scholarly journals Outdoor Localization in Mobile Robot with 3D LiDAR Based on Principal Component Analysis and K-Nearest Neighbors Algorithm

2021 ◽  
Vol 39 (6) ◽  
pp. 965-976
Author(s):  
Hanan A. Atiyah ◽  
Mohammed Y. Hassan
Keyword(s):  
Mobile Robot ◽  
Principal Component ◽  
Light Sensitivity ◽  
Training Data ◽  
Depth Image ◽  
Lidar Data ◽  
K Nearest Neighbor ◽  
Training Time ◽  
Outdoor Localization ◽  
3D Lidar

Localization is one of the potential challenges for a mobile robot. Due to the inaccuracy of GPS systems in determining the location of the moving robot alongside weathering effects on sensors such as RGBs (e.g. rain and light-sensitivity(. This paper aims to improve the localization of mobile robots by combining the 3D LiDAR data with RGB-D images using deep learning algorithms. The proposed approach is to design an outdoor localization system. It is divided into three stages. The first stage is the training stage where 3D LiDAR scans the city and then reduces the dimensions of 3D LiDAR data to 2.5D image. This is based on PCA method where these data are used as training data. The second stage is the testing data stage. RGB and depth image in IHS method are combined to generate 2.5D fusion image. The training and testing of these datasets are based on using Convolution Neural Network. The third stage consists of using the K-Nearest Neighbor algorithm. This is the classification stage to get high accuracy and reduces the training time. The experimental results obtained prove the superiorly of the proposed approach with accuracy up to 97.52%, Mean Square of Error of 0.057568, and Mean error in distance equals 0.804 meters.

scholarly journals Application of Fuzzy K-Nearest Neighbor (FKNN) to Detect the Parkinson’s Disease

2019 ◽  
Vol 1 (1) ◽  
Author(s):  
L.N. Desinaini ◽  
Azizatul Mualimah ◽  
Dian C. R. Novitasari ◽  
Moh. Hafiyusholeh
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Principal Component Analysis ◽  
Parkinson's Disease ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Component Analysis ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Positive Data

AbstractParkinson’s disease is a neurological disorder in which there is a gradual loss of brain cells that make and store dopamine. Researchers estimate that four to six million people worldwide, are living with Parkinson’s. The average age of patients is 60 years old, but some are diagnosed at age 40 or even younger and the worst thing is some patients are late to find out that they have Parkinson's disease. In this paper, we present a diagnosis system based on Fuzzy K-Nearest Neighbor (FKNN) to detect Parkinson’s disease. We use Parkinson’s disease dataset taken from UCI Machine Learning Repository. The first step is normalize the Parkinson’s disease dataset and analyze using Principal Component Analysis (PCA). The result shows that there are four new factors that influence Parkinson’s disease with total variance is 85.719%. In classification step, we use several percentage of training data to classify (detect) the Parkinson's disease i.e. 50%, 60%, 70%, 75%, 80% and 90%. We also use k = 3, 5, 7, and 9. The classification result shows that the highest accuracy obtained for the percentage of training data is 90% and k = 5, where 19 are correctly classified i.e. 14 positive data and 5 negative data, while 1 positive data is classified incorrectly.Keywords: Parkinson's disease; Fuzzy K-Nearest Neighbor; Principal Component Analysis. AbstrakPenyakit Parkinson merupakan kelainan sel saraf pada otak yang menyebabkan hilangnya dopamin pada otak. Para peneliti mengestimasi bahwa, empat sampai enam juta orang di dunia, menderita Parkinson. Penyakit ini rata-rata diderita oleh pasien berusia 60 tahun, namun beberapa orang terdeteksi saat berusia 40 tahun atau lebih muda dan hal terburuk adalah seseorang terlambat untuk mendeteksinya. Di dalam artikel ini, kami menyajikan sistem diagnosa penyakit Parkinson menggunakan metode Fuzzy K-Nearest Neighbor (FKNN). Kami menggunakan Data uji yang diperoleh dari UCI Machine Learning Repository yang telah banyak diterapkan pada masalah klasifikasi. Tahapan pertama yang kami lakukan adalah menormalisasi data kemudian menganalisisnya menggunakan Analisis Komponen Utama (Principal Component Analysis). Hasil Analisis Komponen Utama menunjukkan bahwa terdapat empat factor baru yang mempengaruhi penyakit Parkinson dengan variansi total 87,719%. Pada tahap klasifikasi, kami menggunakan beberapa prosentase data latih untuk mendeteksi penyakit yaitu 50%, 60%, 70%, 75%, 80% and 90%. Selain itu, kami menggunakan beberapa nilai k yaitu 3, 5, 7, and 9. Hasil menunjukkan bahwa klasifikasi dengan akurasi tertinggi diperoleh untuk 90% data latih dengan k = 5, dimana 19 diklasifikasikan secara tepat yaitu 14 data positif dan 5 data negatif, sedangkan satu data positif tidak diklasifikasikan dengan tepat.Keywords: penyakit Parkinson; Fuzzy K-Nearest Neighbor; Analisis Komponen Utama.

