Fatigue in radiology is a readily studied area. Machine learning concepts appliedto the identification of fatigue are also readily available. However, the intersection between the two areas is not a relative commonality. This study looks to explore the intersection of fatigue in radiology and machine learning concepts by analyzing temporal trends in multivariate time series data. A novel methodological approach using support vector machines to observe temporal trends in time-based aggregations of time series data is proposed. The data used in the study is captured in a real-world, unconstrained radiology setting where gaze and facial metrics are captured from radiologists performing live image reviews. The captured data is formatted into classes whose labels represent a window of time during the radiologist’s review. Using the labeled classes, the decision function and accuracy of trained, linear support vector machine models are evaluated to produce a visualization of temporal trends and critical inflection points as well as the contribution of individual features. Consequently, the study finds valid potential justification in the methods suggested. The study offers a prospective use of maximummargin classification to demarcate the manipulation of an abstract phenomenon such as fatigue on temporal data. Potential applications are envisioned that could improve the workload distribution of the medical act.

The reality of smart cities is here and now. The issues of data privacy in tech applications are apparent in smart cities. Privacy as an issue raised by many and addressed by few remains critical for smart cities’ success. It is the common responsibility of smart cities, tech application makers, and users to embark on the journey to solutions. Privacy is an individual problem that smart cities need to provide a collective solution for. The research focuses on understanding users’ data privacy preferences, what information they consider private, and what they need to protect. The research identifies the data security loopholes, data privacy roadblocks, and common opportunities for change to implement a proactive privacy-driven tech solution necessary to address and resolve tech-induced data privacy concerns among citizens. This dissertation aims at addressing the issue of data privacy in tech applications based on known methodologies to address the concerns they allow. Through this research, a data privacy survey on tech applications was conducted, and the results reveal users’ desires to become a part of the solution by becoming aware and taking control of their data privacy while using tech applications. So, this dissertation gives an overview of the data privacy issues in tech, discusses available data privacy basis, elaborates on the different steps needed to create a robust remedy to data privacy concerns in enabling users’ awareness and control, and proposes two privacy applications one as a data privacy awareness solution and the other as a representation of the privacy control framework to address data privacy concerns in smart cities.

The impact of Artificial Intelligence (AI) has increased significantly in daily life. AI is taking big strides towards moving into areas of life that are critical such as healthcare but, also into areas such as entertainment and leisure. Deep neural networks have been pivotal in making all these advancements possible. But, a well-known problem with deep neural networks is the lack of explanations for the choices it makes. To combat this, several methods have been tried in the field of research. One example of this is assigning rankings to the individual features and how influential they are in the decision-making process. In contrast a newer class of methods focuses on Concept Activation Vectors (CAV) which focus on extracting higher-level concepts from the trained model to capture more information as a mixture of several features and not just one. The goal of this thesis is to employ concepts in a novel domain: to explain how a deep learning model uses computer vision to classify music into different genres. Due to the advances in the field of computer vision with deep learning for classification tasks, it is rather a standard practice now to convert an audio clip into corresponding spectrograms and use those spectrograms as image inputs to the deep learning model. Thus, a pre-trained model can classify the spectrogram images (representing songs) into musical genres. The proposed explanation system called “Why Pop?” tries to answer certain questions about the classification process such as what parts of the spectrogram influence the model the most, what concepts were extracted and how are they different for different classes. These explanations aid the user gain insights into the model’s learnings, biases, and the decision-making process.

Ophthalmoscopes are integral to diagnosing various eye conditions; however, they often come at a hefty cost and are not generally portable, limiting access. With the increase in the prevalence of smart devices and improvements to their imaging capabilities, these devices have the potential to benefit areas where specialized imaging infrastructure is not well established. Smart device cameras alone cannot replace an ophthalmoscope. However, with the addition of lens and optics, it becomes possible to take diagnostic quality images. The goal is to design a modular system that acts as an adapter to a smart device enabling any user to take retinal images and corneal images with little to no previous experience. The device should be cost-effective, reliable, and easy to use. The device is not meant to replace conventional funduscopes but acts in areas where current units fail. Applications in non-optimal settings, low resource areas, or areas that currently receive suboptimal care due to geographic or socioeconomic barriers are examples where this device could be used. The introduction of screening programs run by nonspecialized medical personnel with devices that can capture and transmit quality eye images minimizes the long-term complications of degenerative eye conditions.

In some scenarios, true temporal ordering is required to identify the actions occurring in a video. Recently a new synthetic dataset named CATER, was introduced containing 3D objects like sphere, cone, cylinder etc. which undergo simple movements such as slide, pick & place etc. The task defined in the dataset is to identify compositional actions with temporal ordering. In this thesis, a rule-based system and a window-based technique are proposed to identify individual actions (atomic) and multiple actions with temporal ordering (composite) on the CATER dataset. The rule-based system proposed here is a heuristic algorithm that evaluates the magnitude and direction of object movement across frames to determine the atomic action temporal windows and uses these windows to predict the composite actions in the videos. The performance of the rule-based system is validated using the frame-level object coordinates provided in the dataset and it outperforms the performance of the baseline models on the CATER dataset. A window-based training technique is proposed for identifying composite actions in the videos. A pre-trained deep neural network (I3D model) is used as a base network for action recognition. During inference, non-overlapping windows are passed through the I3D network to obtain the atomic action predictions and the predictions are passed through a rule-based system to determine the composite actions. The approach outperforms the state-of-the-art composite action recognition models by 13.37% (mAP 66.47% vs. mAP 53.1%).

