KR20160017543A - Signal estimation apparatus and method - Google Patents

Abstract

According to an embodiment of the present invention, provided is a signal estimation device to offer an effective measure to calculate an estimated value from detected signal values. The signal estimation device comprises a signal processing unit and a signal estimation unit. The signal processing unit detects a plurality of signal values from received signals during a certain period of time. The signal estimation unit determines which of the signal values belong to which signal range among a plurality of signal value ranges, selects some of the signal value ranges according to the number of signal values within each of the signal value ranges, and calculates an estimated value of the signal from some of the signal values.

Description

[0001] SIGNAL ESTIMATION APPARATUS AND METHOD [0002]

The disclosed embodiments relate to signal estimation, and more particularly to techniques for calculating an estimate of a signal from values of a signal received during a particular time period.

There may be anomalies among the numerical values sequentially input to an estimation system. It may be desirable to remove anomalies in order to improve the performance of such an estimation system.

Conventional outlier removal techniques use statistical based modeling or clustering. Estimation systems that use statistical-based modeling can use algorithms such as the Kalman filter. However, this approach can only provide optimal performance under certain statistical models. The clustering-based estimation system treats nearby input data as a single cluster and counts out of the cluster as an outlier. Whenever new data is input, complex computations are performed to identify which clusters the data is contained in .

Therefore, instead of the above-described outlier removal methods, the statistical characteristics of the input values are not specified or rapidly changed according to the surrounding environment, but also in an embedded system in which computing resources are limited (for example, A system that estimates its coordinates from an ultrasound signal) is needed.

Korean Patent Publication No. 10-2006-0070059 (published on June 23, 2006)

The disclosed embodiments provide an efficient technique for calculating an estimate of a signal from detected signal values from an input signal.

According to an exemplary embodiment, a signal processing unit for detecting a plurality of signal values from a signal received during a specific time period; And determining whether each of the plurality of signal values belongs to one of a plurality of signal value intervals and selecting a part of the plurality of signal value intervals based on the number of signal values within each of the plurality of signal value intervals And a signal estimator for calculating an estimated value of the signal from the signal value within the part.

Selecting the portion may comprise selecting a first signal value interval of the plurality of signal value intervals, wherein the first signal value interval includes more signal values than the remaining ones of the plurality of signal value intervals I can belong.

Selecting the portion may comprise selecting one or more signal value intervals of the plurality of signal value intervals and the number of signal values within the one or more signal value intervals may be greater than a preset threshold value.

More than one signal value may be included in each of the one or more signal value sections than the other signal value sections except for the one or more signal value sections of the plurality of signal value sections.

Wherein selecting the one or more signal value intervals may include identifying that the signal value interval in which the largest signal value belongs to at least a portion of the plurality of signal value intervals is within a normal range, And the signal value intervals not yet identified as being included in the normal range, and the selecting of the one or more signal value intervals may repeat the identification if the number of signal values within the normal range is not greater than the preset threshold value And selecting the normal range as the part if the number of signal values within the normal range is greater than the preset threshold value.

The plurality of signal values may be signal values at a predetermined number of the most recent time points within the specific time period, respectively.

The signal estimating device comprising: a sensor for receiving the signal from a user input device; And a coordinate calculator for calculating coordinates of the user input device using the estimated value.

According to another exemplary embodiment, there is provided a method comprising: detecting a plurality of signal values from a signal received during a specific time period; Determining which one of the plurality of signal value intervals belongs to each of the plurality of signal values; Selecting a portion of the plurality of signal value intervals based on the number of signal values within each of the plurality of signal value intervals; And calculating an estimated value of the signal from the signal value within the part.

The selecting of the portion may include selecting a first signal value interval of the plurality of signal value intervals, wherein the first signal value interval includes more signals than the remaining ones of the plurality of signal value intervals The value can belong.

The selecting of the portion may include selecting one or more signal value intervals of the plurality of signal value intervals, and the number of signal values in the one or more signal value intervals may be greater than a preset threshold value.

More than one signal value may be included in each of the one or more signal value sections than the other signal value sections except for the one or more signal value sections of the plurality of signal value sections.

