Water monitoring is an essential process that managesthe well-being of freshwater ecosystems. However, it isgenerally an inefficient process as most data collection is donemanually. By combining wireless sensor technology and machinelearning techniques, projects such as iWater aim to modernizecurrent methods. The purpose of the iWater project is to developa network of smart sensors capable of collecting and analyzingwater quality-related data in real time.To contribute to this goal, a comparative study between theperformance of a centralized machine learning algorithm thatis currently used, and a distributed model based on a federatedlearning algorithm was done. The data used for training andtesting both models was collected by a wireless sensor developedby the iWater project. The centralized algorithm was used asthe basis for the developed distributed model. Due to lack ofsensors, the distributed model was simulated by down-samplingand dividing the sensor data into six data sets representing anindividual sensor. The results are similar for both models andthe developed algorithm reaches an accuracy of 98.41 %. / Vattenövervakning är en nödvändig processför att få inblick i sötvattensekosystems välmående. Dessvärreär det en kostsam och tidskrävande process då insamling avdata vanligen görs manuellt. Genom att kombinera trådlössensorteknologi och maskininlärnings algoritmer strävar projektsom iWater mot att modernisera befintliga metoder.Syftet med iWater är att skapa ett nätverk av smarta sensorersom kan samla in och analysera vattenkvalitetsrelaterade datai realtid. För att bidra till projektmålet görs en jämförandestudie mellan den prediktiva noggrannheten hos en centraliseradmaskininlärningsalgoritm, som i nuläget används, och endistribuerad modell baserad på federerat lärande. Data somanvänds för träning och testning av båda modellerna samladesin genom en trådlös sensor utvecklad inom iWater-projektet.Den centraliserade algoritmen användes som grund för denutvecklade distribuerade modellen. På grund av brist på sensorersimulerades den distribuerade modellen genom nedprovtagningoch uppdelning av data i sex datamängder som representerarenskilda sensorer. Resultaten för båda modellerna var liknandeoch den utvecklade algoritmen har en noggrannhet på 98.41 % / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm

The proliferation of web based technologies has resulted in new forms of communities and organizations with enormous implications for design of learning and education. This thesis explores learning occurring within open source software (OSS) communities. OSS communities are a dominant form of organizing in software development with implications not only for innovative product development but also for the training of a large number of software developers. The central catalyst of learning within these communities is expert-novice interactions. These interactions between experts and novices or newcomers are critical for the growth and sustenance of a community and therefore it is imperative that experts are able to provide newcomers requisite advice and support as they traverse the community and develop software. Although prior literature has demonstrated the significance of expert-novice interactions, there are two central issues that have not been examined. First, there is no examination of the role of external events on community interaction, particularly as it relates to experts and novices. Second, the exact nature of expert help, particularly, the quantity of help and whether it helps or hinders newcomer participation has not been studied. This thesis studies these two aspects of expert-novice interaction within OSS communities. The data for this study comes from two OSS communities. The Java newcomer forum was studied as it provided a useful setting for examining external events given the recent changes in Java's ownership. Furthermore, the forum has a rating system which classifies newcomers and experienced members allowing the analysis of expert-novice interactions. The second set of data comes from the MySQL newcomer forum which has also undergone organizational changes and allows for comparison with data from the Java forum. Data were collected by parsing information from the HTML pages and stored in a relational database. To analyze the effect of external events, a natural experiment method was used whereby participation levels were studied around significant events that affected the community. To better understand the changes contextually, an extensive study of major news outlets was also undertaken. Findings from the external event study show significant changes in participation patterns, especially among newcomers in response to key external events. The study also revealed that the changes in participation of newcomers were observed even though other internal characteristics (help giving, expert participation) did not change indicating that external events have a strong bearing on community participation. The effect of expert advice was studied using a logistic regression model to determine how specific participation patterns in discussion threads led to the final response to newcomers. This was supported by social network analysis to visually interpret the participation patterns of experienced members in two different scenarios, one in which the question was answered and the other where it was not. Findings show that higher number of responses from experienced members did not correlate with a response. Therefore, although expert help is essential, non-moderated or unguided help can lead to conflict among experts and inefficient feedback to newcomers. / Master of Science

