Home smart home
This is a modal window.
The media could not be loaded, either because the server or network failed or because the format is not supported.
Formal Metadata
Title |
| |
Title of Series | ||
Number of Parts | 4 | |
Author | ||
License | CC Attribution 3.0 Unported: You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor. | |
Identifiers | 10.5446/43616 (DOI) | |
Publisher | ||
Release Date | ||
Language |
Content Metadata
Subject Area | ||
Genre | ||
Abstract |
|
1
2
4
00:00
Video gameSeries (mathematics)Axiom of choiceWritingOntologySelf-organizationRoboticsUniverse (mathematics)Staff (military)StatisticsUsabilityArtificial neural networkComputer science2 (number)MassGoodness of fitNeuroinformatikDisk read-and-write headState of matterComputer clusterConstraint (mathematics)Term (mathematics)Mathematical singularityKnowledge representation and reasoningIntegrated development environmentBitAreaOptical disc drivePlastikkarteOnline helpWordLecture/Conference
04:49
State of matterVideo gameMultiplication signExpected valueAxiom of choiceStatisticsTerm (mathematics)DataflowWebsiteTask (computing)Independence (probability theory)Computer animationLecture/ConferenceMeeting/Interview
06:19
Hand fanSlide ruleInheritance (object-oriented programming)Term (mathematics)Computer animationLecture/Conference
07:34
Ambient intelligenceIntegrated development environmentLevel (video gaming)Video gameIndependence (probability theory)PlastikkarteSmartphoneWaveGoodness of fitDemosceneLecture/ConferenceComputer animation
08:51
Ambient intelligenceIntegrated development environmentMilitary baseMultiplication signBasis <Mathematik>FeedbackCuboidRight angleElement (mathematics)Form (programming)State of matterLecture/ConferenceMeeting/InterviewComputer animation
10:04
Ambient intelligenceIntegrated development environmentCognitionView (database)Different (Kate Ryan album)WordoutputAreaAmbient intelligenceElement (mathematics)Food energySound effectComputer animationLecture/ConferenceMeeting/Interview
11:10
Ambient intelligenceIntegrated development environmentAdaptive behaviorPhysical systemGroup actionComputerIntegrated development environmentTransport Layer SecurityComputer scienceNeuroinformatikSlide ruleGreatest elementAmbient intelligenceCASE <Informatik>WordSensitivity analysisComputer animationLecture/ConferenceMeeting/Interview
12:14
Adaptive behaviorLimit (category theory)System programmingIntegrated development environmentLocal GroupDigital signalCodecAreaSoftwareSensitivity analysisRight angleIntegrated development environmentCASE <Informatik>Condition numberCuboidWordMemory managementSlide ruleDependent and independent variablesCovering spaceXMLUMLComputer animation
13:28
ComputerInteractive televisionPhysical systemNeuroinformatikInterface (computing)MaizeMultiplication signInformation securitySet (mathematics)Selectivity (electronic)Water vaporRadical (chemistry)Ambient intelligenceMainframe computerLecture/Conference
14:51
Information privacyBitInternetworkingRight angleWebsitePasswordRoutingMathematicsStandard deviationProcess (computing)Internet service providerKnowledge baseInformation securityPerfect groupInheritance (object-oriented programming)WhiteboardSet (mathematics)Product (business)Arithmetic meanDigitizingNumberRouter (computing)System administratorLoginAmbient intelligenceEmailModemLecture/ConferenceMeeting/Interview
18:20
Position operatorThermal radiationPressureLiquidAreaBitRoboticsType theoryGoodness of fitForm (programming)Right angleInformation securityThermal radiationPerfect groupNoise (electronics)Speech synthesisExtension (kinesiology)LiquidXMLProgram flowchartLecture/Conference
19:44
DistanceNoise (electronics)DataflowPhysical systemProjective planeNeuroinformatikSoftware testingTrailPrice indexPosition operatorForm (programming)Direction (geometry)Computer scienceLecture/Conference
21:14
Position operatorThermal radiationPressureLiquidPressureMoving averagePrice indexSet (mathematics)Student's t-testData miningTask (computing)Prisoner's dilemmaMessage passingSheaf (mathematics)Zoom lensUniverse (mathematics)XMLProgram flowchartLecture/Conference
22:46
VideoconferencingProcess (computing)Medical imagingMachine visionNeuroinformatikTask (computing)Decision theoryComputer animationLecture/Conference
23:53
Wireless LANSource codePlastikkarteFitness functionSmartphoneSpacetimeBitComputer animationLecture/Conference
24:47
Wireless LANSource codeException handlingSoftware developerLie groupCuboidPresentation of a groupStudent's t-testNumberSlide ruleMultiplication signForm (programming)Computer animationLecture/Conference
26:11
Ambient intelligenceComputerVirtual machineProjective planeStudent's t-testCuboidForm (programming)NeuroinformatikGroup actionBitPattern recognitionDirection (geometry)InformationNormal (geometry)DataflowComputer animationLecture/ConferenceXML
27:31
Pattern recognitionState of matterClosed setOpen setVirtual machinePattern recognitionTerm (mathematics)ComputerSequenceLevel (video gaming)State observerProcess (computing)Division (mathematics)InformationRow (database)Similarity (geometry)Lecture/ConferenceComputer animation
28:44
Pattern recognitionObject (grammar)State of matterClosed setOpen setVirtual machineBounded variationSequenceBounded variationMIDITask (computing)Lecture/ConferenceComputer animationMeeting/Interview
29:38
Bounded variationState observerBounded variationResultantVirtual machineClosed setComputer animationLecture/Conference
30:30
Virtual machineWeightMereologyArchaeological field surveyState observerArrow of timeSlide ruleCAN busComputer animationLecture/Conference
31:23
Hidden Markov modelSequenceData modelMarkov chainType theoryState of matterGoodness of fitEndliche ModelltheorieHidden Markov modelDisk read-and-write headNoise (electronics)Lecture/ConferenceMeeting/InterviewComputer animation
32:21
Hidden Markov modelSet (mathematics)SequenceState of matterDistribution (mathematics)Endliche ModelltheorieOrder (biology)CASE <Informatik>SequenceProcess (computing)Ferry CorstenState observerMultiplication signBuildingBridging (networking)outputType theoryNumberHecke operatorRight angleAreaState of matterFatou-MengeUltraviolet photoelectron spectroscopyObjekterkennungComputer animationLecture/ConferenceMeeting/Interview
35:03