Pears Classification Using Principal Component Analysis and K-Nearest Neighbor

SinkrOn ◽  
2020 ◽  
Vol 4 (2) ◽  
pp. 34
Author(s):  
Moh. Arie Hasan ◽  
Arief Setya Budi
Keyword(s):  
Principal Component Analysis ◽  
Western Europe ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Component Analysis ◽  
Training Data ◽  
Morphological Operations ◽  
K Nearest Neighbor ◽  
Tropical Climates

Pears is a fruit that is widely available in tropical climates such as in western Europe, Asia, Africa and one of them is Indonesia. There are many types of pears in Indonesia. Types of pears can be distinguished from the color, size, and shape. But it is still difficult for ordinary people to get to know the types of pears. This is what gave rise to the idea to conduct research related to image processing to classify three types of pears namely abate, red and william pears in order to help determine the type of pears. The pear type classification process is done by verify the image of pears based on existing training data. The research method used consisted of preprocessing image segmentation with morphological operations and feature extraction into Principal Component Analysis (PCA). The classification algorithm used is K-Nearest Neighbor (KNN). The use of adequate training data will further improve the classification of types of pears. The final results of this study amounted to 87.5%.

scholarly journals Comparison of PCA and 2DPCA Accuracy with K-Nearest Neighbor Classification in Face Image Recognition

2019 ◽  
Vol 6 (1) ◽  
pp. 64-72
Author(s):  
Sri Sutarti ◽  
Anggyi Trisnawan Putra ◽  
Endang Sugiharti
Keyword(s):  
Principal Component Analysis ◽  
Covariance Matrix ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Component Analysis ◽  
Face Image ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Testing Data ◽  
Pca Method

Face recognition is a special pattern recognition for faces that compare input image with data in database. The image has a variety and has large dimensions, so that dimension reduction is needed, one of them is Principal Component Analysis (PCA) method. Dimensional transformation on image causes vector space dimension of image become large. At present, a feature extraction technique called Two-Dimensional Principal Component Analysis (2DPCA) is proposed to overcome weakness of PCA. Classification process in 2DPCA using K-Nearest Neighbor (KNN) method by counting euclidean distance. In PCA method, face matrix is changed into one-dimensional matrix to get covariance matrix. While in 2DPCA, covariance matrix is directly obtained from face image matrix. In this research, we conducted 4 trials with different amount of training data and testing data, where data is taken from AT&T database. In 4 time testing, accuracy of 2DPCA+KNN method is higher than PCA+KNN method. Highest accuracy of 2DPCA+KNN method was obtained in 4th test with 96.88%. while the highest accuracy of PCA+KNN method was obtained in 4th test with 89.38%. More images used as training data compared to testing data, then the accuracy value tends to be greater.

scholarly journals Classification of Broadleaf Weeds Using a Combination of K-Nearest Neighbor (KNN) and Principal Component Analysis (PCA)

SinkrOn ◽  
2022 ◽  
Vol 7 (1) ◽  
pp. 93-100
Author(s):  
Alfry Aristo Jansen Sinlae ◽  
Dedy Alamsyah ◽  
Lilik Suhery ◽  
Fryda Fatmayati
Keyword(s):  
Principal Component Analysis ◽  
Oil Palm ◽  
Nearest Neighbor ◽  
Principal Component ◽  
Relevant Information ◽  
Component Analysis ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Object Based ◽  
And Control

