Using Location Data to Predict the Outcome of Emergency Calls

Slides:



Advertisements
Similar presentations
ECE 539 – Introduction to Artificial Neural Networks and Fuzzy Systems Henrique Parreiras Couto.
Advertisements

Alberto Trindade Tavares ECE/CS/ME Introduction to Artificial Neural Network and Fuzzy Systems.
A) 80 b) 53 c) 13 d) x 2 = : 10 = 3, x 3 = 309.
CS771 Machine Learning : Tools, Techniques & Application Gaurav Krishna Y Harshit Maheshwari Pulkit Jain Sayantan Marik
WEEK 6: DEEP TRACKING STUDENTS: SI CHEN & MEERA HAHN MENTOR: AFSHIN DEGHAN.
Face Detection and Neural Networks Todd Wittman Math 8600: Image Analysis Prof. Jackie Shen December 2001.
SVMLight SVMLight is an implementation of Support Vector Machine (SVM) in C. Download source from :
Selecting the Best Set of Features for Efficient Intrusion Detection in Networks Mouhcine Guennoun Aboubakr Lbekkouri Khalil El-Khatib.
Human Gesture Recognition Using Kinect Camera Presented by Carolina Vettorazzo and Diego Santo Orasa Patsadu, Chakarida Nukoolkit and Bunthit Watanapa.
An Example of Course Project Face Identification.
GEOGRAPHY/MAPS UNIT Social Studies Review. What is this a picture of?
ADHD Arjun Watane Soumyabrata Dey. Work accomplished Extracted features for – Normalized brain, GM, WM, CSF Ran feature vectors through SVM Ready to fine.
AI – CS289 Machine Learning - Labs Machine Learning – Lab 4 02 nd November 2006 Dr Bogdan L. Vrusias
Logan Lebanoff Mentor: Haroon Idrees. Two-layer method  Trying a method that will have two layers of neural networks.
Week 8 Shelby Thompson. This week: Continued to work with PubFig83 dataset Saved.mat files for each training and testing image.mat files include information.
WEEK 1 You have 10 seconds to name…
Latitude & Longitude Practice
Sparse Coding: A Deep Learning using Unlabeled Data for High - Level Representation Dr.G.M.Nasira R. Vidya R. P. Jaia Priyankka.
DeepMIDI: Music Generation
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Introduction of SNoW (Sparse Network of Winnows )
CSSE463: Image Recognition Day 14
Machine Learning – Classification David Fenyő
Unit 7- The Brave Little Kite
Outline Problem Description Data Acquisition Method Overview
Human Action Recognition Week 10
ECG data classification with deep learning tools
Semi-supervised Machine Learning Gergana Lazarova
CATEGORIZATION OF NEWS ARTICLES USING NEURAL TEXT CATEGORIZER
Table 1. Advantages and Disadvantages of Traditional DM/ML Methods
Named Entity Tagging Thanks to Dan Jurafsky, Jim Martin, Ray Mooney, Tom Mitchell for slides.
Estimating Link Signatures with Machine Learning Algorithms
Layout - you need to understand that a simple navigation bar:
Schizophrenia Classification Using
Arjun Watane Soumyabrata Dey
Online Gifts Buy for wishes happy mother's day to yours choice and with happy gifts find here:
Unsupervised Learning and Autoencoders
Scale: Kilometers.
Attentional Neural Network: Feature Selection Using Cognitive Feedback
Categorizing networks using Machine Learning
Machine Learning Week 1.
An Inteligent System to Diabetes Prediction
Face Recognition with Deep Learning Method
CSSE463: Image Recognition Day 20
Neural Networks Advantages Criticism
Find the curl of the vector field. {image}
What approaches are there for predicting between points?
Object Classification through Deconvolutional Neural Networks
Automated Video Cutting:
Label Name Label Name Label Name Label Name Label Name Label Name
CSSE463: Image Recognition Day 20
Aleysha Becker Ece 539, Fall 2018
Advanced Artificial Intelligence Classification
Named Entity Tagging Thanks to Dan Jurafsky, Jim Martin, Ray Mooney, Tom Mitchell for slides.
Zip Codes and Neural Networks: Machine Learning for
Nearly Analytical Pose Estimation
CSSE463: Image Recognition Day 18
CSSE463: Image Recognition Day 16
Structure of a typical back-propagated multilayered perceptron used in this study. Structure of a typical back-propagated multilayered perceptron used.
Scale: Kilometers.
Latitude & Longitude Practice
CSSE463: Image Recognition Day 16
Predicting Voter Choice from Census Data
Practice Project Overview
Arjun Watane Soumyabrata Dey
March Madness Data Crunch Overview
Goal: Understand cycles in Sunspot frequency over time.
Experiment for Week 4 Determining the Identity of Several Unknown Substances using Physical Properties CHE116.
Patterson: Chap 1 A Review of Machine Learning
Presentation transcript:

Using Location Data to Predict the Outcome of Emergency Calls Crime in San Francisco Using Location Data to Predict the Outcome of Emergency Calls John Van Gilder

Caffe Struggles Clearly not designed for use with OSX 10.12 or MATLAB 2015a Designed for use with images, not numeric data Caffe group on GitHub often unhelpful www.xkcd.com/979

Methods Formatted Data: Formatted Network Feature Vector: [Day of the week, Latitude, Longitude] Label: {0,1} Formatted Network Four hidden layers: 10-2-10-2 Gave the best accuracy, ranged from ~40-65% depending on these numbers 150000 iterations

Results Previous groups1 have used naïve Bayes classifier to attempt to classify type of crime as well as specific outcome given location and day of the week ~25% accuracy I simply attempted to classify general outcome given location and day of the week ~65.25% accuracy Nearly identical results whether day of the week was included or not [1] Ang, Wang, Chyou at UCSD: http://cseweb.ucsd.edu/~jmcauley/cse255/reports/fa15/037.pdf