Yes / As big data (BD) and data analytics gain significance in Europe, the industry expects that executives will eventually move towards evidence based decision making, and consequently would build sustainable competitive advantages for their organisations. Therefore, the lessons learned from experiences of European executives can be key for human development and also economic development. However, it also seems that in some cases decision makers in Europe seem to not use business intelligence systems at all. Since, executives are intelligent human beings with credible and proven expertise, it seems to raise a question mark on effectiveness of business intelligence systems, and the potential it has in human and economic development. Furthermore, repeated evaluation of literature pointed out that ultimately executives in Europe make decisions by intuition, and this leads to the question whether big data would ever replace intuition. In this paper, the mind-sets of executives about application and limitations of big data have been explored, by taking into account the cognitive factors in decision making. By using this, it is evaluated whether BD technologies can use to accelerate intuition development of the executives, and consequently lead to faster and sustainable economic development in the developing world.

Yes / The increasing prevalence and associated cost of treating chronic obstructive pulmonary disease (COPD) is unsustainable. Health care organizations are focusing on ways to support self-management and prevent hospital admissions, including telehealth-monitoring services capturing physiological and health status data. This paper reports on data captured during a pilot randomized controlled trial of telehealth-supported care within a community-based service for patients discharged from hospital following an exacerbation of their COPD. The aim was to undertake the first analysis of system data to determine whether telehealth monitoring can identify an exacerbation of COPD, providing clinicians with an opportunity to intervene with timely treatment and prevent hospital readmission. Methods: A total of 23 participants received a telehealth-supported intervention. This paper reports on the analysis of data from a telehealth monitoring system that captured data from two sources: (1) data uploaded both manually and using Bluetooth peripheral devices by the 23 participants and (2) clinical records entered as nursing notes by the clinicians. Rules embedded in the telehealth monitoring system triggered system alerts to be reviewed by remote clinicians who determined whether clinical intervention was required. We also analyzed data on the frequency and length (bed days) of hospital admissions, frequency of hospital Accident and Emergency visits that did not lead to hospital admission, and frequency and type of community health care service contacts—other than the COPD discharge service—for all participants for the duration of the intervention and 6 months postintervention. Results: Patients generated 512 alerts, 451 of which occurred during the first 42 days that all participants used the equipment. Patients generated fewer alerts over time with typically seven alerts per day within the first 10 days and four alerts per day thereafter. They also had three times more days without alerts than with alerts. Alerts were most commonly triggered by reports of being more tired, having difficulty with self-care, and blood pressure being out of range. During the 8-week intervention, and for 6-month follow-up, eight of the 23 patients were hospitalized. Hospital readmission rates (2/23, 9%) in the first 28 days of service were lower than the 20% UK norm. Conclusions: It seems that the clinical team can identify exacerbations based on both an increase in alerts and the types of system-generated alerts as evidenced by their efforts to provided treatment interventions. There was some indication that telehealth monitoring potentially delayed hospitalizations until after patients had been discharged from the service. We suggest that telehealth-supported care can fulfill an important role in enabling patients with COPD to better manage their condition and remain out of hospital, but adequate resourcing and timely response to alerts is a critical factor in supporting patients to remain at home. / This project was funded by the National Institute for Health Collaboration for Leadership in Applied Health Research and Care Yorkshire and Humber (CLAHRC YH).

Thesis (M.S.)--University of Missouri-Columbia, 2009. / The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Thesis advisor: Yang Gong. "May 2009" Includes bibliographical references.

No description available.

