Sensorineural hearing loss can be treated using Cochlear implantation. After this surgery using the electrode array impedance measurements, we can check the stability of the impedance value and the dynamic range. Deterioration of speech recognition scores could happen because of increased impedance values. Medicines used to do these measures many times during a year after the surgery. Predicting the electrode impedance could help in taking decisions to help the patient get better hearing. In this research we used a dataset of 80 patients of children who did cochlear implantation using MED-EL FLEX28 electrode array of 12 channels. We predicted the electrode impedance on each channel after 1 month from the surgery date. We used different machine learning algorithms like neural networks and decision trees. Our results indicates that the electrode impedance can be predicted, and the best algorithm is different based on the electrode channel. Also, the accuracy level varies between 66% and 100% based on the electrode channel when accepting an error range between 0 and 3 KO. Further research is required to predict the electrode impedance after three months, six months and one year.
Molecular communication (MC) implemented on Nano networks has extremely attractive characteristics in terms of energy efficiency, dependability, and robustness. Even though, the impact of incredibly slow molecule diffusion and high variability environments remains unknown. Analysis and designs of communication systems usually rely on developing mathematical models that describe the communication channel. However, the underlying channel models are unknown in some systems, such as MC systems, where chemical signals are used to transfer information. In these cases, a new method to analyze and design is needed. In this paper, we concentrate on one critical aspect of the MC system, modelling MC received signal until time t , and demonstrate that using tools from ML makes it promising to train detectors that can be executed well without any information about the channel model. Machine learning (ML) is one of the intelligent methodologies that has shown promising results in the domain. This paper applies Azure Machine Learning (Azure ML) for flexible pavement maintenance regressions problems and solutions. For prediction, four parameters are used as inputs: the receiver radius, transmitter radius, distance between receiver and transmitter, and diffusion coefficient, while the output is mAP (mean average precision) of the received signal. Azure ML enables algorithms that can learn from data and experiences and accomplish tasks without having to be coded. In the established Azure ML, the regression algorithms such as, boost decision tree regression, Bayesian linear regression, neural network, and decision forest regression are selected. The best performance is chosen as an optimality criterion. Finally, a comparison that shows the potential benefits of Azure ML tool over programmed based tool (Python), used by developers on local PCs, is demonstrated
In this study we worked on the classification of the Chess Endgame problem using different algorithms like logistic regression, decision trees and neural networks. Our experiments indicates that the Neural Networks provides the best accuracy (85%) then the decision trees (79%). We did these experiments using Microsoft Azure Machine Learning as a case-study on using Visual Programming in classification. Our experiments demonstrates that this tool is powerful and save a lot of time, also it could be improved with more features that increase the usability and reduce the learning curve. We also developed an application for dataset visualization using a new programming language called Ring, our experiments demonstrates that this language have simple design like Python while integrates RAD tools like Visual Basic which is good for GUI development in the open-source world