beijing 100081 Peoples R China

High-quality data collection is crucial for mobile crowd sensing (MCS) with various applications like smart cities and emergency rescues, where various unmanned mobile terminals (MTs), e.g., driverless cars and unmanned aerial vehicles (UAVs), are equipped with different sensors that aid to collect data. However, they are limited with fixed carrying capacity, and thus, MT's energy resource and sensing range are constrained. It is quite challenging to navigate a group of MTs to move around a target area to maximize their total amount of collected data with the limited energy reserve, while geographical fairness among those point-of-interests (PoIs) should also be maximized. It is even more challenging if fully distributed execution is enforced, where no central control is allowed at the backend. To this end, we propose to leverage emerging deep reinforcement learning (DRL) techniques for directing MT's sensing and movement and to present a novel and highly efficient control algorithm, called energy-efficient distributed MCS (Edics). The proposed neural network integrates convolutional neural network (CNN) for feature extraction and then makes decision under the guidance of multi-agent deep deterministic policy gradient (DDPG) method in a fully distributed manner. We also propose two enhancements into Edics with N-step return and prioritized experienced replay buffer. Finally, we evaluate Edics through extensive simulations and found the appropriate set of hyperparameters in terms of number of CNN hidden layers and neural units for all the fully connected layers. Compared with three commonly used baselines, results have shown its benefits.

关键词： Mobile crowd sensing deep reinforcement learning energy-efficiency distributed data collection

来源：评论

学校读者我要写书评

暂无评论

Cross-Media Big data Tourism Perception Research Based on Multi-Agent

Cross-Media Big Data Tourism Perception Research Based on Mu...

引用

Chinese Intelligent Systems Conference (CISC)

作者： Guan, Dong Du, Junping Beijing Univ Posts & Telecommun Beijing Key Lab Intelligent Telecommun Software & Sch Comp Sci Beijing 100876 Peoples R China

ISBN: (纸本)9783662483862;9783662483848

In this paper, we introduced the design and implementation in detail the cross-media big tourist perception system based on agent. We used the technology based on agent to implement the parallel in the process of data collection. This system mainly consists of a set of cooperation agent, including the data collection agent;the URL Agent;the data update agent and the management agent. Compared with the ordinary distributed information collection system, we designed and implemented the URL agent and data update agent, we used the algorithm to analyze the page based on agent, and then improves the efficiency of the cross-media big tourist perception.

关键词： Cross-media Big data sensing Multi-agent distributed data collection

来源：评论

学校读者我要写书评

暂无评论

A data collection Technology of Virtual Reality Simulation System Based on Load Balancing 11

A Data Collection Technology of Virtual Reality Simulation S...

引用

11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)

作者： Ma, Denghui Zuo, Xin Yue, Yuanlong Qian, Kewei China Univ Petr Coll Informat Sci & Engn Beijing Peoples R China

ISBN: (纸本)9781728118598

Aiming at the problem of high load on data collection site caused by a large amount of real-time data are stored in the database in a large-scale virtual reality simulation system. A distributed data collection scheme was proposed. Firstly, this paper introduced the overall architecture of the virtual reality simulation system for subsea production process of oil and gas and analyzed the data flow of the system. Secondly, based on this virtual reality simulation system, a distributed data collection module was designed. The whole data collection module took the distributed database as the core, and adopted an algorithm combining static load distribution and dynamic collection task scheduling to distribute data collection tasks to each site according to the performance of each index of its server. Then, in the process of data collection, the collection task part of the site with larger load was automatically distributed to the site with smaller load in real time, so that the load of each site was balanced.

关键词： component virtual reality simulation system distributed data collection load balancing algorithm

来源：评论

学校读者我要写书评

暂无评论

Exploring data collection on Bluetooth Mesh networks

引用

AD HOC NETWORKS 2022年 130卷 102809-102809页

作者： Paulon, J. V. Marcelo de Souza, Bruno Jose Olivieri Endler, Markus Pontificia Univ Catolica Rio de Janeiro Rua Marques Sao Vicente Rio De Janeiro RJ Brazil

This work evaluates sporadic data collection on a Bluetooth Mesh network, using the OMNET++ INET simulator. The data collector is a roaming sink node, which could be a smartphone or other portable device, carried by a pedestrian, a biker, an animal, or a drone. The sink node could connect to a mesh network in hard-to-reach areas that do not have internet access and collect sensor data. After implementing Bluetooth Mesh relay extensions, Low Power, and Friend features in OMNET++, we were able to propose and evaluate algorithms for mobility-aware, adaptive, routing of sensor data towards the sink node. One variation of a proposed routing algorithm achieved a 173.54% increase in unique data delivered to the sink node compared to Bluetooth Mesh's default routing algorithm. In that case, there was only a 4.63% increase in energy consumption for the same scenario. Also, the delivery rate increased by 111.82%.

关键词： Wireless sensor networks distributed data collection Mesh networks Bluetooth mesh

来源：评论

学校读者我要写书评

暂无评论

Livestock and poultry posture monitoring based on cloud platform and distributed collection system

引用

INTERNET OF THINGS 2024年 25卷

作者： Shang, Zhendong Li, Zhaoying Wei, Qinzhang Hao, Shuaibo Henan Univ Sci & Technol Sch Mech & Elect Engn Luoyang 471003 Peoples R China Henan Prov Key Lab Mech Design & Transmiss Syst Luoyang 471003 Peoples R China

In order to realize automatic inspection of livestock health and welfare in large-scale intensive farming, a biological state monitoring system based on the IoT cloud platform and distributed data collection technology was designed. Through analysis, a one-dimensional description method of livestock spatial posture is established to determine the spatial posture of livestock by scanning the distance information in a typical cross-section of livestock by a single sensor. Through the distributed configuration of one master and multiple slave detection units, the master-slave hardware circuit was designed based on microprocessors, laser distance sensors, proximity switches, wireless transmission modules, etc. The master, slave and user-side cell phone programs were developed to realize the centralized monitoring of multiple breeding sites. Each slave uses an STC12C5A60S2 microprocessor and multiple sensors for real-time acquisition of status parameters of the organisms. These slave status parameters are packaged and sent to the host control unit via RS485 bus. The host packages the received status data into JSON format packets and sends them to Alibaba Cloud server through the serial port side of the IoT gateway. The IoT gateway follows the MQTT communication protocol to ensure the reliability of the connection and forwards the status monitoring results to the cloud server. The end-user can monitor the status of the organisms anytime and anywhere through the APP of the monitoring management platform and deal with abnormalities in time. After experimental verification, the system achieves remote acquisition, real-time reporting, data storage, polling monitoring and status alarm functions, and the monitoring accuracy reaches to meet the demand for biological status monitoring in intensive farming.

关键词： Spatial posture Automatic inspection Livestock health distributed data collection Microprocessors IoT cloud platform

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：