1 of 35

Visualisasi Data

Program Studi Informatika

Fakultas Sains dan Matematika

Universitas Diponegoro

​

MIK1624713

2 of 35

IDENTITAS MATA KULIAH

KODE

MIK1624713 

NAMA

Visualisasi Data

BEBAN

3 SKS

PENGAMPU

  1. Dr. Indra Waspada
  2. Dinar Mutiara M.K.N, Ph.D

3 of 35

CAPAIAN PEMBELAJARAN

  • CPL05: Mampu menghasilkan rancangan, mengimplementasikan, dan mengevaluasi solusi berbasis algoritma dengan mempertimbangkan aspek kompleksitas
  • CPL07: Mampu memilih, mengadaptasi atau membuat, kemudian menerapkan teknik, sumber daya, kakas komputasi moderen dengan tepat pada aktivitas komputasi kompleks, serta memahami keterbatasannya.
  • CPL12: Mampu berkomunikasi efektif secara lisan dan tulisan dalam bahasa internasional, serta berkolaborasi dalam kerja sama tim baik sebagai anggota maupun pemimpin
  • CPMK: Mampu menghasilkan rancangan solusi manajemen informasi

4 of 35

CAPAIAN PEMBELAJARAN

Sub CPMK:

  • Mahasiswa mampu mengidentifikasi dan mendeskripsikan (C2) konsep dasar visualisasi data
  • Mahasiswa mampu menjelaskan (C2) kerangka kerja analisis dan perancangan visualisasi
  • Mahasiswa mampu mengidentifikasi dan mendeskripsikan (C2) abstraksi data, tugas, dan idiom pada visualisasi
  • Mahasiswa mampu memilih dan menerapkan (C3) marks dan channel yang sesuai dalam visualisasi
  • Mahasiswa mampu menjelaskan (C2) konsep warna
  • Mahasiswa mampu memahami (C2) jenis data tabel dalam memilih dan merancang (C4) tampilan yang sesuai
  • Mahasiswa mampu menerapkan (C3) teknik visualisasi untuk data spasial, geometri, dan jaringan, serta menggunakan warna dan saluran visual lainnya untuk meningkatkan komunikasi visual.
  • Mahasiswa mampu mempresentasikan (C3) dan mendiskusikan (C4) desain visualisasi secara efektif baik dalam bentuk tertulis maupun lisan kepada berbagai audiens.

5 of 35

DESKRIPSI MATA KULIAH

Mata kuliah Visualisasi Data menyediakan pemahaman mendalam tentang cara merancang dan menerapkan visualisasi yang efektif untuk memfasilitasi analisis dan komunikasi data, dengan memfokuskan pada prinsip-prinsip desain, abstraksi data, dan tugas visualisasi berdasarkan teori dan praktik terkini dalam bidang visualisasi.

6 of 35

Posisi Mata Kuliah Visualisasi Data

CRISP-DM (Cross Industry Standard Process for Data Mining)

7 of 35

8 of 35

Materi

  1. Konsep dasar visualisasi data
  2. Kerangka kerja analisis dan perancangan visualisasi
  3. Abstraksi data, tugas, dan idiom pada visualiasasi
  4. Penerapan marks & channel yang sesuai dalam visualisasi
  5. Ujian Tengah Semester

​

​

  1. Konsep warna
  2. Teknik visualisasi data spasial, geometri, dan jaringan
  3. Penggunaan warna dan saluran visual lainnya untuk meningkatkan komunikasi visual
  4. Teknik mempresentasikan dan mendiskusikan desain visualisasi
  5. Ujian Akhir Semester

​

9 of 35

Buku Referensi Utama

https://www.cs.ubc.ca/~tmm/

10 of 35

Visualization Analysis & Design

​

What's Vis, and Why Do It? (Ch 1)

@tamaramunzner

11 of 35

Defining visualization (vis)

11

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

Why?...

12 of 35

Defining visualization (vis)

12

Why?...

13 of 35

Why have a human in the loop?

13

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

14 of 35

Why have a human in the loop?

14

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

Visualization is suitable when there is a need to augment human capabilities rather than replace people with computational decision-making methods.

15 of 35

Why have a human in the loop?

  • don’t need vis when fully automatic solution exists and is trusted
  • many analysis problems ill-specified
    • don’t know exactly what questions to ask in advance
  • possibilities
    • long-term use for end users (ex: exploratory analysis of scientific data)
    • presentation of known results (ex: New York Times Upshot)
    • stepping stone to assess requirements before developing models
    • help automatic solution developers refine & determine parameters
    • help end users of automatic solutions verify, build trust

15

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

Visualization is suitable when there is a need to augment human capabilities rather than replace people with computational decision-making methods.

16 of 35

Why use an external representation?

  • external representation: replace cognition with perception

16

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

[Cerebral: Visualizing Multiple Experimental Conditions on a Graph with Biological Context. Barsky, Munzner, Gardy, and Kincaid. IEEE TVCG (Proc. InfoVis) 14(6):1253-1260, 2008.]

17 of 35

Why use an external representation?

  • external representation: replace cognition with perception

17

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

[Cerebral: Visualizing Multiple Experimental Conditions on a Graph with Biological Context. Barsky, Munzner, Gardy, and Kincaid. IEEE TVCG (Proc. InfoVis) 14(6):1253-1260, 2008.]

18 of 35

Why depend on vision?

