检索结果-内蒙古大学图书馆

Landsat TM/ETM⁺ and machine-learning algorithms for limnological studies and algal bloom management of inland lakes

JOURNAL OF APPLIED REMOTE SENSING 2018年第2期12卷

作者： Lin, Shengpan Novitski, Linda N. Qi, Jiaguo Stevenson, Robert Jan Michigan State Univ Dept Geog Environm & Spatial Sci E Lansing MI 48824 USA Michigan State Univ Dept Integrat Biol E Lansing MI 48824 USA Nanjing Agr Univ Coll Agr Nanjing Jiangsu Peoples R China

Accumulating remotely sensed and ground-measured data and improvements in data mining such as machine-learning techniques open new opportunities for monitoring and managing algal blooms over large spatial scales. The goal of this study was to test the accuracy of remotely sensed algal biomass determined with machine-learning algorithms and Landsat TM/ETM+ imagery. We used chlorophyll-a concentration data from the 2007 National Lake Assessment (NLA) (lake N = 1157) by the US Environmental Protection Agency to train and test Landsat TM/ETM+ algorithms. Results showed significant improvements in chlorophyll-a retrieval accuracy using machine-learning algorithms compared with traditional empirical models using linear regression. Specifically, the results from boosted regression trees and random forest explained, respectively, 45.8% and 44.5% of chlorophyll-a variation. Multiple linear regression could only explain 39.8% of chlorophyll-a variation. The chlorophyll-a concentration derived from Landsat TM/ETM+ and a simple to use Google Earth Engine application, accurately characterized a 2009 algal bloom in western Lake Erie to show the model worked well for the analysis of temporal changes in algal conditions. Compared with chlorophyll-a data from the NLA, chlorophyll-a measurements with our Landsat TM/ETM+ model had almost the same correlation with lake's total phosphorus concentrations, especially when using multiple Landsat images. Therefore, Landsat measurements of chlorophyll-a have value for ecological assessments and managing algal problems in lakes. (C) 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： remote sensing Landsat water quality chlorophyll-a machine-learning algorithm Google Earth Engine

来源：评论

学校读者我要写书评

暂无评论

Measuring Successful Digital Services by Identifying Active Users 1

引用

6th IFIP WG 12.6 International Workshop on Artificial Intelligence for Knowledge Management held at 27th International Joint Conference on Artificial Intelligence (IJCAI)

作者： Morshed, Sarwar Jahan Rana, Juwel Milrad, Marcelo Linnaeus Univ Dept Comp Sci & Media Technol Vaxjo Sweden Telenor Grp Oslo Norway

ISBN: (数字)9783030529031

ISBN: (纸本)9783030529031;9783030529024

This paper is an extended version of the work published in [1]. We extended our previous work by the proposed model representation and more experimental result. Almost every service in the current era are either managed or operated with the help of digital services to manage their customer's activities. So digital service providers are engaging in different ways with the users to know their feedback about the service. Traditional methods for understanding user satisfaction from their direct feedback or survey. Both of these methods might produce biased result due the limited user participations. Therefore, knowledge management of user activities with the digital service could be an alternative approach for identifying satisfied users. In the previous work [1], we have presented a data science model. In this paper, more result using the proposed data science model have been presented to prove that the proposed model is workable to measure successful digital services.

关键词： User feedback Digital service User satisfaction Data science Prediction model Knowledge management Service evaluation machine-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

machine learning Approach-Based Gamma Distribution In for Brain Tumor Detection and Data Sample imbalance Analysis

引用

IEEE ACCESS 2019年 7卷 12-19页

作者： Manogaran, Gunasekaran Shakeel, P. Mohamed Hassanein, Azza S. Kumar, Priyan Malarvizhi Babu, Gokulnath Chandra Univ Calif Davis John Muir Inst Environm Davis CA 95616 USA Univ Teknikal Malaysia Fac Informat & Commun Technol Durian Tunggal 76100 Malaysia Helwan Univ Fac Engn Biomed Engn Dept Helwan 11795 Egypt VIT Univ Sch Informat Technol & Engn Vellore 632014 Tamil Nadu India

