Machine Learning Methodology in a System Applying the Adaptive Strategy for Teaching Human Motions

Wójcik, Krzysztof; Piekarczyk, Marcin

doi:10.3390/s20010314

Cited by 11 publications

(26 citation statements)

References 46 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, deep learning models, based on various variants of neural networks, such as CNN [ 26 ], RNN [ 27 ] or GNN [ 28 ], are also experiencing a renaissance. Depending on the area and specificity of applications, very complex approaches are used, often utilising integration and combination of many techniques, which is particularly visible in case of interdisciplinary problems occurring, for example, in such selected fields as medicine [ 29 , 30 ], education [ 31 , 32 ], metrology [ 33 , 34 , 35 ], biometrics [ 36 , 37 ], learning of motor activities [ 38 , 39 ] or gesture recognition [ 40 , 41 ].…”

Section: Ann-based Methods To Remove Artefactsmentioning

confidence: 99%

CNN-Based Classifier as an Offline Trigger for the CREDO Experiment

Piekarczyk

Bar

Bibrzycki

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Gamification is known to enhance users’ participation in education and research projects that follow the citizen science paradigm. The Cosmic Ray Extremely Distributed Observatory (CREDO) experiment is designed for the large-scale study of various radiation forms that continuously reach the Earth from space, collectively known as cosmic rays. The CREDO Detector app relies on a network of involved users and is now working worldwide across phones and other CMOS sensor-equipped devices. To broaden the user base and activate current users, CREDO extensively uses the gamification solutions like the periodical Particle Hunters Competition. However, the adverse effect of gamification is that the number of artefacts, i.e., signals unrelated to cosmic ray detection or openly related to cheating, substantially increases. To tag the artefacts appearing in the CREDO database we propose the method based on machine learning. The approach involves training the Convolutional Neural Network (CNN) to recognise the morphological difference between signals and artefacts. As a result we obtain the CNN-based trigger which is able to mimic the signal vs. artefact assignments of human annotators as closely as possible. To enhance the method, the input image signal is adaptively thresholded and then transformed using Daubechies wavelets. In this exploratory study, we use wavelet transforms to amplify distinctive image features. As a result, we obtain a very good recognition ratio of almost 99% for both signal and artefacts. The proposed solution allows eliminating the manual supervision of the competition process.

show abstract

Section: Ann-based Methods To Remove Artefactsmentioning

confidence: 99%

CNN-Based Classifier as an Offline Trigger for the CREDO Experiment

Piekarczyk

Bar

Bibrzycki

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The creation of specialized learning algorithms is another important problem, which must be performed with the participation of experts [8], [10]. However, the experts might not necessarily perceive critical relationships between the aspects of the automatic teaching process, and generally may be unprepared for the challenges of creating new, unconventional algorithms of teaching.…”

Section: Learning Methods and The Role Of Expert Knowledgementioning

confidence: 99%

“…The authors of the last two papers suggested analyzing the current teaching context in order to change the teaching method accordingly (however, they did not propose specific methodologies). A system that used the results of the motion signal classification in the task of learning a trajectory, was described by Wójcik and Piekarczyk [10]. The authors concluded however, that, due to a problem with the system-learner communication, the proposed approach was not suitable for teaching fast movements.…”

Section: A the Learning Of Human Motion Activitymentioning

confidence: 99%

“…A wide range of methods for motion signal classification are depicted in Section I-C. The question on the choice of an adequate method is broadly discussed in the subject literature [2], [10], [18], [25], [32]. Regarding the character of the particular motion and the sensors used, the SVM, kNN, and HMM approaches are suggested.…”

Section: The Analysis Of Motion Signalsmentioning

confidence: 99%

See 1 more Smart Citation

Pattern Recognition Methods as a Tool to Build an Automatic System for Learning Coordinated Human Motions

Wójcik

2020

IEEE Access

View full text Add to dashboard Cite

There is great social and economic significance in the teaching and learning of motion activities. This is notably true for teaching the activities involved in rehabilitation, sports, and professional work. The possibility of engaging an automatic teaching system is highly significant. Nevertheless, building an effective system is an ongoing challenge. This article describes a general outline of the teaching system, which includes MEMS (micro-electro-mechanical systems) sensors, haptic actuators, and algorithms for signal classification applied to the online selection of an appropriate teaching method. The main goal of this paper was to prove that the system is able to teach fast and synchronized movements effectively. To this end, system performance was presented and discussed. The statistical tests revealed an efficiency of the proposed approach, especially for tasks of teaching fast and periodic movements. This result was the primary outcome of the presented paper. The described scheme can be utilized for building two types of motor learning systems. The first relates to the "personal" learning systems for rehabilitation and sports. The second type can perform the classification of complex movements of human body parts and may be used in teaching the remote control of machines and vehicles (excavators, cranes, search and rescue drones, etc.).INDEX TERMS haptic feedback, machine learning, MEMS sensors, motor learning, pattern recognition.

show abstract

“…[17]. Based on BD personalization and adaptation, Wójcik and Piekarczyk examined the learning process structure, learning process visualization, and learning effect demonstration, and the findings showed that data analysis of students' learning behavior and knowledge mastery could recommend reasonable learning paths and learning resources with appropriate difficulty [18]. According to Z. Li et al, students' mastery of objective and subjective questions is linked and compensated in different ways [19].…”

Section: Introductionmentioning

confidence: 99%

Reform and Practice of Public English Examination Mode in Colleges and Universities Using Big Data Analysis and Speech Recognition

Zhu¹

2022

Mobile Information Systems

View full text Add to dashboard Cite

In terms of the CPE (College Public English) test mode, it suffers from inefficiency and uniqueness. The test must be comprehensive and objective in order to serve as a standard for evaluating English proficiency. Promoting English examination reform and practice is extremely important for English teachers. In light of the current situation, the CPE test system is being researched and designed using BD (big data) analysis. To establish the index system and parameters for evaluating test questions, the test database maintenance module uses a method based on problem-solving theory. For pronunciation recognition, error judgment, and scoring of spoken English, speech recognition and HMM (hidden Markov model) scores are used, and the final spoken English score is obtained through percentile transformation. In intelligent scoring, the AdaBoost CT (adaptive enhancement classification) algorithm is introduced, and various algorithms are compared through extensive literature reading. The results show that when the parameter is set to 50, the AdaBoost CT algorithm has the highest accuracy, at 88.39%. The platform improves students’ learning efficiency and quality by diagnosing their learning problems and intervening in their learning in real time. The results are significantly better than those of other students.

show abstract

Machine Learning Methodology in a System Applying the Adaptive Strategy for Teaching Human Motions

Cited by 11 publications

References 46 publications

CNN-Based Classifier as an Offline Trigger for the CREDO Experiment

CNN-Based Classifier as an Offline Trigger for the CREDO Experiment

Pattern Recognition Methods as a Tool to Build an Automatic System for Learning Coordinated Human Motions

Reform and Practice of Public English Examination Mode in Colleges and Universities Using Big Data Analysis and Speech Recognition

Contact Info

Product

Resources

About