Feature Selection for Recognition of Online Handwritten Bangla Characters

Feature selection through optimization techniques provides an interesting approach to minimize computational time with enhanced prediction capability, and     

Creep deformation and damage in a continuous fiber-reinforced Ti-6Al-4V composite

Mechanisms of longitudinal creep deformation and damage were studied in an eight-ply unidirectional-reinforced SCS-6/Ti-6Al-4V composite. The composite was creep tested in air under constant tensile load at temperatures from 427 °C to 650 °C and stresses from 621 to 1380 MPa.In situ acoustic emission (AE) monitoring and post-test metallographic evaluation were used to study fiber fracture and damage during creep. At low creep stresses, creep rates continuously decreased to near-zero values. This was attributed to a mechanism of matrix relaxation and the time-dependent redistribution of load from the ductile matrix to the elastic fibers. At higher stresses, progressive fiber overload occurred during creep loading. In this case, the composite exhibited a stage of decreasing creep rate (due primarily to matrix relaxation), followed by a secondary stage of nearly constant creep rate due to fiber fracture. The results indicate that interfacial oxidation damage and inefficient load transfer at elevated temperatures significantly decreased the capability of broken fibers to carry load. As a result, additional time-dependent stress redistribution occurred in the composite, which was responsible for the secondary creep stage.     

Co-Training by Committee: A Generalized Framework for Semi-Supervised Learning with Committees

Many data mining applications have a large amount of data but labeling data is often di cult, expensive, or time consuming, as it requires human experts for annotation.Semi-supervised learning addresses this problem by using unlabeled data together with labeled data to improve the performance. Co-Training is a popular semi-supervised learning algorithm that has the assumptions that each example is represented by two or more redundantly su cient sets of features (views) and additionally these views are independent given the class. However, these assumptions are not satis ed in many real-world application domains. In this paper, a framework called Co-Training by Committee (CoBC) is proposed, in which an ensemble of diverse classi ers is used for semi-supervised learning that requires neither redundant and independent views nor di erent base learning algorithms. The framework is a general single-view semi-supervised learner that can be applied on any ensemble learner to build diverse committees. Experimental results of CoBC using Bagging, AdaBoost and the Random Subspace Method (RSM) as ensemble learners demonstrate that error diversity among classi ers leads to an e ective Co-Training style algorithm that maintains the diversity of the underlying ensemble.     

Investigating fuzzy-input fuzzy-output support vector machines for robust voice quality classification

The dynamic use of voice qualities in spoken language can reveal useful information on a speakers attitude, mood and affective states. This information may be very desirable for a range of, both input and output, speech technology applications. However, voice quality annotation of speech signals may frequently produce far from consistent labeling. Groups of annotators may disagree on the perceived voice quality, but whom should one trust or is the truth somewhere in between? The current study looks first to describe a voice quality feature set that is suitable for differentiating voice qualities on a tense to breathy dimension. Further, the study looks to include these features as inputs to a fuzzy-input fuzzy-output support vector machine (F²SVM) algorithm, which is in turn capable of softly categorizing voice quality recordings. The F²SVM is compared in a thorough analysis to standard crisp approaches and shows promising results, while outperforming for example standard support vector machines with the sole difference being that the F²SVM approach receives fuzzy label information during training. Overall, it is possible to achieve accuracies of around 90% for both speaker dependent (cross validation) and speaker independent (leave one speaker out validation) experiments. Additionally, the approach using F²SVM performs at an accuracy of 82% for a cross corpus experiment (i.e. training and testing on entirely different recording conditions) in a frame-wise analysis and of around 97% after temporally integrating over full sentences. Furthermore, the output of fuzzy measures gave performances close to that of human annotators.     

Classification of bioacoustic time series based on the combination of global and local decisions

Automated classification of cricket songs from Thailand and Ecuador is the topic of this study. For this, the locations of pulses are determined and different features in the time and the frequency domain are extracted automatically from the time series. For the categorization of the sound patterns these features are combined through data fusion, temporal fusion and decision fusion. Local features and global features are distinguished. For the classification a fuzzy-k-nearest-neighbour classifier was used. Classification results for a data set containing songs of 28 different species are presented.     

Influence of foreign particles on fatigue behavior of Ti-6Al-4V prealloyed powder compacts

The effect of three types of contaminants on the fatigue life of prealloyed Plasma Rotating Electrode Process (PREP) Ti-6A1-4V hot isostatically pressed (HIP’d) powder compacts was studied. Ultraclean powder was seeded separately with SiO₂, A1₂O₃, and 316 stainless steel (SS) contaminants of 50 μm, 150 μ, and 350 μm nominal size, a total of nine conditions. Seeded compacts were fatigue tested at room temperature and the results were compared to those of an unseeded baseline compact. It was found that a substantial loss in fatigue life occurred even at the smallest seeded contaminants used in this work. Angular nonmetallic SiO₂ and A1₂O₃ contaminants were found to be more detrimental to fatigue strength than spherical metallic 316 SS contaminants of the same size range also indicating a shape effect. The loss of fatigue life suggests that at the high stress levels there is almost no crack initiation period and fatigue lives are controlled mainly by crack growth.