scholarly journals Plant Disease Diagnosis and Classification by Computer Vision using Statistical Texture Feature Extraction Technique and K Nearest Neighbor Classification

2019 ◽  
Vol 9 (2) ◽  
pp. 2336-2341
Keyword(s):  
Computer Vision ◽  
Plant Growth ◽  
Nearest Neighbor ◽  
Control Method ◽  
Texture Feature ◽  
Disease Diagnosis ◽  
Disease Detection ◽  
K Nearest Neighbor ◽  
Key Points ◽  
Insect Attack

Pest attack and infectious diseases has become more common in the field of agriculture in the recent times. It has become a challenging task to identify the infection or the insect that destructs the plant growth and production. Diagnosing the disease or the insect attack on the plants in the early stage will safe guard the plant growth and the production rate. Timely intervention of technology that deals with disease detection and control method can protect the plants from usage of harmful pesticides. The higher dosage of pesticides impacts the health of human as well as other creatures like birds and animals which directly or indirectly consumes the plant or get in touch with the plants in different circumstances. A Computer vision technique which combines the Digital Image processing and Machine Learning methodology has been proposed to provide pest management solution. The disease detection is based on the statistical texture feature analysis and it is classified using K nearest neighbor classifier. Statistical PCA is combined with SIFT method to extract the key points, which eliminates the non-operational key points and SFTA is used to extract the texture. The system has achieved better result in identifying and differentiating the infection and insect attack on multiple plant taxonomy. The implementation has been performed using MATLAB.

scholarly journals KNNCNV: A K-Nearest Neighbor Based Method for Detection of Copy Number Variations Using NGS Data

2021 ◽  
Vol 9 ◽  
Author(s):  
Kun Xie ◽  
Kang Liu ◽  
Haque A K Alvi ◽  
Yuehui Chen ◽  
Shuzhen Wang ◽  
...  
Keyword(s):  
Copy Number ◽  
Nearest Neighbor ◽  
Human Cancer ◽  
Gaussian Mixture ◽  
Disease Diagnosis ◽  
Copy Number Variations ◽  
Sequencing Data ◽  
K Nearest Neighbor ◽  
Data Types ◽  
Ngs Data

Copy number variation (CNV) is a well-known type of genomic mutation that is associated with the development of human cancer diseases. Detection of CNVs from the human genome is a crucial step for the pipeline of starting from mutation analysis to cancer disease diagnosis and treatment. Next-generation sequencing (NGS) data provides an unprecedented opportunity for CNVs detection at the base-level resolution, and currently, many methods have been developed for CNVs detection using NGS data. However, due to the intrinsic complexity of CNVs structures and NGS data itself, accurate detection of CNVs still faces many challenges. In this paper, we present an alternative method, called KNNCNV (K-Nearest Neighbor based CNV detection), for the detection of CNVs using NGS data. Compared to current methods, KNNCNV has several distinctive features: 1) it assigns an outlier score to each genome segment based solely on its first k nearest-neighbor distances, which is not only easy to extend to other data types but also improves the power of discovering CNVs, especially the local CNVs that are likely to be masked by their surrounding regions; 2) it employs the variational Bayesian Gaussian mixture model (VBGMM) to transform these scores into a series of binary labels without a user-defined threshold. To evaluate the performance of KNNCNV, we conduct both simulation and real sequencing data experiments and make comparisons with peer methods. The experimental results show that KNNCNV could derive better performance than others in terms of F1-score.

Land Cover Classification Using the Proposed Texture Model and Fuzzy k-NN Classifier

2018 ◽  
pp. 226-261
Author(s):  
Jenicka S.
Keyword(s):  
Nearest Neighbor ◽  
Confusion Matrix ◽  
Texture Feature ◽  
Image Texture ◽  
Kappa Statistics ◽  
Grey Level ◽  
Classification Problems ◽  
K Nearest Neighbor ◽  
Texture Model ◽  
Proposed Model

Texture feature is a decisive factor in pattern classification problems because texture features are not deduced from the intensity of current pixel but from the grey level intensity variations of current pixel with its neighbors. In this chapter, a new texture model called multivariate binary threshold pattern (MBTP) has been proposed with five discrete levels such as -9, -1, 0, 1, and 9 characterizing the grey level intensity variations of the center pixel with its neighbors in the local neighborhood of each band in a multispectral image. Texture-based classification has been performed with the proposed model using fuzzy k-nearest neighbor (fuzzy k-NN) algorithm on IRS-P6, LISS-IV data, and the results have been evaluated based on confusion matrix, classification accuracy, and Kappa statistics. From the experiments, it is found that the proposed model outperforms other chosen existing texture models.

