scholarly journals Cervical Cancer Cell Identification & Detection Using Fuzzy C Mean and K nearest Neighbor Techniques

2019 ◽  
Vol 8 (10) ◽  
pp. 1080-1084
Keyword(s):  
Cervical Cancer ◽  
Nearest Neighbor ◽  
Processing Technique ◽  
Image Processing Technique ◽  
Shape Features ◽  
K Nearest Neighbor ◽  
Learning Skills ◽  
Color Features ◽  
High Level ◽  
Morphology Changes

Across the globe, woman has been diagnosed two major forms of cancer, in which one is identified as cervical cancer and its micro classification. Morphology changes in cells or dead nucleus in the cervix causes cervical cancer. These cells are characterized with multiple nucleuses, faulty & lack of cytoplasm and so on. Detection of cervical cancer using smear test is extremely challenging because such cells does not offer texture variations or any significant color from the normal cells. Therefore for identification in abnormality of cells we required high level Digital image processing technique which compromises an automated, comprehensive machine learning skills. An advanced Fuzzy based technique has been implied to separate nucleus and cytoplasm from the cell. KNN is instructed with the color features and shape features of the segmented units of the cell and then an unknown cervix cell samples are classified by this technique. The proposed technique gives shape and color features of nucleus and cytoplasm of the cervix cell.

scholarly journals Klasifikasi Sel Darah Putih Berdasarkan Ciri Warna dan Bentuk dengan Metode K-Nearest Neighbor (K-NN)

2016 ◽  
Vol 6 (2) ◽  
pp. 151 ◽  
Author(s):  
Mizan Nur Khasanah ◽  
Agus Harjoko ◽  
Ika Candradewi
Keyword(s):  
Image Processing ◽  
Blood Cells ◽  
Nearest Neighbor ◽  
White Blood Cells ◽  
Processing Technique ◽  
Image Processing Technique ◽  
K Nearest Neighbor ◽  
Traditional Procedure ◽  
Early Diagnose

The traditional procedure of classification of blood cells using a microscope in the laboratory of hematology to obtain information types of blood cells. It has become a cornerstone in the laboratory of hematology to diagnose and monitor hematologic disorders. However, the manual procedure through a series of labory test can take a while. Thresfore, this research can be helpful in the early stages of the classification of white blood cells automatically in the medical field.Efforts to overcome the length of time and for the purposes of early diagnose can use the image processing technique based on morphology of blood cells. This research aims to classify the white blood cells based on cell morphology with the k-nearest neighbor (knn). Image processing algorithms used hough circle, thresholding, feature extraction, then to the process of classification was used the method of k-nearest neighbor (knn).In the process of testing used 100 images to be aware of its kind. The test results showed segmentation accuracy of 78% and testing the classification of 64%.

scholarly journals Detection of Cataract Through Feature Extraction by the Novel Angular Binary Pattern (NABP) and Classification by Kernel Based Convolutional Neural Networks

2021 ◽  
Author(s):  
A Sirajudeen ◽  
Anuradha balasubramaniam ◽  
S Karthikeyan
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Convolutional Neural Networks ◽  
Texture Features ◽  
Processing Technique ◽  
Image Processing Technique ◽  
The Novel ◽  
Shape Features ◽  
Visual Interpretation ◽  
Color Features

Abstract Cataract is a condition of the opacity in the lenticular regions, which usually results in bad visual interpretation of the viewed object or any entity. Hence the timely detection of cataract is considered to be significant and can even contribute in the prevention from loss of fight that might occur if the cataract is left untreated. In this paper, detection of cataract disease is carried out based on the image processing technique. Color features, texture features and shape features are extracted separately. This study proposed a Novel Angular Binary Pattern (NABP) for the extraction of texture features. And after the extraction of features, the images are subjected to classification through the implementation of the proposed novel Kernel Based Convolutional Neural Networks. Results are obtained separately for all the three types of features. A comparison is carried out for the proposed work with existing works and based on the results obtained it can be seen that the proposed work comes up with the enhanced results than the traditional methods.

