Mobility Data Analysis To Understand Unknown Diseases
Mobility data analysis to understand unknowndiseases behaviorThe case of facial paralysisJalel AkaichiPhD, University of Sciences and Technologies of LilleAssociate Professor, University of Tunis1
General introduction2
Introduction (1/2) Our everyday actions, as expressed by the way we live andmove, leave digital traces in information systems.–Move in workplace, perform a surgery, etc. This is due to the use of mobile location aware devices.– That allow us to communicate.– That allow them to locate us ! Thanks to positioningtechnologies. Through these traces we can sense the objects movementsin a space.–City, delegation, hospitals, human body, etc. Their potential value is high because of the increasingvolume, pervasiveness and positioning accuracy of thesetraces.–Varied queries can be performed.3
Introduction (2/2) Location technologies are capable of:– Providing a better estimation of a mobile object‘sposition. Positioning system-equipped mobile devices can:– Transmit location information to some servicesprovider. Latest advances like :– Wi-Fi and Bluetooth devices are becoming a source ofdata for indoor positioning.– Wi-Max can become an alternative for outdoorpositioning.4
Some kinds of mobility data scenarios5
Scenarios in health care (1/4)6
Scenarios in health care (2/4)7
Scenarios in health care (3/4)8
Scenarios in health care (4/4)9
Pervasive systems10
Pervasive computing Ubiquitous– Accessible from anywhere. Mobile– Integrate mobile devices. Context-aware– Take into account the execution context. Pervasive– Associate ubiquity, mobility and context-awareness. Ambient– Integrated into daily objects.11
Ambient systems12
Pervasive systemPervasive systemMobile anagementContextmanagement13
Four waves - Four paradigms Mainframe computing (60’s-70’s)– Massive computers to execute big data processing applications.– Very few computers in the world. Desktop computing (80’s-90’s)– One computer at every desk to help in business-related activities.– Computers connected in intranets to a massive global network(internet), all wired. Mobile computing (90’s-00’s)– A few devices for every person, small enough to carry around.– Devices connected to cellular networks or WLANs. Ubiquitous computing (now)– Tens/hundreds of computing devices in every room/person, becoming“invisible” and part of the environment.– WANs, LANs, PANs – networking in small spaces.14
Trend: Weiser’s 3 waves of computing15
Ubiquitous computing Ubiquitous computing:– Activates the world.– Is invisible, everywhere computing that does notlive on a personal device of any sort, buteverywhere.– Makes a computer so embedded, so fitting, sonatural, that we use it without even thinkingabout it. Also called: pervasive, deeply embedded,sentient computing, and ambient intelligence.16
Five main properties for ubiquitous elligent17
Ubiquitous health care Environment that collects the information byattaching sensors to medical “objects” andmanaging real-time information through thenetwork. Providing health service of precaution,diagnosis, treatment, post management, etc. Everywhere at anytime.18
Ubiquitous health care exampleBlood PressureHealth InformationSystemBlood SugarECGAccelerationTemperature
Digital bandageLow power and small SizeToumaz company in EnglandDigital PlasterIMEC in BelgiumWireless Sensor Platform20
MIT Wireless Ring SensorMeasurments (wireless)- Heart rate- Heart rate variability- Oxygen saturation- Estimation of blood pressure21 21
Enabling technologies Wireless (data)communication– Higher bandwidth– Lower power– Commodity (readilyavailable and secure) Small form factor devices– Shrinking electronics– Better displays– New input methods Personalization– Machine learning– Inference22
Extremely varied Embedding for smart control– Embedded systems for cars, airplanes, patients,etc. Creating new computing devices Connecting the existing physical world to acomputational infrastructure– Ordinary objects and tasks re-evaluated andextended with computational/communicationcapabilities23
Mobile computing The application of small, portable, andwireless computing and communicationdevices. Being able to use a computing device evenwhen being on the move. Portability is one aspect of mobile computing– portable vs. mobile.24
