{ "article_id": 1235, "public_id": "fae3d0ce-8982-48e5-b2ae-eae7451f126c", "internal_identifier": null, "source_identifier": "84:76", "status": "published", "type": "research_article", "title": "Çok Katmanlı Algılayıcı Yapay Sinir Ağı Kullanarak Packman Oyununda Yapılan El Hareketlerinin Sınıflandırılması", "title_secondary": null, "abstract": "Elektromiyografi, kas aktivitesi sonucunda meydana gelen biyolojik işaretlerin ölçülmesine olanak sağlayan invaziv olmayan bir yöntemidir. Yüzey ve iğne elektromiyografisi olarak uygulama amacına göre iki şekilde kullanılmaktadır.  Bu çalışmada internet üzerinden açık erişime sahip ‘UCI Machine Learning Repository’ veri tabanında bireylerin packman oyununda yapmış oldukları yedi farklı el hareketi (el dinlenimde, el yumruk yapıldığında, bilek büküldüğünde, bilekte radyal ve ulnar sapma olması durumunda), bireylerden ölçülen yüzey elektromiyogram sinyalleri veri seti kullanarak sınıflandırılmaya çalışılmıştır. Bu amaçla ilk olarak verilerden ayrık dalgacık dönüşümüyle öznitelik çıkarımı yapılmıştır. Daha sonra çıkarılan öznitelikler literatürde çok yaygın olarak kullanılan çok katmanlı algılayıcı yapay sinir ağı yaklaşımı kullanılarak sınıflandırılmıştır. Sınıflandırma sürecinde yapay sinir ağı basit çapraz doğrulama algoritması kullanılarak eğitilmiştir ve sınıflandırıcının algoritması ile başarımı Matlab2017a programıyla gerçekleştirilmiştir. Sınıflandırıcının başarımı veri setinin farklı oranlarda bölünmesi ve farklı ara katman sayıları için araştırılmıştır. Optimum ağ topolojisi veri setinin %20-%80 oranında eğitim ve test verisi olarak bölünmesi ve ara katman sayısının 18 olması durumunda en yüksek başarım %91,67 olarak elde edilmiştir.", "language": "tr", "english_title": "Classification of Hand Gestures in Packman Game Using Multilayer Sensor Neural Network", "english_abstract": "Electromyography is a noninvasive method that allows measurement of biological markers as a result of muscle activity. It is used as surface and needle electromyography according to the application purpose in two ways. In this study, seven different hand gestures (hand rest, hand punch, wrist bend, radial and ulnar deviation of the wrist) made by the individuals in the packman game in the „UCI Machine Learning Repository‟ database with open access over the internet were measured by using the data set of surface electromyogram signals tried to be classified. For this purpose, firstly, feature is extracted from data by discrete wavelet transform. Then, the extracted features were classified using the multi-layered sensor artificial neural network approach, which is widely used in the literature. In the classification process, artificial neural network was trained using simple cross validation algorithm, the algorithm and performance of the classifier were realized with Matlab2017a program.. The performance of the classifier has been investigated for the division of the data set at different rates and for different number of intermediate layers. The optimum network topology is obtained when the data set is divided by 20% -80% and the number of interlayers is 18, the highest performance is obtained as 91.67%.", "doi": "10.36287/setsci.4.6.076", "doi_url": "https://doi.org/10.36287/setsci.4.6.076", "resource_url": "https://www.set-science.com/a/fae3d0ce-8982-48e5-b2ae-eae7451f126c", "pdf_url": "https://www.set-science.com/a/fae3d0ce-8982-48e5-b2ae-eae7451f126c/pdf", "og_image": "https://www.set-science.com/assets/img/og-card-v2.png", "authors": [ { "public_id": "c44e0348-6f34-44f9-baee-12764c179168", "given": "Rukiye", "family": "Uzun Arslan", "full": "Rukiye Uzun Arslan", "literal": null, "orcid": null, "orcid_url": null, "email": "rukiyeuzun67@gmail.com", "corresponding": false, "sequence": "first", "affiliations": [ { "name": "Zonguldak Bülent Ecevit University", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] }, { "public_id": "9654876f-2677-4c7b-992b-089b654937cb", "given": "Gizem Kübra", "family": "Yaman", "full": "Gizem Kübra Yaman", "literal": null, "orcid": null, "orcid_url": null, "email": "gizem.2406@gmail.com", "corresponding": false, "sequence": "additional", "affiliations": [ { "name": "Zonguldak