Session Program

 

  • 11 July 2017
  • 08:00AM - 10:00AM
  • Room: Sveva
  • Chairs: Antonino Staiano Angelo Ciaramella and Sushmita Mitra

Advances in Soft Computing modelling for biomedical data

Abstract - Modern methods for ab initio prediction of protein structures typically analyze multiple simulated conformations, called decoys, to find the best native-like conformations. To limit the search space, clustering algorithms are routinely used to group similar decoys, based on the hypothesis that the largest group of similar decoys will be the closest to the native state. In this paper a novel clustering algorithm, called Graded Possibilistic c-Medoids, is proposed and applied to a decoy selection problem. As it will be shown, the added flexibility of the graded possibilistic framework allows a very effective selection of the best decoys with respect to similar methods based on medoids - that is the most central points belonging to each cluster. The proposed algorithm has been compared with other c-medoids algorithms and also with SPICKER on real data, the large majority of times outperforming both.
Abstract - Brain tumors constitute one of the deadliest forms of cancers, with a high mortality rate. Of these, Glioblastoma multiforme (GBM) remains the most common and lethal primary brain tumor in adults. Tumor biopsy being challenging for brain tumor patients, noninvasive techniques like imaging play an important role in the process of brain cancer detection, diagnosis and prognosis; particularly using Magnetic Resonance Imaging (MRI). Therefore, development of advanced extraction and selection strategies of quantitative MRI features become necessary for noninvasively predicting and grading the tumors. In this paper we extract 56 three-dimensional quantitative MRI features, related to tumor image intensities, shape and texture, from 254 brain tumor patients. An adaptive neuro-fuzzy classifier based on linguistic hedges (ANFC-LH) is developed to simultaneously select significant features and predict the tumor grade. ANFCLH achieves a significantly higher testing accuracy (85:83\%) as compared to existing standard classifiers.
Abstract - Computing with Words (CW) is a concept which solves problems when input is provided in form of natural language. CW is at its initial stages and is not at its full potential. Medicine is a pivotal field and CW has barely been explored here. This paper concentrates on how to use CW methods to overcome challenging problems in medicine. It especially focuses on finding a solution to help Dementia affected people whose symptoms are not curable. The latter part lists down some more ways in which CW can affect areas in medicine.
Abstract - In fuzzy logic context, some works deal with the camphor odor perception. In this paper, we present a novel rule-based decision system for the camphor odor recognition within unbalanced multiset. Our first contribution consists in an adaptation of fuzzy knowledge representation and inference rules to the multi- valued logic context. The second contribution concerns the improvement of the knowledge base by changing facts representation and adding new rules. This proposition provides satisfactory results in term of precision, recall, F- measure and accuracy.
Abstract - Human activity recognition (HAR) is an important research issue for pervasive computing that aims to identify human activities. Extracted features from raw sensors are often large and some of them can be irrelevant and redundant. Therefore, it's important to perform feature selection to select the most relevant features in order to increase the recognition accuracy. However, classical feature selection methods are generally linear and sequential and they do not consider existing dependencies and interactions among activities (classes). To overcome this shortcoming, a feature selection based on Choquet integral for HAR is proposed in this paper. The Choquet integral is a non linear and a non additive method. It's employed to determine scores for features by modeling interactions between activities through the fuzzy measure theory. Classification results on HAR dataset using Random Forest classifier indicate that the recognition accuracy remains stable using half of the features. Moreover, classification performance is further improved.