The VLDB journal : the international journal on very large data bases.

Picture processing system by computer complex and recognition of human faces

The History of Information Security: A Comprehensive Handbook

Performing predefined tasks using the human–robot interaction on speech recognition for an industrial robot

The lack of dopamine in the human brain is the cause of Parkinson disease (PD) which is a degenerative disorder common globally to older citizens. However, late detection of this disease before the first clinical diagnosis has led to increased mortality rate. Research effort towards the early detection of PD has encountered challenges such as: small dataset size, class imbalance, overfitting, high false detection rate, model complexity, etc. This paper aims to improve early detection of PD using machine learning through data augmentation for very small datasets. We propose using Spline interpolation and Piecewise Cubic Hermite Interpolating Polynomial (Pchip) interpolation methods to generate synthetic data instances. We further investigate on reducing dimensionality of features for effective and real-time classification while considering computational complexity of implementation on real-life mobile phones. For classification we use Bidirectional LSTM (BiLSTM) deep learning network and compare the results with traditional machine learning algorithms like Support Vector Machine (SVM), Decision Tree, Logistic regression, KNN and Ensemble bagged tree. For experimental validation we use the Oxford Parkinson disease dataset with 195 data samples, which we have augmented with 571 synthetic data samples. The results for BiLSTM shows that even with a holdout of 90%, the model was still able to effectively recognize PD with an average accuracy for ten rounds experiment using 22 features as 82.86%, 97.1%, and 96.37% for original, augmented (Spline) and augmented (Pchip) datasets, respectively. Our results show that proposed data augmentation schemes have significantly (p < 0.001) improved the accuracy of PD recognition on a small dataset using both classical machine learning models and BiLSTM

/pdf/bilstm-with-data-augmentation-using-interpolation-methods-to-2x0u192122.pdf

BiLSTM with Data Augmentation using Interpolation Methods to Improve Early Detection of Parkinson Disease

Nowadays, deep learning methods have been used in many areas such as big data analysis, speech and image processing with the increasing processing power and the development of graphics processors. In particular, face recognition systems have become one of the most important research topics in biometry. Light direction, reflection, emotional and physical changes in facial expression are the main factors in face recognition systems that make recognition difficult. Training of the system with the available data in small data sets is an important factor that negatively affects the performance. The Convolutional Neural Network (CNN) model is a deep learning architecture used for large amounts of training data. In this study, a small number of employee images set of a small-scale company has been increased by applying different filters. In addition, it has been tried to determine which data augmentation options have more effect on face recognition. Thus, non-real-time face recognition has been performed by training with new augmented dataset of each picture with many features.

/pdf/the-effects-of-augmented-training-dataset-on-performance-of-4gqeoneg0j.pdf

The Effects of Augmented Training Dataset on Performance of Convolutional Neural Networks in Face Recognition System

Text generation systems provide facilities such as making new information deductions from the existing ones, getting information related to them by going out to a knowledgeable way, and generating more detailed results about the calls to the users by generating the codes entered on the internet. In this study, it is aimed to generate meaningful new Turkish sentences using class-based n-gram model from the sentences in the source data set. In order to realize sentence production, a trigram model is proposed and sentences are generated from the word or word groups in the sentence to the number of groups related to it. Thus, new sentences are generated, none of which were identical to the others.

Turkish meaningful text generation with class based n-gram model

As an increasing number of digital images are generated, a demand for an efficient and effective image retrieval mechanisms grows. In this work, we present a new skeleton-based algorithm for 2D and 3D shape retrieval. The algorithm starts by drawing circles (spheres for 3D) of increasing radius around skeletons. Since each skeleton corresponds to the center of a maximally inscribed circle (sphere), this process results in circles (spheres) that are partially inside the shape. Computing the ratio between pixels that lie within the shape and the total number of pixels allows us to distinguish shapes with similar skeletons. Experimental evaluation of the proposed approach including a comprehensive comparison with the previous techniques demonstrates both effectiveness and robustness of our algorithm for shape retrieval using several 2D and 3D datasets.

2D and 3D shape retrieval using skeleton filling rate

As an increasing number of digital images are generated, a demand for an efficient and effective image retrieval mechanisms grows. In this work, we present a new skeleton-based shape retrieval algorithm, which starts by drawing circles of increasing radius around skeleton points. Since each skeleton corresponds to the center of a maximally inscribed circle, this process results in circles that are partially inside the shape. Computing the ratio between pixels that lie within the shape and the total number of pixels allows us to distinguish shapes with similar skeletons. Experimental evaluation of the proposed approach including a comparison with the previous techniques demonstrates both effectiveness and robustness of our algorithm for shape retrieval experiments.

Skeleton Filling Rate for Shape Recognition

Biometric artificial intelligence application depends on amount of material on which they are trained. In this paper, we integrated Glow data augmentation technique to diversify the facial images dataset to analyze its effects on face classification and identification system based on Convolutional Neural Network (CNN). In first phase, we trained our CNN with publicly available Labeled Faces in the Wild (LFW) database and evaluated the proposed system, which achieved accuracy of 92.2%. In second phase, we diversified LFW dataset with Glow method and then trained our CNN network. The experiment results shows that Glow data augmentation improved the accuracy of proposed network to 93.6%.

Yahya Sirin

Papers

The Effects of Augmented Training Dataset on Performance of Convolutional Neural Networks in Face Recognition System

Turkish meaningful text generation with class based n-gram model

2D and 3D shape retrieval using skeleton filling rate

Skeleton Filling Rate for Shape Recognition

Effects of Glow Data Augmentation on Face Recognition System based on Deep Learning