We are seeing a revolution in computing and artificial intelligence; intelligent machines have become ingrained in and improved every aspect of our lives. Despite the increasing number of intelligent devices and breakthroughs in artificial intelligence, we have yet to achieve truly intelligent environments. Audio is one of the most common sensing and actuation modalities used in intelligent devices. In this thesis, we focus on how we can more robustly integrate audio intelligence into a wide array of resource-constrained platforms that enable more intelligent environments. We present systems and methods for adaptive audio filtering that enables us to more robustly embed acoustic intelligence into a wide range of real time and resource-constrained mobile, embedded, and cyber-physical systems that are adaptable to a wide range of different applications, environments, and scenarios. First, we introduce methods for embedding audio intelligence into wearables, like headsets and helmets, to improve pedestrian safety in urban environments by using sound to detect vehicles, localize vehicles, and alert pedestrians well in advance to give them enough time to avoid a collision. We create a segmented architecture and data processing pipeline that partitions computation between embedded front-end platform and the smartphone platform. The embedded front-end hardware platform consists of a microcontroller and commercial-off-the shelf (COTS) components embedded into a headset and samples audio from an array of four MEMS microphones. Our embedded front-end platform computes a series of spatiotemporal features used to localize vehicles: relative delay, relative power, and zero crossing rate. These features are computed in the embedded front-end headset platform and transmitted wirelessly to the smartphone platform because there is not enough bandwidth to transmit more than two channels of raw audio with low latency using standard wireless communication protocols, like Bluetooth Low-Energy. The smartphone platform runs machine learning algorithms to detect vehicles, localize vehicles, and alert pedestrians. To help reduce power consumption, we integrate an application specific integrated circuit into our embedded front-end platform and create a new localization algorithm called angle via polygonal regression (AvPR) that combines the physics of audio waves, the geometry of a microphone array, and a data driven training and calibration process that enables us to estimate the high resolution direction of the vehicle while being robust to noise resulting from movements in the microphone array as we walk the streets. Second, we explore the challenges in adapting our platforms for pedestrian safety to more general and noisier scenarios, namely construction worker safety sounds of nearby power tools and machinery that are orders of magnitude greater than that of a distant vehicle. We introduce an adaptive noise filtering architecture that allows workers to filter out construction tool sounds and reveal low-energy vehicle sounds to better detect them. Our architecture combines the strengths of both the physics of audio waves and data-driven methods to more robustly filter out construction sounds while being able to run on a resource-limited mobile and embedded platform. In our adaptive filtering architecture, we introduce and incorporate a data-driven filtering algorithm, called probabilistic template matching (PTM), that leverages pre-trained statistical models of construction tools to perform content-based filtering. We demonstrate improvements that our adaptive filtering architecture brings to our audio-based urban safety wearable in real construction site scenarios and against state-of-art audio filtering algorithms, while having a minimal impact on the power consumption and latency of the overall system. We also explore how these methods can be used to improve audio privacy and remove privacy-sensitive speech from applications that have no need to detect and analyze speech. Finally, we introduce a common selective audio filtering platform that builds upon our adaptive filtering architecture for a wide range of real-time mobile, embedded, and cyber-physical applications. Our architecture can account for a wide range of different sounds, model types, and signal representations by integrating an algorithm we present called content-informed beamforming (CIBF). CIBF combines traditional beamforming (spatial filtering using the physics of audio waves) with data driven machine learning sound detectors and models that developers may already create for their own applications to enhance and filter out specified sounds and noises. Alternatively, developers can also select sounds and models from a library we provide. We demonstrate how our selective filtering architecture can improve the detection of specific target sounds and filter out noises in a wide range of application scenarios. Additionally, through two case studies, we demonstrate how our selective filtering architecture can easily integrate into and improve the performance of real mobile and embedded applications over existing state-of-art solutions, while having minimal impact on latency and power consumption. Ultimately, this selective filtering architecture enables developers and engineers to more easily embed robust audio intelligence into common objects found around us and resource-constrained systems to create more intelligent environments.

The objective of this study was to assess the biomechanical and subjective measures of elementary school teachers while wearing active and/or passive wearable devices during the average workday. Five elementary school teachers wore a harness that held an Upright GO 2 posture tracking device and a Vicon Blue Trident sensor on the participant's upper back for two school days. Haptic feedback was on for one day and off for the other. Data from the Vicon wearable was analyzed to determine participants’ trunk flexion severity, frequency, and duration. Surveys were used to determine perceived exertion and perception of wearable technology. This study proved that teachers are undergoing severe trunk flexion throughout the day; however, there was not consistent improvement in trunk flexion when haptic feedback was applied. Results also indicated that perceived exertion levels of teachers did not always correlate to the frequency of trunk flexion measured through the wearable device.

