Abstract: A wound multiple sensing method, including: calculating the similarity between the current data sequence and each of the case-data sequences in each of the reference cases; selecting the case-data sequence which has the greatest similarity with the current data sequence, from the case-data sequences in each of the reference cases, to be a similar case-data sequence in each of the reference cases, wherein each similar case-data sequence corresponds to a similar case treatment; performing a multiple regression analysis using the similar case-data sequences and the similar case treatments to calculate a fitness function, wherein the dependent variable of the fitness function is a wound change; performing a parameter optimization algorithm using the current data sequence and the fitness function to calculate an optimal treatment which maximizes the wound change, and to calculate an expected wound change value that corresponds to the optimal treatment.

Abstract: A portable medical device includes a portable medical bag, a plurality of connectors and a processor. These connectors respectively connect the portable medical bag and every medical device contained inside the portable medical bag. The portable medical bag obtains the device management information of each the medical device through these connectors. The device management information includes the remaining power of medical device. The processor calculates the charge strategy information of the corresponding medical device according to the medical device information, address information and device management information. In addition, a management method for portable medical device is also provided.

Abstract: A system and method for automatically generating a care record are provided, which are suitable for a baby bed cover. The system includes an image capturing device and a processor. The image capturing device captures a real-time image of a baby in the baby bed. The processor is configured to receive the real-time image and detects whether an abnormal event occurs in the real-time image. The processor detects an opening time and a closing time of the bed cover to obtain a start and end time of a care operation. The processor recognizes an abnormal event type according to the abnormal event, selects a care record template according to the abnormal event type, and generates a care record according to an occurrence time of the abnormal event, the abnormal event type, the start and end time of the care operation, and the care record template.

Abstract: A wound multiple sensing method, including: calculating the similarity between the current data sequence and each of the case-data sequences in each of the reference cases; selecting the case-data sequence which has the greatest similarity with the current data sequence, from the case-data sequences in each of the reference cases, to be a similar case-data sequence in each of the reference cases, wherein each similar case-data sequence corresponds to a similar case treatment; performing a multiple regression analysis using the similar case-data sequences and the similar case treatments to calculate a fitness function, wherein the dependent variable of the fitness function is a wound change; performing a parameter optimization algorithm using the current data sequence and the fitness function to calculate an optimal treatment which maximizes the wound change, and to calculate an expected wound change value that corresponds to the optimal treatment.

Abstract: A lung sound monitoring device is provided. The lung sound monitoring device includes an acoustic sensor and a processor. The acoustic sensor is configured to capture the chest cavity sound of a subject at a first monitoring position on the subject and convert the chest cavity sound into a first chest cavity sound signal. The processor is configured to receive the first chest cavity sound signal and perform a filter process to obtain a first lung sound signal, and convert the first lung sound signal into a first lung sound spectrum using time-domain frequency-domain conversion. The processor acquires a first intensity index according to the first lung sound spectrum, and outputs a prompt signal according to the first intensity index to indicate whether the first monitoring position is a qualified monitoring position.

Abstract: A wound treatment recommendation method includes: storing a database; receiving a wound characterization record; generating a current data sequence according to the wound observation data in the wound characterization record; calculating similarity parameters of the current data sequence to each of case data sequences; regarding one of the similarity parameters with a highest restoration parameters and under a similarity threshold as the best case; selecting the questions used in the best case, excluding a plurality of existed questions in a questionnaire record, so as to establish a suggested questionnaire, and obtaining a plurality of answers of the suggested questionnaire; including all multiple reference cases within a specific range of values in each of the answers; and selecting multiple treatment cases including a nice recovery record from a plurality of treatment groups as at least one recommended treatment.

Abstract: A lung sound monitoring device is provided. The lung sound monitoring device includes an acoustic sensor and a processor. The acoustic sensor is configured to capture the chest cavity sound of a subject at a first monitoring position on the subject and convert the chest cavity sound into a first chest cavity sound signal. The processor is configured to receive the first chest cavity sound signal and perform a filter process to obtain a first lung sound signal, and convert the first lung sound signal into a first lung sound spectrum using time-domain frequency-domain conversion. The processor acquires a first intensity index according to the first lung sound spectrum, and outputs a prompt signal according to the first intensity index to indicate whether the first monitoring position is a qualified monitoring position.

Abstract: A system for analyzing wound status is provided. The system includes an image obtaining device and an image analyzing device. The image obtaining device is configured to obtain a plurality of infrared (IR) images which are photographed from a wound of a user's body portion, wherein the plurality of IR images are photographed at different time. The image analyzing device is configured to align the plurality of IR images based on features of non-wound regions from the plurality of IR images, and then analyze wound image regions from the plurality of IR images for finding out variations of the wound.

