izpis_h1_title_alt

AVTOMATSKO DOLOČANJE KONTEKSTA MOBILNEGA UPORABNIKA
VIDMAR, LUKA (Author), Pogačnik, Matevž (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (3,63 MB)

Abstract
Komercialno dostopni pametni telefoni vsebujejo čedalje več komunikacijskih tehnologij, kot so Wi-Fi, IR (angl. infrared), bluetooth, radiofrekvenčna identifikacija (angl. radio-frequency identification - RFID) in sistem globalnega pozicioniranja (angl. global positioning system - GPS), ter senzorskih modulov, kot so pospeškometer, kompas, mikrofon in fotografski aparat. Hkrati mobilni telefoni postajajo ključni potrošniki in ustvarjalci večpredstavnostnih vsebin. V veliki množici informacij, aplikacij in storitev je zato potrebno izluščiti tiste, ki so za uporabnika resnično relevantne. Za ugotavljanje njihove primernosti se poleg personalizacije vedno pogosteje uporablja tudi zavedanje uporabniškega konteksta (angl. context-awareness). To omogoča, da se vsebine in obnašanje sistema prilagodijo okoliščinam uporabnika in mobilnega telefona, tj. kontekstu. Uporabniški kontekst se lahko določi ročno, kar ni prijazno do uporabnika, ali samodejno z analizo podatkov različnih senzorjev na mobilnem telefonu. Poleg izbire ustreznih senzorjev in obdelave njihovih podatkov je za samodejno določitev konteksta pomembna tudi izbira kontekstnega modela, kar med drugim vključuje določitev namena modela ter opredelitev nabora vrednosti in načina sklepanja. V disertaciji smo si zamislili kontekstni model uporabniških aktivnosti. Te so opredeljene z več kontekstnimi parametri skupaj. Med njimi so poglavitni: lokacija, čas, uporabniški profil in fizična aktivnost. Vsi so bili uporabljeni tudi pri našem delu. Za parameter lokacija smo najprej (A) predlagali in ovrednotili hibridno metodo za pozicioniranje ter razvili metodo, ki omogoča ocenjevanje različnih metod za pozicioniranje v semantičnem prostoru, tj. prostoru s semantičnimi lokacijami, kot na primer poštnimi naslovi in točkami zanimanja (angl. point of interest - POI). (B) Nadalje smo v kontekstnem modelu definirali nabor vrednosti, tj. uporabniške vsakodnevne aktivnosti, kot na primer doma, delo, nakupovanje in tek. (C) Nazadnje smo za samodejno določanje teh vrednosti nadgradili metodo za analizo uporabniških poti, določenih z uporabljenimi senzorji, ter uporabili različne metode za sklepanje o uporabniškem kontekstu. Ad A: Predlagana hibridna metoda za pozicioniranje uporablja podatke GPS, servisno (angl. serving) mobilno celico in moč sprejetega signala ter številne podrobnosti o mobilnem omrežju, kot na primer frekvenco mobilnega kanala, tip mobilne bazne postaje in višino oddajnega stolpa. Glede na vir podatkov loči tri poti za oceno pozicije: (i) privzame lokacijo bazne postaje kot oceno pozicije uporabnika, ko je mobilni telefon priključen na notranjo bazno postajo; (ii) privzame pozicijo, ko je določena s podatki GPS; (iii) v vseh ostalih primerih pozicijo izračuna z najustreznejšim modelom razširjanja radijskih valov. Poleg ocene pozicije poda tudi oceno točnosti predlagane pozicije, za kar smo ovrednotili številne faktorje, ki bi lahko vplivali na netočnost meritve, kot na primer število satelitov, sprejeto moč in razne podatke o gostoti mobilnega omrežja, in iskali korelacijo z napako metode. S podatki terenskih meritev na 167 naključnih točkah smo optimizirali delovanje predlagane metode in ovrednotili faktorje za oceno točnosti posamezne meritve. Z