gyroscopyГироскопия и навигацияGiroskopiya i Navigatsiya0869-70352075-0927AO «Концерн «ЦНИИ «Электроприбор»10.17285/0869-7035.2018.26.2.043-058gyroscopy-277Research ArticleСтатьиКлассификация маневров подвижного объекта с шестью степенями свободы методом логистической регрессииManeuver Classification of a Moving Vehicle with Six Degrees of Freedom Using Logistic Regression TechniqueАль-МансурМ.Al MansourM.

Аль-Мансур Мехьяр. Аспирант, факультет электронных и механических систем

ЧуаибИ.ChouaibI.

Чуаиб Ибрахим. Доктор наук, профессор

ДжафарА.JafarA.

Джафар Асеф. Доктор наук, профессор

Институт прикладных наук и технологий (Дамаск).СирияHigher Institute for Applied Sciences and Technology (HIAST), DamascusSyrian Arab Republic2018201120252624358Copyright © Аль-Мансур М., Чуаиб И., Джафар А., 20252025Аль-Мансур М., Чуаиб И., Джафар А.Al Mansour M., Chouaib I., Jafar A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.gyroscopy.ru/jour/article/view/277

Представлен новый онлайн-алгоритм классификации маневров подвижного объекта с шестью степенями свободы на основе данных бортового микромеханического инерциального измерительного модуля (ИИМ) (трех акселерометров и трех гироскопических датчиков угловой скорости). Классификация может быть как дискретной (то есть резкий маневр, плавный маневр или отсутствие маневра), так и непрерывной (величина, указывающая на интенсивность маневра). В основе предлагаемого алгоритма лежат метод главных компонент и метод машинного обучения, известный как логистическая регрессия, которая представляет собой модель дискриминативной вероятностной классификации. Результаты полунатурного моделирования с использованием данных микромеханического ИИМ, взятых из реальных экспериментов с беспилотными летательными аппаратами (БЛА), показали эффективность предложенного алгоритма и его пригодность для широкого спектра применений.

This paper presents a novel on line algorithm for maneuver classification of a moving vehicle with six degrees of freedom, using on-board MEMS IMU’s data (three accelerometers and three rate gyros). The classification is either discrete (i.e. high, low or no maneuver), or continuous (a value that reflects the intensity of the maneuver). It should be mentioned that there is no explicit solution for this problem in any research paper previously published, due to the inability to find a direct mathematical model capable of characterizing this problem, despite its importance and its impact in improving the functioning of navigation systems. The proposed algorithm is based on a machine learning technique called logistic regression, which is a discriminative probabilistic classification model. Computer simulations, using MEMS IMU’s data taken from real experiments of an UAV, showed the effectiveness of the proposed algorithm, taking into account the sampling time, and the suitability for a wide spectrum of applications.