Abstract: A system for analyzing wound status is provided. The system includes an image obtaining device and an image analyzing device. The image obtaining device is configured to obtain a plurality of infrared (IR) images which are photographed from a wound of a user's body portion, wherein the plurality of IR images are photographed at different time. The image analyzing device is configured to align the plurality of IR images based on features of non-wound regions from the plurality of IR images, and then analyze wound image regions from the plurality of IR images for finding out variations of the wound.

Abstract: A system for object recognition includes an image/spectrum sensing device, to fetch an object image from a real object and sense spectra at sensing regions of the real object. A fetching module obtains a real-object image feature pattern for each ROI of the object image. An analyzing module for object image feature searches for a first candidate object from data bank and analyzes a correlation between the real object and candidate object. A fetching module for object spectrum feature obtains a real-object spectrum pattern for each ROI of the object image. An analyzing module for object spectrum feature is to search for a second candidate object from data bank and to further analyze a match level between the real-object and the second candidate object. A fusion module further analyzes information of image feature and spectrum feature find whether or not having a matched object as an identify object.

Abstract: A diet ingestion analyzing method is provided. The diet ingestion analyzing method includes the following steps. A plurality of nutrition amounts of a plurality of diet records are calculated according to a food nutrition database. A plurality of specific diet records corresponding a specific time are obtained from the diet records. A nutrition ingestion ratio of a total of a plurality of nutrition amounts of the specific diet records to a total of the nutrition amounts of the diet records is generated. A nutrition recommendation is generated according to a nutrition recommended range and the nutrition ingestion ratio. A plurality of selected records is selected from the specific diet records. Whether each of a plurality of nutrition amounts of the selected records is abnormal or not is determined according to the nutrition recommendation. A diet model is constructed and an abnormal food is marked according to the selected records.

Abstract: A system for object recognition includes an image/spectrum sensing device, to fetch an object image from a real object and sense spectra at sensing regions of the real object. A fetching module obtains a real-object image feature pattern for each ROI of the object image. An analyzing module for object image feature searches for a first candidate object from data bank and analyzes a correlation between the real object and candidate object. A fetching module for object spectrum feature obtains a real-object spectrum pattern for each ROI of the object image. An analyzing module for object spectrum feature is to search for a second candidate object from data bank and to further analyze a match level between the real-object and the second candidate object. A fusion module further analyzes information of image feature and spectrum feature find whether or not having a matched object as an identify object.

Abstract: A system and a method for detecting multi-level intrusion events are provided. The system includes an area recognition module and an area classification module. The area recognition module performs a geometric topology operation to recognize a plurality of areas in a ground plane that has a plurality of boundaries and a plurality of gates, and each of the areas is constituted of at least one of the boundaries and at least one of the gates. The area classification module defines a plurality of security levels and classifies each of the areas recognized by the area recognition module as one of the security levels. Accordingly, the system is able to automatically recognize the areas in the ground plane, set the security levels of the areas, and generate the corresponding detection areas and tripwires according to the security levels of the areas.

Abstract: A system and a method for dispatching of video recording are provided. In the method, one or more video recording servers having an available CPU utilization larger than an average CPU loading per task is found from one or more video recording servers having a task capability greater than zero. One of the found one or more video recording servers is selected to execute a video recording task whose execution status is indicated as unexecuted in a video recording task status table.

Abstract: A computer implemented method for recognizing license plate image, and related computer product, computer-readable recording medium, and image recognizing apparatus using the same is provided. The method includes collecting a plurality of character template images and respectively homogenizing the character template images to generate a plurality of simulated character template images based on the license plate image. The method also includes respectively generating a plurality of similarity degrees corresponding to the simulated character template images by comparing the simulated character template images with the license plate image. The method further includes estimating at least one candidate character corresponding to the license plate image and at least one candidate character position corresponding to the at least one candidate character according to the similarity degrees corresponding to the simulated character template images.

Abstract: The invention discloses a camera recalibration system and the method thereof. The camera recalibration system includes a first camera, which is to be recalibrated, for capturing image; an image processing unit comprising a storage unit for storing a first image and a second image, the second image being captured by the first camera; and a computing unit for measuring camera motion from the first image to the second image and computing calibration information corresponding to the camera motion; and a display unit for presenting the calibration information.

Abstract: A system and a method for detecting multi-level intrusion events are provided. The system includes an area recognition module and an area classification module. The area recognition module performs a geometric topology operation to recognize a plurality of areas in a ground plane that has a plurality of boundaries and a plurality of gates, and each of the areas is constituted of at least one of the boundaries and at least one of the gates. The area classification module defines a plurality of security levels and classifies each of the areas recognized by the area recognition module as one of the security levels. Accordingly, the system is able to automatically recognize the areas in the ground plane, set the security levels of the areas, and generate the corresponding detection areas and tripwires according to the security levels of the areas.