Electrocardiogram Dynamic Interval Feature Extraction for Heartbeat Characterization

2019 ◽  
pp. 242-253
Author(s):  
Atul Kumar Verma ◽  
Indu Saini ◽  
Barjinder Singh Saini
Keyword(s):  
Feature Extraction ◽  
Time Domain ◽  
Nearest Neighbor ◽  
Premature Ventricular Contraction ◽  
Extraction Methods ◽  
Experimental Result ◽  
K Nearest Neighbor ◽  
Bundle Branch Block ◽  
Heartbeat Classification ◽  
Dynamic Time

In the chapter, dynamic time domain features are extracted in the proposed approach for the accurate classification of electrocardiogram (ECG) heartbeats. The dynamic time-domain information such as RR, pre-RR, post-RR, ratio of pre-post RR, and ratio of post-pre RR intervals to be extracted from the ECG beats in proposed approach for heartbeat classification. These four extracted features are combined and fed to k-nearest neighbor (k-NN) classifier with tenfold cross-validation to classify the six different heartbeats (i.e., normal [N], right bundle branch block [RBBB], left bundle branch block [LBBB], atrial premature beat [APC], paced beat [PB], and premature ventricular contraction[PVC]). The average sensitivity, specificity, positive predictivity along with overall accuracy is obtained as 99.77%, 99.97%, 99.71%, and 99.85%, respectively, for the proposed classification system. The experimental result tells that proposed classification approach has given better performance as compared with other state-of-the-art feature extraction methods for the heartbeat characterization.

scholarly journals Pengenalan Wajah Menggunakan Metode Linear Discriminant Analysis dan k Nearest Neighbor

2017 ◽  
Vol 9 (1) ◽  
pp. 1-9
Author(s):  
Fandiansyah Fandiansyah ◽  
Jayanti Yusmah Sari ◽  
Ika Putri Ningrum
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Nearest Neighbor ◽  
Experimental Result ◽  
K Nearest Neighbor ◽  
Linear Discriminant ◽  
Nearest Neighbor Classifier ◽  
Neighbor Classifier

Face recognition is one of the biometric system that mostly used for individual recognition in the absent machine or access control. This is because the face is the most visible part of human anatomy and serves as the first distinguishing factor of a human being. Feature extraction and classification are the key to face recognition, as they are to any pattern classification task. In this paper, we describe a face recognition method based on Linear Discriminant Analysis (LDA) and k-Nearest Neighbor classifier. LDA used for feature extraction, which directly extracts the proper features from image matrices with the objective of maximizing between-class variations and minimizing within-class variations. The features of a testing image will be compared to the features of database image using K-Nearest Neighbor classifier. The experiments in this paper are performed by using using 66 face images of 22 different people. The experimental result shows that the recognition accuracy is up to 98.33%. Index Terms—face recognition, k nearest neighbor, linear discriminant analysis.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 2 (3) ◽  
pp. 35
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 5 (1) ◽  
pp. 35 ◽  
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 2 (3) ◽  
pp. 35
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

scholarly journals Automated Hertbeat Abnormality Detection Using Realtime R-Assisted Lightweight Feature Extraction Algorithm

2018 ◽  
Author(s):  
Diptangshu Pandit ◽  
Chengyu Liu ◽  
Li Zhang
Keyword(s):  
Feature Extraction ◽  
Classification Scheme ◽  
Nearest Neighbor ◽  
Abnormality Detection ◽  
K Nearest Neighbor ◽  
Heartbeat Classification ◽  
Ecg Signals ◽  
Feature Extraction Algorithm ◽  
Extraction Algorithm ◽  
Electrocardiogram Ecg

Automated Electrocardiogram (ECG) processing is an important technique which helps in identifying abnormalities in the heart before any formal diagnosis. This research presents a real-time and lightweight R-assisted feature extraction algorithm and a heartbeat classification scheme which achieves highly accurate abnormality detection. In the proposed algorithm, we extract fifteen features from each heartbeat taken from raw Lead-II ECG signals. The features carry medically valuable information such as locations, amplitude and energy of ECG waves (P, Q, R, S, T waves) which are then used for detection of any abnormality that might be present in the heartbeat using various classification algorithms. We have used four popular databases from Physionet and extracted ten thousand ECG signals from each for training the models and benchmarking results. Four classification models i.e. Naïve Bays, k-Nearest Neighbor, Neural Network, Decision Tree were used for abnormality detection validating the efficiency of the system.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 2 (3) ◽  
pp. 35 ◽  
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

scholarly journals PENGENALAN CITRA RAMBU LALU LINTAS MENGGUNAKAN EKSTRAKSI FITUR MOMENWARNA DAN K-NEAREST NEIGHBOR

2019 ◽  
Vol 3 (1) ◽  
pp. 39
Author(s):  
Rusma Eko Fiddy Rizarta ◽  
Donny Avianto
Keyword(s):  
Feature Extraction ◽  
Nearest Neighbor ◽  
Histogram Equalization ◽  
Extraction Methods ◽  
Feature Representation ◽  
K Nearest Neighbor ◽  
Traffic Signs ◽  
Road Users ◽  
Road Sign ◽  
Spatial Moment

