EEG-based epileptic seizure detection using binary dragonfly algorithm and deep neural network.

Electroencephalogram (EEG) is one of the most common methods used for seizure detection as it records the electrical activity of the brain. Symmetry and asymmetry of EEG signals can be used as indicators of epileptic seizures. Normally, EEG signals are symmetrical in nature, with similar patterns on both sides of the brain. However, during a seizure, there may be a sudden increase in the electrical activity in one hemisphere of the brain, causing asymmetry in the EEG signal. In patients with epilepsy, interictal EEG may show asymmetric spikes or sharp waves, indicating the presence of epileptic activity. Therefore, the detection of symmetry/asymmetry in EEG signals can be used as a useful tool in the diagnosis and management of epilepsy. However, it should be noted that EEG findings should always be interpreted in conjunction with the patient's clinical history and other diagnostic tests. In this paper, we propose an EEG-based improved automatic seizure detection system using a Deep neural network (DNN) and Binary dragonfly algorithm (BDFA). The DNN model learns the characteristics of the EEG signals through nine different statistical and Hjorth parameters extracted from various levels of decomposed signals obtained by using the Stationary Wavelet Transform. Next, the extracted features were reduced using the BDFA which helps to train DNN faster and improve its performance. The results show that the extracted features help to differentiate the normal, interictal, and ictal signals effectively with 100% accuracy, sensitivity, specificity, and F1 score with a 13% selected feature subset when compared to the existing approaches.

Anomalous strength characteristics of Stone-Thrower-Wales defects in graphene sheets - a molecular dynamics study.

Graphene, viz., the one-atom-thick sheet of carbon, exhibits outstanding mechanical properties, but defects, which are inevitable at the time of synthesis, may strongly affect these properties. In this study, the effects of two types of Stone-Thrower-Wales (namely, STW-1 and STW-2) defects on the mechanical properties of graphene sheets at different temperatures and strain rates were investigated on the basis of molecular dynamics simulations. The authors also investigated the effect of the strain rate and defect concentration on the failure morphology of STW-1 and STW-2 defected graphene sheets. It was observed that, irrespective of the strain rate, the fracture strengths of STW-1 and STW-2 defected graphene sheets are identical in the zigzag and armchair directions, respectively, at low temperatures. It was also observed that the fracture strengths of graphene sheets with STW-1 defects in the armchair direction and STW-2 defects in the zigzag direction decrease drastically at higher temperatures and also at lower strain rates. On the other hand, it was noticed that the fracture strengths of graphene sheets with STW-1 defects in the zigzag direction and STW-2 defects in the armchair direction decrease gradually with an increase in the temperature and a decrease in the strain rate. It was also predicted that the failure morphology of graphene sheets with STW-1 defects in the zigzag direction and STW-2 defects in the armchair direction depends on the defect concentration and the strain rate.

Optimised cut-off function for Tersoff-like potentials for a BN nanosheet: a molecular dynamics study.

In this article, molecular dynamics based simulations were carried out to study the tensile behaviour of boron nitride nanosheets (BNNSs). Four different sets of Tersoff potential parameters were used in the simulations for estimating the interatomic interactions between boron and nitrogen atoms. Modifications were incorporated in the Tersoff cut-off function to improve the accuracy of results with respect to fracture stress, fracture strain and Young's modulus. In this study, the original cut-off function was optimised in such a way that small and large cut-off distances were made equal, and hence a single cut-off distance was used with all sets of Tersoff potential parameters. The single value of cut-off distance for the Tersoff potential was chosen after analysing the potential energy and bond forces experienced by boron and nitrogen atoms subjected to bond stretching. The simulations performed with the optimised cut-off function help in identifying the Tersoff potential parameters that reproduce the experimentally evaluated mechanical behaviour of BNNSs.

Isolation of Legionella pneumophila from hospital cooling towers in Johor, Malaysia.

Water-based cooling towers and their water supply at two hospitals in Johor were surveyed for the presence Legionella pneumophila. L. pneumophila were grown from 19 (76%) out of 25 collected water samples. One hospital cooling tower was contaminated with L. pneumophila serogroup 1.