A5005120711- EEG and Brain-Computer Interfaces
- Neural Networks and Applications
- Muscle activation and electromyography studies
- Neuroscience and Neural Engineering
- Geochemistry and Geologic Mapping
- ECG Monitoring and Analysis
- Complex Systems and Time Series Analysis
- Earthquake Detection and Analysis
- Seismology and Earthquake Studies
- Energy Load and Power Forecasting
- Cardiovascular Function and Risk Factors
- Non-Invasive Vital Sign Monitoring
- Speech and Audio Processing
- Electric Power System Optimization
- Insurance, Mortality, Demography, Risk Management
- Cardiovascular Effects of Exercise
- Machine Learning and ELM
- Chaos control and synchronization
- Hemodynamic Monitoring and Therapy
- Geological and Geochemical Analysis
- Monetary Policy and Economic Impact
- Blind Source Separation Techniques
- Cardiovascular Health and Disease Prevention
- Cardiac pacing and defibrillation studies
- earthquake and tectonic studies
AventuSoft (United States)
2022-2023
University of Florida
2017-2019
International Institute of Earthquake Engineering and Seismology
2008-2012
Institute of Economics and Industrial Engineering
2012
Iran National Science Foundation
2007
In this paper, a nonlinear autoregressive (NAR) recurrent neural network is used for the prediction of next 18 data samples each time series in set 11 unknown dynamics NN3 Database. The models are built on reconstructed state spaces and no other domain knowledge available to be used. Here, we clarify that employed method part similar superior subclass network, namely model with exogenous inputs (NARX). Using extensive research about NARX networks, briefly explain our preferred both...
A methodology for the development of a fuzzy expert system (FES) with application to earthquake prediction is presented. The idea reproduce performance human in prediction. To do this, at first step, rules provided by are used generate rule base. These then fed into an inference engine produce (FIS) and infer results. In this paper, we have Sugeno type build FES. At next adaptive network-based (ANFIS) refine FES parameters improve its performance. proposed framework employed attain predict...
The performance of upper-limb prostheses is currently limited by the relatively poor functionality unintuitive control schemes. This paper proposes to extract, from multichannel electromyographic signals (EMG), motor neuron spike trains and project them into lower dimensional continuous signals, which are used as proportional inputs prosthetic's actuators. These an estimation common synaptic input that neurons receive. We use simplest metric learning approaches known principal component...
A competitive modular multinet structure is introduced as a local learning framework. Here, there not control switching mechanism between modules. Instead, the modules are encouraged to specialize in sub-regions of feature space competitively. In my decomposition scheme, created, developed, shrunk or vanished during process, based on an interaction pool networks. Just after specialization networks certain sub-regions, selector trained learn mapping and experts, which helps system be used...
The exact mechanisms leading to an earthquake are not fully understood and the space-time structural features non-trivial. Previous studies suggest seismicity of very low intensity earthquakes, known as micro-earthquakes, may contain information about source process before major they can quantify modifications stress or strain across time that finally lead a earthquake. This work uses history seismic activity micro-earthquakes analyze spatio-temporal statistical independence among monitoring...
ECG signals are essential in diagnosing cardiovascular diseases (CVD). Automatic localization of fiducial points helps the end-point detection and tracking CVD. Nowadays, collecting is more accessible because availability wearable devices. We develop an algorithm to estimate peaks P T waves onset offset QRS complex. evaluate it using collected a device named HEMOTAG. The combines rule-based method for heartbeat deep convolutional neural network (CNN) localization. Three datasets were used...