Collaborative electronic nose management in personal devices

• US 10,402,541 B2
• Filed: 08/20/2014
• Issued: 09/03/2019
• Est. Priority Date: 08/28/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Sidoti, Stefano, Donatelli, Alessandro, Benedetti, Fabio, Ferrara, Filomena, Di Balsamo, Arcangelo
• Primary Examiner(s): Krcha, Matthew D
• Application Number:
  US14/912,409
• Publication Number:
  US 20160210425A1
• Time in Patent Office: 1,840 Days
• CPC Class Codes: G01D 1/14 giving a distribution function of a value, i.e. number of times the value comes within specified ranges of amplitude
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

A system and diagnosis server are provided for collaborating with electronic noses, as well as a related mobile diagnosis unit and related method. The diagnosis server includes a receiver unit for receiving a set of data from one e-nose of a plurality of e-noses. The set of data may include a sensor identifier, a sensor output value, and a relevance flag for a predefined diagnosis. In addition, a determination unit determines a probability factor for the predefined diagnosis based on the set of data, a relevance function and a distribution function.

Claims

1. A system for collaborating with electronic noses, the system comprising:

a memory; and

a processor communicatively coupled to the memory, wherein the system performs a method comprising;

receiving, by the processor, during a given time interval, a set of data from one e-nose of a plurality of e-noses, the set of data including;

one or more sensor identifiers of one or more sensors;

one or more sensor output values, each sensor output value originating from a sensor of the one or more sensors; and

a relevance flag for a predefined diagnosis, wherein the relevance flag is indicative of a usefulness of the sensor output value for the predefined diagnosis for each of the one or more sensors, wherein for each sensor, the relevance flag for the predefined diagnosis is a static value, set, by the processor, upon performing a baseline measurement of the sensor, wherein the baseline measurement comprises an evaluation of respective output values on the sensor, in relation to the predefined diagnosis, and wherein the relevance flag for the predefined diagnosis for each of the one or more sensors comprises either a first value or a second value, the first value indicating that the sensor output of a sensor of the one or more sensors is not relevant for the predefined diagnosis, and the second value indicating that the sensor output of the sensor of the one or more sensors is relevant for the predefined diagnosis;

storing, by the processor, the sensor output values and additional sensor output values received from additional e-noses of the one plurality of e-noses correlated with the predefined diagnosis;

determining a relevance function, wherein the relevance function is indicative of the relevance of a sensor output value for a given sensor of the one or more sensors for the predefined diagnosis, wherein a basis of the relevance function is a database comprising historic diagnoses reflected using sensor output values, and wherein the relevance function and the relevance flag are different entities with different functions, and wherein the relevance function is derived from data originating from more than one sensor over a given timeframe;

determining a distribution function, wherein the distribution function is indicative of a distribution of the sensor output value for the given sensor of the one or more sensors for the predefined diagnosis, wherein the distribution function comprises a pre-defined portion of stored sensor output values having an equivalent sensor output value to the sensor output value for the given sensor of the one or more sensors, during the given time interval, for the predefined diagnosis;

determining a probability factor for the predefined diagnosis based on the set of data, the relevance function and the distribution function,

generating a probability report for the predetermined diagnosis, utilizing the sensor output values and additional sensor output values received from the additional e-noses of the one plurality of e-noses correlated with the predefined diagnosis, and the probability factor; and

transmitting the probability report and the probability factor for the predetermined predefined diagnosis to a user interface adapted to notify a user of the probability factor, wherein the probability factor includes an indication of usefulness, based on the relevance flags of the one or more sensors utilized to determine the probability factor.

2. The system of claim 1, wherein the set of data comprises environmental data selected from the group consisting of:

at least one of a photo, a time stamp, geographical coordinates, temperature, humidity, and altitude.

3. The system of claim 1, wherein the determining ascertains the probability factor P(s) for the given sensor of the one or more sensors based on:

P(s)=RF(v(s))*DF(v(s)),

wherein

s=sensor identifier;

v(s)=sensor output value;

RF is the relevance function; and

DF is the distribution function, wherein the relevance function and the distribution function each consist of a value between 0 and 1, wherein the relevance function indicates a relevance of the sensor output value for the predefined diagnosis, wherein the relevance value is derived from data originating from more than one sensor over a given timeframe, and wherein the probability factor expressing a correlation between the predetermined diagnosis and the sensor output value of a sensor from which the sensor output value is output.

4. The system of claim 3, further comprising:

determining a total probability P(d) for a predetermined diagnosis based on multiplying probability factors of each sensor of the one or more sensors together.

5. The system of claim 4, further comprising transmitting the total probability for the predetermined diagnosis.

6. The system of claim 5, wherein at least one of the receiving the set of data or the transmitting the total probability comprises wirelessly receiving or wirelessly transmitting, respectively.