Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 9

kNN Related Abstracts

9 Brainwave Classification for Brain Balancing Index (BBI) via 3D EEG Model Using k-NN Technique

Authors: M. E. Marwan, N. Fuad, M. N. Taib, R. Jailani

Abstract:

In this paper, the comparison between k-Nearest Neighbor (kNN) algorithms for classifying the 3D EEG model in brain balancing is presented. The EEG signal recording was conducted on 51 healthy subjects. Development of 3D EEG models involves pre-processing of raw EEG signals and construction of spectrogram images. Then, maximum PSD values were extracted as features from the model. There are three indexes for the balanced brain; index 3, index 4 and index 5. There are significant different of the EEG signals due to the brain balancing index (BBI). Alpha-α (8–13 Hz) and beta-β (13–30 Hz) were used as input signals for the classification model. The k-NN classification result is 88.46% accuracy. These results proved that k-NN can be used in order to predict the brain balancing application.

Keywords: power spectral density, brain balancing, kNN

Procedia PDF Downloads 310
8 Performance Evaluation of Contemporary Classifiers for Automatic Detection of Epileptic EEG

Authors: K. E. Ch. Vidyasagar, M. Moghavvemi, T. S. S. T. Prabhat

Abstract:

Epilepsy is a global problem, and with seizures eluding even the smartest of diagnoses a requirement for automatic detection of the same using electroencephalogram (EEG) would have a huge impact in diagnosis of the disorder. Among a multitude of methods for automatic epilepsy detection, one should find the best method out, based on accuracy, for classification. This paper reasons out, and rationalizes, the best methods for classification. Accuracy is based on the classifier, and thus this paper discusses classifiers like quadratic discriminant analysis (QDA), classification and regression tree (CART), support vector machine (SVM), naive Bayes classifier (NBC), linear discriminant analysis (LDA), K-nearest neighbor (KNN) and artificial neural networks (ANN). Results show that ANN is the most accurate of all the above stated classifiers with 97.7% accuracy, 97.25% specificity and 98.28% sensitivity in its merit. This is followed closely by SVM with 1% variation in result. These results would certainly help researchers choose the best classifier for detection of epilepsy.

Keywords: Epilepsy, classification, ANN, SVM, LDA, kNN, seizure

Procedia PDF Downloads 354
7 Musical Instruments Classification Using Machine Learning Techniques

Authors: Bhalke D. G., Bormane D. S., Kharate G. K.

Abstract:

This paper presents classification of musical instrument using machine learning techniques. The classification has been carried out using temporal, spectral, cepstral and wavelet features. Detail feature analysis is carried out using separate and combined features. Further, instrument model has been developed using K-Nearest Neighbor and Support Vector Machine (SVM). Benchmarked McGill university database has been used to test the performance of the system. Experimental result shows that SVM performs better as compared to KNN classifier.

Keywords: Feature Extraction, SVM, kNN, musical instruments

Procedia PDF Downloads 315
6 Dependence of Dielectric Properties on Sintering Conditions of Lead Free KNN Ceramics Modified With Li-Sb

Authors: K. Chandramani Singh, Radhapiyari Laishram, Roopam Gaur

Abstract:

In order to produce lead free piezoceramics with optimum piezoelectric and dielectric properties, KNN modified with Li+ (as an A site dopant) and Sb5+ (as a B site dopant) (K0.49Na0.49Li0.02) (Nb0.96Sb0.04) O3 (referred as KNLNS in this paper) have been synthesized using solid state reaction method and conventional sintering technique. The ceramics were sintered in the narrow range of 10500C-10900C for 2-3 hours to get precise information about sintering parameters. Detailed study of dependence of microstructural, dielectric and piezoelectric properties on sintering conditions was then carried out. The study suggests that the volatility of the highly hygroscopic KNN ceramics is not only sensitive to sintering temperatures but also to sintering durations. By merely reducing the sintering duration for a given sintering temperature we saw an increase in the density of the samples which was supported by the increase in dielectric constants of the ceramics. And since density directly or indirectly affects almost all the associated properties, other dielectric and piezoelectric properties were also enhanced as we approached towards the most suitable sintering temperature and duration combination.

Keywords: piezoelectric, kNN, dielectric, conventional sintering

Procedia PDF Downloads 259
5 Using Scale Invariant Feature Transform Features to Recognize Characters in Natural Scene Images

Authors: Belaynesh Chekol, Numan Çelebi

Abstract:

The main purpose of this work is to recognize individual characters extracted from natural scene images using scale invariant feature transform (SIFT) features as an input to K-nearest neighbor (KNN); a classification learner algorithm. For this task, 1,068 and 78 images of English alphabet characters taken from Chars74k data set is used to train and test the classifier respectively. For each character image, We have generated describing features by using SIFT algorithm. This set of features is fed to the learner so that it can recognize and label new images of English characters. Two types of KNN (fine KNN and weighted KNN) were trained and the resulted classification accuracy is 56.9% and 56.5% respectively. The training time taken was the same for both fine and weighted KNN.