Palm oil is one of the leading commodities in Indonesia. Oil palm yields can be influenced by several factors, one of which is proper weed control. Uncontrolled weeds can damage oil palm plantations. To be able to manage and control weeds, especially large leaf weeds, it is necessary to know the types of weeds. However, not all farmers have knowledge about the types of weeds. For that we need a system that can help identify broadleaf weeds based on leaf images using image processing. So this study aims to build a large leaf weed classification system using a combination of the K-Nearest Neighbor (KNN) and Principal Component Analysis (PCA) algorithms. PCA is used as feature extraction based on the characteristics formed from each spatial property. PCA can be used to reduce and retain most of the relevant information from the original features according to the optimal criteria. The results of the information will then be used by KNN for learning by paying attention to the closest distance from the object. Based on the test results, the developed model is able to produce an accuracy of 90%. Principal Component Analysis (PCA) and K-Nearest Neighbor (KNN) algorithms can be used in the classification process properly. Accuracy results are strongly influenced by the amount of training data and test data as well as the quality of the image used.

An Efficient Ear Recognition Method from Two-Dimensional Images

2014 ◽  
Vol 1049-1050 ◽  
pp. 1531-1535
Author(s):  
Yu Jun Zhang ◽  
Mei Xiang ◽  
Ying Tian
Keyword(s):  
Wavelet Transformation ◽  
Nearest Neighbor ◽  
Recognition Rate ◽  
Low Frequency ◽  
Principal Component ◽  
K Nearest Neighbor ◽  
Recognition Method ◽  
Training Time ◽  
Ear Recognition ◽  
Detail Image

An efficient ear recognition method by weighted wavelet transformation and Bi-Directional principal component analysis was proposed. First, each ear image was decomposed into four sub-images by wavelet transformation ,the four sub-images were low frequency image , vertical detail image ,horizontal detail image and high frequency image .Then the low frequency image was decomposed into four sub-images, the four-images were weighted by different coefficients, then ,the four sub-images were reconstructed into a image .On this basis ,the feature was extraction by the BDPCA method ,and then we use the k-Nearest Neighbor Classification to recognition .Experimental results show that the method have high recognition rate and shorted training time.

scholarly journals Improved SinGAN Integrated with an Attentional Mechanism for Remote Sensing Image Classification

2021 ◽  
Vol 13 (9) ◽  
pp. 1713
Author(s):  
Songwei Gu ◽  
Rui Zhang ◽  
Hongxia Luo ◽  
Mengyao Li ◽  
Huamei Feng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Real Life ◽  
Attention Mechanism ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Natural Image ◽  
Remote Sensing Images ◽  
Training Time ◽  
Adversarial Networks ◽  
Remote Sensing Image Classification

Deep learning is an important research method in the remote sensing field. However, samples of remote sensing images are relatively few in real life, and those with markers are scarce. Many neural networks represented by Generative Adversarial Networks (GANs) can learn from real samples to generate pseudosamples, rather than traditional methods that often require more time and man-power to obtain samples. However, the generated pseudosamples often have poor realism and cannot be reliably used as the basis for various analyses and applications in the field of remote sensing. To address the abovementioned problems, a pseudolabeled sample generation method is proposed in this work and applied to scene classification of remote sensing images. The improved unconditional generative model that can be learned from a single natural image (Improved SinGAN) with an attention mechanism can effectively generate enough pseudolabeled samples from a single remote sensing scene image sample. Pseudosamples generated by the improved SinGAN model have stronger realism and relatively less training time, and the extracted features are easily recognized in the classification network. The improved SinGAN can better identify sub-jects from images with complex ground scenes compared with the original network. This mechanism solves the problem of geographic errors of generated pseudosamples. This study incorporated the generated pseudosamples into training data for the classification experiment. The result showed that the SinGAN model with the integration of the attention mechanism can better guarantee feature extraction of the training data. Thus, the quality of the generated samples is improved and the classification accuracy and stability of the classification network are also enhanced.

scholarly journals k-Nearest Neighbor Learning with Graph Neural Networks

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 830
Author(s):  
Seokho Kang
Keyword(s):  
Neural Network ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Weighting Function ◽  
High Sensitivity ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Main Challenge ◽  
Benchmark Datasets ◽  
Graph Neural Networks

k-nearest neighbor (kNN) is a widely used learning algorithm for supervised learning tasks. In practice, the main challenge when using kNN is its high sensitivity to its hyperparameter setting, including the number of nearest neighbors k, the distance function, and the weighting function. To improve the robustness to hyperparameters, this study presents a novel kNN learning method based on a graph neural network, named kNNGNN. Given training data, the method learns a task-specific kNN rule in an end-to-end fashion by means of a graph neural network that takes the kNN graph of an instance to predict the label of the instance. The distance and weighting functions are implicitly embedded within the graph neural network. For a query instance, the prediction is obtained by performing a kNN search from the training data to create a kNN graph and passing it through the graph neural network. The effectiveness of the proposed method is demonstrated using various benchmark datasets for classification and regression tasks.