Hidden Markov modelSet (mathematics)SequenceState of matterDistribution (mathematics)FLOPSRange (statistics)Physical systemWindowCovering spaceRight angleMatching (graph theory)Order (biology)Wave packetDataflowState observerFile formatLevel (video gaming)Goodness of fitEndliche ModelltheorieMereologyBitSpezielle orthogonale GruppeOpen setComputer animation
36:25
Context awarenessProcess (computing)Right angleLevel (video gaming)Physical systemEntropie <Informationstheorie>Type theoryState observerArithmetic meanFile formatQuicksortState of matterInformationOpen setStudent's t-testHypermediaPoint (geometry)Roundness (object)SpeciesCAN busLecture/ConferenceMeeting/Interview
39:15
Pattern recognitionContext awarenessMaxima and minimaFinite-state machineInformationFinite-state machineState of matterProcess (computing)Context awarenessMappingMedical imagingArmGoodness of fitMultiplication signTimestampDiagramLecture/ConferenceProgram flowchart
40:35
Context awarenessPattern recognitionComputer networkBoltzmann constantStochasticThomas BayesWell-formed formulaMultiplication signType theoryVirtual machineWave packetNetbookInstance (computer science)Boltzmann constantArtificial neural networkDisk read-and-write headEndliche ModelltheorieLecture/ConferenceComputer animation
41:45
Well-formed formulaThomas BayesBoltzmann constantCASE <Informatik>Context awarenessConditional probabilityWell-formed formulaCondition numberLecture/ConferenceComputer animation
43:14
Right angleMetropolitan area networkInformation systemsConditional probabilityCondition numberService (economics)VideoconferencingDisk read-and-write headContext awarenessLecture/Conference
44:47
Conditional probabilityComputer networkBedingte UnabhängigkeitRandom numberVariable (mathematics)Computer scienceBayesian networkSoftwareState observerNetwork topologyTransport Layer SecurityInformation securityCondition numberCASE <Informatik>Endliche ModelltheorieInsertion lossSlide ruleComputer animationLecture/Conference
46:47
Variable (mathematics)Context awarenessProgrammer (hardware)Spring (hydrology)PlastikkarteSmartphoneInformationReading (process)Computer programmingSpring (hydrology)Sign (mathematics)Broadcast programmingBitView (database)Lecture/ConferenceComputer animation
48:09
Bayesian networkDivision (mathematics)SoftwareTable (information)Core dumpCalculationOffice suiteCASE <Informatik>Point (geometry)Lecture/ConferenceMeeting/InterviewComputer animationEngineering drawing
49:13
TheoryCoroutineCoroutineInformationComplete informationMultiplication signRight angleLecture/ConferenceComputer animation
50:47
TheoryCoroutineMassFunction (mathematics)Context awarenessInformationSet (mathematics)Element (mathematics)Time domainFuzzy logicGradientLiquidInheritance (object-oriented programming)Message passingRight angleFormal grammarGastropod shellLiquidDifferent (Kate Ryan album)Fuzzy logicDegree (graph theory)Lecture/ConferenceMeeting/InterviewComputer animation
52:22
Fuzzy logicTheoryLiquidSubsetLiquidDegree (graph theory)Set (mathematics)Portable communications deviceSpring (hydrology)Tap (transformer)ExplosionWater vaporQuicksortSummierbarkeitDifferent (Kate Ryan album)Right angleLecture/ConferenceMeeting/InterviewComputer animation
53:29
Personal digital assistantFuzzy logicTheoryDegree (graph theory)Event horizonTerm (mathematics)Set (mathematics)Computer scienceInternetworkingForm (programming)State observerGoodness of fitRow (database)CASE <Informatik>Lecture/ConferenceMeeting/InterviewComputer animation
54:23
MereologyNumberForm (programming)Lecture/Conference
55:17
Electric currentInformation privacyInformation securityContext awarenessComputer networkInformationType theoryHausdorff dimensionSocial softwarePlastikkarteDigital signalInformationInformation securityInformation privacyPoint (geometry)Computer scienceConnected spaceType theoryView (database)Slide ruleBitProjective planeHypermediaXMLComputer animationLecture/Conference
56:39
Hausdorff dimensionComputer networkSocial softwareDigital signalPlastikkarteProjective planeCircleDependent and independent variablesClosed setTheory of relativityTelecommunicationHypermediaInternet service providerMemory managementSmartphoneLibrary (computing)Meeting/InterviewComputer animationLecture/Conference
57:37
Smart DeviceControl flowPlastikkartePrototypeIntegrated development environmentPlastikkarteMultiplication signAreaStandard deviationGame controllerExecution unitCondition numberFocus (optics)Computer animationLecture/Conference
58:49
Information securityNetwork topologySet (mathematics)View (database)Decision theoryProcess (computing)NeuroinformatikMereologyComputer sciencePoint (geometry)Student's t-testState of matterStress (mechanics)AreaCASE <Informatik>Expert systemBitField (computer science)Multiplication signMaxima and minimaWebsiteLogistic distributionDifferent (Kate Ryan album)Slide ruleIntegrated development environmentArithmetic meanDivisorObservational studyInformationEvent horizonRight angleOnline helpProjective planeInformation privacyForcing (mathematics)Video gameCausalitySelf-organizationSpacetimeFood energyPatch (Unix)Perturbation theoryPrice indexGodUniverse (mathematics)Rule of inferenceData storage deviceBit rateLattice (order)Arithmetic progressionReading (process)Extreme programmingElectronic mailing listPlastikkarteMetropolitan area networkLecture/ConferenceMeeting/Interview
Transcript: English(auto-generated)
00:05
Well, good evening. Good evening and welcome. It's fantastic to see so many people here on a slightly stormy night out there. Welcome to the second of the lectures in this year's Gibbons series where we're looking
00:21
at the steps towards the singularity, artificial intelligence and its impact. I'm Robert Amor. I'm head of computer science department here at the University of Auckland and it's my really great pleasure to introduce Professor Hans Gusken who's a friend and colleague to many of us over the years and I don't think Hans got a drink or any food because he was
00:45
saying hello to so many friends in the audience as he came in. So Hans is a professor of computer science at Massey University and his qualifications Hans come from universities in Germany and Bonn and Kaiserslautern and Hamburg and he
01:01
came to New Zealand in 1992 so he's almost lost his accent. And he came to the University of Auckland when he joined us there and in 2007 he shifted to Massey University where he's a professor in computer science.
