Thesis (MEng)--Stellenbosch University, 2015. / ENGLISH ABSTRACT: Road accidents are a growing concern for governments and is rising to become one of the leading causes of death in developing countries. Aggressive driving is one of the major causes of road accidents, and it is therefore important to investigate ways to improve people's driving habits. The ubiquitous presence of smartphones provides a new platform on which to implement sensor networks in vehicles, and therefore this thesis focuses on the use of smartphones to monitor a person's driving behaviour. The framework for a smartphone-based system that can detect and classify various driving manoeuvres is researched. As a proof of concept, a system is developed that specifically detects lateral driving manoeuvres and that classifies them as aggressive or not, using a supervised learning classification algorithm. Existing solutions found in research literature are investigated and presented. The best existing solution, a dynamic time warping classification approach, is also implemented and tested. We use an aggressive driving model that is based on the angle of a turn, the lateral force exerted on the vehicle and its speed through the turn. The tests and results of the implemented manoeuvre detection and classifcation algorithms are presented, and thoroughly discussed. The performance of each classifer is tested using the same data set, and a quantitative comparison are made between them. Ultimately, a lateral driving manoeuvre detection and recognition system was successfully developed, and its potential to be implemented on a smartphone was substantiated. The suitability of supervised learning classi ers for classifying aggressive driving, in comparison to dynamic time warping classifcation, was successfully demonstrated and used to validate our aggressive driving model. Conceivably, this work can be employed in the future to develop an holistic smartphone-based driver behaviour monitoring system, which can be easily deployed on a large scale to help make the public drive better. This would make our roads safer, reducing the occurrence of road accidents and fatalities. / AFRIKAANSE OPSOMMING: Padongelukkige is 'n groeiende bekommernis vir regerings en is een van die hoof oorsake van sterftes in ontwikkelende lande. Aggressiewe bestuur is een van die grootste oorsake van padongelukke, en dit is dus belangrik om ondersoek in te stel oor hoe mense se bestuurgewoontes verbeter kan word. Die alomteenwoordigheid van slimfone bied 'n nuwe platform waarop sensor netwerke geïmplementeer kan word in voertuie. Daarom fokus hierdie tesis op die gebruik van slimfone om 'n persoon se bestuurgedrag te moniteer. Die raamwerk vir 'n slimfoon-gebaseerde stelsel wat verskeie bestuurbewegings kan opspoor en klassifiseer is nagevors. As 'n bewys van die konsep, is 'n stelsel ontwikkel wat spesifiek laterale bestuurbewegings opspoor en dan klassifiseer of dit aggressief is of nie, met behulp van 'n klassifikasie algoritme wat onder toesig geleer is. Bestaande oplossings gevind in navorsingsliteratuur word ondersoek en aangebied. Die beste bestaande oplossing, 'n dinamiese tyd buiging klassifikasie benadering, word ook geïmplementeer en getoets. Ons gebruik 'n aggressiewe bestuurmodel wat gebaseer is op die hoek van 'n draai, die laterale krag wat uitgeofen is op die voertuig en sy spoed deur die draai. Die toetse en die resultate van die geïmplementeer beweging opsporing en klassifisering algoritmes word aangebied, en deeglik bespreek. Die prestasie van elke klassifiseerder is getoets met behulp van dieselfde stel data, en 'n kwantitatiewe vergelyking is tussen beide gemaak. Oplaas is 'n laterale bestuurbeweging bemerking en herkenning stelsel suksesvol ontwikkel en sy potensiaal om geïmplementeer te word op 'n slimfoon is gestaaf. Die geskiktheid van die onder-toesig-geleerde klassifiseerders vir die klassifikasie van aggressiewe bestuur, in vergelyking met dinamiese tyd buiging klassifikasie, was suksesvol gedemonstreer en gebruik om ons aggressiewe bestuurmodel te bewys. Hierdie werk kan in die toekoms gebruik word in 'n holistiese slimfoon-gebaseerde bestuurdergedrag monitering stelsel, wat maklik op groot skaal ontplooi kan word om te help verseker dat die publiek beter bestuur. Dit sal ons paaie veiliger maak, en die voorkoms van padongelukke en sterftes verminder.

