Diagnosis of dengue virus infection using spectroscopic images and deep learning.

Dengue virus (DENV) infection is one of the major health issues and a substantial epidemic infectious human disease. More than two billion humans are living in dengue susceptible regions with annual infection mortality rate is about 5%-20%. At initial stages, it is difficult to differentiate dengue virus symptoms with other similar diseases. The main objective of this research is to diagnose dengue virus infection in human blood sera for better treatment and rehabilitation process. A novel and robust approach is proposed based on Raman spectroscopy and deep learning. In this regard, the ResNet101 deep learning model is modified by exploiting transfer learning (TL) concept on Raman spectroscopic data of human blood sera. Sample size was selected using standard statistical tests. The proposed model is evaluated on 2,000 Raman spectra images in which 1,200 are DENV-infected of human blood sera samples, and 800 are healthy ones. It offers 96.0% accuracy on testing data for DENV infection diagnosis. Moreover, the developed approach demonstrated minimum improvement of 6.0% and 7.0% in terms of AUC and Kappa index respectively over the other state-of-the-art techniques. The developed model offers superior performance to capture minute Raman spectral variations due to the better residual learning capability and generalization ability compared to others deep learning models. The developed model revealed that it might be applied for diagnosis of DENV infection to save precious human lives.

Activity recognition in a smart home using local feature weighting and variants of nearest-neighbors classifiers.

Recognition of activities, such as preparing meal or watching TV, performed by a smart home resident, can promote the independent living of elderly in a safe and comfortable environment of their own homes, for an extended period of time. Different activities performed at the same location have commonalities resulting in less inter-class variations; while the same activity performed multiple times, or by multiple residents, varies in its execution resulting in high intra-class variations. We propose a Local Feature Weighting approach (LFW) that assigns weights based on both inter-class and intra-class importance of a feature in an activity. Multiple sensors are deployed at different locations in a smart home to gather information. We exploit the obtained information, such as frequency and duration of activation of sensors, and the total sensors in an activity for feature weighting. The weights for the same features vary among activities, since a feature may have more importance for one activity but less for the other. For the classification, we exploit the two variants of K-Nearest Neighbors (KNN): Evidence Theoretic KNN (ETKNN) and Fuzzy KNN (FKNN). The evaluation of the proposed approach on three datasets, from CASAS smart home project, demonstrates its ability in the correct recognition of activities compared to the existing approaches.