A Survey on Blood Image Diseases Detection Using Deep Learning

2020 ◽  
Vol 11 (3) ◽  
pp. 18-32
Author(s):  
Mohamed Loey ◽  
Mukdad Rasheed Naman ◽  
Hala Helmy Zayed
Keyword(s):  
Deep Learning ◽  
Blood Cells ◽  
Nearest Neighbor ◽  
Disease Diagnosis ◽  
Research Area ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Blood Disease ◽  
Active Research ◽  
Time Accuracy

Blood disease detection and diagnosis using blood cells images is an interesting and active research area in both the computer and medical fields. There are many techniques developed to examine blood samples to detect leukemia disease, these techniques are the traditional techniques and the deep learning (DL) technique. This article presents a survey on the different traditional techniques and DL approaches that have been employed in blood disease diagnosis based on blood cells images and to compare between the two approaches in quality of assessment, accuracy, cost and speed. This article covers 19 studies, 11 of these studies were in traditional techniques which used image processing and machine learning (ML) algorithms such as K-means, K-nearest neighbor (KNN), Naïve Bayes, Support Vector Machine (SVM), and 8 studies in advanced techniques which used DL, particularly Convolutional Neural Networks (CNNs) which is the most widely used in the field of blood image diseases detection since it is highly accurate, fast, and has the least cost. In addition, it analyzes a number of recent works that have been introduced in the field including the size of the dataset, the used methodologies, the obtained results, etc. Finally, based on the conducted study, it can be concluded that the proposed system CNN was achieving huge successes in the field whether regarding features extraction or classification task, time, accuracy, and had a lower cost in the detection of leukemia diseases.

scholarly journals A hybrid cost-sensitive ensemble for heart disease prediction

2021 ◽  
Author(s):  
Zhenya Qi ◽  
Zuoru Zhang
Keyword(s):  
Heart Disease ◽  
Nearest Neighbor ◽  
Statistical Tests ◽  
Disease Diagnosis ◽  
Medical Decision ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Misclassification Cost ◽  
Promising Alternative ◽  
Relief Algorithm

Abstract Background: Heart disease is the primary cause of morbidity and mortality in the world. It includes numerous problems and symptoms. The diagnosis of heart disease is difficult because there are too many factors to analyze. What's more, the misclassification cost could be very high. Methods: A cost-sensitive ensemble method was proposed to improve the efficiency of diagnosis and reduce the misclassification cost. The proposed method contains five heterogeneous classifiers: random forest, logistic regression, support vector machine, extreme learning machine and k-nearest neighbor. T-test was used to investigate if the performance of the ensemble was better than individual classifiers and the contribution of Relief algorithm. Results: The best performance was achieved by the proposed method according to ten-fold cross validation. The statistical tests demonstrated that the performance of the proposed ensemble was significantly superior to individual classifiers, and the efficiency of classification was distinctively improved by Relief algorithm. Conclusions: The proposed ensemble gained significantly better results compared with individual classifiers and previous studies, which implies that it can be used as a promising alternative tool in medical decision making for heart disease diagnosis.

scholarly journals A hybrid cost-sensitive ensemble for heart disease prediction

2020 ◽  
Author(s):  
Zhenya Qi ◽  
Zuoru Zhang
Keyword(s):  
Heart Disease ◽  
Nearest Neighbor ◽  
Statistical Tests ◽  
Disease Diagnosis ◽  
Medical Decision ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Misclassification Cost ◽  
Promising Alternative ◽  
Relief Algorithm

Abstract Background: Heart disease is the primary cause of morbidity and mortality in the world. It includes numerous problems and symptoms. The diagnosis of heart disease is difficult because there are too many factors to analyze. What's more, the misclassification cost could be very high. Methods: A cost-sensitive ensemble method was proposed to improve the efficiency of diagnosis and reduce the misclassification cost. The proposed method contains five heterogeneous classifiers: random forest, logistic regression, support vector machine, extreme learning machine and k-nearest neighbor. T-test was used to investigate if the performance of the ensemble was better than individual classifiers and the contribution of Relief algorithm. Results: The best performance was achieved by the proposed method according to ten-fold cross validation. The statistical tests demonstrated that the performance of the proposed ensemble was significantly superior to individual classifiers, and the efficiency of classification was distinctively improved by Relief algorithm. Conclusions: The proposed ensemble gained significantly better results compared with individual classifiers and previous studies, which implies that it can be used as a promising alternative tool in medical decision making for heart disease diagnosis.

