Yaman Akbulut

NS-k-NN: Neutrosophic Set-Based k-Nearest Neighbors Classifier

k-nearest neighbors (k-NN), which is known to be a simple and efficient approach, is a non-parametric supervised classifier. It aims to determine the class label of an unknown sample by its k-nearest neighbors that are stored in a training set. The k-nearest neighbors are determined based on some distance functions. Although k-NN produces successful results, there have been some extensions for improving its precision. The neutrosophic set (NS) defines three memberships namely T, I and F. T, I, and F shows the truth membership degree, the false membership degree, and the indeterminacy membership degree, respectively. In this paper, the NS memberships are adopted to improve the classification performance of the k-NN classifier. A new straightforward k-NN approach is proposed based on NS theory. It calculates the NS memberships based on a supervised neutrosophic c-means (NCM) algorithm. A final belonging membership U is calculated from the NS triples as U = T + I − F . A similar final voting scheme as given in fuzzy k-NN is considered for class label determination. Extensive experiments are conducted to evaluate the proposed method’s performance. To this end, several toy and real-world datasets are used. We further compare the proposed method with k-NN, fuzzy k-NN, and two weighted k-NN schemes. The results are encouraging and the improvement is obvious.

DeepEMGNet: An Application for Efficient Discrimination of ALS and Normal EMG Signals

This paper proposes a deep learning application for efficient classification of amyotrophic lateral sclerosis (ALS) and normal Electromyogram (EMG) signals. EMG signals are helpful in analyzing of the neuromuscular diseases like ALS. ALS is a well-known brain disease, which progressively degenerates the motor neurons. Most of the previous works about EMG signal classification covers a dozen of basic signal processing methodologies such as statistical signal processing, wavelet analysis, and empirical mode decomposition (EMD). In this work, a different application is implemented which is based on time-frequency (TF) representation of EMG signals and convolutional neural networks (CNN). Short Time Fourier Transform (STFT) is considered for TF representation. Two convolution layers, two pooling layer, a fully connected layer and a lost function layer is considered in CNN architecture. The efficiency of the proposed implementation is tested on publicly available EMG dataset. The dataset contains 89 ALS and 133 normal EMG signals with 24 kHz sampling frequency. Experimental results show 96.69% accuracy. The obtained results are also compared with other methods, which show the superiority of the proposed method.

KNCM: Kernel Neutrosophic c-Means Clustering

Abstract Data clustering is an important step in data mining and machine learning. It is especially crucial to analyze the data structures for further procedures. Recently a new clustering algorithm known as ‘neutrosophic c-means’ (NCM) was proposed in order to alleviate the limitations of the popular fuzzy c-means (FCM) clustering algorithm by introducing a new objective function which contains two types of rejection. The ambiguity rejection which concerned patterns lying near the cluster boundaries, and the distance rejection was dealing with patterns that are far away from the clusters. In this paper, we extend the idea of NCM for nonlinear-shaped data clustering by incorporating the kernel function into NCM. The new clustering algorithm is called Kernel Neutrosophic c-Means (KNCM), and has been evaluated through extensive experiments. Nonlinear-shaped toy datasets, real datasets and images were used in the experiments for demonstrating the efficiency of the proposed method. A comparison between Kernel FCM (KFCM) and KNCM was also accomplished in order to visualize the performance of both methods. According to the obtained results, the proposed KNCM produced better results than KFCM.

A Novel Neutrosophic Weighted Extreme Learning Machine for Imbalanced Data Set

Extreme learning machine (ELM) is known as a kind of single-hidden layer feedforward network (SLFN), and has obtained considerable attention within the machine learning community and achieved various real-world applications. It has advantages such as good generalization performance, fast learning speed, and low computational cost. However, the ELM might have problems in the classification of imbalanced data sets. In this paper, we present a novel weighted ELM scheme based on neutrosophic set theory, denoted as neutrosophic weighted extreme learning machine (NWELM), in which neutrosophic c-means (NCM) clustering algorithm is used for the approximation of the output weights of the ELM. We also investigate and compare NWELM with several weighted algorithms. The proposed method demonstrates advantages to compare with the previous studies on benchmarks.

A novel microaneurysms detection approach based on convolutional neural networks with reinforcement sample learning algorithm

Microaneurysms (MAs) are known as early signs of diabetic-retinopathy which are called red lesions in color fundus images. Detection of MAs in fundus images needs highly skilled physicians or eye angiography. Eye angiography is an invasive and expensive procedure. Therefore, an automatic detection system to identify the MAs locations in fundus images is in demand. In this paper, we proposed a system to detect the MAs in colored fundus images. The proposed method composed of three stages. In the first stage, a series of pre-processing steps are used to make the input images more convenient for MAs detection. To this end, green channel decomposition, Gaussian filtering, median filtering, back ground determination, and subtraction operations are applied to input colored fundus images. After pre-processing, a candidate MAs extraction procedure is applied to detect potential regions. A five-stepped procedure is adopted to get the potential MA locations. Finally, deep convolutional neural network (DCNN) with reinforcement sample learning strategy is used to train the proposed system. The DCNN is trained with color image patches which are collected from ground-truth MA locations and non-MA locations. We conducted extensive experiments on ROC dataset to evaluate of our proposal. The results are encouraging.

