检索结果-内蒙古大学图书馆

IEEE 7th Southern Power Electronics Conference (SPEC)

作者： Nademi, Hamed Calif State Univ Dept Elect Engn San Marcos CA 92096 USA

ISBN: (纸本)9798350399882

An intelligent controller is developed based on machine learning algorithm incorporated into predictive control strategy. The model of interest is trained during transfer learning process utilizing measurement dataset. The introduced control scheme provides an optimal load dispatching among distributed energy resources (DERs) interconnected with a benchmarked Electric Vehicle (EV) battery charger. The proposed scheme offers an easy realization on various embedded hardware systems independently. In this study, a few operational conditions of an exemplary charging station are examined via Hardware-in-the-Loop (HIL) testing. The findings are then compared to the classical finite-control-set model predictive control (FCS-MPC) which has been widely used in recent studies. Several operation scenarios have been evaluated and the obtained results are paving the way for future solutions addressing the concern of utilities pertaining to DERs load management for vehicle-to-grid (V2G) technologies.

关键词： electric vehicle hardware-in-the-loop testing machine-learning algorithm power converters predictive control

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

Early identification of sepsis in burn patients using compensatory reserve measurement: A prospective case series study

引用

Burns Open 2022年第4期6卷 137-145页

作者： Convertino, Victor A. Wagner, Amanda R. Akers, Kevin S. VanFosson, Christopher A. Cancio, Leopoldo C. US Army Institute of Surgical Research JBSA Fort Sam Houston TX United States

Background: Early identification of sepsis can be lifesaving, but current diagnostic approaches rely on standard vital signs and biochemistry analyses that delay recognition. We postulate that early identification of sepsis could be accomplished with a clinical assessment of real-time changes in physiological responses that reflect compensation to relative hypovolemia, or the compensatory reserve measurement (CRM). In this pilot study, we measured CRM in burn patients who transitioned from a non-infected state to sepsis to determine if CRM would be reduced prior to clinical identification of sepsis using traditional standard-of-care criteria. Methods: Each subject underwent placement of a radial arterial catheter upon arrival to the burn ICU. Morphology of analog arterial waveforms was recorded and analyzed based on a machine-learning algorithm, employing feature-extraction techniques that provided CRM values on a relative scale of 100% (normal) to 0% (onset of decompensated shock). CRM values one (D-1) or two (D-2) times prior to the day of sepsis diagnosis (D+0) were compared in time to standard diagnostic techniques. Results: CRM was lower in all patients on D+0 compared to ICU admission day. Complete analyzable arterial waveform data collected on D-1 and D-2 were captured from 5 subjects. These patients demonstrated an average reduction (p = 0.003) in CRM from 48 ± 14% on D-2 to 31 ± 14% on D-1 prior to sepsis diagnosis with standard criteria on D+0. Conclusion: The results of this clinical investigation conducted in burn patients provide the first data to substantiate a capability for early diagnosis of sepsis by measurement of the compensatory reserve. Our findings support the notion that this novel technology could offer caregivers of at-risk burn patients with a user-friendly decision-support indicator of infection for individualized triage and treatment. Level of evidence: Diagnostic, level IV. © 2022

关键词： Burns Infection machine-learning algorithm Monitoring Sepsis

来源：评论

学校读者我要写书评

暂无评论

Hypoxia Detection for Confined-Space Workers: Photoplethysmography and machine-learning Techniques

引用

SN Computer Science 2022年第4期3卷 1-11页

作者： Wei, Yixuan Jin, Longzhe Wang, Shu Xu, Yifei Ding, Tianqi School of Civil Engineering and Resources University of Science and Technology Beijing Beijing 100083 China

