Leptospirosis modelling using hydrometeorological indices and random forest machine learning.

Leptospirosis is a zoonosis that has been linked to hydrometeorological variability. Hydrometeorological averages and extremes have been used before as drivers in the statistical prediction of disease. However, their importance and predictive capacity are still little known. In this study, the use of a random forest classifier was explored to analyze the relative importance of hydrometeorological indices in developing the leptospirosis model and to evaluate the performance of models based on the type of indices used, using case data from three districts in Kelantan, Malaysia, that experience annual monsoonal rainfall and flooding. First, hydrometeorological data including rainfall, streamflow, water level, relative humidity, and temperature were transformed into 164 weekly average and extreme indices in accordance with the Expert Team on Climate Change Detection and Indices (ETCCDI). Then, weekly case occurrences were classified into binary classes "high" and "low" based on an average threshold. Seventeen models based on "average," "extreme," and "mixed" indices were trained by optimizing the feature subsets based on the model computed mean decrease Gini (MDG) scores. The variable importance was assessed through cross-correlation analysis and the MDG score. The average and extreme models showed similar prediction accuracy ranges (61.5-76.1% and 72.3-77.0%) while the mixed models showed an improvement (71.7-82.6% prediction accuracy). An extreme model was the most sensitive while an average model was the most specific. The time lag associated with the driving indices agreed with the seasonality of the monsoon. The rainfall variable (extreme) was the most important in classifying the leptospirosis occurrence while streamflow was the least important despite showing higher correlations with leptospirosis.

Full Ground Ultra-Wideband Wearable Textile Antenna for Breast Cancer and Wireless Body Area Network Applications.

Wireless body area network (WBAN) applications have broad utility in monitoring patient health and transmitting the data wirelessly. WBAN can greatly benefit from wearable antennas. Wearable antennas provide comfort and continuity of the monitoring of the patient. Therefore, they must be comfortable, flexible, and operate without excessive degradation near the body. Most wearable antennas use a truncated ground, which increases specific absorption rate (SAR) undesirably. A full ground ultra-wideband (UWB) antenna is proposed and utilized here to attain a broad bandwidth while keeping SAR in the acceptable range based on both 1 g and 10 g standards. It is designed on a denim substrate with a dielectric constant of 1.4 and thickness of 0.7 mm alongside the ShieldIt conductive textile. The antenna is fed using a ground coplanar waveguide (GCPW) through a substrate-integrated waveguide (SIW) transition. This transition creates a perfect match while reducing SAR. In addition, the proposed antenna has a bandwidth (BW) of 7-28 GHz, maximum directive gain of 10.5 dBi and maximum radiation efficiency of 96%, with small dimensions of 60 × 50 × 0.7 mm3. The good antenna's performance while it is placed on the breast shows that it is a good candidate for both breast cancer imaging and WBAN.