Feature-quantity extracting apparatus
First Claim
Patent Images
1. A feature-quantity extracting apparatus having a processor, which apparatus receives time-series data from a sensor and extracts a feature quantity of the received data without performing a time-frequency conversion process on the received data, wherein the processor performs a process comprising:
- a code information acquiring process, executed by the processor, for obtaining plural pieces of time-series data A(1) to A(n) (n;
an integer) each having a predetermined time period from the received time-series data;
obtaining difference data D from the plural time-series data A(1) to A(n) by performing a following equation
D(k)=A(k+1)−
A(k)(1≤
k≤
n−
1);
and, giving a code of “
+”
to the difference data D when the difference data D has a positive value, and giving a code of “
−
”
to the difference data D when the difference data D has a negative value, thereby acquiring plural pieces of code information with the code of “
+”
or “
−
”
given, which are sequential time serially beginning from a predetermined timea code-information string acquiring process, executed by the processor, for picking out P (P;
an integer smaller than “
n”
) pieces of code information which are sequential in time from a piece of code information as a code information string from the acquired plural pieces of code information which are sequential time serially starting from a predetermined time, and then sequentially picking out another P pieces of code information which are sequential in time starting from a piece of code information shifted by 1 in a time axis as another code information string from the acquired plural pieces of code information, thereby picking out plural code information strings each containing P pieces of code information, wherein each of the plural code information strings comprises P elements wherein each of the of the P elements are either “
+”
or “
−
”
;
a histogram representing process, executed by the processor, for counting a frequency of a pattern indicated by the arranged codes of “
+” and
/or “
−
”
included in the code information string, wherein each plural code information string are grouped with other plural code information strings that have a same number of “
−
”
in the plural code information strings, and a histogram is formed where the x axis represents difference groupings of plural code information strings based on the number of “
−
”
in the plural code information string, and the y axis represents a frequency of occurrence of each plural code information string, and representing the counted frequency of each of the plural code information strings in a histogram;
a feature-quantity extracting process, executed by the processor, for extracting the histogram as the feature quantity of the received data; and
displaying the histogram and feature quantity on a liquid crystal display device.
1 Assignment
0 Petitions
Accused Products
Abstract
A feature-quantity extracting apparatus is provided, which can calculate a proper feature quantity, by performing a simple calculating operation. The apparatus is provided with a code-string acquiring unit for acquiring code strings for every given period from a series of input data, wherein the code string is an arrangement of codes and the code is given to a value of each piece of input data, a code-string pattern frequency counting unit for counting the number of code-string patterns for every code-string pattern among the code strings acquired by the code-string acquiring unit, wherein the code-string pattern represents a code-string whose codes are arranged in accordance with a given order, and a feature-quantity outputting unit for outputting the number of code-string patterns for every code-string pattern counted by the code-string pattern frequency counting unit as a feature quantity of the series of input data.
11 Citations
3 Claims
-
1. A feature-quantity extracting apparatus having a processor, which apparatus receives time-series data from a sensor and extracts a feature quantity of the received data without performing a time-frequency conversion process on the received data, wherein the processor performs a process comprising:
-
a code information acquiring process, executed by the processor, for obtaining plural pieces of time-series data A(1) to A(n) (n;
an integer) each having a predetermined time period from the received time-series data;
obtaining difference data D from the plural time-series data A(1) to A(n) by performing a following equation
D(k)=A(k+1)−
A(k)(1≤
k≤
n−
1);and, giving a code of “
+”
to the difference data D when the difference data D has a positive value, and giving a code of “
−
”
to the difference data D when the difference data D has a negative value, thereby acquiring plural pieces of code information with the code of “
+”
or “
−
”
given, which are sequential time serially beginning from a predetermined timea code-information string acquiring process, executed by the processor, for picking out P (P;
an integer smaller than “
n”
) pieces of code information which are sequential in time from a piece of code information as a code information string from the acquired plural pieces of code information which are sequential time serially starting from a predetermined time, and then sequentially picking out another P pieces of code information which are sequential in time starting from a piece of code information shifted by 1 in a time axis as another code information string from the acquired plural pieces of code information, thereby picking out plural code information strings each containing P pieces of code information, wherein each of the plural code information strings comprises P elements wherein each of the of the P elements are either “
+”
or “
−
”
;a histogram representing process, executed by the processor, for counting a frequency of a pattern indicated by the arranged codes of “
+” and
/or “
−
”
included in the code information string, wherein each plural code information string are grouped with other plural code information strings that have a same number of “
−
”
in the plural code information strings, and a histogram is formed where the x axis represents difference groupings of plural code information strings based on the number of “
−
”
in the plural code information string, and the y axis represents a frequency of occurrence of each plural code information string, and representing the counted frequency of each of the plural code information strings in a histogram;a feature-quantity extracting process, executed by the processor, for extracting the histogram as the feature quantity of the received data; and displaying the histogram and feature quantity on a liquid crystal display device.