01:22
It doesn't seem like a decade that Hans left us. That just seems a few years ago that that happened, but 10 years ago. So his main interests are in the area of smart environments, ambient computing and intelligence, knowledge representation and inference, constraint satisfaction and spatio-temporal reasoning
01:43
and tonight he's going to talk about artificial intelligence as it can impact on society and addressing one very specific problem where with our aging population and a population whose mental and physical capabilities are declining, how can AI help in that area?
02:06
And so there are some solutions. Hans is going to tell us about those solutions and the solutions which will give us a home sweet home. Thank you very much Robert. Thank you for this very warm welcome.
02:24
It reminded me of my arrival in New Zealand 25 years ago where I received an equally warm welcome both in general from New Zealanders and in particular from the staff members in this department and I will never forget that. Now when Robert said I had to catch up with a lot of friends and therefore couldn't
02:41
have a drink, it's half the truth. The other half is that my wife says if you're doing alcohol your accent becomes even worse and nobody will understand you. So that has to wait until after the talk or otherwise you wouldn't understand the word. Now I'm really honored to be here, to work quite frank.
03:01
When Bob approached me he said well look Hans, do you want to give a lecture in the Gibbons lecture series and I thought oh that's great but to be frank you are our second choice actually. But nevertheless I'm really really happy that you're... Louder? Thank you. I think I should move this purpose a little bit.
03:21
Is it better? No, it's not. Okay I will try to speak up a little bit. So I'm really delighted to be here and just to give you a little bit of an idea.
03:42
So it's almost my silver anniversary in New Zealand and ten years since I left the University of Auckland and moved to Massey. I've done artificial intelligence almost my whole academic life so to speak. There was an odd professor in Germany who said look Hans, there is a topic nobody
04:04
has heard of, artificial intelligence, it's really hot, you do that. And I said yeah, I do it. And since then I got stuck and over the years I developed various flavours and the most recent one is smart homes.
04:21
Now when we talk about smart homes there are a lot of things probably going through your head and the term is actually quite overloaded. You can install your own smart home nowadays which automates most of the things in your home or you can use it in various other ways. And the way I want to use it is to support elderly.
04:46
So this is my motivation. So here's some statistics. According to statistics about a quarter of our population will be aged 65 or beyond.
05:03
So that's one thing. So there's an expectation nowadays that we live longer and of course who doesn't wish to live longer a healthy life, an independent life. But at the same time that poses a problem because it's not always possible to live an independent life because as some of you might have already experienced and I
05:25
start to experience this slightly, there are certain things that happen over age. So I run much slower now than I run as a child I notice. I also find it difficult to do particular tasks.
05:42
I didn't have a problem with at all like touching the floor with my nose when I'm sitting down and things like that. I mean that's silly things but you see where I'm coming from. So the question then holds how do we actually support people because obviously it's not
06:03
always possible to live independently or in other terms who cares. So we need to find a solution and the question is what is that solution? We needed to find an alternative solution.
06:23
There are various solutions and the one you see on the slide is probably not one somebody prefers but if you're a fan of Dan Brown you probably noticed that in his recent book Inferno he suggests a more subtle solution which is to make half the population
06:43
sterile. Well even then it's kind of unsatisfactory but even if we somehow manage to get a solution there's another problem and I think back to my parents.
07:02
My mom married the guy from the next village. My grandparents never moved. Nowadays people are very flexible in terms of moving. I'm now probably on the opposite side of the world almost from where my parents live.
07:20
So with this flexibility actually comes a problem that we are not as easily prepared to take care of our parents or grandparents. So this is more a goal I'm looking at. Independent happy life and preferably not in a rest home very early, in the early stage.
07:50
So how do we achieve this or what is necessary to achieve this? I'll probably do the following and have a short break and put my watch here because
08:04
I otherwise go on forever. Okay, so there are various aspects in smart homes or what we could use a smart home for. Is my voice still all right? Can you hear me or am I fading off already? Okay, thank you.
08:21
Give me a sign, wave. So if you wave I know I'm too quiet. If you wave I know I have not switched on my microphone because I see no waves there, no waves there, everything's good. Okay, so first thing, assurance. I think this is not something which is particularly related to older people.
08:42
I don't know if you are in a situation sometimes you leave the house and you think, oh, have I switched off the stove or have I locked the door? And you can really get paranoid about that. I do from time to time and then you go back and check and then you leave again and say, did I actually check that?
09:03
Okay, so assurance is actually something that is quite welcome. Just on an individual basis feedback to certain things to a person living in a smart home. The other one is support. Support can mean a lot of things.
09:21
If you depend on medication it could mean that you get reminders at the right time to take the right medication. You probably all have heard about these intelligent boxes that open and the pills come out automatically at the right time. I'm always asking myself, are the people then taking the pills or throwing them away?
09:45
So they are already supporting elements like that. But it could also be just intelligent reminders that something has cooked long enough that you have forgotten, for example, to drink enough during the day and so on and so forth.
10:02
And the third aspect is assessment. So sometimes with becoming older it goes along a diminishing physical or mental capability and there is a fundamental difference in my view about the two.
10:22
So the physical impairments is certainly something that you probably notice very easily, right? You find things harder. The danger with cognitive impairments or, for example, diminished mental capabilities
10:41
is that you might not notice it, right? You might forget things and so what? It doesn't affect you immediately but it affects you in the long run. So for that we need, of course, input from the outside. So these are the three supporting elements.
11:01
And the key word here, how some of the research in this area tries to tackle these is what is called ambient intelligence. And what is on the bottom of the slide is actually a phrase not I came up with but people usually refer to ambient intelligence in literature.
11:25
A digital environment that proactively but sensibly supports people in their daily lives. So what is this beast ambient intelligence? What are the features we are talking about? Obviously, you might have guessed, I haven't said so.
11:42
Could be all kind of things but as you probably know I come from computer science. It's a computer science lecture so it has to do something with computing, computer system. But what kind of computer system? It's a system where there's ambient intelligence in there to play with words.
12:01
So there's the artificial intelligence in there. So it's an intelligent system, computer system that's intelligent. But it's not disconnected from the world. What does that mean? It is sensitive and you probably might interpret the word in a way I don't mean it in this case
12:24
or researchers don't mean it in this case, it just means it senses the environment. It's responsive, it acts on the environment, it's adaptive, it has some transparency so you know what's going on and it is ubiquitous.
12:43
I finally managed to actually say ubiquitous, it's a difficult word for me. I was actually considering not to do research in this area because of this word. Right, so that's what it is. And people came up with more sophisticated definitions.
