<p dir="ltr">Data is collected everywhere in our world; however, it often is noisy and incomplete. Different sources of data may have different characteristics, quality levels, or come from dynamic and diverse environments. This poses challenges for both humans who want to gain insights from data and machines which are learning patterns from data. How can we leverage the diversity of data across domains to enhance our understanding and decision-making? In this thesis, we address this question by proposing novel methods and applications that use multiple domains as more holistic sources of information for both human and machine learning tasks. For example, to help human operators understand environmental dynamics, we show the detection and localization of distribution shifts to problematic features, as well as how interpretable distributional mappings can be used to explain the differences between shifted distributions. For robustifying machine learning, we propose a causal-inspired method to find latent factors that are robust to environmental changes and can be used for counterfactual generation or domain-independent training; we propose a domain generalization framework that allows for fast and scalable models that are robust to distribution shift; and we introduce a new dataset based on human matches in StarCraft II that exhibits complex and shifting multi-agent behaviors. We showcase our methods across various domains such as healthcare, natural language processing (NLP), computer vision (CV), etc. to demonstrate that learning from data across domains can lead to more faithful representations of data and its generating environments for both humans and machines.</p>

Lågströmskommunikationsprotokoll såsom 6LoWPAN har använts i stor utsträckning för applikationer som kräver mindre energiförbrukning för trådlös kommunikation på korta avstånd, exempelvis IoT-enheter. Eftersom antalet sådana enheter ökar blir det allt viktigare att överväga ambient energy harvesting som en energikälla för att driva sådana enheter. Det framkallar ett behov av att ompröva designen av ett energieffektivt kommunikationsprotokoll som gör det möjligt för sensorer och aktuatorer att använda den utvunna energin för beräkning och kommunikation. Eftersom den utvunna energin från en energikälla är begränsad och det tar tid för en enhet att samla tillräckligt med energi för datahantering och kommunikation, finns det ett behov av att undersöka energibudgeten och bestämma de kritiska parametrarna som påverkar energiförbrukningen för trådlös kommunikation. En analys av energiförbrukningen utfördes genom att anpassa en Python-modell och simuleringar genomfördes för att hjälpa till att förstå påverkan av nyckelparametrar på energiförbrukningen med hänsyn till en lämplig radio frequency energy harvesting (RF-EH) för “zero” energienheter. I examensarbetet föreslås designöverväganden för ett nytt lågströmskommunikationsprotokoll för “zero” energienheter. Resultaten visade att adaptive data rate (ADR) har en stor betydelse för energibesparingar. Med lämpliga överföringsparametrar inställda kan energiförlusterna för omsändningar och kollisioner minskas. Det är också möjligt att införa en schemaläggningsalgoritm för kommunikationsprocessen för förbättrad kollisionsundvikande. De föreslagna designövervägandena kan tillämpas i framtida arbeten för att förbättra kortdistanskommunikationsprotokollet för “zero” energienheter. / Low power communication protocols such as 6LoWPAN have been widely used on applications that require less energy consumption for short-range wireless communication, for example, Internet of Thing (IoT) devices. As the amount of these devices escalates, it becomes increasingly important to consider ambient energy harvesting (EH) as an energy source to power such devices. This induces a need to reconsider the design of an energy-efficient data transfer protocol that enables the sensors and actuators to utilize the harvested energy for computing and communication. As the harvested energy from an energy source is limited and it takes time for a device to accumulate enough energy for data processing and communication, there is a need to investigate the energy budget and determine the critical parameters that affect the energy consumption for wireless communication. An energy consumption analysis was performed by adapting a Python model, and simulations were carried out to help understand the impact of key parameters on energy consumption while considering a suitable range for radio frequency (RF) energy harvesting “zero” energy devices. The thesis project aims to propose the design considerations of a new low-power communication protocol for “zero” energy devices. The results showed that adaptive data rate (ADR) has a major contribution to energy saving. With suitable transmitting parameters set, the energy waste of retransmissions and collisions could be reduced. It is also possible to introduce a scheduling algorithm to the communication process for improved collision avoidance. The proposed design considerations can be applied in future work to improve the shortrange communication protocol for zero-energy devices.

