{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:42:30Z","timestamp":1760233350162,"version":"build-2065373602"},"reference-count":45,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2021,1,7]],"date-time":"2021-01-07T00:00:00Z","timestamp":1609977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The present aim was to compare the accuracy of several algorithms in classifying data collected from food scent samples. Measurements using an electronic nose (eNose) can be used for classification of different scents. An eNose was used to measure scent samples from seven food scent sources, both from an open plate and a sealed jar. The k-Nearest Neighbour (k-NN) classifier provides reasonable accuracy under certain conditions and uses traditionally the Euclidean distance for measuring the similarity of samples. Therefore, it was used as a baseline distance metric for the k-NN in this paper. Its classification accuracy was compared with the accuracies of the k-NN with 66 alternative distance metrics. In addition, 18 other classifiers were tested with raw eNose data. For each classifier various parameter settings were tried and compared. Overall, 304 different classifier variations were tested, which differed from each other in at least one parameter value. The results showed that Quadratic Discriminant Analysis, MLPClassifier, C-Support Vector Classification (SVC), and several different single hidden layer Neural Networks yielded lower misclassification rates applied to the raw data than k-NN with Euclidean distance. Both MLP Classifiers and SVC yielded misclassification rates of less than 3% when applied to raw data. Furthermore, when applied both to the raw data and the data preprocessed by principal component analysis that explained at least 95% or 99% of the total variance in the raw data, Quadratic Discriminant Analysis outperformed the other classifiers. The findings of this study can be used for further algorithm development. They can also be used, for example, to improve the estimation of storage times of fruit.<\/jats:p>","DOI":"10.3390\/s21020361","type":"journal-article","created":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T23:03:42Z","timestamp":1610319822000},"page":"361","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Comparison of Various Algorithms for Classification of Food Scents Measured with an Ion Mobility Spectrometry"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9160-8155","authenticated-orcid":false,"given":"Georgy","family":"Minaev","sequence":"first","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, 33720 Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4314-7339","authenticated-orcid":false,"given":"Philipp","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, 33720 Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0284-7622","authenticated-orcid":false,"given":"Katri","family":"Salminen","sequence":"additional","affiliation":[{"name":"R&amp;D and Innovation Services, Tampere University of Applied Sciences, 33230 Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6308-7874","authenticated-orcid":false,"given":"Jussi","family":"Rantala","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, 33720 Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3986-0713","authenticated-orcid":false,"given":"Veikko","family":"Surakka","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, 33720 Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8895-2879","authenticated-orcid":false,"given":"Ari","family":"Visa","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology and Communication Sciences, Tampere University, 33720 Tampere, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,7]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"Application of electronic nose systems for assessing quality of medicinal and aromatic plant products: A review","volume":"3","author":"Kiani","year":"2016","journal-title":"J. Appl. Res. Med. Aromat. Plants"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"5099","DOI":"10.3390\/s90705099","article-title":"Applications and advances in electronic-nose technologies","volume":"9","author":"Wilson","year":"2009","journal-title":"Sensors"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.trac.2017.07.006","article-title":"Current applications and perspectives of ion mobility spectrometry to answer chemical food safety issues","volume":"94","author":"Escourrou","year":"2017","journal-title":"TrAC Trends Anal. Chem."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.aca.2011.07.021","article-title":"A review of recent, unconventional applications of ion mobility spectrometry (IMS)","volume":"703","author":"Armenta","year":"2011","journal-title":"Anal. Chim. Acta"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.eaef.2016.05.004","article-title":"State of ion mobility spectrometry and applications in agriculture: A review","volume":"9","author":"Kafle","year":"2016","journal-title":"Eng. Agric. Environ. Food"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Salminen, K., Nieminen, V., Kontunen, A., Karjalainen, M., Isokoski, P., Rantala, J., Savia, M., V\u00e4liaho, J., and Kallio, P. (2018). Scent Classification by K Nearest Neighbors using Ion-Mobility Spectrometry Measurements. Expert Syst. Appl., 