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.

scholarly journals Fish survival prediction in an aquatic environment using random forest model

2021 ◽  
Vol 10 (3) ◽  
pp. 614
Author(s):  
Md. Monirul Islam ◽  
Mohammod Abul Kashem ◽  
Jia Uddin
Keyword(s):  
Random Forest ◽  
Fish Species ◽  
Aquatic Environment ◽  
Nearest Neighbor ◽  
Performance Metrics ◽  
Survival Prediction ◽  
Kappa Statistics ◽  
Accuracy Score ◽  
K Nearest Neighbor ◽  
Proposed Model

In the real world, it is very difficult for fish farmers to select the perfect fish species for aquaculture in a specific aquatic environment. The main goal of this research is to build a machine learning that can predict the perfect fish species in an aquatic environment. In this paper, we have utilized a model using random forest (RF). To validate the model, we have used a dataset of aquatic environment for 11 different fishes. To predict the fish species, we utilized the different characteristics of aquatic environment including pH, temperature, and turbidity. As a performance metrics, we measured accuracy, true positive (TP) rate, and kappa statistics. Experimental results demonstrate that the proposed RF-based prediction model shows accuracy 88.48%, kappa statistic 87.11% and TP rate 88.5% for the tested dataset. In addition, we compare the proposed model with the state-of-art models J48, RF, k-nearest neighbor (k-NN), and classification and regression trees (CART). The proposed model outperforms than the existing models by exhibiting the higher accuracy score, TP rate and kappa statistics.

scholarly journals Computational Intelligence-Based Model for Mortality Rate Prediction in COVID-19 Patients

2021 ◽  
Vol 18 (12) ◽  
pp. 6429
Author(s):  
Irfan Ullah Khan ◽  
Nida Aslam ◽  
Malak Aljabri ◽  
Sumayh S. Aljameel ◽  
Mariam Moataz Aly Kamaleldin ◽  
...  
Keyword(s):  
Mortality Rate ◽  
Computational Intelligence ◽  
Nearest Neighbor ◽  
Gradient Boosting ◽  
K Nearest Neighbor ◽  
Detection And Identification ◽  
Proposed Model ◽  
Extreme Gradient Boosting ◽  
The World ◽  
Detection And Diagnosis

The COVID-19 outbreak is currently one of the biggest challenges facing countries around the world. Millions of people have lost their lives due to COVID-19. Therefore, the accurate early detection and identification of severe COVID-19 cases can reduce the mortality rate and the likelihood of further complications. Machine Learning (ML) and Deep Learning (DL) models have been shown to be effective in the detection and diagnosis of several diseases, including COVID-19. This study used ML algorithms, such as Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and K-Nearest Neighbor (KNN) and DL model (containing six layers with ReLU and output layer with sigmoid activation), to predict the mortality rate in COVID-19 cases. Models were trained using confirmed COVID-19 patients from 146 countries. Comparative analysis was performed among ML and DL models using a reduced feature set. The best results were achieved using the proposed DL model, with an accuracy of 0.97. Experimental results reveal the significance of the proposed model over the baseline study in the literature with the reduced feature set.

scholarly journals KLASIFIKASI CITRA REKAMAN SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN METODE ANALISIS TEKSTUR, K-NN DAN MULTILAYER PERCEPTRON

2016 ◽  
Vol 7 (1) ◽  
pp. 233
Author(s):  
Mohamad Sofie ◽  
Achmad Rizal
Keyword(s):  
Multilayer Perceptron ◽  
Nearest Neighbor ◽  
Grey Level ◽  
K Nearest Neighbor

Sinyal elektrokardiogram (EKG) memiliki informasi yang menggambarkan kondisi kesehatan jantung. Beragai teknik analisis sinyal EKG dikembangkan untuk mengetahui kelainan di jantung secara ototmatis. Pada kenyataannya di Indonesia, kebanyakan perangkat EKG hanya menghasilkan rekaman berupa kertas EKG sehingga metode pengolahan sinyal tidak bisa diterapkan. Pada penelitian ini dilakukan pengenalan kelainan jantung melalui citra rekaman EKG menggunakan analisis tekstur. Garis sinyal EKG yang tergambar dalam citra rekaman EKG diharapkan bisa dibedakan antara kondisi yang satu dengan yang lain. Untuk ekstraksi ciri digunakan ciri statistik orde 1 dan grey level co-occurence matrix (GLCM) pada arah 0o, 45o, 90o, dan 135o. Untuk klasifikasi digunakan K-nearest neighbor (K-NN) dan multilayer perceptron (MLP). Akurasi yang dihasilkan mencapai 44.12% untuk lima kelas data dan 65.82% untuk dua kelas data. Penggunaan teknik pengolahan ctra terbukti mampu meningkatkan akurasi yang semula rendah.Kata kunci: analisis tekstur, K-NN, multilayerperceptron, citra rekaman EKG, pengolahan citra.

scholarly journals Delineation of Cocoa Agroforests Using Multiseason Sentinel-1 SAR Images: A Low Grey Level Range Reduces Uncertainties in GLCM Texture-Based Mapping.

