scholarly journals K-NN Classification of Brain Dominance

2018 ◽  
Vol 8 (4) ◽  
pp. 2494
Author(s):  
Khairul Amrizal Abu Nawas ◽  
Mahfuzah Mustafa ◽  
Rosdiyana Samad ◽  
Dwi Pebrianti ◽  
Nor Rul Hasma Abdullah
Keyword(s):  
Wavelet Analysis ◽  
Nearest Neighbor ◽  
Gabor Wavelet ◽  
Image Feature ◽  
Band Pass Filter ◽  
K Nearest Neighbor ◽  
Brain Dominance ◽  
Pass Filter ◽  
Band Frequency ◽  
The Brain

<span>The brain dominance is referred to right brain and left brain. The brain dominance can be observed with an Electroencephalogram (EEG) signal to identify different types of electrical pattern in the brain and will form the foundation of one’s personality. The objective of this project is to analyze brain dominance by using Wavelet analysis. The Wavelet analysis is done in 2-D Gabor Wavelet and the result of 2-D Gabor Wavelet is validated with an establish brain dominance questionnaire. Twenty-one samples from University Malaysia Pahang (UMP) student are required to answer the establish brain dominance questionnaire has been collected in this experiment. Then, brainwave signal will record using Emotiv device. The threshold value is used to remove the artifact and noise from data collected to acquire a smoother signal. Next, the Band-pass filter is applied to the signal to extract the sub-band frequency components from Delta, Theta, Alpha, and Beta. After that, it will extract the energy of the signal from image feature extraction process. Next the features were classified by using K-Nearest Neighbor (K-NN) in two ratios which 70:30 and 80:20 that are training set and testing set (training: testing). The ratio of 70:30 gave the highest percentage of 83% accuracy while a ratio of 80:20 gave 100% accuracy. The result shows that 2-D Gabor Wavelet was able to classify brain dominance with accuracy 83% to 100%.</span>

scholarly journals Conditional Entropy: A Potential Digital Marker for Stress

Entropy ◽  
2021 ◽  
Vol 23 (3) ◽  
pp. 286
Author(s):  
Soheil Keshmiri
Keyword(s):  
Resting State ◽  
Nearest Neighbor ◽  
Brain Activity ◽  
Solution Concept ◽  
Conditional Entropy ◽  
K Nearest Neighbor ◽  
Brain Response ◽  
Substantial Progress ◽  
Eeg Recordings ◽  
The Brain

Recent decades have witnessed a substantial progress in the utilization of brain activity for the identification of stress digital markers. In particular, the success of entropic measures for this purpose is very appealing, considering (1) their suitability for capturing both linear and non-linear characteristics of brain activity recordings and (2) their direct association with the brain signal variability. These findings rely on external stimuli to induce the brain stress response. On the other hand, research suggests that the use of different types of experimentally induced psychological and physical stressors could potentially yield differential impacts on the brain response to stress and therefore should be dissociated from more general patterns. The present study takes a step toward addressing this issue by introducing conditional entropy (CE) as a potential electroencephalography (EEG)-based resting-state digital marker of stress. For this purpose, we use the resting-state multi-channel EEG recordings of 20 individuals whose responses to stress-related questionnaires show significantly higher and lower level of stress. Through the application of representational similarity analysis (RSA) and K-nearest-neighbor (KNN) classification, we verify the potential that the use of CE can offer to the solution concept of finding an effective digital marker for stress.

Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB

2021 ◽  
Vol 5 (4) ◽  
pp. 783-793
Author(s):  
Muhammad Muttabi Hudaya ◽  
Siti Saadah ◽  
Hendy Irawan
Keyword(s):  
Image Matching ◽  
Nearest Neighbor ◽  
Feature Matching ◽  
Image Feature ◽  
Brute Force ◽  
K Nearest Neighbor ◽  
Matching Method ◽  
Average Precision ◽  
Detection Model ◽  
Matching Process

needs a solid validation that has verification and matching uploaded images. To solve this problem, this paper implementing a detection model using Faster R-CNN and a matching method using ORB (Oriented FAST and Rotated BRIEF) and KNN-BFM (K-Nearest Neighbor Brute Force Matcher). The goal of the implementations is to reach both an 80% mark of accuracy and prove matching using ORB only can be a replaced OCR technique. The implementation accuracy results in the detection model reach mAP (Mean Average Precision) of 94%. But, the matching process only achieves an accuracy of 43,46%. The matching process using only image feature matching underperforms the previous OCR technique but improves processing time from 4510ms to 60m). Image matching accuracy has proven to increase by using a high-quality dan high quantity dataset, extracting features on the important area of EKTP card images.

