I am getting the gps position and time of a voluntary person which moves around. I am acquiring the position every second with Matlab and save it in a matrix.
Now I would like to be able to say if the person is moving normal or not. For example running in circles is not normal for a person who usually only walks around.
I am not looking for a complete solution because I would like to learn through my project and understand every aspect. I would be very grateful if you could show me the right direction. Good literature, tutorials and simple catchwords would also be very helpful for me because at the moment I dont know how to approach my problem.
Thank you very much in advance!
Kind regards,
Tom
What you're looking for is anomaly detection. The primary commercial application of this technology is in fraud detection. As for pointing to resources any books that cover data mining should have a section about anomaly detection.
Something to for warn you about, it sounds from your description that you will be working with time series data which is its own branch of data mining.
Catchwords: Anomaly Detection, and Time Series Data.
Books: ISBN-13 978-0321321367 Introduction to Data Mining (This is a good starting point if you don't have a lot of background in the subject)
Related
Hope you're alright.
For the last two weeks, I'm trying to find one algorithm for generating procedural cities/towns on a grid system. I'm more focused on the road network than buildings, nature etc.
I've tried L-System (following this tutorial series on YouTube: https://www.youtube.com/playlist?list=PLcRSafycjWFcbaI8Dzab9sTy5cAQzLHoy) and some modifications of maze algorithms (explained here: http://weblog.jamisbuck.org/2011/2/7/maze-generation-algorithm-recap), but no success to react what I want.
Searching more, I found this old thread Generating a city/town on a grid (Simply my approach) where that guy created an algorithm that makes exactly what I want. Now I'm trying to understand (and, maybe, simplify) that algorithm to rewrite it on Unity game engine.
So now, I want to know if someone knows other algorithm(s) that makes something next to this: a city/road network based on a grid.
Thank you for your help and for sharing your knowledge! This project is part of my graduate thesis and, if you can help me, I will be very thankful!
I'm trying to train a classifier to detect a fall based on accelerometer and gyroscope data. However, I'm having a hard time determining what type of algorithm to use.
This is a picture of some of the dataset:
This data is an example of raw x-,y- and z-coordinates read from the accelerometer during a fall. As you can see, the data is relatively steady until the point where the fall begins.
My question is: what classifier should I use to detect the fall.
I've read some research in the field, where the scientists used Naive-Bayes algorithms to classify the data, but as I understand it, Naive-Bayes doesn't take into account the previous datasets in the classification.
I thought about using an HMM, but since I'm quite new to machine learning, I thought I'd ask for some general guidance.
Thanks in advance.
You should look at Conditional Random Field (CRF) which can be used as a classifier to take "neighboring samples" into account. If you do some google search, you should be able to find some papers about "fall detection" with CRF.
As you mentioned, HMM is also an appropriate model for your problem, in which you have a hidden variable (fall or not) but unobservable (only x-y-z coordinates are observable).
Salient object in an image is that part of the image where all the human attention goes and rest part is mostly ignored by the vision of humans.
i wonder why many people researching about saliency. i can't get enough illustration how saliency would be any of use to human in the world. could u give me any example that describe usefullness of saliency?
This is not the place where you should ask this kind of questions, because here we can help you with problems in your code...
But anyway, I will try to explain it. From Wikipedia:
Saliency detection is considered to be a key attentional mechanism
that facilitates learning and survival by enabling organisms to focus
their limited perceptual and cognitive resources on the most pertinent
subset of the available sensory data.
So in order to survive you use the visual saliency. In an primitive world, suppose you were hunting. If anything moved in the forest the saliency generated by the movement would made you react immediatelly.
Examples:
Suppose you are driving and suddenly a truck appears.
You react immediatelly because of the saliency generated by the
moving truck.
Suppose you are driving and suddenly a cyclist appears
(wearing yellow clothes). The saliency focus your attention in the cyclist and you slow down your car.
You can learn a little bit more here.
