Mixed Normal Vector Estimation Strategy for Unstructured Point Clouds

Convolutional Neural Network (CNN) is a deep learning algorithm that is widely used to identify and classify a digital image object. In this study the Convolutional Neural Network (CNN) is used as an algorithm that functions to identify leaf types (certain plants) based on images obtained from a public dataset provider named Daun Jamu Indonesia. The existence of image characteristics causes the assistance process to require a more detailed feature selection process. Therefore the CNN method is used in order to solve the problem. The Convolutional Neural Network (CNN) method is capable of performing image recognition by minimizing feature extraction. CNN is also reliable in processing unstructured data because it uses a multi-layered structure of artificial reasoning networks. The image recognition process is carried out by looking for the shape of the model that matches the processed data in order to get the best results. In this study, the augmentation process was carried out on the training data and validation data so that overfitting does not occur in the Convolutional Neural Network (CNN). The results obtained in this study indicate that the Convolutional Neural Network (CNN) method can identify leaf types with a measured accuracy rate of 92% using the Confusion Matrix evaluation method. It is hoped that this research can be used as a reference for the use of the Convolutional Neural Network (CNN) method for image data, especially plant leaf types.

This paper analyzes and studies the task of traffic sign recognition in the complex traffic road environment, analyzes the defects of the traditional classification algorithm and CNN (convolutional neural network) algorithm, cannot maximize the elimination of the lack of use of image disturbance information and hidden image information. This paper proposes a traffic sign recognition algorithm based on CNN, PCA (Principal Component Analysis) and LVQ (Learning Vector Quantization) algorithm, and uses PCA algorithm and LVQ algorithm to perform eigenvectors generated by CNN model. Dimensionality reduction and classification processing eliminates picture interference information and in-depth use of hidden information in pictures, further improves the accuracy of identification of traffic signs in complex environments, validates the effectiveness of the proposed method on the GTSRB data set, and relates to depth volumes. The product network model, LeNet-5, performs comparative experiments and proves that this method can further improve the classification accuracy.

This research aims to implement deep learning techniques to determine fact and fake news in Indonesian language. The methods used are Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The stages of the research consisted of collecting data, labeling data, preprocessing data, word embedding, splitting data, forming CNN and LSTM models, evaluating, testing new input data and comparing evaluations of the established CNN and LSTM models. The Data are collected from a fact and fake news provider site that is valid, namely TurnbackHoax.id. There are 1786 news used in this study, with 802 fact and 984 fake news. The results indicate that the CNN and LSTM methods were successfully applied to determine fact and fake news in Indonesian language properly. CNN has an accuracy test, precision and recall value of 0.88, while the LSTM model has an accuracy test and precision value of 0.84 and a recall of 0.83. In testing the new data input, all of the predictions obtained by CNN are correct, while the prediction results obtained by LSTM have 1 wrong prediction. Based on the evaluation results and the results of testing the new data input, the model produced by the CNN method is better than the model produced by the LSTM method.

The normal vector estimation of the large-scale scattered point cloud (LSSPC) plays an important role in point-based shape editing. However, the normal vector estimation for LSSPC cannot meet the great challenge of the sharp increase of the point cloud that is mainly attributed to its low computational efficiency. In this paper, a novel, fast method-based on bi-linear interpolation is reported on the normal vector estimation for LSSPC. We divide the point sets into many small cubes to speed up the local point search and construct interpolation nodes on the isosurface expressed by the point cloud. On the premise of calculating the normal vectors of these interpolated nodes, a normal vector bi-linear interpolation of the points in the cube is realized. The proposed approach has the merits of accurate, simple, and high efficiency, because the algorithm only needs to search neighbor and calculates normal vectors for interpolation nodes that are usually far less than the point cloud. The experimental results of several real and simulated point sets show that our method is over three times faster than the Elliptic Gabriel Graph-based method, and the average deviation is less than 0.01 mm.

