Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Exercises for Patterns in Recordings

Ben Fields
July 05, 2016
Technology
0
32

Exercises for Patterns in Recordings

from DHOxSS 2015-16

Ben Fields

July 05, 2016
Tweet

More Decks by Ben Fields

See All by Ben Fields
People in the loop machine learning: A case Study in news similarity
bfields
0
120
Human-centric evaluation of similarity spaces of news articles
bfields
2
54
Ethics, Data Science, and Public Service Media
bfields
1
33
The Case for Public Service Recommender Algorithms
bfields
0
450
Bikes are Dope
bfields
0
51
Beyond Your Reckons: from feels to facts
bfields
0
64
People who like cheese also like crackers: a learning hour on recommender systems
bfields
0
78
Auto-Summarising Beer Reviews
bfields
0
57
rMIXr: how we learned to stop worrying and love the graph
bfields
0
77

Other Decks in Technology

See All in Technology
ヒューリスティックコンテストで機械学習しよう
nagiss
5
1.3k
アジャイルな組織を作るために開発チーム作成ガイドを書いた話 / Scrum Fest Mikawa 2023
ama_ch
3
1.6k
LINE 平台與開發生態系介紹
line_developers_tw
PRO
0
250
コドモンSREにおける オブザーバビリティ改善の道のり
codmoninc
0
140
承認コネクタについて
miyakemito
1
130
失敗から学ぶAPIファースト / API first learning from failure
yokawasa
14
4.6k
DDD e Team Topologies como estes conceitos podem te dar pistas de como montar seus times de engenharia!!!
claudioed
2
290
Azure OpenAI Service リファレンスアーキテクチャからみる本番システムレベルの LLM アプリに必要な検討項目の解説 / From Azure OpenAI Reference Architecture to Production-Ready LLM Apps #serverlessdays #serverlesstokyo
koudaiii
5
1.2k
Designing an Incident Response Process at Scale
opeonikute
0
150
ビジネス向けアプリを開発するときに知っておくべきAndroid Enterpriseの世界
imsaku
1
570
LLM 時代におさえておきたい Azure Serverless ファミリーまとめ / serverlessdaystokyo2023-llm-aoai
miyake
5
530
Mutating Meetup with GraphQL
adavis
1
420

Featured

See All Featured
Being A Developer After 40
akosma
52
580k
Writing Fast Ruby
sferik
615
59k
Build your cross-platform service in a week with App Engine
jlugia
223
17k
Visualization
eitanlees
131
13k
The MySQL Ecosystem @ GitHub 2015
samlambert
240
11k
A Tale of Four Properties
chriscoyier
150
21k
Robots, Beer and Maslow
schacon
154
7.6k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
352
21k
Art, The Web, and Tiny UX
lynnandtonic
285
18k
Fireside Chat
paigeccino
18
2.2k
Mobile First: as difficult as doing things right
swwweet
214
8.2k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
41
11k

Transcript

  1. Patterns in Recording -
    Exercises
    Ben Fields

    View Slide

  2. WEKA basics
    • Launch the WEKA
    Application

    • Select ‘Explorer’

    • Load
    ’50_weka_class_labeled.arff’

    • Select various Attributes
    (features)

    View Slide

  3. WEKA basics
    • Attribute selection with
    regular expressions (‘.*’ is
    an expanding wild card)

    • Find all the MFCC
    attributes

    • also select ‘CLASS’

    • press ‘Invert’, then
    ‘Remove’

    View Slide

  4. using a classifier
    • Select ‘Classify’ tab

    • ‘Choose’ >>
    ‘classifiers/bayes/
    NaiveBayes’

    • set test options to
    ‘Cross-validation’

    • press ‘Start’

    View Slide

  5. putting it all together
    • now repeat the whole process using LPC features

    View Slide

  6. Explore more files and
    features
    • Load ‘training_data_after_parsing.arff’

    • Classify against the CLASS mood labels using Random
    Forests and J48. Which performs better? Which classes
    are most confused?

    View Slide