machine learning assists the classification of reports by
play

Machine Learning Assists the Classification of Reports by Citizens - PowerPoint PPT Presentation

Feb 26, 2024 •139 likes •346 views

Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquitoes Antonio Rodriguez 1 Frederic Bartumeus 2 , 3 , 4 a 1 Ricard Gavald` Universitat Polit` ecnica de Catalunya, Barcelona (Spain) Centre for Advanced

  1. Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquitoes Antonio Rodriguez 1 Frederic Bartumeus 2 , 3 , 4 a 1 Ricard Gavald` Universitat Polit` ecnica de Catalunya, Barcelona (Spain) Centre for Advanced Studies of Blanes (CEAB-CSIC), 17300 Girona (Spain) CREAF, Cerdanyola del Vall` es, 08193 Barcelona (Spain) ICREA, Pg Llu´ ıs Companys 23, 08010 Barcelona (Spain) Workshop on Data Science for Social Good, SoGood September 2016 Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  2. Overview Introduction 1 Methodology 2 Project development 3 Exploratory data analysis Data cleaning and pre-processing Classifier training, evaluation and selection Real-time classification system design Discussion 4 Future work 5 Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  3. Introduction - Mosquito Alert Citizen Science Platform Mobile application Growing fast Various mosquito species Worldwide localizations Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  4. Introduction - Mobile App Send breeding site Send specimen report Small questionnaire Geolocated! Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  5. Introduction - Mosquito Alert System Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  6. Introduction - Classification system Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  7. Methodology 1 Exploratory data analysis 2 Data cleaning and pre-processing 3 Classifiers training evaluation selection 4 Real-time classification system design Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  8. Exploratory data analysis - Raw files users 16967 observations of 10 variables userID userRegistTimeOriginal userRegistDatetime userRegistDate userRegistMonthNum userRegistMonthString userRegistWeekdayString userRegistWeekdayNum userSyst userDaysSystRelease Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  9. Exploratory data analysis - Raw files reports 10618 observations of 23+1 variables reportVersionID reportCreationMonthNum reportVersionNum reportCreationMonthString userID reportCreationWeekdayString reportID reportCreationWeekdayNum reportType reportLong reportNote reportLat os missionNum hide missionName reportCreationDatetime tiger q1 response reportCreationDate tiger q2 response reportVersionDatetime tiger q3 response reportVersionDate class Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  10. Questionnaire variables Questions Is small, black and has white stripes? Has a white stripe in both head and thorax? Has white stripes in both abdomen and legs? Response values -1 No 0 Not sure 1 Yes Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  11. The class variable -2 The report is definitely not a valid specimen. -1 The report doesn’t seem to be a valid specimen. But it is not sure. 0 There isn’t enough information to classify the report. 1 The report seems to be a valid specimen. But it is not sure. 2 The report is definitely a valid specimen. Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  12. Instance variables Added reportNote reportTimeOfDay. newUser userNumReports Preserved userAccuracy os userTimeForFirstReport reportMonth userTimeSinceLastReport reportQ*Answ (3) userMeanTimeBetweenReports class userNumActionAreas userMobilityIndex reports1kmLast* (4) validReports1kmLast* (4) Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  13. Generated instances 2094 instances from usable reports Class 2 1 − 1 − 2 Frequency 47% 46% 2% 5% Class-imbalanced problem: positive instances over 7 times as frequent as negative ones. Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  14. Studied classifiers Naive Bayes k-nearest neighbors Decision trees Random Forests Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  15. Classifiers - Considerations Most classifiers have trouble dealing with imbalanced classes Merged “unsure” (-1,1) classes into “sure” ones (-2,2) Replication of minority class performed . . . but testing still on original proportion Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  16. Classifiers - Selected classifier Naive Bayes Training conditions: Aggregated instances Positive Negative Replicated (x10) Accuracy 0,380 negatives in training Precision 0,983 0,086 Recall 0,344 0,912 High positive Precision F-measure (F1) 0,51 0,157 High negative Recall Table: Evaluation metrics, Naive Bayes can detect approximately 1 third of the valid reports with a precision near 98% Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  17. ROC curve and variable importance Variable name Importance reportQ2Answ 0.7424 reportQ3Answ 0.7038 reports1kmLastMonth 0.6623 reportQ1Answ 0.6615 userNumReports 0.6405 userNumActionAreas 0.6348 validReports1kmLastMonth 0.6216 userTimeForFirstReport 0.6197 reports1kmLastWeek 0.6158 userAccuracy 0.6085 Table: Variable importance in the NB classifier. Numbers are the values of the model coefficients after standarization. Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