Wherein the selecting of the one or more signal value intervals may include identifying that a signal value interval in which at least a portion of the plurality of signal value intervals belongs to is within a normal range, The signal value intervals may be signal value intervals that are not yet identified as being included in the normal range before identification, and wherein the selecting of the one or more signal value intervals may include: if the number of signal values within the normal range is not greater than the preset threshold value Repeating the identification; And selecting the normal range as the part if the number of signal values within the normal range is greater than the preset threshold value.

The plurality of signal values may be signal values at a predetermined number of the most recent time points within the specific time period, respectively.

The signal estimation method comprising: receiving the signal from a user input device; And calculating the coordinates of the user input device using the estimated value.

According to another exemplary embodiment, there is provided a method comprising: detecting a plurality of signal values from a signal received during a specific time period; Determining which one of the plurality of signal value intervals belongs to each of the plurality of signal values; Selecting a portion of the plurality of signal value intervals based on the number of signal values within each of the plurality of signal value intervals; And calculating an estimate of the signal from the signal value within the portion.

According to some embodiments, the abnormal value among the signal values detected from the input signal can be removed with a small amount of calculation.

According to some embodiments, a technique of calculating an estimated value of a signal by efficiently removing an ideal value in a system in which signal values detected from an input signal do not comply with a specific statistical characteristic or a computing resource is limited can be provided.

1 is a diagrammatic representation of a computing device suitable for removing anomalous values from signal values of a signal and calculating an estimate of the signal, according to an exemplary embodiment;
FIG. 2 is a diagram for explaining a data structure held in a signal estimation process according to an exemplary embodiment; FIG.
3 is a diagram illustrating a signal estimation process according to an exemplary embodiment;
4 is a diagram illustrating pseudocode for adjusting the ranking of signal value intervals according to an exemplary embodiment;
5 is a diagram illustrating pseudocode for adjusting the ranking of signal value intervals according to an exemplary embodiment;
6 illustrates an apparatus for receiving a signal indicative of a coordinate of a user input device and estimating its coordinates according to an exemplary embodiment;

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to provide a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, this is merely an example and the present invention is not limited thereto.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. The following terms are defined in consideration of the functions of the present invention, and may be changed according to the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification. The terms used in the detailed description are intended only to describe embodiments of the invention and should in no way be limiting. Unless specifically stated otherwise, the singular form of a term includes plural forms of meaning. In this description, the expressions "comprising" or "comprising" are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, Should not be construed to preclude the presence or possibility of other features, numbers, steps, operations, elements, portions or combinations thereof.

Figure 1 graphically illustrates a computing device suitable for removing anomalies from signal values of a signal and calculating an estimate of the signal, according to an exemplary embodiment.

1, an exemplary computing device 100 may include one or more processors 110 and a computer readable storage medium 120, such as a memory accessible by the processor 110. In one embodiment, The computer readable storage medium 120 may be located within or external to the processor 110 and may be coupled to the processor 110 by various well known means. Computer readable storage medium 120 may store computer executable instructions 122. The processor 110 may execute instructions 122 stored on the computer readable storage medium 120. [ Such an instruction 122 may cause the computing device 100 to perform an operation according to the illustrative embodiment when executed by the processor 110. [ For example, instruction 122 may cause processor 110, when executed by processor 110, to perform signal estimation while maintaining data structure 124 in media 120. In addition, the computing device 100 may include one or more interfaces 130. The computing device 100 may be coupled to one or more external devices via the interface 130. For example, the interface 130 may support input / output operations and / or communications between the computing device 100 and an external device such that the computing device 100 may receive signals to be estimated and provide an estimate of the signals. .

2 is a diagram for explaining a data structure held in a signal estimation process according to an exemplary embodiment.

2, according to an exemplary signal estimation process, 32 signal values (for example, values of a discrete signal received during a time interval 210) input during a time interval 210 from a time point 0 to a time point t Or the sampled values of the continuous signal) belongs to which of the signal value intervals 220 to 228, respectively. For example, the data structure 124 may comprise a set I 230 of different indicators (e.g., non-negative integers) that each represent signal value intervals 220-228. In some embodiments, each of the signal value intervals 220 to 228 may have a predetermined size.