I have a robot that I need to write an autonomous program for. The program is to play on this feild: http://www.vexforum.com/wiki/index.php/Gateway.
and pick up the balls and barrels and put them in the cylinders(goals). I have sensors like light detection(best for following white line on ground or keeping track of location by noticing when you cross a white line), ultrasonic sonar, bump sensors, and encoders(count amount of wheel rotations). I want to make a program where the program learns the field and learns how to navigate best with the tasks at hand. I am thinking a neural net is my best choice but I can't think of what inputs I would use. The main thing is I don't want scripted paths. I know this is pretty vague but too much detail and no one would read this. Anyone ave any ideas?
Check out Udacity course 373by Prof Thurn at http://www.udacity.com/overview/Course/cs373.
He has successfully applied 'particle filters' to program the Google Driveless car
You need to use Simultaneous localization and mapping (SLAM)
It is a pretty standard and successful technique for robot localization.
Disclaimer: I'm not actually trying to make one I'm just curious as to how it could be done.
When I say "Most Accurate" I include the basics
wall
distance
light levels
and the more complicated
Dust in Atmosphere
rain, sleet, snow
clouds
vegetation
smoke
fire
If I were to want to program this, what resources should I look into and what things should I watch out for?
Also, are there any relevant books on the theory behind line of sight including all these variables?
I personally don't know too much about this topic but a quick couple of Google searches turns up some formal papers that contain some very relevant information:
http://www.tecgraf.puc-rio.br/publications/artigo_1999_efficient_lineofsight_algorithms.pdf - Provides a detailed description of two different methods of efficiently performing an LOS calculation, along with issues involved
http://www.agc.army.mil/operations/programs/LOS/LOS%20Compendium.doc - This one aims to maintain "a current list of unique LOS algorithms"; it has a section listing quite a few and describing them in detail with a focus on military applications.
Hope this helps!
Typically, one represents the world as a set of volumes of space held in some kind of space partitioning data structure, then intersects the ray representing your "line of sight" with that structure to find the set of objects it hits; these are then walked in order from ray origin to determine the overall result. Reflective objects cause further rays to be fired, opaque objects stop the walk and semitransparent objects partially contribute to the result.
You might like to read up on ray tracing; there is a great body of literature on the subject and well-understood ways of solving what are basically the same problems you list exist.
The obvious question is do you really want the most accurate, and why?
I've worked on games that depended on line of sight and you really need to think clearly about what kind of line of sight you want.
First, can the AI see any part of your body? Or are you talking about "eye to eye" LOS?
Second, if the player's camera view is not his avatar's eye view, the player will not perceive your highly accurate LOS as highly accurate. At which point inaccuracies are fine.
I'm not trying to dissuade you, but remember that player experience is #1, and that might mean not having the best LOS.
A good friend of mine has done the AI for a long=-running series of popular console games. He often tells a story about how the AIs are most interesting (and fun) in the first game, because they stumble into you rather than see you from afar. Now, he has great LOS and spends his time trying to dumb them down to make them as fun as they were in the first game.
So why are you doing this? Does the game need it? Or do you just want the challenge?
There is no "one algorithm" for these since the inputs are not well defined.
If you treat Dust-In-Atmosphere as a constant value then there is an algorithm that can take it into account, but the fact is that dust levels will vary from point to point, and thus the algorithm you want needs to be aware of how your dust-data is structured.
The most used algorithm in todays ray-tracers is just incremental ray-marching, which is by definition not correct, but it does approximate the Ultimate Answer to a fair degree.
Even if you managed to incorporate all these properties into a single master-algorithm, you'd still have to somehow deal with how different people perceive the same setting. Some people are near-sighted, some far-sighted. Then there's the colour-blind. Not to mention that Dust-In-Atmosphere levels also affect tear-glands, which in turn affects visibility. And then there's the whole dichotomy between what people are actually seeying and what they think they are seeying...
There are far too many variables here to aim for a unified solution. Treat your environment as a voxelated space and shoot your rays through it. I suspect that's the only solution you'll be able to complete within a single lifetime...