115.","DOI":"10.1016\/j.eswa.2018.08.042"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"6435","DOI":"10.3390\/s110606435","article-title":"An Electronic Nose for Reliable Measurement and Correct Classification of Beverages","volume":"11","author":"Mamat","year":"2011","journal-title":"Sensors"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0003-2670(01)01355-1","article-title":"Electronic nose based on metal oxide semiconductor sensors and pattern recognition techniques: Characterisation of vegetable oils","volume":"449","author":"Oliveros","year":"2001","journal-title":"Anal. Chim. Acta"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1556\/AAlim.34.2005.2.5","article-title":"Evaluation of the signal response of the electronic nose measured on oregano and lovage samples using different methods of multivariate analysis","volume":"34","year":"2005","journal-title":"Acta Aliment."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zheng, S., Ren, W., and Huang, L. (2015). Geoherbalism evaluation of Radix Angelica sinensis based on electronic nose. J. Pharm. Biomed. Anal., 105.","DOI":"10.1016\/j.jpba.2014.10.033"},{"key":"ref_11","first-page":"1","article-title":"Rapid discrimination of Apiaceae plants by electronic nose coupled with multivariate statistical analyses","volume":"84C","author":"Lin","year":"2013","journal-title":"J. Pharm. Biomed. Anal."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.jfoodeng.2008.11.014","article-title":"Identification of coumarin-enriched Japanese green teas and their particular flavor using electronic nose","volume":"92","author":"Yang","year":"2009","journal-title":"J. Food Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1578","DOI":"10.3390\/s130201578","article-title":"Fast Classification of Meat Spoilage Markers Using Nanostructured ZnO Thin Films and Unsupervised Feature Learning","volume":"13","author":"Coradeschi","year":"2013","journal-title":"Sensors"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0925-4005(96)80047-5","article-title":"Fuzzy Neural Computing of Coffee and Tainted Water Data from an Electronic Nose","volume":"30","author":"Singh","year":"1999","journal-title":"Sensors Actuators B Chem."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1670","DOI":"10.1109\/TIM.2014.2298691","article-title":"Performance Study of Multilayer Perceptrons in a Low-Cost Electronic Nose","volume":"63","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1016\/j.trac.2010.12.007","article-title":"Ion-mobility spectrometry for environmental analysis","volume":"30","author":"Aguilera","year":"2011","journal-title":"TrAC Trends Anal. Chem."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Szyma\u0144ska, E., Davies, A., and Buydens, L. (2016). Chemometrics for ion mobility spectrometry data: Recent advances and future prospects. Analyst, 141.","DOI":"10.1039\/C6AN01008C"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1016\/j.envres.2015.05.017","article-title":"Review. Moving your laboratories to the field\u2014Advantages and limitations of the use of field portable instruments in environmental sample analysis","volume":"140","author":"Migaszewski","year":"2015","journal-title":"Environ. Res."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Minaev, G., M\u00fcller, P., Visa, A., and Pich\u00e9, R. (2018, January 24\u201326). Indoor Localisation using Aroma Fingerprints: Comparing Nearest Neighbour Classification Accuracy using Different Distance Measures. Proceedings of the 7th International Conference on Systems and Control (ICSC), Valencia, Spain.","DOI":"10.1109\/ICoSC.2018.8587811"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Lekkala, J., Ali-L\u00f6ytty, S., and Pich\u00e9, R. (2017, January 25\u201326). Indoor Localisation using Aroma Fingerprints: A First Sniff. Proceedings of the 14th Workshop on Positioning, Navigation and Communications (WPNC), Bremen, Germany.","DOI":"10.1109\/WPNC.2017.8250046"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1016\/S0039-9140(99)00241-6","article-title":"Analysis of explosives using electrospray ionization\/ion mobility spectrometry (ESI\/IMS)","volume":"50","author":"Asbury","year":"2000","journal-title":"Talanta"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"126158","DOI":"10.1016\/j.foodchem.2019.126158","article-title":"Recent progress in food flavor analysis using gas chromatography\u2013ion mobility spectrometry (GC\u2013IMS)","volume":"315","author":"Wang","year":"2020","journal-title":"Food Chem."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"012030","DOI":"10.1088\/1755-1315\/545\/1\/012030","article-title":"Application of GC-IMS in Detection of Food Flavor Substances","volume":"545","author":"He","year":"2020","journal-title":"IOP Conf. Ser. Earth Environ. Sci."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.foodchem.2019.03.124","article-title":"Development of a flavor fingerprint by HS-GC\u2013IMS with PCA for volatile compounds of Tricholoma matsutake Singer","volume":"290","author":"Li","year":"2019","journal-title":"Food Chem."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.foodcont.2018.11.001","article-title":"HS-GC-IMS and chemometric data treatment for food authenticity assessment: Olive oil mapping and classification through two different devices as an example","volume":"98","author":"Arce","year":"2019","journal-title":"Food Control"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Salminen, K., Nieminen, V., Kontunen, A., Karjalainen, M., Isokoski, P., Rantala, J., Savia, M., V\u00e4liaho, J., and Kallio, P. (2020, May 05). Dataset for M\u00fcller et al.