Through this identification, the number of signal values belonging to each of the signal value intervals 220 to 228 can be identified. Indicators indicating the identified number (e.g., non-negative integers) may be included in array N 240 in data structure 124. For example, the number of signal values in the signal value interval indicated by the indicator i (i? I) may be represented by N (i).

In addition, the sum of the signal values within each of the signal value intervals 220 to 228 can be calculated. Indicators (e.g., real numbers) indicating the computed sum may be included in the array S 250 in the data structure 124. For example, the sum of the signal values in the signal value interval indicated by the indicator i (i? I) may be represented by S (i).

The signal value intervals 220 to 228 may be arranged according to the number of signal values within each signal value interval. In some embodiments, a signal value interval in which more signal values belong, among the signal value intervals 220 to 228, may have a lower value ranking. Data structure 124 may include a set R 260 of different indicators (e.g., non-negative integers) that each represent rankings of signal value intervals 220-228. For example, the ranking of the signal value interval indicated by the indicator i (i? I) may be represented by R (i).

The data structure 124 may also include a ranking index set RI 270 that indicates the signal value intervals 220-228 and the rankings of the signal value intervals 220-228 You can have directives sorted in order. For example, an indicator indicating a signal value interval having a rank r (r? R) may be represented by RI (r).

Using this data structure 124, an estimate of the signal input over the time domain 210 may be computed. In particular, the exemplary signal estimation process selects some of the signal value intervals 220-228 according to criteria effective to remove an anomaly from the collected signal values and estimates the signal from the signal values within the selected signal value interval (s) A method of calculating a value can be adopted. This scheme may require much less computational complexity than the conventional outlier removal scheme.

According to some embodiments, the number of signal values in one or more signal value intervals selected from among the signal value intervals 220 to 228 may be set to a predetermined value in accordance with the ascending order of ranking values in set R 260 One or more signal value intervals may be selected from among the signal value intervals 220 to 228. [

As a specific example, when the preset threshold value is 50% of the number of signal values during time period 210, the number of signal values (i.e., N (4)) in the signal value interval 224 to which the largest signal value belongs, ) Exceeds the threshold value. However, since N (4) is 12, the threshold value 32 * 50% = 16 is not satisfied. Therefore, it is determined whether the sum of the number of signal values (i.e., N (5)) and N (4) in the signal value section 225 to which the next largest signal value belongs exceeds the threshold value. Since N (4) + N (5) is 20, it is larger than the threshold value 16. Therefore, the signal value interval 224 and the signal value interval 225 can be selected as the normal range. The estimated value of the signal can then be calculated from the signal values within the selected signal value intervals 224, For example, an average value (i.e., {S (4) + S (5)} / {N (4) + N (5)}) of signal values (considered normal) in signal value intervals 224, May be calculated and provided as an estimated value of the signal for the time domain 210.

FIG. 3 illustrates a signal estimation process according to an exemplary embodiment. For example, the operations included in the exemplary process 300 may be performed by the computing device 100.

After the start operation, the process 300 proceeds to operation S305. In operation S305, the set I 230, the array N 240, the array S 250, the set R 260 and the set RI 270 included in the data structure 124 0). In operation S305, a variable C indicating the number of input all signal values is initialized to zero.

In operation S310, a signal value D is received. Then, the size H of each signal value section, the window size W, and the signal value interval selection function F may be set (S315). H, W, and / or F may change with time or may be fixed, and it may be set only once at an initial stage among H, W, and F.

In operation S320, the signal value interval to which the signal value D belongs is identified. For example, such a signal value interval may be indicated by the indicator i = [D / H], where [x] is the maximum integer not exceeding x.

In operation S325, the number N (i) of signal values in the identified signal value interval is N (i) +1 and the sum S (i) of signal values in the signal value interval is S (i) + D , And the number C of all input signal values is updated to C + 1.

