scholarly journals A Method to Estimate Horse Speed per Stride from One IMU with a Machine Learning Method

Sensors ◽  
2020 ◽  
Vol 20 (2) ◽  
pp. 518 ◽  
Author(s):  
Amandine Schmutz ◽  
Laurence Chèze ◽  
Julien Jacques ◽  
Pauline Martin
Keyword(s):  
Machine Learning ◽  
Global Positioning System ◽  
Learning Model ◽  
External Input ◽  
Smart Device ◽  
Positioning System ◽  
Machine Learning Method ◽  
Learning Method ◽  
Machine Learning Model ◽  
Global Positioning

With the emergence of numerical sensors in sports, there is an increasing need for tools and methods to compute objective motion parameters with great accuracy. In particular, inertial measurement units are increasingly used in the clinical domain or the sports one to estimate spatiotemporal parameters. The purpose of the present study was to develop a model that can be included in a smart device in order to estimate the horse speed per stride from accelerometric and gyroscopic data without the use of a global positioning system, enabling the use of such a tool in both indoor and outdoor conditions. The accuracy of two speed calculation methods was compared: one signal based and one machine learning model. Those two methods allowed the calculation of speed from accelerometric and gyroscopic data without any other external input. For this purpose, data were collected under various speeds on straight lines and curved paths. Two reference systems were used to measure the speed in order to have a reference speed value to compare each tested model and estimate their accuracy. Those models were compared according to three different criteria: the percentage of error above 0.6 m/s, the RMSE, and the Bland and Altman limit of agreement. The machine learning method outperformed its competitor by giving the lowest value for all three criteria. The main contribution of this work is that it is the first method that gives an accurate speed per stride for horses without being coupled with a global positioning system or a magnetometer. No similar study performed on horses exists to compare our work with, so the presented model is compared to existing models for human walking. Moreover, this tool can be extended to other equestrian sports, as well as bipedal locomotion as long as consistent data are provided to train the machine learning model. The machine learning model’s accurate results can be explained by the large database built to train the model and the innovative way of slicing stride data before using them as an input for the model.

scholarly journals Predicting Rice Heading Date Using an Integrated Approach Combining a Machine Learning Method and a Crop Growth Model

2020 ◽  
Vol 11 ◽  
Author(s):  
Tai-Shen Chen ◽  
Toru Aoike ◽  
Masanori Yamasaki ◽  
Hiromi Kajiya-Kanegae ◽  
Hiroyoshi Iwata
Keyword(s):  
Machine Learning ◽  
Environmental Variables ◽  
Heading Date ◽  
Integrated Approach ◽  
Learning Model ◽  
Crop Growth ◽  
Day Length ◽  
Machine Learning Method ◽  
Learning Method ◽  
Machine Learning Model

Accurate prediction of heading date under various environmental conditions is expected to facilitate the decision-making process in cultivation management and the breeding process of new cultivars adaptable to the environment. Days to heading (DTH) is a complex trait known to be controlled by multiple genes and genotype-by-environment interactions. Crop growth models (CGMs) have been widely used to predict the phenological development of a plant in an environment; however, they usually require substantial experimental data to calibrate the parameters of the model. The parameters are mostly genotype-specific and are thus usually estimated separately for each cultivar. We propose an integrated approach that links genotype marker data with the developmental genotype-specific parameters of CGMs with a machine learning model, and allows heading date prediction of a new genotype in a new environment. To estimate the parameters, we implemented a Bayesian approach with the advanced Markov chain Monte-Carlo algorithm called the differential evolution adaptive metropolis and conducted the estimation using a large amount of data on heading date and environmental variables. The data comprised sowing and heading dates of 112 cultivars/lines tested at 7 locations for 14 years and the corresponding environmental variables (day length and daily temperature). We compared the predictive accuracy of DTH between the proposed approach, a CGM, and a single machine learning model. The results showed that the extreme learning machine (one of the implemented machine learning models) was superior to the CGM for the prediction of a tested genotype in a tested location. The proposed approach outperformed the machine learning method in the prediction of an untested genotype in an untested location. We also evaluated the potential of the proposed approach in the prediction of the distribution of DTH in 103 F2 segregation populations derived from crosses between a common parent, Koshihikari, and 103 cultivars/lines. The results showed a high correlation coefficient (ca. 0.8) of the 10, 50, and 90th percentiles of the observed and predicted distribution of DTH. In this study, the integration of a machine learning model and a CGM was better able to predict the heading date of a new rice cultivar in an untested potential environment.

scholarly journals Automated Machine Learning Overview

2019 ◽  
Vol 27 (45) ◽  
pp. 107-112
Author(s):  
Roman Budjač ◽  
Marcel Nikmon ◽  
Peter Schreiber ◽  
Barbora Zahradníková ◽  
Dagmar Janáčová
Keyword(s):  
Machine Learning ◽  
Image Classification ◽  
Learning Model ◽  
Machine Learning Method ◽  
Learning Method ◽  
Learning Tasks ◽  
Machine Learning Model ◽  
Automated Machine Learning ◽  
Expertise Level

Abstract This paper aims at deeper exploration of the new field named auto-machine learning, as it shows promising results in specific machine learning tasks e.g. image classification. The following article is about to summarize the most successful approaches now available in the A.I. community. The automated machine learning method is very briefly described here, but the concept of automated task solving seems to be very promising, since it can significantly reduce expertise level of a person developing the machine learning model. We used Auto-Keras to find the best architecture on several datasets, and demonstrated several automated machine learning features, as well as discussed the issue deeper.