13:02
I just put up this slide so those of you who really want to know more about it, there's heaps of literature around and some of the definitions tick certain boxes. So in this column, the S-R-A-A-T you might have guessed is what was on the previous slide, the sensitivity, responsiveness, adaptiveness, transparency, ubiquitous intelligence
13:22
and some cover more and some cover less aspects on there. So how do we go about this? Well, we try to create a computer system that can act, sense, reason about the world
13:42
but we don't just want to do it in any way. There are various aspects that also play a significant role and it's sometimes overlooked. One is the what is usually called human-computer interaction and you probably have a feeling of what that means
14:01
but what does it actually mean in a system that's ubiquitous? I actually haven't said what ubiquitous is. Ubiquitous is you don't see it, right? It's all over the place. And then it makes sense. You don't want to have your R2D2 standing in a corner or something like that, your mainframe.
14:20
You don't want to see it. It doesn't want to intrude. You don't want to have the system intruding on you. So it needs some, but you want to interact. So traditional computer interfaces really don't do it, right? You can't expect an older person to go to a terminal all the time and use the mouse and select something.
14:40
That is disruptive. So we need to find new ways of interaction with an ambient intelligence. And the other thing is security. People are usually quite concerned about their privacy, right?
15:05
People are usually concerned about their privacy. Although they don't act on it. Just to give you some idea, security cameras or internet security cameras are quite a hype nowadays.
15:21
Who in the room has an internet camera? Yeah. Yeah. Makes perfect sense. I installed one in my house. My daughter's living with us sometimes. The parents are not at home and she gets frightened. Living in Palmy. It's not as populated, so you can feel a little bit,
15:41
oh, is there somebody out there? We saw it in the camera and I looked around and I got one and then I just browse to familiarize myself with new issues around it and so on. And it turned out it's amazing of how many security cameras you can access through the internet.
16:01
There's a site in the US and it lists security cameras. So you can look into living rooms, into garages of people. How does this happen? Well, you buy this security camera, right? Where do you buy it? Don't want to name a particular provider in New Zealand, nor overseas.
16:21
Maybe you get it somewhere brought in from overseas, by email. Per mail, sorry. You install the thing, it works, you're delighted, perfect. Well, these things come with standard settings, right? One of the standard settings is the standard password.
16:41
And there are not so many manufacturers and they are not very creative about their passwords or logins. Let me guess. If you go into your router, right, who logs in with admin?
17:03
Yeah. Because you are so proud to be an admin? No, because people call it admin. So if I have to guess, that's the login, right? Now, up to probably a year or two ago, when you bought a router from one of the major providers in New Zealand, it had a standard password.
17:29
Recently they changed it and now the standard admin password are the last so and so many digits of the serial number of your modem. So at least it's personalized.
17:40
So if you don't bother to change that, I know your password. So I can log into your router, right? I open the port, perfect. Your camera has the same password anyway and one of the favorite passwords for the camera seems to be 12345678. Okay, there might be another password.
18:03
And the same thing of course in principle can happen in ambient intelligence. So let's look at something which is a little bit more straightforward, which is the sensor side of ambient intelligence.
18:27
I have to catch my breath a little bit, keep my voice up a little bit difficult. So I can perhaps say something with a lower voice. Robert mentioned the weather.
18:41
He actually ordered that, especially for me, me from Palmerston North always being windy in a windy area. So he ordered some wind so I feel at home. Very good. Okay, so what type of sensors do we actually use?
19:00
You are all familiar with sensors to some extent. If you come home, I guess most of you have security light around your home, right? There's a sensor in there, passive infrared sensor, switches on, perfect. We have other sensors instead of motion sensors. So what we could sense as well is light and actually your sensors in
19:23
your security lights do that already because they don't switch on usually during the day. Some form of radiation, temperature, all kind of things. We can of course have a sound sensor if there's noise in the house.
19:41
Another thing is solids, liquids and gases. So think about the tap running. How do you notice that? Well, you put something in the pipe and if flow goes through, it senses this and the system recognizes the tap is open.
20:04
Now we had an interesting project. I get a little bit sidetracked, but I'm hoping that this is making it easier for you to relate to this type of technology. We had an experiment in Palmerston North of an elderly gentleman in his 90s, blind, living independently in his home and we equipped the home with sensors.
20:27
Now the problem is, although there's kiwi ingenuity, there are a few things you can't do in New Zealand. So you can't just go in as a computer test and cut the pipes.
20:41
First of all, it's not good anyway, but even if you think you can fix them later on, put something in there, it's not legal. So one of my colleagues invented something that listens to the pipe, a little device we just glued on and looked for noises. And he did some other things to filter out, for example, voice, which is a different form of noise.
21:06
So you can do quite a few things to get around the problems. Okay, the last one, I haven't mentioned position, direction, distance and motion. So one thing we are currently doing is trying to track people in their movements,
21:25
because these movements might give us an indication of whether something is wrong with the person. Now, of course, this is a non-trivial task, a passive infrared sensor doesn't really do the trick.
21:41
What people usually do nowadays or what has been suggested in the literature and also in experimental setups around the world is putting pressure sets into the floor. So these are pressure mats and they recognize if somebody steps on that. This is actually a nice thing here, there are no pressure mats in this floor.
22:02
I was expecting one because this is recorded, this lecture, and when we do that at Massey University, we have to stand on the pressure mat and the camera zooms in and as soon as you go off, the camera zooms off. And if you are a very movable person like I am, because a student recently complained, not to me, to a colleague of mine,
22:22
with a short message, you are making me sick. Alright, so these are the sensors. Then the question is, well, they are all quite limited, right? They just sense certain aspects. How about cameras? Talking about cameras.
22:42
Well, people usually are not happy to have cameras everywhere. They are, at least in some places, perceived as invasive. Thank you.
23:03
They are, although the prices have dropped quite significantly, they are more expensive than these cheap sensors. So if you talk about infrared sensors or just sensor doors, they are less expensive. And because you get an image, it doesn't necessarily mean that the job is done.
23:26
And I have the pleasure to have some in the audience who are quite familiar with computer vision and they built whole careers on this and not, definitely not because it's a trivial task.
23:40
So just having cameras doesn't do all the work for you. And it turned out, depending on what you want to achieve, it's not really essential. Okay, so the other aspects you need to consider is wired versus wireless sensors.