Approved for public release, distribution is unlimited / This thesis critically analyzes the Sharable Content Object Reference Model (SCORM) within higher education and examines SCORM's limitations within a realistic application environment versus within a theoretical/conceptual platform. The thesis also examines environments better suited for implementation of SCORM technology. In addressing the research questions, it was discovered that from the current standards set forth by Advanced Distributed Learning (ADL), SCORM is not well suited for higher education. SCORM technology will prove of greater utility within the Navy Training environment than in higher education. In their effort to share information, higher education institutions would benefit more from a Content Management System in conjunction with a Learning Management System. Subsequent chapters addressed the limitations of SCORM, provided a comparison of the applicability of SCORM within the separate domains of naval Education and Training, and provided a prototype of a Content Management System for institutions of higher learning. / Lieutenant Commander, Hellenic Navy / Lieutenant, United States Naval Reserve

Stochastic and data-distributed optimization algorithms have received lots of attention from the machine learning community due to the tremendous demand from the large-scale learning and the big-data related optimization. A lot of stochastic and deterministic learning algorithms are proposed recently under various application scenarios. Nevertheless, many of these algorithms are based on heuristics and their optimality in terms of the generalization error is not sufficiently justified. In this talk, I will explain the concept of an optimal learning algorithm, and show that given a time budget and proper hypothesis space, only those achieving the lower bounds of the estimation error and the optimization error are optimal. Guided by this concept, we investigated the stochastic minimization of nonsmooth convex loss functions, a central problem in machine learning. We proposed a novel algorithm named Accelerated Nonsmooth Stochastic Gradient Descent, which exploits the structure of common nonsmooth loss functions to achieve optimal convergence rates for a class of problems including SVMs. It is the first stochastic algorithm that can achieve the optimal O(1/t) rate for minimizing nonsmooth loss functions. The fast rates are confirmed by empirical comparisons with state-of-the-art algorithms including the averaged SGD. The Alternating Direction Method of Multipliers (ADMM) is another flexible method to explore function structures. In the second part we proposed stochastic ADMM that can be applied to a general class of convex and nonsmooth functions, beyond the smooth and separable least squares loss used in lasso. We also demonstrate the rates of convergence for our algorithm under various structural assumptions of the stochastic function: O(1/sqrt{t}) for convex functions and O(log t/t) for strongly convex functions. A novel application named Graph-Guided SVM is proposed to demonstrate the usefulness of our algorithm. We also extend the scalability of stochastic algorithms to nonlinear kernel machines, where the problem is formulated as a constrained dual quadratic optimization. The simplex constraint can be handled by the classic Frank-Wolfe method. The proposed stochastic Frank-Wolfe methods achieve comparable or even better accuracies than state-of-the-art batch and online kernel SVM solvers, and are significantly faster. The last part investigates the problem of data-distributed learning. We formulate it as a consensus-constrained optimization problem and solve it with ADMM. It turns out that the underlying communication topology is a key factor in achieving a balance between a fast learning rate and computation resource consumption. We analyze the linear convergence behavior of consensus ADMM so as to characterize the interplay between the communication topology and the penalty parameters used in ADMM. We observe that given optimal parameters, the complete bipartite and the master-slave graphs exhibit the fastest convergence, followed by bi-regular graphs.

