Traumatic injuries are the leading cause of death in children under 18, with head trauma being the leading cause of death in children below 5. A large but unknown number of traumatic injuries are non-accidental, i.e. inflicted. The lack of sensitivity and specificity required to diagnose Abusive Head Trauma (AHT) from radiological studies results in putting the children at risk of re-injury and death. Modern Deep Learning techniques can be utilized to detect Abusive Head Trauma using Computer Tomography (CT) scans. Training models using these techniques are only a part of building AI-driven Computer-Aided Diagnostic systems. There are challenges in deploying the models to make them highly available and scalable.

The thesis models the domain of Abusive Head Trauma using Deep Learning techniques and builds an AI-driven System at scale using best Software Engineering Practices. It has been done in collaboration with Phoenix Children Hospital (PCH). The thesis breaks down AHT into sub-domains of Medical Knowledge, Data Collection, Data Pre-processing, Image Generation, Image Classification, Building APIs, Containers and Kubernetes. Data Collection and Pre-processing were done at PCH with the help of trauma researchers and radiologists. Experiments are run using Deep Learning models such as DCGAN (for Image Generation), Pretrained 2D and custom 3D CNN classifiers for the classification tasks. The trained models are exposed as APIs using the Flask web framework, contained using Docker and deployed on a Kubernetes cluster.



The results are analyzed based on the accuracy of the models, the feasibility of their implementation as APIs and load testing the Kubernetes cluster. They suggest the need for Data Annotation at the Slice level for CT scans and an increase in the Data Collection process. Load Testing reveals the auto-scalability feature of the cluster to serve a high number of requests.

Driving is the coordinated operation of mind and body for movement of a vehicle, such as a car, or a bus. Driving, being considered an everyday activity for many people, still has an issue of safety. Driver distraction is becoming a critical safety problem. Speed, drunk driving as well as distracted driving are the three leading factors in the fatal car crashes. Distraction, which is defined as an excessive workload and limited attention, is the main paradigm that guides this research area. Driver behavior analysis can be used to address the distraction problem and provide an intelligent adaptive agent to work closely with the driver, fay beyond traditional algorithmic computational models. A variety of machine learning approaches has been proposed to estimate or predict drivers’ fatigue level using car data, driver status or a combination of them.

Three important features of intelligence and cognition are perception, attention and sensory memory. In this thesis, I focused on memory and attention as essential parts of highly intelligent systems. Without memory, systems will only show limited intelligence since their response would be exclusively based on spontaneous decision without considering the effect of previous events. I proposed a memory-based sequence to predict the driver behavior and distraction level using neural network. The work started with a large-scale experiment to collect data and make an artificial intelligence-friendly dataset. After that, the data was used to train a deep neural network to estimate the driver behavior. With a focus on memory by using Long Short Term Memory (LSTM) network to increase the level of intelligence in two dimensions: Forgiveness of minor glitches, and accumulation of anomalous behavior., I reduced the model error and computational expense by adding attention mechanism on the top of LSTM models. This system can be generalized to build and train highly intelligent agents in other domains.

As autonomous vehicle development rapidly accelerates, it is important to not lose sight of what the worst case scenario is during the drive of an autonomous vehicle. Autonomous vehicles are not perfect, and will not be perfect for the foreseeable future. These vehicles will shift the responsibility of driving to the passenger in front of the wheel, regardless if said passenger is prepared to do so. However, by studying the human reaction to an autonomous vehicle crash, researchers can mitigate the risk to the passengers in an autonomous vehicle. Located on the ASU Polytechnic campus, there is a car simulation lab, or SIM lab, that enables users to create and simulate various driving scenarios using the Drive Safety and HyperDrive software. Using this simulator and the Window of Intervention, the time a driver has to avoid a crash, vital research into human reaction time while in an autonomous environment can be safely performed. Understanding the Window of Intervention is critical to the development of solutions that can accurately and efficiently help a human driver. After first describing the simulator and its operation in depth, a deeper look will be offered into the autonomous vehicle field, followed by an in-depth explanation into the Window of Intervention and how it is studied and an experiment that looks to study both the Window of Intervention and human reactions to certain events. Finally, additional insight from one of the authors of this paper will be given documenting their contributions to the study as a whole and their concerns about using the simulator for further research.

Parents fulfill a pivotal role in early childhood development of social and communication

skills. In children with autism, the development of these skills can be delayed. Applied

behavioral analysis (ABA) techniques have been created to aid in skill acquisition.

Among these, pivotal response treatment (PRT) has been empirically shown to foster

improvements. Research into PRT implementation has also shown that parents can be

trained to be effective interventionists for their children. The current difficulty in PRT

training is how to disseminate training to parents who need it, and how to support and

motivate practitioners after training.

Evaluation of the parents’ fidelity to implementation is often undertaken using video

probes that depict the dyadic interaction occurring between the parent and the child during

PRT sessions. These videos are time consuming for clinicians to process, and often result

in only minimal feedback for the parents. Current trends in technology could be utilized to

alleviate the manual cost of extracting data from the videos, affording greater

opportunities for providing clinician created feedback as well as automated assessments.