Brain Computer Interface (BCI) is a system that connects the human brain with the outside world for people who have motor skills disability problems. One form of utilization is the P300 speller which is used for character recognition or detection by classifying the P300 signal. The Convolutional Neural Network (CNN) method is a deep learning method that can be used to handle signal problems with ID-CNN. At the initial stage the data signal will be transformed and followed by a duplication process using RandomOverSampling because the amount of data in each class is not balanced. The data will be divided into training, validation, and test data. After that, a training with CNN will be conducted and followed by an evaluation to find the best model. The test results from this study are a good-fitting CNN model with an evaluation value consisting of an accuracy of 94.27%, precision of 90.64%, sensitivity / recall of 98.30%, and f-measure of 94.31%. Based on the test, the CNN method can be used and implemented in authentication detection based on the P300 signal.

Aiming at the time-consuming problem of the full-wave (FW) simulation of the scattering characteristics of the traditional graphene reconfigurable reflectarray antenna, a fast prediction method of electromagnetic (EM) response based on deep learning is proposed. The convolutional neural network (CNN) method in deep learning is effectively used in the research of this paper. This method first discretizes the input vector (patch geometry, chemical potential, frequency, incident angle, etc.) of the graphene reflectarray antenna, and then preprocesses the data into a two-dimensional image suitable for CNN training, and finally uses CNN to train the model instead of extensive FW simulation calculations, the EM response of the reflectarray antenna is calculated. The training results of three algorithms of support vector regression (SVR), radial basis function network (RBFN) and CNN are comprehensively compared. The experimental results show that CNN method has good performance and accuracy in the EM response prediction of the graphene reconfigurable reflectarray antenna, with an accuracy of over 99%, and can also save at least 99% of time.

Some researchers propose using the Convolutional Neural Network (CNN) method to classified batik images. It can extract features automatically without the need to define feature manually from the image. However, CNN’s weakness is that its accuracy is quite low, especially for small-sized datasets, compared to machine learning methods that use handcrafted feature extraction. In this research, an ensemble CNN method is proposed to improve the accuracy of the CNN method in classifying batik images. This method will train several CNN models at once, and then by voting and averaging techniques, the output label will be determined. Test results for two different datasets show this method can improve the accuracy of the CNN method and get an accuracy value of 100%. This method is also proven to extract features faster than the state-of-the-art method like MTCD+SVM, which is included in the hand-crafted feature extraction category.

Garbage is a unique problem in Indonesia. From ordinary waste to limited emergency plastic waste, Indonesia is the second-largest source of plastic waste in the world. Separate collection and disposal of waste is one way to reduce the waste generated by society and industry in Indonesia. Sorting out the types of waste is the first step before the recycling process. In the field of Computer Vision research, it is difficult to see the type and form of waste with a camera, therefore this study aims to overcome this problem by using Deep Learning technology which is expected to be implemented in the whole of Indonesia starting from some of the largest waste-producing cities. Deep Learning is a computer (AI) technique for learning like a human - with experiments being a Part of Machine Learning that can be used to classify images. The method used in this study uses the Convolutional Neural Network (CNN) method which can be used to detect and recognize objects in an image, which can be used to create an automatic waste classification system. Broadly speaking, CNN utilizes the convolution process by moving a convolution kernel (filter) of a certain size to an image, the computer gets new representative information from the results of multiplying that part of the image with the filter used. The test results show that the CNN method can classify inorganic waste with accuracy. 96% and organic waste with an accuracy of 62%.

Aiming at the problem of objects in image recognition rectangle, but objects which are input into convolutional neural networks square, the object recognition model was put forward which was based on BING method to realize object estimate, used vectorization of convolutional neural networks to realize input square image in convolutional networks, therefore, built joint convolution neural networks, which achieve multiple size image input. Verified by experiments, the accuracy of multi-object image recognition was improved by 6.70% compared with single vectorization of convolutional neural networks. Therefore, image recognition method of joint convolutional neural networks can enhance the accuracy in image recognition, especially for target in rectangular shape.