Recently, artificial intelligence applications in magnetic resonance imaging have been applied in several clinical studies. The analysis of brain tumors without human intervention is considered a significant area of research because the extracted brain images need to be optimized using a segmentation algorithm that is highly resilient to noise and cluster size sensitivity problems and automatically detects the region of interest (ROI). In this paper, an improved orthogonal gamma distribution-based machine-learning approach is used to analyze the under- segments and over-segments of brain tumor regions to automatically detect abnormalities in the ROI. Further data imbalances due to improper edge matching in the abnormal region is sampled by matching the edge coordinates and sensitivity, and the selectivity parameters are measured using the machine learning algorithm. The benchmark medical image database was collected and analyzed to validate the efficiency and accuracy of the optimal automatic detection in tumor and non-tumor regions. The mean error rate of the algorithm was determined using a mathematical formulation. The system is evaluated based on experimental results that showed the method of orthogonal gamma distribution with the machine learning approach attained an accuracy of 99.55% in detecting brain tumors. This research contributes to the field of brain abnormality detection and analysis without human intervention in the health care sector.

关键词： Magnetic resonance imaging gamma distribution machine-learning algorithm brain abnormality

来源：评论

学校读者我要写书评

暂无评论

Citizen Scientists Help Detect and Classify Dynamically Triggered Seismic Activity in Alaska

引用

FRONTIERS IN EARTH SCIENCE 2020年 8卷

作者： Tang, Vivian Roesler, Boris Nelson, Jordan Thompson, JaCoya van der Lee, Suzan Chao, Kevin Paulsen, Michelle Northwestern Univ Dept Earth & Planetary Sci Evanston IL 60208 USA Northwestern Univ Dept Chem Evanston IL USA Northwestern Univ Dept Comp Sci Evanston IL USA Northwestern Univ Northwestern Inst Complex Syst Evanston IL USA Northwestern Univ Ctr Interdisciplinary Explorat & Res Astrophys Evanston IL USA

In this citizen science project, we ask citizens to listen to relevant sections of seismograms that are converted to audible frequencies. Citizen scientists helped identify local seismic events whose recorded signals are much smaller than those associated with the surface waves that have triggered these local events. The local events include small earthquakes as well as tectonic tremor. While progress has been made in understanding how these events might be triggered by surface waves from large teleseismic earthquakes around the world, there is no consensus on its physical mechanism. The aim of our project is to engage the help of citizen scientists to increase general knowledge of triggered seismic events that may or may not occur during transient strain changes, such as from propagating surface waves. A better understanding of triggered seismic events is expected to provide important clues toward a fundamental understanding of how earthquakes nucleate and the physical mechanisms that connect different earthquakes and other slip events. From the volunteers' classifications we determined that citizen scientists achieve a higher reliability in detecting earthquakes and noise than in detecting tremor or other signals and that citizen scientists more accurately identify earthquake signals than a trained machine-learning algorithm. For tremor classifications we currently depend entirely on humans as no machine has yet learned to detect triggered tremor.

关键词： earthquake detective citizen sciences triggered seismic events machine-learning algorithm audible pitches Alaska

来源：评论

学校读者我要写书评

暂无评论

Automatic identification and counting of repetitive actions related to an industrial worker 2

Automatic identification and counting of repetitive actions ...

引用

2nd IEEE International Workshop on Metrology for Industry 4.0 and Internet of Things (IoT) (MetroInd4.0 and IoT)

作者： Taborri, Juri Bordignon, Marco Marcolin, Francesco Donati, Marco Rossi, Stefano Univ Tuscia Dept Econ Engn Soc & Business Org DEIM Viterbo VT Italy ErgoCert Ente Certificaz Ergon Srl Udine UD Italy Motustech Sport & Hlth Technol Marilab Ostia RM Italy

ISBN: (纸本)9781728104294

This study aims at proposing an innovative experimental methodology for the automatic recognition and counting of occupational repetitive action during a work cycle of an industrial worker. Through this aim, we want to evaluate the possibility to objectivize the computation of the OCcupational Repetitive Action (OCRA) index. Two healthy subjects were enrolled in the study and they were asked to perform 11 technical actions in two different repetitions. Participants were equipped with 23 inertial sensors place on different body segments in order to evaluate angles related to trunk, shoulder, elbow and wrist in the three anatomical planes. An algorithm based on Support Vector machines was used for the automatic recognition of the technical actions;a further algorithm was implemented for the counting of the actions after their recognition. The recognition algorithm was tested with both a subject-specific training and a standard training. Results showed an accuracy in the recognition greater than 89.5% and 86.5% for the subject-specific and standard training, respectively. As regards the action counting, algorithm showed an accuracy from 72.2% to 100% based on different actions. This preliminary study opens the possibility to validate an automatic methodology for the automatic detection and counting of repetitive actions in industrial environment based on machine-learning algorithm and inertial sensors.