24:01
And there are various pros and cons. Wired sensors are usually a little bit cheaper, but you pay for the wiring. And if we think about getting smart home technology into houses in New Zealand, we can't just wait until all the houses have been replaced with new houses that have the equipment wired in.
24:24
And retrofitting houses, although I can tell you retrofitting anything in a New Zealand house is easier than in a house in Germany because you don't have to drill into concrete and do things like that. You can usually access the space over your living room and things like that, but it's still an effort.
24:44
So wireless is a little bit more expensive, but it has downside circuits, used batteries and so on. And possibly it's not as robust. Again, a trade-off people need to consider. Now, reasoning.
25:02
This is actually where my work lies. I am not an electrical engineer, so the sensors we use are usually out-of-the-box sensors, except for the little developments my colleagues do. I'm interested in reasoning, so making sense out of what comes in from this huge amount of sensors.
25:22
So in this picture, which is incredibly small, I realize that. Which is really amazing that I put something like that on my slide. I had a talk yesterday to my students, how to avoid presentation mistakes.
25:40
And I was just thinking, oh, okay, this is number 12 at least that counted so far. Anyway, the first one is actually not being anxious, but when I stared at this room at the beginning, I was kind of terrified.
26:00
But I'm also at the same time very delighted. So these are sensors. What do these sensors produce? These sensors produce some form of data. They transmit some form of data. This data goes into a magical box. And this is our ambient intelligence. This is essentially a computer system.
26:23
And it's amazing what you can do nowadays on small computers. So we're not talking about these rooms full of machines. Even with simple, very small computers, you can achieve quite a bit. Some of you are familiar with Raspberry Pi, I guess. Quite a few interesting projects you can do, and we let our students do.
26:46
Which already goes in that direction and provides some aspects of ambient intelligence. So out comes some recognition of some activity. So let's say the ambient intelligence says, oh, yeah, the older person in the house just got up and is preparing her breakfast.
27:09
And with this information, we can do various things. We can just ignore it if it's a normal activity. Or if it's an unusual activity, let's say it happened at 2 o'clock in the morning, we might give some support.
27:23
For example, calling a carer. So that's the general idea of the flow of what we want to achieve. Now, we call this activity recognition. Some people call it behavior recognition. I don't know which is the most more appropriate term.
27:44
So we want to first find out what is going on in the house. Now, what we get is something similar as shown on this slide. This could be a typical data stream, so really row by row.
28:01
So in comes a signal at approximately 5 past 6 that in the living room, the television was switched off. And the curtains were closed about three minutes later. Things like that come in. Of course, if you look at that, it doesn't, well, it might tell you something.
28:22
But if your computer system looks at it without any reasoning process, it doesn't tell you anything. It's just data. It's no information at this stage, no knowledge that comes out of it. Data that comes from the census is not, these observations are not activities.
28:40
So we need to think about how we turn observations into activities. How we can map a sequence like this to the occupant is making breakfast or having a shower and so on.
29:02
This might sound easy, but it's actually incredibly difficult. And there are various things that get in the way. And one thing that gets in the way is variation. Luckily, it doesn't get in the way completely because people have their habits.
29:26
And it's amazing what kind of habits people develop. But in principle, if you think of a simple task like making a cup of tea with milk. So do you put the tea or the coffee into your cup first and then the milk or the milk first and then the coffee?
29:47
It might not be the best example, but you can see there are variations in there. If you have your bathroom routine, do you brush your teeth first and then shave or shave first and then brush your teeth? Who knows? So the observations as a result of that might be quite different.
30:09
Second thing that gets in the way, interwoven activities. What does interwoven activities mean?
30:21
It means that sometimes we interrupt an activity and do something else. For example, if you put your clothes in the washing machine, I guess you are not switching it on and then you stand in front of the washing machine and wait until it's finished. Most people don't do that, I think.
30:43
They do something else, even if it's just having a cup of coffee. But that gets in the way because the cup of coffee has nothing to do with doing the laundry. Unless you think doing laundry is really a ritual which involves coffee drinking, but it could be something else you do in between.
31:04
Most people actually do. So if you look at the observation, what really fits together is just the part, the observation that belong to these orangey arrows on the slide and are labeled laundry. Whereas there's something in between, making coffee.
31:21
So we need to take care of that. And one thing, we did this and now it becomes technical. Hidden Markov model. Who are familiar with hidden Markov models? Wow, that is great. I wasn't when I started. Well, I wasn't a long time ago.
31:42
But, okay. So it is what is called a probabilistic model. Hmm. Probabilities, you have probably heard about probabilities. Probably have heard about probabilities. Blah, blah, blah. Probabilistic. Yeah. So it's something that's not quite certain, right? You toss a coin and there's a 50-50 chance that you see head when it comes down.
32:05
We know all these kind of things. So somehow this approach incorporates probabilities. Sorry about you guys who already know about hidden Markov models and now bored to death. Okay. For you, I have this slide.
32:21
The rest ignores it. So what does the hidden Markov model actually do? Well, imagine yourself getting blindfolded. Okay? And I put you in my car, which I haven't here. But let's say I had a car here.
32:42
And I drive around and we get out somewhere in Auckland and you get certain signals. Okay? So let's say you heard some church bell ring. Okay? Then we walk along and you hear a ship horn.
33:04
Right? And you walk along and you get some other input. Maybe you smell something funny. So what do you do? The first thing you probably say, where the heck am I? Right? I don't see anything.
33:21
Where the heck am I? Okay. Could be any type of places. Now Auckland is a better example because there is a huge number of places. But let's say it was somewhere in your house or in a restricted area. You probably say, oh, okay. I could be either in my garden or I could be in my living room or I could be in my kitchen. Okay.
33:41
I don't know. Probabilities. But then you get observations in. Suddenly you hear something. The ship horn. Suddenly you think, ah, so I must be now at the harbour. And you develop a model over time. We call states.
34:02
That's where you are. And we want to find out, or in your process while being blindfolded, you want to find out what I have actually done with you in Auckland, where I led you. And you might or might not be successful.
34:20
At the end you might answer, yeah, I know you dropped me off Upper Queen Street. Then we walked down Queen Street. We ended up at the Ferry Building. Then we went to, I don't know, the bridge and so on. Or you might say, well, we could have been Upper Queen Street
34:41
or it could have been some other street in Auckland, right? And it could have been 50-50 chance. But then something else happened. So I think in the end we ended up through that particular sequence. That's what the Hidden Markov Models do. So what does this have to do with activity recognition?
35:00
Well, so I skipped this. There's just a few features why we use these. Let's go to this slide. It looks very technical, but it's not really. So on this, what is this colour? It's a pinkish.
