An Efficient Artificial Neural Network for Coronary Heart Disease Prediction

Coronary heart disease is rapidly increasing over these days also with a significant number of deaths. A large population around the world is suffering from the disease. When surveys were carried out of the death rate and the number of people suffering from the coronary heart disease, it was understood that how important is the diagnosis of this disease at an early stage. The old way for detecting the disease was not found effective. This paper suggests a different method and technology to detect the disease and the proposed method is more effective than the old traditional methods. In this paper, an artificial neural network that predicts the coronary heart disease is used with 14 features as the input. Feature selection, data preprocessing, and removing irrelevant data was done before training the neural network. The backpropagation algorithm was used for making the neural network learn the features. The output of data was basically binary but the neural network was trained to give the output as a probability between 0 and 1. Two algorithms were proposed for this prediction named Logistic Regression and Artificial Neural Network but the later was selected because of the accuracy of 94%. The accuracy of Logistic Regression was 87%.

Evolutionary Computation for Feature Manipulation in Salient Object Detection

<p>The human visual system can efficiently cope with complex natural scenes containing various objects at different scales using the visual attention mechanism. Salient object detection (SOD) aims to simulate the capability of the human visual system in prioritizing objects for high-level processing. SOD is a process of identifying and localizing the most attention grabbing object(s) of a scene and separating the whole extent of the object(s) from the scene. In SOD, significant research has been dedicated to design and introduce new features to the domain. The existing saliency feature space suffers from some difficulties such as having high dimensionality, features are not equally important, some features are irrelevant, and the original features are not informative enough. These difficulties can lead to various performance limitations. Feature manipulation is the process which improves the input feature space to enhance the learning quality and performance. Evolutionary computation (EC) techniques have been employed in a wide range of tasks due to their powerful search abilities. Genetic programming (GP) and particle swarm optimization (PSO) are well-known EC techniques which have been used for feature manipulation. The overall goal of this thesis is to develop feature manipulation methods including feature weighting, feature selection, and feature construction using EC techniques to improve the input feature set for SOD. This thesis proposes a feature weighting method utilizing PSO to explore the relative contribution of each saliency feature in the feature combination process. Saliency features are referred to the features which are extracted from different levels (e.g., pixel, segmentation) of an image to compute the saliency values over the entire image. The experimental results show that different datasets favour different weights for the employed features. The results also reveal that by considering the importance of each feature in the combination process, the proposed method has achieved better performance than that of the competitive methods. This thesis proposes a new bottom-up SOD method to detect salient objects by constructing two new informative saliency features and designing a new feature combination framework. The proposed method aims at developing features which target to identify different regions of the image. The proposed method makes a good balance between computational time and performance. This thesis proposes a GP-based method to automatically construct foreground and background saliency features. The automatically constructed features do not require domain-knowledge and they are more informative compared to the manually constructed features. The results show that GP is robust towards the changes in the input feature set (e.g., adding more features to the input feature set) and improves the performance by introducing more informative features to the SOD domain. This thesis proposes a GP-based SOD method which automatically produces saliency maps (a 2-D map containing saliency values) for different types of images. This GP-based SOD method applies feature selection and feature combination during the learning process for SOD. GP with built-in feature selection process which selects informative features from the original set and combines the selected features to produce the final saliency map. The results show that GP can potentially explore a large search space and find a good way to combine different input features. This thesis introduces GP for the first time to construct high-level saliency features from the low-level features for SOD, which aims to improve the performance of SOD, particularly on challenging and complex SOD tasks. The proposed method constructs fewer features that achieve better saliency performance than the original full feature set.</p>

Evolutionary Computation for Feature Manipulation in Salient Object Detection

<p>The human visual system can efficiently cope with complex natural scenes containing various objects at different scales using the visual attention mechanism. Salient object detection (SOD) aims to simulate the capability of the human visual system in prioritizing objects for high-level processing. SOD is a process of identifying and localizing the most attention grabbing object(s) of a scene and separating the whole extent of the object(s) from the scene. In SOD, significant research has been dedicated to design and introduce new features to the domain. The existing saliency feature space suffers from some difficulties such as having high dimensionality, features are not equally important, some features are irrelevant, and the original features are not informative enough. These difficulties can lead to various performance limitations. Feature manipulation is the process which improves the input feature space to enhance the learning quality and performance. Evolutionary computation (EC) techniques have been employed in a wide range of tasks due to their powerful search abilities. Genetic programming (GP) and particle swarm optimization (PSO) are well-known EC techniques which have been used for feature manipulation. The overall goal of this thesis is to develop feature manipulation methods including feature weighting, feature selection, and feature construction using EC techniques to improve the input feature set for SOD. This thesis proposes a feature weighting method utilizing PSO to explore the relative contribution of each saliency feature in the feature combination process. Saliency features are referred to the features which are extracted from different levels (e.g., pixel, segmentation) of an image to compute the saliency values over the entire image. The experimental results show that different datasets favour different weights for the employed features. The results also reveal that by considering the importance of each feature in the combination process, the proposed method has achieved better performance than that of the competitive methods. This thesis proposes a new bottom-up SOD method to detect salient objects by constructing two new informative saliency features and designing a new feature combination framework. The proposed method aims at developing features which target to identify different regions of the image. The proposed method makes a good balance between computational time and performance. This thesis proposes a GP-based method to automatically construct foreground and background saliency features. The automatically constructed features do not require domain-knowledge and they are more informative compared to the manually constructed features. The results show that GP is robust towards the changes in the input feature set (e.g., adding more features to the input feature set) and improves the performance by introducing more informative features to the SOD domain. This thesis proposes a GP-based SOD method which automatically produces saliency maps (a 2-D map containing saliency values) for different types of images. This GP-based SOD method applies feature selection and feature combination during the learning process for SOD. GP with built-in feature selection process which selects informative features from the original set and combines the selected features to produce the final saliency map. The results show that GP can potentially explore a large search space and find a good way to combine different input features. This thesis introduces GP for the first time to construct high-level saliency features from the low-level features for SOD, which aims to improve the performance of SOD, particularly on challenging and complex SOD tasks. The proposed method constructs fewer features that achieve better saliency performance than the original full feature set.</p>