Distributed IS duties Data persistency.Data exchange between heterogonous applications.Data distribution on distant sites.Data permanent consistency management.Platforms interoperability.Applications portability.Concurrent access management.Legacy systems integration.Openness.Security.25
Pervasive IS duties Distributed IS Intelligence (« smartness »).Pro-action « all the time everywhere ».26
Scalability Scaling. Manage increasing volumes of– Users.– Applications.– Connected devices. Develop applications whose their “heart” isindependent from the volume, the users, and thedevices. Use adaptation techniques to be able to giveanswers for each case.27
Invisibility Requires minimal human intervention.Self adaptation to changes.Self-learning.Example:– Dynamic reconfiguration of networkcharacteristics of a device.– Space resources access according to geographiczone encapsulating that space.– Out of space limits definition of space.28
Context-awareness Perception of the environment to interactmore 'naturally' with the user. Sensors of the physical environment. Self-descriptive devices. Persons description. Applications meta-data.29
« Smartness » Smart intelligent, quick-witted, malignant,resourceful. Perceive the execution context is notsufficient. Must effectively use context information. Example : smart home.30
Pro-action Suggest, propose corrective actions to the userdepending on the context present or predicted.– For example, move 100 meters to a more efficientnetwork and thus accomplish a task in a correct time. Implies to know:––––Predict an event, a situation, etc.Assess a current or a possible situation.Compare two situations and judge the best.That "it's worth" to break invisibility.31
Pervasive computing32
Facial paralysis use case33
Motivation scenario: Medical case Let us consider a health care organization which is interested:– In analyzing mobility data in different areas such as in facial nerve.– To decide upon bell’s patients recovery and about the diseasebehavior. It is interested in analyzing:– The recovery process of a patient in time intervals.– The demographical profiles of patients coming from differentgeographical zones, belonging to different age intervals, havingdifferent family antecedents, etc. This knowledge will enable physicians:– To understand the disease behavior.– To apply more effective strategies according to patients recovery.34
Facial nerve components modelingModeling the facial nerve stream as a movingobject circulating into the facial nerve “network”.35
Anatomy of facial nerve36
Facial nerve graphMuscles graphGlands Graph37
Mobility data analysis38
Analyzing mobility data (1/3) Modern communication and computing devices are pervasiveand carried by various objects: people, vehicles, etc. The consequence is that object and its activity in a space maybe sensed:– Not necessarily on purpose. We just collect data.– As a side effect of the services provided to mobile users. Calls made and/or received, SMS, emails, shopping, diagnosis, etc. Wireless mobile devices network is an infrastructure able:– To gather mobility data.– To analyze them and gain insights about objects movements. Trajectories (stop, moves, activities, etc.).39
Analyzing mobility data (2/3) Usage of location aware devices allows access tolarge spatiotemporal datasets. The space-time nature of this kind of data:– Results in the generation of huge amounts ofspatiotemporal data.– Imposes new challenges regarding the analytical toolsto be used for transforming raw data to knowledge. Necessity to investigate the extension oftraditional analytical techniques to be applicableon mobility data.40
Analyzing mobility data (3/3) The analysis of mobility data raises opportunities for discoveringbehavioral patterns to be exploited in applications like:––––––––Mobile marketing.Mobile information collections.Mobile hospitals.Mobile physicians.Stream nerve detection.Heart disease supervision.Robots.Traffic management, etc. OLAP and DM techniques can be employed in order to convert thisvast amount of raw data into useful knowledge.41
Expectations from mobility data analysis (1/3) To propose innovative analytical techniques aiming toextract useful patterns from spatiotemporal data.– Extraction, Transformation, and Loading.– Mobile devices, MOD, TDW. To identify the difference between two types ofspatiotemporal data: mobility and immobility data.– Stream nerve vs muscles. To focus on data warehousing and mining techniquesthat can be applied on MODs.– Patients, physicians, devices, medical staffs, hospitals,cities, etc.42
