Thesis (Ph. D.)--University of Chicago, Graduate School of Business. / Includes bibliographical references. Also available on the Internet.

Thesis (M.S. in National Security Affairs)--Naval Postgraduate School, December 2003. / Thesis Advisor(s): H. Lyman Miller, Glenn R. Cook. "December 2003." Includes bibliographical references (p. 63-67). Also available in print.

Magister Scientiae - MSc / Huge amounts of data are being collected as a result of the increased use of mobile telecommunications. Insight into information and knowledge derived from these databases can give operators a competitive edge in terms of customer care and retention, marketing and fraud detection. One of the strategies for fraud detection checks for signs of questionable changes in user behavior. Although the intentions of the mobile phone users cannot be observed, their intentions are reflected in the call data which define usage patterns. Over a period of time, an individual phone generates a large pattern of use. While call data are recorded for subscribers for billing purposes, we are making no prior assumptions about the data indicative of fraudulent call patterns, i.e. the calls made for billing purpose are unlabeled. Further analysis is thus, required to be able to isolate fraudulent usage. An unsupervised learning algorithm can analyse and cluster call patterns for each subscriber in order to facilitate the fraud detection process. This research investigates the unsupervised learning potentials of two neural networks for the profiling of calls made by users over a period of time in a mobile telecommunication network. Our study provides a comparative analysis and application of Self-Organizing Maps (SOM) and Long Short-Term Memory (LSTM) recurrent neural networks algorithms to user call data records in order to conduct a descriptive data mining on users call patterns. Our investigation shows the learning ability of both techniques to discriminate user call patterns; the LSTM recurrent neural network algorithm providing a better discrimination than the SOM algorithm in terms of long time series modelling. LSTM discriminates different types of temporal sequences and groups them according to a variety of features. The ordered features can later be interpreted and labeled according to specific requirements of the mobile service provider. Thus, suspicious call behaviours are isolated within the mobile telecommunication network and can be used to to identify fraudulent call patterns. We give results using masked call data from a real mobile telecommunication network. / South Africa

Thirty-six drivers of both genders from three different age groups performed auditory cognitive tasks while driving an instrumented vehicle. The tasks were of two types. The first type of task was the selection of a driving route from a list presented as a recorded sound. These tasks represented the use of In-Vehicle Information Systems (IVIS). The second type of task consisted of a conversation like series of questions designed to replicate the use of a cellular telephone while driving. The IVIS tasks consisted of two levels of information density (short-term memory load) and four element types (complexity levels) including listening, interpretation, planning, and computation. The effects of age, information density, and element type on driving performance were assessed using a composite set of performance measures. Primary measures of driving performance included lateral tracking, longitudinal control and eye glances. Secondary task performance was assessed by task completion time, skipped tasks and task errors. Additionally, subjective assessment was done using a situational awareness probe question and a modified NASA-TLX question set. Results showed that drivers demonstrated a general decrease in their ability to maintain their lateral position with increased task complexity. Additionally, speed and following distance were less stable during tasks. During tasks, drivers glanced less at their mirrors and instruments and left their lane more often than during baseline driving periods. Even during difficult tasks, drivers had high self-confidence in their awareness of surroundings. One result of particular interest was an increase in lane deviations and headway variance coupled with increased forward eye glance durations. It is believed that this is evidence of a condition called "Cognitive Capture" in which a driver, though looking more extensively at the forward roadway, is having difficulty tracking the lead vehicle and lane position. High cognitive load is causing the driver to disregard or shed visual information to allow processing of auditory task-related information. Another result of concern is the inability of drivers to assess their own impairment while performing in vehicle tasks. During tasks drivers demonstrated reduced scanning of mirrors and vehicle instrumentation. This clearly demonstrates reduced situational awareness. Additionally, during tasks lane tracking and headway maintenance performance decreased as well. However, during all tasks drivers assessed their workload higher than baseline driving even though they rated it near the bottom of the scale. Also, drivers perceived no decrease in their situational awareness. The results of this study show that driving performance can be negatively impacted by even fairly simple cognitive tasks while a driver is looking at the road with their hands on the wheel. Even while viewing the road, a driver may perform an auditory task and be cognitively overloaded to the point of safety concerns. An additional concern is that drivers underestimate the degree of their cognitive load and its impact on their driving performance. / Master of Science

Thesis (M.B.A.)--University of Hong Kong, 1998. / Includes bibliographical references (leaf 86-88).

Thesis (M.S.)--Virginia Polytechnic Institute and State University, 1993. / Vita. Abstract. Includes bibliographical references (leaves 138-145). Also available via the Internet.

