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.

Integrated Temperature-Humidity Sensors for a Pouch-Type Battery Using 100% Printing Process.

The performance, stability, and lifespan of lithium-ion batteries are influenced by variations in the flow of lithium ions with temperature. In electric vehicles, coolants are generally used to maintain the optimal temperature of the battery, leading to an increasing demand for temperature and humidity sensors that can prevent leakage and short circuits. In this study, humidity and temperature sensors were fabricated on a pouch film of a pouch-type battery. IDE electrodes were screen-printed on the pouch film and humidity- and temperature-sensing materials were printed using a dispenser process. Changes in the capacitance of the printed Ag-CNF film were used for humidity sensing, while changes in the resistance of the printed PEDOT:PSS film were used for temperature sensing. The two sensors were integrated into a single electrode for performance evaluation. The integrated sensor exhibited a response of ΔR ≈ 0.14 to temperature variations from 20 °C to 100 °C with 20% RH humidity as a reference, and a response of ΔC ≈ 2.8 to relative humidity changes from 20% RH to 80% RH at 20 °C. The fabricated integrated sensor is expected to contribute to efficient temperature and humidity monitoring applications in various pouch-type lithium-ion batteries.

Multiplex polymerase chain reaction assays for the detection of the zearalenone chemotype of Fusarium species in white and brown rice.

Early detection of the zearalenone (ZEA) chemotype of Fusarium species could be a precautionary measure for preventing ZEA contamination in rice. In this study, a multiplex polymerase chain reaction (mPCR) assay for detecting ZEA-producing fungi in rice was established using a set of four primers targeting the ZEA biosynthesis genes PKS3, PKS13, ZEB1, and ZEB2. Two mPCR approaches were used: one that amplified the DNA obtained from Fusarium isolates (conventional method) and another that directly amplified the target DNA from rice samples without time-consuming DNA isolation (direct method). The two mPCR methods showed high sensitivity in detecting ZEA-producing species, with a detection limit of 1.25 pg/µL of genomic DNA and 102 and 103 spores/g of white and brown rice, respectively. Both methods were specific for ZEA-producing species and gave four band patterns. The application of the two mPCR methods to 51 Fusarium isolates and 41 rice samples revealed that 31% (16 of 51) and 24% (10 of 41) of the samples were contaminated with ZEA-producing species, respectively. The mPCR results were further evaluated using high-performance liquid chromatography; in general, the two methods yielded similar results. These findings indicate that both mPCR methods are suitable for the detection of ZEA-producing Fusarium species in white and brown rice; however, the direct method yielded more rapid results.