• Journal of Information Processing Systems
• /
• v.13 no.1
• /
• pp.174-183
• /
• 2017

In this paper, we propose a novel feature for recognizing handwritten Odia numerals. By using polygonal approximation, each numeral is segmented into segments of equal pixel counts where the centroid of the character is kept as the origin. Three primitive contour features namely, distance (l), angle (${\theta}$), and arc-tochord ratio (r), are extracted from these segments. These features are used in a neural classifier so that the numerals are recognized. Other existing features are also considered for being recognized in the neural classifier, in order to perform a comparative analysis. We carried out a simulation on a large data set and conducted a comparative analysis with other features with respect to recognition accuracy and time requirements. Furthermore, we also applied the feature to the numeral recognition of two other languages-Bangla and English. In general, we observed that our proposed contour features outperform other schemes.

• Journal of information and communication convergence engineering
• /
• v.18 no.4
• /
• pp.207-215
• /
• 2020

Part of speech (POS) tagging is an indispensable part of major NLP models. Its progress can be perceived on number of languages around the globe especially with respect to European languages. But considering Indian Languages, it has not got a major breakthrough due lack of supporting tools and resources. Particularly for Odia language it has not marked its dominancy yet. With a motive to make the language Odia fit into different NLP operations, this paper makes an attempt to develop a POS tagger for the said language on a HMM (Hidden Markov Model) platform. The tagger judiciously considers bigram HMM with dynamic Viterbi algorithm to give an output annotated text with maximum accuracy. The model is experimented on a corpus belonging to tourism domain accounting to a size of approximately 0.2 million tokens. With the proportion of training and testing as 3:1, the proposed model exhibits satisfactory result irrespective of limited training size.

• Safety and Health at Work
• /
• v.4 no.2
• /
• pp.100-104
• /
• 2013

Background: The aim of this study was to assess public and private medical diagnostic laboratories in Nigeria for the presence of biosafety equipment, devices, and measures. Methods: A total of 80 diagnostic laboratories in biosafety level 3 were assessed for the presence of biosafety equipment, devices, and compliance rate with biosafety practices. A detailed questionnaire and checklist was used to obtain the relevant information from enlisted laboratories. Results: The results showed the presence of an isolated unit for microbiological work, leak-proof working benches, self-closing doors, emergency exits, fire extinguisher(s), autoclaves, and hand washing sinks in 21.3%, 71.3%, 15.0%, 1.3%, 11.3%, 82.5%, and 67.5%, respectively, of all laboratories surveyed. It was observed that public diagnostic laboratories were significantly more likely to have an isolated unit for microbiological work (p = 0.001), hand washing sink (p = 0.003), and an autoclave ($p{\leq}0.001$) than private ones. Routine use of hand gloves, biosafety cabinet, and a first aid box was observed in 35.0%, 20.0%, and 2.5%, respectively, of all laboratories examined. Written standard operating procedures, biosafety manuals, and biohazard signs on door entrances were observed in 6.3%, 1.3%, and 3.8%, respectively, of all audited laboratories. No biosafety officer(s) or records of previous spills, or injuries and accidents, were observed in all diagnostic laboratories studied. Conclusion: In all laboratories (public and private) surveyed, marked deficiencies were observed in the area of administrative control responsible for implementing biosafety. Increased emphasis on provision of biosafety devices and compliance with standard codes of practices issued by relevant authorities is strongly advocated.