  18. Real-time classification system design Two subsystems: Instance generation system Instance creation script Environment Classification system Training script Classifier Classification script Workshop on Data Science for Social Good, SoGo Antonio Rodriguez, Frederic Bartumeus, Ricard Gavald` Machine Learning Assists the Classification of Reports by Citizens on Disease-Carrying Mosquito a (Universitat Polit` ecnica de Catalunya, Barcelona (Spain), Centre for Advanced Studies / 20

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Classifiers: Support Vector Machine 1 MACHINE LEARNING What is Classification? Female Adult

Classifiers: Support Vector Machine 1 MACHINE LEARNING What is Classification? Female Adult

MACHINE LEARNING MACHINE LEARNING Classifiers: Support Vector Machine 1 MACHINE LEARNING What is Classification? Female Adult Children Detecting facial attributes He & Zhang, Pattern Recognition, 2011 Sony (Make Believe) Training set

914 views • 80 slides
Traditional Machine Learning: Unsupervised Learning Juhan Nam Traditional Machine Learning

Traditional Machine Learning: Unsupervised Learning Juhan Nam Traditional Machine Learning

GCT634/AI613: Musical Applications of Machine Learning (Fall 2020) Traditional Machine Learning: Unsupervised Learning Juhan Nam Traditional Machine Learning Pipeline in Classification Tasks A set of hand-designed audio features are selected

398 views • 26 slides
Machine Learning Classification over Encrypted Data Raphal Bost Raluca Ada Popa,

Machine Learning Classification over Encrypted Data Raphal Bost Raluca Ada Popa,

Machine Learning Classification over Encrypted Data Raphal Bost Raluca Ada Popa, Universit Rennes 1 ETH Zrich MIT MIT Stephen Tu Shafi Goldwasser MIT MIT Classification (Machine Learning) Supervised learning (training)

1.3k views • 29 slides
Multiclass Classification Machine Learning So far: Binary Classification We have seen linear

Multiclass Classification Machine Learning So far: Binary Classification We have seen linear

Multiclass Classification Machine Learning So far: Binary Classification We have seen linear models Learning algorithms for linear models Perceptron, Winnow, Adaboost, SVM We will see more soon: Nave Bayes, Logistic Regression

635 views • 24 slides
Introduction to Machine Learning Classification: Tasks Sonar Learning goals 0.20 Understand

Introduction to Machine Learning Classification: Tasks Sonar Learning goals 0.20 Understand

Introduction to Machine Learning Classification: Tasks Sonar Learning goals 0.20 Understand the main difference between regression and 0.15 classification Response V2 M R 0.10 Know that classification can be binary or multiclass 0.05

510 views • 8 slides
Machine learning strikes from below, a mining application: Material Classification by Drilling

Machine learning strikes from below, a mining application: Material Classification by Drilling

Machine learning strikes from below, a mining application: Material Classification by Drilling Machine Learning 2005 Johan Larsson Papers Material Classification by Drilling Diana LaBelle, John Bares, Illah Nourbakhsh Robotics Institute,

509 views • 29 slides
1 Why Study Machine Learning? Why Study Machine Learning? Cognitive Science The Time is Ripe