Expectations from mobility data analysis (2/3) How traditional data cube model is adapted toTDWs in order to transform raw location datainto valuable information. How ETL procedure feeds a TDW withaggregated trajectory data. How to aggregate cube measures for OLAPpurposes.43
Expectations from mobility data analysis (3/3) To study a new approach in designing trajectorydata cubes. To give answers to ad hoc OLAP queries related tovarious applications. To propose a new OLAP data model that include aflexible fact table that:– Can answer queries considering semantic definitionsof trajectories.– Provides the option to choose the appropriatesemantic for aggregation queries over trajectory data.44
Moving object data management,warehousing and mining45
Health care decisional processBioinformatics Feedback / Value-Added taMonitoringSensingMeasuringbiological signalsLong-termAnalysisResultsETLFiltered &Analyzed DataDisplayAnalyzingLong-term Data storageTrend analysisMedical DevicesOLAP, Data mingFeedback Behavior modification Emergency Alert Feedback-Action(Prescription, exercise, eu-Health visualization46
Facial nerve TDW47
Concepts on spatiotemporaldata48
Basic concepts on spatiotemporal data (1/3) Generation of dissimilar, dynamic, andgeographically distributed spatiotemporaldata has exploded, thanks to advances in:– Mobile devices and remote sensors.– Networks.– Location sensing devices. 2 types of spatiotemporal data: mobile andstatic.49
Basic concepts on spatiotemporal data (2/3) The rate at which geospatial data aregenerated exceeds the ability to organize andanalyze them to extract patterns in a timelymanner. CS and Geo-informatics collaborate to provideinnovative and effective solutions.50
Basic concepts on spatiotemporal data (3/3) A typical category of mobility data is the time-stampedlocation data:– Collected by location-aware devices.– Allowing access to large datasets consisting of time-stampedgeographical locations. The traditional database technology has been extendedinto MODs that handle:– Modeling.– Indexing.– Query processing issues for trajectories. The challenge after storing the data is:– The implementation of analytics to extract useful knowledge.51
Immobile entities (1/2) Sensing technologies feel, record and study phenomena.– Human body, diseases, etc. At least data collection occurs every one small time unitdepending on applications. Patients data collection is huge and rapidly increasing. Medical staffs record information to describe and studypatients bodies activities. Analysts find a valuable “data treasure”, to process andanalyze to discover knowledge from this data.52
Immobile entities (2/2) Human body phenomena are instantly recordedby a number of organizations worldwide. A system collecting and analyzing most accuratedata among different sources is needed. Some sources provide data about the samephenomena though with differences in theirdetails. The need for a generic architecture will be able tointegrate the remote sources in a proper way byrefining and homogenizing raw data.53
Data warehousing and miningcomponents54
Data warehousing and miningcomponents Tools for data exploration and inspection. Algorithms for generating historic profiles of activitiesrelated to specific spaces and time periods. Techniques providing the association of data with othergeophysical parameters of interest:– Patient morphology, disease and recovery evolution, etc.– Visualization components using geographic and otherthematic-oriented maps for: Presentation of data to users such as medical staffs. Supporting sophisticated user interaction.55
Trajectory data warehousing andmining users profiles Physicians are interested in:– Constructing and visualizing patients' profiles ofcertain body regions during specific time periodsof a disease evolution.– Discovering regions of similar behavior.– Disease activity, thus querying the system forproperties of general interest.56
Facial paralysis warehousing andmining DWMS architecture provides users a wealth ofinformation about patients recovery from Bell’spalsy recovery. Collected data can be stored in a local databaseand/or a data warehouse (for simple queryingand analysis for decision making, respectively). Data within the database is dynamic and detailed;while that within the data warehouse is static andsummarized.57