关键词： OCRA index Inertial Sensors Industrial worker machine-learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Identification of Sludge in Water Pumping System Using Support Vector machine 20

Identification of Sludge in Water Pumping System Using Suppo...

引用

19th International Conference on Electrical Drives and Power Electronics (EDPE) / 9th Joint Slovakian-Croatian Conference

作者： Subramaniam, Umashankar Dutta, Nabanita Padmanaban, Sanjeevikumar Almakhles, Dhafer Kyslan, Karol Fedak, Viliam Prince Sultan Univ Dept Commun & Networks Riyadh Saudi Arabia VIT Univ Dept Energy & Power Elect Vellore Tamil Nadu India Aalborg Univ Dept Energy Technol Esbjerg Denmark Prince Sultan Univ Dept Commun & Networks Engn Riyadh Saudi Arabia Tech Univ Kosice Dept Elect Engn & Mechatron Kosice Slovakia

ISBN: (纸本)9781728103891

Pumps play a pivotal role in both energy and water conservation. They account for the 20% of the world's total energy consumption and thus monitoring it becomes more relevant to decrease an energy wastage. The performance of the pump deteriorates for various reasons, such as cavitation, sedimentation of silt and water hammering, electrical and mechanical faults. Performance of the pump under silt-laden and identification of silt is seldom studied. It causes severe damage in the pumping system. Identification of sludge particles can productively result in energy savings, water conservation, and energy efficiency. With the advent of machine learning and artificial intelligence, pumps can incorporate these methods to become self-reliant in the identification of type and concentration of silt while pumping the fluid. machine learning is a modern advanced technology, which leads to predict the anomalies of the machine in ground level. This paper presents the how to identify and predict sludge problem in water pumping system using machine learning algorithm.

关键词： centrifugal pumps faults machine-learning algorithm support vector machine

来源：评论

学校读者我要写书评

暂无评论

machine learning-Based Pre-Impact Fall Detection Model to Discriminate Various Types of Fall

引用

JOURNAL OF BIOMECHANICAL ENGINEERING-TRANSACTIONS OF THE ASME 2019年第8期141卷 081010-081010页

作者： Kim, Tae Hyong Choi, Ahnryul Heo, Hyun Mu Kim, Kyungran Lee, Kyungsuk Mun, Joung Hwan Sungkyunkwan Univ Dept Biomechatron Engn Coll Biotechnol & Bioengn 2066 Seoburo Suwon 16419 Gyeonggi South Korea Catholic Kwandong Univ Coll Med Convergence Dept Biomed Engn 24Beomil Ro 579 Beon Gill Kangnung 25601 Gangwon South Korea Rural Dev Adm Agr Hlth & Safety Div 300 Nongsaengmyeong Ro Jeonju 54875 Jeollabuk South Korea

Pre-impact fall detection can send alarm service faster to reduce long-lie conditions and decrease the risk of hospitalization. Detecting various types of fall to determine the impact site or direction prior to impact is important because it increases the chance of decreasing the incidence or severity of fall-related injuries. In this study, a robust pre-impact fall detection model was developed to classify various activities and falls as multiclass and its performance was compared with the performance of previous developed models. Twelve healthy subjects participated in this study. All subjects were asked to place an inertial measuring unit module by fixing on a belt near the left iliac crest to collect accelerometer data for each activity. Our novel proposed model consists of feature calculation and infinite latent feature selection (ILFS) algorithm, auto labeling of activities, and application of machine learning classifiers for discrete and continuous time series data. Nine machine-learning classifiers were applied to detect falls prior to impact and derive final detection results by sorting the classifier. Our model showed the highest classification accuracy. Results for the proposed model that could classify as multiclass showed significantly higher average classification accuracy of 99.57 +/- 0.01% for discrete data-based classifiers and 99.84 +/- 0.02% for continuous time series-based classifiers than previous models (p<0.01). In the future, multiclass pre-impact fall detection models can be applied to fall protector devices by detecting various activities for sending alerts or immediate feedback reactions to prevent falls.