In operation S330, the ranking of each signal value interval is adjusted based on the array N 240 including the updated N (i). For example, in accordance with the pseudo code shown in Fig. 4, after initializing the variable r with the ranking value R (i) of the identified signal value interval, if the signal r has a positive value, It is possible to repeat changing the ranking of the above two signal value ranges until the number of signal values in the value interval (i.e., N (RI (r-1))) becomes equal to or larger than N (RI (r)). If r is 0, the ranking value R (i) of the identified signal value interval will remain as r.

In operation S335, it is determined whether the number C of the entire signal values is equal to or smaller than the window size W. If C is less than or equal to W, the process 300 proceeds to operation S360.

If C is greater than W, the oldest signal value OD is identified (S340).

Then, a signal value section to which the signal value OD belongs is identified (S345). For example, the signal value interval may be indicated by the indicator j = [OD / H].

In operation S350, in order to delete the signal value OD from the current window, the number N (j) of signal values within the identified signal value interval is N (j) -1, and the sum of the signal values within the signal value interval S (j) is updated to S (j) -OD, and the number C of all input signal values is updated to C-1.

In operation S355, the ranking of each signal value interval is adjusted based on the array N 240 including the updated N (j). For example, in accordance with the pseudo code shown in Fig. 5, the variable r is initialized with the ranking value R (j) of the identified signal value interval, and then the signal r in the signal value interval having the ranking value r + It is possible to repeat changing the ranking of the above two signal value ranges until the number of values (i.e., N (RI (r + 1))) becomes N (RI (r)) or less. Subsequently, the process 300 proceeds to operation S360.

At operation S360, a signal value interval selection is made based on the data structure 124 including set I 230, array N 240, array S 250, set R 260 and set RI 270 The function F is called. Accordingly, some of the signal value intervals 220 to 228 may be selected.

Examples of criteria for selecting one or more signal value intervals in the signal value interval selection function F may vary. For example, the first signal value interval (i.e., the signal value interval having the largest N (i) to the smallest R (i)) to which the largest number of signal values belong can be selected. In addition, as described above with reference to FIG. 2, a first signal value interval and, in some cases, an additional signal value interval may be selected using a predetermined threshold value, and each selected signal value interval (s) More signal values can belong to each of the remaining signal value intervals except for the value interval (s). Furthermore, one alternative is that the number of signal values in one or more signal value intervals selected in a manner similar to that described in connection with FIG. 2 exceeds a predetermined threshold value, and the selected one or more signal value intervals are divided into a first signal value interval . ≪ / RTI > However, according to this alternative method, when the number of signal values in the first signal value interval does not exceed the threshold value, the signal value interval to which the next large number of signal values belong is considered, May be considered.

In operation S365, an estimated signal value is calculated from the signal values within one or more selected signal value intervals. For example, an average value of signal values within a selected signal value interval may be calculated and provided as an estimated value.

Then, the process 300 proceeds to operation S310 again.

6 shows a signal estimating device for receiving a signal indicative of the coordinates of a user input device and providing the coordinates thereof according to an exemplary embodiment.

6, the exemplary signal estimating apparatus 600 includes at least one sensor 610-1, 610-2, ..., 610-n, a signal processing unit 620, a signal estimating unit 630, A coordinate calculation unit 640, and a coordinate output unit 650. Such a signal estimating apparatus 600 may be implemented by one or more hardware modules (e.g., ultrasonic sensors, processors, memories and / or input / output interfaces).

The one or more sensors 610-1, 610-2, ..., 610-n are adapted to receive a signal (e.g., signals 670-1, 670-2, ..., , 670-n) from a user input device 680, such as a stylus pen. Each of the one or more sensors 610-1, 610-2 ... 610-n may be a type of sensor suitable for sensing the movement of the user input device 680 (e.g., an ultrasonic sensor or an infrared sensor) . Also, the one or more sensors 610-1, 610-2, ..., 610-n may be a sufficient number of sensors to sense movement of the user input device 680. For example, signals representing positions of the user input device 680 on the X, Y, and Z axes, respectively, may be received at three sensors.

The signal processing unit 620 may be configured to detect a plurality of signal values from a signal received during a specific time period. Referring back to FIG. 2, the signal processing unit 620 can detect 32 signal values over the time interval 210.