Machine learning methodology for TEC prediction using global positioning system signal measurements

2020 ◽  
Author(s):  
S.G. Prasad Mutchakayala ◽  
V.L. Manasa Mandalapu ◽  
J.R.K. Kumar Dabbakuti ◽  
Sai Sruti Vedula
Keyword(s):  
Machine Learning ◽  
Global Positioning System ◽  
Positioning System ◽  
Global Positioning

scholarly journals Development of a Cable Damage Detection Deep Learning Method based on Acceleration Response of Cable-Stayed Bridge

2021 ◽  
Vol 12 (6) ◽  
pp. 638-647
Author(s):  
Park Gi-Hun Et.al
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Damage Detection ◽  
Learning Model ◽  
Learning Method ◽  
Acceleration Response ◽  
Damage Location ◽  
Cable Stayed Bridge ◽  
Machine Learning Model ◽  
Cable Damage

The purpose of this thesis was to select a cable-stayed bridge to which external force may cause damage as the subject, to develop a damage detection deep learning method capable of detecting cable damage, and to test and verify the developed damage detection deep learning method. The damage detection method was developed as a system that utilizes the acceleration response of a structure measured for maintenance purposes. To extract information capable of identifying the damage locations from among the measured acceleration responses, a CNN ID was used to develop the damage detection deep learning method. The developed damage detection deep learning method was developed in a way not independently arranging 1 machine learning model per each measuring point and finally predicting the damage location based on the decision-making results collected from each machine learning model. The developed damage detection deep learning method performed the learning per each machine learning model by utilizing the acceleration response of a structure acquired based on the preliminary damage test. Finally, the damage detection deep learning method that completed the learning verified the cable damage location detection performance by utilizing the data acquired based on the cable-stayed bridge damage test. As a result, it was confirmed that the developed damage detection deep learning method predicted the damage location of a cable-stayed bridge at an average accuracy of 89%. In the current research, only the cable-stayed bridge of the Seohaegyo Bridge was studied, but in the improved study, the research will be conducted on other bridges and damage assessment will be conducted on all cables.

scholarly journals Application of differential countermeasure machine learning model in the field of UAV circuit inspection

2021 ◽  
Vol 2083 (3) ◽  
pp. 032027
Author(s):  
Xinrui Huang
Keyword(s):  
Machine Learning ◽  
Visual Analysis ◽  
Path Selection ◽  
Movement Trajectory ◽  
Machine Learning Method ◽  
Learning Method ◽  
Machine Learning Model ◽  
Angle Difference ◽  
Optimal Pursuit ◽  
Attack And Defense

Abstract In this paper, we establish one-objective differential game equations for one-to-one attack and defense in a two-dimensional plane. Through calculation and visual analysis, obtain the optimal pursuit path movement trajectory, and through machine learning method to training UAV, using cycle process of simulation, output with time growth each cycle pursuit path results, by comparing the movement trajectory image of the pursuit results and find the sheep just escape critical point exit. After that, the angle difference between the two initial positions was changed and tested again to enable the UAV to learn the optimal escape strategy more comprehensively, thus making a more precise path selection. Finally, this method can be reasonably evaluated.

scholarly journals Wheel Obstraction Detection with Machine Learning

2019 ◽  
Vol 8 (9S4) ◽  
pp. 267-274
Keyword(s):  
Machine Learning ◽  
Global Positioning System ◽  
Positioning System ◽  
Assessment Framework ◽  
Special Cases ◽  
Global Positioning ◽  
Quantitative Examination ◽  
Separation Size ◽  
Special Case

In this paper, to blessing an ongoing programmed innovative and insightful based absolutely rail assessment framework, which plays examinations at sixteen km/h with a casing rate of 20 fps. The framework identifies significant rail segments including ties, tie plates, and grapples, with high exactness and productivity. To accomplish this objective, to initially widen an immovable of picture and video investigation and after that prompt a particular worldwide streamlining structure to join proof from two or three cameras, Global Positioning System, and separation size apparatus to moreover improve the recognition execution. Additionally, as the grapple is a significant kind of rail clasp, to've as needs be propelled the push to hit upon stay special cases, which consolidates evaluating the grapple circumstances on the tie stage and recognizing grapple design exemptions on the consistence level. Quantitative examination performed on a huge video certainties set caught with unmistakable tune and lighting installations conditions, notwithstanding on a continuous order check, has affirmed empotoring execution on each rail perspective recognition and stay special case location. In particular, a middle of 94.67% accuracy and ninety three% remember expense has been finished for recognizing each of the 3 rail segments, and a 100% recognition charge is practiced for consistence level stay special case with three phony positives predictable with hour. To our excellent comprehension, our framework is the essential to address and clear up both perspective and special case location issues in this rail assessment region

scholarly journals An Intelligent System to Enhance Visually-Impaired Navigation and Disaster Assistance using Geo-Based Positioning and Machine Learning

