Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: K-nearest neighbour

Sortuj według:

Ogranicz wyniki do:

Classification of mild and severe adolescent idiopathic scoliosis (AIS) from healthy subjects via a supervised learning model based on electromyogram and ground reaction force data during gait

Sikidar Arnab, Vidyasagar Koyyana Eshwar Chandra, Gupta Manish, Garg Bhavuk, Kalyanasundaram Dinesh

Biocybernetics and Biomedical Engineering

2022

Vol. 42, no. 3

870--887

At early stages, adolescent idiopathic scoliosis (AIS) is quite hard to be distinguished from healthy (HC) subjects by the naked eye. AIS demands multiple corrective surgeries when detected later, thereby causing significant physical and psychological trauma as no mathematical models exist for the classification of mild AIS (MS) (20° < Cobb’s angle < 40°) from HC, we propose a k-nearest neighbour (kNN) method based model. In this work, we collected both the EMG and GRF data from nine severe AIS (SS), three MS and four female HC during gait. Delayed muscle activation in Erector spinatus Iliocostalis, Gluteus Medius and Gastrocnemius lateralis was observed in SS compared to HC. However, no such distinction was noticed between MS and HC motivating for a mathematical model. Eighteen time-domain and nine frequency-domain features were computed from the EMG data of 14 lower extremity muscles, while five time-domain features were calculated from GRF data during gait. Out of all the features computed for each subject, the principal component analysis (PCA) yielded 15 principal components that coupled both time and frequency domains (TFD). Further, the kNN model classified SS, MS and HC from each other by these 15 TFD features. The model was trained and validated using 32 and 21 EMG and GRF data datasets during gait, respectively. The classification and validation accuracy of 90.6% and 85.7% were obtained among SS, MS and HC. The proposed model is capable of early detection of AIS and can be used by medical professionals to plan treatments and corrective measures.

Voice Command Recognition Using Hybrid Genetic Algorithm

Wroniszewska M., Dziedzic J.

TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk

2010

Vol. 14, No 4

377-396

Speech recognition is a process of converting the acoustic signal into a set of words, whereas voice command recognition consists in the correct identification of voice commands, usually single words. Voice command recognition systems are widely used in the military, control systems, electronic devices, such as cellular phones, or by people with disabilities (e.g., for controlling a wheelchair or operating a computer system). This paper describes the construction of a model for a voice command recognition system based on the combination of genetic algorithms (GAs) and K-nearest neighbour classifier (KNN). The model consists of two parts. The first one concerns the creation of feature patterns from spoken words. This is done by means of the discrete Fourier transform and frequency analysis. The second part constitutes the essence of the model, namely the design of the supervised learning and classification system. The technique used for the classification task is based on the simplest classifier – K-nearest neighbour algorithm. GAs, which have been demonstrated as a good optimization and machine learning technique, are applied to the feature extraction process for the pattern vectors. The purpose and main interest of this work is to adapt such a hybrid approach to the task of voice command recognition, develop an implementation and to assess its performance. The complete model of the system was implemented in the C++ language, the implementation was subsequently used to determine the relevant parameters of the method and to improve the approach in order to obtain the desired accuracy. Different variants of GAs were surveyed in this project and the influence of particular operators was verified in terms of the classification success rate. The main finding from the performed numerical experiments indicates the necessity of using genetic algorithms for the learning process. In consequence, a highly accurate recognition system was obtained, providing 94.2% correctly classified patterns. The hybrid GA/KNN approach constituted a significant improvement over the simple KNN classifier. Moreover, the training time required for the GA to learn the given set of words was found to be on a level that is acceptable for the efficient functioning of the voice command recognition system.