Improved GSO optimized ESN soft-sensor model of flotation process based on multisource heterogeneous information fusion.

For predicting the key technology indicators (concentrate grade and tailings recovery rate) of flotation process, an echo state network (ESN) based fusion soft-sensor model optimized by the improved glowworm swarm optimization (GSO) algorithm is proposed. Firstly, the color feature (saturation and brightness) and texture features (angular second moment, sum entropy, inertia moment, etc.) based on grey-level co-occurrence matrix (GLCM) are adopted to describe the visual characteristics of the flotation froth image. Then the kernel principal component analysis (KPCA) method is used to reduce the dimensionality of the high-dimensional input vector composed by the flotation froth image characteristics and process datum and extracts the nonlinear principal components in order to reduce the ESN dimension and network complex. The ESN soft-sensor model of flotation process is optimized by the GSO algorithm with congestion factor. Simulation results show that the model has better generalization and prediction accuracy to meet the online soft-sensor requirements of the real-time control in the flotation process.

Features extraction of flotation froth images and BP neural network soft-sensor model of concentrate grade optimized by shuffled cuckoo searching algorithm.

For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy.

[Effects of Genipin on the expression of uncoupling protein 1 in brown adipose and white adipose tissues in mice].

OBJECTIVE: To investigate the effects of genipin on promoting brown adipose tissue activation and white adipose tissue browning. METHODS: The male C57BL/6J mice were divided into three groups: normal control group, genipin group and cold-stimulus group.Genipin group were treated consecutively with genipin at a dose of 15 mg/kg once a day for 9 days, normal control group were treated with the saline.The mice with cold-stimulus were exposed to 4℃ environment for 5 days.Daily food amount and body weight were measured.Morphological changes were observed in the subscapular region, inguinal region and epididymis around the adipose tissue.The expression of uncoupling protein 1 (UCP1) was determined by real-time PCR and Western blot respectively. RESULTS: The wet weight of white fat in genipin-treated mice was decreased by 16% , and 28% in that of cold-stimulus mice, compared with the normal control group (P＜0.05).After treatments of genipin and cold-stimulus, the color of white adipose tissues was darker, and the size of lipid droplets in adipocytes was smaller, whereas the number was increased.Compared with the normal control group, UCP1 expression was increased obviously in fat tissues, including the subcutaneous and visceral white adipose tissues, and brown adipose tissue after treated with genipin and cold-stimulus (P＜0.05). CONCLUSION: Genipin promoted activation of brown adipose tissue and browning of white adipose tissue by upregulating UCP1 expression, which could contribute to the loss of body weight against obesity.