35:21
In the middle you see these O's. So here come your sensor data, right? You see the cupboard door opening, the fridge door opening. You see some activity in the living room and so on. So this is a signal to our system. So our system does the same thing you did in Auckland when being blindfolded. It's blindfolded, but it makes some assumption.
35:42
And it tries with these Hidden Markov Models to find a good match for a part in the observation. So this is what this in principle is about. There are a few things to consider because this comes in as a flow. So at some stage the activity changed, so we need to find the right window.
36:02
So there was a little bit of research around this. So when is it actually relevant to listen to certain hours, to certain sensor information, and when do we stop? But you can do a few tricks, and it's quite a successful approach. So after this, then we have a good idea of,
36:22
hopefully a good idea, for what is going on in the house. Of course these things have to be trained. Trained means in AI lingo, you just observe people in the house and you tell the system, like to train or teach a human being
36:42
what certain observations actually correspond to. Let's call it the ground truth. So we say this type of observation is actually breakfast. But at some stage we of course stop this and we expect the system to actually do the job on its own.
37:05
Okay, right. So this gives you some idea of how you can do it in principle. Now, what does it actually tell you? Well, it tells you some things. For example, if you don't observe that a person has used a shower for a few days,
37:23
you could imagine that this might be something that is not acceptable. Or maybe it is. Depending on your lifestyle, I shouldn't really jump to conclusions here. Okay.
37:40
But you see where I'm coming from. So certain things that are missing, you could interpret as abnormal and potentially dangerous. The same thing the other way around. Things that happen too often. So let's say a person opens the fridge every two hours, 24 hours.
38:04
Maybe there is some eating disorder going on, right? Or maybe the person prefers white wine over red wine, which of course you keep in the fridge. But again, then every two hours, 24 hours might not be something you want to accept.
38:21
But there's a more subtle way of things. Unacceptable abnormal behaviors. And that's behaviors that happen in the wrong context. So having, for example, dinner at six, seven o'clock at night, quite perfect.
38:41
But if suddenly you realize the dinner is taking place at eleven o'clock and the next night at two o'clock in the morning, it's still the dinner activity, which is perfectly fine, but the context is wrong. Or let's say the person puts on the heater and is in the middle of summer. Now this is an incredibly bad example given the late summer,
39:03
at least the Bahamas north one. Okay, so I will think of better examples, sorry about that. But you see, out of context can, context information, so that's spatial information, everything with where are things happening,
39:20
do they happen in the right place? So taking a shower in the bathroom is quite normal, but outside is not so normal. Temporal information, we had that example, emotional states and so on. All this information can feed in and then either can boost the recognizer process, which I haven't referred to,
39:41
but what I refer to is to recognize abnormalities. So that's the idea. Then the next question is, how do we do this? So we're now moving on from activity to context. So the image that we have in mind is to use context maps.
40:04
These are maps where we record when certain things happen. So let's say you have certain activities, lunch, watching TV, ironing and so on, and they happen at certain times. So whenever we observe that somebody is having lunch,
40:21
we record which day it is, which month it is, which season it is, in which room it happens and so on. Now, the thing that's important here, when we talk about temporal data, it's not just a timestamp, right? Because some kind of abnormalities happen
40:43
because they happen at the wrong time of the day. Some abnormalities happen because they happen on the wrong day. That you suddenly do things on the weekend you did during the week, or during the wrong month or the wrong season, right?
41:00
So we have to distinguish between these. And the same holds for spatial data. Now, in the following, I just mentioned a few things for those who are familiar with techniques of AI. So there are various, again, probabilistic models around
41:21
based on neural network approaches, and one keyword here is Boltzmann machines, for instance, a particular type of approach that can be used for that. However, I would like to go into something
41:42
which I think is a little more intuitive and perhaps easier to get your head around with. Because this Boltzmann machine, again, like the activity recognizer, you train and you hope that something is coming out that is right. And in most cases, that is the case, and sometimes not.
42:05
So let's forget about all this stuff and say how would we actually, in a naive way, tackle the problem? And let's get back to these probabilities. So I'm now assuming that you're all familiar with probabilities, right? I don't assume anything.
42:28
So what is A and C and P? So it's the probability of something happening. A, activity, and C, context.
42:40
What is the probability that an activity happens in a particular context? It both happens. So there are all these formulas around, and you don't have to really be bothered about it. But what we're actually interested in is what is on the bottom line, which is so-called conditional probability. And there's some way to calculate this, which I've put on there.
43:06
Conditional probabilities. What is a conditional probability? Well, a conditional probability, how can I best explain this? It's difficult enough. So we had the coin, right? That was a simple probability, tossing a coin. Okay.
43:20
Let me try to find an example that brings it closer. One day, a man was caught when entering the aircraft because he was carrying a bomb. And of course, nowadays the assumption is tasked with T, ends with Ist.
43:48
Right. But this man had a perfectly valid explanation. He said, I read in the newspaper that there's a certain chance
44:01
that you enter an aircraft and there's a bomb on the aircraft. But it's very unlikely that there are two bombs on the aircraft. So I thought, if I carry a bomb on the aircraft, I'm safe. Conditional probabilities.
44:20
Right? So this person didn't know anything about conditional probabilities because the conditional probability is actually the same as the probability of one bomb on the aircraft. So the conditional probability of two bombs, given that I'm carrying a bomb is similar. Right. That's what conditional probabilities are about.
44:41
Sorry, not bombs, but that kind of stuff. Okay. So we would need them because we want to condition the activities on our context, so given that it's a Monday, what is the probability that the person does the laundry? The problem is, you need a lot of these.
45:03
And you need to calculate a lot of these. Or first of all, you need to observe a lot of these. And that's, computer scientists are notoriously lazy, so they don't want that. So we need to find something else. So they came up with something that is called a Bayesian network.
45:25
What is this beast? Again, probabilistic graphical model. But I give you an example. This example is in the middle of the slide. So what does it mean? I know something. I know A.
45:40
And A influences B. Okay. Let's say A is me carrying a bomb. B is a bomb on the aircraft. Now think smart homes. A is observing that the light goes on in the living room. B is me watching TV. So obviously, the lights going on or the TV goes on
46:05
has an impact on how I feel about whether I would assume that the TV is on or not. Other things don't. So if the security light goes on outside,
46:21
it doesn't have an impact on whether the TV is on. We would say they are independent. So that's what people call conditionally independent. So in this case, E is conditionally independent of all the stuff that is not directly related to E. So that's the, in a nutshell, what Bayesian networks is about.
