This article shows an interesting approach to predict the user movements registering the user’s position through a GPS. The starting point is that for any technology to be useful the system must have a knowledge of what the user will do, where or when s/he will do it and the reason for the action. –In my case I am looking for the description of the place rather than on the user’s behavior.– The approach they followed is interesting and exemplar, because it is build on simple assumption, which are mainly inferred conjectures: a person who stops for a couple of time at a certain places may have particular interests there, therefore the place is a location. [other examples: stopping time marks the end and starting point of a trip (Wolf); loss of GPS signal is a building (Marmasse)]. On the application side there are several ideas proposed by the authors: spatial to-do-list: associate a task-reminder at a particular location; another may be the task sharing with other peers or the proximity-help-optimization: a friend is near a place you cannot go to pick up something and you ask for help; find people with similar interests based on physical proximity of certain preferential zones (Social Net – Terry). The goal they started with was to find a technique that would automatically pick out patterns in the data that would normally mirror what we observe about human movement. Then they reconsidered to aim for providing some starting inputs into the system that eventually would give some results. Their initial definition of “place” is interesting: any logged GPS coordinate with an interval of time “t” between it and the previous one. In addition they also did something interesting for defining statistically the notion of location and sublocation: they did clustering using a variant of the k-means clustering algorithm. They also used user inputs to enhance the identity of the space for the extent to verify the outcomes of the algorithm with the user’s expectations. The experimental model, though, I found weak. The conclusions is that they proved the possibility to detect space structures but their goal was also to detect time structures. They used a system called GPSVis to log data.
Monthly Archive for June, 2004
Page 2 of 3
Reading the article about epistomat I found the missing link for my thesis project. Basically the idea is to give the user the ability to validate the ontology defined by the agent so that they collaboratively participate to the social meaning construction. In this process there is also an informal learning.
See the link with the Nomic game.
(0)He is a philosopher, a university teacher and a researcher. He designed the game Nomic. He is also involved with the Open Acess project.
[more ...]
Nomic is a game invented in 1982. It’s a game in which changing the rules is a move. The Initial Set of rules does little more than regulate the rule-changing process. While most of its initial rules are procedural in this sense, it does have one substantive rule (on how to earn points toward winning); but this rule is deliberately boring so that players will quickly amend it to please themselves.
[more...]
OWL is an acronym for Web Ontology Language, a markup language for publishing and sharing data using ontologies on the Internet. OWL is a vocabulary extension of RDF (the Resource Description Framework) and is derived from the DAML+OIL Web Ontology Language. Together with RDF and other components, these tools make up the semantic web project.
wikipedia
OpenCyc is the open source version of the Cyc technology, the world’s largest and most complete general knowledge base and commonsense reasoning engine. Cycorp, the builders of Cyc, have set up an independent organization, OpenCyc.org, to disseminate and administer OpenCyc, and have committed to a pipeline through which all current and future Cyc technology will flow into ResearchCyc (available for R&D in academia and industry) and then OpenCyc.
[more ...]
In computer science, an ontology is the attempt to formulate an exhaustive and rigorous conceptual schema within a given domain, a typically hierarchical data structure containing all the relevant entities and their relationships and rules (theorems, regulations) within that domain.
wikipedia
An ontology specifies the way that people interface with information. In computer science, an ontology is the attempt to formulate an exhaustive and rigorous conceptual schema within a given domain, a typically hierarchical data structure containing all the relevant entities and their relationships and rules (theorems, regulations) within that domain. (wikipedia).
The core idea of this paper is to use a predefined ontology defined in OWL as bootstrap for a world model to use in an interface. Then the paper focus on the idea that the connections and word of the ontology have to pass through a social process which will rate them and will give consent to them. They extract this principle from a game called Nomic. In this game players start with a predefined number of rules which progressively change during the game. The way new rules are applied is through a voting process.