The traffic signs are signs with specific shape and symbols, letters, numbers, or words which have the aim to warn or inform the road users. However, there are many road users who are not aware of the meaning of each signs. In this research, we develop an application which can classify a road sign image into three classes, priority four-way crossroad, do-not-park sign, and follow-this-road sign. Initially, the system will do preprocessing step such as grays calling, histogram equalization, and input image segmentation. Next, the feature extraction step will be conducted, namely the spatial moment feature extraction, normalized centering, and color statistics. Lastly, the feature representation from both extraction methods will be used to classify the image using K-nearest neighbor. Experiment result shows that the combination of both feature extraction methods gives promising result. From 21 training images and 15 testing images, the system can recognize the traffic signs with 100% accuracy with K=3, 86.6% with K=5, and 86.6% with K=7. Rambu lalu lintas merupakan salah satu alat perlengkapan jalan dalam bentuk tertentu yang memuat lambang, huruf, angka, kalimat yang digunakan untuk memberikan perintah, larangan, peringatan dan petunjuk bagi pengguna jalan agar tertib berlalu lintas. Namun, banyak di antara pengguna jalan yang belum mengetahui arti dari setiap rambu lalu lintas yang terpasang.Pada penelitian ini, dibuatlah suatu aplikasi yang mampu melakukan klasifikasi citra rambu ke dalam 3 kelas yaitu: peringatan simpang empat prioritas, larangan parkir dan perintah memasuki jalur atau lajur yang ditunjuk. Mula-mula sistem akan melakukan prapemrosesan seperti seperti: grayscalling, histogram equalization, dan segmentasi pada citra input. Selanjutnya, tahap ekstraksi ciri akan dilakukan pada citra hasil pra-pemrosesan. Adapun metode ekstraksi ciri yang digunakan pada penelitian kali ini adalah ekstraksi fitur momen spasial dan pusat ternormalisai (momen) dan ekstraksi fitur statistika warna (warna). Terakhir, nilai fitur yang dihasilkan oleh kedua metode tersebut akan diklasifikasi mengguakan K-Nearest Neighbor. Hasil uji coba menunjukkan bahwa metode ekstraksi fitur gabungan momen-warna memberikan hasil yang menjanjikan. Dari 21 citra latih dan 15 citra uji yang digunakan, sistem mampu mengenali rambu dengan tepat 100% pada K=3 , 86,6% pada K=5, dan 86,6% pada K=7. 

Handwritten Balinesse Character Recognition using K-Nearest Neighbor

2018 ◽  
Author(s):  
I Wayan Agus Surya Darma
Keyword(s):  
Feature Extraction ◽  
Success Rate ◽  
Character Recognition ◽  
Nearest Neighbor ◽  
Recognition System ◽  
Extraction Process ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
K Nearest Neighbor Algorithm ◽  
Character Feature

Balinese character recognition is a technique to recognize feature or pattern of Balinese character. Feature of Balinese character is generated through feature extraction process. This research using handwritten Balinese character. Feature extraction is a process to obtain the feature of character. In this research, feature extraction process generated semantic and direction feature of handwritten Balinese character. Recognition is using K-Nearest Neighbor algorithm to recognize 81 handwritten Balinese character. The feature of Balinese character images tester are compared with reference features. Result of the recognition system with K=3 and reference=10 is achieved a success rate of 97,53%.

scholarly journals A Comparative Survey of Feature Extraction and Machine Learning Methods in Diverse Acoustic Environments

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1274
Author(s):  
Daniel Bonet-Solà ◽  
Rosa Ma Alsina-Pagès
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Best Practice ◽  
Nearest Neighbor ◽  
Gaussian Mixture ◽  
Machine Learning Algorithms ◽  
Multimedia Retrieval ◽  
Natural Environments ◽  
K Nearest Neighbor ◽  
Acoustic Environments

Acoustic event detection and analysis has been widely developed in the last few years for its valuable application in monitoring elderly or dependant people, for surveillance issues, for multimedia retrieval, or even for biodiversity metrics in natural environments. For this purpose, sound source identification is a key issue to give a smart technological answer to all the aforementioned applications. Diverse types of sounds and variate environments, together with a number of challenges in terms of application, widen the choice of artificial intelligence algorithm proposal. This paper presents a comparative study on combining several feature extraction algorithms (Mel Frequency Cepstrum Coefficients (MFCC), Gammatone Cepstrum Coefficients (GTCC), and Narrow Band (NB)) with a group of machine learning algorithms (k-Nearest Neighbor (kNN), Neural Networks (NN), and Gaussian Mixture Model (GMM)), tested over five different acoustic environments. This work has the goal of detailing a best practice method and evaluate the reliability of this general-purpose algorithm for all the classes. Preliminary results show that most of the combinations of feature extraction and machine learning present acceptable results in most of the described corpora. Nevertheless, there is a combination that outperforms the others: the use of GTCC together with kNN, and its results are further analyzed for all the corpora.

scholarly journals A novel content based image retrieval system using K-means/KNN with feature extraction

2012 ◽  
Vol 9 (4) ◽  
pp. 1645-1661 ◽  
Author(s):  
Ray-I Chang ◽  
Shu-Yu Lin ◽  
Jan-Ming Ho ◽  
Chi-Wen Fann ◽  
Yu-Chun Wang
Keyword(s):  
Feature Extraction ◽  
Image Retrieval ◽  
Nearest Neighbor ◽  
Clustering Algorithms ◽  
Content Based Image Retrieval ◽  
K Nearest Neighbor ◽  
Color Analysis ◽  
Image Retrieval System ◽  
First Time ◽  
System Designs

Image retrieval has been popular for several years. There are different system designs for content based image retrieval (CBIR) system. This paper propose a novel system architecture for CBIR system which combines techniques include content-based image and color analysis, as well as data mining techniques. To our best knowledge, this is the first time to propose segmentation and grid module, feature extraction module, K-means and k-nearest neighbor clustering algorithms and bring in the neighborhood module to build the CBIR system. Concept of neighborhood color analysis module which also recognizes the side of every grids of image is first contributed in this paper. The results show the CBIR systems performs well in the training and it also indicates there contains many interested issue to be optimized in the query stage of image retrieval.

Sign in / Sign up

Export Citation Format

Share Document