scholarly journals A DINÂMICA DO USO E OCUPAÇÃO DA TERRA NO LAGO POPÓO (BOLÍVIA) ENTRE 1985 E 2017 UTILIZANDO CLASSIFICAÇÃO VOLTADA AO OBJETO EM DADOS LANDSAT

2020 ◽  
Vol 38 (4) ◽  
pp. 1073-1082
Author(s):  
Florença das Graças MOURA ◽  
Álvaro Xavier FERREIRA ◽  
Tati ALMEIDA ◽  
Jérémie GARNIER ◽  
Rejane Ennes CICERELLI ◽  
...  
Keyword(s):  
Support Vector Machines ◽  
Nearest Neighbor ◽  
Support Vector ◽  
Landsat 8 ◽  
K Nearest Neighbor ◽  
Vector Machines

O lago Poópo é o segundo maior lago da Bolívia e atualmente vem passando por uma forte crise hídrica que alguns autores associam diretamente a mudança de ocupação da terra. Neste trabalho foi realizada a classificação do uso e ocupação do solo na sub-bacia P6 do lago entre os anos de 1985 e 2017. Foi analisado o desempenho dos classificadores SVM (Support Vector Machines), KNN (K-Nearest Neighbor) e MaxVer (Máxima Verossimilhança). A classificação que obteve melhor acurácia foi a gerada pelo classificador SVM, em que o valor do índice Kappa foi de 82,28% e 83,7% para as imagens Landat-5 e Landsat-8, respectivamente, e a exatidão global foi de 92% para ambas as imagens. A partir das classificações geradas foi verificado que as maiores alterações se deram nas classes de vegetação nativa, agricultura e área úmida. A perda de área úmida na sub-bacia vem ocorrendo desde 1995, 15 anos antes do aumento da atividade agrícola, que começou a partir de 2010. Assim, diversos são os fatores que podem estar contribuindo com essa redução acelerada dos corpos de água, como variações climáticas locais e as atividades antrópicas que interferem no ciclo hidrológico de forma regional.

Smartphone Naïve Bayes Human Activity Recognition Using Personalized Datasets

2020 ◽  
Vol 24 (5) ◽  
pp. 685-702
Author(s):  
Moses L. Gadebe ◽  
◽  
Okuthe P. Kogeda ◽  
Sunday O. Ojo
Keyword(s):  
Support Vector Machines ◽  
Real Time ◽  
Activity Recognition ◽  
Human Activity ◽  
Nearest Neighbor ◽  
Human Activity Recognition ◽  
Training Dataset ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Vector Machines

Recognizing human activity in real time with a limited dataset is possible on a resource-constrained device. However, most classification algorithms such as Support Vector Machines, C4.5, and K Nearest Neighbor require a large dataset to accurately predict human activities. In this paper, we present a novel real-time human activity recognition model based on Gaussian Naïve Bayes (GNB) algorithm using a personalized JavaScript object notation dataset extracted from the publicly available Physical Activity Monitoring for Aging People dataset and University of Southern California Human Activity dataset. With the proposed method, the personalized JSON training dataset is extracted and compressed into a 12×8 multi-dimensional array of the time-domain features extracted using a signal magnitude vector and tilt angles from tri-axial accelerometer sensor data. The algorithm is implemented on the Android platform using the Cordova cross-platform framework with HTML5 and JavaScript. Leave-one-activity-out cross validation is implemented as a testTrainer() function, the results of which are presented using a confusion matrix. The testTrainer() function leaves category K as the testing subset and the remaining K-1 as the training dataset to validate the proposed GNB algorithm. The proposed model is inexpensive in terms of memory and computational power owing to the use of a compressed small training dataset. Each K category was repeated five times and the algorithm consistently produced the same result for each test. The result of the simulation using the tilted angle features shows overall precision, recall, F-measure, and accuracy rates of 90%, 99.6%, 94.18%, and 89.51% respectively, in comparison to rates of 36.9%, 75%, 42%, and 36.9% when the signal magnitude vector features were used. The results of the simulations confirmed and proved that when using the tilt angle dataset, the GNB algorithm is superior to Support Vector Machines, C4.5, and K Nearest Neighbor algorithms.

scholarly journals Vehicle Recognition based on Support Vector Machine

2019 ◽  
Vol 8 (4) ◽  
pp. 9513-9515
Keyword(s):  
Support Vector Machine ◽  
Support Vector Machines ◽  
Decision Tree ◽  
Nearest Neighbor ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Vehicle Recognition ◽  
Basic Procedure ◽  
Vector Machines ◽  
Made In

These days, there is a colossal progression in zones of computerization and PC vision. Item ID is a basic procedure in these innovations. It distinguishes a particular item from a picture or video arrangement and the move is made in like manner. AI calculations are widely utilized for article ID in different applications. The essential highlights are removed from the pictures and are prepared utilizing different classifiers. This paper proposes an article recognizable proof method utilizing Support Vector Machines (SVM). The proposed framework is contrasted and Decision Tree (DT) and K-Nearest Neighbor (KNN) characterization calculations. The item ID framework is surveyed on ID precision, prevision and review.

Sign in / Sign up

Export Citation Format

Share Document