1 Why Study Machine Learning? Why Study Machine Learning? Cognitive Science The Time is Ripe

What is Learning? Herbert Simon: Learning is any process by which a system improves performance from CS 391L: Machine Learning experience. Introduction What is the task? Classification Problem solving / planning /

603 views • 6 slides
Machine learning and event classification SOTARRIVA ALVAREZ ISAI ROBERTO Advisor Dr. Antonio

Machine learning and event classification SOTARRIVA ALVAREZ ISAI ROBERTO Advisor Dr. Antonio

Machine learning and event classification SOTARRIVA ALVAREZ ISAI ROBERTO Advisor Dr. Antonio Ortiz Velasquez 1 MACHINE LEARNING APPLIED TO EVENT CLASSIFICATION Motivation Jet like Sphere like OR Machine learning (low spherocity) (High

301 views • 14 slides
Decision Trees TJ Machine Learning Club Classification vs. Regression Classification

Decision Trees TJ Machine Learning Club Classification vs. Regression Classification

Decision Trees TJ Machine Learning Club Classification vs. Regression Classification Classifying photos of fruits Determining whether tumor is benign or malignant Regression Predicting COVID-19 cases given demographic data

505 views • 26 slides
Machine Learning Classification over Encrypted Data Raphael Bost, Raluca Ada Popa, Stephen Tu,

Machine Learning Classification over Encrypted Data Raphael Bost, Raluca Ada Popa, Stephen Tu,

Machine Learning Classification over Encrypted Data Raphael Bost, Raluca Ada Popa, Stephen Tu, Shafi Goldwasser Classification (Machine Learning) Supervised learning (training) Classification data classification training model

1.29k views • 54 slides
This Lecture Classification Machine Learning and Pattern Recognition Now we focus on

This Lecture Classification Machine Learning and Pattern Recognition Now we focus on

This Lecture Classification Machine Learning and Pattern Recognition Now we focus on classfication . Weve already seen the naive Bayes classifier. This time: An alternative classification family, discriminative methods Chris Williams

398 views • 5 slides
Overview CS 446 What is machine learning? Machine learning : study of computational

Overview CS 446 What is machine learning? Machine learning : study of computational

Overview CS 446 What is machine learning? Machine learning : study of computational mechanisms that learn from data to make predictions and decisions. 1 / 21 Application 1: image classification Birdwatcher takes photos of birds,

1.08k views • 83 slides
MSc Course MACHINE LEARNING TECHNIQUES AND APPLICATIONS Classification with GMM + Bayes 1

MSc Course MACHINE LEARNING TECHNIQUES AND APPLICATIONS Classification with GMM + Bayes 1

APPLIED MACHINE LEARNING MSc Course MACHINE LEARNING TECHNIQUES AND APPLICATIONS Classification with GMM + Bayes 1 APPLIED MACHINE LEARNING Clustering, semi-supervised clustering and classification Classification Clustering

1.21k views • 45 slides
Introduction to Machine Learning: Classification and The Noisy Channel Model CMSC 473/673 UMBC

Introduction to Machine Learning: Classification and The Noisy Channel Model CMSC 473/673 UMBC

Introduction to Machine Learning: Classification and The Noisy Channel Model CMSC 473/673 UMBC Some slides adapted from 3SLP Outline Classification Why incorporate uncertainty Classification with Bayes Rule Example: Email Classifier

1.68k views • 89 slides
Softmax Classifier + SGD Todays Class Intro to Machine Learning What is Machine Learning?

Softmax Classifier + SGD Todays Class Intro to Machine Learning What is Machine Learning?

