46 results about "Sensory analysis" patented technology

A method, a program, and a device for evaluating food preference of pets that do not require humans to eat a pet food itself. The preference of pets can be evaluated by conducting sensory analysis on selected palatants contained in a pet food by humans. Accordingly, highly precise prediction of the preference can be made by a simple and intuitive method based on sensory attributes for human. Further, humans are not required to eat a pet food itself because the humans may conduct sensory analysis on selected palatants contained in the pet food.

The invention relates to a method for evaluating the shelf life of cooling pork at fluctuating temperature. The method comprises the following steps of: (1) sample microorganism and sensory analysis; (2) microorganism growth prediction models; and (3) application and verification of the prediction models at the fluctuating temperature. The method has the advantages that a predictive microbiology method is applied to analyze the growth situations of aerobic bacteria in the cooling pork at different time points under different temperature conditions and establish the microorganism prediction models of the cooling pork at different storage temperatures so as to evaluate the edible safety of the cooling pork; the established prediction microorganism dynamical-models can effectively predict the shelf life of the cooling pork at the temperature of 4-15 DEG C; and a strong technical support is provided for monitoring and tracking the shelf life of the cooling pork under the environment condition with the fluctuating temperature in real time.

The invention discloses a voice gender recognition deep learning method, comprising the following steps: a. collecting voice signals; b. detecting the endpoints of the collected voice signals and segmenting the human voice voice signal segments; c. The voice signal segment is divided into frames and multi-resolution cochlear voice features are extracted for each frame; d. Input the voice features of each frame into the pre-trained deep learning model of voice gender recognition for classification; e. Determine the output voice gender Voting statistics, according to the final output of the speaker's gender of the voice signal segment, the present invention uses multi-resolution cochlear voice features, which are more in line with the voice feature parameters of human auditory perception analysis, and uses capsule networks as the voice gender recognition acoustic reasoning model , can adapt to the speech environment with low signal-to-noise ratio, and has a higher recognition rate than traditional methods.

The invention discloses a classified identification method for fish sauce, belonging to the technical field of condiments analysis and identification methods. The method comprises the following steps: respectively determining volatile organic compounds in different types of fish sauce samples by an electronic nose analysis method to obtain the response intensity data of the different types of the fish sauce samples in an electronic nose sensor matrix; performing statistic classification on the response intensity data of the fish sauce samples, and establishing a fish sauce classified identification model; obtaining the response intensity data of a fish sauce sample in the electronic nose sensor matrix, substituting the response intensity data into the fish sauce classified identification model for analysis, and judging to obtain the classification of the fish sauce sample. By the adoption of the method, the quality of odor can be quantized and standardized, and the fish sauce classified identification model is established, so that the fish sauce can be evaluated objectively, quickly and accurately; the standardization of the quality of the fish sauce can be effectively guaranteed; the quality and the market competitiveness of the product are improved; the blank that the precision and the standardization cannot be realized by conventional sensory analysis is filled.