Browsing by Author "Chandana, T.L."

Now showing 1 - 4 of 4

Feature engineering on forest cover type data with ensemble of decision trees
(2015) Pruthvi, H.R.; Nisha, K.K.; Chandana, T.L.; Navami, K.; Biju, R.M.
The paper aims to determine the forest cover type of the dataset containing cartographic attributes evaluated over four wilderness areas of Roosevelt National Forest of Northern Colorado. The cover type data is provided by US Forest service inventory, while Geographic Information System (GIS) was used to derive cartographic attributes like elevation, slope, soil type etc. Dataset was analyzed, pre processed and feature engineering techniques were applied to derive relevant and non-redundant features. A comparative study of various decision tree algorithms namely, CART, C4.5, C5.0 was performed on the dataset. With the new dataset built by applying feature engineering techniques, Random Forest and C5.0 improved the accuracy by 9% compared to the raw dataset. � 2015 IEEE.
Feature engineering on forest cover type data with ensemble of decision trees
(Institute of Electrical and Electronics Engineers Inc., 2015) Pruthvi, H.R.; Nisha, K.K.; Chandana, T.L.; Navami, K.; Mohan, R.
The paper aims to determine the forest cover type of the dataset containing cartographic attributes evaluated over four wilderness areas of Roosevelt National Forest of Northern Colorado. The cover type data is provided by US Forest service inventory, while Geographic Information System (GIS) was used to derive cartographic attributes like elevation, slope, soil type etc. Dataset was analyzed, pre processed and feature engineering techniques were applied to derive relevant and non-redundant features. A comparative study of various decision tree algorithms namely, CART, C4.5, C5.0 was performed on the dataset. With the new dataset built by applying feature engineering techniques, Random Forest and C5.0 improved the accuracy by 9% compared to the raw dataset. Â© 2015 IEEE.
Language modelling and english speech prediction system to aid people with stuttering disorder
(2015) Chandana, T.L.; Kalwad, P.S.; Pattanaik, S.; Ram Mohana Reddy, Guddeti
This paper proposes a novel method to predict the speech based on N-Gram language model for English Language. It also concentrates on how Speech Completion can be combined with stuttering detection to aid people suffering from this disorder to overcome psychological and social introversion. To the best of our knowledge, such systems exist only in Japanese language and hence, this paper is the first to introduce such an application for English language. The existing work in Japanese language uses a vocabulary tree structure for prediction in contrast to the n-gram language model used in this paper. The basic idea of the proposed work is to consider the user's speech input for detecting the repetition of words as stuttering. If this repetition of words is detected then, the next word can be predicted after eliminating the repeated word using the n-gram language model and the predicted word can be converted back to speech. Using this proposed methodology, we are able to achieve a prediction accuracy of 87% when a 10-fold test is carried out. � 2015 ACM.
Language modelling and english speech prediction system to aid people with stuttering disorder
(Association for Computing Machinery acmhelp@acm.org, 2015) Chandana, T.L.; Kalwad, P.S.; Pattanaik, S.; Guddeti, G.
This paper proposes a novel method to predict the speech based on N-Gram language model for English Language. It also concentrates on how Speech Completion can be combined with stuttering detection to aid people suffering from this disorder to overcome psychological and social introversion. To the best of our knowledge, such systems exist only in Japanese language and hence, this paper is the first to introduce such an application for English language. The existing work in Japanese language uses a vocabulary tree structure for prediction in contrast to the n-gram language model used in this paper. The basic idea of the proposed work is to consider the user's speech input for detecting the repetition of words as stuttering. If this repetition of words is detected then, the next word can be predicted after eliminating the repeated word using the n-gram language model and the predicted word can be converted back to speech. Using this proposed methodology, we are able to achieve a prediction accuracy of 87% when a 10-fold test is carried out. Â© 2015 ACM.