The study of convolutional neural networks for 3D point clouds is becoming increasingly popular, and the difficulty lies mainly in the disorder and irregularity of point clouds. At present, it is straightforward to propose a convolution operation and perform experimental validation. Although good results are achieved, the principles behind them are not explained—i.e., why this can solve the disorder and irregularity of point clouds—and it is difficult for the researchers to design a point cloud convolution network suitable for their needs. For this phenomenon, we propose a point convolution network framework based on spatial location correspondence. Following the correspondence principle can guide us in designing convolution networks adapted to our needs. We analyzed the intrinsic mathematical nature of the convolution operation, and we argue that the convolution operation remains the same when the spatial location correspondence between the convolution kernel points and the convolution range elements remains unchanged. Guided by this principle, we formulated a general point convolution framework based on spatial location correspondence, which explains how to handle a disordered point cloud. Moreover, we discuss different kinds of correspondence based on spatial location, including M-to-M, M-to-N, and M-to-1 relationships, etc., which explain how to handle the irregularity of point clouds. Finally, we give the example of a point convolution network whose convolution kernel points are generated based on the sample’s covariance matrix distribution according to our framework. Our convolution operation can be applied to various point cloud processing networks. We demonstrated the effectiveness of our framework for point cloud classification and semantic segmentation tasks, achieving competitive results with state-of-the-art networks.

One of the conditions for hiring workers in Indonesian companies is to pass a psychology test. Psychology test has many types of tests, one of which is the Baum test, a tree-drawing test. Baum test requires participants to draw a tree following the imagination of the participants. Later, the picture of the participant tree obtained from the Baum test will be assessed by psychologists as one of the labor assessment tools. This assessment is based on the shape of the tree crown, leaf shape, tree size on paper, etc. Currently, the assessment of the Baum test is still done manually by a psychologist. In order to help psychologists in assessing the Baum test, we propose an application in the form of a model that can study and classify tree images based on the tree size in the image by using the Convolutional Neural Network (CNN) method. CNN method allows computers to classify an object. The data are provided in the form of digital images of tree images from Baum testing that has been conducted. The data that has been collected will be used to train the model. The model used in this study has an architecture in the form of a convolution layer with a kernel size of 3×3, a pooling layer with a parameter size of 2×2, a dropout layer, a flatten layer, and a dense layer. The model was trained with 60 epochs and had a test and training data scale of 70:30. The model in this research has an accuracy of 74.07% in predetermined data testing and has an accuracy of 75% in new data testing.

Deep convolutional neural network (CNN) and its derivatives have recently shown great promise in the prediction of brain disorders using brain connectome data. Existing deep CNN methods using single global row and column convolutional filters have limited ability to extract discriminative information from brain connectome for prediction tasks. This paper presents a novel deep Connectome-Inception CNN (ConCeptCNN) model, which is developed based on multiple convolutional filters. The proposed model is used to extract topological features from brain connectome data for neurological disorders classification and analysis. The ConCeptCNN uses multiple vector-shaped filters extract topological information from the brain connectome at different levels for complementary feature embeddings of brain connectome. The proposed model is validated using two datasets: the Neuro Bureau ADHD-200 dataset and the Cincinnati Early Prediction Study (CINEPS) dataset. In a cross-validation experiment, the ConCeptCNN achieved a prediction accuracy of 78.7% for the detection of attention deficit hyperactivity disorder (ADHD) in adolescents and an accuracy of 81.6% for the prediction of cognitive deficits at 2 years corrected age in very preterm infants. In addition to the classification tasks, the ConCeptCNN identified several brain regions that are discriminative to neurodevelopmental disorders. We compared the ConCeptCNN with several peer CNN methods. The results demonstrated that proposed model improves overall classification performance of neurodevelopmental disorders prediction tasks.