The objective of the report is to investigate which kind of mobile appli-cation, native, hybrid or web, that is the best regarding cross-platform support compared to development cost. As there are little information regarding pure web applications for mobile devices a prototype will be constructed to give light in this technology. The prototype should an-swer the questions if it can save a year's usage in the cell phones memory, if it is possible to have support for 100 percent of Sweden area and generally if this approach would suffice. There are also some physi-cal restrictions on the web application. A login must be done in less than 5 second, fetch TOs( timber orders) within 10 seconds, report a row within 5 seconds. This in a 2G environment, in Telias network, which is mostly likely to be used in the forest. To easily test the application the CPN-tools(colored petri nets) are used to graphically model the applica-tion and simulations are thereafter done to get a scenes how the applica-tion would perform during many years of usage. To construct have been constructed with the aid of open web technologies as HTML5,CSS4, JavaScript, JQuery and JQuery mobile. The prototype used asynchronies communication to mask loss of coverage and long loading times. It also utilized HTML5 localStorage to save TOs and employer information so that minimize the need for fetching information many times. The proto-type application cannot be used in 100 percent of Sweden's area because the cellular coverage is not present in big areas in the north of Sweden. Therefore information is stored locally but after the pre fetched work orders are completed new work orders must be fetched where cellular coverage is present. The application still have a big usage area and as most wood products comes from the middle of Sweden this cannot be seen as a big problem. To save a year's usage of data on the other hand is not a problem at all. About 10 percent of the available 5 MB of storage in the HTML5 localStorage would be needed. It did also with ease handle the time limitations. As a conclusion the need for a web applica-tion, for SDC, is only present if both IVR and web reporting through a computer is if these services are liquidated in the long run. There are a bit more work with creating a hybrid native/web application using third-party applications but it in turns would give a better coverage area as that kind of application can pre download all TOs and employers ignoring any limitations in storage. This is not possible to do as a pure web application can't be run in the background on the phone.

Work in demanding postures is a known risk factor for work-related musculoskeletal disorders (MSDs), specifically work with elevated arms may cause neck/shoulder disorders. Such a disorder is a tragedy for the individual, and costly for society. Technical measurements are more precise in estimating the work exposure, than observation and self-reports, and there is a need for uncomplicated methods for risk assessments. The aim of this project was to develop and validate an iOS application for measuring arm elevation angle. Such an application was developed, based on the built-in accelerometer and gyroscope of the iPhone/iPod Touch. The application was designed to be self-exploratory. Directly after a measurement, 10th, 50th and 90th percentiles of angular distribution and median angular velocity, and percentage of time above 30°, 60°, and 90° are presented. The focused user group, ergonomists, was consulted during the user interface design phase. Complete angular datasets may be exported via email as text files for further analyses. The application was validated by comparison to the output of an optical motion capture system for four subjects. The two methods correlated above 0.99, with absolute error below 4.8° in arm flexion and abduction positions. During arm swing movements, the average root-mean-square differences (RMSDs) were 3.7°, 4.6° and 6.5° for slow (0.1 Hz), medium (0.4 Hz) and fast (0.8 Hz) arm swings, respectively. For simulated painting, the mean RMSDs was 5.5°. Since the accuracy was similar to other tested field research methods, this convenient and “low-cost” application should be useful for ergonomists, for risk assessments or educational use. The plan is to publish this iOS application on Apple Store (Apple Inc.) for free. New user feedback may further improve the user interface.

