Deep Learning Model for Cosmetic Gel Classification Based on a Short-Time Fourier Transform and Spectrogram.

Cosmetics and topical medications, such as gels, foams, creams, and lotions, are viscoelastic substances that are applied to the skin or mucous membranes. The human perception of these materials is complex and involves multiple sensory modalities. Traditional panel-based sensory evaluations have limitations due to individual differences in sensory receptors and factors such as age, race, and gender. Therefore, this study proposes a deep-learning-based method for systematically analyzing and effectively identifying the physical properties of cosmetic gels. Time-series friction signals generated by rubbing the gels were measured. These signals were preprocessed through short-time Fourier transform (STFT) and continuous wavelet transform (CWT), respectively, and the frequency factors that change over time were distinguished and analyzed. The deep learning model employed a ResNet-based convolution neural network (CNN) structure with optimization achieved through a learning rate scheduler. The optimized STFT-based 2D CNN model outperforms the CWT-based 2D and 1D CNN models. The optimized STFT-based 2D CNN model also demonstrated robustness and reliability through k-fold cross-validation. This study suggests the potential for an innovative approach to replace traditional expert panel evaluations and objectively assess the user experience of cosmetics.

Flexible Pyroresistive Graphene Composites for Artificial Thermosensation Differentiating Materials and Solvent Types.

When we touch an object, thermosensation allows us to perceive not only the temperature but also wetness and types of materials with different thermophysical properties (i.e., thermal conductivity and heat capacity) of objects. Emulation of such sensory abilities is important in robots, wearables, and haptic interfaces, but it is challenging because they are not directly perceptible sensations but rather learned abilities via sensory experiences. Emulating the thermosensation of human skin, we introduce an artificial thermosensation based on an intelligent thermo-/calorimeter (TCM) that can objectively differentiate types of contact materials and solvents with different thermophysical properties. We demonstrate a TCM based on pyroresistive composites with ultrahigh sensitivity (11.2% °C-1) and high accuracy (<0.1 °C) by precisely controlling the melt-induced volume expansion of a semicrystalline polymer, as well as the negative temperature coefficient of reduced graphene oxide. In addition, the ultrathin TCM with coplanar electrode design shows deformation-insensitive temperature sensing, facilitating wearable skin temperature monitoring with accuracy higher than a commercial thermometer. Moreover, the TCM with a high pyroresistivity can objectively differentiate types of contact materials and solvents with different thermophysical properties. In a proof-of-principle application, our intelligent TCM, coupled with a machine-learning algorithm, enables objective evaluation of the thermal attributes (coolness and wetness) of skincare products.

Compliance and Effectiveness of Smoking Cessation Program Started on Hospitalized Patients.

BACKGROUND: Varenicline is now very useful medication for cessation; however, there is only little result of researches with varenicline for cessation of hospitalized patients. This research attempted to analyze the cessation effect of medication and compliance of hospitalized patients. METHODS: This research included data for 52 patients who were prescribed varenicline among 280 patients who were consulted for cessation during their admission period. This research checked whether smoking was stopped or not after six months and analyzed their compliance, the factors for succeeding in smoking cessation. RESULTS: One hundred and ninety hospitalized patients participated in smoking cessation counseling among 280 patients who included consultation from their admission departments. And varenicline was prescribed for only 80 patients after counseling. Nineteen smokers were successful in smoking cessation among 52 final participants representing the rating of success of 36.5%. The linkage between compliance of varenicline and rate of smoking successful has no statistical significance. The factors for succeeding in smoking of hospitalized patients are admission departments, diseases, and economic states. CONCLUSION: Smoking cessation program has low inpatient compliance. Cooperation of each departments is very important for better compliance. Success rate of cessation was relatively high (36.5%). Cessation attempt during hospitalization is very effective strategy.