istimi meritvami smo primerjali delovanje optimizirane metode za pozicioniranje z obstoječo metodo pri opazovanem mobilnem operaterju in z nekaterimi komercialnimi rešitvami: navigacijsko napravo GPS, Googlom in Foursquarom. Delovanje metode smo ovrednotili na dva načina: s povprečnimi vrednostmi napak in z novo metodo za primerjanje metod za pozicioniranje v semantičnem prostoru. Slednja je ocenila pravilnost pretvorbe pozicij v poštne naslove in pomembne kategorije POI-jev. Optimizirana predlagana metoda je imela povprečno napako 85,9 m in 67. kvantil 86,9 m. Analiza je pokazala smiselnost treh vrednosti za oceno točnosti: 33, 270 in 377 m. Za pozicije določene z GPS-om nismo našli faktorja, ki bi koreliral z napakami meritev, zato smo za oceno točnosti vzeli eno vrednost, tj. 33 m. Za pozicije, določene na podlagi servisne celice, ki niso bile notranje, smo med faktorji izbrali povprečno razdaljo med ocenjeno pozicijo in prvima najbližjima sosednjima celicama. Na podlagi tega faktorja smo razporedili meritve v dve kategoriji točnosti, tj. 270 in 377 m. Predlagana metoda je sicer delovala bolje od obstoječe metode pri opazovanem mobilnem operaterju, a precej slabše od navigacijske naprave, ki je imela z našimi meritvami najboljše rezultate. Pozicioniranju navigacijske naprave se je najbolj približala Googlova storitev pozicioniranja. Ko je predlagana metoda pozicijo določila na podlagi podatkov GPS ali notranje bazne postaje, je bila ocenjena pozicija točna, vendar je njena točnost zelo upadla v vseh ostalih slučajih. Razlike med opazovanimi metodami za pozicioniranje so bile pri vrednotenju pretvorjenih pozicij v semantični prostor manjše. Med vsemi opazovanimi metodami pa se je predlagana metoda najbolje izkazala pri oceni točnosti, saj je bila njena ocena največkrat pravilna. Metodo odlikuje praktična uporabnost na vseh pametnih telefonih in komplementarna uporaba dveh tehnologij, ki zagotavljata dostopnost storitve pozicioniranja skoraj povsod. Vendar je pozicioniranje samo na osnovi servisne celice premalo točno za avtomatsko določanje uporabniškega konteksta. Kot rešitev bi bilo mogoče narediti dvoslojno prepoznavo konteksta: ko bi bila ocenjena pozicija točna, bi skušali prepoznati podroben uporabniški kontekst; v nasprotnih primerih bi se zadovoljili s prepoznavo splošnega konteksta. Po izkušnjah s terenskih meritev bi se morali v večini primerov zadovoljiti s prepoznavo splošnega konteksta, zato smo opustili idejo o uporabi predlagane metode za pozicioniranje za nadaljnje delo. Ad B: Nato smo v disertaciji predlagali hierarhični kontekstni model, ki smo ga zgradili na podlagi pregleda relevantne literature. Sestavljajo ga statične in tudi dinamične aktivnosti, ki zapolnjujejo vsakdan uporabnikov. Model vsebuje štiri splošne uporabniške kontekste: doma, delo, prosti čas in tranzit. Nekateri od teh so razdeljeni v podskupine in med njimi nekateri še v nadaljnje podskupine. Hierarhična struktura predlaganega modela omogoča, da se prepozna kontekst do potrebnega nivoja oziroma do tistega nivoja, ki ga je z razpoložljivimi senzorskimi podatki v danem trenutku mogoče prepoznati. Hkrati taka struktura omogoča, da se nanjo lahko navežejo bolj specifični, ožje-domenski modeli. Izvedli smo terenski preskus z desetimi uporabniki tekom enega meseca in preverili, kako se predlagani model obnese v praksi ter katere aktivnosti se najpogosteje in najdlje odvijajo v vsakdanu uporabnika. Medtem