Keywords: Character Recognition, SIFT, kNN, natural scene image

Procedia PDF Downloads 155
4 FCNN-MR: A Parallel Instance Selection Method Based on Fast Condensed Nearest Neighbor Rule

Authors: Lei Luo, Jun Ma, Jie Yu, Qingbo Wu, Yongqi Ma, Zhengji Liu, Lu Si, Shasha Li

Abstract:

Instance selection (IS) technique is used to reduce the data size to improve the performance of data mining methods. Recently, to process very large data set, several proposed methods divide the training set into some disjoint subsets and apply IS algorithms independently to each subset. In this paper, we analyze the limitation of these methods and give our viewpoint about how to divide and conquer in IS procedure. Then, based on fast condensed nearest neighbor (FCNN) rule, we propose a large data sets instance selection method with MapReduce framework. Besides ensuring the prediction accuracy and reduction rate, it has two desirable properties: First, it reduces the work load in the aggregation node; Second and most important, it produces the same result with the sequential version, which other parallel methods cannot achieve. We evaluate the performance of FCNN-MR on one small data set and two large data sets. The experimental results show that it is effective and practical.

Keywords: Data Reduction, kNN, MapReduce, instance selection

Procedia PDF Downloads 106
3 Lung Cancer Detection and Multi Level Classification Using Discrete Wavelet Transform Approach

Authors: G. Narendra Kumar, V. Veeraprathap, G. S. Harish

Abstract:

Uncontrolled growth of abnormal cells in the lung in the form of tumor can be either benign (non-cancerous) or malignant (cancerous). Patients with Lung Cancer (LC) have an average of five years life span expectancy provided diagnosis, detection and prediction, which reduces many treatment options to risk of invasive surgery increasing survival rate. Computed Tomography (CT), Positron Emission Tomography (PET), and Magnetic Resonance Imaging (MRI) for earlier detection of cancer are common. Gaussian filter along with median filter used for smoothing and noise removal, Histogram Equalization (HE) for image enhancement gives the best results without inviting further opinions. Lung cavities are extracted and the background portion other than two lung cavities is completely removed with right and left lungs segmented separately. Region properties measurements area, perimeter, diameter, centroid and eccentricity measured for the tumor segmented image, while texture is characterized by Gray-Level Co-occurrence Matrix (GLCM) functions, feature extraction provides Region of Interest (ROI) given as input to classifier. Two levels of classifications, K-Nearest Neighbor (KNN) is used for determining patient condition as normal or abnormal, while Artificial Neural Networks (ANN) is used for identifying the cancer stage is employed. Discrete Wavelet Transform (DWT) algorithm is used for the main feature extraction leading to best efficiency. The developed technology finds encouraging results for real time information and on line detection for future research.

Keywords: Artificial Neural Networks, roi, ANN, discrete wavelet transform, DWT, kNN, region of interest, GLCM, k-nearest neighbor, gray-level co-occurrence matrix

Procedia PDF Downloads 1
2 Identification of Breast Anomalies Based on Deep Convolutional Neural Networks and K-Nearest Neighbors

Authors: Ayyaz Hussain, Tariq Sadad

Abstract:

Breast cancer (BC) is one of the widespread ailments among females globally. The early prognosis of BC can decrease the mortality rate. Exact findings of benign tumors can avoid unnecessary biopsies and further treatments of patients under investigation. However, due to variations in images, it is a tough job to isolate cancerous cases from normal and benign ones. The machine learning technique is widely employed in the classification of BC pattern and prognosis. In this research, a deep convolution neural network (DCNN) called AlexNet architecture is employed to get more discriminative features from breast tissues. To achieve higher accuracy, K-nearest neighbor (KNN) classifiers are employed as a substitute for the softmax layer in deep learning. The proposed model is tested on a widely used breast image database called MIAS dataset for experimental purposes and achieved 99% accuracy.

Keywords: Breast Cancer, Mammography, kNN, DCNN

Procedia PDF Downloads 1
1 Convolutional Neural Networks for Feature Extraction and Automated Target Recognition in Synthetic Aperture Radar Images

Authors: Ying Zhao, John Geldmacher, Christopher Yerkes

Abstract:

Advances in the development of deep neural networks and other machine learning algorithms combined with ever more powerful hardware and the huge amount of data available on the internet has led to a revolution in ML research and applications. These advances present massive potential and opportunity for the military applications such as the analysis of Synthetic Aperture Radar (SAR) imagery. Synthetic Aperture Radar imagery is a useful tool capable of capturing high resolution images regardless of cloud coverage and at night. However, there is a limited amount of publicly available SAR data to train a machine learning model. This paper shows how to successfully dissect, modify, and re-architect cross-domain object recognition models such as the VGG-16 model, transfer learning models from the ImageNet, and the k-nearest neighbor (kNN) classifier. The paper demonstrates that the combinations of these factors can significantly and effectively improve the automated object recognition (ATR) of SAR clean and noisy images. The paper shows a potentially inexpensive, accurate, transfer and unsurpervised learning SAR ATR system when data labels are scarce and data are noisy, simplifying the whole recognition for the tactical operation requirements in the area of SAR ATR.

Keywords: Deep learning, Transfer Learning, kNN, SAR images, k-nearest neighbor, synthetic aperture radar images, VGG-16

Procedia PDF Downloads 1