Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging
In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Xin, Zhou [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2019transfer abstract |
|---|
| Umfang: |
6 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training - An, Chen-Chi ELSEVIER, 2017, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:206 ; year:2019 ; day:5 ; month:01 ; pages:378-383 ; extent:6 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.saa.2018.07.049 |
|---|
| Katalog-ID: |
ELV044239165 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV044239165 | ||
| 003 | DE-627 | ||
| 005 | 20230626004822.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 181113s2019 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.saa.2018.07.049 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica |
| 035 | |a (DE-627)ELV044239165 | ||
| 035 | |a (ELSEVIER)S1386-1425(18)30703-0 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 660 |q VZ |
| 084 | |a 50.21 |2 bkl | ||
| 100 | 1 | |a Xin, Zhou |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging |
| 264 | 1 | |c 2019transfer abstract | |
| 300 | |a 6 | ||
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. | ||
| 520 | |a In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. | ||
| 700 | 1 | |a Jun, Sun |4 oth | |
| 700 | 1 | |a Xiaohong, Wu |4 oth | |
| 700 | 1 | |a Bing, Lu |4 oth | |
| 700 | 1 | |a Ning, Yang |4 oth | |
| 700 | 1 | |a Chunxia, Dai |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a An, Chen-Chi ELSEVIER |t Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training |d 2017 |g Amsterdam [u.a.] |w (DE-627)ELV000384860 |
| 773 | 1 | 8 | |g volume:206 |g year:2019 |g day:5 |g month:01 |g pages:378-383 |g extent:6 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.saa.2018.07.049 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OLC-PHA | ||
| 936 | b | k | |a 50.21 |j Messtechnik |q VZ |
| 951 | |a AR | ||
| 952 | |d 206 |j 2019 |b 5 |c 0105 |h 378-383 |g 6 | ||
| author_variant |
z x zx |
|---|---|
| matchkey_str |
xinzhoujunsunxiaohongwubingluningyangchu:2019----:eerhnodtaetrcasfctobsdnknloihad |
| hierarchy_sort_str |
2019transfer abstract |
| bklnumber |
50.21 |
| publishDate |
2019 |
| allfields |
10.1016/j.saa.2018.07.049 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica (DE-627)ELV044239165 (ELSEVIER)S1386-1425(18)30703-0 DE-627 ger DE-627 rakwb eng 660 VZ 50.21 bkl Xin, Zhou verfasserin aut Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging 2019transfer abstract 6 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. Jun, Sun oth Xiaohong, Wu oth Bing, Lu oth Ning, Yang oth Chunxia, Dai oth Enthalten in Elsevier Science An, Chen-Chi ELSEVIER Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training 2017 Amsterdam [u.a.] (DE-627)ELV000384860 volume:206 year:2019 day:5 month:01 pages:378-383 extent:6 https://doi.org/10.1016/j.saa.2018.07.049 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 50.21 Messtechnik VZ AR 206 2019 5 0105 378-383 6 |
| spelling |
10.1016/j.saa.2018.07.049 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica (DE-627)ELV044239165 (ELSEVIER)S1386-1425(18)30703-0 DE-627 ger DE-627 rakwb eng 660 VZ 50.21 bkl Xin, Zhou verfasserin aut Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging 2019transfer abstract 6 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. Jun, Sun oth Xiaohong, Wu oth Bing, Lu oth Ning, Yang oth Chunxia, Dai oth Enthalten in Elsevier Science An, Chen-Chi ELSEVIER Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training 2017 Amsterdam [u.a.] (DE-627)ELV000384860 volume:206 year:2019 day:5 month:01 pages:378-383 extent:6 https://doi.org/10.1016/j.saa.2018.07.049 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 50.21 Messtechnik VZ AR 206 2019 5 0105 378-383 6 |
| allfields_unstemmed |
10.1016/j.saa.2018.07.049 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica (DE-627)ELV044239165 (ELSEVIER)S1386-1425(18)30703-0 DE-627 ger DE-627 rakwb eng 660 VZ 50.21 bkl Xin, Zhou verfasserin aut Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging 2019transfer abstract 6 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. Jun, Sun oth Xiaohong, Wu oth Bing, Lu oth Ning, Yang oth Chunxia, Dai oth Enthalten in Elsevier Science An, Chen-Chi ELSEVIER Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training 2017 Amsterdam [u.a.] (DE-627)ELV000384860 volume:206 year:2019 day:5 month:01 pages:378-383 extent:6 https://doi.org/10.1016/j.saa.2018.07.049 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 50.21 Messtechnik VZ AR 206 2019 5 0105 378-383 6 |
| allfieldsGer |
10.1016/j.saa.2018.07.049 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica (DE-627)ELV044239165 (ELSEVIER)S1386-1425(18)30703-0 DE-627 ger DE-627 rakwb eng 660 VZ 50.21 bkl Xin, Zhou verfasserin aut Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging 2019transfer abstract 6 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. Jun, Sun oth Xiaohong, Wu oth Bing, Lu oth Ning, Yang oth Chunxia, Dai oth Enthalten in Elsevier Science An, Chen-Chi ELSEVIER Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training 2017 Amsterdam [u.a.] (DE-627)ELV000384860 volume:206 year:2019 day:5 month:01 pages:378-383 extent:6 https://doi.org/10.1016/j.saa.2018.07.049 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 50.21 Messtechnik VZ AR 206 2019 5 0105 378-383 6 |