ko so kumulativni in statistični rezultati pokazali raznolike življenjske sloge testnih uporabnikov, se je model v preskusu izkazal za celovitega, a ne povsem nedvoumnega. Ad C: Na koncu smo razvili preprosto, uporabniku prijazno in avtomatsko metodo za določanje uporabniškega konteksta na podlagi prstnih odtisov Wi-Fi, podatkov GPS in pospeškometra. Metoda najprej najde uporabniške pomembne lokacije, tj. točke zadrževanja in regije zadrževanja, ter tranzite med njimi. Za iskanje točk zadrževanja smo uporabili metodo SensLoc [1], poiskali nabor nastavitev, ki bi dale najboljše rezultate na naših podatkih in predlagali pet izboljšav metode. Nato smo predlagali sedem različnih shem za inovativno združevanje najdenih točk zadrževanja, ki imajo isti semantični pomen za uporabnika, v regije zadrževanja. Na ta način smo tvorili splošnejše lokacije istega uporabniškega konteksta in pri tem ohranili podrobnosti pripadajočih točk zadrževanja. Najdenim točkam in regijam zadrževanja ter tranzitnim točkam smo z logičnimi pravili, časovno-prostorskim gručenjem, statistično obdelavo, inovativno analizo družabnih mrež, bazo točk zanimanja in matriko POI-aktivnost določili statični in dinamični uporabniški kontekst dveh nivojev. Prvi je vključeval splošne uporabniške aktivnosti, kot so doma, delo, prosti čas in tranzit, in drugi nekatere podrobne kontekste, kot na primer druženje, tek in na koncertu. Metodo za iskanje točk in regij smo optimizirali in ovrednotili na podlagi zbranih podatkov šestih uporabnikov v osmih dneh. Delovanje sklepanja o uporabniškem kontekstu pa smo ovrednotili na podlagi zbranih podatkov desetih uporabnikov v enem mesecu. Našli smo nabor nastavitev, ki so na naših podatkih mnogo bolje od prvotnih nastavitev SensLoca ločile mirovanje od gibanja in našle točke zadrževanja. Kombinacija štirih predlaganih izboljšav je nadalje izboljšala delovanje prvotne metode in pri tem ohranila bistvene podatke o uporabniških poteh. Tako izboljšana metoda je prepoznala 636 ur mirovanja od zabeleženih 690 ur s točnostjo, natančnostjo in priklicem prepoznave mirovanja večjimi od 96,5%. Pri združevanju točk v regije se je najbolje izkazala shema, ki je združevala na podlagi podobnosti prstnih odtisov dostopovnih točk in podobnosti prstnih odtisov identifikatorjev nabora storitev (angl. service set identifier - SSID). Priklic in natančnost te sheme sta bila 77%. Na koncu je metoda točno določila splošen kontekst v 95,3% časa. Za točke zadrževanja so bili konteksti doma, delo in prosti čas določeni z natančnostjo in priklicem večjima od 86%. Med podrobnimi konteksti je metoda povsem natančno določila kontekste druženje, obisk počitniške hiše in terensko delo, najslabša pa je bila natančnost za kontekst tek. Še več, pokazali smo, kako lahko sklepamo o podrobnih kontekstih posameznih točk zadrževanja znotraj regij zadrževanja, tj. obeh tipov lokacij, ki smo jih določili v predhodnih korakih naše metode. Rezultati kažejo, da je predlagana metoda robustna in se jo lahko uporablja na podatkih različnih uporabnikov in z različnih telefonov. Zaradi svojih značilnosti so lahko celotna metoda ali njeni deli uporabljeni na različnih področjih, kot na primer pri prilagajanju večpredstavnostnih aplikacij in storitev, v sistemih priporočanja in pri upravljanju s človeškimi viri ali premičninami. Glede na potrebe posameznega področja uporabe se predlagana metoda lahko nadalje prilagodi ali razširi.

