The Experts below are selected from a list of 291 Experts worldwide ranked by ideXlab platform
Anouck Girard - One of the best experts on this subject based on the ideXlab platform.
-
Optimal fusion rules in team classification under three Decision Structures
2013 American Control Conference, 2013Co-Authors: Baro Hyun, Pierre Kabamba, Anouck GirardAbstract:In this paper, we study the performance of a team of dichotomous classifiers, where the classifiers' Decisions are combined by logical fusion rules. Three Decision Structures are derived using the confusion matrix of a single classifier and a priori information, and the performances of the different Decision Structures are compared. First, we consider the performance of a team of three classifiers with a total of 256 fusion rules. Then, we propose a Decision Structure that utilizes a moderator, i.e., an entity that exploits Bayesian inference from individual classifiers' Decisions and makes final Decisions based on maximum likelihood classification. We show the benefits of using a moderator (compared to a Decision Structure without a moderator). Finally, we propose a Decision Structure that exploits pairing, i.e., fusing the classifiers' Decisions sequentially two-by-two. Two pairing schemes, i.e., incremental and tournament-like, are proposed and we show that incremental pairing is the most effective Decision Structure among the proposed ones.
-
ACC - Optimal fusion rules in team classification under three Decision Structures
2013 American Control Conference, 2013Co-Authors: Baro Hyun, Pierre Kabamba, Anouck GirardAbstract:In this paper, we study the performance of a team of dichotomous classifiers, where the classifiers' Decisions are combined by logical fusion rules. Three Decision Structures are derived using the confusion matrix of a single classifier and a priori information, and the performances of the different Decision Structures are compared. First, we consider the performance of a team of three classifiers with a total of 256 fusion rules. Then, we propose a Decision Structure that utilizes a moderator, i.e., an entity that exploits Bayesian inference from individual classifiers' Decisions and makes final Decisions based on maximum likelihood classification. We show the benefits of using a moderator (compared to a Decision Structure without a moderator). Finally, we propose a Decision Structure that exploits pairing, i.e., fusing the classifiers' Decisions sequentially two-by-two. Two pairing schemes, i.e., incremental and tournament-like, are proposed and we show that incremental pairing is the most effective Decision Structure among the proposed ones.
Yasemin Arda - One of the best experts on this subject based on the ideXlab platform.
-
supply chain coordination a game theory approach
Engineering Applications of Artificial Intelligence, 2008Co-Authors: Jeanclaude Hennet, Yasemin ArdaAbstract:In a supply chain organized as a network of autonomous enterprises, the main objective of each partner is to optimize his production and supply policy with respect to his own economic criterion. Conflicts of interests and the distributed nature of the Decision Structure may induce a global loss of efficiency. Contracts can then be used to improve global performance and decrease risks. The purpose of the paper is to evaluate the efficiency of different types of contracts between the industrial partners of a supply chain. Such an evaluation is made on the basis of the relationship between a producer facing a random demand and a supplier with a random lead-time. The model combines queuing theory for evaluation aspects and game theory for Decisional purposes.
Janine A. Van Til - One of the best experts on this subject based on the ideXlab platform.
-
Comparison of analyic hierarchy process and conjoint analysis methods in assessing treatment alternatives in stroke rehabilitation
Value in Health, 2010Co-Authors: M Ijzerman, John F. P. Bridges, Janine A. Van TilAbstract:OBJECTIVES: There has been increasing interest novel HTA methods that will incorporate patient preferences in a more transparent and scientifically valid way. The fundamental problem of the assessment of benefits in HTA is the identification, ranking and valuation of multiple health care outcomes. We used two multi-criteria methods to rank and value five different treatments in stroke rehabilitation. Analytic Hierarchy Process (AHP) stems from operations research and is increasingly being used in health care to weigh patient-reported endpoints. Conjoint analysis (CA) is a stated preference method that often takes the discrete choice format. In CA, hypothetical scenarios are used to generate part-worth utilities for attributes. METHODS: To determine the clinical Decision context and related criteria, a paper-and-pencil questionnaire was conducted among a sample of Dutch physiatrists united in a stroke interest group. From the lists of criteria (e.g. clinical benefit, impact of treatment) an expert panel defined the AHP Decision Structure as well as the conjoint analysis survey format. Finally, the complete questionnaire including the AHP and CA survey was sent out to 184 patients with ankle-foot impairments. Eventually, 89 patients completed both surveys. RESULTS: On average, the prediction of preferred treatment on a group level is similar for both AHP and CA. However. on an inidividual level there seems to be more variation in treatment preference. Using AHP weights, a vast majority preferred soft-tissue surgery where most patients preferred orthopedic shoes if CA weights were used. This may have been caused by labelling effects of the attributes. CONCLUSIONS: Both methods have there pros and cons in ranking and valuing patient-reported endpoints. Of the methods AHP is relatively easy to apply. In prediction of overall outcome, both methods perform equally. However, for individual treatment preference we observed some differences. It may be concluded that the Decision Structure, framing and labelling of the treatment attributes are more important than the specific elicitation method used.
