Limits...
Optimal Sensor Selection for Classifying a Set of Ginsengs Using Metal-Oxide Sensors.

Miao J, Zhang T, Wang Y, Li G - Sensors (Basel) (2015)

Bottom Line: The relation of the minimum numbers of sensors with number of samples in the sample set was revealed.The results showed that as the number of samples increased, the average minimum number of sensors increased, while the increment decreased gradually and the average optimal classification rate decreased gradually.Moreover, a new approach of sensor selection was proposed to estimate and compare the effective information capacity of each sensor.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou 310027, Zhejiang, China. jiacheng@zju.edu.cn.

ABSTRACT
The sensor selection problem was investigated for the application of classification of a set of ginsengs using a metal-oxide sensor-based homemade electronic nose with linear discriminant analysis. Samples (315) were measured for nine kinds of ginsengs using 12 sensors. We investigated the classification performances of combinations of 12 sensors for the overall discrimination of combinations of nine ginsengs. The minimum numbers of sensors for discriminating each sample set to obtain an optimal classification performance were defined. The relation of the minimum numbers of sensors with number of samples in the sample set was revealed. The results showed that as the number of samples increased, the average minimum number of sensors increased, while the increment decreased gradually and the average optimal classification rate decreased gradually. Moreover, a new approach of sensor selection was proposed to estimate and compare the effective information capacity of each sensor.

No MeSH data available.


The first step of comparison of average classification performance (A2) of sensor sets including certain sensor with that not including it for sensor number of N = 1 to 11. ‘YES’ means including, ‘NO’ means not including.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541866&req=5

sensors-15-16027-f005: The first step of comparison of average classification performance (A2) of sensor sets including certain sensor with that not including it for sensor number of N = 1 to 11. ‘YES’ means including, ‘NO’ means not including.

Mentions: When a certain sensor set is used to discriminate a certain sample set, some sensors may contain more valid information, while some may contain less valid or redundant information. Some sensors even carry a lot of noise that degrades the performance of the classifier. In this section, we come up with a new approach to grade the sensors within the sensor set for discriminating a certain sample set. Firstly, for a certain sample set consisting of M sample species, the classification accuracies of each potential combination of sensors were calculated. We compared the average performance of sensor sets of N (N = 1 to 11) sensors including certain sensors with those not including it. ‘+’ was added after sensor’s serial number for ‘better when including it’, and ‘−’ for ‘worse when including it’. Then we deleted the sensor sets including sensors with ‘−’ values. The entire procedure was repeated until no sensor was added a ‘−’. Finally, the sensors are graded according to performance during the whole procedure. This procedure does not need any initial condition or parameter, and the selection result in every step is fixed after calculating the classification accuracy of all combinations of sensors. Taking sample set A2 = 2, 5, 9 as an example, the result of the first step of the procedure was shown in Figure 5 and the results are listed in Table 3.


Optimal Sensor Selection for Classifying a Set of Ginsengs Using Metal-Oxide Sensors.

Miao J, Zhang T, Wang Y, Li G - Sensors (Basel) (2015)

The first step of comparison of average classification performance (A2) of sensor sets including certain sensor with that not including it for sensor number of N = 1 to 11. ‘YES’ means including, ‘NO’ means not including.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541866&req=5

sensors-15-16027-f005: The first step of comparison of average classification performance (A2) of sensor sets including certain sensor with that not including it for sensor number of N = 1 to 11. ‘YES’ means including, ‘NO’ means not including.
Mentions: When a certain sensor set is used to discriminate a certain sample set, some sensors may contain more valid information, while some may contain less valid or redundant information. Some sensors even carry a lot of noise that degrades the performance of the classifier. In this section, we come up with a new approach to grade the sensors within the sensor set for discriminating a certain sample set. Firstly, for a certain sample set consisting of M sample species, the classification accuracies of each potential combination of sensors were calculated. We compared the average performance of sensor sets of N (N = 1 to 11) sensors including certain sensors with those not including it. ‘+’ was added after sensor’s serial number for ‘better when including it’, and ‘−’ for ‘worse when including it’. Then we deleted the sensor sets including sensors with ‘−’ values. The entire procedure was repeated until no sensor was added a ‘−’. Finally, the sensors are graded according to performance during the whole procedure. This procedure does not need any initial condition or parameter, and the selection result in every step is fixed after calculating the classification accuracy of all combinations of sensors. Taking sample set A2 = 2, 5, 9 as an example, the result of the first step of the procedure was shown in Figure 5 and the results are listed in Table 3.

Bottom Line: The relation of the minimum numbers of sensors with number of samples in the sample set was revealed.The results showed that as the number of samples increased, the average minimum number of sensors increased, while the increment decreased gradually and the average optimal classification rate decreased gradually.Moreover, a new approach of sensor selection was proposed to estimate and compare the effective information capacity of each sensor.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou 310027, Zhejiang, China. jiacheng@zju.edu.cn.

ABSTRACT
The sensor selection problem was investigated for the application of classification of a set of ginsengs using a metal-oxide sensor-based homemade electronic nose with linear discriminant analysis. Samples (315) were measured for nine kinds of ginsengs using 12 sensors. We investigated the classification performances of combinations of 12 sensors for the overall discrimination of combinations of nine ginsengs. The minimum numbers of sensors for discriminating each sample set to obtain an optimal classification performance were defined. The relation of the minimum numbers of sensors with number of samples in the sample set was revealed. The results showed that as the number of samples increased, the average minimum number of sensors increased, while the increment decreased gradually and the average optimal classification rate decreased gradually. Moreover, a new approach of sensor selection was proposed to estimate and compare the effective information capacity of each sensor.

No MeSH data available.