En imagerie par résonance magnétique (IRM) interventionnelle, des interventions percutanées minimalement-invasives (biopsies, ablations de tumeurs,...) sont réalisées sous guidage IRM. Lors de l’intervention, les plans de coupe acquis sont alignés sur l’outil chirurgical et les régions anatomiques d’intérêt afin de surveiller la progression de l’outil dans le corps du patient en temps réel. Le suivi d’objets dans l’IRM facilite et accélère les interventions guidées par IRM en permettant d’aligner automatiquement les plans de coupe avec l’outil chirurgical. Dans cette thèse, un système d’alignement automatique des plans de coupe établi sur une séquence IRM clinique est développé. Celui-ci réalise automatiquement la détection et le suivi d’un marqueur passif directement dans les images IRM tout en minimisant le temps d’imagerie dédié à la détection. L’inconvénient principal de cette approche est sa dépendance au temps d’acquisition de la séquence IRM clinique utilisée. Dans un premier temps, les performances du suivi ont pu être améliorées grâce à l’estimation et la prédiction du mouvement suivi par un filtre de Kalman. Puis un capteur optique complémentaire a été ajouté pour réaliser un suivi multi-capteurs, découplant ainsi la fréquence de rafraichissement du suivi de la fréquence de rafraichissement des images IRM. La performance du système développé a été évaluée par des simulations et des expériences utilisant un banc d’essai compatible IRM. Les résultats montrent une bonne robustesse du suivi multi-capteurs pour l’alignement des plans de coupe grâce à la combinaison des qualités individuelles de chaque capteur. / Interventional magnetic resonance imaging (MRI) aims at performing minimally invasive percutaneous interventions, such as tumor ablations and biopsies, under MRI guidance. During such interventions, the acquired MR image planes are typically aligned to the surgical instrument (needle) axis and to surrounding anatomical structures of interest in order to efficiently monitor the advancement in real-time of the instrument inside the patient’s body. Object tracking inside the MRI is expected to facilitate and accelerate MR-guided interventions by allowing to automatically align the image planes to the surgical instrument. In this PhD thesis, an image-based workflow is proposed and refined for automatic image plane alignment. An automatic tracking workflow was developed, performing detection and tracking of a passive marker directly in clinical real-time images. This tracking workflow is designed for fully automated image plane alignment, with minimization of tracking-dedicated time. Its main drawback is its inherent dependence on the slow clinical MRI update rate. First, the addition of motion estimation and prediction with a Kalman filter was investigated and improved the workflow tracking performance. Second, a complementary optical sensor was used for multi-sensor tracking in order to decouple the tracking update rate from the MR image acquisition rate. Performance of the workflow was evaluated with both computer simulations and experiments using an MR compatible testbed. Results show a high robustness of the multi-sensor tracking approach for dynamic image plane alignment, due to the combination of the individual strengths of each sensor.

The monitoring of continuous phenomena like temperature, air pollution, precipitation, soil moisture etc. is of growing importance. Decreasing costs for sensors and associated infrastructure increase the availability of observational data. These data can only rarely be used directly for analysis, but need to be interpolated to cover a region in space and/or time without gaps. So the objective of monitoring in a broader sense is to provide data about the observed phenomenon in such an enhanced form. Notwithstanding the improvements in information and communication technology, monitoring always has to function under limited resources, namely: number of sensors, number of observations, computational capacity, time, data bandwidth, and storage space. To best exploit those limited resources, a monitoring system needs to strive for efficiency concerning sampling, hardware, algorithms, parameters, and storage formats. In that regard, this work proposes and evaluates solutions for several problems associated with the monitoring of continuous phenomena. Synthetic random fields can serve as reference models on which monitoring can be simulated and exactly evaluated. For this purpose, a generator is introduced that can create such fields with arbitrary dynamism and resolution. For efficient sampling, an estimator for the minimum density of observations is derived from the extension and dynamism of the observed field. In order to adapt the interpolation to the given observations, a generic algorithm for the fitting of kriging parameters is set out. A sequential model merging algorithm based on the kriging variance is introduced to mitigate big workloads and also to support subsequent and seamless updates of real-time models by new observations. For efficient storage utilization, a compression method is suggested. It is designed for the specific structure of field observations and supports progressive decompression. The unlimited diversity of possible configurations of the features above calls for an integrated approach for systematic variation and evaluation. A generic tool for organizing and manipulating configurational elements in arbitrary complex hierarchical structures is proposed. Beside the root mean square error (RMSE) as crucial quality indicator, also the computational workload is quantified in a manner that allows an analytical estimation of execution time for different parallel environments. In summary, a powerful framework for the monitoring of continuous phenomena is outlined. With its tools for systematic variation and evaluation it supports continuous efficiency improvement.