scholarly journals Design and Realization of Band Pass Filter in K-Band Frequency for Short Range Radar Application

2021 ◽  
Vol 21 (1) ◽  
pp. 1
Author(s):  
Arie Setiawan ◽  
Taufiqqurrachman Taufiqqurrachman ◽  
Adam Kusumah Firdaus ◽  
Fajri Darwis ◽  
Aminuddin Rizal ◽  
...  
Keyword(s):  
Insertion Loss ◽  
Short Range ◽  
Return Loss ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Band Frequency ◽  
Measurement Results ◽  
Band Pass ◽  
Bandwidth Analysis ◽  
K Band

Short range radar (SRR) uses the K-band frequency range in its application. The radar requires high-resolution, so the applied frequency is 1 GHz wide. The filter is one of the devices used to ensure only a predetermined frequency is received by the radar system. This device must have a wide operating bandwidth to meet the specification of the radar. In this paper, a band pass filter (BPF) is proposed. It is designed and fabricated on RO4003C substrate using the substrate integrated waveguide (SIW) technique, results in a wide bandwidth at the K-band frequency that centered at 24 GHz. Besides the bandwidth analysis, the analysis of the insertion loss, the return loss, and the dimension are also reported. The simulated results of the bandpass filter are: VSWR of 1.0308, a return loss of -36.9344 dB, and an insertion loss of -0.6695 dB. The measurement results show that the design obtains a VSWR of 2.067, a return loss of -8.136 dB, and an insertion loss of -4.316  dB. While, it is obtained that the bandwidth is reduced by about 50% compared with the simulation. The result differences between simulation and measurement are mainly due to the imperfect fabrication process.

Improved Elastic Model Matching Algorithm for Facial Expression Recognition

2013 ◽  
Vol 397-400 ◽  
pp. 2143-2147
Author(s):  
Wen Dong Zhao ◽  
Jie Zhang ◽  
You Dong Zhang
Keyword(s):  
Nearest Neighbor ◽  
Detection Algorithm ◽  
Gabor Wavelet ◽  
Similar Degree ◽  
Elastic Model ◽  
Expression Recognition ◽  
Model Matching ◽  
K Nearest Neighbor ◽  
Matching Algorithm ◽  
Expression Template

Key frames detected in Video stream contain sufficient expression information. In order to classify and recognize these expression information, a new elastic model matching algorithm is proposed in this paper. Firstly, expression template is transformed by Gabor wavelet , and the detection algorithm of the key expression in the template image is used. According to the feature information of the key expression, structure expression elastic graph, then by changing the key location in the expression template graph and doing non-rigid match of the expression template and expression elastic graph which is measured, so that similar degree between them is got. Finally, by improving the K-nearest neighbor classification strategy, the effective classification and recognition of measured image expression is achieved.

scholarly journals Writer Identification Based on Arabic Handwriting Recognition by using Speed Up Robust Feature and K- Nearest Neighbor Classification

2019 ◽  
Vol 27 (1) ◽  
pp. 1-10
Author(s):  
Alia Karim Abdul Hassan ◽  
Bashar Saadoon Mahdi ◽  
Asmaa Abdullah Mohammed
Keyword(s):  
Feature Extraction ◽  
Nearest Neighbor ◽  
Recognition Rate ◽  
Image Feature ◽  
Writer Identification ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Classification ◽  
Speed Up ◽  
Speed Up Robust Feature ◽  
Neighbor Classification

In a writer recognition system, the system performs a “one-to-many” search in a large database with handwriting samples of known authors and returns a possible candidate list. This paper proposes method for writer identification handwritten Arabic word without segmentation to sub letters based on feature extraction speed up robust feature transform (SURF) and K nearest neighbor classification (KNN) to enhance the writer's  identification accuracy. After feature extraction, it can be cluster by K-means algorithm to standardize the number of features. The feature extraction and feature clustering called to gather Bag of Word (BOW); it converts arbitrary number of image feature to uniform length feature vector. The proposed method experimented using (IFN/ENIT) database. The recognition rate of experiment result is (96.666).

