KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Access type: UnknownSubject: search.filters.subject.Feature Extraction

Search Results

Now showing 1 - 6 of 6
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Common Spatial Pattern Variants for Feature Extraction in Multi-Class Motor Imagery BCI
    (2025-01-01)
    Asadi, Fawad
    ;
    Thangthong, Kantham
    ;
    Tungjitkusolmun, Supan
    Brain-Computer Interfaces (BCIs) based on Motor Imagery (MI) offer intuitive control but face challenges due to noisy electroencephalography (EEG) signals that often contain artifacts, necessitating effective feature extraction. Common Spatial Pattern (CSP) is a standard technique, yet its limitations in multi-class MI scenarios motivate various extensions. This paper investigates the classification performance, computational cost, and the crucial performance versus cost trade-off inherent in practical BCI applications of five prominent CSP variants, including standard CSP, Regularized CSP (RCSP), Filter Bank CSP (FBCSP), Sparse CSP, and Kernel CSP, when applied to multi-class MI classification. Using the PhysioNet MI dataset, we employed a consistent preprocessing pipeline (18 sensorimotor channels, filtering, epoching) and evaluated each variant by feeding extracted features into a Support Vector Machine (SVM) classifier with an RBF kernel. The evaluation revealed that standard CSP and RCSP achieved the highest peak average accuracy (~97.8%) with near-efficient computational cost. FBCSP yielded high accuracy (~96.7%) but incurred the highest computational cost. Sparse CSP was computationally efficient but achieved lower peak accuracy (~95.3%), while Kernel CSP showed the lowest peak accuracy (~92.8%) at moderate cost. The findings highlight the performance profiles and efficiency of these CSP methods for this multi-class MI task, indicating that standard CSP and RCSP offer a particularly effective combination of high accuracy and manageable computational load under the evaluated conditions.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    DASSL: Dynamic, AI-assisted, Scalable System for Labelling Used Bottle Images
    (2020-09-21)
    Daengphruan, Parnmet
    ;
    Sangpetch, Orathai
    ;
    Sangpetch, Akkarit
    To ensure sustainable consumption and production, one way is to reduce waste generation by increasing the reuse rate. We have been working with the bottle classification facility to enhance the efficiency and productivity. Many used bottles come in with unimaginable ways of dirty, defective conditions. To manage the sheer volume of used bottles, we create an AI-enabled, bottle classification system. However, it requires many labelled images for training to improve accuracy. Unfortunately, the traditional approach, having human label individual images, is very time consuming. Even worse, it is not effective for our dataset because conditions of used bottles are not well defined and studied. From our experiments, the human experts cannot agree on the same labelling for similar bottle conditions, especially when impurities or defects are not separable objects. For 42%-99% of images in certain subcategories, human experts assign different labels to bottles with similar conditions. With huge inconsistency in data labelling, it deteriorates the accuracy of our classification models. To alleviate this problem, we propose a Dynamic, AI-assisted, Scalable System for Labelling used bottle images, called DASSL. DASSL employs multiple algorithms to extract and/or quantize different features of used bottle images, and cluster the images into groups with the supervision of human. With DASSL, we can achieve labelling consistency and improve scalability by reducing the data labelling time by at least 10x. To enhance agility, we can dynamically adjust DASSL to adapt to changes of cleaning machines' capabilities or bottle demand.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    The Walking Assistance System using the Lower Limb Exoskeleton Suit Commanded by Backpropagation Neural Network
    (2019-01-10)
    Karantarat, Obnithi
    ;
    Kitjaidure, Yuttana
    Currently there are many elderly people who have walking problems. This paper aims to develop and solve these problems by introducing walking assistance system which can recognize 3 types of gestures, include walking, sitting and standing. Our system is divided into 3 main parts including Feature extraction which consists of Time domain and Frequency domain, Classification and Exoskeleton suit system. Conjugate Gradient Backpropagation Neural Network is used to classify sEMG signal of lower limb posture after extracted the features. Then the output of classification is used to command the Exoskeleton suit to perform the gesture according to the results of the recognition. In addition, our paper uses PID controller to control DC motor of Four Bar Linkages Mechanisms of Lower Limb Exoskeleton suit in order to reduce the number of motors and increase stability during the Stance Phase. The results from the experiment have concluded that all feature in time domain has the most recognition rate which up to 99.39%.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    A Novel Feature Extraction for American Sign Language Recognition Using Webcam
    (2019-01-10)
    Thongtawee, Ariya
    ;
    Pinsanoh, Onamon
    ;
    Kitjaidure, Yuttana
    Sign language is physical communication for contributing the meaning instead of using voice to demonstrate communicator's opinion. This paper introduces a simple and efficient algorithm for feature extraction to recognize American Sign Language alphabets from both static and dynamic gestures. The proposed algorithm comprises of four different techniques: Number of white pixels at the edge of the image (NwE), Finger length from the centroid point (Fcen), Angles between fingers (AngF) and Differences of angles between fingers of the first and last frame (delAng). After extracting features from video images, an Artificial Neural Network (ANN) is used to classify the signs. The result of these experiments is achieved up to 95% recognition rate, which is clearly to be the highest accuracy comparing with the other research worked in this field.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    SEMG signal classification using SMO algorithm and singular value decomposition
    (2015-01-01)
    Ruangpaisarn, Yotsapat
    ;
    Jaiyen, Saichon
    Surface Electromyography (sEMG) signal analysis is a challenging task in neuroscience. The signal is associated with an activity of muscles in Human body. It is a part of how human can control the robotic arm for helping people with disabilities. In this paper, we propose a new method based on Singular Value Decomposition (SVD) and SMO algorithm for classifying sEMG signals into six basic hand movements. By this proposed method, SVD is adopted for feature extraction and SMO classifier is used for classifying sEMG signals into six classes of basic hand movements in five subjects. In preliminary experiment, we investigates the number of features that can yield the best performance in the classification and it is found that the optimal number of features is 50. For performance evaluation, five classifiers including Decision Tree, K-nearest neighbor, Naive Bayes, RBF, and SMO, with 10 fold cross-validation technique are adopted. The experimental results have shown that SMO algorithm with V2M-SVD feature extraction can achieve the best performance for the classification of basic hand movements.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Adaptive Histogram of Oriented Gradient for Printed Thai Character Recognition
    (2014-01-01)
    Woraratpanya, Kuntpong
    ;
    Titijaroonroj, Taravichet
    A similarity of printed Thai characters is a grand challenge of optical character recognition (OCR), especially in case of a variety of font types, sizes, and styles. This paper proposes an effective feature extraction, adaptive histogram of oriented gradient (AHOG), for overcoming the character similarity. The proposed method improves the conventional histogram of oriented gradient (HOG) in two principal phases, which are (i) adaptive partition for gradient images and (ii) adaptive binning for oriented histograms. The former is implemented with quadtree partition based on gradient image variance so as to provide for an effective local feature extraction. The later is implemented with non-uniform mapping technique, so that the AHOG descriptor can be constructed with minimal errors. Based on 59,408 single character images equally divided into training and testing samples, the experimental results show that the AHOG method outperforms the conventional HOG and state-of-the-art methods, including scale space histogram of oriented gradient (SSHOG), pyramid histogram of oriented gradient (PHOG), multilevel histogram of oriented gradient (MHOG), and HOG column encoding algorithm (HOG-Column). © Springer International Publishing Switzerland 2014.