Thesis (MSc)--University of Stellenbosch, 2005. / ENGLISH ABSTRACT: Cellular network operators globally loose between 3% and 5% of their annual revenue to telecommunications fraud. Hence it is of great importance that fraud management systems are implemented to detect, alarm, and shut down fraud within minutes, minimising revenue loss. Modern proprietary fraud management systems employ (i) classification methods, most often artificial neural networks learning from classified call data records to classify new call data records as fraudulent or legitimate, (ii) statistical methods building subscriber behaviour profiles based on the subscriber’s usage in the cellular network and detecting sudden changes in behaviour, and (iii) rules and threshold values defined by fraud analysts, utilising their knowledge of valid fraud cases and the false alarm rate as guidance. The purpose of this thesis is to establish a context for and evaluate the performance of well-known data mining techniques that may be incorporated in the fraud detection process. Firstly, a theoretical background of various well-known data mining techniques is provided and a number of seminal articles on fraud detection, which influenced this thesis, are summarised. The cellular telecommunications industry is introduced, including a brief discussion of the types of fraud experienced by South African cellular network operators. Secondly, the data collection process and the characteristics of the collected data are discussed. Different data mining techniques are applied to the collected data, demonstrating how user behaviour profiles may be built and how fraud may be predicted. An appraisal of the performances and appropriateness of the different data mining techniques is given in the context of the fraud detection process. Finally, an indication of further work is provided in the conclusion to this thesis, in the form of a number of recommendations for possible adaptations of the fraud detection methods, and improvements thereof. A combination of data mining techniques that may be used to build a comprehensive fraud detection model is also suggested. / AFRIKAANSE OPSOMMING: Sellulêre netwerk operateurs verloor wêreldwyd tussen 3% en 5% van hul jaarlikse inkomste as gevolg van telekommunikasie bedrog. Dit is dus van die uiterse belang dat bedrog bestuurstelsels geïmplimenteer word om bedrog op te spoor, alarms te genereer, en bedrog binne minute te staak om verlies aan inkomste tot ’n minimum te beperk. Moderne gepatenteerde bedrog bestuurstelsels maak gebruik van (i) klassifikasie metodes, mees dikwels kunsmatige neurale netwerke wat leer vanaf geklassifiseerde oproep rekords en gebruik word om nuwe oproep rekords as bedrog-draend of nie bedrog-draend te klassifiseer, (ii) statistiese metodes wat gedragsprofiele van ’n intekenaar bou, gebaseer op die intekenaar se gedrag in die sellulêre netwerk, en skielike verandering in gedrag opspoor, en (iii) reëls en drempelwaardes wat deur bedrog analiste daar gestel word, deur gebruik te maak van hulle ondervinding met geldige gevalle van bedrog en die koers waarteen vals alarms gegenereer word. Die doel van hierdie tesis is om ’n konteks te bepaal vir en die werksverrigting te evalueer van bekende data ontginningstegnieke wat in bedrog opsporingstelsels gebruik kan word. Eerstens word ’n teoretiese agtergrond vir ’n aantal bekende data ontginningstegnieke voorsien en ’n aantal gedagteryke artikels wat oor bedrog opsporing handel en wat hierdie tesis beïnvloed het, opgesom. Die sellulêre telekommunikasie industrie word bekend gestel, insluitend ’n kort bespreking oor die tipes bedrog wat deur Suid-Afrikaanse sellulˆere telekommunikasie netwerk operateurs ondervind word. Tweedens word die data versamelingsproses en die eienskappe van die versamelde data bespreek. Verskillende data ontginningstegnieke word vervolgens toegepas op die versamelde data om te demonstreer hoe gedragsprofiele van gebruikers gebou kan word en hoe bedrog voorspel kan word. Die werksverrigting en gepastheid van die verskillende data ontginningstegnieke word bespreek in die konteks van die bedrog opsporingsproses. Laastens word ’n aanduiding van verdere werk in die gevolgtrekking tot hierdie tesis verskaf, en wel in die vorm van ’n aantal aanbevelings oor moontlike aanpassings en verbeterings van die bedrog opsporingsmetodes wat beskou en toegepas is. ’n Omvattende bedrog opsporingsmodel wat gebruik maak van ’n kombinasie van data ontginningstegnieke word ook voorgestel.

<p>This thesis investigates the use of mobile phones as service-delivery devices in a sign language machine translation system. Four sign language visualization methods were evaluated on mobile phones. Three of the methods were synthetic sign language visualization methods. Three factors were considered: the intelligibility of sign language, as rendered by the method / the power consumption / and the bandwidth usage associated with each method. The average intelligibility rate was 65%, with some methods achieving intelligibility rates of up to 92%. The average le size was 162 KB and, on average, the power consumption increased to 180% of the idle state, across all methods. This research forms part of the Integration of Signed and Verbal Communication: South African Sign Language Recognition and Animation (SASL) project at the University of the Western Cape and serves as an integration platform for the group's research. In order to perform this research a machine translation system that uses mobile phones as service-delivery devices was developed as well as a 3D Avatar for mobile phones. It was concluded that mobile phones are suitable service-delivery platforms for sign language machine translation systems.</p>

<p>This thesis investigates the use of mobile phones as service-delivery devices in a sign language machine translation system. Four sign language visualization methods were evaluated on mobile phones. Three of the methods were synthetic sign language visualization methods. Three factors were considered: the intelligibility of sign language, as rendered by the method / the power consumption / and the bandwidth usage associated with each method. The average intelligibility rate was 65%, with some methods achieving intelligibility rates of up to 92%. The average le size was 162 KB and, on average, the power consumption increased to 180% of the idle state, across all methods. This research forms part of the Integration of Signed and Verbal Communication: South African Sign Language Recognition and Animation (SASL) project at the University of the Western Cape and serves as an integration platform for the group's research. In order to perform this research a machine translation system that uses mobile phones as service-delivery devices was developed as well as a 3D Avatar for mobile phones. It was concluded that mobile phones are suitable service-delivery platforms for sign language machine translation systems.</p>

Thesis (M.B.A.)--University of Hong Kong, 1998. / Includes bibliographical references (leaf 148-152).