Маневрымашинное обучениестатистические классификаторылогистическая регрессияметод главных компонентбеспилотный летательный аппарат.Maneuversmachine learningstatistical classifierslogistic regressionprincipal component analysesUAV.ReferencesStengel, R., Aircraft Flight Dynamics, Princeton University, 2014.Stengel, R., Aircraft Flight Dynamics, Princeton University, 2014.Triantafyllou, M.S., Hover, F.S., Maneuvering and control of marine vehicles, Cambridge, Massachusetts, USA: edited by authors, 2003.Triantafyllou, M.S., Hover, F.S., Maneuvering and control of marine vehicles, Cambridge, Massachusetts, USA: edited by authors, 2003.Oza, N.C., Tumer, K., Tumer, I.Y., Hu, E.M., Classification of aircraft maneuvers for fault detection, in: International Workshop on Multiple Classifier Systems, Springer, 2003, pp. 375–384.Oza, N.C., Tumer, K., Tumer, I.Y., Hu, E.M., Classification of aircraft maneuvers for fault detection, in: International Workshop on Multiple Classifier Systems, Springer, 2003, pp. 375–384.Tumer, I.Y., Hu, E.M., Principal components analysis of triaxial vibration data from helicopter transmissions, Society for Machinery Failure Prevention Technology, 2001.Tumer, I.Y., Hu, E.M., Principal components analysis of triaxial vibration data from helicopter transmissions, Society for Machinery Failure Prevention Technology, 2001.Stojakovic, P., Rasuo, B., Single propeller airplane minimal flight speed based upon the lateral maneuver condition, Aerospace Science and Technology, Elsevier, vol. 49, 2016.Stojakovic, P., Rasuo, B., Single propeller airplane minimal flight speed based upon the lateral maneuver condition, Aerospace Science and Technology, Elsevier, vol. 49, 2016.Larry, E.S.I., Croyle S.R., Zero motion detection system for improved vehicle navigation system, uS Patent 5,991,692 (Nov. 23 1999).Larry, E.S.I., Croyle S.R., Zero motion detection system for improved vehicle navigation system, uS Patent 5,991,692 (Nov. 23 1999).Bishop, C., Pattern Recognition and Machine Learning, Springer, New York, 2006.Bishop, C., Pattern Recognition and Machine Learning, Springer, New York, 2006.Jurafsky, D., Martin, J.H., Speech and Language Processing, Classification: Naive Bayes,Logistic Regression, Sentiment, Pearson, 2014, Ch. 7.Jurafsky, D., Martin, J.H., Speech and Language Processing, Classification: Naive Bayes,Logistic Regression, Sentiment, Pearson, 2014, Ch. 7.Kay, S.M., Nuttall, A.H., Baggenstoss, P.M., Multidimensional probability density function approximations for detection, classification, and model order selection, Signal Processing, IEEE Transactions on, IEEE, vol. 49, 2001.Kay, S.M., Nuttall, A.H., Baggenstoss, P.M., Multidimensional probability density function approximations for detection, classification, and model order selection, Signal Processing, IEEE Transactions on, IEEE, vol. 49, 2001.Mitchell, M.H.T.M., Machine Learning, 2nd Edition, Spring, 2015, Ch. 3.Mitchell, M.H.T.M., Machine Learning, 2nd Edition, Spring, 2015, Ch. 3.Alpaydin, E., Introduction to Machine Learning, third edition Edition, MIT Press, 2014.Alpaydin, E., Introduction to Machine Learning, third edition Edition, MIT Press, 2014.Paalanen, P., Bayesian classification using Gaussian mixture model and EM estimation: Implementations and comparisons, Information Technology Project, 2004.Paalanen, P., Bayesian classification using Gaussian mixture model and EM estimation: Implementations and comparisons, Information Technology Project, 2004.Jordan, A., On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes, Advances in neural information processing systems, vol. 14, 2002.Jordan, A., On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes, Advances in neural information processing systems, vol. 14, 2002.Park, H.-A., An Introduction to Logistic Regression: From Basic Concepts to Interpretation with Particular Attention to Nursing Domain, J Korean Acad Nurs, Korean Society of Nursing Science, 2013.Park, H.-A., An Introduction to Logistic Regression: From Basic Concepts to Interpretation with Particular Attention to Nursing Domain, J Korean Acad Nurs, Korean Society of Nursing Science, 2013.Jiang, Chengyu, Xue, Liang, Chang, Honglong, Yuan, Guangmin, and Yuan, Weizheng, Signal Processing of MEMS Gyroscope Arrays to Improve Accuracy Using a 1st Order Markov for Rate Signal Modeling, Sensors, 2012.Jiang, Chengyu, Xue, Liang, Chang, Honglong, Yuan, Guangmin, and Yuan, Weizheng, Signal Processing of MEMS Gyroscope Arrays to Improve Accuracy Using a 1st Order Markov for Rate Signal Modeling, Sensors, 2012.Shitikov, V.K., Mastitskii, S.E., Classification, Regression, and Other Data Mining Algorithms Using R, Togliatti, London, 2017. (Шитиков В.К., Мастицкий С.Э. Классификация, регрессия и другие алгоритмы Data Mining с использованием R. Тольятти, Лондон, 2017. 351 с. URL: https://github.com/ranalytics/data-mining.)Shitikov, V.K., Mastitskii, S.E., Classification, Regression, and Other Data Mining Algorithms Using R, Togliatti, London, 2017. (Шитиков В.К., Мастицкий С.Э. Классификация, регрессия и другие алгоритмы Data Mining с использованием R. Тольятти, Лондон, 2017. 351 с. URL: https://github.com/ranalytics/data-mining.)Crossbow technology, inc, AHRS 400CC User’s Manual, Document Part Number: 6020-0025-01, www. xbow.com.Crossbow technology, inc, AHRS 400CC User’s Manual, Document Part Number: 6020-0025-01, www. xbow.com.

The authors declare that there are no conflicts of interest present.