2021 ◽  
Author(s):  
Wenhua Liang ◽  
Ishmael Rico ◽  
Yu Sun
Keyword(s):  
Machine Learning ◽  
Global Positioning System ◽  
Visually Impaired ◽  
Intelligent System ◽  
Positioning System ◽  
Technological Advancement ◽  
Disaster Assistance ◽  
Global Positioning ◽  
New Phase ◽  
Do So

Technological advancement has brought many the convenience that the society used to lack, but unnoticed by many, a population neglected through the age of technology has been the visually impaired population. The visually impaired population has grown through ages with as much desire as everyone else to adventure but lack the confidence and support to do so. Time has transported society to a new phase condensed in big data, but to the visually impaired population, this quick-pace living lifestyle, along with the unpredictable natural disaster and COVID-19 pandemic, has dropped them deeper into a feeling of disconnection from the society. Our application uses the global positioning system to supportthe visually impaired in independent navigation, alerts them in face of natural disasters, and remindsthem to sanitize their devices during the COVID-19 pandemic.

Water Level Prediction of Rainwater Pipe Network Using an SVM-Based Machine Learning Method

2019 ◽  
Vol 34 (02) ◽  
pp. 2051002 ◽  
Author(s):  
Hao Wang ◽  
Lixiang Song
Keyword(s):  
Machine Learning ◽  
Water Level ◽  
Water Levels ◽  
Machine Learning Method ◽  
Learning Method ◽  
Pipe Network ◽  
Hydrodynamic Models ◽  
Time Step ◽  
Running Speed ◽  
Machine Learning Model

Model accuracy and running speed are the two key issues for flood warning in urban areas. Traditional hydrodynamic models, which have a rigorous physical mechanism for flood routine, have been widely adopted for water level prediction of rainwater pipe network. However, with the amount of pipes increasing, both the running speed and data availability of hydrodynamic models would be decreased rapidly. To achieve a real-time prediction for the water level of the rainwater pipe network, a new framework based on a machine learning method was proposed in this paper. The spatial and temporal autocorrelation of water levels for adjacent manholes was revealed through theoretical analysis, and then a support vector machine (SVM)-based machine learning model was developed, in which the water levels of adjacent manholes and rivers-near-by-outlets at the last time step were chosen as the independent variables, and then the water levels at the current time step can be computed by the proposed machine learning model with calibrated parameters. The proposed framework was applied in Fuzhou city, China. It turns out that the proposed machine learning method can forecast the water level of the rainwater pipe network with good accuracy and running speed.

GPS/INS Integration During GPS Outages Using Machine Learning Augmented with Kalman Filter

2021 ◽  
Vol 16 ◽  
pp. 294-301
Author(s):  
Reshma Verma ◽  
Lakshmi Shrinivasan ◽  
K Shreedarshan
Keyword(s):  
Machine Learning ◽  
Kalman Filter ◽  
Global Positioning System ◽  
Navigation System ◽  
Inertial Navigation System ◽  
Inertial Navigation ◽  
Supervised Machine Learning ◽  
Positioning System ◽  
Position Information ◽  
Global Positioning

Nowadays a tremendous progress has been witnessed in Global Positioning System (GPS) and Inertial Navigation System (INS). The Global Positioning System provides information as long as there is an unobstructed line of sight and it suffers from multipath effect. To enhance the performance of an integrated Global Positioning System and Inertial Navigation System (GPS/INS) during GPS outages, a novel hybrid fusion algorithm is proposed to provide a pseudo position information to assist the integrated navigation system. A new model that directly relates the velocity, angular rate and specific force of INS to the increments of the GPS position is established. Combined with a Kalman filter the hybrid system is able to predict and estimate a pseud GPS position when GPS signal is unavailable. Field test data are collected to experimentally evaluate the proposed model. In this paper, the obtained GPS/INS datasets are pre-processed and semi-supervised machine learning technique has been used. These datasets are then passed into Kalman filtering for the estimation/prediction of GPS positions which were lost due to GPS outages. Hence, to bridge out the gaps of GPS outages Kalman Filter plays a major role in prediction. The comparative results of Kaman filter and extended Kalman filter are computed. The simulation results show that the GPS positions have been predicted taking into account some factors/measurements of a vehicle, the trajectory of the vehicle, the entire simulation was done using Anaconda (Jupyter Notebook).

Sign in / Sign up

Export Citation Format

Share Document