2019 ◽  
Vol 8 (4) ◽  
pp. 179 ◽  
Author(s):  
Frederick N. Numbisi ◽  
Frieke M. B. Van Coillie ◽  
Robert De Wulf
Keyword(s):  
Optical Sensors ◽  
Spectral Characteristics ◽  
Texture Feature ◽  
Image Texture ◽  
Optical Data ◽  
Grey Level ◽  
Sar Images ◽  
Quantization Level ◽  
Class Prediction ◽  
Sar Imagery

Delineating the cropping area of cocoa agroforests is a major challenge in quantifying the contribution of land use expansion to tropical deforestation. Discriminating cocoa agroforests from tropical transition forests using multispectral optical images is difficult due to the similarity of the spectral characteristics of their canopies. Moreover, the frequent cloud cover in the tropics greatly impedes optical sensors. This study evaluated the potential of multiseason Sentinel-1 C-band synthetic aperture radar (SAR) imagery to discriminate cocoa agroforests from transition forests in a heterogeneous landscape in central Cameroon. We used an ensemble classifier, Random Forest (RF), to average the SAR image texture features of a grey level co-occurrence matrix (GLCM) across seasons. We then compared the classification performance with results from RapidEye optical data. Moreover, we assessed the performance of GLCM texture feature extraction at four different grey levels of quantization: 32 bits, 8 bits, 6 bits, and 4 bits. The classification’s overall accuracy (OA) from texture-based maps outperformed that from an optical image. The highest OA (88.8%) was recorded at the 6 bits grey level. This quantization level, in comparison to the initial 32 bits in the SAR images, reduced the class prediction error by 2.9%. The texture-based classification achieved an acceptable accuracy and revealed that cocoa agroforests have considerably fragmented the remnant transition forest patches. The Shannon entropy (H) or uncertainty provided a reliable validation of the class predictions and enabled inferences about discriminating inherently heterogeneous vegetation categories.

scholarly journals Chicago Crime Analysis using R Programming

2019 ◽  
pp. 937-944
Author(s):  
Monish N
Keyword(s):  
Law Enforcement ◽  
Data Science ◽  
Nearest Neighbor ◽  
Crime Rates ◽  
K Nearest Neighbor ◽  
Proposed Model ◽  
The Us ◽  
Steep Decline ◽  
R Programming ◽  
And Behavior

In recent years law enforcement have improved by taking better strategies, computer aided technology, efficient use of resource, etc. As a result of these over the couple of years there has been a steep decline in crime rate in the US (United States). Law enforcement have turned to data science for insights (ranging from reports, corrective analysis and behavior modelling). There has been an overall drop in crime rates in Chicago in recent years. In fact, these rates are at the lowest when compared to the previous decades. This paper uses the criminal dataset found at “data.cityofchicago.org/Public-Safety/Crimes-2001-to-present/ijzp-q8t2” to describe historical trends, insights, etc. in Chicago from 1965 to 2018 and not to assign any casual interpretation of the vanguards of crime rates during this period. Here K-Nearest Neighbor (KNN) classification is used for training and crime predication. Discussions on future investigation can also be found. The proposed model has an accuracy of 83.2%.

scholarly journals K-NN supervised learning algorithm in the predictive analysis of the quality of the university administrative service in the virtual environment

2022 ◽  
Vol 25 (1) ◽  
pp. 521
Author(s):  
Omar Freddy Chamorro-Atalaya ◽  
Guillermo Morales Romero ◽  
Adrián Quispe Andía ◽  
Beatriz Caycho Salas ◽  
Elizabeth Katerin Auqui Ramos ◽  
...  
Keyword(s):  
Predictive Model ◽  
Engineering Students ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Confusion Matrix ◽  
Area Under The Curve ◽  
Operational Characteristic ◽  
K Nearest Neighbor ◽  
Administrative Service

The objective of this study is to analyze and discuss the metrics of the predictive model using the K-nearest neighbor (K-NN) learning algorithm, which will be applied to the data on the perception of engineering students on the quality of the virtual administrative service, such as part of the methodology was analyzed the indicators of accuracy, precision, sensitivity and specificity, from the obtaining of the confusion matrix and the receiver operational characteristic (ROC) curve. The collected data were validated through Cronbach's Alpha, finding consistency values higher than 0.9, which allows to continue with the analysis. Through the predictive model through the Matlab R2021a software, it was concluded that the average metrics for all classes are optimal, presenting a precision of 92.77%, sensitivity 86.62%, and specificity 94.7%; with a total accuracy of 85.5%. In turn, the highest level of the area under the curve (AUC) is 0.98, which is why it is considered an optimal predictive model. Having carried out this study, it is possible to contribute significantly to the decision-making of the higher institution in relation to the improvement of the quality of the virtual administrative service.

scholarly journals Heart disease prediction model with k-nearest neighbor algorithm