scholarly journals Diagnosis and Classification of the Diabetes Using Machine Learning Algorithms

2021 ◽  
Author(s):  
Prasannavenkatesan Theerthagiri ◽  
Usha Ruby A ◽  
Vidya J
Keyword(s):  
Machine Learning ◽  
Multilayer Perceptron ◽  
Nearest Neighbor ◽  
False Positive Rate ◽  
Learning Algorithms ◽  
False Negative ◽  
False Negative Rate ◽  
Disease Diagnosis ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbor

Abstract Diabetes mellitus is characterized as a chronic disease may cause many complications. The machine learning algorithms are used to diagnosis and predict the diabetes. The learning based algorithms plays a vital role on supporting decision making in disease diagnosis and prediction. In this paper, traditional classification algorithms and neural network based machine learning are investigated for the diabetes dataset. Also, various performance methods with different aspects are evaluated for the K-nearest neighbor, Naive Bayes, extra trees, decision trees, radial basis function, and multilayer perceptron algorithms. It supports the estimation on patients suffering from diabetes in future. The results of this work shows that the multilayer perceptron algorithm gives the highest prediction accuracy with lowest MSE of 0.19. The MLP gives the lowest false positive rate and false negative rate with highest area under curve of 86 %.

scholarly journals A hybrid cost-sensitive ensemble for heart disease prediction

2020 ◽  
Author(s):  
Zhenya Qi ◽  
Zuoru Zhang
Keyword(s):  
Heart Disease ◽  
Nearest Neighbor ◽  
Statistical Tests ◽  
Disease Diagnosis ◽  
Medical Decision ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Misclassification Cost ◽  
Promising Alternative ◽  
Relief Algorithm

Abstract Background: Heart disease is the primary cause of morbidity and mortality in the world. It includes numerous problems and symptoms. The diagnosis of heart disease is difficult because there are too many factors to analyze. What's more, the misclassification cost could be very high. Methods: A cost-sensitive ensemble method was proposed to improve the efficiency of diagnosis and reduce the misclassification cost. The proposed method contains five heterogeneous classifiers: random forest, logistic regression, support vector machine, extreme learning machine and k-nearest neighbor. T-test was used to investigate if the performance of the ensemble was better than individual classifiers and the contribution of Relief algorithm. Results: The best performance was achieved by the proposed method according to ten-fold cross validation. The statistical tests demonstrated that the performance of the proposed ensemble was significantly superior to individual classifiers, and the efficiency of classification was distinctively improved by Relief algorithm. Conclusions: The proposed ensemble gained significantly better results compared with individual classifiers and previous studies, which implies that it can be used as a promising alternative tool in medical decision making for heart disease diagnosis.

FASICA Framework: Service Selection Using K-d Tree and Cache

2015 ◽  
Vol 25 (05) ◽  
pp. 807-828
Author(s):  
Aimrudee Jongtaveesataporn ◽  
Shingo Takada
Keyword(s):  
Nearest Neighbor ◽  
Service Oriented Architecture ◽  
Service Selection ◽  
K Nearest Neighbor ◽  
Search Results ◽  
Key Points ◽  
Service Oriented ◽  
Selection For ◽  
Selection Of

The selection of services is a key part of Service Oriented Architecture (SOA). Services are primarily selected based on function, but Quality of Service (QoS) is an important factor when choosing among several services with the same function. But current service selection approaches often takes time to unnecessarily recompute requests. Furthermore, if the same service is chosen as having the "best" QoS for multiple selections, this may result in that service having too much load. We thus propose the FASICA (FAst service selection for SImilar constraints with CAche) Framework which chooses a service with satisfactory QoS as quickly as possible. The key points are (1) to use a cache which stores previous search results, (2) to use K-Nearest Neighbor (K-NN) algorithm with K-d tree when a satisfactory service does not exist in the cache, and (3) to distribute the service request according to a distribution policy. Results of simulations show that our framework can rapidly select a service compared to a conventional approach.