Language:Slovenian
Keywords:mobilna omrežja, senzorji, lokacijske storitve, zavedanje uporabniškega konteksta, kontekstni modeli, uporabniške poti, pomembne uporabniške lokacije, pozicioniranje
Work type:Dissertation (m)
Organization:FE - Faculty of Electrical Engineering
Year:2015
Views:1333
Downloads:298
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:AUTOMATIC CONTEXT DETERMINATION OF A MOBILE USER
Abstract:
Commercially available smartphones contain an increasing number of communication technologies, such as Wi-Fi, infrared (IR), Bluetooth, radio-frequency identification (RFID) and global positioning system (GPS), as well as sensor modules, such as an accelerometer, compass, microphone and camera. At the same time, smartphones are becoming the key users and producers of multimedia contents. In the context of an enormous amount of information, applications and services, it is necessary to recommend only those that are really relevant for the user. To evaluate relevancy, the systems use personalisation and, since recently, context-awareness is gaining in importance as well. By being aware of the user context, the operation of the services and the suggested content can be adopted to the circumstances of the user and his smartphone. The user context can be determined manually, which is not very user-friendly, or automatically with the analysis of various sensor data from smartphones. Besides selection of the relevant sensors and processing of their data, the selection of context model plays a central role in the automatic inference of the user context. The selection of the context model includes defining its aim and a set of inferred values, as well as deciding upon the methods of context inference. In the dissertation, we envisioned the context model of user activities. These are typically determined with several context parameters together. Among them, the key parameters are: location, time, user profile and physical activity, and they were all used in our work. For the parameter location, we (A) proposed and evaluated a hybrid positioning method and developed a method that evaluates various positioning methods in the semantic space, i.e. in space with the semantic locations, such as street addresses and points of interest (POIs). (B) Then, we defined the context values of the context model, i.e. daily user activities, such as home, work, shopping and running. (C) Finally, in order to automatically determine these values, we upgraded the method for analysis of the user trajectories, determined with the sensors of smartphones, and used various methods for inference of the user context. Ad A: The proposed hybrid positioning method uses the GPS data, the serving mobile cell and its received signal strength, and several details about mobile network, such as the mobile channel frequency, type of the mobile base station and height of the base station tower. With regard to the data source, the method estimates the user position in three ways: (i) it adopts the location of the serving mobile base station, when the smartphone is connected to the indoor base station; (ii) it adopts the GPS position, when it is available; (iii) in all other cases, it calculates the position with the most appropriate radio propagation model. Besides the user position, also accuracy estimation of the positioning is provided. For that, we evaluated several factors that could influence positioning error, such as number of satellites, received signal strength and various data about density of mobile network, and sought for a correlation with the positioning error. Based on the field measurements, obtained on 167 random locations, we optimised the proposed method and evaluated factors that could be used to estimate accuracy of each measurement. With the same field measurements, performance of the optimised proposed method was compared to the existing positioning method, used by the observed mobile operator, and some commercial methods: GPS navigation device, Google and Foursquare. The performance of the method was evaluated two-fold: with average positioning errors and with the new method for evaluation of the positioning methods in the semantic space. The latter evaluated the correctness of conversion of the user positions into street address and important categories of POIs. The optimised proposed method had an average error of 85.9 m and 67-th percentile of 86.9 m. The analysis showed that three accuracy values were reasonable: 33, 270 and 377 m. For positions determined with GPS, no correlation factor was found, therefore we used a common value for all such measurements, i.e. 33 m. For positions determined with the serving mobile cells that were not installed indoor, we chose the average distance between the estimated position and the first two neighbouring cells among all evaluated factors. Based on the selected factor, the cell-based measurements were divided into two classes of accuracy, i.e. with the accuracy values of 270 and 377 m. The proposed method performed better than the existing method deployed by the observed operator, but still much worse than the GPS navigation device. The latter had the best overall results in our measurement scenario, followed by the Google positioning service. When our method determined the position with the GPS or the indoor base station, the estimation was accurate, but the accuracy of estimation significantly decreased in all other cases. Differences among observed positioning methods were smaller, when they were evaluated in the semantic space. However, among