As more electric vehicles (EVs) are adopted, users need a solution to meet their expectations when it comes to Level 2 EV Charging (EVC). Currently, Adaptive Charging (AC) Techniques are used in multi-unit, public, settings. In the future, AC should be utilized to provide an optimized charging experience for the EV user in a single-unit residential application. In this experiment, an Electric Vehicle simulation tool was created using Python. A training dataset was generated from Alternative Fuels and Data Center (EVI-Pro) using charging data from Phoenix, Arizona. Similarly, the utility price plan chosen for this exercise was SRP Electric Vehicle Price plan. This will be the cost-basis for the thesis. There were four cases that were evaluated by the simulation tool. (1) Utility Guided Scheduling (2) Automatic Scheduling (3) Off-Site Enablement (4) Bidirectional enablement. These use-cases are some of the critical problems facing EV users when it comes to charging at home. Each of these scenarios and algorithms were proven to save the user money in their daily bill. Overall, the user will need some sort of weighted scenario that considers all four cases to provide the best solution to the user. All four scenarios support the use of Adaptive Charging techniques in residential level 2 electric vehicle chargers. By applying these techniques, the user can save up to 90% on their energy bill while offsetting the energy grid during peak hours. The adaptive charging techniques applied in this thesis are critical to the adoption of the next generation electric vehicles. Users need to be enabled to use the latest and greatest technology. In the future, individuals can use this report as a baseline to use an Artificial Intelligence model to make an educated case-by-case decision to deal with the variability of the data.

This paper serves to report the research performed towards detecting PD and the effects of medication through the use of machine learning and finger tapping data collected through mobile devices. The primary objective for this research is to prototype a PD classification model and a medication classification model that predict the following: the individual’s disease status and the medication intake time relative to performing the finger-tapping activity, respectively.

This paper serves to report the research performed towards detecting PD and the effects of medication through the use of machine learning and finger tapping data collected through mobile devices. The primary objective for this research is to prototype a PD classification model and a medication classification model that predict the following: the individual’s disease status and the medication intake time relative to performing the finger-tapping activity, respectively.