Thesis (MSc (Applied Mathematics))--University of Stellenbosch, 2010. / ENGLISH ABSTRACT: In this dissertation we study the machine learning subfield of Reinforcement Learning (RL). After developing a coherent background, we apply a Monte Carlo (MC) control algorithm with exploring starts (MCES), as well as an off-policy Temporal-Difference (TD) learning control algorithm, Q-learning, to a simplified version of the Weapon Assignment (WA) problem. For the MCES control algorithm, a discount parameter of τ = 1 is used. This gives very promising results when applied to 7 × 7 grids, as well as 71 × 71 grids. The same discount parameter cannot be applied to the Q-learning algorithm, as it causes the Q-values to diverge. We take a greedy approach, setting ε = 0, and vary the learning rate (α ) and the discount parameter (τ). Experimentation shows that the best results are found with set to 0.1 and constrained in the region 0.4 ≤ τ ≤ 0.7. The MC control algorithm with exploring starts gives promising results when applied to the WA problem. It performs significantly better than the off-policy TD algorithm, Q-learning, even though it is almost twice as slow. The modern battlefield is a fast paced, information rich environment, where discovery of intent, situation awareness and the rapid evolution of concepts of operation and doctrine are critical success factors. Combining the techniques investigated and tested in this work with other techniques in Artificial Intelligence (AI) and modern computational techniques may hold the key to solving some of the problems we now face in warfare. / AFRIKAANSE OPSOMMING: Die fokus van hierdie verhandeling is die masjienleer-algoritmes in die veld van versterkingsleer. ’n Koherente agtergrond van die veld word gevolg deur die toepassing van ’n Monte Carlo (MC) beheer-algoritme met ondersoekende begintoestande, sowel as ’n afbeleid Temporale-Verskil beheer-algoritme, Q-leer, op ’n vereenvoudigde weergawe van die wapentoekenningsprobleem. Vir die MC beheer-algoritme word ’n afslagparameter van τ = 1 gebruik. Dit lewer belowende resultate wanneer toegepas op 7 × 7 roosters, asook op 71 × 71 roosters. Dieselfde afslagparameter kan nie op die Q-leer algoritme toegepas word nie, aangesien dit veroorsaak dat die Q-waardes divergeer. Ons neem ’n gulsige aanslag deur die gulsigheidsparameter te verstel na ε = 0. Ons varieer dan die leertempo ( α) en die afslagparameter (τ). Die beste eksperimentele resultate is behaal wanneer = 0.1 en as die afslagparameter vasgehou word in die gebied 0.4 ≤ τ ≤ 0.7. Die MC beheer-algoritme lewer belowende resultate wanneer toegepas op die wapentoekenningsprobleem. Dit lewer beduidend beter resultate as die Q-leer algoritme, al neem dit omtrent twee keer so lank om uit te voer. Die moderne slagveld is ’n omgewing ryk aan inligting, waar dit kritiek belangrik is om vinnig die vyand se planne te verstaan, om bedag te wees op die omgewing en die konteks van gebeure, en waar die snelle ontwikkeling van die konsepte van operasie en doktrine lei tot sukses. Die tegniekes wat in die verhandeling ondersoek en getoets is, en ander kunsmatige intelligensie tegnieke en moderne berekeningstegnieke saamgesnoer, mag dalk die sleutel hou tot die oplossing van die probleme wat ons tans in die gesig staar in oorlogvoering.

Thesis (MSc)--University of Stellenbosch, 2006. / Please refer to full text for abstract

D. Tech. Business Information Systems / Information supports the smooth operations and vital decision making of the normal operation of business processes within an enterprise. Developing countries’ Small and Medium Enterprises (SMEs) are faced with challenges of accessing intelligent information for decision making at different operational sites. Developing countries' SMEs could have benefited from the use of Mobile Business Intelligence (MBI) system. However, there is a lack of a framework that is contextualized to inform the deployment of Mobile Business Intelligence in developing countries' SMEs. This thesis therefore is envisioned to design a framework for the deployment of Mobile Business Intelligence in developing countries' SMEs. This study identified the factors that are needed in the development of a deployment framework for MBI within SMEs in developing countries.

Given its relative infancy, there is a dearth of research on a comprehensive view of business social media analytics (SMA). This dissertation first examines current literature related to SMA and develops an integrated, unifying definition of business SMA, providing a nuanced starting point for future business SMA research. This dissertation identifies several benefits of business SMA, and elaborates on some of them, while presenting recent empirical evidence in support of foregoing observations. The dissertation also describes several challenges facing business SMA today, along with supporting evidence from the literature, some of which also offer mitigating solutions in particular contexts. The second part of this dissertation studies one SMA implication focusing on identifying social influencer. Growing social media usage, accompanied by explosive growth in SMA, has resulted in increasing interest in finding automated ways of discovering influencers in online social interactions. Beginning 2008, many variants of multiple basic approaches have been proposed. Yet, there is no comprehensive study investigating the relative efficacy of these methods in specific settings. This dissertation investigates and reports on the relative performance of multiple methods on Twitter datasets containing between them tens of thousands to hundreds of thousands of tweets. Accordingly, the second part of the dissertation helps further an understanding of business SMA and its many aspects, grounded in recent empirical work, and is a basis for further research and development. This dissertation provides a relatively comprehensive understanding of SMA and the implementation SMA in influencer identification.

