By Christo Dichev, Gennady Agre

This booklet constitutes the refereed complaints of the seventeenth foreign convention on synthetic Intelligence: technique, platforms, and functions, AIMSA 2016, held in Varna, Bulgaria in September 2015.

The 32 revised complete papers 6 poster papers offered have been rigorously reviewed and chosen from 86 submissions. They disguise a variety of subject matters in AI: from desktop studying to ordinary language platforms, from info extraction to textual content mining, from wisdom illustration to smooth computing; from theoretical matters to real-world applications.

Show description

Read or Download Artificial Intelligence: Methodology, Systems, and Applications: 17th International Conference, AIMSA 2016, Varna, Bulgaria, September 7-10, 2016, Proceedings PDF

Similar international_1 books

Distributed, Parallel and Biologically Inspired Systems: 7th IFIP TC 10 Working Conference, DIPES 2010 and 3rd IFIP TC 10 International Conference, BICC 2010, Held as Part of WCC 2010, Brisbane, Australia, September 20-23, 2010. Proceedings

St This quantity includes the complaints of 2 meetings held as a part of the 21 IFIP international computing device Congress in Brisbane, Australia, 20–23 September 2010. th the 1st a part of the booklet provides the complaints of DIPES 2010, the 7 IFIP convention on disbursed and Parallel Embedded platforms. The convention, int- duced in a separate preface via the Chairs, covers a number issues from specification and layout of embedded platforms via to dependability and fault tolerance.

Critical Infrastructure Protection IV: Fourth Annual IFIP WG 11.10 International Conference on Critical Infrastructure Protection, ICCIP 2010, Washington, DC, USA, March 15-17, 2010, Revised Selected Papers

The knowledge infrastructure – comprising desktops, embedded units, networks and software program structures – is essential to operations in each region: inf- mation know-how, telecommunications, power, banking and ? nance, tra- portation platforms, chemical substances, agriculture and nutrition, safeguard commercial base, public healthiness and health and wellbeing care, nationwide monuments and icons, consuming water and water therapy platforms, advertisement amenities, dams, emergency providers, advertisement nuclear reactors, fabrics and waste, postal and transport, and govt amenities.

Social informatics : 7th International Conference, SocInfo 2015, Beijing, China, December 9-12, 2015 : proceedings

This publication constitutes the lawsuits of the seventh overseas convention on Social Informatics, SocInfo 2015, held in Beijing, China, in December 2015. the nineteen papers provided during this quantity have been rigorously reviewed and chosen from forty two submissions. They conceal subject matters resembling consumer modeling, opinion mining, person habit, and crowd sourcing.

Principles and Practice of Constraint Programming: 22nd International Conference, CP 2016, Toulouse, France, September 5-9, 2016, Proceedings

This booklet constitutes the refereed convention court cases of the twenty second foreign convention on ideas and perform of Constraint Programming, CP 2016, held in Toulouse, France, in September 2016. The sixty three revised average papers awarded including four brief papers and the abstracts of four invited talks have been conscientiously reviewed and chosen from 157 submissions.

Additional info for Artificial Intelligence: Methodology, Systems, and Applications: 17th International Conference, AIMSA 2016, Varna, Bulgaria, September 7-10, 2016, Proceedings

Sample text

We intend also to apply a pruning technique to reduce the dimensionality space and improve the classification accuracy. References 1. : UCI machine learning repository (2013). University of California, Irvine, School of Information and Computer Sciences. edu/ml 2. : Classification and Regression Trees. Wadsworth and Brooks, Monterey (1984) 3. : Classification with belief decision trees. , Dochev, D. ) AIMSA 2000. LNCS (LNAI), vol. 1904, pp. 80–90. Springer, Heidelberg (2000) 4. : Belief decision trees: theoretical foundations.

An } represented within the TBM framework. Objects of L may belong to the set of classes C = {C1 , . . , Cq }. The different steps of our building decision tree algorithm are described as follows: 1. Create the root node of the decision tree that contain all the training set objects. 2. Check if the node verify the stopping criteria presented previously. – If yes, declare it as a leaf node and compute its probability distribution. – If not, the attribute that has the highest GainRatio will be designed as the root of the decision tree related to the whole training set.

Let us denote by Θ the frame of discernment including a finite non empty set of elementary events related to a given problem. The power set of Θ, denoted by 2Θ is composed of all subsets of Θ. The basic belief assignment (bba) expressing beliefs on the different subsets of Θ is a function m : 2Θ → [0, 1] such that: m(A) = 1. (1) A⊆Θ The quantity m(A), also called basic belief mass (bbm), states the part of belief committed exactly to the event A. All subsets A in Θ such that m(A) > 0 are called focal elements.

Download PDF sample

Rated 4.68 of 5 – based on 5 votes