Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Deep Learning Based LSTM and SeqToSeq Models to Detect Monsoon Spells of India(Springer Verlag service@springer.de, 2019) Saicharan, S.; Saha, M.; Mitra, P.; Nanjundiah, R.S.Monsoon spells are important climatic phenomenon modulating the quality and quantity of monsoon over a year. India being an agricultural country, identification of monsoon spells is extremely important to plan agricultural policies following the phases of monsoon to attain maximum productivity. Monsoon spells’ detection involve analyzing and predicting monsoon at daily levels which make it more challenging as daily-variability is higher as compared to monsoon over a month or an year. In this article, deep-learning based long short-term memory and sequence-to-sequence models are utilized to classify monsoon days, which are finally assembled to detect the spells. Dry and wet days are classified with precision of 0.95 and 0.87, respectively. Break spells are observed to be forecast with higher accuracy than the active spells. Additionally, sequence-to-sequence model is noted to perform superior to that of long-short term memory model. The proposed models also outperform traditional classification models for monsoon spell detection. © Springer Nature Switzerland AG 2019.Item Attention-Based CRNN Models for Identification of Respiratory Diseases from Lung Sounds(Institute of Electrical and Electronics Engineers Inc., 2023) Sanjana, J.; Naik, P.P.; Mahesh, M.A.; Koolagudi, S.G.; Rajan, J.Respiratory diseases are a major global health concern, with millions of people suffering from disorders such as asthma, bronchitis, chronic obstructive pulmonary disease (COPD), and pneumonia. In recent years, machine learning and other forms of Artificial Intelligence have proven to be useful resources for resolving issues in the medical field. In this study, we examine the diagnostic utility of Convolutional Recurrent Neural Network (CRNN) models for identifying respiratory diseases using digitally recorded lung sounds. We developed two deep learning models to diagnose and classify lung diseases: a binary classification to classify COPD and non-COPD, and a multi-class classification model to classify five lung disorders (COPD, URTI-upper respiratory tract infection, Pneumonia, Bronchiectasis and Bronchiolitis) and healthy conditions. The ICBHI 2017 challenge dataset [1] was used to develop the models. The accuracy of the binary and multiclass classification models was 98.6% and 97.6%, respectively, with ICBHI Scores of 0.9866 and 0.9723. © 2023 IEEE.Item OntoPred: An Efficient Attention-Based Approach for Protein Function Prediction Using Skip-Gram Features(Springer, 2023) Chintawar, S.; Kulkarni, R.; Patil, N.Proteins play an essential role in performing many cellular functions in organisms and are responsible for various biochemical activities. The main objective of this task of protein function prediction is to annotate protein sequences with their correct functions, which are represented by Gene Ontology (GO) terms. Recently, the number of new proteins released has been increasing. As the experimental approach of annotating these proteins is very time-consuming, the need for faster annotation techniques has arisen. Approaches using deep learning and machine learning have been shown to be beneficial in this regard. In this research, we propose a novel approach, OntoPred, for the task of function prediction which makes use of the standalone protein sequences and annotates them with their corresponding functions (GO terms). The core idea is to use an attention mechanism to identify which parts of a sequence influence the presence of a function. The model uses a combination of n-grams and skip-gram features extracted from the sequences. The proposed model was evaluated on multiple datasets including the CAFA3 evaluation benchmark. The maximal F1 scores obtained on molecular function (MF), biological process (BP), and cellular component (CC) aspect on the CAFA3 evaluation benchmark are 0.494, 0.480, and 0.637 respectively. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.