Abstract Resource allocation and interference management in wireless small cell networks have been areas of key research interest in the past few years. Although a large number of research studies have been carried out, the needs for high capacity, reliability, and energy efficiency in the emerging fifth-generation (5G) networks warrants the development of methodologies focusing on ultra-dense and self-organizing small cell network (SCN) scenarios. In this regard, the prime motivation of this thesis is to propose an array of distributed methodologies to solve the problem of joint resource allocation and interference management in SCNs pertaining to different network architectures. The present dissertation proposes and investigates distributed control mechanisms for wireless SCNs mainly in three cases: a backhaul-aware interference management mechanism of the uplink of wireless SCNs, a dynamic cluster-based approach for maximizing the energy efficiency of dense wireless SCNs, and a joint power control and user scheduling mechanism for optimizing energy efficiency in ultra-dense SCNs. Optimizing SCNs, especially in the ultra-dense regime, is extremely challenging due to the severe coupling in interference and the dynamics of both queues and channel states. Moreover, due to the lack of inter-base station/cluster communications, smart distributed learning mechanisms are required to autonomously choose optimal transmission strategies based on local information. To overcome these challenges, an array of distributed algorithms are developed by combining the tools from machine learning, Lyapunov optimization and mean-field theory. For each of the above proposals, extensive sets of simulations have been carried out to validate the performance of the proposed methods compared to conventional models that fail to account for the limitations due to network scale, dynamics of queue and channel states, backhaul heterogeneity and capacity constraints, and the lack of coordination between network elements. The results of the proposed methods yield significant gains of the proposed methods in terms of energy savings, rate improvements, and delay reductions compared to the conventional models studied in the existing literature. / Tiivistelmä Langattomien piensoluverkkojen resurssien allokointi ja häiriön hallinta on ollut viime vuosina tärkeä tutkimuskohde. Tutkimuksia on tehty paljon, mutta uudet viidennen sukupolven (5G) verkot vaativat suurta kapasiteettia, luotettavuutta ja energiatehokkuutta. Sen vuoksi on kehitettävä menetelmiä, jotka keskittyy ultratiheisiin ja itseorganisoituviin piensoluverkkoihin. (SCN). Tämän väitöskirjan tärkein tavoite onkin esittää joukko hajautettuja menetelmiä piensoluverkkojen yhteisten resurssien allokointiin ja häiriön hallintaan, kun käytössä on erilaisia verkkoarkkitehtuureja. Tässä väitöskirjassa ehdotetaan ja tutkitaan hajautettuja menetelmiä langattomien piensoluverkkojen hallintaan kolmessa eri tilanteessa: välityskanavan huomioiva häiriönhallinta menetelmä langattomissa piensoluverkoissa, dynaamisiin klustereihin perustuva malli tiheiden langattomien piensoluverkkojen energiatehokkuuden maksimointiin ja yhteinen tehonsäädön ja käyttäjien allokaatio menetelmä ultratiheiden piensoluverkkojen energiatehokkuuden optimointiin. Ultratiheiden piensoluverkkojen optimointi on erittäin haastavaa häiriön sekä jonojen ja kanavatilojen vahvojen kytkösten vuoksi. Lisäksi, koska klustereilla/tukiasemilla ei ole kommunikaatiota, tarvitaan hajautettuja oppimisalgoritmeja, jotta saadaan itsenäisesti valittua optimaaliset lähetys menetelmät hyödyntäen vain paikallista tietoa. Tämän vuoksi kehitetään useita hajautettuja algoritmeja, jotka hyödyntävät koneoppimista, Lyapunov optimointia ja mean-field teoriaa. Kaikki yllä olevat esitetyt menetelmät on validoitu laajoilla simulaatioilla, joilla on voitu todentaa niiden suorituskyky perinteisiin malleihin verrattuna. Perinteiset mallit eivät pysty ottamaan huomioon verkon laajuuden, jonon ja kanavatilojen dynamiikan, eri välityskanavien ja rajallisen kapasiteetin asettamia rajoituksia sekä verkon elementtien välisen koordinoinnin puuttumista. Esitetyt menetelmät tuottavat huomattavia parannuksia energiansäästöön, siirtonopeuteen ja viiveiden vähentämiseen verrattuna perinteisiin malleihin, joita kirjallisuudessa on tarkasteltu.

We consider a wireless communication system in which there are N transmitter-receiver pairs and each transmitter wants to communicate with its corresponding receiver. This is modelled as an interference channel. We propose power allocation algorithms for increasing the sum rate of two and three user interference channels. The channels experience fast fading and there is an average power constraint on each transmitter. In this case receivers use successive decoding under strong interference, instead of treating interference as noise all the time. Next, we u se game theoretic approach for power allocation where each receiver treats interference as noise. Each transmitter-receiver pair aims to maximize its long-term average transmission rate subject to an average power constraint. We formulate a stochastic game for this system in three different scenarios. First, we assume that each user knows all direct and crosslink channel gains. Next, we assume that each user knows channel gains of only the links that are incident on its receiver. Finally, we assume that each use r knows only its own direct link channel gain. In all cases, we formulate the problem of finding the Nash equilibrium(NE) as a variational in equality problem. For the game with complete channel knowledge, we present an algorithm to solve the VI and we provide weaker sufficient conditions for uniqueness of the NE than the sufficient conditions available in the literature. Later, we present a novel heuristic for solving the VI under general channel conditions. We also provide a distributed algorithm to compute Pare to optimal solutions for the proposed games. We use Bayesian learning that guarantees convergence to an Ɛ-Nash equilibrium for the incomplete information game with direct link channel gain knowledge only, that does not require knowledge of the power policies of other users but requires feedback of the interference power values from a receiver to its corresponding transmitter. Later, we consider a more practical scenario in which each transmitter transmits data at a certain rate using a power that depends on the channel gain to its receiver. If a receiver can successfully receive the message, it sends an acknowledgement(ACK), else it sends a negative ACK(NACK). Each user aims to maximize its probability of successful transmission. We formulate this problem as a stochastic game and propose a fully distributed learning algorithm to find a correlated equilibrium(CE). In addition, we use a no regret algorithm to find a coarse correlated equilibrium(CCE) for our power allocation game. We also propose a fully distributed learning algorithm to find a Pareto optimal solution. In general Pareto points do not guarantee fairness among the users. Therefore we also propose an algorithm to compute a Nash bargaining solution which is Pareto optimal and provides fairness among the users. Finally, we extend these results when each transmitter sends data at multiple rates rather than at a fixed rate.