The signal estimator 630 may be configured to perform the signal estimation process described above. For example, the signal estimator 630 can identify which of a plurality of signal value intervals a plurality of signal value values belong to. Accordingly, the signal estimator 630 can update the number of signal values within each signal value interval. In some embodiments, the plurality of signal values may each be signal values at a predetermined number of most recent points within a particular time period. For example, if the signal processing unit 620 detects one signal value at a time according to the passage of time and the number of detected signal values up to the latest time exceeds a predetermined number, Only the signal estimation unit 630 can be used. For this purpose, the signal estimator 630 may increase the number of signal values in the signal value interval to which the new signal value belongs by 1, and decrease the number of signal values in the signal value interval to which the oldest signal value belongs by one .

Further, the signal estimator 630 may select some of the plurality of signal value intervals based on the number of signal values within each signal value interval. Accordingly, the signal estimator 630 can calculate the estimated value of the signal indicating the coordinates of the user input device 680 from the signal values within the selected one or more signal value intervals.

As mentioned above, the criterion for selecting the signal value interval for use by the signal estimator 630 to estimate the signal may vary.

For example, the signal estimator 630 may preferentially and / or uniquely select a first signal value interval in which more signal values belong to each of the plurality of signal value intervals than the rest of the plurality of signal value intervals. 2, the signal estimator 630 may select a signal value interval 224 for signal estimation. If the number of signal values in the signal value interval 224 is greater than the number of signal values in the other signal value interval You can see the point.

Another additional or alternative criterion may be that the number of signal values within the selected one or more signal value intervals must exceed a preset threshold value. Further, a criterion that each of the selected signal value sections includes more signal values than the remaining ones of the plurality of signal value sections may be further adopted. Referring back to FIG. 2, it can be seen that the signal value interval 224 and the signal value interval 225 are selected, with the ranking values being 0 and 1, respectively.

According to some embodiments, the signal estimator 630 selecting one or more signal value intervals may involve the following operations. First, the signal estimator 630 determines that the signal value interval in which the greatest number of signal values belongs to at least a part of the plurality of signal value intervals (that is, the signal value intervals not yet included in the normal range) Can be identified. Further, the signal estimator 630 can determine whether the number of signal values within the normal range is larger than a preset threshold value. If the number of signal values within the normal range is not greater than the predetermined threshold value, the signal estimator 630 can repeat the above identification operation and determination operation. If the number of signal values in the normal range is larger than a preset threshold value, the signal estimator 630 can select the signal value interval (s) within the normal range and calculate an estimated value of the signal therefrom. Referring back to FIG. 2, it can be recognized that the signal value interval 224 with a ranking value of 0 initially is included in the normal range. Subsequently, it may be determined whether the number of signal values within the current normal range is greater than a predetermined threshold value (32 * 50% = 16). Since the number of signal values in the signal value interval 224 is 12 and smaller than the threshold value, the remaining signal value intervals 220, 221, 222, 223, 225, 226, 227, 228 (That is, having a ranking value of 1) within the normal range can be identified as being included in the normal range. It is then determined whether the number of signal values within the current normal range (i.e., the sum of the number of signal values in the signal value section 224 and the number of signal values in the signal value section 225) is greater than a threshold value. Since the number of signal values in the current normal range is 20 and larger than the threshold value, the signal value intervals 224 and 225 within the normal range can be selected and the estimated value of the signal can be calculated therefrom.

The coordinate calculator 640 calculates the coordinates of the user input device 680 using the estimated values of the signals received from the sensors 610-1, 610-2, ..., and 610- Of the coordinates). The coordinate output unit 650 may be configured to provide the calculated coordinates to an external device (e.g., a target device 690, which is a computing device that uses the coordinates to represent various graphical elements on a display device).

On the other hand, certain embodiments may include a computer readable storage medium comprising a program for performing the procedures described herein on a computer. Such computer-readable storage media may include program instructions, local data files, local data structures, etc., alone or in combination. The computer-readable storage medium may be those specially designed and constructed for the present invention. Examples of computer-readable storage media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floppy disks, and ROMs, And hardware devices specifically configured to store and execute the same program instructions. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. According to another embodiment, a computer program for performing the processes described herein may be provided. Such a program may be stored on a medium such as a computer-readable storage medium in combination with hardware to perform the above process.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, . Therefore, the scope of the present invention should not be limited to the above-described embodiments, but should be determined by equivalents to the appended claims, as well as the appended claims.