46:45
I hope there are not too many people familiar with Bayesian networks in this room because otherwise I have trouble when leaving this room because they will tell me this was too, it was not right. But the reason I'm trying to give you the idea of it
47:01
because I now want to build one. So how do I do that in the smart home context? Weekday weather season. We have our behaviors, watch TV, ironing, lunch at home, and we have sensor readings. The TV is on, the iron is on. So let's say you have a little sensor in your iron
47:21
and on your TV. So we create something that mimics what is going on in the smart home. So here's an example we made up. Mary goes out for lunch in summer if the weather is fine, rarely in spring, autumn, and nearly never in winter.
47:41
Easily to imagine, right? So if it's nice, nice to go out. If it's not nice, you don't go out. We all know TV program isn't all the same every day, so maybe she prefers to have, in her view it's good on Monday and Fridays, sometimes on Saturday and Sunday, and if she thinks otherwise, not for her.
48:01
She would iron while watching TV, rarely during lunch, nearly never otherwise. So if you have that kind of information and it's a little bit of a made-up and simplified one, we construct something like this. This is our very easy network, and I'm not going fully through this, but just to give you the idea,
48:21
there are these bubbles, nodes in there, and we have, for example, lunch at home, and that means that signals to us, behind this is a probability that we'll get a value. Yeah, it's likely, it's not likely. And that is influenced by the weather and the season. So when we run this network,
48:41
we run it, it does magical things. We've seen some calculations, and we suddenly get something like these tables there. And if we go back to the lunch at home example, suddenly you say T0.78 and F0.22, and what that means is, there is roughly a 25% chance that this is not the case,
49:06
and 75% chance that this is the case, okay? So these are the things we get out of this. Now, just to, I skipped the next thing,
49:24
the details of the next slides, but one thing you need to consider also if you deal with probabilities is that there is a requirement that probabilities add up to one. Right, so if I toss a coin, there's a 50% chance that I have a tail
49:41
and a 50% chance that I have a head, so together I have a 100% chance that the coin comes down somehow. Right, that's, now, the problem is if you don't have information, complete information, this might cause trouble. For example, let's assume,
50:01
I don't know anything about your hygiene routine, which is really fair to say, because I actually don't know anything about your hygiene routines. So you ask me, what is my belief? Anybody of you can ask me, what is your belief, Hans, that I shower in the morning,
50:20
and I would say, I don't know, so I say, I don't believe it, it's zero. So you think I'm not showering in the morning, right? No, that's not what I said, right? It's just that I don't have any knowledge. Yeah, but if you say it, I don't, the opposite must be true, right?
50:40
No, not really. So then you say, oh, yeah, Hans, you did it all wrong. You should have said 50%, right, because if you don't know, like the coin, 50, 50 chance. Okay, okay, you ask me again. I say 50%. Okay, that's right. So shower in the morning, shower in the evening,
51:06
shower midday. No, the 50% don't work, right, because 50% in the morning, 50% midday, 50% in the evening. Wow, 150% that you shower at all.
51:21
Super clean. Okay, so message here is, there are formalisms that do that, you can use, and I skip these, that do all that stuff. Okay, and the last thing is, you could even talk about imprecise concepts,
51:41
as opposed to probability. Oh, now it's getting technical. Imprecise concepts are supposed to probabilities. What is he talking about? Okay, example. What is probability versus fuzzy logic? Okay, let me give you an example again. I want to talk about a fuzzy model,
52:01
and I want to talk about a probabilistic model, okay? And they both belong to their set with a probability or a degree of 90%. So what is the difference if I say, for example, a bottle contains portable liquid
52:23
with probability of 90%, or I say, I have a fuzzy bottle that contains a subset that belongs to the set of portable liquids with a degree of 90%. Is it the same? No, it's not the same.
52:40
So here's a scenario. A fuzzy bottle means that you filled it from a slightly polluted well. So it's not the best, it's not your New Zealand spring water, which we soon won't have anymore because I'll export it. But maybe you filled it from the tap, and that's reasonably good, right?
53:02
It's not your cleanest water, okay? So that's your fuzzy bottle. The probabilistic bottle is, I give you a ten-pack of Evian bottles, and in one of them is a poison that drops you dead. So here's the difference, right?
53:20
Both are 90% portable liquid, but some is a degree, some is a probability. So again, you can talk about this and rephrasing things in terms of fuzzy theories. You could ask, to which degree is a shopping event
53:41
a Sunday event? And you can play around with this and you get information. Okay, the last thing I would like to talk about is dependencies between activities, and then the formal stuff is over. So what we did is, what computer scientists often do,
54:02
they download from the internet some what is called data sets. So data sets is a kind gesture of other researchers that they make available observations they have made in their setup. It's very convenient, so you don't have to set up your smart home. You get these data sets, and one of the sets of data sets
54:22
is the so-called CASAS data set from the University of Washington. And we played around with this. They recorded a number of activities, and then we analyzed them, and not surprisingly, some activities follow other activities more likely than others.
54:43
So if you have a particular activity, let's say breakfast, it's more likely that the next activity is leaving the house because you go to work, and it's less likely that the next activity is going to bed. Well, I run out of sensible examples because whenever I say something,
55:02
I immediately think, maybe there are people who have breakfast and go back to bed, which is totally sensible, but anyway. So there are, given a particular individual, you have these dependencies. Okay, so that's the form part. So what is actually going beyond all this reasoning stuff? Where do we go from here?
55:22
Detect if an activity is normal or abnormal in a current context, and initiate a reaction. But how about privacy and security? Coming back to these topics that I had on one of the first slides. So what type of information will be gathered? Who will this information be shared with?
55:42
And how will information be encrypted and sent? So security. Where does it reside? And why is the information needed in the first place? And these, again, probably not from a computer scientist's point of view purely, but these are sensitive issues.
56:01
These are issues that have to be resolved. And there is actually a project, another project I'm involved in, but I'm really a little bit of an outsider here, because this is actually a project that's run from the business school, and sponsored by HRC, which is the Health Research Council.
56:23
And they want to look at how you can sensibly use that, and now we're using sensibly, not in the sense of sensing, but how we would use sensibly use, and how can you integrate it with social media technology?
56:42
So the picture, it serves as a metaphor for this project, is in the center is your elderly person in the smart home, and there's your circle of friends around, close friends, relatives, and then there are the wider circle, like healthcare providers, and so on and so on.