Thesis (PhD (Logistics))--University of Stellenbosch, 2010. / ENGLISH ABSTRACT: Computerised sugarcane harvest scheduling decision support is an active fi eld of research which ties in closely with the broader problem of automating and streamlining the various activities in the sugar supply chain. In this dissertation, the problem of providing decision support with respect to sugarcane harvesting decisions is defined within a number of contexts, each representing a typical kind of organisation of sugarcane farmers into a cohesive decision making unit with its speci fic requirements and limitations that exist in practice. A number of variations relevant to these contexts of an overarching tactical sugarcane harvest scheduling problem (THSP) are considered and solved in this dissertation. The THSP is the problem of providing objective, responsible decision support to persons charged with the task of determining optimal harvesting dates for a set of sugarcane fields across an entire season. Sugarcane fields typically diff er in terms of the age, variety, life-cycle stage and in many other properties of the cane grown on them. The growth of sugarcane crops may also be a ffected by environmental conditions such as accidental fires, frosts or storms which have a detrimental e ffect on crop-value. Since sugarcane is a living organism, its properties change over time, an so does the potential pro t associated with it. The practicalities of farming cause further complication of the problem (for example, seasonal changes alter the conditions under which the crop is harvested and transported). The rainy season carries with it the added cost of disallowing long-range vehicles to drive into the fields, forcing the unloading and reloading of cane at so-called loading zones. Other considerations, such as the early ploughing out of fields to allow them to fallow before being replanted, compounds the THSP into a multi-faceted difficult problem requiring efficient data management, mathematical modelling expertise and efficient computational work. In the literature the THSP has been viewed from many different standpoints and within many contexts, and a variety of operations research methodologies have been employed in solving the problem in part. There is, however, no description in the literature of a solution to the THSP that takes the negative e ffects of extreme environmental conditions on the quality of a harvesting schedule into account in a scienti fically justifi able manner; most models in the literature are based on optimising sucrose yield alone under normal conditions, rendering weak schedules in practice. The scope of the modelling and solution methodologies employed in this dissertation towards solving the THSP is restricted to integer programming formulations and approximate solution methods. The parameters associated with these models were determined empirically using historical data, as well as previous work on deterioration of sugarcane following environmental and other events. The THSP is solved in this dissertation by designing a generic architecture for a conceptual decision support system (DSS) for the THSP in the various contexts referred to above, which is capable of accommodating the e ects of extra-ordinary environmental conditions, as well as the introduction of a computer-implemented version of a real DSS for the THSP conforming to the framework of this generic architecture. The DSS building blocks include prediction models for sugarcane yield, sugarcane recoverable value under normal circumstances, the costs associated with a harvesting schedule and the negative e ects on sugarcane recoverable value of extraordinary environmental conditions. The working of the DSS is based on a combinatorial optimisation model resembling the well-known asymmetric traveling salesman problem with time-dependent costs which is solved approximately by means of an attribute-based tabu search in which both local and global moves have been incorporated. The DSS is also validated by experienced sugarcane industry experts in terms of the practicality and quality of the schedules that it produces. / AFRIKAANSE OPSOMMING: Gerekenariseerde besluitsteun vir die skedulering van suikerriet-oeste is 'n aktiewe navorsingsveld wat nou verwant is aan die bre ër probleem van die outomatisering en vaartbelyning van 