Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/25644
Title: | Brain Inspired Intelligence for Engineering and Healthcare Applications |
Authors: | Naghshvarianjahromi, Mahdi |
Advisor: | Kumar, Shiva Deen, Jamal |
Department: | Electrical and Computer Engineering |
Publication Date: | 2020 |
Abstract: | The cyber processing layer of smart systems based on a cognitive dynamic system (CDS) can be a good solution for better decision making and situation understanding in non-Gaussian and nonlinear environments (NGNLEs). The NGNLE situation understanding means deciding between certain known situations in NGNLE to understand the current state condition. Here, we report on a cognitive decision-making (CDM) system inspired by the human brain decision-making using prediction outcome of actions using a virtual NGNLE. The simple low-complexity algorithmic design of the proposed CDM system can make it suitable for real-time applications. The proposed system can be extended as a general software-based platform for brain-inspired decision making in smart systems in the presence of nonlinearity and non-Gaussian characteristics. Therefore, it can easily upgrade conventional systems to a smart one for autonomic CDM applications. Towards these objectives, CDS is applied to long-haul fiber optic link and a smart e-Health system as two examples of NGNLE. In first case study, brain-inspired intelligence using the CDS concept is proposed to control the quality-of-service (QoS) over a long-haul fiber-optic link that is nonlinear and with non-Gaussian channel noise. Digital techniques such as digital-back-propagation (DBP) assume that the fiber optic link parameters such as loss, dispersion, and nonlinear coefficients, are known at the receiver. However, the proposed CDSs does not need to know about the fiber optic link physical parameters, and it can improve the bit error rate (BER) or enhance the data rate based on information extracted from the fiber optic link. The information extraction (Bayesian statistical modeling) using intelligent perception processing on the received data, or using the previously extracted models in the model library, is carried out to estimate the transmitted data in the receiver. Then, the BER is sent to the executive through the main feedback channel and the executive produces actions on the physical system/signal or internal commands for adaptive modeling configurations to ensure that the BER is continuously under the pre-defined forward-error-correction (FEC) threshold. Therefore, the proposed CDS is an intelligent and adaptive system that can mitigate disturbance in the fiber optic link (especially in an optical network) using prediction in the perceptor and/or doing proper actions in the executive based on BER and the internal reward. Also, the earlier versions of CDS can achieve pre-defined goal faster using prediction outcome of actions in the executive. CDS was implemented for nonlinear fiber optic systems based on orthogonal frequency division multiplexing (OFDM) to show how the proposed CDS can bring noticeable improvement in the system’s performance. In second case study, CDS is applied for the autonomic computing layer of smart e-Health system for automatic diagnostic test and automatic screening process. In recent years, there has been a growing interest in smart e-Health systems to improve people’s quality of life by enhancing healthcare accessibility and reducing healthcare costs. Continuous monitoring of health through a smart e-Health system may enable automatic diagnosis of diseases like Arrhythmia at its early onset that otherwise may become fatal if not detected on time. Towards this objective, we start from understanding the health situation by diagnosing healthy and unhealthy persons for automatic diagnostic test. For this, a decision-making system is developed that is inspired by medical doctors (MDs) decision-making processes. Our system is based on a CDS for CDM and it can create a decision tree automatically. Then, a CDS-based framework is developed for the smart e-Health system to realize an automatic screening process in the presence of a defective dataset. A defective dataset may have poor labeling and/or lack enough training patterns. To mitigate the adverse effect of such a defective dataset, we developed a decision-making system that is inspired by the decision-making processes in humans in case of conflict-of-opinions (CoO). The proposed CDS algorithm can thereby be incorporated in the autonomic computing layer of a smart-e-Health-home platform to achieve a pre-defined degree of screening accuracy in the presence of a defective dataset. The proposed platforms for automatic diagnostic test and automatic screening process can be extended for more healthcare applications such as disease class diagnosis, prevention, treatment or monitoring healing. As a result, the proposed CDS algorithms can be an example of the initial steps for designing the autonomic computing layer of a smart e-Health home platform. |
URI: | http://hdl.handle.net/11375/25644 |
Appears in Collections: | Open Access Dissertations and Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Naghshvarianjahromi_Mahdi_2020-08_PhD.pdf | 8.31 MB | Adobe PDF | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.