Baro Hyun - One of the best experts on this subject based on the ideXlab platform.
-
Optimal fusion rules in team classification under three Decision Structures
2013 American Control Conference, 2013Co-Authors: Baro Hyun, Pierre Kabamba, Anouck GirardAbstract:In this paper, we study the performance of a team of dichotomous classifiers, where the classifiers' Decisions are combined by logical fusion rules. Three Decision Structures are derived using the confusion matrix of a single classifier and a priori information, and the performances of the different Decision Structures are compared. First, we consider the performance of a team of three classifiers with a total of 256 fusion rules. Then, we propose a Decision Structure that utilizes a moderator, i.e., an entity that exploits Bayesian inference from individual classifiers' Decisions and makes final Decisions based on maximum likelihood classification. We show the benefits of using a moderator (compared to a Decision Structure without a moderator). Finally, we propose a Decision Structure that exploits pairing, i.e., fusing the classifiers' Decisions sequentially two-by-two. Two pairing schemes, i.e., incremental and tournament-like, are proposed and we show that incremental pairing is the most effective Decision Structure among the proposed ones.
-
ACC - Optimal fusion rules in team classification under three Decision Structures
2013 American Control Conference, 2013Co-Authors: Baro Hyun, Pierre Kabamba, Anouck GirardAbstract:In this paper, we study the performance of a team of dichotomous classifiers, where the classifiers' Decisions are combined by logical fusion rules. Three Decision Structures are derived using the confusion matrix of a single classifier and a priori information, and the performances of the different Decision Structures are compared. First, we consider the performance of a team of three classifiers with a total of 256 fusion rules. Then, we propose a Decision Structure that utilizes a moderator, i.e., an entity that exploits Bayesian inference from individual classifiers' Decisions and makes final Decisions based on maximum likelihood classification. We show the benefits of using a moderator (compared to a Decision Structure without a moderator). Finally, we propose a Decision Structure that exploits pairing, i.e., fusing the classifiers' Decisions sequentially two-by-two. Two pairing schemes, i.e., incremental and tournament-like, are proposed and we show that incremental pairing is the most effective Decision Structure among the proposed ones.
Pablo Javier Alsina - One of the best experts on this subject based on the ideXlab platform.
-
ISM - Consonantal Recognition Using SVM and New Hierarchical Decision Structure Based in the Articulatory Phonetics
2008 Tenth IEEE International Symposium on Multimedia, 2008Co-Authors: A. De Andrade Bresolin, Adrião Duarte Dória Neto, Pablo Javier AlsinaAbstract:In this work, a new concept of making the consonantal recognition is proposed. We used several units (phonemes, diphones and syllables) to make the word recognition. This concept was carried out by a new hierarchical Decision Structure, based on the articulatory phonetics and SVM (support vector machine). The speech features used were MFCC (mel-frequency cepstral coefficient) and WPT (waveletpacket transform). Eighteen consonantal phonemes have been used in the recognition. The database used for the recognition was a set of two-syllable words of the Brazilian Portuguese language. The experimental results showed success rates of 98.41% for the user dependent case.
-
Consonantal Recognition Using SVM and New Hierarchical Decision Structure Based in the Articulatory Phonetics
2008 Tenth IEEE International Symposium on Multimedia, 2008Co-Authors: Adriano De A. Bresolin, Adriao Duarte D. Neto, Pablo Javier AlsinaAbstract:In this work, a new concept of making the consonantal recognition is proposed. We used several units (phonemes, diphones and syllables) to make the word recognition. This concept was carried out by a new hierarchical Decision Structure, based on the articulatory phonetics and SVM (support vector machine). The speech features used were MFCC (mel-frequency cepstral coefficient) and WPT (waveletpacket transform). Eighteen consonantal phonemes have been used in the recognition. The database used for the recognition was a set of two-syllable words of the Brazilian Portuguese language. The experimental results showed success rates of 98.41% for the user dependent case.
-
Brazilian Vowels Recognition using a New Hierarchical Decision Structure with Wavelet Packet and SVM
2007 IEEE International Conference on Acoustics Speech and Signal Processing - ICASSP '07, 2007Co-Authors: A. De Andrade Bresolin, Adriao Duarte D. Neto, Pablo Javier AlsinaAbstract:In this work, a new phoneme recognition system is proposed. The base of Decision of the proposed system is the tongue position and roundedness of the lips. The features of the speech are the coefficients of wavelet packet transform with sub-bands selected through the Mel scale. The SVM (support vector machine) is used as classifier in the Structure of a hierarchical committee machine. The database used for the recognition was a set of oral vocalic phonemes of the Portuguese language. The experimental results show success rates of 98.07% for the user-dependent case and 91.01% for the user-independent case. This new proposal increased 4.1% and 3.5% the success rate in relation to the "one vs. all" Decision strategy, to user-dependent and user-independent case respectively.