Working memory plays an important role in human activities across academic,professional, and social settings. Working memory is dened as the memory extensively involved in goal-directed behaviors in which information must be retained and manipulated to ensure successful task execution. The aim of this research is to understand the effect of image captioning with image description on an individual's working memory. A study was conducted with eight neutral images comprising situations relatable to daily life such that each image could have a positive or negative description associated with the outcome of the situation in the image. The study consisted of three rounds where the first and second round involved two parts and the third round consisted of one part. The image was captioned a total of five times across the entire study. The findings highlighted that only 25% of participants were able to recall the captions which they captioned for an image after a span of 9-15 days; when comparing the recall rate of the captions, 50% of participants were able to recall the image caption from the previous round in the present round; and out of the positive and negative description associated with the image, 65% of participants recalled the former description rather than the latter. The conclusions drawn from the study are participants tend to retain information for longer periods than the expected duration for working memory, which may be because participants were able to relate the images with their everyday life situations and given a situation with positive and negative information, the human brain is aligned towards positive information over negative information.

The knee joint has essential functions to support the body weight and maintain normal walking. Neurological diseases like stroke and musculoskeletal disorders like osteoarthritis can affect the function of the knee. Besides physical therapy, robot-assisted therapy using wearable exoskeletons and exosuits has shown the potential as an efficient therapy that helps patients restore their limbs’ functions. Exoskeletons and exosuits are being developed for either human performance augmentation or medical purposes like rehabilitation. Although, the research on exoskeletons started early before exosuits, the research and development on exosuits have recently grown rapidly as exosuits have advantages that exoskeletons lack. The objective of this research is to develop a soft exosuit for knee flexion assistance and validate its ability to reduce the EMG activity of the knee flexor muscles. The exosuit has been developed with a novel soft fabric actuator and novel 3D printed adjustable braces to attach the actuator aligned with the knee. A torque analytical model has been derived and validate experimentally to characterize and predict the torque output of the actuator. In addition to that, the actuator’s deflation and inflation time has been experimentally characterized and a controller has been implemented and the exosuit has been tested on a healthy human subject. It is found that the analytical torque model succeeded to predict the torque output in flexion angle range from 0° to 60° more precisely than analytical models in the literature. Deviations existed beyond 60° might have happened because some factors like fabric extensibility and actuator’s bending behavior. After human testing, results showed that, for the human subject tested, the exosuit gave the best performance when the controller was tuned to inflate at 31.9 % of the gait cycle. At this inflation timing, the biceps femoris, the semitendinosus and the vastus lateralis muscles showed average electromyography (EMG) reduction of - 32.02 %, - 23.05 % and - 2.85 % respectively. Finally, it is concluded that the developed exosuit may assist the knee flexion of more diverse healthy human subjects and it may potentially be used in the future in human performance augmentation and rehabilitation of people with disabilities.

Touch plays a vital role in maintaining human relationships through social andemotional communications. This research proposes a multi-modal haptic display capable of generating vibrotactile and thermal haptic signals individually and simultaneously. The main objective for creating this device is to explore the importance of touch in social communication, which is absent in traditional communication modes like a phone call or a video call. By studying how humans interpret haptically generated messages, this research aims to create a new communication channel for humans. This novel device will be worn on the user's forearm and has a broad scope of applications such as navigation, social interactions, notifications, health care, and education. The research methods include testing patterns in the vibro-thermal modality while noting its realizability and accuracy. Different patterns can be controlled and generated through an Android application connected to the proposed device via Bluetooth. Experimental results indicate that the patterns SINGLE TAP and HOLD/SQUEEZE were easily identifiable and more relatable to social interactions. In contrast, other patterns like UP-DOWN, DOWN-UP, LEFTRIGHT, LEFT-RIGHT, LEFT-DIAGONAL, and RIGHT-DIAGONAL were less identifiable and less relatable to social interactions. Finally, design modifications are required if complex social patterns are needed to be displayed on the forearm.

In this experiment, a haptic glove with vibratory motors on the fingertips was tested against the standard HTC Vive controller to see if the additional vibrations provided by the glove increased immersion in common gaming scenarios where haptic feedback is provided. Specifically, two scenarios were developed: an explosion scene containing a small and large explosion and a box interaction scene that allowed the participants to touch the box virtually with their hand. At the start of this project, it was hypothesized that the haptic glove would have a significant positive impact in at least one of these scenarios. Nine participants took place in the study and immersion was measured through a post-experiment questionnaire. Statistical analysis on the results showed that the haptic glove did have a significant impact on immersion in the box interaction scene, but not in the explosion scene. In the end, I conclude that since this haptic glove does not significantly increase immersion across all scenarios when compared to the standard Vive controller, it should not be used at a replacement in its current state.