<p>In this thesis, we present algorithms to allow agents to estimate certain properties in a robust, online, and distributed manner. Each agent receives a sequence of observations, and through communication, collectively infers properties of the data gathered by all agents by communicating.</p> <p><br></p> <p>In the first part of the thesis, we provide algorithms to infer the correlations between interacting entities from these large datasets. Gaussian graphical models have been well studied to represent the relationships between the various random variables which generate data, and numerous algorithms have been proposed to learn the dependencies in such models. However, existing algorithms typically process data in a batch at a central location, limiting their applications in scenarios where data arrive in real-time and are gathered by different agents.  </p> <p><br></p> <p>To address these challenges, first, we propose an online sparse inverse covariance algorithm to infer the static network structure (i.e., dependencies between nodes) in real-time from time-series data, in a centralized location. Subsequently, we propose a distributed algorithm to cooperatively learn the network structure in real-time from data collected by distributed agents. We characterize the theoretical convergence properties and provide simulations using synthetic datasets and real-world hurricane Twitter datasets in disaster management applications.    </p> <p><br></p> <p>The second part of this thesis addresses the robustness of online and distributed learning under arbitrary data corruption. We propose online and distributed algorithms for robust mean, covariance, and sparse inverse covariance estimation. These algorithms are capable of operating effectively even in the presence of adversarial data attacks. We provide theoretical bounds on the error and rate of convergence of these methods and evaluate their performance under various settings.</p> <p><br></p> <p>Finally, we consider the problem of classification with a network of heterogeneous and partially informative agents, each receiving local data from an underlying true class, and equipped with a classifier that only distinguishes between a subset of the entire set of classes. We propose an iterative algorithm that uses the posterior probabilities of any classifier and recursively updates each agent's local belief based on its local signals and belief information from its neighbors. We then adopt a novel distributed min-rule to update each agent’s global belief and enable learning of the true class for all agents. We analyze the convergence properties of our proposed algorithm, and subsequently, demonstrate and compare its performance with local averaging and global average consensus through simulations and with a visual image dataset.</p>

Abstract With the current technological advancements, stage is being set for new ultra-responsive and robust 5G-enabled applications (e.g., virtual reality, Tactile Internet,…) to deliver critical real-time traffic. The emergence of such critical applications requires new networking models that can handle more connected devices with super high reliability and low latency communications. In the view of these research challenges, this thesis aims to propose new techno-economic models and networking paradigms needed in the redesign of wireless network architectures and protocols to support the connectivity requirements by which operators and users effectively benefit from new opportunities introduced by 5G-enabled applications. In this thesis, new paradigms in wireless network access are presented and analyzed. First, dynamic network architecture (DNA) is introduced, where certain classes of wireless terminals can be turned temporarily into an access point (AP) anytime while connected to the Internet. In this concept, a framework is proposed to optimize different aspects of this architecture. Furthermore, to dynamically reconfigure an optimum topology and adjust it to the traffic variations, a new specific encoding of genetic algorithm (GA) is presented. Then, a distributed user-centric spectrum sharing is developed based on DNA networks to enable user-provided access points pervasively share the unused resources. Next, a flexible cloud-based radio access network (FRAN) is proposed to offload traffic to DNA networks in order to provide low latency communications. In the sequel of the thesis, as a new paradigm, a context-aware resource allocation scheme based on adaptive spatial beamforming and reinforcement learning is proposed. In addition, semi-cognitive radio network (SCRN) as a new spectrum sharing model is developed to improve the utility of primary and secondary owners. / Tiivistelmä Nykyaikaisilla teknologisilla edistysaskeleilla mahdollistetaan uusien 5G-pohjaisien erittäin lyhyen vasteajan ja suuren luotettavuuden sovelluksien ilmestyminen kriittisen reaaliaikaisen informaation välittämiseen (esim. taktiiliset ja virtuaalitodellisuus-sovellukset). Näiden kaltaiset sovellukset vaativat uudenlaisia verkottumismalleja, jotka kykenevät käsittelemään enemmän laitteita suurella toimintavarmuudella ja matalalla latenssilla. Tämä väitöskirja ehdottaa näiden haasteiden valossa uusia teknis-taloudellisia malleja ja verkottumisparadigmoja, joita tarvitaan verkkoarkkitehtuurien ja -protokollien uudelleensuunnittelussa tulevaisuuden sovelluksien tarpeet huomioiden, joiden kautta operaattorit ja käyttäjät voivat hyödyntää tulevien 5G-sovelluksien tuomat mahdollisuudet. Tässä väitöskirjassa esitetään ja analysoidaan uusia paradigmoja langattomaan verkkoliityntään. Ensimmäisenä esitellään dynaaminen verkkoarkkitehtuuri (dynamic network architecture, DNA), missä tietyt langattomat terminaalit voidaan väliaikaisesti muuttaa liityntäpisteiksi milloin vain internetyhteyden ollessa käytettävissä. Tämän konseptin puitteissa ehdotetaan viitekehys sen eri osa-alueiden optimoimiseksi. Tämän lisäksi esitetään uusi spesifinen geneettisen algoritmin (GA) koodaus optimaalisen topologian dynaamiseen konfigurointiin ja sen säätämiseen tietoliikenteen määrän mukaan. Tämän jälkeen esitellään kehitetty hajautettu käyttäjäkeskeinen spektrinjako, joka perustuu DNA-verkkoihin ja joka mahdollistaa käyttämättömien resurssien kokonaisvaltaisen jakamisen käyttäjien kautta. Seuraavaksi työssä ehdotetaan joustavaa pilvipalvelu-pohjaista liityntäverkkoa (flexible cloud-based radio access network, FRAN) käyttäjädatan purkamiseksi DNA-verkoille matalalatenssisen tietoliikenteen tarjoamiseksi. Edellä mainittujen menetelmien seurauksena ehdotetaan uutta paradigmaa: Kontekstiriippuvaista resurssien allokointia perustuen adaptiiviseen spatiaaliseen keilanmuodostukseen ja vahvistusoppimiseen. Näiden lisäksi kehitetään uusi spektrinjakomalli puolikognitiivisille radioverkoille (semi-cognitive radio network, SCRN) ensisijaisien ja toissijaisien käyttäjien utiliteetin parantamiseksi.

