Search

The paper proposes a classification algorithm based on support tensor machines which finds the maximum margin between the tensor spaces. The proposed algorithm has been deployed to classify erythemato-squamous diseases (ESDs) with the help of its features. Features are derived from the skin lesion images of ESDs, and it has been represented as second-order tensors, i.e., $$ \varvec{X} \in \varvec{ }{\mathbb{R}}^{\varvec{n}} $$ can be transformed into $$ \varvec{X} \in \,\varvec{ }{\mathbf{\Re }}^{{\varvec{n}_{1} }} \,\varvec{ } \otimes \,{\mathbf{\Re }}^{{\varvec{n}_{2} }} $$ where $$ n_{1} \times n_{2} \cong n $$. After deriving the features from the skin lesion images, dominant features are extracted using Tucker tensor decomposition method. Most of the existing machine learning algorithms depend on the vector-based learning models, and these algorithms suffer from the data overfitting problem. To resolve this problem, in this paper, tensor-based learning is implemented for classification. Proposed algorithm is evaluated with the real-time dataset (Xie et al. in: He, Liu, Krupinski, Xu (eds) Health information science, Springer, Berlin, 2012), and higher classification accuracy of 99.93–100% is achieved. The acquired results are compared with the existing machine learning algorithms, and it drives home the point that the proposed algorithm provides higher classification accuracy.

Little Andaman, the fourth largest island in the Andaman group of islands of India, was severely affected by the December 26, 2004, Indian Ocean tsunami generated by massive earthquake of moment magnitude 9.3 Mw which devastated the Andaman and Nicobar group of islands causing heavy damage to life and property. Due to hostile terrain conditions not much information was available on the extent of inundation and run-up along the island except for Hut Bay region. In order to study the vulnerability of the island to tsunami hazard, the inundation in the island due to the 2004 tsunami was studied using TUNAMI N2 numerical model and ENVISAT ASAR datasets. The extent of inundation derived from the SAR imagery was compared using the RTK-GPS field survey points collected in the Hut Bay regions immediately after the 2004 tsunami. The extent of inundation obtained from SAR images for the entire island was compared with inundation obtained from model. It was observed that the inundation obtained from the model matched well with inundation extent from SAR imagery for nearshore regions, while for low-lying areas and creeks large deviations were observed. In the absence of field datasets, the inundation derived from SAR imagery would be effective in providing ground data to validate the numerical models which can then be run for multiple scenarios for disaster mitigation and planning operation in areas that have hostile terrain conditions.

This paper focuses on efficient techniques based on AdaBoost and its hybrid (AdaBoost-SVM) classifiers for an automatic detection of the erythemato-squamous diseases (ESD). The classification of ESD requires an enormous amount of computational effort, as all the features of the diseases have more than 90 % commonality. Some of the approaches reported in literature are fuzzy logic, artificial neural networks, neuro-fuzzy models and support vector machine. Recently, AdaBoost and its hybrid algorithms are widely used to enhance the accuracy of the learning algorithms. In this paper, we propose AdaBoost and its hybrid algorithms for diagnosis of erythemato-squamous diseases for the first time. User-friendly-interface is designed to assist dermatologists to estimate the ESD with the help of 34 features includes patient's histopathological and clinical data sets. Efficient interface design is based on the following steps: (1) feature selection for all the 34 parameters involved in the erythemato-squamous disease is done using association rule based Apriori algorithm, (2) association rules are used to find $$\upalpha \%$$?% of transactions (diseases) to meet $$\upbeta \%$$β% of the features of the diseases, (3) support value of all the subset of $$\upalpha $$? transaction from $$\upalpha \%$$?% of transactions is found and the dominant subset is found using Apriori algorithm, and (4) AdaBoost and its hybrid classifiers are used to classify the diseases. In this paper, the real, modest, gentle and hybrid AdaBoost algorithms are implemented and tested with the dataset of 366 patients. The data preprocessing reduces the dimensionality of the dataset and improves the time complexity of the estimation of the diseases. Proposed methodologies are proved as a potential solution for diagnosing ESD with significant improvement in computational time and accuracy compared to other models discussed in the recent literature.

The 2004 Indian Ocean tsunami had a significant impact on the Tamil Nadu coast in India. In this paper, a range of field survey data collected by different survey teams available in literature have been analyzed and compiled to serve as a basis for validation of numerical tsunami simulations. The individual field surveys reveal a significant scatter in the run-up data between the different teams, which point out that the uncertainty in these data must be taken into account when using them for validation. The inundation of the 2004 Indian Ocean tsunami is simulated for the coastlines of Chennai and Nagapattinam based on high-resolution topography. Different spatially uniform Manning friction as well as heterogeneous friction maps is used. Overall, the simulation results showed a good agreement with the field observations, but there are also some observed spatial variability in the goodness of the fit between the data and simulations. In some areas, clear discrepancies are found. The results obtained using detailed land use maps including spatially variable friction are not significantly more accurate than those employing spatially constant values. For most areas, parameters indicating relatively low friction provided best match with the observations. This may also suggest that the inundation is often strongly governed by local variations in topography.

Radionuclide gastro-esophageal scintigraphy was performed on 25 control and 183 children suffering from recurrent lower respiratory tract infection. Gastro-esophageal reflux (GER) of varying grades was observed in 135 patients. The severity of clinical symptoms in the patients was found to be directly related to the severity of reflux observed in the radionuclide study. In some patients an attempt was also made to quantitate GER by calculating the Gastro-esophageal reflux index. The results of the scintigraphic study were correlated with the results of the other commonly used and more conventional Barium swallow and fluoroscopy study. Gastro-esophageal scintigraphy was found to be much superior in terms of sensitivity, specificity and accuracy in detecting GER. It was also possible to objectively evaluate and monitor response to treatment following conservative or corrective surgical therapy using the radionuclide technique. The results of the study demonstrated a remarkably high incidence of GER in the patients. Whether GER is the cause of recurrent lower respiratory tract infection or not is difficult to establish firmly. But within the preview of the study the association seems to be very strong and cannot be easily ignored.