Bülent Ecevit University", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] }, { "public_id": "5acfaee6-baf7-4041-ac91-e9543a451efa", "given": "Yalçın", "family": "İşler", "full": "Yalçın İşler", "literal": null, "orcid": null, "orcid_url": null, "email": "islerya@yahoo.com", "corresponding": true, "sequence": "additional", "affiliations": [ { "name": "İzmir Katip Çelebi University", "department": null, "country": null, "country_code": null, "ror": null, "ror_url": null } ] } ], "keywords": [], "translations": [ { "language": "en", "title": "Classification of Hand Gestures in Packman Game Using Multilayer Sensor Neural Network", "abstract": "Electromyography is a noninvasive method that allows measurement of biological markers as a result of muscle activity. It is used as surface and needle electromyography according to the application purpose in two ways. In this study, seven different hand gestures (hand rest, hand punch, wrist bend, radial and ulnar deviation of the wrist) made by the individuals in the packman game in the „UCI Machine Learning Repository‟ database with open access over the internet were measured by using the data set of surface electromyogram signals tried to be classified. For this purpose, firstly, feature is extracted from data by discrete wavelet transform. Then, the extracted features were classified using the multi-layered sensor artificial neural network approach, which is widely used in the literature. In the classification process, artificial neural network was trained using simple cross validation algorithm, the algorithm and performance of the classifier were realized with Matlab2017a program.. The performance of the classifier has been investigated for the division of the data set at different rates and for different number of intermediate layers. The optimum network topology is obtained when the data set is divided by 20% -80% and the number of interlayers is 18, the highest performance is obtained as 91.67%.", "keywords": [ "Yapay sinir ağları, çok katmanlı algılayıcı, sınıflandırma, elektromiyogram, ayrık dalgacık dönüşümü" ] } ], "subjects": [], "subject_names": [], "published_date": "2019-12-22", "published_year": "2019", "received_date": null, "accepted_date": null, "volume": "9", "issue": null, "page_first": "266", "page_last": "269", "article_number": null, "conference": { "short_name": "ISAS WINTER-2019 (ENS)", "full_title": "4th International Symposium on Innovative Approaches in Engineering and Natural Sciences", "name": "4th International Symposium on Innovative Approaches in Engineering and Natural Sciences", "acronym": "ISAS WINTER-2019 (ENS)", "location": "Samsun, Türkiye", "start_date": "2019-11-22", "end_date": null, "public_id": "ede2435c-3820-4bef-84a9-59e7d8de9d60" }, "proceedings": { "title": "4th International Symposium on Innovative Approaches in Engineering and Natural Sciences", "series_title": "SETSCI Conference Proceedings", "publisher": "SET Technology", "isbn": "978-605-81988-8-3", "eisbn": null, "issn": null, "eissn": "2687-5527", "doi": null, "doi_prefix": "10.36287", "slug": "setsci-volume-9-2019-legacy-84", "public_id": "5d3c128d-5090-429f-8398-4e32c57e5584", "url": "https://www.set-science.com/p/setsci-volume-9-2019-legacy-84" }, "license": { "name": "CC BY 4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "code": "CC-BY-4.0", "open_access": true }, "copyright": { "holder": "SET Technology", "year": "2019" }, "funding_statement": null, "funders": [], "references": [ { "order": 1, "raw": "M.Z. Al Faiz and A.H. Miry, Artificial Human Arm Driven by EMG\r\nMATLAB - A Fundamental Tool for Scientific Computing and\r\nEngineering Applications, Ed. In Katsikis VN,. Intech Open, Greece,\r\n2012.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 2, "raw": "P. Konrad, ABC of EMG: A Practical Introduction To\r\nKinesiological Electromyography, Noraxon USA, Inc., Arizona, USA,\r\n2005.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 3, "raw": "S.A. Güvenç, “Ön kol yüzey EMG sinyallerinin örüntü tanıma tabanlı\r\nanalizi ve yapay sinir ağları ile sınıflandırılması,” Yüksek lisans tezi,\r\nBilgisayar Mühendisliği Anabilim Dalı, Fen Bilimleri Enstitüsü,\r\nKaradeniz Teknik Üniversitesi, Trabzon, Türkiye, 2014.