  • human visual system is high-bandwidth channel to brain
    • overview possible due to background processing
      • subjective experience of seeing everything simultaneously
      • significant processing occurs in parallel and pre-attentively
  • sound: lower bandwidth and different semantics
    • overview not supported
      • subjective experience of sequential stream
  • touch/haptics: impoverished record/replay capacity
    • only very low-bandwidth communication thus far
  • taste, smell: no viable record/replay devices

18

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

19 of 35

Why represent all the data?

  • summaries lose information, details matter
    • confirm expected and find unexpected patterns
    • assess validity of statistical model

19

Computer-based visualization systems provide visual representations of datasets designed to help people carry out tasks more effectively.

Identical statistics

x mean

9

x variance

10

y mean

7.5

y variance

3.75

x/y correlation

0.816

20 of 35

Anscombe’s Quartet

20

Identical statistics

x mean

9

x variance

10

y mean

7.5

y variance

3.75

x/y correlation

0.816

21 of 35

What resource limitations are we faced with?

  • computational limits
    • computation time, system memory
  • display limits
    • pixels are precious & most constrained resource
    • information density: ratio of space used to encode info vs unused whitespace
      • tradeoff between clutter and wasting space
      • find sweet spot between dense and sparse
  • human limits
    • human time, human memory, human attention

21

Vis designers must take into account three very different kinds of resource limitations: those of computers, of humans, and of displays.

22 of 35

Why analyze?

  • imposes structure on �huge design space
    • scaffold to help you think systematically about choices
    • analyzing existing as stepping stone to designing new
    • most possibilities ineffective for particular task/data combination

22

23 of 35

Why analyze?

  • imposes structure on �huge design space
    • scaffold to help you think systematically about choices
    • analyzing existing as stepping stone to designing new
    • most possibilities ineffective for particular task/data combination

23

[SpaceTree: Supporting Exploration in Large Node Link Tree, Design Evolution and Empirical Evaluation. Grosjean, Plaisant, and Bederson. Proc. InfoVis 2002, p 57–64.]

SpaceTree

[TreeJuxtaposer: Scalable Tree Comparison Using Focus+Context With Guaranteed Visibility. ACM Trans. on Graphics (Proc. SIGGRAPH) 22:453– 462, 2003.]

TreeJuxtaposer

24 of 35

Why analyze?

  • imposes structure on �huge design space
    • scaffold to help you think systematically about choices
    • analyzing existing as stepping stone to designing new
    • most possibilities ineffective for particular task/data combination

24

[TreeJuxtaposer: Scalable Tree Comparison Using Focus+Context With Guaranteed Visibility. ACM Trans. on Graphics (Proc. SIGGRAPH) 22:453– 462, 2003.]

TreeJuxtaposer

[SpaceTree: Supporting Exploration in Large Node Link Tree, Design Evolution and Empirical Evaluation. Grosjean, Plaisant, and Bederson. Proc. InfoVis 2002, p 57–64.]

SpaceTree

25 of 35

Spoiler : Best Practices dalam Visualisasi Data

26 of 35

Best Practices dalam Visualisasi Data

  • Atribut Pra-perhatian
  • Warna
  • Memilih jenis grafik yang tepat
  • Desain visualisasi yang efektif

27 of 35

Best Practices dalam Visualisasi Data

  • Atribut Pra-perhatian
    • Hitunglah jumlah angka 9!

​

28 of 35

Best Practices dalam Visualisasi Data

Temukan bulatan warna merah

    • Berapa lama waktu yang dibutuhkan?

Pemrosesan paralel pada banyak kanal tunggal

    • Kecepatan tidak bergantung pada jumlah pengganggu
    • Kecepatan bergantung pada kanal dan jumlah perbedaan dari pengganggu

Pencarian serial untuk (hampir semua) kombinasi

    • Kecepatan bergantung pada jumlah pengganggu

​

29 of 35

Best Practices dalam Visualisasi Data

  • Atribut Pra-perhatian

30 of 35

Best Practices dalam Visualisasi Data

  • Warna
    • Penggunaan Warna Dalam Visualisasi Data

​

31 of 35

Best Practices dalam Visualisasi Data

  • Memilih jenis grafik yang tepat
  • Desain visualisasi yang efektif

32 of 35

Contoh publikasi topik visualisasi

33 of 35

Further Reading

Why Use an External Representation? The role and use of external representations are analyzed in papers on the nature of externa representations in problem solving [Zhang 97] and a representational analysis of number systems [Zhang and Norman 95]. The influential paper Why A Diagram Is (Sometimes) Worth Ten Thousand Words is the basis for the discussion of�diagrams in this chapter [Larkin and Simon 87].�

Why Show the Data in Detail? Anscombe proposed his quartet of illustrative examples in a lovely, concise paper [Anscombe 73]. An early paper on the many faces of the scatterplot includes a cogent discussion of why to show as much of the data as possible [Cleveland and McGill 84b].�

34 of 35

Further Reading

What Is the Vis Design Space? The discussion of the vis design space is based on the paper on the methodology of design studies that covers the question of progressing from a loose to a crisp understanding of the user’s requirements [Sedlmair et al. 12].�

What Resource Limitations Matter? Ware’s textbook provides a very thorough discussion of human limitations in terms of perception, memory, and cognition [Ware 13]. A survey paper provides a good overview of the change blindness literature [Simons 00]. The idea of information density dates back to Bertin’s discussion of graphic density [Bertin 67], and Tufte has discussed the data–ink ratio at length [Tufte 83]. �

35 of 35

Thank You