MUTE-Reco: MUTual Information Assisted Ensemble Feature RECOmmender System for Healthcare Prognosis

no code implementations • 28 Sep 2022 • Abhishek Dey, Debayan Goswami, Rahul Roy, Susmita Ghosh, Yu Shrike Zhang, Jonathan H. Chan

The performance of the proposed recommender is compared with four state-of-the-art methods using recommender systems' performance metrics like average precision@K, precision@K, recall@K, F1@K, reciprocal rank@K. Experimental results show that the model built with the recommended features can attain a higher accuracy (96. 6% and 98. 6% using support vector machine and neural network, respectively) for classifying different stages of ccRCC with a reduced feature set as compared to existing methods.

feature selection Recommendation Systems

Lexical Tone Recognition in Mizo using Acoustic-Prosodic Features

no code implementations • LREC 2020 • Parismita Gogoi, Abhishek Dey, Wendy Lalhminghlui, Priyankoo Sarmah, S R Mahadeva Prasanna

it is observed that the DNN based classifier shows comparable performance in correctly recognizing four phonological Mizo tones as of the SVM based classifier.