| allfieldsSound |
10.1016/j.saa.2018.07.049 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica (DE-627)ELV044239165 (ELSEVIER)S1386-1425(18)30703-0 DE-627 ger DE-627 rakwb eng 660 VZ 50.21 bkl Xin, Zhou verfasserin aut Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging 2019transfer abstract 6 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. Jun, Sun oth Xiaohong, Wu oth Bing, Lu oth Ning, Yang oth Chunxia, Dai oth Enthalten in Elsevier Science An, Chen-Chi ELSEVIER Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training 2017 Amsterdam [u.a.] (DE-627)ELV000384860 volume:206 year:2019 day:5 month:01 pages:378-383 extent:6 https://doi.org/10.1016/j.saa.2018.07.049 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 50.21 Messtechnik VZ AR 206 2019 5 0105 378-383 6 |
| language |
English |
| source |
Enthalten in Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training Amsterdam [u.a.] volume:206 year:2019 day:5 month:01 pages:378-383 extent:6 |
| sourceStr |
Enthalten in Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training Amsterdam [u.a.] volume:206 year:2019 day:5 month:01 pages:378-383 extent:6 |
| format_phy_str_mv |
Article |
| bklname |
Messtechnik |
| institution |
findex.gbv.de |
| dewey-raw |
660 |
| isfreeaccess_bool |
false |
| container_title |
Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training |
| authorswithroles_txt_mv |
Xin, Zhou @@aut@@ Jun, Sun @@oth@@ Xiaohong, Wu @@oth@@ Bing, Lu @@oth@@ Ning, Yang @@oth@@ Chunxia, Dai @@oth@@ |
| publishDateDaySort_date |
2019-01-05T00:00:00Z |
| hierarchy_top_id |
ELV000384860 |
| dewey-sort |
3660 |
| id |
ELV044239165 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV044239165</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626004822.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">181113s2019 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.saa.2018.07.049</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV044239165</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1386-1425(18)30703-0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">50.21</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Xin, Zhou</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">6</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Jun, Sun</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiaohong, Wu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bing, Lu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ning, Yang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chunxia, Dai</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">An, Chen-Chi ELSEVIER</subfield><subfield code="t">Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training</subfield><subfield code="d">2017</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV000384860</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:206</subfield><subfield code="g">year:2019</subfield><subfield code="g">day:5</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:378-383</subfield><subfield code="g">extent:6</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.saa.2018.07.049</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">50.21</subfield><subfield code="j">Messtechnik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">206</subfield><subfield code="j">2019</subfield><subfield code="b">5</subfield><subfield code="c">0105</subfield><subfield code="h">378-383</subfield><subfield code="g">6</subfield></datafield></record></collection>
|
| author |
Xin, Zhou |
| spellingShingle |
Xin, Zhou ddc 660 bkl 50.21 Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging |
| authorStr |
Xin, Zhou |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV000384860 |
| format |
electronic Article |
| dewey-ones |
660 - Chemical engineering |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
660 VZ 50.21 bkl Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging |
| topic |
ddc 660 bkl 50.21 |
| topic_unstemmed |
ddc 660 bkl 50.21 |
| topic_browse |
ddc 660 bkl 50.21 |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
s j sj w x wx l b lb y n yn d c dc |
| hierarchy_parent_title |
Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training |
| hierarchy_parent_id |
ELV000384860 |
| dewey-tens |
660 - Chemical engineering |
| hierarchy_top_title |
Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV000384860 |
| title |
Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging |
| ctrlnum |
(DE-627)ELV044239165 (ELSEVIER)S1386-1425(18)30703-0 |
| title_full |
Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging |
| author_sort |
Xin, Zhou |
| journal |
Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training |
| journalStr |
Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2019 |
| contenttype_str_mv |
zzz |
| container_start_page |
378 |
