No abstract

No abstract

Climate change impact is one of the major burning issues all over the world where Bangladesh is one of the most affected areas. The aim of this study was to understand the climate-induced migrationrelated issues in the coastal areas of Chittagong. A total of 120 individual surveys and six key informant interviews were done in six unions of Banshkhali Upazila in Chittagong district. The result showed that agriculture and fishing practices are reducing compared to the past and people are more interested in migrating abroad. Among the six villages, the highest percentage of migration was found to be from the areas closer to the coast compared to others. Despite less awareness on climate change terms, most of the respondents have positively replied to the changes in the frequencies of climatic hazards. Several forms of driver, e.g. environmental, social and political are also discussed. The linear regression showed that the factors which positively influence the peoples' decision to migrate are average family age and social status. The dependency on agriculture, business near coast and fishing has a coefficient of −0.18, −0.36 and −0.24, respectively. Identification of community-based needs is important to ensure safe migration as an adaptation against climate change.

Research on recognizing Bengali script has been started since mid 1980's. A variety of different techniques have been applied and the performance is examined. In this paper we present a high performance domain specific OCR for recognizing Bengali script. We select the training data set from the script of the specified domain. We choose Hidden Markov Model (HMM) for character classification due to its simple and straightforward way of representation. We examine the primary error types that mainly occurred at preprocessing level and carefully handled those errors by adding special error correcting module as a part of recognizer. Finally we added a dictionary and some error specific rules to correct the probable errors after the word formation is done. The entire technique significantly increases the performance of the OCR for a specific domain to a great extent.

Abstract. In this paper, we study different discrete data clustering methods, which use the Model-Based Clustering (MBC) framework with the Multinomial distribution. Our study comprises several relevant issues, such as initialization, model estimation and model selection. Additionally, we propose a novel MBC method by efficiently combining the partitional and hierarchical clustering techniques. We conduct experiments on both synthetic and real data and evaluate the methods using accuracy, stability and computation time. Our study identifies appropriate strategies to be used for discrete data analysis with the MBC methods. Moreover, our proposed method is very competitive w.r.t. clustering accuracy and better w.r.t. stability and computation time.