2021 ◽  
Vol 10 (3) ◽  
pp. 225
Author(s):  
Tssehay Admassu Assegie
Keyword(s):  
Heart Disease ◽  
Prediction Model ◽  
Nearest Neighbor ◽  
Predictive Performance ◽  
Data Repository ◽  
Disease Prediction ◽  
K Nearest Neighbor ◽  
Proposed Model ◽  
K Nearest Neighbor Algorithm ◽  
Learning Data

<span>In this study, the author proposed k-nearest neighbor (KNN) based heart disease prediction model. The author conducted an experiment to evaluate the performance of the proposed model. Moreover, the result of the experimental evaluation of the predictive performance of the proposed model is analyzed. To conduct the study, the author obtained heart disease data from Kaggle machine learning data repository. The dataset consists of 1025 observations of which 499 or 48.68% is heart disease negative and 526 or 51.32% is heart disease positive. Finally, the performance of KNN algorithm is analyzed on the test set. The result of performance analysis on the experimental results on the Kaggle heart disease data repository shows that the accuracy of the KNN is 91.99%</span>

scholarly journals Prediction of Train Arrival Delay Using Hybrid ELM-PSO Approach

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Xu Bao ◽  
Yanqiu Li ◽  
Jianmin Li ◽  
Rui Shi ◽  
Xin Ding
Keyword(s):  
Nearest Neighbor ◽  
Pso Algorithm ◽  
Bayesian Optimization ◽  
Gradient Boosting ◽  
K Nearest Neighbor ◽  
Delay Management ◽  
Buffer Time ◽  
Proposed Model ◽  
Learning Machine ◽  
Hidden Layer

In this study, a hybrid method combining extreme learning machine (ELM) and particle swarm optimization (PSO) is proposed to forecast train arrival delays that can be used for later delay management and timetable optimization. First, nine characteristics (e.g., buffer time, the train number, and station code) associated with train arrival delays are chosen and analyzed using extra trees classifier. Next, an ELM with one hidden layer is developed to predict train arrival delays by considering these characteristics mentioned before as input features. Furthermore, the PSO algorithm is chosen to optimize the hyperparameter of the ELM compared to Bayesian optimization and genetic algorithm solving the arduousness problem of manual regulating. Finally, a case is studied to confirm the advantage of the proposed model. Contrasted to four baseline models (k-nearest neighbor, categorical boosting, Lasso, and gradient boosting decision tree) across different metrics, the proposed model is demonstrated to be proficient and achieve the highest prediction accuracy. In addition, through a detailed analysis of the prediction error, it is found that our model possesses good robustness and correctness.

scholarly journals K-Nearest Neighbor Berbasis Particle Swarm Optimization untuk Analisis Sentimen Terhadap Tokopedia

2020 ◽  
Vol 6 (2) ◽  
Author(s):  
Dicki Pajri ◽  
Yuyun Umaidah ◽  
Tesa Nur Padilah
Keyword(s):  
Particle Swarm Optimization ◽  
Nearest Neighbor ◽  
Confusion Matrix ◽  
Particle Swarm ◽  
K Nearest Neighbor ◽  
Swarm Optimization ◽  
Evaluation Result ◽  
Source Of Information ◽  
F Measure ◽  
Evaluation Accuracy

Tokopedia is a popular marketplace used by e-commerce in Indonesia. Customers’ perception of Twitter towards Tokopedia can be used as an important source of information and can be processed into useful insights. Sentiment analysis is a solution that can be used to process the customers’ perception using K-Nearest Neighbor based on Particle Swarm Optimization. The purpose of this study is to classify customers’ perception based on positive, neutral, and negative classes. The test is carried out with four different scenarios and k values which are evaluated using a confusion matrix. Evaluation results showed the distribution of the dataset is 90:10 and the value of k = 1 is the best evaluation result, which is 88.11%. The feature selection was used for results by using Particle Swarm Optimization. The Particle Swarm Optimization used 20 iterations and 10 particles. It produced 97.9% the best evaluation accuracy, 96.17% precision, 96.62% recall, and 96.39% f-measure.

scholarly journals Security System Aided by Voice Fingerprint

2021 ◽  
Vol 14 (1) ◽  
pp. 24-29
Author(s):  
Gabriel Popan ◽  
Lorena Muscar ◽  
Lacrimioara Grama
Keyword(s):  
Private Information ◽  
Nearest Neighbor ◽  
Confusion Matrix ◽  
Training Model ◽  
Security System ◽  
Fingerprint Recognition ◽  
K Nearest Neighbor ◽  
Mel Frequency Cepstral Coefficients ◽  
K Nearest Neighbor Algorithm ◽  
Audio Files

Abstract The goal of this paper is to create a security system to identify a specific person who wants to access private information or enter a building using their voice. To perform this system, we identified a database containing the audio files of the users who will be able to authenticate with this system. Several steps were sequentially performed in order to extract the characteristics of the Mel Frequency Cepstral Coefficients from the audio files. Based on the k-Nearest Neighbor algorithm with an Euclidean distance and 4 neighbors, a training model was created. Through experimental results we prove in two ways, using confusion matrix and scatter plot, that the overall voice fingerprint recognition is 100%, for this particular configuration.

Sign in / Sign up

Export Citation Format

Share Document