60results about How to "Analysis results are objective" patented technology

The application discloses a depth-learning-based eye-fundus image processing method, device and system. The method comprises: eye-fundus image pretreatment is carried out and region segmentation extraction is carried out on the eye-fundus image; resampling is carried out on a regional image obtained by the segmentation extraction; data expansion is carried out on the regional image after resampling; and a regional image feature is identified by using a depth learning method. Therefore, an eye-fundus image can be analyzed automatically; the analysis result is objective and accurate; and the manpower cost is saved.

The invention discloses a method for detecting the quality of oranges in different maturity on the basis of a taste-smell fingerprint spectrum. The method comprises the following steps of washing the oranges, peeling the oranges, juicing the oranges, and obtaining the orange juice; carrying out an electronic nose experiment: placing the filtered orange juice in a closed vessel, standing, detecting an overhead air by adopting an electronic nose, extracting characteristic data from the smell fingerprint spectrum, and adopting the extracted characteristic data as an original data of the electronic nose part; carrying out the electronic tongue experiment: placing the filtered orange juice in a special beaker for an electronic tongue, enabling an electronic tongue sensor array to contact sample liquid, generating a sensor response signal, extracting characteristic data from the taste fingerprint spectrum, and adopting the extracted characteristic data as the original data of the electronic tongue part; processing response values from different systems in three different preprocessing methods, so that the generalization capability of a model can be improved. By adopting the method, the high-efficient data fusion of the taste and smell fingerprint spectrum can be realized, the quality of the orange in different maturity can be directly, conveniently, objectively and rapidly evaluated and predicted, and the popularization and application value is relatively high.

The invention provides the apparatus and method for analyzing physical and mental health condition, which comprises an electrocardio signal acquisition module and a mobile terminal; wherein the electrocardio signal acquisition module is used for collecting original electrocardio signal data; the mobile terminal comprises: a heart rate variability data acquisition module , which is used for determining heart rate variability data according to original electrocardiogram data and analyzing time-domain parameters and / or frequency-domain parameters of the heart rate variability data so as to obtaintime-domain analysis parameters and / or frequency-domain analysis parameters; the physical and mental health index analysis module is used for obtaining a physical and mental health analysis result according to the time-domain analysis parameter and / or the frequency-domain analysis parameter. According to the method, the original electrocardiograph data is obtained through the electrocardiograph signal acquisition module. Then the heart rate variability data is obtained through the data processing method, and time-domain and frequency-domain analysis is carried out on the heart rate variability data, so that the analysis result of the physical and mental health condition is finally obtained, and the analysis result is more objective and accurate.

The invention provides a discriminating method for heroin origins based on neutral or acidic impurities and partial least-squares discriminant analysis (PLS-DA), which is suitable for discriminating affiliation of heroin in two origins: southeast Asia and southwest Asia. The method comprises the following steps: firstly, putting forward a discriminating function of PLS-DA of the heroin origins; detecting peak area numerical values of independent variables of 25 neutral or acidic impurities in a heroin sample, and substituting the peak area numerical values into the PLS-DA discriminating function; calculating the numerical value t of the obtained discriminating function; when t is greater than 0 and less than 6, judging that the heroin origin is southeast Asia; and when t is greater than -6 and less than 0, judging that the heroin origin is southwest Asia.

The invention discloses a method and device for analyzing data fluctuation, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining a dataset of to-be-analyzed data; determining fluctuation data in the data set; and matching fluctuation factor information for the fluctuation data in an information table of at least one fluctuation factor to generate fluctuation reason analysis data of the fluctuation data. The method can automatically analyze reasons of data fluctuation, is high in efficiency, and is objective and accurate in analysis result.

The invention provides a method for quickly detecting the quality of donkey-hid gelatin. Qualified Dong'e donkey-hide gelatin is selected to serve as a standard reference sample; a crushed donkey-hide gelatin sample is dissolved in distilled water and put in a sample bottle, and then the sample bottle is sealed; the sample bottle is put on a sample plate of an electronic nose system, analysis parameters of the electronic nose system are set, and analysis and testing are performed through the electronic nose system; smell fingerprint information of the donkey-hide gelatin is collected through the electronic nose system, and each sample is analyzed for 120 s; a sensor array of the electronic nose system acquires the smell which the donkey-hide gelatin emits, acquired data are subjected to system cluster analysis by means of SPSS (statistical product and service solutions) data statistical software, and the quality of the donkey-hide gelatin can be quickly detected. The pre-treatment of the sample is simple, no organic solvents are required, and the method is natural, cannot cause any pollution and has the characteristics of low price, fastness, objectivity and the like.

The invention discloses a method for obtaining a resident travel characteristic parameter based on mobile phone positioning data. The method comprises the following steps of: (1) collecting mobile phone positioning data; (2) filtering the mobile phone positioning data, matching the mobile phone positioning data to traffic zones, and obtaining the matched mobile phone positioning data; (3) using users as units, ordering the matched mobile phone positioning data in one day by time, merging the continuous data in the same one traffic zone into one piece, and obtaining mobile phone positioning pretreatment data; (4) according to the number of emerged pieces and influence duration, judging residing points, restoring a travel path between two residing points, and obtaining the travel distance and the travel speed, and then obtaining a travel log table of all users; (5) on the basis of the matched mobile phone positioning data, statistically obtaining a place of residence and workplace result table; and (6) and conjointly analyzing the travel log table and the place of residence and workplace result table, and obtaining resident travel characteristic parameters. The method has the characteristics of low cost, large sample quantity, high precision and high time validity.