scholarly journals KLASIFIKASI PENGGUNAAN PROTOKOL KOMUNIKASI PADA TRAFIK JARINGAN MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR

2016 ◽  
Vol 16 (1) ◽  
pp. 67
Author(s):  
Komang Kompyang Agus Subrata ◽  
I Made Oka Widyantara ◽  
Linawati Linawati
Keyword(s):  
Quality Of Service ◽  
Network Traffic ◽  
Network Architecture ◽  
Nearest Neighbor ◽  
Computer Network ◽  
Data Communication ◽  
Data Capture ◽  
K Nearest Neighbor ◽  
High Level

ABSTRACT—Network traffic internet is data communication in a network characterized by a set of statistical flow with the application of a structured pattern. Structured pattern in question is the information from the packet header data. Proper classification to an Internet traffic is very important to do, especially in terms of the design of the network architecture, network management and network security. The analysis of computer network traffic is one way to know the use of the computer network communication protocol, so it can be the basis for determining the priority of Quality of Service (QoS). QoS is the basis for giving priority to analyzing the network traffic data. In this study the classification of the data capture network traffic that though the use of K-Neaerest Neighbor algorithm (K-NN). Tools used to capture network traffic that wireshark application. From the observation of the dataset and the network traffic through the calculation process using K-NN algorithm obtained a result that the value generated by the K-NN classification has a very high level of accuracy. This is evidenced by the results of calculations which reached 99.14%, ie by calculating k = 3. Intisari—Trafik jaringan internet adalah lalu lintas ko­mu­nikasi data dalam jaringan yang ditandai dengan satu set ali­ran statistik dengan penerapan pola terstruktur. Pola ter­struktur yang dimaksud adalah informasi dari header paket data. Klasifikasi yang tepat terhadap sebuah trafik internet sa­ngat penting dilakukan terutama dalam hal disain perancangan arsitektur jaringan, manajemen jaringan dan keamanan jari­ngan. Analisa terhadap suatu trafik jaringan komputer meru­pakan salah satu cara mengetahui penggunaan protokol komu­nikasi jaringan komputer, sehingga dapat menjadi dasar pe­nen­tuan prioritas Quality of Service (QoS). Dasar pemberian prio­ritas QoS adalah dengan penganalisaan terhadap data trafik jaringan. Pada penelitian ini melakukan klasifikasi ter­hadap data capture trafik jaringan yang di olah menggunakan Algoritma K-Neaerest Neighbor (K-NN). Apli­kasi yang digu­nakan untuk capture trafik jaringan yaitu aplikasi wireshark. Hasil observasi terhadap dataset trafik jaringan dan melalui proses perhitungan menggunakan Algoritma K-NN didapatkan sebuah hasil bahwa nilai yang dihasilkan oleh klasifikasi K-NN memiliki tingkat keakuratan yang sangat tinggi. Hal ini dibuktikan dengan hasil perhi­tungan yang mencapai nilai 99,14 % yaitu dengan perhitungan k = 3. DOI: 10.24843/MITE.1601.10

scholarly journals Character Recognition And Extraction of An Indian State License Plates Using K-NN

2019 ◽  
Author(s):  
Rajasekhar Ponakala ◽  
Hari Krishna Adda ◽  
Ch. Aravind Kumar ◽  
Kavya Avula ◽  
K. Anitha Sheela
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Nearest Neighbor ◽  
Extraction Process ◽  
License Plate ◽  
K Nearest Neighbor ◽  
Open Hardware ◽  
Character Extraction ◽  
Indian State ◽  
High Level