| author_browse |
Xin, Zhou |
| container_volume |
206 |
| physical |
6 |
| class |
660 VZ 50.21 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Xin, Zhou |
| doi_str_mv |
10.1016/j.saa.2018.07.049 |
| dewey-full |
660 |
| title_sort |
research on moldy tea feature classification based on wknn algorithm and nir hyperspectral imaging |
| title_auth |
Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging |
| abstract |
In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. |
| abstractGer |
In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. |
| abstract_unstemmed |
In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA |
| title_short |
Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging |
| url |
https://doi.org/10.1016/j.saa.2018.07.049 |
| remote_bool |
true |
| author2 |
Jun, Sun Xiaohong, Wu Bing, Lu Ning, Yang Chunxia, Dai |
| author2Str |
Jun, Sun Xiaohong, Wu Bing, Lu Ning, Yang Chunxia, Dai |
| ppnlink |
ELV000384860 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth oth |
| doi_str |
10.1016/j.saa.2018.07.049 |
| up_date |
2024-07-06T20:57:23.996Z |
| _version_ |
1803864709787549696 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV044239165</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626004822.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">181113s2019 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.saa.2018.07.049</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001034.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV044239165</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1386-1425(18)30703-0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">50.21</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Xin, Zhou</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Research on moldy tea feature classification based on WKNN algorithm and NIR hyperspectral imaging</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2019transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">6</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In order to identify the moldy tea leaves in a fast and nondestructive way, a method involving wavelet coupled with k-nearest neighbor (WKNN) was proposed to select effective characteristic wavelengths in this paper. The hyperspectral imaging of 300 dried tea samples with 3 different mildew degrees (contrast check, mild moldy and severe moldy) were obtained using hyperspectral data acquisition device. Besides, food microbiological examination results showed that mold count and total numbers of colony increased with the increase of storage time, temperature and humidity. Roughness penalty smoothing (RPS) algorithm was used to preprocess the raw spectra. Afterwards, WKNN was applied to select the optimal wavelengths of spectral data by using db4, db6, sym5, sym7 as wavelet basis functions, respectively. In addition, five layers of wavelet decomposition were adopted based on different wavelet basis functions. Linear discriminant analysis (LDA) algorithm was used to build the classification models based on preprocessed spectra feature in characteristic wavelengths. The results showed that four optimal prediction models were optimal decomposition level in each wavelet basis function. In addition, the best performance model among all LDA models achieved an identification rate of 100% in the calibration set and 98.33% in the prediction set, in which db4 was used as wavelet basis function and the optimal wavelet decomposition level was 2. WKNN algorithm can effectively achieve the best wavelet decomposition layer and the best wavelengths. WKNN algorithm combined with NIR hyperspectral imaging technology can realize the effective wavelength extraction and classification of dried tea with different mildew degrees.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Jun, Sun</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiaohong, Wu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bing, Lu</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ning, Yang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chunxia, Dai</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">An, Chen-Chi ELSEVIER</subfield><subfield code="t">Developing an audio analyzer for instantaneous stroke position identification on table tennis racket to assist technical training</subfield><subfield code="d">2017</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV000384860</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:206</subfield><subfield code="g">year:2019</subfield><subfield code="g">day:5</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:378-383</subfield><subfield code="g">extent:6</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.saa.2018.07.049</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">50.21</subfield><subfield code="j">Messtechnik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">206</subfield><subfield code="j">2019</subfield><subfield code="b">5</subfield><subfield code="c">0105</subfield><subfield code="h">378-383</subfield><subfield code="g">6</subfield></datafield></record></collection>
|
| score |
7.3998413 |