Hydrolytic stability and protective properties of polyurethane oligomers based on polyester/ether/polyols

The present study deals with effect of the type and chemical character of incorporated polyester/polyether blocks on the hydrolytic stability of crosslinked polyurethane oligomers. Diffusion parameters of the investigated polyurethane oligomers, giving information concerning chemical changes taking place in neutral, basic and acidic aqueous environments, have also been determined.     

Automatic detection of microaneurysms in colour fundus images for diabetic retinopathy screening

Regular eye screening is essential for the early detection and treatment of the diabetic retinopathy. This paper presents a novel automatic screening system for diabetic retinopathy that focuses on the detection of the earliest visible signs of retinopathy, which are microaneurysms. Microaneurysms are small dots on the retina, formed by ballooning out of a weak part of the capillary wall. The detection of the microaneurysms at an early stage is vital, and it is the first step in preventing the diabetic retinopathy. The paper first explores the existing systems and applications related to diabetic retinopathy screening, with a focus on the microaneurysm detection methods. The proposed decision support system consists of an automatic acquisition, screening and classification of diabetic retinopathy colour fundus images, which could assist in the detection and management of the diabetic retinopathy. Several feature extraction methods and the circular Hough transform have been employed in the proposed microaneurysm detection system, alongside the fuzzy histogram equalisation method. The latter method has been applied in the preprocessing stage of the diabetic retinopathy eye fundus images and provided improved results for detecting the microaneurysms.     

Deep imitation learning for 3D navigation tasks

Deep learning techniques have shown success in learning from raw high-dimensional data in various applications. While deep reinforcement learning is recently gaining popularity as a method to train intelligent agents, utilizing deep learning in imitation learning has been scarcely explored. Imitation learning can be an efficient method to teach intelligent agents by providing a set of demonstrations to learn from. However, generalizing to situations that are not represented in the demonstrations can be challenging, especially in 3D environments. In this paper, we propose a deep imitation learning method to learn navigation tasks from demonstrations in a 3D environment. The supervised policy is refined using active learning in order to generalize to unseen situations. This approach is compared to two popular deep reinforcement learning techniques: deep-Q-networks and Asynchronous actor-critic (A3C). The proposed method as well as the reinforcement learning methods employ deep convolutional neural networks and learn directly from raw visual input. Methods for combining learning from demonstrations and experience are also investigated. This combination aims to join the generalization ability of learning by experience with the efficiency of learning by imitation. The proposed methods are evaluated on 4 navigation tasks in a 3D simulated environment. Navigation tasks are a typical problem that is relevant to many real applications. They pose the challenge of requiring demonstrations of long trajectories to reach the target and only providing delayed rewards (usually terminal) to the agent. The experiments show that the proposed method can successfully learn navigation tasks from raw visual input while learning from experience methods fail to learn an effective policy. Moreover, it is shown that active learning can significantly improve the performance of the initially learned policy using a small number of active samples.

     

New trends on digitisation of complex engineering drawings

Neural Computing and Applications - Engineering drawings are commonly used across different industries such as oil and gas, mechanical engineering and others. Digitising these drawings is becoming...     

Special issue: engineering applications of neural networks

Neural Computing and Applications -     

Special issue: Engineering applications of neural networks

Neural Computing and Applications -     

Neural network methods for one-to-many multi-valued mapping problems

An investigation of the applicability of neural network-based methods in predicting the values of multiple parameters, given the value of a single parameter within a particular problem domain is presented. In this context, the input parameter may be an important source of variation that is related with a complex mapping function to the remaining sources of variation within a multivariate distribution. The definition of the relationship between the variables of a multivariate distribution and a single source of variation allows the estimation of the values of multiple variables given the value of the single variable, addressing in that way an ill-conditioned one-to-many mapping problem. As part of our investigation, two problem domains are considered: predicting the values of individual stock shares, given the value of the general index, and predicting the grades received by high school pupils, given the grade for a single course or the average grade. With our work, the performance of standard neural network-based methods and in particular multilayer perceptrons (MLPs), radial basis functions (RBFs), mixture density networks (MDNs) and a latent variable method, the general topographic mapping (GTM), is compared. According to the results, MLPs and RBFs outperform MDNs and the GTM for these one-to-many mapping problems.