Fundamentally, interaction design is about getting in between: Between people and what is important to them. While it often makes sense to make mediated interactions explicit, implicit interactions can integrate harmoniously into the here and now and happen almost unnoticed. In this master’s thesis, I explore different approaches to harmoniously integrate interactions with mobile and wearable devices into cycling. Cycling can be treated as a modality. It can influence the behaviour of the operating system or provide considerations for the design of applications. Rather than adding to the existing flow of signals, I propose to tap into that flow and even take it a step further: I explore ways to add meaning to what people are already doing as if there were no interface. Wearable devices, such as the current Apple Watch, can provide comprehensive insight into ongoing activities. The name "smartwatch" suggests that this device is meant to be attended to, but the greater opportunity lies in sensing and adding meaning to what is already happening. This allows people to immerse themselves in their ‘natural’ environment with their heads up and their hands free.

Addressing the shortage of healthcare professionals is critical for improving access to safe surgery in low- and middle-income countries. Patient safety precautions in surgical training include restricting the number of trainees present in the operating room, imposing limitations on how many surgeons can be trained simultaneously. The use of head-mounted cameras is suggested as a means to enhance and make surgical training more accessible by enabling remote viewing of surgical procedures from the surgeon's point-of-view. This research explores healthcare professionals' acceptance of incorporating a head-mounted smart camera as a complementary tool in surgical training. The case study, conducted during three surgical training workshops in Kenya and Ethiopia, utilized a modified UTAUT model. Questionnaires and five semi-structured interviews were employed, revealing a high level of technology acceptance. While some drawbacks were noted, overall positivity was expressed. The smart camera did in many ways align well with the needs of surgeons and anesthesiologists. Challenges mainly revolved around facilitating conditions such as poor connectivity and costs. Although the smart camera in many aspects enhanced the efficiency of surgical training, the findings highlight its inability to fully replace direct observation in the operating room.

Childhood obesity is a foremost concern throughout the health care community. Approximately 17.6% of the pediatric population meet the criteria for obesity, which can lead to health disparities later in life, such as hypertension, type 2 diabetes mellitus, and metabolic syndrome. Emerging mobile and wearable lifestyle tracking devices can be a viable solution to the challenging problem of childhood obesity through behavior changes, feasibility, and adherence. The purpose of this literature review was to determine the effect that mobile and wearable activity tracking devices have on the obese pediatric population. A centralized review of the literature was conducted using various data basesand resulted in 19 articles. 5 articles were chosen to review in more detail. 13 other articles were hand searched through credible resource citations, rendering 14 articles that met all criteria. The three general themes found in this literature review suggest that wearable activity tracking devices can be designed and effectively used by the pediatric population. Also, wearable activity tracking devices are accurate in conveying information on physical activity, calories, and heart rate. Lastly, wearable activity tracking devices can initiate behavioral changes in children leading to an increase in physical activity, resulting in the prevention and treatment of pediatric obesity.While in a majority of the studies analyzed trails were short. The research suggests wearable activity tracking devices will produce the desired results of increased activity in pediatric populations when they are worn correctly, are adequately engaging, and when they are designed in a feasible manner that is appealing to children.

No description available.

Wearable technology has made a positive impact in the consumer industry with its focus on adult fitness. Devices and applications are pervasive, inexpensive and are in high demand. Our nation struggles with obesity and health concerns related to poor fitness. However, the research on such technology has been more focused on adults. Therefore, the need to investigate wearable technology for fitness improvement with children is essential. Children lead increasingly sedentary lifestyles through TV watching, technology-use and a reduction in physical activities. Further, our society is exposed to quick food loaded with calories. These factors contribute to the growing epidemic of childhood obesity. The need to educate students early, on their ability to monitor their fitness, is the focus of this research. This dissertation investigated the impact of an integrated technology-enhanced physical education model with 127 fifth grade students over an 11-week period. A detailed analysis, looking at theoretical perspectives across multiple data collections was conducted. This study answered the questions, 1. To what extent can students improve their performance with technology-enhanced physical education? 2. To what extent can students learn to self-monitor their performance levels? How do affective components impact teaching and learning with a technology-enhanced physical education model? Results showed that technology-enhanced physical education does improve performance measures, does improve students' ability to self-regulate and positively impacts student and teachers' affective states. However long term results were inconclusive, stimulating multiple, potential opportunities for continued research.