DWMS querying functionality Retrieval of spatial information given a temporal instance.– When we are dealing with records including: Position (segments). Time of facial nerve partial or total recovery together withattributes like intensity, segments, paths, muscles, etc. Retrieval of spatial information given a temporal interval.– Evolution of spatial objects (stream nerve) over time.– Recording the duration of partial and total recoveries andhow certain parameters of the phenomenon varythroughout the time interval of its duration.58
Examples of typical queries Find the number of recoveries realized duringthe past four months, which reside moreclosely to a given location. Find all sequelae of patients residing in acertain region. Find the number of recoveries occurred in aspecified time interval.59
Maintaining summary for dataanalysis (1/3) Two popular techniques for analyzing data and interpreting theirmeaning are:– OLAP analysis.– Data mining. Summarized health care data can study the phenomenon from ahigher level and search for hidden, previously unknown knowledge. View part of the historical recovery profile:– Example. the number of cases that leads to a surgery in the pasttwenty years, over a specified region. View the same information over a country, continent, the world.– More detailed view, formally a drill-down operation.– Worldwide. More summarized view, formally a roll-up operation.60
Maintaining summary for dataanalysis (2/3) Slice and dice, for selecting parts of a datacube by imposing conditions on a single ormultiple cube dimensions. Pivot, which provides the user with alternativepresentations of the cube. Integrating data analysis and miningtechniques into an DWMS aims to thediscovery of interesting, implicit andpreviously unknown knowledge.61
Examples of useful patterns found throughKnowledge Discovery & Delivery (KDD) process Clustering of information.– Cases occurred closely in space and/or time.– Cases related to kids, adults, etc. Classification of phenomena with respect to recoveredareas, and detecting phenomena semantics by usingpattern finding techniques, etc.– Characterizing the main recovery aspects in recoverysequences.– Measuring the similarity of sequelae sequences, accordingto a similarity measure specified by the domain expert,etc.62
Mobile entities63
The case of trajectory data Moving objects are geometries (i.e. points, lines,areas) changing over time.– Pills, stunts, stream nerve, etc. Trajectory data describes the movement of theseobjects. Movement implies two dimensions: the spatialand the temporal (recovery). Movement can be described as continuouschange of position in the geographical space andthrough comparison between two differenttemporal instants.64
Spatio-temporal trajectory A sequence of spatiotemporal points In a road network. In a human body network. In a part a body network: The face forexample.65
A semantic trajectory example Semantic enrichmentintegrate structuredtrajectories withsemantic knowledgefrom the two semanticviewpoints, i.e.:– Geographic view.– Application domain view.66
A hybrid semantic trajectory model67
Structured trajectory (a sequence ofepisodes)68
Semantic trajectory (a sequence ofsemantic episodes)69
Offline trajectory computingframework70
Formalization71
Formalization (1/3) A trajectory T is a continuous mapping fromthe temporal I R to the spatial domain (R2,the 2D plane). I R R2: t a(t) (ax(t), ay(t)). T {(ax(t), ay(t), t) t I} R2xR. Where (ax(t), ay(t), t) are the sample pointscontained in the available dataset.72
Formalization (2/3) From an application point of view:– A trajectory is the recording of an object‘s motion.– Example. The recording of the positions of anobject at specific timestamps. The actual trajectory consists of a curve. Real-world requirements imply that thetrajectory has to be built upon a set of samplepoints.– The time-stamped positions of the object.73
Formalization (3/3) Trajectories of moving points are oftendefined as sequences of (x, y, t) triples. T {(x1, y1, t1), (x2, y2, t2), , (xn, yn, tn)}, wherexi, yi, ti R, and t1 t2 tn. The main objective is to include appropriatetechniques for the representation, querying,indexing and modeling of moving object‘strajectories.74
Innovation75
The need for innovation in decisionsupport techniques (1/2) Traditional decision support techniques developed asa set of applications and technologies ing access to data. Example:––––Data warehousing.Online analytical processing.Data mining.Visualization.76