The most common navigation aid visually-impaired people employ is a white cane, but, recently, technology has given rise to a varied set of sophisticated navigation aids. While these new aids can provide more assistance to a visually-impaired person than a white cane, they tend to be expensive due to a small market segment, which in turn can reduce their accessibility. In an effort to produce a technologically-advanced yet accessible navigation aid, an Android application is proposed that detects and notifies users about obstacles within their path through the use of a smartphone's camera. While the smartphone is mounted on a harness worn by the user, the Walking Assistant application operates by capturing images as the user walks, finding features of objects within each frame, and determining how the features have moved from image to image. If it is discovered that an object is moving towards the user, the Walking Assistant will activate the smartphone's vibration mode to alert the user to the object's presence. Additionally, the user can control the Walking Assistant through the use of either touch or voice commands. By conducting real-world tests, it was determined that the Walking Assistant can correctly identify obstacles 42.1% of the time, while generating false positive obstacle identifications only 15.0% of the time. The accuracy of the Walking Assistant can be further improved by implementing additional features, such as a fuzzy-decision-based thresholding system or image stabilization.

Poverty and long distances are two reasons why some people in the third world countries hasdifficulties seeking medical help. A solution to the long distances could be if the medical carewas more mobile and diagnostically tests could be performed on site in villages. A new pointof-care test based on a small blood shows promising results both in run time and mobility.However, the method still needs more advanced equipment for analysis of the resultingmicroarray. This study has investigated the potential to perform the analysis within asmartphone application, performing all steps from image capturing to a diagnostic result. Theproject was approach in two steps, starting with implementation and selection of imageanalysis methods and finishing with implementing those results into an Android application.A final application was not developed, but the results gained from this project indicates that asmartphone processing power is enough to perform heavy image analysis within a sufficientamount of time. It also imply that the resolution in the evaluated images taken with a Nexus 6together with an external macro lens most likely is enough for the whole analysis, but furtherwork must be done to ensure it.

Since 1999 when the report To Err is Human: Building a Safer Health System was released, medical errors have come into focus (Kohn, 2000). In an effort to reduce medication administration errors in prehospital emergency care, an android-based smartphone application simulation was created. The app has components including QR barcode scanning, text to speech for medication cross-checking, weight-based medication dose calculations, and time stamped medication data wirelessly transferring to a database in real-time. Color standard identification was implemented, aiding to a designed systematic process for patient treatment to reduce medication errors. Direct observation was performed of emergency patient calls with Richmond Ambulance Authority’s providers for a preliminary assessment. Device testing was assessed with emergency medical interns and functionally tested in different light environments. Results showed how similar different pharmaceutical vendors created medication labeling and that 58.3% of medical experts would say this device served to reduce medication administration errors.

Sensory deficits represent a major global public health problem. According to the World Health Organization, vision impairment affects an estimated 300 million people worldwide, and hearing impairment affects an estimated 360 million people worldwide. Consistent clinical evaluations for all individuals with sensory deficits cannot be practically realized due to the rising costs of healthcare, capital and labor limitations, and inaccessibility to healthcare due to a multitude of factors including proximity. The high prevalence of visual and hearing deficits can be lessened through consistent, comprehensive, at-home testing which can allow a larger amount of the affected and at-risk populations to be screened for abnormal function earlier and prior to permanent loss, and provide a wealth of patient-specific data that can be used to understand the time-scale of diseases and monitor the effectiveness of clinical interventions in unprecedented detail. While health-oriented smartphone applications exhibit a strong presence on the app stores, these applications are seldom vetted by expert scientists, engineers, and clinicians, and there are considerable opportunities for methodological improvements. The present work discusses the creation, calibration, and proof-of-concept, preliminary validation of a suite of psychophysical tests implemented as smartphone applications that can be utilized to rapidly and objectively quantify several functional sensory behaviors including flicker sensitivity, contrast sensitivity, visual acuity, and hearing-in-noise. Rigorous steps were undertaken to perform the necessary calibrations (a feat not routinely achieved by the creators of existing medical smartphone applications), and ensure the technical validity of the varying stimuli presented. Preliminary tests in the clinic have documented the potential of these tests to objectively provide numerous quantifications of, but not limited to, individual visual and hearing function, and variation between normal and abnormal subjects and function. The foundation laid by this work allows novel psychophysical tests to rapidly be implemented, vetted, and added to this battery of publicly and universally accessible medical smartphone applications.

