RESUMO
In order to solve a series of problems with kelp drying including long drying time, high energy consumption, low drying efficiency, and poor quality of dried kelp, this work proposes the design of a novel greenhouse double-evaporator solar-assisted heat pump drying system. Experiments on kelp solar-assisted heat pump drying (S-HP) and heat pump drying (HP) under the condition of irradiance of 100-700 W/m2 and a temperature of 30, 40, or 50 °C were conducted and their results were compared in terms of system performance, drying kinetics, and quality impact. The drying time was reduced with increasing irradiance or temperature. The coefficient of performance (COP) and specific moisture extraction rate (SMER) of S-HP were 3.590-6.810, and 1.660-3.725 kg/kW·h, respectively, roughly double those of HP when the temperatures are identical. The Deff of S-HP and HP were 5.431 × 10-11~11.316 × 10-11 m2/s, and 1.037 × 10-11~1.432 × 10-11 m2/s, respectively; additionally, solar radiation greatly improves Deff. The Page model almost perfectly described the changes in the moisture ratio of kelp by S-HP and HP with an inaccuracy of less than 5%. When the temperature was 40 °C and the irradiance was above 400 W/m2, the drying time of S-HP was only 3 h, and the dried kelp maintained the green color with a strong flavor and richness in mannitol. Meanwhile, the coefficient of performance was 6.810, the specific moisture extraction rate was 3.725 kg/kWh, and the energy consumption was 45.2%, lower than that of HP. It can be concluded that S-HP is highly efficient and energy-saving for macroalgae drying and can serve as an alternate technique for the drying of other aquatic products.
RESUMO
Early intervention for depression is very important to ease the disease burden, but current diagnostic methods are still limited. This study investigated automatic depressed speech classification in a sample of 170 native Chinese subjects (85 healthy controls and 85 depressed patients). The classification performances of prosodic, spectral, and glottal speech features were analyzed in recognition of depression. We proposed an ensemble logistic regression model for detecting depression (ELRDD) in speech. The logistic regression, which was superior in recognition of depression, was selected as the base classifier. This ensemble model extracted many speech features from different aspects and ensured diversity of the base classifier. ELRDD provided better classification results than the other compared classifiers. A technique for identifying depression based on ELRDD, ELRDD-E, was here suggested and tested. It offered encouraging outcomes, revealing a high accuracy level of 75.00% for females and 81.82% for males, as well as an advantageous sensitivity/specificity ratio of 79.25%/70.59% for females and 78.13%/85.29% for males.