Improved Izhikevich neurons for spiking neural networks

Spiking neural networks constitute a modern neural network paradigm that overlaps machine learning and computational neurosciences. Spiking neural networks use neuron models that possess a great degree of biological realism. The most realistic model of the neuron is the one created by Alan Lloyd Hodgkin and Andrew Huxley. However, the Hodgkin–Huxley model, while accurate, is computationally very inefficient. Eugene Izhikevich created a simplified neuron model based on the Hodgkin–Huxley equations. This model has better computational efficiency than the original proposed by Hodgkin and Huxley, and yet it can successfully reproduce all known firing patterns. However, there are not many articles dealing with implementations of this model for a functional neural network. This study presents a spiking neural network architecture that utilizes improved Izhikevich neurons with the purpose of evaluating its speed and efficiency. Since the field of spiking neural networks has reinvigorated the interest in biological plausibility, biological realism was an additional goal. The network is tested on the correct classification of logic gates (including XOR) and on the iris dataset. Results and possible improvements are also discussed.     

A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry

This paper presents a fully automated segmentation and classification scheme for mammograms, based on breast density estimation and detection of asymmetry. First, image preprocessing and segmentation techniques are applied, including a breast boundary extraction algorithm and an improved version of a pectoral muscle segmentation scheme. Features for breast density categorization are extracted, including a new fractal dimension-related feature, and support vector machines (SVMs) are employed for classification, achieving accuracy of up to 85.7%. Most of these properties are used to extract a new set of statistical features for each breast; the differences among these feature values from the two images of each pair of mammograms are used to detect breast asymmetry, using an one-class SVM classifier, which resulted in a success rate of 84.47%. This composite methodology has been applied to the miniMIAS database, consisting of 322 (MLO) mammograms -including 15 asymmetric pairs of images-, obtained via a (noisy) digitization procedure. The results were evaluated by expert radiologists and are very promising, showing equal or higher success rates compared to other related works, despite the fact that some of them used only selected portions of this specific mammographic database. In contrast, our methodology is applied to the complete miniMIAS database and it exhibits the reliability that is normally required for clinical use in CAD systems.     

Visual Focus of Attention in Non-calibrated Environments using Gaze Estimation

Estimating the focus of attention of a person highly depends on her/his gaze directionality. Here, we propose a new method for estimating visual focus of attention using head rotation, as well as fuzzy fusion of head rotation and eye gaze estimates, in a fully automatic manner, without the need for any special hardware or a priori knowledge regarding the user, the environment or the setup. Instead, we propose a system aimed at functioning under unpretending conditions, only with the usage of simple hardware, like a normal web-camera. Our system is aimed at functioning in a human-computer interaction environment, considering a person is facing a monitor with a camera adjusted on top. To this aim, we propose in this paper two novel techniques, based on local and appearance information, estimating head rotation, and we adaptively fuse them in a common framework. The system is able to recognize head rotational movement, under translational movements of the user towards any direction, without any knowledge or a-priori estimate of the user’s distance from the camera or camera intrinsic parameters.     

A novel rapid method for the determination of frying oil quality: development of prototype and equations and examination with respect to legislation criteria

The present work presents a prototype apparatus developed for a novel method based on capillary penetration for the determination of frying oil quality and examines the method and the performance of the prototype. The work further assesses the method results in comparison with the results of established methods and proposes equations for calculating frying oil quality parameters relevant to legislation criteria. The examination of the method is performed by using 184 oil samples produced by frying different foods in different oils for forty-five successive batches. Equations relating the method output with the total polar compounds, total polymers and viscosity are proposed. High correlation coefficients between legislation criteria and the method result are obtained: R² = 0.96, R² = 0.91 and R² = 0.86 for correlation with the oil viscosity, the polymer compounds and the TPC of the fried oils, respectively. The false-positive and false-negative answers of the method are below 2.5% for all cases.     

Evidence for Novel Structures Relating CSR Reporting and Economic Welfare: Environmental Sustainability—A Continent-Level Analysis

Computational Economics - This paper aims to work towards a factual framework to substantiate the linkage between corporate social responsibility (CSR) reporting and economic activity and between...     

The Yarrowia lipolytica PAH1 homologue contributes but is not required for triacylglycerol biosynthesis during growth on glucose

The PAH1-encoded phosphatidate phosphatase (PAP) catalyzes the Mg²⁺-dependent dephosphorylation of phosphatidate to produce diacylglycerol, which can be acylated to form triacylglycerol (TAG). In the model oleaginous yeast Yarrowia lipolytica, TAG is the major lipid produced, and its biosynthesis requires a continuous supply of diacylglycerol, which can be provided by the PAP reaction. However, the regulation of Pah1 has not been studied in detail in Y. lipolytica, and thus its contribution to the biosynthesis of TAG in this yeast is not well understood. In this work, we examined the regulation of the PAH1-mediated PAP activity and Pah1 abundance and localization in cells growing on glucose. We found that Pah1 abundance and localization were regulated in a growth-dependent manner, yet the loss of Pah1 did not have a major effect on PAP activity. We also examined the effects of the Y. lipolytica pah1Δ mutation on cell physiology and lipid biosynthesis. The lack of Pah1 in the pah1Δ mutant resulted in a moderate decrease in TAG levels and an increase in phospholipid levels. These results showed that Pah1 contributed to TAG biosynthesis in Y. lipolytica but also suggested the presence of other activities in the pah1Δ mutant that compensate for the loss of Pah1. Also, the levels of linoleic acid were elevated in pah1Δ cells with a concomitant decrease in the oleic acid levels suggesting that the pah1Δ mutation affected the biosynthesis of fatty acids.     

Electromagnetic Shielding and Reflection Loss of Conductive Yarn Incorporated Woven Fabrics at the S and X Radar Bands

Journal of Electronic Materials - This study provides comparison of different types of conductive yarns stitched on top of the plain woven fabric via two different structures (parallel and mesh...     

Efficient PCA-driven EAs and metamodel-assisted EAs,with applications in turbomachinery

This article presents methods to enhance the efficiency of Evolutionary Algorithms (EAs), particularly those assisted by surrogate evaluation models or metamodels. The gain in efficiency becomes important in applications related to industrial optimization problems with a great number of design variables. The development is based on the principal components analysis of the elite members of the evolving EA population, the outcome of which is used to guide the application of evolution operators and/or train dependable metamodels/artificial neural networks by reducing the number of sensory units. Regarding the latter, the metamodels are trained with less computing cost and yield more relevant objective function predictions. The proposed methods are applied to constrained, single- and two-objective optimization of thermal and hydraulic turbomachines.     

Techno-economic comparison of MIMO and DAS cost models in 5G networks

Wireless Networks - High communicational standards have been set for the 5G mobile networks. Therefore, it is of great importance that technological solutions that include all the significant...     

Rapid Methods for Frying Oil Quality Determination: Evaluation with Respect to Legislation Criteria

This work focuses on the evaluation of commercially available rapid methods for determining frying oil quality. Five rapid methods differing in principle were selected: FOM320 (Ebro), PCT120 (3M), LRSM (3M), Fritest (Merck) and Viscofrit (Viscofrit). The performance of the methods was examined by use of 184 oil samples produced by controlled frying experiments. Twelve series of frying experiments (45 batches each) were performed in which the oil type (palm, sunflower and olive) and the food type (potatoes, zucchini and minced beef meat) varied. Control thermal oxidation experiments with the same oil types were also performed. Results of the rapid methods were compared to results of analytical methods determining legislation criteria. Namely, the total polar compounds and total polymer compounds were determined using High Pressure Size Exclusion Chromatography with and without prior separation of the polar fraction. Furthermore, determination of the free fatty acid concentration, acidity, viscosity and level of oxidation of the oils using UV spectroscopy were carried out. Principal component analysis and linear regression analysis were used in order to assess the obtained results. Comparison of the results of the rapid methods with the analytical ones showed differences in most examined cases. For many of the examined rapid methods the agreement of the results versus those of analytical methods depended on the food-oil combination used in the frying experiments.