Automatic Defect Detection and Classification of Terminals in a Bussed Electrical Center Using Computer Vision

2016 ◽  
pp. 241-266
Author(s):  
Osslan Osiris Vergara Villegas ◽  
Vianey Guadalupe Cruz Sánchez ◽  
Humberto de Jesús Ochoa Domínguez ◽  
Jorge Luis García-Alcaraz ◽  
Ricardo Rodriguez Jorge
Keyword(s):  
Computer Vision ◽  
Defect Detection ◽  
Nearest Neighbor ◽  
Region Of Interest ◽  
Morphological Operation ◽  
K Nearest Neighbor ◽  
Electrical Center ◽  
Salt And Pepper ◽  
Intelligent Computer

In this chapter, an intelligent Computer Vision (CV) system, for the automatic defect detection and classification of the terminals in a Bussed Electrical Center (BEC) is presented. The system is able to detect and classify three types of defects in a set of the seven lower pairs of terminals of a BEC namely: a) twisted; b) damaged and c) missed. First, an environment to acquire a total of 56 training and test images was created. After that, the image preprocessing is performed by defining a Region Of Interest (ROI) followed by a binarization and a morphological operation to remove small objects. Then, the segmentation stage is computed resulting in a set of 12-14 labeled zones. A vector of 56 features is extracted for each image containing information of area, centroid and diameter of all terminals segmented. Finally, the classification is performed using a K-Nearest Neighbor (KNN) algorithm. Experimental results on 28 BEC images have shown an accuracy of 92.8% of the proposed system, allowing changes in brightness, contrast and salt and pepper noise.

scholarly journals Klasifikasi Mutu Telur Burung Puyuh Berdasarkan Warna dan Tekstur Menggunakan Metode K-Nearest Neighbor (KNN) dan Fusi Informasi

2021 ◽  
Vol 8 (5) ◽  
pp. 1019
Author(s):  
Arwin Datumaya Wahyudi Sumari ◽  
Putri Indah Mawarni ◽  
Arie Rachmad Syulistyo
Keyword(s):  
Information Fusion ◽  
Nearest Neighbor ◽  
Egg Quality ◽  
Imaging System ◽  
Texture Feature ◽  
Image Data ◽  
K Nearest Neighbor ◽  
Color Feature ◽  
Otsu Thresholding

<p>Kualitas produk merupakan faktor utama untuk menjamin keberlangsungan satu usaha peternakan. Perusahaan telur puyuh yang memiliki ribuan burung Puyuh seperti CV. NS Quail Farm mampu memproduksi ribuan telur dalam sehari karena seekor burung Puyuh mampu menghasilkan 250-300 butir telur per tahun. Penyeleksian ribuan telur-telur tersebut dilakukan secara tradisional oleh para pekerja peternakan sehingga kualitas telur-telur hasil seleksi bergantung pada perspektif masing-masing pekerja. Guna memperoleh telur hasil seleksi dengan kualitas yang sama, maka dibangun sebuah sistem pencitraan digital untuk pemilihan telur burung Puyuh berdasarkan fitur warna dan tekstur kulit telur menggunakan metode klasifikasi K-<em>Nearest Neighbor</em> (KNN) yang dikombinasikan dengan fusi informasi. 300 data citra telur burung Puyuh diolah menggunakan normalisasi <em>Red, Green, Blue</em> (RGB) dan <em>Otsu thresholding</em> guna memperoleh fitur warna dan fitur tekstur yang kemudian difusikan menjadi fitur terfusi tunggal sebagai masukan pengklasifikasi KNN. Dari hasil-hasil penelitian, disimpulkan bahwa sistem berhasil mengklasifikasikan mutu telur Baik, Sedang, dan Buruk dengan akurasi rata-rata sebesar 77,78%. Disamping itu, klasifikasi dengan fusi informasi mampu mengungguli klasifikasi tanpa fusi informasi sebesar 11,11% pada nilai  yang sama yakni 7 dan fusi informasi juga mampu mempercepat proses klasifikasi sebesar 0,22 detik dibandingkan terhadap klasifikasi tanpa fusi informasi.</p><p><strong><em>Abstract</em></strong></p><p><em>The quality of product us a primary factor to ensure the sustainability of a farm business. A company which has thousands of quail such as CV. NS Quail is capable of producing thousand quail eggs in a day because a quail is able to produce 250-300 eggs per year. The selection of the eggs is carried out traditionally by the farm workers so that the quality of the selected eggs are depended on the perspective of each worker. In order to obtain the same quality of the selected eggs, a digital imaging system for quail egg selection based on color feature and texture feature using K-Nearest Neighbor (KNN) combined with information fusion is developed. 300 image data of quail egg was processed using Red, Green, Blue (RGB) and Otsu thresholding to obtain color feature and texture feature which then were fused to become single fused feature as the input to KNN classifier. From the research results, it is concluded that the system was managed to classify egg quality as good, medium, and bad with an accuracy of 77,78%. In addition, the classification with information fusion was able to outperform the classification without information fusion by 11.11% at the same  value of 7 and information fusion is also able to accelerate classification process by 0.22 seconds compared to that of without information fusion.</em></p>

Sign in / Sign up

Export Citation Format

Share Document