Indian Institute of Technology Guwahati

About: Indian Institute of Technology Guwahati is a education organization based out in Guwahati, Assam, India. It is known for research contribution in the topics: Catalysis & Computer science. The organization has 6933 authors who have published 17102 publications receiving 257351 citations.

Relation extraction from clinical texts using domain invariant convolutional neural network

Abstract: In recent years extracting relevant information from biomedical and clinical texts such as research articles, discharge summaries, or electronic health records have been a subject of many research efforts and shared challenges. Relation extraction is the process of detecting and classifying the semantic relation among entities in a given piece of texts. Existing models for this task in biomedical domain use either manually engineered features or kernel methods to create feature vector. These features are then fed to classifier for the prediction of the correct class. It turns out that the results of these methods are highly dependent on quality of user designed features and also suffer from curse of dimensionality. In this work we focus on extracting relations from clinical discharge summaries. Our main objective is to exploit the power of convolution neural network (CNN) to learn features automatically and thus reduce the dependency on manual feature engineering. We evaluate performance of the proposed model on i2b2-2010 clinical relation extraction challenge dataset. Our results indicate that convolution neural network can be a good model for relation exaction in clinical text without being dependent on expert’s knowledge on defining quality features.

Measurement of the branching fraction B(Λc+ → pK-π+).

Abstract: We present the first model-independent measurement of the absolute branching fraction of the Lambda(+)(c) -> pK(-)pi(+)decay using a data sample of 978 fb(-1) collected with the Belle detector at the KEKB asymmetric-energy e(+)e(-) collider. The number of Lambda(+)(c) baryons is determined by reconstructing the recoiling D(*)(-)(p) over bar pi(+)system in events of the type e(+)e(-) -> D(*)(-)(p) over bar pi(+)Lambda(+)(c). The branching fraction is measured to be B(Lambda(+)(c) -> pK(-)pi(+)) = (6.84 +/- 0.24(-0.27)(+0.21))%, where the first and second uncertainties are statistical and systematic, respectively.

Influence of geosynthetic encasement on the performance of stone columns floating in soft clay

Abstract: This paper investigates the influence of geosynthetic encasement on the performance of stone columns floating in soft clay. It was found that with unencased columns the bearing capacity improvement...

Conjugated Polyelectrolyte Based Sensitive Detection and Removal of Antibiotics Tetracycline from Water

Abstract: A new conjugated polyelectrolyte poly[5,5′-(((2-phenyl-9H-fluorene-9,9-diyl)bis(hexane-6,1-diyl))bis(oxy))diisophthalate] sodium (PFPT) was synthesized via the palladium-catalyzed Suzuki cross-coupling polymerization method and successfully applied for the rapid, real time, and highly sensitive detection of antibiotics tetracycline (Tc) in 100% aqueous media via photoinduced electron transfer with detection limit in the ppb level. Remarkably, PFPT could also be applied for the trace analysis of Tc in serum samples having recoveries well in the range 92–97% with relative standard deviations (RSD) of 1.01–1.14%, confirming reliability of the present method for the analysis of Tc. Additionally, PFPT was blended with the abundant natural polysaccharide chitosan to form CS-PFPT composite films and developed as a biopolymer based membrane for the removal of Tc from water samples with a good adsorption capacity of 3.12 mg g–1, thus finding vital application in the treatment of antibiotic infested wastewater.