Modern technological innovations are constantly seen throughout every aspect of life, and higher education is no exception. To this end, this article sheds some light on the types of and pedagogical value of new media adopted by academics to promote self-directed learning at the University of South Africa. The study answers the following questions: Which new media approaches have been adopted by academics to enhance self-directed learning? What is the pedagogical value of new media in an ODL environment? A qualitative approach was employed and data was collected through face-to-face interviews with 30 purposively selected Unisa academics. The Unified Theory of Acceptance and Use of Technology model was found relevant to this study. Thematic categorisation was employed for data analysis. The findings depict that a variety of new media have been adopted to promote self-directed learning at Unisa. The study also found that new media are playing a pivotal role in promoting self-directed learning in an ODL landscape. It is therefore important to note that new media have emerged as strong catalysts in fostering pedagogical transformation. / College of Education / M. Ed (Open and Distance Learning)

The impact of affect on learning and performance has caused many researchers in the field of cognitive psychology to acknowledge the value of motivationally supportive instruction. Goal orientation, which refers to the perceptions and behaviors of the learner in achievement situations, has been the most predominant theory in learning motivation. However, research suggests multiple components are responsible for affecting student cognitive engagement. The traditional framework distinguishes individuals who are self-motivated to master challenging tasks from those who are motivated to earn favorable judgments of performance as intrinsic and extrinsic learners, respectively. In addition, learners may be further categorized by an eagerness to ensure a positive outcome or by their vigilance in avoiding negative outcomes. As such, my research explores how these motivational categories can be utilized to construct a more robust instructional model. The objective of this research is to evaluate the effectiveness of adaptive remediation strategies on motivation and learning performance. Research suggests the cost of integrating cognitive tasks with error analysis outweigh the benefits of sparse learning gains. However, further investigation is required to understand how feedback can improve these outcomes. The experiment presented here seeks to evaluate the adaptive instruction of two pedagogical agents embedded within two separate versions of the Virtual BNI Trainer. The basic coach uses a model of the learner's experience level to determine an appropriate level of elaboration required during remediation. In contrast, the motivationally enhanced coach uses a model of the learner's goal orientation to construct feedback that appeals to their natural disposition. A controlled experiment was conducted to evaluate the effects of adaptive instruction on student self-efficacy, engagement, and learning performance in the Virtual BNI Training Environment. The results of this experiment are used to establish guidelines for integrating goal orientation, error analysis, and feedback within a virtual coach, to improve motivation and learning performance. In addition, these findings also indicate areas for future research.