Featured links:

• Big Data: SSD’s, R, and Linked Data Streams [1]
• Data Mining and Warehousing blog [2]

Linki na pracownię:

• Attach:zadania.pdf
• Wprowadzenie do języków Octave i R
• Zadanie1 (eksploracyjna analiza danych)
• Zadanie2 (rozkład normalny i symulacja/generowanie)
• Zadanie3 (wielojądrowe SVMy)
  • Support Vector Machines, Tutorial Slides by Andrew Moore [3], Support Vector and Kernel Machines [4]
  • Sparse and large-scale learning with heterogeneous data [5]
  • SVM-Tutorial using R (e1071-package) [6]
  • Shogun - A Large Scale Machine Learning Toolbox [7]
• Zadanie4 (sieci Bayesowskie i reguły asocjacyjne)
  • Short Overview of Bayes Nets [8], Inference in Bayesian Networks [10] Learning Bayesian Networks [9]: Tutorial Slides by Andrew Moore
  • Bayes Net Toolbox for Matlab [11] Written by Kevin Murphy, 1997—2002: A Brief Introduction to Graphical Models and Bayesian Networks [12], How to use the toolbox [13]
• Zadanie5 (klasyfikacja, drzewa decyzyjne)
  • Statistics with R: Rozdział 12 [14] Using regression in a classification problem, Nearest Neighbours, Naive Bayes classifier
  • A Practical Guide to Support Vector Classification [15]
  • An Introduction to Recursive Partitioning Using the RPART Routines [16] (wersja skrócona [17] — bez opisu teoretycznego)
  • Classification and regression by randomForest [18] R News, 3, 2002
  • KLIMT Making trees interactive [19] (Klassification - Interactive Methods for Trees)
• Zadanie6 (grupowanie, metody hierarchiczne, ocena ilości skupień)
  • Statistics with R: Clustering [20]
• Zadanie7 (wizualizacja danych)
  • Statistics with R: Factorial methods: Around Principal Component Analysis (PCA) [21]
  • PCA by Projection Pursuit. The Package pcaPP [22] Heinrich Fritz
  • Dimensional Reduction for Data Mapping [23] (Jonathan Edwards and Paul Oman) R News, 3, 2003
• Zadanie8 (szeregi czasowe)
  • Statistics with R: Time series [24]
  • Data mining on time series: an illustration using fast-food restaurant franchise data [25]
• Zadanie9 (“niestandardowe” bazy danych)
  • Querying RDF Data from a Graph Database Perspective [26] (Renzo Angles and Claudio Gutierrez), Querying from a Graph Database Perspective: the case of RDF [27] — prezentacja
  • Tethering Cultural Data with RDF [28] (Kate Byrne)
    • RelEx is an English-language semantic relationship extractor, built on the Carnegie-Mellon link parser
  • Bazy danych lub “interfejsy” do baz danych:
    • Sesame [29] is an open source framework for storage, inferencing and querying of RDF data.
    • Mondrian [30] is an OLAP server written in Java. It enables you to interactively analyze very large datasets stored in SQL databases without writing SQL.
    • the Exist XML database [31]
    • the RDF/SPARQL/XML part of the OpenLink Virtuoso system [32]
    • the Jena/ARQ combo [33]
    • HyperGraphDB [34]
    • RDF Gateway [35] (komercyjne)
    • 4Suite: an open-source platform for XML and RDF processing [36]
    • Rx4RDF [37]

Other links for the class:

• Data Mining with R: learning by case studies [38] (by Luis Torgo), nice tutorial with SQL interaction
• Statistics with R [39], a very interesting but unpolished course on R
• Introduction to R and Exploratory data analysis [40]
• Using R for Introductory Statistics [41] (pre-draft of a published book)
• Using R for data analysis and graphics [42] (JH Maindonald)
  • from Introduction to R [43] (a collection of links by Karl W Broman)
• Learning classifiers from distributed, semantically heterogeneous, autonomous data sources [44]

Propozycje referatów (w trakcie opracowywania):

1. Komunikacja z bazą danych z poziomu środowiska R. [zajęty]
2. Automatyczne generowanie raportów w środowisku R. [wolny]
3. Tematy z Learning classifiers from distributed, semantically heterogeneous, autonomous data sources [45]: [wszystkie wolne]
   1. Rozdział trzeci: “Learning classifiers from distributed data”,
   2. Rozdział czwarty: “Learning classifiers from sementically heterogeneous data”,
   3. W razie zainteresowania możemy zrobić więcej.
4. Tematy z książki “The Handbook of Data Mining”. Można wybrać jeden rozdział lub kilka powiązanych rozdziałów. [wszystkie wolne]
   1. 13 Distributed Data Mining 341 (Byung-Hoon Park and Hillol Kargupta)
   2. II: MANAGEMENT OF DATA MINING 14 Data Collection, Preparation, Quality, and Visualization 365 (Dorian Pyle)
   3. 15 Data Storage and Management 393 (Tong (Teresa) Wu and Xiangyang (Sean) Li)
   4. 16 Feature Extraction, Selection, and Construction 409 (Huan Liu, Lei Yu, and Hiroshi Motoda)
   5. 17 Performance Analysis and Evaluation 425 (Sholom M. Weiss and Tong Zhang)
   6. 18 Security and Privacy 441 (Chris Clifton)
   7. 19 Emerging Standards and Interfaces 453 (Robert Grossman, Mark Hornick, and Gregor Meyer)
   8. III: APPLICATIONS OF DATA MINING 20 Mining Human Performance Data 463 (David A. Nembhard)
   9. 21 Mining Text Data 481 (Ronen Feldman)
   10. 22 Mining Geospatial Data 519 (Shashi Shekhar and Ranga Raju Vatsavai)
   11. 23 Mining Science and Engineering Data 549 (Chandrika Kamath)
   12. 24 Mining Data in Bioinformatics 573 (Mohammed J. Zaki)
   13. 25 Mining Customer Relationship Management (CRM) Data 597 (Robert Cooley)
   14. 26 Mining Computer and Network Security Data 617 (Nong Ye)
   15. 27 Mining Image Data 637 (Chabane Djeraba and Gregory Fernandez)
   16. 28 Mining Manufacturing Quality Data 657 (Murat C. Testik and George C. Runger)

WARNING: Old stuff below.

Some random links for now:

• Information Retrieval (Searching the Web) [46], Tomasz Jurdzinski course and links from there
• Picture languages in machine understanding of medical visualization [47], Marek R. Ogiela, Ryszard Tadeusiewicz
• Learning the structure of image collections with latent aspect models [48], Florent Monay
• Recommendation Based on Personal Preference [49], Pei Wang. (Asking a database questions like: “give me five best examples of fast and cheap notebook”, “find cheap ticket for a flight that leaves C around 9AM and arives at D as early as possible”.)
• Sparse and large-scale learning with heterogeneous data [50], Google Tech Talk
• FilterBoost: Regression and Classification on Large Datasets [51], Joseph K. Bradley and Robert E. Schapire

Software:

• Vowpal Wabbit (Fast Online Learning) [52]

Places:

• Google Research [53]

Amusements:

• Wikipedia:Petabyte#Petabytes_in_use
• Arstechnica: Rumors suggest Google is set to open scientific data store [54]
• Wired: This Psychologist Might Outsmart the Math Brains Competing for the Netflix Prize [55]

Copyright © 2005–2006 the Main wiki and its authors