100: computing device
110: Processor
120: computer readable storage medium
122: Computer executable instructions
124: Data structure
130: Interface
600: Signal Estimation Apparatus
610-1, 610-2, ..., 610-n: sensors
620:
630:
630: coordinate calculation unit
640: Coordinate output unit
670-1, 670-2, ..., 670-n: signal
680: User input device
690: Target device

Claims (15)

A signal processing unit for detecting a plurality of signal values from a signal received during a specific time period; And
And determines which of the plurality of signal value sections belongs to which of the plurality of signal value sections and selects a part of the plurality of signal value sections based on the number of signal values within each of the plurality of signal value sections And a signal estimator for calculating an estimated value of the signal from the signal value in the part
/ RTI > The method according to claim 1,
Wherein selecting the portion includes selecting a first signal value interval of the plurality of signal value intervals, wherein the first signal value interval includes more signal values than the remaining ones of the plurality of signal value intervals, / RTI > The method according to claim 1,
Wherein selecting the portion comprises selecting one or more signal value intervals of the plurality of signal value intervals, wherein the number of signal values in the one or more signal value intervals is greater than a preset threshold value. The method of claim 3,
Wherein each of the one or more signal value sections includes more signal values than each of the remaining signal value sections excluding the one or more signal value sections of the plurality of signal value sections. The method of claim 3,
Wherein the selecting of the one or more signal value intervals includes identifying that a signal value interval in which at least a portion of the plurality of signal value intervals belongs to is within a normal range, Wherein the step of selecting the one or more signal value intervals is to repeat the identification if the number of signal values within the normal range is not greater than the preset threshold value, Further comprising selecting said normal range as said part if the number of signal values within said range is greater than said preset threshold value. The method according to claim 1,
Wherein the plurality of signal values are signal values at a predetermined number of most recent points within the specific time period, respectively. The method according to claim 1,
A sensor for receiving the signal from a user input device; And
And a coordinate calculation unit for calculating coordinates of the user input device using the estimated value. Detecting a plurality of signal values from a signal received during a specific time period;
Determining which one of the plurality of signal value intervals belongs to each of the plurality of signal values;
Selecting a portion of the plurality of signal value intervals based on the number of signal values within each of the plurality of signal value intervals; And
And calculating an estimated value of the signal from the signal value within the portion
Signal estimation method. The method of claim 8,
Selecting a portion of the plurality of signal value intervals comprises selecting a first signal value interval of the plurality of signal value intervals, wherein the first signal value interval includes more signal values than the remaining ones of the plurality of signal value intervals Belongs to the signal estimation method. The method of claim 8,
Wherein the selecting a portion comprises selecting one or more signal value intervals of the plurality of signal value intervals, wherein the number of signal values in the one or more signal value intervals is greater than a preset threshold value. The method of claim 10,
Wherein each of the one or more signal value sections includes more signal values than each of the remaining signal value sections excluding the one or more signal value sections of the plurality of signal value sections. The method of claim 10,
Wherein the step of selecting the one or more signal value intervals includes identifying that a signal value interval in which at least a portion of the plurality of signal value intervals belongs to is within a normal range, Wherein the step of selecting one or more signal value intervals comprises:
Repeating the identification if the number of signal values within the normal range is not greater than the preset threshold value; And
And selecting the normal range as the part if the number of signal values within the normal range is greater than the preset threshold value. The method of claim 8,
Wherein the plurality of signal values are signal values at a predetermined number of most recent time points within the specific time period, respectively. The method of claim 8,
Receiving the signal from a user input device; And
And calculating the coordinates of the user input device using the estimated value. Combined with hardware,
Detecting a plurality of signal values from a signal received during a specific time period;
Determining which one of the plurality of signal value intervals belongs to each of the plurality of signal values;
Selecting a portion of the plurality of signal value intervals based on the number of signal values within each of the plurality of signal value intervals; And
And calculating an estimated value of the signal from the signal value within the portion.

Images