License plate recognition is an application-specific optimization in Optical Character Recognition (OCR) software which enables computer systems to read automatically the License Plates of vehicles from digital images. This thesis discusses the character extraction from the respective License Plates of vehicles and problems in the character extraction process. An OCR based training algorithm named k-nearest neighbor with predefined OpenCV libraries is implemented and evaluated in the BeagleBone Black Open Hardware. In an OCR, the character extraction involves certain steps which include Image acquisition, Pre-processing, Feature extraction, Detection/ Segmentation, High-level processing, Decision making. A key advantage of the method is that it is a fairly straightforward technique which utilizes from k-nearest neighbor algorithm segments normalized result as a format in text. The results show that training an image with this algorithm gives better results when compared with other algorithms.

scholarly journals A Perspective View of Cotton Leaf Image Classification Using Machine Learning Algorithms Using WEKA

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Bhagya M. Patil ◽  
Vishwanath Burkpalli
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Texture Features ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Cotton Leaf ◽  
K Nearest Neighbor ◽  
Color Features ◽  
Leaf Image

Cotton is one of the major crops in India, where 23% of cotton gets exported to other countries. The cotton yield depends on crop growth, and it gets affected by diseases. In this paper, cotton disease classification is performed using different machine learning algorithms. For this research, the cotton leaf image database was used to segment the images from the natural background using modified factorization-based active contour method. First, the color and texture features are extracted from segmented images. Later, it has to be fed to the machine learning algorithms such as multilayer perceptron, support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor. Four color features and eight texture features were extracted, and experimentation was done using three cases: (1) only color features, (2) only texture features, and (3) both color and texture features. The performance of classifiers was better when color features are extracted compared to texture feature extraction. The color features are enough to classify the healthy and unhealthy cotton leaf images. The performance of the classifiers was evaluated using performance parameters such as precision, recall, F-measure, and Matthews correlation coefficient. The accuracies of classifiers such as support vector machine, Naïve Bayes, Random Forest, AdaBoost, and K-nearest neighbor are 93.38%, 90.91%, 95.86%, 92.56%, and 94.21%, respectively, whereas that of the multilayer perceptron classifier is 96.69%.

scholarly journals Classification of EEG Signals using Nonlinear Features and Preprocessing Techniques

2021 ◽  
Vol 10 (5) ◽  
pp. 297-301
Author(s):  
Saneesh Cleatus T ◽  
Dr. Thungamani M
Keyword(s):  
Brain Tumor ◽  
Nearest Neighbor ◽  
Processing Technique ◽  
Support Vector ◽  
Statistical Features ◽  
K Nearest Neighbor ◽  
Eeg Signals ◽  
Mode Decomposition ◽  
Nonlinear Features

In this paper we study the effect of nonlinear preprocessing techniques in the classification of electroencephalogram (EEG) signals. These methods are used for classifying the EEG signals captured from epileptic seizure activity and brain tumor category. For the first category, preprocessing is carried out using elliptical filters, and statistical features such as Shannon entropy, mean, standard deviation, skewness and band power. K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) were used for the classification. For the brain tumor EEG signals, empirical mode decomposition is used as a pre-processing technique along with standard statistical features for the classification of normal and abnormal EEG signals. For epileptic signals we have achieved an average accuracy of 94% for a three-class classification and for brain tumor signals we have achieved a classification accuracy of 98% considering it as a two class problem.

Building a predictive model to assist in the diagnosis of cervical cancer

2021 ◽  
Author(s):  
Emmanuel Kwateng Drokow ◽  
Adu Asare Baffour ◽  
Clement Yaw Effah ◽  
Clement Agboyibor ◽  
Gloria Selorm Akpabla ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Nearest Neighbor ◽  
Learning Models ◽  
K Nearest Neighbor ◽  
Effective Technique ◽  
Ensemble Technique ◽  
Cervical Cancer Risk ◽  
Average Accuracy ◽  
The World ◽  
Machine Learning Models