Two-parameter KNN algorithm and its application in recognition of brand rice

2021 ◽  
pp. 1-7
Author(s):  
Zhu Siyu ◽  
He Chongnan ◽  
Song Mingjuan ◽  
Li Linna
Keyword(s):  
Near Infrared ◽  
Nearest Neighbor ◽  
Recognition Accuracy ◽  
Principal Component ◽  
Kernel Principal Component Analysis ◽  
K Nearest Neighbor ◽  
Fisher Discriminant Analysis ◽  
Pattern Class ◽  
Fisher Discriminant ◽  
Two Parameter

In response to the frequent counterfeiting of Wuchang rice in the market, an effective method to identify brand rice is proposed. Taking the near-infrared spectroscopy data of a total of 373 grains of rice from the four origins (Wuchang, Shangzhi, Yanshou, and Fangzheng) as the observations, kernel principal component analysis(KPCA) was employed to reduce the dimensionality, and Fisher discriminant analysis(FDA) and k-nearest neighbor algorithm (KNN) were used to identify brand rice respectively. The effects of the two recognition methods are very good, and that of KNN is relatively better. Howerver the shortcomings of KNN are obvious. For instance, it has only one test dimension and its test of samples is not delicate enough. In order to further improve the recognition accuracy, fuzzy k-nearest neighbor set is defined and fuzzy probability theory is employed to get a new recognition method –Two-Parameter KNN discrimination method. Compared with KNN algorithm, this method increases the examination dimension. It not only examines the proportion of the number of samples in each pattern class in the k-nearest neighbor set, but also examines the degree of similarity between the center of each pattern class and the sample to be identified. Therefore, the recognition process is more delicate and the recognition accuracy is higher. In the identification of brand rice, the discriminant accuracy of Two-Parameter KNN algorithm is significantly higher than that of FDA and that of KNN algorithm.

Estimation of biophysical characteristics for highly variable mixed-conifer stands using small-footprint lidar

2006 ◽  
Vol 36 (5) ◽  
pp. 1129-1138 ◽  
Author(s):  
Jennifer L. Rooker Jensen ◽  
Karen S Humes ◽  
Tamara Conner ◽  
Christopher J Williams ◽  
John DeGroot
Keyword(s):  
Regression Model ◽  
Large Scale ◽  
Canopy Height ◽  
Training Data ◽  
Lidar Data ◽  
Mixed Conifer ◽  
Wood Volume ◽  
Small Footprint ◽  
Mean Square Errors ◽  
Single Regression

Although lidar data are widely available from commercial contractors, operational use in North America is still limited by both cost and the uncertainty of large-scale application and associated model accuracy issues. We analyzed whether small-footprint lidar data obtained from five noncontiguous geographic areas with varying species and structural composition, silvicultural practices, and topography could be used in a single regression model to produce accurate estimates of commonly obtained forest inventory attributes on the Nez Perce Reservation in northern Idaho, USA. Lidar-derived height metrics were used as predictor variables in a best-subset multiple linear regression procedure to determine whether a suite of stand inventory variables could be accurately estimated. Empirical relationships between lidar-derived height metrics and field-measured dependent variables were developed with training data and acceptable models validated with an independent subset. Models were then fit with all data, resulting in coefficients of determination and root mean square errors (respectively) for seven biophysical characteristics, including maximum canopy height (0.91, 3.03 m), mean canopy height (0.79, 2.64 m), quadratic mean DBH (0.61, 6.31 cm), total basal area (0.91, 2.99 m2/ha), ellipsoidal crown closure (0.80, 0.08%), total wood volume (0.93, 24.65 m3/ha), and large saw-wood volume (0.75, 28.76 m3/ha). Although these regression models cannot be generalized to other sites without additional testing, the results obtained in this study suggest that for these types of mixed-conifer forests, some biophysical characteristics can be adequately estimated using a single regression model over stands with highly variable structural characteristics and topography.

Sign in / Sign up

Export Citation Format

Share Document