The need for innovation in decisionsupport techniques (2/2) These techniques are embedded in decision supportsystems.– To support business and organizational decision-makingactivities. Such systems help decision makers to identify, analyze andsolve problems as well as make decisions, by combining:––––Raw data.Documents.Personal knowledge.Business models, etc. Decision support techniques were developed to satisfy thechangeable and complicated needs of current business andtechnological environment.77
Decision support techniquesextensions (1/2) The extension of traditional techniques to delivernew analytics, suitable for mobility data. To serve emerging applications (e.g. mobile healthcare) that need to convert raw location data intouseful knowledge. A TDW can help towards computing aggregations ontrajectory data and thus studying them in a higherlevel of abstraction.78
Decision support techniquesextensions (2/2) Data mining techniques are used to discoverunknown, useful patterns. The vast amount of available mobility data requiresthe extension of traditional mining techniques so asto be suitable for this new kind of data. Discovering spatiotemporal associations, clusters,predicting actions, etc., lead to mobility patterns:– That could help to construct summary and useful abstractions of largevolumes of raw location data and gain insights on movementbehaviors.79
Efficient trajectory datawarehousing80
Efficient trajectory data warehousing(1/2) Data warehousing is a techn
Facial paralysis warehousing and mining DWMS architecture provides users a wealth of information about patients recovery from ells palsy recovery. Collected data can be stored in a local database and/or a data warehouse (for simple querying and analysis for decision making, respecti
Aruba 7008 Mobility Controller Aruba 7010 Mobility Controller Aruba 7024 Mobility Controller Aruba 7030 Mobility Controller Aruba 7210 Mobility Controller ArubaOS_72xx_8.1.0.0-1.0.0.0 ArubaOS_72xx_ 8.4.0.0-1.0.6.0 ArubaOS_72xx_8.4.0.0-1.0.5.1 Aruba 7220 Mobility Controller Aruba 7240 Mobility Con
2 Introduction: - Transformational Shifts Reshaping the Future of Mobility New Mobility Business Models Mobility Integration Convergence of Corporate Mobility The City as a Customer Women and the Automotive Industry Focus on Health Wellness and Wellbeing in the Automotive Industry Connected and Automated Mobility Growth in high Speed Rail and Public transport .
01.26.10.0033 Trial double mobility liner Ø 22mm / DMC 1 on demand 01.26.10.0034 Trial double mobility liner Ø 22mm / DMD 01.26.10.0035 Trial double mobility liner Ø 28mm / DMD 01.26.10.0036 Trial double mobility liner Ø 28mm / DME 01.26.10.0037 Trial double mobility liner Ø 28mm / DMF 01.26.10.0038 Trial double mobility liner Ø 28mm / DMG
work/products (Beading, Candles, Carving, Food Products, Soap, Weaving, etc.) ⃝I understand that if my work contains Indigenous visual representation that it is a reflection of the Indigenous culture of my native region. ⃝To the best of my knowledge, my work/products fall within Craft Council standards and expectations with respect to
This is why we called the 4th High Level Dialogue on Connected & Automated Mobility in Vienna “Beyond SAE LEVELS: Towards Safe and Sustainable Mobility”. We wanted to pick up on the Swedish focus on integrated mobility and ask ourselves how we can integrate new automated services into a future-proof and sustainable mobility eco-system.
mobility in the advisor role The evolution of the global mobility professional is a continual process. The increased use of flexible mobility policy, along with growing business and employee demands for choices, requires those in the function to advise and support decision-makers in new ways.
FIREPOWER MOBILITY (Maneuver) PROTECTION Mobility (manoeuvrability), is a key element of combat power At the strategic level, mobility usually involves the movement of forces and resources to the theatre of conflict. At the operational level, mobility involves placing forces and resources at the critical place in time to achieve an .
2 The building blocks An employer's guide to improving social mobility in the workplace About the Social Mobility Commission The Social Mobility Commission monitors progress towards improving social mobility in the UK, and promotes social mobility in England. It is an independent statutory body created by an Act of Parliament.
