Eye Movement Signal Classification for Developing Human-Computer Interface Using Electrooculogram

Human-computer interfaces (HCI) allow people to control electronic devices, such as computers, mouses, wheelchairs, and keyboards, by bypassing the biochannel without using motor nervous system signals. These signals permit communication between people and electronic-controllable devices. This communication is due to HCI, which facilitates lives of paralyzed patients who do not have any problems with their cognitive functioning. The major plan of this study is to test out the feasibility of nine states of HCI by using modern techniques to overcome the problem faced by the paralyzed. Analog Digital Instrument T26 with a five-electrode system was used in this method. Voluntarily twenty subjects participated in this study. The extracted signals were preprocessed by applying notch filter with a range of 50 Hz to remove the external interferences; the features were extracted by applying convolution theorem. Afterwards, extracted features were classified using Elman and distributed time delay neural network. Average classification accuracy with 90.82% and 90.56% was achieved using two network models. The accuracy of the classifier was analyzed by single-trial analysis and performances of the classifier were observed using bit transfer rate (BTR) for twenty subjects to check the feasibility of designing the HCI. The achieved results showed that the ERNN model has a greater potential to classify, identify, and recognize the EOG signal compared with distributed time delay network for most of the subjects. The control signal generated by classifiers was applied as control signals to navigate the assistive devices such as mouse, keyboard, and wheelchair activities for disabled people.

Global Stability Analysis of a Five-Dimensional Unemployment Model with Distributed Delay

The present paper proposes a five-dimensional mathematical model for studying the labor market, focusing on unemployment, migration, fixed term contractors, full time employment and the number of available vacancies. The distributed time delay is considered in the rate of change of available vacancies that depends on the past regular employment levels. The non-dimensional mathematical model is introduced and the existence of the equilibrium points is analyzed. The positivity and boundedness of solutions are provided and global asymptotic stability findings are presented both for the employment free equilibrium and the positive equilibrium. The numerical simulations support the theoretical results.

Overlapping Decentralized Controller Design for Descriptor-type Systems with Distributed Time-delay

Decentralized controller design using overlapping decompositions is considered for descriptor-type systems with distributed time-delay. The approach is based on the principle of extension. In this approach, a given large-scale system is decomposed overlappingly into a number of subsystems and expanded such that the overlapping parts appear as disjoint. A decentralized controller is then designed for the expanded system. This controller is then contracted for implementation on the original system. It is shown that if the decentralized controllers are designed to stabilize the expanded system and to achieve certain performance, then the contracted controller, which would have an overlapping decentralized structure, will stabilize the original system and will achieve corresponding performance

Comparison of two different types of fractional-order COVID-19 distributed time-delay models with real data application

The outbreak of COVID-19 has a great impact on the world. Considering that there are different infection delays among different populations, which can be expressed as distributed delay, and the distributed time-delay is rarely used in fractional-order model to simulate the real data, here we establish two different types of fractional order (Caputo and Caputo–Fabrizio) COVID-19 models with distributed time-delay. Parameters are estimated by the least-square method according to the report data of China and other 12 countries. The results of Caputo and Caputo–Fabrizio model with distributed time-delay and without delay, the integer-order model with distributed delay are compared. These show that the fractional-order model can be better in fitting the real data. Moreover, Caputo order is better in short-term time fitting, Caputo–Fabrizio order is better in long-term fitting and prediction. Finally, the influence of several parameters is simulated in Caputo order model, which further verifies the importance of taking strict quarantine measures and paying close attention to the incubation period population.

An Improved Neural Network Based on Parasitism – Predation Algorithm for an Automatic Voltage Regulator

The parasitism – predation algorithm (PPA) is an optimization method that duplicates the interaction of mutualism between predators (cats), parasites (cuckoos), and hosts (crows). The study employs a combination of the PPA methods using the cascade-forward backpropagation neural network. This hybrid method employs an automatic voltage regulator (AVR) on a single machine system, with the performance measurement focusing on speed and the rotor angle. The performance of the proposed method is compared with the feed-forward backpropagation neural network (FFBNN), cascade-forward backpropagation neural network (CFBNN), Elman recurrent neural network (E-RNN), focused time-delay neural network (FTDNN), and distributed time-delay neural network (DTDNN). The results show that the proposed method exhibits the best speed and rotor angle performance. The PPA-CFBNN method has the ability to reduce the overshoot of the speed by 1.569% and the rotor angle by 0.724%.