Aim: Cervical cancer is still one of the most common gynecologic cancers in the world. Since cervical cancer is a potentially preventive cancer, earlier detection is the most effective technique for decreasing the worldwide incidence of the illness. Materials and methods: This research presents a novel ensemble technique for predicting cervical cancer risk. Specifically, the authors introduce a voting classifier that aggregates prediction probabilities from multiple machine-learning models: logistic regression, K-nearest neighbor, decision tree, XGBoost and multilayer perceptron. Results: The average accuracy, precision, recall and f1-score of the voting classifier were 96.6, 97.4, 95.9 and 96.6, respectively. Furthermore, the voting algorithm gains average high values for all evaluation metrics (accuracy, precision, recall and f1-score). The f1-score of the algorithm is 96%, which demonstrates the robustness of the model. Conclusion: The findings suggest that the probability of having cervical cancer can be accurately predicted utilizing the voting technique.

scholarly journals Effect of Double Pulse MIG Welding on Porosity Formation on Aluminium 5083 Fillet Joint

2019 ◽  
Vol 269 ◽  
pp. 01002
Author(s):  
Eakkachai Warinsiriruk ◽  
Jukkapun Greebmalai ◽  
Montri Sangsuriyun
Keyword(s):  
Duty Cycle ◽  
Plate Thickness ◽  
Travel Speed ◽  
Processing Technique ◽  
Double Pulse ◽  
Image Processing Technique ◽  
Porosity Formation ◽  
High Level ◽  
Welding Consumables ◽  
Wire Feed

In this article, parameters of Double-Pulse Metal Inert Gas Welding (DP-MIG) was used for minimising a porosity formation in a T-joint fillet weld. AA5083-H112 aluminium alloy (Non-heat treatable series) with the plate thickness of 10 millimetres is base metal for this study. Welding consumables were filler wire ER5356 with a diameter of 1.2 millimetres and shielded by industrial argon gas. Three majorities parameter of DP-MIG were Delta wire feed (m/min), Frequency (Hz) and Duty cycle (%). Measurable signal current pattern and opened porosity on the fractured surface were couple observed to study their relationships. An appropriate image processing technique was employed to quantitative measuring and calculating a size grouping area of several opened porosities overall weld length, precisely. The result found that the optimal was used a low-level of Delta wire feed of 0.8 m/min, a high-level of a frequency of 5.0 Hz, a mid-level of the duty cycle 30 % and a high travel speed 60 cm/min could minimise the porosity formation with complete penetration.

A Hybrid GA-LDA Scheme for Feature Selection in Content-Based Image Retrieval

2018 ◽  
Vol 9 (2) ◽  
pp. 48-71 ◽  
Author(s):  
Khadidja Belattar ◽  
Sihem Mostefai ◽  
Amer Draa
Keyword(s):  
Feature Selection ◽  
Image Retrieval ◽  
Nearest Neighbor ◽  
Skin Lesions ◽  
Processing Technique ◽  
Input Image ◽  
Content Based Image Retrieval ◽  
K Nearest Neighbor ◽  
Feature Selection Problem ◽  
Linear Discriminant

Feature selection is an important pre-processing technique in the pattern recognition domain. This article proposes a hybridization between Genetic Algorithm (GA) and the Linear Discriminant Analysis (LDA) for solving the feature selection problem in Content-Based Image Retrieval (CBIR) applied to dermatological images. In the first step, we preprocess and segment the input image, then we derive color and texture features characterizing healthy skin and the segmented skin lesion. At this stage, a binary GA is used to evolve chromosome subsets whose fitness is evaluated by a Logistic Regression classifier. The optimal identified features are then used to feed LDA for a CBIR system, based on a K-Nearest Neighbor classification. To assess the proposed approach, the authors have opted for a K-fold cross validation method on a database of 1097 images of melanomas and other skin lesions. As a result, the authors obtained a reduced number of features and an improved CBDIR system compared to PCA, LDA and ICA methods.

Sign in / Sign up

Export Citation Format

Share Document