There are several methods to measure surface evenness for car roads, but almost none for bike paths. Accordingly, VTI (the Swedish National Road and Transport Research Institute) have created a smartphone application which uses the accelerometers in the phone to measure the vibration from the road. This report’s aim is to analyze the data collected using this application, investigate if the data is repeatable, to find factors that are important for evenness and perform classification of bike paths as even or wiggly. Two main methods were used, Gaussian process and wavelets. Gaussian process was used to classify bike paths and wavelets to investigate the repeatability and see how many trips are needed to get a consistent result. The results show that the two different smartphones gave quite different results; one smartphone indicated almost twice as high RMS values (measure of vibration) than the other. The GPS positions of smartphones were quite good, except under a tunnel and close to high buildings. Some short section of the road gave very high or very low RMS values, but the general standard of all investigated bike paths were too even to detect any significant differences between the paths. The results show that there’s some unexplained variance in the turns, but the effect of the turns hasn’t been tested. The wavelets analysis show that around 15 trips were needed to get a consistent result. The report contains a description of a designed experiment that will continue this project. This new data will be collected in a more carefully to make a better separation between good and bad cycle routes by the RMS value. / <p>Uppdragsgivare: VTI (Anna Niska och Leif Sjögren)</p>

Background: Smartphones and related applications are increa singly gaining relevance in the healthcare domain. We previously assessed the demands and preferences of medical students towards an application accompanying them during a course on general practice. The current study aims to elucidate the factors associated with adop tion of such a technology. Therefore we provided students with a prototype of an application specifically related to their studies in general practice.

Abstract The purpose of this Bachelor thesis has been to find a way to increase physical activity through the digitization of hiking trails. With information on interesting places around the hiking trail, we hope that this will enable people to get out on the hiking trails. Both to exercise but also to learn a little more about places in their vicinity. Through walking interviews, we have gathered data about the user's thoughts and ideas about the hiking trails. As well as studying UX design and HCI to see patterns of the user that can be applied in the product, to make our design more appealing and more user friendly. In our process, we have used Wireframe to get a common and visual image to work for. After that, we have worked with Extreme programming to work together and create the code for the design. Our result has grown into a demo application that is open to more features and other fields of use if desired. At the end of this work, new thoughts and ideas have also been brought to life, how the demo app could be used in other areas, such as in the archipelago and for educational purposes for children. Keywords Smartphone application, walking trails, points of interests, movement, hiking. / Abstrakt Detta kandidatarbetets syfte har varit att finna ett sätt att öka den fysiska aktiviteten genom digitalisering av vandringsleder. Med hjälp av information om intressanta platser runt om vandringsleden, hoppas vi att detta förmår folk att ta sig ut på vandringslederna. Både för att motionera men också för att lära sig lite mer om platser i sin närmiljö. Vi har genom promenadintervjuer samlat data om användarens tankar och ideér gällande vandringslederna. Samt studerat UX design och HCI för att kunna se mönster hos användaren som går att applicera i produkten, för att göra vår design mer tilltalande och mera användarvänlig. I vår process har vi använt oss av Wireframe för att få en gemensam och visuell bild att jobba efter. Därefter har vi jobbat med Extreme programming för att tillsammans arbeta fram koden till gestaltningen. Vårt resultat har vuxit fram till en demo-applikation som är öppen för fler funktioner och användningsområden om så önskas. I slutet av detta arbetet har även nya tankar och ideér väckts till liv, om hur demo-appen skulle kunna användas inom andra områden såsom i skärgården och i lärosyfte för barn. Nyckelord Mobilapplikation, Vandringsleder, Intressepunkter, Rörelse, Vandring.