Optimal Neuro Fuzzy Classification for Arrhythmia Data Driven System

This paper presents a data driven system used for cardiac arrhythmia classification. It applies the Neuro-Fuzzy Inference System (ANFIS) to classify MIT-BIH arrhythmia database electrocardiogram (ECG) recordings into five (5) heartbeat types. In fact, in order to obtain the input feature vector from recordings, a time scale method based on a Discrete Wavelet Transform (DWT) was investigated. Then, the time scale features are selected by applying the Principal Component Analysis (PCA). Therefore, the selected input feature vectors are classified by the Neuro-Fuzzy method. However, the ANFIS configuration needs mainly the choice of an initial Fuzzy Inference System (FIS) and the training algorithm. Indeed, two clustering algorithms which are the fuzzy c-means (FCM) and the subtractive ( SUBCLUST) algorithms, are applied to generate the initial FIS. Besides, for tuning the ANFIS membership function and rule base parameters, Gradient descent and evolutionary training algorithms are also evaluated. Gradient descent consists of the backpropagation (BP) method and its hybridization with the least square algorithm (Hybrid). However, the evolutionary training methods involve the Particle Swarm Optimization (PSO) and the Genetic Algorithm (GA). Therefore, eight (8) ANFIS are configured and assessed. Accordingly, a comparison study between their obtained Root Mean Square Error (RMSE) is analyzed. At the end, we have selected an optimal ANFIS which uses the SUBTRUCT algorithm to generate the initial FIS and the GA to tune its parameters. Moreover, to guarantee the effectiveness of this work, a comparison study with related works is done.

Multipath Lightweight Deep Network Using Randomly Selected Dilated Convolution

Robot vision is an essential research field that enables machines to perform various tasks by classifying/detecting/segmenting objects as humans do. The classification accuracy of machine learning algorithms already exceeds that of a well-trained human, and the results are rather saturated. Hence, in recent years, many studies have been conducted in the direction of reducing the weight of the model and applying it to mobile devices. For this purpose, we propose a multipath lightweight deep network using randomly selected dilated convolutions. The proposed network consists of two sets of multipath networks (minimum 2, maximum 8), where the output feature maps of one path are concatenated with the input feature maps of the other path so that the features are reusable and abundant. We also replace the 3×3 standard convolution of each path with a randomly selected dilated convolution, which has the effect of increasing the receptive field. The proposed network lowers the number of floating point operations (FLOPs) and parameters by more than 50% and the classification error by 0.8% as compared to the state-of-the-art. We show that the proposed network is efficient.

Employing GRU to combine feature maps in DeeplabV3 for a better segmentation model

In this paper, we aim to enhance the segmentation capabilities of DeeplabV3 by employing Gated Recurrent Neural Network (GRU). A 1-by-1 convolution in DeeplabV3 was replaced by GRU after the Atrous Spatial Pyramid Pooling (ASSP) layer to combine the input feature maps. The convolution and GRU have sharable parameters, though, the latter has gates that enable/disable the contribution of each input feature map. The experiments on unseen test sets demonstrate that employing GRU instead of convolution would produce better segmentation results. The used datasets are public datasets provided by MedAI competition.

Free-viewpoint Indoor Neural Relighting from Multi-view Stereo

We introduce a neural relighting algorithm for captured indoors scenes, that allows interactive free-viewpoint navigation. Our method allows illumination to be changed synthetically, while coherently rendering cast shadows and complex glossy materials. We start with multiple images of the scene and a three-dimensional mesh obtained by multi-view stereo (MVS) reconstruction. We assume that lighting is well explained as the sum of a view-independent diffuse component and a view-dependent glossy term concentrated around the mirror reflection direction. We design a convolutional network around input feature maps that facilitate learning of an implicit representation of scene materials and illumination, enabling both relighting and free-viewpoint navigation. We generate these input maps by exploiting the best elements of both image-based and physically based rendering. We sample the input views to estimate diffuse scene irradiance, and compute the new illumination caused by user-specified light sources using path tracing. To facilitate the network's understanding of materials and synthesize plausible glossy reflections, we reproject the views and compute mirror images . We train the network on a synthetic dataset where each scene is also reconstructed with MVS. We show results of our algorithm relighting real indoor scenes and performing free-viewpoint navigation with complex and realistic glossy reflections, which so far remained out of reach for view-synthesis techniques.

An Intelligent System to Assist Piano Composition and Chords Generation using AI and Machine Learning

As a musician and producer, I’ve always struggled with finding chords when I first started writing music [5]. It sometimes goes to the extent of me forgetting my melody because I take so long trying to figure out the chords. So I came up with an idea for this app, that will help amateur and beginner musicians save time and provide chord suggestions to them as a booster to start writing songs [6]. It features a recording or a midi input feature, then the app will carefully analyze the given melody and give a selection of the best chord progressions using intelligent AI. As an output, it is able to present it as guitar chords, piano chords, and ukulele chords, enabling more different musicians to use this app.