Image denoising faces significant challenges, arising from the sources of noise. Specifically, Gaussian, impulse, salt, pepper, and speckle noise are complicated sources of noise in imaging. Convolutional neural network (CNN) has increasingly received attention in image denoising task. Several CNN methods for denoising images have been studied. These methods used different datasets for evaluation. In this paper, we offer an elaborate study on different CNN techniques used in image denoising. Different CNN methods for image denoising were categorized and analyzed. Popular datasets used for evaluating CNN image denoising methods were investigated. Several CNN image denoising papers were selected for review and analysis. Motivations and principles of CNN methods were outlined. Some state-of-the-arts CNN image denoising methods were depicted in graphical forms, while other methods were elaborately explained. We proposed a review of image denoising with CNN. Previous and recent papers on image denoising with CNN were selected. Potential challenges and directions for future research were equally fully explicated.

For the depth data of a single time of flight (TOF) sensor, the existing detection can determine the safe distance and issue a safety alarm, but it cannot be combined with the robot attitude. Based on this, a TOF sensor based Principal component analysis (PCA) normal vector estimation method is proposed in this paper, which transforms the depth data into a three-dimensional point cloud, and uses the PCA method to calculate the normal vector of the point cloud. It lays a foundation for real-time attitude adjustment of future robots.

Remote sensing technology provides an unprecedented tool for the continuous and real-time monitoring of atmospheric SO2 from volcanic eruption and anthropogenic emission. The Global Ozone Monitoring Experiment (GOME), SCanning Imaging Absorption spectroMeter for Atmospheric CHartographY (SCIAMACHY), and Ozone Monitoring Instrument (OMI) have high SO2 monitoring capability. The OMI, which was launched on the EOS/Aura platform in July 2004, has the same hyperspectral measurements as the GOME and SCIAMACHY, but offers the improved spatial resolution at nadir (1324 km2) and daily global coverage for short-lifetime SO2. For OMI operational SO2 planetary boundary layer (PBL) retrieval, the previous band residual difference (BRD) algorithm has been replaced by principal component analysis (PCA) algorithm, which effectively reduces the systematic biases in SO2 column retrievals. However, there are few studies on the evaluations and validations of PCA SO2 retrievals over China, and the long-term comparisons with BRD SO2 retrievals also need to be conducted. In this study, the accuracies of PCA and BRD SO2 retrievals are validated by using ground-based multi axis differential optical absorption spectroscopy (MAX-DOAS) located in Beijing, and regional atmospheric modeling system, community multi-scale air quality (RAMS-CMAQ) modeling system model which can simulate the vertical distribution of atmospheric SO2. Moreover, BRD and PCA SO2 retrievals from oceanic area, eastern China and Reunion volcanic eruption are compared to find the long-term trend and spatiotemporal differences between SO2 columns. Finally, the uncertainty of SO2 retrieval, caused by measurement errors, band selection and input parameter errors in radiative transfer model, are analysed to understand the limitations of BRD and PCA algorithms. Results show that both PCA and BRD SO2 retrievals over Beijing are lower than ground-based MAX-DOAS measurements of SO2. PCA and BRD SO2 retrievals over eastern China are lower than the simulated SO2 columns from RAMS-CMAQ in winter 2008, but in July and August BRD SO2 columns are higher than RAMS-CMAQ simulations. The values of SO2 columns from BRD over China are more consistent with those from ground-based MAX-DOAS and RAMS-CMAQ model than from PCA. Although PCA algorithm effectively reduces the noise in SO2 column retrieval, SO2 columns from PCA over China are lower than those from BRD. For oceanic area where SO2 amount is nearly zero, the standard deviation of PCA results is lower than that of BRD, but the absolute value of averaged PCA SO2 column is larger than that of BRD. In the case of Reunion volcanic eruption with SO2 columns larger than 25 DU, the BRD SO2 columns are lower than PCA retrievals. Meanwhile, with the increase of SO2 column, the difference between BRD and PCA SO2 retrievals increases. Detailed uncertainty analysis shows the influences of measurement errors, band selection and inputs of radiative transfer model on the retrieval results. This study is important for developing the retrieval algorithm, and can also improve the application of OMI SO2 products.