An Efficient Image Segmentation Algorithm Using Neutrosophic Graph Cut

Segmentation is considered as an important step in image processing and computer vision applications, which divides an input image into various non-overlapping homogenous regions and helps to interpret the image more conveniently. This paper presents an efficient image segmentation algorithm using neutrosophic graph cut (NGC). An image is presented in neutrosophic set, and an indeterminacy filter is constructed using the indeterminacy value of the input image, which is defined by combining the spatial information and intensity information. The indeterminacy filter reduces the indeterminacy of the spatial and intensity information. A graph is defined on the image and the weight for each pixel is represented using the value after indeterminacy filtering. The segmentation results are obtained using a maximum-flow algorithm on the graph. Numerous experiments have been taken to test its performance, and it is compared with a neutrosophic similarity clustering (NSC) segmentation algorithm and a graph-cut-based algorithm. The results indicate that the proposed NGC approach obtains better performances, both quantitatively and qualitatively.

An effective color texture image segmentation algorithm based on hermite transform

Abstract In this paper, an efficient color texture image segmentation approach is proposed. The proposed approach uses color and texture information independently. The color information is obtained by converting the RGB color space to Luv color space and each color component is considered as a color descriptor. For texture descriptors, Hermite transform is considered. Hermite transform uses the Hermite filters which are formed by the product of Hermite polynomials with Gaussian function. Instead of using all Hermite filters, a filter selection process is adopted to obtain optimal filters. A feature image is constructed based on the magnitude of each filter response. A region smoothing procedure is employed for both the color components and the feature image in order to make the region smoother while preserving the edge information. To this end, weighted least square edge-preserving filtering is used. Comprehensive experiments were conducted to demonstrate the efficiency of the proposed method, using the Berkeley segmentation dataset.

Deep learning based face liveness detection in videos

The human face is an important biometric quantity which can be used to access a user-based system. As human face images can easily be obtained via mobile cameras and social networks, user-based access systems should be robust against spoof face attacks. In other words, a reliable face-based access system can determine both the identity and the liveness of the input face. To this end, various feature-based spoof face detection methods have been proposed. These methods generally apply a series of processes against the input image(s) in order to detect the liveness of the face. In this paper, a deep-learning-based spoof face detection is proposed. Two different deep learning models are used to achieve this, namely local receptive fields (LRF)-ELM and CNN. LRF-ELM is a recently developed model which contains a convolution and a pooling layer before a fully connected layer that makes the model fast. CNN, however, contains a series of convolution and pooling layers. In addition, the CNN model may have more fully connected layers. A series of experiments were conducted on two popular spoof face detection databases, namely NUAA and CASIA. The obtained results were then compared, and the LRF-ELM method yielded better results against both databases.

A novel approach based on image processing algorithms for microaneurysm candidate detection

Interpretting color fundus images by doctors is enhanced by computer-aided detection (CAD). Microaneurysm (MA) detection in CAD is an important step to identify the retinal diseases automatically. However, MA detection is still a challenging task due to the variations in retinal images. In this paper, a new MA extraction method is developed. The proposed method contains two steps: 1.) image pre-processing 2.) candidate extraction. The pre-processing stage includes a variety of operations such as binary region of interest (ROI) mask generation, median and Gaussian filtering, background subtraction and bright pixel determination. On the other hand, MA candidate extraction is carried out in five steps; 1.) The spiral sequence of gray scale values is obtained 2.) An increasing length segmentation approach is employed for partitioning of the spirally sequenced gray scale values 3.) Two new images are generated based on the mean gray scale values 4.) The newly generated images are thresholded 5.) All connected and elongated structures are removed. Our experiments and analysis show that our proposed method is efficient. Furthermore, we demonstrate that through experimental modification of a threshold parameter, our method has the potential to achieve over 90% accuracy.

Gender recognition from face images with deep learning

Gender is one of the main factors in the interaction between individuals. Recently, with the development of social media environments and smartphones, gender recognition applications have both begun to grow and become important. In many fields such as face recognition, facial expression analysis, tracking and surveillance, human-computer interaction, biometry, gender recognition applications can be seen. In this study, gender recognition was carried out from face images with deep learning. The Local Receptive Field-Extreme Learning Machine (LRF-ELM) and Convolutional Neural Networks (CNN) were used as the deep learning methods. Experiments were performed on a face data set generated for age and gender recognition. LRF-ELM and CNN achieved performance rate of 80% and 87.13%, respectively.