Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
4 results
Search Results
Item Unsupervised Abstractive Text Summarization with Length Controlled Autoencoder(Institute of Electrical and Electronics Engineers Inc., 2022) Dugar, A.; Singh, G.; Balamuralidhar, B.; Anand Kumar, A.M.This work deals with taking an unsupervised approach to abstractive text summarization where a large set of sentences is converted into a concise summary highlighting the essential details. This is achieved with the use of an adversarial autoencoder model. The model encodes the input to a smaller latent vector and the decoder decodes this latent code to generate the higher dimensional output with some loss. Unlike variational autoencoders, AAE's use discriminators to learn using adversarial loss. K-Means clustering and language models are used to get the final summary. This model has been tested with different datasets like the Amazon, Rotten Tomatoes and Yelp reviews dataset to essentially do an opinion summarization task and this is finally evaluated using ROGUE-1, ROGUE-2,ROGUE-L and BLEU scores. The same task is also conducted on a dataset in Hindi. We obtain a ROGUE-1 score of around 24% for Amazon, Yelp and CNN/Daily Mail dataset and a score of 12% for Rotten Tomatoes while the score obtained for the Hindi news articles dataset is only 8%. © 2022 IEEE.Item Prediction of Drug Interactions Using Graph-Topological Features and GNN(Springer Science and Business Media Deutschland GmbH, 2023) Balamuralidhar, N.; Surendran, P.; Singh, G.; Bhattacharjee, S.; Shetty, R.D.The risk of side effects is sometimes inevitable every time two or more drugs are prescribed together, and these side effects of varying adversity levels can be referred to as drug-drug interactions (DDI). Massive amounts of data and the constraints of experimental circumstances result in clinical trials for medication compatibility being time-consuming, risky, expensive, and impractical. Recent research has demonstrated that DDI can be modelled as graphs and experimentally shown that deep learning on graphs can be a practical choice for determining the correlation and side effects of taking multiple medications simultaneously. We propose a novel approach to use inductive graph learning with GraphSAGE, along with topological features, to leverage the structural information of a graph along with the node attributes. An experimental study of the approach is done on a publicly available subset of the DrugBank dataset. We achieve our best results that are comparable with state-of-the-art works using degree, closeness and PageRank centrality measures as additional features with less computational complexity. This study can provide a reliable and cost-effective alternative to clinical trials to predict dangerous side effects, ensuring the safety of patients. © 2023, IFIP International Federation for Information Processing.Item The objective of the present study is to predict analytically the material perforation under hyper velocity impact. Hyper velocity impact is a complex phenomenon involving wave propagation, penetration and responses exceeding elastic limits, leading to hydrodynamic behaviour. A general-purpose program (GPP) that permits a combination of non-linear finite element technique and explicit integration scheme, is employed for the simulations. The geometry of perforation is computed for various projectiles with different incident angles, impact velocities and materials. The computed values are compared with test results available in the literature. The results indicate excellent agreement with the measurements and give good insight into the effect of various parameters on the perforation size and geometry.(Perforation under hyper velocity impact - A prediction using finite element technique) Suhas, M.; Samgeeth, R.; Veenaranjini, S.M.; Singh, G.2005Item Air quality assessment of Dhanbad District, India - A case study(2010) Anantharamu, A.; Singh, G.; Venkat Reddy, D.Ambient air pollution status in Dhanbad district is studied and presented in this article. The selection of Dhanbad is made considering its importance and the nature of activities taking place around the district. For the assessment of ambient air quality in Dhanbad, the following five locations were chosen: Main Gate of Indian School of Mines(ISM), Dhanbad: It is a site representing purely commercial activities and road traffic. Bankmore: It is one of the busiest marketing centres of the district and is surrounded by residential areas. All the vehicles going to Bokaro pass by this place and thus the traffic density is pretty high. Kusunda: It is a place 10.9 kilometres from Dhanbad Railway Station. It is just beside one of the coal mines, hence, all vehicles going to the mine passes through this place. Steel Gate: It consists of a small market. Trucks and other heavy vehicle are more frequent during night as this road connects to a highway. ISM Admin Block: It can be considered as a sensitive area since it is a very calm place where the usage of vehicles is minimum throughout the day. Monitoring of ambient air quality is done following the standard procedure prescribed in IS: 5182. In addition, the concentration of lead, zinc, cadmium, copper, manganese and iron metals in SPM is also monitored. The ambient air quality assessment was done in the month of June, 2009. The concentration of SPM was higher than the permissible limit in three locations namely ISM Main Gate, Bankmore and Steel Gate, while it was less than the permissible limit in other two locations, ISM Admin Block and Kusunda. Since the generation of SPM was mainly due to vehicular traffic it was expected to cross the limit in the above mentioned three locations as density of vehicular movement is very high. © 2010 CAFET-INNOVA TECHNICAL SOCIETY.