-
-
2. A feature-quantity extracting method for receiving time-series data received from a sensor and extracting a feature-quantity of the received data without performing a time-frequency conversion process on the received data, the method comprising the steps of:
-
(a) obtaining, by a processor, plural pieces of time-series data A(1) to A(n) (n;
an integer) each having a predetermined time period from the received time-series data;(b) obtaining, by the processor, difference data D from the plural time-series data A(1) to A(n) by performing a following equation
D(k)=A(k+1)−
A(k)(1≤
k≤
n−
1);(c) giving, by the processor, a code of “
+”
to the difference data D when the difference data D has a positive value, and giving a code of “
−
”
to the difference data D when the difference data D has a negative value, thereby acquiring plural pieces of code information with the code of “
+”
or “
−
”
given, which are sequential time serially beginning from a predetermined time;(d) picking, by the processor, out P (P;
an integer smaller than “
n”
) pieces of code information which are sequential in time from a piece of code information as a code information string from the acquired plural pieces of code information which are sequential time serially starting from a predetermined time, and then sequentially picking out another P pieces of code information which are sequential in time from a piece of code information shifted by 1 in a time axis as another code information string from the acquired plural pieces of code information, thereby picking out plural code information strings each containing P pieces of code information, wherein each of the plural code information strings comprises P elements wherein each of the of the P elements are either “
+”
or “
−
”
;(e) counting, by the processor, a frequency of a pattern indicated by the arranged codes of “
+” and
/or “
−
”
included in the code information string, wherein each plural code information string are grouped with other plural code information strings that have a same number of “
−
”
in the plural code information strings, and a histogram is formed where the x axis represents difference groupings of plural code information strings based on the number of “
−
”
in the plural code information string, and the y axis represents a frequency of occurrence of each plural code information string, and representing the counted frequency of each of the plural code information strings in a histogram;(f) extracting, by the processor, the histogram as the feature quantity of the received data; and displaying the histogram and feature quantity on a liquid crystal display device.
-
-
3. A non-transitory computer-readable storage medium with an executable program stored thereon, wherein a computer is mounted on a feature-quantity extracting apparatus which receives time-series data from a sensor and extracts a feature quantity of the received data without performing a time-frequency conversion process on the received data, the program, when installed on the computer, making the computer perform a process comprising:
-
a code information acquiring process, executed by a processor, for obtaining plural pieces of time-series data A(1) to A(n) (n;
an integer) each having a predetermined time period from the received time-series data;
obtaining difference data D from the plural time-series data A(1) to A(n) by performing a following equation
D(k)=A(k+1)−
A(k)(1≤
k≤
n−
1);and, giving a code of “
+”
to the difference data D when the difference data D has a positive value, and giving a code of “
−
”
to the difference data D when the difference data D has a negative value, thereby acquiring plural pieces of code information with the code of “
+”
or “
−
”
given, which are sequential time serially beginning from a predetermined time;a code-information string acquiring process, executed by the processor, for picking out P (P;
an integer smaller than “
n”
) pieces of code information which are sequential in time from a piece of code information as a code information string from the acquired plural pieces of code information which are sequential time serially starting from a predetermined time, and then sequentially picking out another P pieces of code information which are sequential in time starting from a piece of code information shifted by 1 in a time axis as another code information string from the acquired plural pieces of code information, thereby picking out plural code information strings each containing P pieces of code information, wherein each of the plural code information strings comprises P elements wherein each of the of the P elements are either “
+”
or “
−
”
;a histogram representing process, executed by the processor, for counting a frequency of a pattern indicated by the arranged codes of “
+” and
/or “
−
”
included in the code information string, wherein each plural code information string are grouped with other plural code information strings that have a same number of “
−
”
in the plural code information strings, and a histogram is formed where the x axis represents difference groupings of plural code information strings based on the number of “
−
”
in the plural code information string, and the y axis represents a frequency of occurrence of each plural code information string, and representing the counted frequency of each of the plural code information strings in a histogram;a feature-quantity extracting process, executed by the processor, for extracting the histogram as the feature quantity of the received data; and displaying the histogram and feature quantity on a liquid crystal display device.
-
Specification
-
- Resources
Litigation Campaign Assessment
Thank you for your request. You will receive a custom alert email when the Litigation Campaign Assessment is available.
×
-
Current AssigneeCasio Computer Company Limited
-
Original AssigneeCasio Computer Company Limited
-
InventorsYahata, Takashi, Kanke, Takao
-
Primary Examiner(s)DO, AN H
-
Application NumberUS14/298,024Publication NumberTime in Patent Office1,642 DaysField of Search702127, 702189, 702190US Class CurrentCPC Class CodesA61B 5/1112 Global tracking of patients...A61B 5/1116 Determining posture transit...A61B 5/1118 Determining activity levelA61B 5/1123 Discriminating type of move...