Oxygen-deficiency is a cause of fatalities in confined-space workplaces. Most research and projects have been conducted to reduce work-related accidents by external measurements, while works addressing the early warning of workers’ hypoxia state through a bio-electrical signal have rarely been conducted. In this paper, we present a hypoxia detection system based on non-invasive photoplethysmograph (PPG) measurement using machine-learning (ML) algorithms. The PPG signals obtained from 22 subjects underwent preprocessing and features extraction steps. Time-domain features, rising and falling slopes, and amplitude parameters were adopted to train and test the ML algorithms. In addition, an Internet of Things- (IoT) based smart wearable device and monitoring system were developed to measure the vital parameters of workers in confined spaces. Cardiac cycle time of all the participants except subject 8 decreased significantly (P < 0.01) throughout the oxygen-deficiency trial. The PPG signal complexity essentially decreased (P = 0.006) when the concentration of environmental oxygen declined. The DT algorithm with nine input parameters outperformed the other algorithms in prediction accuracy (Acc = 0.9). The results show that the features extracted from the PPG signal can be adopted as important indicators to revealing the hypoxia state of workers. The device and system automatically measure and analyze the PPG signal with the location details of caregivers and notify the monitoring staff in the case of an emergency. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Confined space Hypoxia Internet of Things (IoT) machine-learning algorithm Photoplethysmography (PPG)

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

Crop specific algorithms trained over ground measurements provide the best performance for GAI and fAPAR estimates from Landsat-8 observations

引用

REMOTE SENSING OF ENVIRONMENT 2021年 260卷

作者： Camacho, Fernando Fuster, Beatriz Li, Wenjuan Weiss, Marie Ganguly, Sangram Lacaze, Roselyne Baret, Fred Parc Cient Univ Valencia EOLAB C Catedrat Agustin Escardino 9 Valencia 46980 Spain EMMAH Domaine St Paul INRA UMR114 F-84914 Avignon France NASA Ames Res Ctr BAERI Moffett Field California CA 94043 USA HYGEOS Euratechnol 165 Ave Bretagne F-59000 Lille France

Estimation of Green Area Index (GAI) and fraction of Absorbed Photosynthetically Active Radiation (fAPAR) from decametric satellites was investigated in this study using a large database of ground measurements over croplands. It covers six main crop types including rice, corn, wheat and barley, sunflower, soybean and other types of crops. Ground measurements were completed using either digital hemispherical cameras, LAI-2000 or AccuPAR devices over sites representative of a decametric pixel. Sites were spread over the globe and the data collected at several growth stages concurrently to the acquisition of Landsat-8 images. Several machine learning techniques were investigated to retrieve GAI and fAPAR from the Landsat-8 top of canopy reflectance values, either using empirical or simulated calibration databases and generic or crop-type specific algorithms. Results show that using the six Landsat-8 bands together provided the best estimates of GAI and fAPAR. machine learning techniques trained over a dataset simulated by the PROSAIL model provided less accurate estimates of GAI and fAPAR as compared to machine learning techniques trained over the ground data collected and applied over a similar dataset (best-case scenario). All machine learning techniques performed similarly when calibrated on PROSAIL simulations. The Gaussian process regression (GPR) was the best performing machine learning technique as compared to artificial neural networks (ANN), support vector machine regression (SVM) and as compared to NDVI simple model when calibrated over the ground dataset in the best-case scenario. However, the performance of the GPR trained over ground data is notably degraded when applied to crop types excluded from the calibration (worst-case scenario), and models based on simulations performs similarly of even better. Furthermore, training the GPR over specific crop types was performing slightly better than training over all the crop types together if at least 100 well di

关键词： GAI fAPAR Landsat-8 machine-learning algorithm Croplands Gaussian processes Regresion PROSAIL simulations Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

On the Problem of State Recognition in Injection Molding Based on Accelerometer Data Sets

引用

SENSORS 2022年第16期22卷 6165页

作者： Brunthaler, Julian Grabski, Patryk Sturm, Valentin Lubowski, Wolfgang Efrosinin, Dmitry AISEMO GmbH A-4675 Weibern Austria Linz Ctr Meachtron GmbH A-4040 Linz Austria Johannes Kepler Univ Linz Inst Stochast A-4040 Linz Austria

The last few decades have been characterised by a very active application of smart technologies in various fields of industry. This paper deals with industrial activities, such as injection molding, where it is required to monitor continuously the manufacturing process to identify both the effective running time and down-time periods. Supervised machine learning algorithms are developed to recognize automatically the periods of the injection molding machines. The former algorithm uses directly the features of the descriptive statistics, while the latter one utilizes a convolutional neural network. The automatic state recognition system is equipped with an 3D-accelerometer sensor whose datasets are used to train and verify the proposed algorithms. The novelty of our contribution is that accelerometer data-based machine learning models are used to distinguish producing and non-producing periods by means of recognition of key steps in an injection molding cycle. The first testing results show the approximate overall balanced accuracy of 72-92% that illustrates the large potential of the monitoring system with the accelerometer. According to the ANOVA test, there are no sufficient statistical differences between the comparative algorithms, but the results of the neural network exhibit higher variances of the defined accuracy metrics.