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 4, "raw": "S. Yağcıoğlu, “El hareketlerinin elektromiyogram sinyalleri ve\r\nyardımcı sensör verileri ile sınıflandırılması”, Yüksek lisans tezi, Fen\r\nBilimleri Enstitüsü, Elektronik ve Haberleşme Mühendisliği Anabilim\r\nDalı Biyomedikal Mühendisliği Programı, İstanbul Teknik\r\nÜniversitesi, İstanbul, Türkiye, 2016.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 5, "raw": "H.J. Hermens, B. Freriks, C. Disselhorst-Klug and G. Rau,\r\n“Development of recommendations for sEMG sensors and sensor\r\nplacement procedures”, J Electromyogr Kinesiol, vol.10(5), pp.361-\r\n74, 2000.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 6, "raw": "C. Tepe, “EMG işareti ile protez elin değişken hızla denetimi:\r\nDonanım, yazılım ve algoritmik yöntemler”, Doktora tezi, Fen\r\nBilimleri Enstitüsü, Elektrik-Elektonik Mühendisliği Anabilim Dalı,\r\nOndokuz Mayıs Üniversitesi, Samsun, Türkiye, 2014.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 7, "raw": "O. Erkaymaz, İ. Şenyer, and R. Uzun, “Yüzey EMG sinyallerinden\r\ndiz anormalliğinin yapay sinir ağları ile tespiti”, IEEE 25. Sinyal\r\nİşleme ve İletişim Uygulamaları Kurultayı, Malatya, 2017, p.16-19.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 8, "raw": "M.J. Aminof, Clinical electromyography. In: Electrodiagnosis in\r\nClinical Neurology, New York, USA: Churchill Livingstone, 1992.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 9, "raw": "K. Biçen, “EMG (Elektromiyografi) kontrollü protez kol tasarımı,”\r\nYüksek lisans tezi, Fen Bilimleri Enstitüsü, Mekatronik Mühendisliği\r\nAnabilim Dalı, Dokuz Eylül Üniversitesi, İzmir, Türkiye, 2011.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 10, "raw": "L. Cai, Z. Wang, and H. Zhang, “An EMG classification method\r\nbased on wavelet transform,” Proceedings of the First Joint\r\nBMES/EMBS Conference, 1999.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 11, "raw": "F. Hardalaç and M. Poyraz, “Classification of EMG signals using\r\nartificial neural network and diagnosis of neuropathy neuromuscular\r\ndisease,” Journal of Polytechic, vol. 5, pp. 75-81, 2002.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 12, "raw": "N.F. Güler and S. Koçer, “Classification of EMG signals using PCA\r\nand FFT,” Journal of Medical Systems, vol. 29(3), pp. 241-50, 2005.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 13, "raw": "A. Subasi, M. Yilmaz, and H.R. Ozcalik. “Classification of EMG\r\nsignals using wavelet neural network,” Journal of Neuroscience\r\nMethods. Vol. 156, pp. 360-367, 2006.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 14, "raw": "M.F. Lucas, A. Gaufriau, S. Pascual, S. Doncarli, and D. Farina,\r\n“Multi-channel surface EMG classification using support vector\r\nmachines and signal-based wavelet optimization,” Biomedical Signal\r\nProcessing and Control, vol. 3(2), pp. 169-174, 2008.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 15, "raw": "S. Koçer, “Classification of EMG signals using neuro-fuzzy system\r\nand diagnosis of neuromuscular diseases,” Journal of Medical\r\nSystems, vol. 34(3), pp. 321–329, 2010.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 16, "raw": "G. Akgün, M. Demetgül ve E. Kaplanoğlu, “EMG sinyallerinin\r\nöznitelik çakarımı ve geri yayılımlı yapay sinir ağı algoritması ile\r\nsınıflandırılması,” Otomatik Kontrol Ulusal Toplantısı, Malatya,\r\n2013.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 17, "raw": "R. Uzun, O. Erkaymaz, İ. Senyer Yapici, “Comparison of artificial\r\nneural network and regression models to diagnose of knee disorder in\r\ndifferent postures using surface electromyography,” Gazi University\r\nJournal of Science, vol. 31(1), pp. 100-110, 2018.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 18, "raw": "B. Taşar, A.K. Tanyıldızı, O. Yakut ve A. Gülten, “EMG\r\nsinyallerinin anlamlandırılması için radyal fonksiyonlu yapay sinir ağı\r\ntasarımı,” Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi,\r\nvol. 10(1), pp. 153-159, 2018.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 19, "raw": "Y. Koçyiğit ve M. