An automated methodology for the classification of focal and nonfocal EEG signals using a hybrid classification approach

The uncertainty in human brain leads to the formation of epilepsy disease in human. The automatic detection and severity analysis of epilepsy disease is proposed in this article using a hybrid classification algorithm. The proposed method consists of decomposition stage, feature extraction, and classification stages. The electroencephalogram (EEG) signals are decomposed using dual-tree complex wavelet transform and then features are extracted from these coefficients. These features are then classified using the neural network classification approach in order to classify the EEG signals into either focal or nonfocal EEG signals. Furthermore, severity of the focal EEG signal is analyzed using an adaptive neuro-fuzzy inference system classification approach. The proposed hybrid classification method for the classification of focal signals and nonfocal signals achieved 98.6% of sensitivity, 99.1% of specificity, and 99.4% of accuracy. The average detection rate for both focal and nonfocal dataset is about 98.5%.     

Machine learning-based model of surface tension of liquid metals: a step in designing multicomponent alloys for additive manufacturing

Journal of Materials Science - The surface tension (ST) of metallic alloys is a key property in many processing techniques. Notably, the ST value of liquid metals is crucial in additive...     

LoRAS: an oversampling approach for imbalanced datasets

Machine Learning - The Synthetic Minority Oversampling TEchnique (SMOTE) is widely-used for the analysis of imbalanced datasets. It is known that SMOTE frequently over-generalizes the minority...     

Analytical modeling methodology for ultrawideband low noise amplifiers with generalized filter-based impedance matching

In this paper, we present a modeling methodology for fully integrated inductively degenerated cascode ultrawideband low noise amplifiers (LNA) with generalized filter-based impedance matching networks. Our accurate analytical models capture the impact of device and passive component parasitics and transistor short channel effects to generate accurate designs. Utilizing our methodology, we are able to accurately generate an ultrawideband LNA in the 3.1–10.6 GHz frequency band using third and fifth order Chebyshev filters as input impedance matching networks. The speed and accuracy of the proposed analytical model will facilitate rapid design space exploration for ultrawideband LNAs.     

Preparation and Characterization of Carboxymethyl Starch (CMS) Products and Their Utilization in Textile Printing

Starch and oxidized starches of different molecular sises were carboxymethylated under identical conditions. The degree of substitution (DS) of the so obtained. CMS samples increases by decreasing the molecular sise of starch which, indeed, is a manifestation of higher extents of oxidation. The latter was effected using different sodium hypochlorite concentrations and the extent of oxidation was expressed as chlorine consumption. Pastes of these CMS samples exhibit pseudoplastic behaviour and their apparent viscosity decreases as the extent of oxidation increases, when used as thickeners in printing polyester fabric with disperse dyes, these pastes bring about prints the colour strength (K/S) of which are comparable with these for conventional thickeners, namely commercial CMS and sodium alginate. Mixing of sodium alginate with the prepared CMS samples increases the efficiency of the latter to act as the thickening agent. The highest K/S is obtained with CMS derived from starch oxidized using 1.25g active chlorine/1. Mean while, the colour fastness properties of the prints towards rubbing, washing and perspiration are nearly equal to those fabrics printed using the conventional thickeners such as sodium alginate or commercial CMS.     

Isolation,Chemical Modification and Rheological Characterization of Leucaena Gum. Part I: Carboxymethylation

Leucaena gum was isolated from leucaena seeds and subjected to chemical modification via carboxymethylation under a variety of conditions. Variables studied include concentration of the etherifying agents and the preparation medium. It was found that the extent of carboxymethylation expressed as DS increases by increasing the concentration of the etherifying agents. Higher DS values were obtained in non-aqueous medium. The carboxymethylated leucaena derivatives are cold water soluble and can be precipitated by ethanol. Their pastes are characterized by non-Newtonian pseudoplastic behaviour regardless of the method of preparation or DS of the products. The apparent viscosity at various rates was thouroughly investigated. The effect of storing of these pastes on the rheological properties was also studied.