关键词： injection molding accelerometer sensor state recognition machine-learning algorithm convolutional neural network

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

Seismic response and performance prediction of steel buckling-restrained braced frames using machine-learning methods

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 128卷

作者： Asgarkhani, N. Kazemi, F. Jakubczyk-Galczynska, A. Mohebi, B. Jankowski, R. Gdansk Univ Technol Fac Civil & Environm Engn Ul Narutowicza 11-12 PL-80233 Gdansk Poland UCL Dept Civil Environm & Geomat Engn London England Imam Khomeini Int Univ Fac Engn & Technol Qazvin Iran

Nowadays, Buckling-Restrained Brace Frames (BRBFs) have been used as lateral force-resisting systems for low-, to mid-rise buildings. Residual Interstory Drift (RID) of BRBFs plays a key role in deciding to retrofit buildings after seismic excitation;however, existing formulas have limitations and cannot effectively help civil engineers, e.g., FEMA P-58, which is a conservative estimation method. Therefore, there is a need to provide a comprehensive tool for estimating seismic responses of Interstory Drift (ID) and RID with novel approaches to fulfill the shortcomings of existing formulas. The machine learning (ML) method is an interdisciplinary approach that makes it possible to solve these types of engineering problems. Therefore, the current study proposes ML algorithms to provide a prediction model for determining the seismic response, seismic performance curve, and seismic failure probability curve of BRBFs. To train ML-based prediction models, Nonlinear Time-History Analysis (NTHA) and Incremental Dynamic Analysis (IDA) were performed on the 2-, to 12-Story BRBFs subjected to 78 far-field ground motions, and 606944 data points were prepared for different prediction purposes. The results indicate that the considered approaches are justified. For instance, the proposed ML methods have the ability to predict the maximum ID, maximum RID and maximum roof ID with the accuracy of even 98.7%, 95.2%, and 93.8%, respectively, for the 4-Story BRBF. Moreover, a general preliminary estimation tool is introduced to provide predictions based on the input parameters considered in the study.

关键词： Buckling-restrained braced frame machine-learning algorithm Residual interstory drift Seismic retrofit Seismic performance curve Seismic failure probability

来源：评论

学校读者我要写书评

暂无评论

A Raman spectral database of naturally aged plastics: A proof-of-concept study for waste plastic sorting

引用

JOURNAL OF RAMAN SPECTROSCOPY 2023年第3期54卷 305-313页

作者： Marica, Ioana Pinzaru, Simona Cinta Babes Bolyai Univ Fac Phys Kogalniceanu 1 RO-400084 Cluj Napoca Romania

A Raman spectral database of naturally aged plastics for years is developed aiming to support efficient and proper plastic waste management based on Raman sorting technology. The database is designed as a website and contains the Raman spectral data for 146 plastic waste samples degraded for years in natural environmental conditions. Plastic samples aged for years in indoor conditions are also included along with a few undegraded, common plastics. The natural environmental degradation occurring for years of exposure to sun radiation, terrestrial and aquatic factors, or temperature variations is poorly understood in terms of spectral changes of representative plastics. The samples of choice are represented by the widespread types of plastics such as polyethylene terephthalate, high-density polyethylene, low-density polyethylene, polyvinyl chloride, polypropylene, and polystyrene. Each plastic sample is described individually on the database's website, and its Raman spectrum is available as a txt file for both educational and analytical purposes. Moreover, the database was validated by external validation of the machine-learning classifiers: k-nearest neighbor, support vector machine, logistic regression, random forest, and Naive Bayes resulting in a classification accuracy between 0.902 and 0.973.

关键词： machine-learning algorithm plastic Raman database plastic waste Raman sorting technology

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：