The naturalistic context of the video probes along with the dependence on ubiquitous

recording devices creates a difficult scenario for classification tasks. The domain of the

PRT video probes can be expected to have high levels of both aleatory and epistemic

uncertainty. Addressing these challenges requires examination of the multimodal data

along with implementation and evaluation of classification algorithms. This is explored

through the use of a new dataset of PRT videos.

The relationship between the parent and the clinician is important. The clinician can

provide support and help build self-efficacy in addition to providing knowledge and

modeling of treatment procedures. Facilitating this relationship along with automated

feedback not only provides the opportunity to present expert feedback to the parent, but

also allows the clinician to aid in personalizing the classification models. By utilizing a

human-in-the-loop framework, clinicians can aid in addressing the uncertainty in the

classification models by providing additional labeled samples. This will allow the system

to improve classification and provides a person-centered approach to extracting

multimodal data from PRT video probes.

Intelligence is a loosely defined term, but it is a quality that we try to measure in humans, animals, and recently machines. Progress in artificial intelligence is slow, but we have recently made breakthroughs by paying attention to biology and neuroscience. We have not fully explored what biology has to offer us in AI research, and this paper explores aspects of intelligent behavior in nature that machines still struggle with.

Brains and computers have been interacting since the invention of the computer. These two entities have worked together to accomplish a monumental set of goals, from landing man on the moon to helping to understand how the universe works on the most microscopic levels, and everything in between. As the years have gone on, the extent and depth of interaction between brains and computers have consistently widened, to the point where computers help brains with their thinking in virtually infinite everyday situations around the world. The first purpose of this research project was to conduct a brief review for the purposes of gaining a sound understanding of how both brains and computers operate at fundamental levels, and what it is about these two entities that allow them to work evermore seamlessly as the years go on. Next, a history of interaction between brains and computers was developed, which expanded upon the first task and helped to contribute to visions of future brain-computer interaction (BCI). The subsequent and primary task of this research project was to develop a theoretical framework for a potential brain-aiding device of the future. This was done by conducting an extensive literature review regarding the most advanced BCI technology in modern times and expanding upon the findings to argue feasibility of the future device and its components. Next, social predictions regarding the acceptance and use of the new technology were made by designing and executing a survey based on the Unified Theory of the Acceptance and Use of Technology (UTAUT). Finally, general economic predictions were inferred by examining several relationships between money and computers over time.

Today, in a world of automation, the impact of Artificial Intelligence can be seen in every aspect of our lives. Starting from smart homes to self-driving cars everything is run using intelligent, adaptive technologies. In this thesis, an attempt is made to analyze the correlation between driving quality and its impact on the use of car infotainment system and vice versa and hence the driver distraction. Various internal and external driving factors have been identified to understand the dependency and seriousness of driver distraction caused due to the car infotainment system. We have seen a number UI/UX changes, speech recognition advancements in cars to reduce distraction. But reducing the number of casualties on road is still a persisting problem in hand as the cognitive load on the driver is considered to be one of the primary reasons for distractions leading to casualties. In this research, a pathway has been provided to move towards building an artificially intelligent, adaptive and interactive infotainment which is trained to behave differently by analyzing the driving quality without the intervention of the driver. The aim is to not only shift focus of the driver from screen to street view, but to also change the inherent behavior of the infotainment system based on the driving statistics at that point in time without the need for driver intervention.

The Internet is a major source of online news content. Online news is a form of large-scale narrative text with rich, complex contents that embed deep meanings (facts, strategic communication frames, and biases) for shaping and transitioning standards, values, attitudes, and beliefs of the masses. Currently, this body of narrative text remains untapped due—in large part—to human limitations. The human ability to comprehend rich text and extract hidden meanings is far superior to known computational algorithms but remains unscalable. In this research, computational treatment is given to online news framing for exposing a deeper level of expressivity coined “double subjectivity” as characterized by its cumulative amplification effects. A visual language is offered for extracting spatial and temporal dynamics of double subjectivity that may give insight into social influence about critical issues, such as environmental, economic, or political discourse. This research offers benefits of 1) scalability for processing hidden meanings in big data and 2) visibility of the entire network dynamics over time and space to give users insight into the current status and future trends of mass communication.

A lot of research can be seen in the field of social robotics that majorly concentrate on various aspects of social robots including design of mechanical parts and their move- ment, cognitive speech and face recognition capabilities. Several robots have been developed with the intention of being social, like humans, without much emphasis on how human-like they actually look, in terms of expressions and behavior. Fur- thermore, a substantial disparity can be seen in the success of results of any research involving ”humanizing” the robots’ behavior, or making it behave more human-like as opposed to research into biped movement, movement of individual body parts like arms, fingers, eyeballs, or human-like appearance itself. The research in this paper in- volves understanding why the research on facial expressions of social humanoid robots fails where it is not accepted completely in the current society owing to the uncanny valley theory. This paper identifies the problem with the current facial expression research as information retrieval problem. This paper identifies the current research method in the design of facial expressions of social robots, followed by using deep learning as similarity evaluation technique to measure the humanness of the facial ex- pressions developed from the current technique and further suggests a novel solution to the facial expression design of humanoids using deep learning.