Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
2 results
Search Results
Item An effective feature extraction with deep neural network architecture for protein-secondary-structure prediction(Springer, 2021) Jayasimha, A.; Mudambi, R.; Pavan, P.; Lokaksha, B.M.; Bankapur, S.; Patil, N.With the increased importance of proteins in day-to-day life, it is imperative to know the protein functions. Deciphering protein structure elucidates protein functions. Experimental approaches for protein-structure analysis are expensive and time-consuming, and require high dexterity. Thus, finding a viable computational approach is vital. Due to the high complexity of predicting protein structure (tertiary structure) directly, research in this field aims at the protein-secondary-structure prediction which is directly related to its tertiary structure. This research aims at exploring a plethora of features, namely position-specific scoring matrices, hidden Markov model alignment matrices, and physicochemical properties, that carry rich information required to predict the secondary structure. Furthermore, it aims at exploring a suitable combination of the features which could capture diverse information about the protein secondary structure. Finally, a cascaded convolutional neural network and bidirectional long short-term memory architecture is fit on the models, and two evaluation metrics, namely, Q8 score and segment overlap score, are benchmarked on various datasets. Our proposed model trained on data of CB6133 dataset and tested on CB513 dataset beats the benchmark models by a minimum of 2.9%. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.Item Nature-inspired query optimisation models for medical information retrieval with relevance feedback(Inderscience Publishers, 2023) Jayasimha, A.; Mudambi, R.; Kamath S․, S.S.Medical information retrieval (MedIR) involves retrieving relevant medical-related information from a set of medical documents for a particular user query. As the volume of medical records grows, the challenging problem is determining those documents which best suiting a given query by considering user satisfaction. Statistical term weighting and probabilistic approaches for this purpose have several limitations. The gap between information need and user query can be addressed through query optimisation and relevance feedback. In this paper, we propose a document retrieval framework that incorporates query optimisation using techniques like genetic algorithm, particle swarm optimisation (PSO), and global swarm optimisation (GSO). Further, we use relevance feedback methods to reformulate the user query. The proposed techniques are applied to datasets with predefined relevance judgments to perform quantitative validation. Experimental results using the relevance judgements available in the University of Glasgow's Medline collection underscored the significant improvement achieved using BM25 scores as the fitness function. © 2023 Inderscience Enterprises Ltd.