In the author’s view the same system may be used to evolute the ontology used during the bootstrap of the interface. In my vision the action-series of the user may be the intentional subscription to the vote. This process is then very close to a social meaning process. In addition while the group give meaning to the ontology, also the peers of the group are learning how to assign these meaning though a democratic process. To highlight the informal learning process which takes place when different worldviews are negotiated by the consensus process.
Garage Cinema is doing research about Mobile Media Metadata. From their Internet site:
Our research is about making video a data type that humans and computers can create, access, process, reuse, and share according to descriptions of its semantic content and the principles of its syntactic construction. Our research aims to make this process as effortless as possible. Prof. Davis discussed the outlines of this agenda in an invited article for the 50th Anniversary Issue of the Communications of the ACM (Davis 1997).
[more...]
This paper describes the Mobile Media Metadata System, which creates automaticaly a description of the content of pictures taken with SmartPhones from the context in which the picture was taken. Two features of the system are of particular interest: a) the annotation of the images is collaborative; b) the contextual metadata is built from the social interaction the user has with his/her peers.
In this context one of the most interesting aspect of this study is that a mean for an image can be taken from the way a picture is shared and reused in the group. For instance it is possible to infer the social context if the peers happens o be in the same cell at the same time and use this information in combination with others to know if the one of the peer is likely to be in the picture.
Again, is possible to infer spatial context from the cell id and time stamp of a picture. For a pedestrian, for example, is likely that two pictures represents the same area if these are taken with a couple of minutes of difference to one another.
Unfortunately the article does not go in details of the implemented algorithm. So it is not possible to know which strategies were used and how much to rely on those. Certainly they did not implement and machine learning algorithm.
Interesting link to the work of Toyama from which they took the idea of bootstraping contextual information from the header of the JPEG image.
Great brainstorm session today at CRAFT. We played attaching messages to a map of Lausanne. This can be an initial step in building an ontology of spatialised communication. Some ideas are here reported:
1. Maybe is possible to concatenate the messages so that the receiver can retrieve the follower once taken the one before. This can be achieved giving the user the possibility to set the spatial range at which the message can be retrieved.
2. A spatial wiki approach may be taken. We can give control to the participants to comment, rate and override messages.
3. We can use vector landmarks that shows the intentional direction of the emitter.
4. We can envisage an approaching alert to be used in a crowd scenario.
5. Gaming application.
From the evaluation of this activity I realised that it is difficult to relate the message with the position unless you can see the historical trace of the emitter. We have to consider that retrieving the message is asynchronous so by the time you retrieve people can have moved. From Nico’s descritpion:
…we tried to sketch out possible uses: recommending system (good/bad), help, threaded discussion, wiki-like (to reach a consensus), reminder system, spam/virus/breakdown, I’m late, anchors (like rave party system), synchronous/asychronous use, query (anybody wants to paly tennis here?), crowd scenario…
Other interesting comments about a possible criteria to categories the messages depending on the retrieving time (limited / unlimited) versus the receiver (one-many / range limited / everybody).
I presented the ideas I had to Pierre. The comments raised during the conversation concentrated on the definition of an initial ontology. He said that the kind of reasoning I am expecting is too advanced for machine learning. The kind of A.I. I am considering in the project is too far into neuro–network connections.
Something to do includes:
1. We have to know an initial ontology to start defining our algorithm;
2. We need to imagine what it could be;
3. What are the data we can take automatically from the system that mean something for the ontology?
WordNet® is an online lexical reference system whose design is inspired by current psycholinguistic theories of human lexical memory. English nouns, verbs, adjectives and adverbs are organized into synonym sets, each representing one underlying lexical concept. Different relations link the synonym sets.
Prof. Kuhn is a professor at the Institute for Geoinformatics at the University of Münster; and a lecturer (Dozent) at the Department of Geoinformation at the Technical University Vienna.
From his site:
The fundamental question underlying my research is how the meaning of geographic information can be mapped from one context to another. Typical contexts are human activities, professional disciplines, or natural languages. Contexts are ingrained in human minds, data models, user interfaces, business models, laws and regulations.
Recent Comments