57:01
And they're all connected through social media and other things of communication. And the idea behind this project, or the question behind this project, is to find out which kind of technology is acceptable where and to which degree. And I guess one reason why this technology
57:22
hasn't really spread widely is that people are hesitant to just accept this technology. So to conclude, there's heaps of research, and I'm confident all of you are now so hyped up about it.
57:43
You will immediately go to the library, which I think is over there, and get the 10 newest publication on smart homes, and read the whole night about it. Tomorrow you go to any shop, buy yourself some equipment, and build your prototype, like many people all around the world.
58:03
Because there is no integrated package you can buy. We are getting there. There are still hurdles, things like standardization and so on and so forth. And again, this opens another new research area. But you can get already some smart devices.
58:22
For example, some of you might have heard about Nest. Just to give you one example, it's a controller for your air conditioning unit or your heat pump. And it learns how you control the temperature over time, and then does it automatically.
58:42
And of course, I focus on smart homes, but this is just one of the areas where this is used. This technology can be used. The other, of course, are smart cities controlling things in the city. For example, lighting.
59:01
Probably for somebody living in Auckland, not really an issue because the city is alive all night. But if you go to Palmerston North, the lights are on, right? But nobody's home. Everybody's home. That's the problem. So there's a lot of waste of energy, right? You light all the streets are lit. So it would make much more sense to keep a minimal lighting for security reasons.
59:24
But when actually traffic picks up, especially in more rural areas, the lights come on. A big thing for Massey. You probably know Massey University was an agricultural college before it long ago turned into a university.
59:42
So part of the heritage is that agriculture is a big thing, Massey. So smart agriculture, or what some people call precision agriculture, is a hot topic. And smart retail. Amazon perhaps brings...
01:00:00
Well, there has been some discussion recently in New Zealand and Amazon. So there's a lot more. And with that, I should really stop and thank you for your patience. And it was a pleasure talking to you. Thank you.
01:00:24
We do have a little bit of time for questions. So if there are questions, a hand jumps up in the back. Yeah, please. There's a very big difference between an elderly person who wants to live and an elderly person who wants to die.
01:00:48
Yeah? I'm going out on a limb here a little bit because I'm not an expert. I'm not a psychologist.
01:01:01
But reading a little bit in a wider area, so one of the issues is actually emotional state and stress that people have through these diminished capabilities. And they go hand in hand. What you just mentioned, the extreme case of the wish to live or the wish to die,
01:01:21
is sometimes influenced by these factors. And not only that, sadly, it also influences the person who is healthy, so the person who takes care of a person with diminished mental capabilities. There are studies that there is a higher probability
01:01:42
that they will die. Now with this technology, this technology by no means make a decision about these issues. But it might help to ease a little bit on the emotional stress that people
01:02:01
suffer through the onset of diminished mental capabilities. Because if you don't want to go to a retirement home, and there have been studies that people actually want to live in their own home, then the prospect of that might make things even worse.
01:02:21
It might actually lead to an extreme, like you just mentioned, that the people switch this from, yeah, I'm happy to live, to I had enough. So it could. But I don't have strong evidence about it. I don't have data to back this up. But I know that others actually do work in this area
01:02:41
that I think was in Germany or some other European country where they actually build retirement homes where they equipped the rooms in a certain style, let's say the 50s or the 60s or what people are familiar with. And the reason being, if you suffer from dementia,
01:03:02
what goes are more recent events. So you suddenly feel not at home in a modern environment. But if you recognize the room you have lived in or the style you have lived in as a kid or a young adult, it eases. So they're pursuing the same goal,
01:03:25
not easing the stress on people but with different approaches. I hope that answers some of your question.
01:03:41
Some reasonable probability of events. So I remember seeing something down there. I think there's a Japanese product, which is just the kettle. Yeah. And the only thing that sits in the house is kettle. And that was good enough for a lot of people. I reckon that mom and dad had put the kettle on three
01:04:01
times a day, and they were OK, you know? Yep. Mm-hmm. Yeah. Does it actually work on how many senses are enough? Right. The sense is much higher. Mm-hmm. Not much. A little bit. So there are two issues. One is driven by what goal do you want to achieve.
01:04:23
So if it's just a particular assurance of something, let's say you know that a problem would be that a person doesn't drink enough or doesn't do a certain thing enough, in a particular sense, I might give that indication. It certainly doesn't help you to,
01:04:42
it's not enough to recognize complete activity, what kind of activity is going on. So from that point of view, it's not sufficient. As part of this project with the Hidden Marker or there was a PhD project, in the last phase, the student actually tried to answer this question.
01:05:03
And the way to answer this is you have a set of sensors, so you go the other way around. You throw everything into the house, so full throttle, so everything. And then you analyze the information gain you get from a computer science point of view with each of the sensors.
01:05:23
So in principle, the same thing you do with decision trees. And then you try to find a set of most informative sensors. So that was the idea behind that. And there was limited success. We didn't get very far with it, unfortunately. But it's a very relevant question, actually, yes.
01:05:42
Because we want to keep the cost down, right? So innovation and privacy, computational resources, and so on. Yes. Yes. I felt like we changed the parts. And there was enough assurance for humans to know that at least they were in the back.
01:06:06
Yes. Well, I think that's absolutely correct. And in a certain way, these pillboxes are pretty much the same. They focus on one aspect. Because if there is an issue, if that medication is really essential, and that's what it's all about, this does the job.
01:06:28
I am more than happy to share them. Yes, I don't know what the logistics were. I'm putting up the slides of the lectures where they shared. So they'll be on the Gibbons website. Excellent. Great.
01:06:43
Yes. I'll just briefly. Firstly, I've had done a few attempts at data gathering for domestic related stuff a few years ago. Yes. As a whole, I'd like to have you shut up to address it.
01:07:00
OK. I might just need permission of the people. OK. Secondly, I still have my old HCI assignment for Massey in 1992, which was, I think, part of the gap at the time when we attempted to publish it at the time. Is there any possibility of a possibility of publishing it?
01:07:24
Well, out of blue eyes, difficult for me to say. But if there is still something in there that's novel, sure. But it's something you need to look at in more detail, of course. Because field progressed quite dramatically in 1992.
01:07:42
Here we are with the 25 years ago. OK. Can I ask you to join with me in thanking Thomas. Thank you.
01:08:02
And this isn't the end of it. Next week, there's another one. So Marcus Freeman from Victoria University is going to be here talking about deep learning, whatever that is.