Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
Item Domain-specific sentiment analysis approaches for code-mixed social network data(Institute of Electrical and Electronics Engineers Inc., 2017) Pravalika, A.; Oza, V.; Meghana, N.P.; Kamath S․, S.Sentiment Analysis is one of the prominent research fields in Natural Language Processing because of its widespread real-world applications. Customer preferences, options and experiences can be analyzed through social media, reviews, blogs and other online social networking site data. However, due to increasing informal usage of local languages in social media platforms, multi-lingual or code-mixed data is fast becoming a common occurrence. Mixed code is generated when users use more than a single language in social network comments. Such data presents a significant challenge for applications using sentiment analysis and is yet to be fully explored by researchers. Existing sentiment analysis methods applied to monolingual social data are not suitable for code-mixed data due to the inconsistency in the grammatical structure in these sentences. In this paper, a novel method focused on performing effective sentiment analysis of bilingual sentences written in Hindi and English is proposed, that takes into account linguistic code switching and the grammatical transitions between the two considered languages. Experimental evaluation using real-world, code-mixed datasets obtained from Facebook showed that the proposed approach achieved very good accuracy and was also efficient performance-wise. © 2017 IEEE.Item A supervised learning approach for ICU mortality prediction based on unstructured electrocardiogram text reports(Springer Verlag service@springer.de, 2018) S. Krishnan, G.S.; Kamath S․, S.Extracting patient data documented in text-based clinical records into a structured form is a predominantly manual process, both time and cost-intensive. Moreover, structured patient records often fail to effectively capture the nuances of patient-specific observations noted in doctors’ unstructured clinical notes and diagnostic reports. Automated techniques that utilize such unstructured text reports for modeling useful clinical information for supporting predictive analytics applications can thus be highly beneficial. In this paper, we propose a neural network based method for predicting mortality risk of ICU patients using unstructured Electrocardiogram (ECG) text reports. Word2Vec word embedding models were adopted for vectorizing and modeling textual features extracted from the patients’ reports. An unsupervised data cleansing technique for identification and removal of anomalous data/special cases was designed for optimizing the patient data representation. Further, a neural network model based on Extreme Learning Machine architecture was proposed for mortality prediction. ECG text reports available in the MIMIC-III dataset were used for experimental validation. The proposed model when benchmarked against four standard ICU severity scoring methods, outperformed all by 10–13%, in terms of prediction accuracy. © 2018, Springer International Publishing AG, part of Springer Nature.Item ML based QSAR Models for Prediction of Pharmacological Permeability of Caco-2 Cell(Institute of Electrical and Electronics Engineers Inc., 2021) Likitha, S.; Kamath S․, S.In the initial stages of de novo drug discovery, numerous drug components need to be considered, in order to determine those candidates which bind to a particular disease protease. The greater the binding effect the better the drug efficacy. However, mapping every potentially relevant drug and its effect on the protein is a time consuming task. To discard the drugs at the initial stage we can know how much permeable a drug is through a particular layer or cell membrane. A potential approach to determine this by measuring the permeability of a compound through a specific layer. In this paper, an approach for QSAR regression for predicting pharmacological permeability of the Caco-2 cell is proposed. The compounds are represented by chemical descriptors calculated from their construction properties and structural properties sets of descriptors were derived from the chemical compounds structures. Linear regression, nonlinear regression and nonlinear artificial neural network models were experimented with to correlate their reported permeability value. Two different sets of chemical descriptors were derived and each set was used for training different machine learning and neural network models. The results were evaluated using standard metrics like mean square error and R-squared error, during which it was observed that boosting based ML models achieved the lowest values when compared to other regression models. © 2021 IEEE.Item Spatio-temporal Analysis and Modeling of Coastal areas for Water Salinity Prediction(Institute of Electrical and Electronics Engineers Inc., 2023) Sudhakara, B.; Priyadarshini, R.; Bhattacharjee, S.; Kamath S․, S.; Umesh, P.; Gangadharan, K.V.; Ghosh, S.K.Salinity is an important parameter affecting the quality of water, and excessive amounts adversely affect vege-tation growth and aquatic organism populations. Natural factors like tidal waves, natural calamities etc., and man-made factors like unchecked disposal of industrial wastes, domestic/ urban sewage, and fish hatchery activities can cause significant increases in water salinity. In this article, an approach that utilizes multimodal data like Landsat 8 optical observations and the SMAP salinity data product for predicting water salinity indices in the coastal region is proposed. Machine Learning models such as K-nearest neighbor (KNN), Gradient Boost (GB), Extremely Randomized Tree (ERT), Random Forest Regression (RFR), Decision Tree (DT), Multiple Linear Regression (MLR), Lasso Regression (LR), and Ridge Regression (RR) are used for salinity prediction. Empirical experiments revealed that the ERT model outperformed other ML models, with a R2 of 0.92 and RMSE of 0.25 psu. © 2023 IEEE.