CS6501: Deep Learning for Visual Recognition Softmax Classifier + SGD Todays Class Intro to Machine Learning What is Machine Learning? Supervised Learning: Classification with K-nearest neighbors Unsupervised Learning: Clustering with

1.36k views • 91 slides
Machine Learning Basics Classification & Text Categorization Features Overfitting

Machine Learning Basics Classification & Text Categorization Features Overfitting

Machine Learning Basics Classification & Text Categorization Features Overfitting and Regularization Perceptron Classifier Supervised Learning V.S. Unsupervised Learning Generative Learning V.S. Discriminative Learning

591 views • 30 slides
Mogden Sewage Treatment Works Residents Liaison Meeting 26 September 2019 1 Mogden Residents

Mogden Sewage Treatment Works Residents Liaison Meeting 26 September 2019 1 Mogden Residents

Mogden Sewage Treatment Works Residents Liaison Meeting 26 September 2019 1 Mogden Residents Meeting Mogden Agenda Welcome and introductions Site Tour Review of previous minutes and actions Operations update: Mogden

756 views • 20 slides
QuickCheck 11.2 A 2.0 kg object moving to the right with speed 0.50 m/s experiences the force

QuickCheck 11.2 A 2.0 kg object moving to the right with speed 0.50 m/s experiences the force

QuickCheck 11.2 A 2.0 kg object moving to the right with speed 0.50 m/s experiences the force shown. What are the objects speed and direction after the force ends? A. 0.50 m/s left B. At rest C. 0.50 m/s right D. 1.0 m/s right E. 2.0 m/s

178 views • 4 slides
Superconformal field theories A-Maximization classically the trace of the energymomentum

Superconformal field theories A-Maximization classically the trace of the energymomentum

Superconformal field theories A-Maximization classically the trace of the energymomentum tensor for a scale- invariant theory vanishes. trace anomaly. r: ) 2 a ( R ) 2 + . . . , g 3 1 T ( F b = central charge

453 views • 34 slides
Good Morning SWIFT HI! I'm Marc Prud'hommeaux marc@glimpse.io Swift Public beta: June 2014

Good Morning SWIFT HI! I'm Marc Prud'hommeaux marc@glimpse.io Swift Public beta: June 2014

Good Morning SWIFT HI! I'm Marc Prud'hommeaux marc@glimpse.io Swift Public beta: June 2014 v1.0: September 2014 v1.2: February 2015 POLL: Swift? Agenda 1. Swift Syntax 2. Interesting Stuff 3. Questions (GOTO Guide) // Swift Bank &

1.53k views • 102 slides
So urc e : WDI , 2013 1995: 70%, 1999/ 2000: 59%, 2005/ 6: 57%, 2010/ 11: 45% I ne q ua

So urc e : WDI , 2013 1995: 70%, 1999/ 2000: 59%, 2005/ 6: 57%, 2010/ 11: 45% I ne q ua

So urc e : WDI , 2013 1995: 70%, 1999/ 2000: 59%, 2005/ 6: 57%, 2010/ 11: 45% I ne q ua lity: pe a ke d a t 0.52 in 2005/ 6, the n do wn to 0.49 ha t tric k o f ra pid g ro wth, sha rp po ve rty re duc tio n a nd re duc e d ine

627 views • 46 slides
Covering Tours with Turn Cost: Variants, Approximation and Practical Solution S andor P.

Covering Tours with Turn Cost: Variants, Approximation and Practical Solution S andor P.

Institute of Operating Systems and Computer Networks Covering Tours with Turn Cost: Variants, Approximation and Practical Solution S andor P. Fekete and Dominik Krupke EuroCG2017, Malm o, 05.04.2017 Introduction Problem Integer

770 views • 27 slides
Lymantria dispar Gypsy moth (5th instar larva)

Lymantria dispar Gypsy moth (5th instar larva)

Lymantria dispar Gypsy moth (5th instar larva)

428 views • 4 slides
1 Transient Typechecks are (almost) Free Richard Roberts, Stefan Marr Michael

1 Transient Typechecks are (almost) Free Richard Roberts, Stefan Marr Michael

1 Transient Typechecks are (almost) Free Richard Roberts, Stefan Marr Michael Homer, James Noble 2 Transient Performance The transient approach checks types at uses, so the act of adding types to a program introduces more

1.15k views • 51 slides

More recommend