'n verskeidenheid aktiwiteite in die suikervoorsieningsketting. Die probleem van die daarstelling van steun rakende suikkerriet oestingsbesluite word in hierdie proefskrif in 'n aantal kontekste oorweeg, elk met betrekking tot 'n tipiese soort organisasie van suikerrietboere in 'n samehorige besluitnemingseenheid met sy spesi eke vereistes en beperkings in die praktyk. Verskeie variasies van 'n oorkoepelende taktiese suikerriet-oesskeduleringsprobleem (TSOSP) wat in hierde kontekste relevant is, naamlik die probleem om objektiewe, verantwoordbare steun aan besluitnemers te bied wat verantwoordelik is vir die bepaling van optimale oesdatums vir 'n versameling suikerrietplantasies oor die bestek van 'n hele seisoen, word in hierdie proefskrif bestudeer en opgelos. Suikerrietplantasies verskil tipies in terme van ouderdom, gewastipe, posisie in die lewensiklus, en vele ander eienskappe van die suikerriet wat daar groei. Omgewingstoestande, soos onbeplande brande, ryp of storms, het verder ook 'n negatiewe impak op die waarde van suikerriet op sulke plantasies. Omdat suikerriet 'n lewende organisme is, verander die eienskappe daarvan oor tyd, en so ook die potensi ele wins wat daarmee geassosieer word. Boerderypraktyke bemoeilik verder die skeduleringsprobleem onder beskouing (seisoenale veranderings beïnvloed byvoorbeeld die wyse waarop suikerriet ge-oes en vervoer word). Addisionele koste gaan voorts met die re ënseisoen gepaard, omdat die plantasies dan nie toeganklik is vir langafstand transportvoertuie nie en suikerriet gevolglik na spesiale laaisones gekarwei moet word voordat dit op hierdie voertuie gelaai kan word. Ander oorwegings, soos die vroe ë uitploeg van plantasies sodat die grond kan rus voordat nuwe suikerriet aangeplant word, veroorsaak dat die TSOSP 'n moeilike multi-faset probleem is, wat goeie databestuur, wiskundige modelleringsvernuf en doeltreff ende rekenaarwerk vereis. Die TSOSP word in die literatuur vanuit verskillende standpunte en in verskeie kontekste oorweeg, en 'n aantal uiteenlopende operasionele navorsingsmetodologie ë is al ingespan om hierdie probleem ten dele op te los. Daar is egter geen poging in die literatuur om 'n oplossing vir die TSOSP daar te stel waarin daar op 'n wetenskaplik-verantwoordbare wyse voorsiening gemaak word vir die negatiewe e ffekte wat uitsonderlike omgewingstoestande op die kwaliteit van oesskedules het nie; die meeste modelle in die literatuure is op slegs sukrose-opbrengs onder normale omstandighede gebaseer, wat lei na swak skedules in die praktyk. Die bestek van die wiskundige modellerings- en gepaardgaande oplossings-metodologie ë word in hierdie proefskrif vir die TSOSP beperk tot onderskeidelik heeltallige programmeringsformulerings en die bepaling van benaderde oplossings deur lokale soekprosedures. Die parameters wat met hierdie modelle en soekmetodes geassosieer word, word empiries bepaal deur gebruikmaking van historiese data asook bestaande werk oor die degradering van suikerriet as gevolg van omgewings- en ander eksterne faktore. Die TSOSP word in hierdie proefskrif opgelos deur die ontwerp van 'n generiese argitektuur vir 'n konseptuele besluitsteunstelsel (BSS) vir die TSOSP in die onderskeie kontekste waarna hierbo verwys word en wat die e ekte van uitsonderlike omgewingsfaktore in ag neem, asook die daarstelling van 'n rekenaar-ge ïmplementeerde weergawe van 'n daadwerklike BSS vir die TSOSP wat in die raamwerk van hierdie generiese argitektuur pas. Die boustene van hierdie BSS sluit modelle in vir die voorspelling van suikerrietopbrengs, die herwinbare waarde van suikerriet onder normale omstandighede, die verwagte koste geassosieer met 'n oesskedule en die negatiewe e ekte van omgewingsfaktore op die herwinbare waarde van suikerriet. Die werking van die BSS is gebaseer op 'n kombinatoriese optimeringsprobleem wat aan die welbekende asimmetriese handelreisigersprobleem met tyd-afhanklike kostes herinner, en hierdie model word benaderd opgelos deur middel van 'n eienskap-gebaseerde tabu-soektog waarin beide lokale en globale skuiwe ge ïnkorporeer is. Die BSS word ook gevalideer in terme van die haalbaarheid en kwaliteit van die skedules wat dit oplewer, soos geassesseer deur ervare kundiges in die suikerrietbedryf.

published_or_final_version / abstract / Geography / Master / Master of Geographic Information System