Ausgehend von einer modularen Plattform zur Erfassung und Verarbeitung von Sensordaten bereichert die vorliegende Dissertationsschrift den Systementwurf eingebetteter Systeme um neue Facetten. Ihr besonderer Fokus liegt dabei auf rekonfigurierbaren Architekturen und Linux-basierten Systemen. Ein wesentlicher Beitrag ist die Darstellung und Diskussion von Konzepten und Architekturen vorgenannter Systeme durch ihre Betrachtung auf einer hohen Abstraktionsebene. Dazu schafft die Arbeit ein umfassendes Verständnis für Kommunikation und Konfiguration in heterogenen rekonfigurierbaren Systemen und überträgt die Erkenntnisse auf das Linux-Betriebssystem. Es erfolgt außerdem eine systematische Darstellung der etablierten Zusammenhänge und Abläufe beim Software-, Paket- und Versionsmanagement im Linux-Umfeld. Zur Verbesserung des Entwurfsflusses werden Konzepte und ein geeignetes Werkzeug zur High-Level Spezifikation von Linux-Systemen dargestellt. Die in der Arbeit gewonnenen wissenschaftlichen Erkenntnisse werden hinsichtlich praktischer Relevanz evaluiert und durch prototypische Implementierungen verifiziert. / Based on a modular platform for recording and processing of sensor data the present thesis enriches the field of system design of embedded systems with new facets. Its particular focus is on reconfigurable architectures and Linux-based systems. A major contribution is the presentation and discussion of concepts and architectures of aforementioned systems by investigating them on a high level of abstraction. To achieve this, the work creates a comprehensive understanding of communication and configuration in heterogeneous reconfigurable systems. This knowledge is transferred on the Linux operating system. In addition, a systematic presentation of the established relationships and processes in software, package and version management in the Linux environment takes place. To improve the design flow of Linux systems, the thesis presents appropriate concepts as well as a tool for high-level specification of embedded Linux systems. The gained scientific findings are evaluated in terms of practical relevance and verified by prototype implementations.

<p><strong>The Energy Monitoring Framework</strong>, designed and developed by IAC, IUPUI, aims to provide a cloud-based solution that combines business analytics with sensors for real-time energy management at the plant level using wireless sensor network technology.</p> <p>The project provides a platform where users can analyze the functioning of a plant using sensor data. The data would also help users to explore the energy usage trends and identify any energy leaks due to malfunctions or other environmental factors in their plant. Additionally, the users could check the machinery status in their plant and have the capability to control the equipment remotely.</p> <p>The main objectives of the project include the following:</p> <ul> <li>Set up a wireless network using sensors and smart implants with a base station/ controller.</li> <li>Deploy and connect the smart implants and sensors with the equipment in the plant that needs to be analyzed or controlled to improve their energy efficiency.</li> <li>Set up a generalized interface to collect and process the sensor data values and store the data in a database.</li> <li>Design and develop a generic database compatible with various companies irrespective of the type and size.</li> <li> Design and develop a web application with a generalized structure. Hence the database can be deployed at multiple companies with minimum customization. The web app should provide the users with a platform to interact with the data to analyze the sensor data and initiate commands to control the equipment.</li> </ul> <p>The General Structure of the project constitutes the following components:</p> <ul> <li>A wireless sensor network with a base station.</li> <li>An Edge PC, that interfaces with the sensor network to collect the sensor data and sends it out to the cloud server. The system also interfaces with the sensor network to send out command signals to control the switches/ actuators.</li> <li>A cloud that hosts a database and an API to collect and store information.</li> <li>A web application hosted in the cloud to provide an interactive platform for users to analyze the data.</li> </ul> <p>The project was demonstrated in:</p> <ul> <li>Lecture Hall (https://iac-lecture-hall.engr.iupui.edu/LectureHallFlask/).</li> <li>Test Bed (https://iac-testbed.engr.iupui.edu/testbedflask/).</li> <li>A company in Indiana.</li> </ul> <p>The above examples used sensors such as current sensors, temperature sensors, carbon dioxide sensors, and pressure sensors to set up the sensor network. The equipment was controlled using compactable switch nodes with the chosen sensor network protocol. The energy consumption details of each piece of equipment were measured over a few days. The data was validated, and the system worked as expected and helped the user to monitor, analyze and control the connected equipment remotely.</p> <p><br></p>

<p>There are no commercially available wearable shoe in-sole sensors that are capable of measuring and distinguishing between shear and compression forces. Companies have already developed shoe sensors that simply measure pressure and make general inferences on the collected data with elaborate software [2, 3, 4, 5]. Researchers have also attempted making sensors that are capable of measuring shear forces, but they are not well suited for biomedical applications [61, 62, 63, 64]. This work focuses on the development of a novel wearable sensor system that is capable of identifying and measuring shear and compression forces through the use of capacitive sensing. Custom hardware and software tools such as materials test systems and capacitive measurement systems were developed during this work. Numerous sensor prototypes were developed, characterized, and optimized during the scope of this project. Upon analysis of the data, the best capacitive measurement system developed in this work utilized the CAV444 IC chip, whereas the use of the Arduino-derived measurement system required data filtering using median and Butterworth zero phase low pass filters. The highest dielectric constant reported from optimization experiments yielded 9.7034 (+/- 0.0801 STD) through the use of 60.2% by weight calcium copper titanate and ReoFlex-60 silicone. The experiments suggest certain sensors developed in this work feasibly measure and distinguish between shear and compressional forces. Applications for such technology focus on improving quality of life in areas such as managing diabetic ulcer formation, preventing injuries, optimizing performance for athletes and military personnel, and augmenting the scope of motion capture in biomechanical studies.</p>