Designing for and with animals is common within Animal-Computer Interaction (ACI). However, studies involving animals within the design process has challenges due to verbal barriers, and an unclear methodology on how to both understand, and analyse animals in ACI. This paper explores how an air-scent search dog can participate in the design process from the beginning to end involved in various design methods with a Participatory design (PD) approach, to empower the relationship between human and dog with the help of wearable technology. The study explores the benefits and challenges of the involvement of other species than humans in the process of making a prototype. Furthermore, two types of tools with biting and pulling interactions attached to a vest were developed and tested on an air-scent search dog in two different environments. Due to the verbal barrier between dogs and humans, it was necessary to let the dog participate by testing physical prototypes. This study aims to empower this relationship between an air-scent search dog and its handler with the help of wearable technology. The results suggest that direct contact with the other species is crucial in the creation and iteration of prototypes regarding; weight, placement, and wearable technology. The results also showed that in the context of search training, or situated based action, it is crucial to test the prototypes in an environment that reflects a real scenario in a forest, which is a typical place for search training.

The main objective of the presented research is to design, fabricate, fully characterize, and assess the usability and functionality of a novel wireless tongue-operated assistive technology, called Tongue Drive System (TDS), that allows individuals with severe physical disabilities (such as quadriplegics) to effectively access computers, drive powered wheelchairs, and control environments using their voluntary tongue motion. The system can wirelessly detect users' tongue movements using an array of magnetic sensors, and a magnetic tracer secured on the tongue, and translate them into a set of user-defined commands in real time, which can then be used to communicate with target devices in users' environment. The principal advantage of the TDS is that a combination of magnetic sensors and a small permanent magnet can capture a large number of tongue movements, each of which can represent one specific command. A set of dedicated tongue movements can be configured as specific commands for each individual user based on his/her preferences, lifestyle, and remaining abilities. As a result, this technology can benefit a wide range of potential users with different types of disabilities. The work carried out in this dissertation is largely split into three portions: (1) Development, fabrication and characterization of external TDS (eTDS) prototypes to verify the concept of TDS that is detecting and extracting user's intention through their voluntary tongue motion, utilizing a combination of magnetic sensors and a small magnet, as well as the application of this idea in the context of assistive technology. This part of the work is presented in Chapters IV, V and VI. (2) Assessment of the TDS performance in medium term usage for both computer access and wheelchair control. The main purpose of this work was to gain valuable insight into the TDS learning process and its current limiting factors, which could lead the way in designing new generations of TDS with improved usability. This portion of the work is described in Chapter VII. (3) Development and performance assessment of a multimodal TDS (mTDS), that operates based on the information collected from two independent input channels: the tongue motion and speech. This multimodal system expands the access beyond one input channel and therefore improves the speed of access by increasing the information transfer bandwidth between users and computers. This part of the work is presented in Chapters VIII and IX. This dissertation has contributed to the innovation and advancement of the start-of-the-art assistive technology research by exploring, realizing and validating the use of tongue motion as a voluntary motor output to substitute some of the lost arm and hand functions in people with severe disabilities for computer access, wheelchair navigation, and environmental control.

How can vibrotactile stimuli be used to create a technology-mediated somatic learning experience? This question motivates this practice-based research, which explores how the Feldenkrais Method and cognate neuroscience research can be applied to technology design. Supported by somaesthetic philosophy, soma-based design theories, and a critical acknowledgement of the socially-inflected body, the research develops a systematic method grounded in first- and third-person accounts of embodied experience to inform the creation and evaluation of design of Haplós, a wearable, user-customisable, remote-controlled technology that plays methodically composed vibrotactile patterns on the skin in order to facilitate body awareness—the major outcome of this research and a significant contribution to soma-based creative work. The research also contributes to design theory and somatic practice by developing the notion of a somatic learning affordance, which emerged during course of the research and which describes the capacity of a material object to facilitate somatic learning. Two interdisciplinary collaborations involving Haplós contribute to additional fields and disciplines. In partnership with experimental psychologists, Haplós was used in a randomised controlled study that contributes to cognitive psychology by showing that vibrotactile compositions can reduce, with statistical significance, intrusive food-related thoughts. Haplós was also used in Bisensorial, an award-winning, collaboratively developed proof-of-concept of a neuroadaptive vibroacoustic therapeutic device that uses music and vibrotactile stimuli to induce desired mental states. Finally, this research contributes to cognitive science and embodied philosophy by advancing a neuroscientific understanding of vibrotactile somaesthetics, a novel extension of somaesthetic philosophy.