scholarly journals Classification of Concentration Levels in Adult-Early Phase using Brainwave Signals by Applying K-Nearest Neighbor

2019 ◽  
Vol 1 (1) ◽  
pp. 14-24
Author(s):  
Ahmad Azhari ◽  
Fathia Irbati Ammatulloh
Keyword(s):  
Early Phase ◽  
Nearest Neighbor ◽  
Concentration Level ◽  
Cognitive Activity ◽  
Statistical Characteristics ◽  
K Nearest Neighbor ◽  
Mental Action ◽  
The Brain ◽  
Concentration Levels

The brain controls the center of human life. Through the brain, all activities of living can be done. One of them is cognitive activity. Brain performance is influenced by mental conditions, lifestyle, and age. Cognitive activity is an observation of mental action, so it includes psychological symptoms that involve memory in the brain's memory, information processing, and future planning. In this study, the concentration level was measured at the age of the adult-early phase (18-30 years) because in this phase, the brain thinks more abstractly and mental conditions influence it. The purpose of this study was to see the level of concentration in the adult-early phase with a stimulus in the form of cognitive activity using IQ tests with the type of Standard Progressive Matrices (SPM) tests. To find out the IQ test results require a long time, so in this study, a recording was done to get brain waves so that the results of the concentration level can be obtained quickly.EEG data was taken using an Electroencephalogram (EEG) by applying the SPM test as a stimulus. The acquisition takes three times for each respondent, with a total of 10 respondents. The method implemented in this study is a classification with the k-Nearest Neighbor (kNN) algorithm. Before using this method, preprocessing is done first by reducing the signal and filtering the beta signal (13-30 Hz).The results of the data taken will be extracted first to get the right features, feature extraction in this study using first-order statistical characteristics that aim to find out the typical information from the signals obtained. The results of this study are the classification of concentration levels in the categories of high, medium, and low. Finally, the results of this study show an accuracy rate of 70%.

scholarly journals A Customized VGG19 Network with Concatenation of Deep and Handcrafted Features for Brain Tumor Detection

2020 ◽  
Vol 10 (10) ◽  
pp. 3429 ◽  
Author(s):  
Venkatesan Rajinikanth ◽  
Alex Noel Joseph Raj ◽  
Krishnan Palani Thanaraj ◽  
Ganesh R. Naik
Keyword(s):  
Brain Tumor ◽  
Nearest Neighbor ◽  
Detection Accuracy ◽  
K Nearest Neighbor ◽  
Clinical Images ◽  
Softmax Classifier ◽  
Clinical Level ◽  
Bio Imaging ◽  
The Brain ◽  
Fold Cross Validation

Brain tumor (BT) is one of the brain abnormalities which arises due to various reasons. The unrecognized and untreated BT will increase the morbidity and mortality rates. The clinical level assessment of BT is normally performed using the bio-imaging technique, and MRI-assisted brain screening is one of the universal techniques. The proposed work aims to develop a deep learning architecture (DLA) to support the automated detection of BT using two-dimensional MRI slices. This work proposes the following DLAs to detect the BT: (i) implementing the pre-trained DLAs, such as AlexNet, VGG16, VGG19, ResNet50 and ResNet101 with the deep-features-based SoftMax classifier; (ii) pre-trained DLAs with deep-features-based classification using decision tree (DT), k nearest neighbor (KNN), SVM-linear and SVM-RBF; and (iii) a customized VGG19 network with serially-fused deep-features and handcrafted-features to improve the BT detection accuracy. The experimental investigation was separately executed using Flair, T2 and T1C modality MRI slices, and a ten-fold cross validation was implemented to substantiate the performance of proposed DLA. The results of this work confirm that the VGG19 with SVM-RBF helped to attain better classification accuracy with Flair (>99%), T2 (>98%), T1C (>97%) and clinical images (>98%).

Sign in / Sign up

Export Citation Format

Share Document