\u2014Scent Classification by K Nearest Neighbors Using Ion-Mobility Spectrometry. Available online: http:\/\/urn.fi\/urn:nbn:fi:csc-kata20180418151056882791.","DOI":"10.1016\/j.eswa.2018.08.042"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"M\u00fcller, P., Salminen, K., Kontunen, A., Karjalainen, M., Isokoski, P., Rantala, J., Leivo, J., V\u00e4liaho, J., Kallio, P., and Lekkala, J. (2019). Online Scent Classification by Ion-Mobility Spectrometry Sequences. Front. Appl. Math. Stat., 5.","DOI":"10.3389\/fams.2019.00039"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Isokoski, P., Salminen, K., M\u00fcller, P., Rantala, J., Nieminen, V., Karjalainen, M., Valiaho, J., Kontunen, A., Savia, M., and Leivo, J. (2020, January 29\u201330). Transferring Scents over a Communication Network. Proceedings of the 23rd International Conference on Academic Mindtrek, Tampere, Finland.","DOI":"10.1145\/3377290.3377301"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yang, J., Sun, Z., and Chen, Y. (2016). Fault Detection Using the Clustering-k-NN Rule for Gas Sensor Arrays. Sensors, 16.","DOI":"10.3390\/s16122069"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ye, W., Zhao, X., Pan, X., and Cao, Y. (2017). Classification of Data from Electronic Nose Using Gradient Tree Boosting Algorithm. Sensors, 17.","DOI":"10.3390\/s17102376"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Minaev, G., Visa, A., and Pich\u00e9, R. (2017, January 18\u201321). Comprehensive survey of similarity measures for ranked based location fingerprinting algorithm. Proceedings of the 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN), Sapporo, Japan.","DOI":"10.1109\/IPIN.2017.8115922"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1145\/361002.361007","article-title":"Multidimensional Binary Search Trees Used for Associative Searching","volume":"18","author":"Bentley","year":"1975","journal-title":"Commun. ACM"},{"key":"ref_33","unstructured":"Ghojogh, B., and Crowley, M. (2021, January 06). Linear and Quadratic Discriminant Analysis: Tutorial. Available online: https:\/\/arxiv.org\/abs\/1906.02590."},{"key":"ref_34","unstructured":"Haykin, S. (2009). Neural Networks and Learning Machines, Pearson Education. [3rd ed.]."},{"key":"ref_35","unstructured":"Sohl-Dickstein, J., Poole, B., and Ganguli, S. (2014, January 21\u201326). Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods. Proceedings of the 31st International Conference on Machine Learning, Beijing, China."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Chang, C.C., and Lin, C.J. (2011). LIBSVM: A Library for Support Vector Machines. ACM Trans. Intell. Syst. Technol.","DOI":"10.1145\/1961189.1961199"},{"key":"ref_37","unstructured":"Duda, R., Hart, P., and Stork, G.D. (2001). Pattern Classification, Wiley Interscience."},{"key":"ref_38","first-page":"542","article-title":"Cross-Validation","volume":"1","author":"Berrar","year":"2019","journal-title":"Encycl. Bioinform. Comput. Biol."},{"key":"ref_39","unstructured":"(2020, August 17). ChemPro100i Handheld Chemical Detector. Available online: https:\/\/www.environics.fi\/product\/chempro100i\/."},{"key":"ref_40","unstructured":"Minaev, G., Pich\u00e9, R., and Visa, A. (2021, January 06). Distance Measures for Classification of Numerical Features. Available online: http:\/\/urn.fi\/URN:NBN:fi:tuni-202012168900."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Deza, M., and Deza, E. (2009). Encyclopedia of Distances, Springer. [3rd ed.].","DOI":"10.1007\/978-3-642-00234-2"},{"key":"ref_42","first-page":"300","article-title":"Comprehensive Survey on Distance\/Similarity Measures Between Probability Density Functions","volume":"1","author":"Cha","year":"2007","journal-title":"Int. J. Math. Model. Methods Appl. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"4744","DOI":"10.3390\/s110504744","article-title":"Electronic Noses and Tongues: Applications for the Food and Pharmaceutical Industries","volume":"11","author":"Baldwin","year":"2011","journal-title":"Sensors"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1016\/j.foodres.2012.11.029","article-title":"Applications of ion mobility spectrometry (IMS) in the field of foodomics","volume":"54","author":"Karpas","year":"2013","journal-title":"Food Res. Int."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez-Mesa, M., Ropartz, D., Garc\u00eda-Campana, A.M., Rogniaux, H., Dervilly-Pinel, G., and Le Bizec, B. (2019). Ion Mobility Spectrometry in Food Analysis: Principles, Current Applications and Future Trends. Molecules, 24.","DOI":"10.3390\/molecules24152706"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/2\/361\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:08:04Z","timestamp":1760159284000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/2\/361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,7]]},"references-count":45,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["s21020361"],"URL":"https:\/\/doi.org\/10.3390\/s21020361","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,1,7]]}}}