This dissertation proposes two real-time human activity recognition algorithms intelligent fuzzy inference (IFI) algorithm and Amplitude omega ($A \omega$) algorithm to identify the human activities, i.e., stationary and locomotion activities. The IFI algorithm uses knee angle and ground contact forces (GCFs) measurements from four inertial measurement units (IMUs) and a pair of smart shoes. Whereas, the $A \omega$ algorithm is based on thigh angle measurements from a single IMU.
This dissertation also attempts to address the problem of online tuning of virtual impedance for an assistive robot based on real-time gait and activity measurement data to personalize the assistance for different users. An automatic impedance tuning (AIT) approach is presented for a knee assistive device (KAD) in which the IFI algorithm is used for real-time activity measurements. This dissertation also proposes an adaptive oscillator method known as amplitude omega adaptive oscillator ($A\omega AO$) method for HeSA (hip exoskeleton for superior augmentation) to provide bilateral hip assistance during human locomotion activities. The $A \omega$ algorithm is integrated into the adaptive oscillator method to make the approach robust for different locomotion activities. Experiments are performed on healthy subjects to validate the efficacy of the human activities recognition algorithms and control strategies proposed in this dissertation. Both the activity recognition algorithms exhibited higher classification accuracy with less update time. The results of AIT demonstrated that the KAD assistive torque was smoother and EMG signal of Vastus Medialis is reduced, compared to constant impedance and finite state machine approaches. The $A\omega AO$ method showed real-time learning of the locomotion activities signals for three healthy subjects while wearing HeSA. To understand the influence of the assistive devices on the inherent dynamic gait stability of the human, stability analysis is performed. For this, the stability metrics derived from dynamical systems theory are used to evaluate unilateral knee assistance applied to the healthy participants.
The research presented in this Honors Thesis provides development in machine learning models which predict future states of a system with unknown dynamics, based on observations of the system. Two case studies are presented for (1) a non-conservative pendulum and (2) a differential game dictating a two-car uncontrolled intersection scenario. In the paper we investigate how learning architectures can be manipulated for problem specific geometry. The result of this research provides that these problem specific models are valuable for accurate learning and predicting the dynamics of physics systems.<br/><br/>In order to properly model the physics of a real pendulum, modifications were made to a prior architecture which was sufficient in modeling an ideal pendulum. The necessary modifications to the previous network [13] were problem specific and not transferrable to all other non-conservative physics scenarios. The modified architecture successfully models real pendulum dynamics. This case study provides a basis for future research in augmenting the symplectic gradient of a Hamiltonian energy function to provide a generalized, non-conservative physics model.<br/><br/>A problem specific architecture was also utilized to create an accurate model for the two-car intersection case. The Costate Network proved to be an improvement from the previously used Value Network [17]. Note that this comparison is applied lightly due to slight implementation differences. The development of the Costate Network provides a basis for using characteristics to decompose functions and create a simplified learning problem.<br/><br/>This paper is successful in creating new opportunities to develop physics models, in which the sample cases should be used as a guide for modeling other real and pseudo physics. Although the focused models in this paper are not generalizable, it is important to note that these cases provide direction for future research.
High-entropy alloys possessing mechanical, chemical, and electrical properties that far exceed those of conventional alloys have the potential to make a significant impact on many areas of engineering. Identifying element combinations and configurations to form these alloys, however, is a difficult, time-consuming, computationally intensive task. Machine learning has revolutionized many different fields due to its ability to generalize well to different problems and produce computationally efficient, accurate predictions regarding the system of interest. In this thesis, we demonstrate the effectiveness of machine learning models applied to toy cases representative of simplified physics that are relevant to high-entropy alloy simulation. We show these models are effective at learning nonlinear dynamics for single and multi-particle cases and that more work is needed to accurately represent complex cases in which the system dynamics are chaotic. This thesis serves as a demonstration of the potential benefits of machine learning applied to high-entropy alloy simulations to generate fast, accurate predictions of nonlinear dynamics.
In the last two decades, fantasy sports have grown massively in popularity. Fantasy football in particular is the most popular fantasy sport in the United States. People spend hours upon hours every year building, researching, and perfecting their teams to compete with others for money or bragging rights. One problem, however, is that National Football League (NFL) players are human and will not perform the same as they did last week or last season. Because of this, there is a need to create a machine learning model to help predict when players will have a tough game or when they can perform above average. This report discusses the history and science of fantasy football, gathering large amounts of player data, manipulating the information to create more insightful data points, creating a machine learning model, and how to use this tool in a real-world situation. The initial model created significantly accurate predictions for quarterbacks and running backs but not receivers and tight ends. Improvements significantly increased the accuracy by reducing the mean average error to below one for all positions, resulting in a successful model for all four positions.
This thesis also introduces a new metric, titled Edge, to quantify model performance in regions of an image that show the highest change in ground truth depth values along either the x-axis or the y-axis. Existing metrics in depth estimation like Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) quantify model performance across the entire image and don’t focus on specific regions of an image that are hard to predict. To this end, the proposed Edge metric focuses specifically on these hard to classify regions. The experiments also show that using the Edge metric as a small addition to existing loss functions like L1 loss in current state-of-the-art methods leads to vastly improved performance in these hard to classify regions, while also improving performance across the board in every other metric.
Meanwhile, machine learning is growing more advanced by the day. Online retailers like Amazon run complex algorithms to recommend future purchases and monitor price changes. Mobile phones use neural networks to interpret speech. GPS apps track anonymous motion data in smartphones to give real-time traffic estimates. Artificial intelligence is becoming increasingly ubiquitous because of its versatility in analyzing and solving human problems; it follows, then, that a machine could learn how to teach humans skills and techniques. HelperBot is a platform fighting game project that employs this cutting-edge learning technology to close the skill gap between novice and veteran gamers as quickly and seamlessly as possible.
This paper analyzes responses to deviated Trolley Problem scenarios [5] in a simulated driving environment and still images from MIT’s moral machine website [8] to better understand how humans respond to various crashes. Also included is participants driving habits and personal values, however the bulk of that analysis is not included here. The results of the simulation prove that for the most part in driving scenarios, people would rather sacrifice themselves over people outside of the vehicle. The moral machine scenarios prove that self-sacrifice changes as the trend to harm one’s own vehicle was not so strong when passengers were introduced. Further defending this idea is the importance placed on Family Security over any other value.
Suggestions for implementing ethics into autonomous vehicle crashes stem from the results of this experiment but are dependent on more research and greater sample sizes. Once enough data is collected and analyzed, a moral baseline for human’s moral domain may be agreed upon, quantified, and turned into hard rules governing how self-driving cars should act in different scenarios. With these hard rules as boundary conditions, artificial intelligence should provide training and incremental learning for scenarios which cannot be determined by the rules. Finally, the neural networks which make decisions in artificial intelligence must move from their current “black box” state to something more traceable. This will allow researchers to understand why an autonomous vehicle made a certain decision and allow tweaks as needed.