关键词： pre-impact fall detection multiclass fall type machine-learning algorithm accelerometer time series

来源：评论

学校读者我要写书评

暂无评论

Intelligent fault diagnosis system based on big data

引用

JOURNAL OF ENGINEERING-JOE 2019年第23期2019卷 8980-8985页

作者： Wu, Tianshu Chen, Shuyu Wu, Peng Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Chongqing Chuanyi Automat Co Ltd Chongqing 401121 Peoples R China

In view of the actual problems existing in life-cycle health monitoring and diagnosis of large complex equipment, the machine-learning algorithm is applied to data mining of the equipment operation big data, the expert knowledge base is established, the diagnosis rules related to the fault are obtained, the intelligent online monitoring and remote diagnosis of the equipment health condition are realised. The system uses uncertain fault prediction method and hybrid intelligent algorithm to discover the hierarchical association between operation feature big data and operation faults, the feature extraction of operation faults, and the intelligent diagnosis of operation faults. It effectively improved the sensitivity, robustness, and accuracy of monitoring and diagnosis. In the cloud service platform based on the Internet of things, the system realises the intelligent fault prediction and diagnosis, establishes a proactive maintenance system, improves the production efficiency, and ensures the production safety.

关键词： computerised monitoring maintenance engineering condition monitoring feature extraction cloud computing learning (artificial intelligence) data mining production engineering computing Big Data fault diagnosis equipment operation big data data mining machine-learning algorithm complex equipment life-cycle health monitoring actual problems intelligent fault diagnosis system proactive maintenance system intelligent fault prediction intelligent diagnosis operation faults hybrid intelligent algorithm uncertain fault prediction method equipment health condition remote diagnosis intelligent online monitoring diagnosis rules expert knowledge base

来源：评论

学校读者我要写书评

暂无评论

A machine-learning analysis of the rationality of aggregate stock market forecasts

引用

INTERNATIONAL JOURNAL OF FINANCE & ECONOMICS 2018年第4期23卷 642-654页

作者： Pierdzioch, Christian Risse, Marian Helmut Schmidt Univ Dept Econ Holstenhofweg 85POB 700822 D-22008 Hamburg Germany

We use a machine-learning algorithm known as boosted regression trees (BRT) to implement an orthogonality test of the rationality of aggregate stock market forecasts. The BRT algorithm endogenously selects the predictor variables used to proxy the information set of forecasters so as to maximize the predictive power for the forecast error. The BRT algorithm also accounts for a potential non-linear dependence of the forecast error on the predictor variables and for interdependencies between the predictor variables. Our main finding is that, given our set of predictor variables, the rational expectations hypothesis (REH) cannot be rejected for short-term forecasts and that there is evidence against the REH for longer term forecasts. Results for three different groups of forecasters corroborate our main finding.

关键词： boosted regression trees machine-learning algorithm permutation test rationality test stock market survey forecasts

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of a Calf's Feeding State Based on Data Collected by Active Sensors with 3D-Accelerometer 1

引用

20th International Conference on Distributed and Computer and Communication Networks (DCCN)

作者： Sturm, Valentin Efrosinin, Dmitry Efrosinina, Natalia Roland, Leonie Iwersen, Michael Drillich, Marc Auer, Wolfgang Johannes Kepler Univ Linz Altenbergerstr 69 A-4030 Linz Austria RUDN Univ Peoples Friendship Univ Russia Miklukho Maklaya St 6 Moscow 117198 Russia Univ Vet Med Vienna Clin Unit Herd Hlth Management Ruminants Univ Clin Ruminants Dept Farm Anim & Vet Publ Hlth A-1210 Vienna Austria Smartbow GmbH Jutogasse 3 A-4675 Weibern Austria

ISBN: (数字)9783319668369

ISBN: (纸本)9783319668369;9783319668352

The paper deals with the problem of time series classification for the feeding state of calves by means of features evaluated for acceleration real-time data sets. The eartags equipped with an active sensor were developed for location and animal activity identification. Video records synchronized with a sensor data were collected from three calves. After the data preprocessing including the reconstruction of lost information, filtering and frequency stabilization, new time series were used to develop a machine-learning algorithm with equidistant and non-equidistant time series segmentation method based on a modified Kolmogorov-Smirnov statistic. The proposed classification method has achieved a good recognition quality for the feeding state with a best overall accuracy of approximately 94%. Thus this methodology is useful in identifying the feeding state and we may expect the possibility to generalize it to the multi-state case as well. The further improvement of the algorithm is a subject of our future research.

关键词： Eartag Time series classification Kolmogorov-Smirnov statistic machine-learning algorithm

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：