the observed methods, the proposed method had the best results in estimation of accuracy, because its estimations were correct for most measurements. There are two main advantages of the proposed positioning method: it can be used in practice for all smartphones and it uses two complementary technologies which ensures availability of the positioning service almost everywhere. However, positioning based solely on the servingmobile cell is too inaccurate for automatic inference of the user context. Consequently, it would be possible to infer the user context in two levels: when the positioning is accurate, the detailed user context could be determined; when it is not accurate, only the general user context would be determined. In practice, the general user context would be determined most of the time, therefore we omitted this source of the user location for our further work. Ad B: Then, we proposed a hierarchical context model that was build based on a survey of the relevant literature. It consists of static and also dynamic activities that fill every day of a user. The model includes four general user contexts: home, work, free time and transit. Some of them are further divided into sub-contexts and some of sub-contexts were divided even further. The hierarchical structure of the proposed model enables inference of the user context to the desired level or to the level that can be determined with the available sensor data at a given time. At the same time, more domain-specific models can be attached onto such hierarchical structure. We performed a field trail with ten users over one month. We checked if the proposed model proved effective in practice, and examined which activities are most frequent, and which occupy most time in daily schedules of the users. While the cumulative and statistical results indicated various life styles of the participating users, the model proved to be integral, but not entirely unambiguous. Ad C: Finally, we developed a simple, non-intrusive and automatic method for determination of the user context based on the Wi-Fi fingerprints, GPS and accelerometer data. Firstly, the method finds important user locations, i.e. the stay points and stay regions, and transits among them. To find the Wi-Fi stay points, we implemented the method from [1], found the optimal set of parameter values for our dataset, and suggested five improvements. Then, we suggested six different schemes for novel aggregation of determined stay points that had the same semantic meaning to a user into meaningful stay regions. Thus, we formed more general locales of the same user context, while maintaining the details about the belonging stay points. For determined stay points, stay regions and transits among them, we inferred static and dynamic user contexts in two levels with logical rules, spatio-temporal clustering, statistical analysis, innovate analysis of the social network data, database of POIs and POI-activity matrix. The first level of the user context included the four general user contexts, such as home, work, free time and transit, and the second level included some, more detailed user contexts, such as visiting, running and at concert. The method for finding stay points and stay regions was optimised and evaluated based on the real life traces collected by six users over eight days. The method for automatic inference of user context was evaluated based on the real life traces collected by ten users over one month. We found a set of parameter values that on our dataset performed better than the originalsettings of the SensLoc method in determination of moving vs. static mode and in determination of stay points. A combination of our four proposed improvements further improved the performance of the original SensLoc method, while it maintained the key information about the user trajectories. The method recognized 636 hours of the stay mode out of the annotated 690 hours, with accuracy, precision and recall of stay mode determination of above 96.5%. For the aggregation of stay points into stay regions, results of the aggregation scheme that was based on the fingerprint similarity of access points and of their service set identifiers (SSIDs), resembled the user annotations the most. For this scheme, the precision and recall of region determination were 77%. Finally, the method accurately inferred the user context 95.3% of the time. The contexts home, work and free time were assigned to stay points with precision and recall higher than 86%. On the other hand, the method precisely determined the contexts visiting, visit of weekend house and field work, while the context running was inferred with the lowest precision. Moreover, we demonstrated how the more detailed user contexts could be extracted for stay points within stay regions, i.e. both types of locales that were determined in the previous steps of our method. The results indicate that the suggested method is robust and can be used with various users and on various smartphones. Due to its characteristics, the entire method or its modules can potentially be deployed in various fields, such as in adjustment of the multimedia applications and services, in the recommender systems and in the fleet management. According to the needs in the specific field of deployment, the method can be further adjusted and expanded.

Keywords:mobile networks, sensors, location-based services, context-awareness, context models, user trajectories, user important locations, positioning

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back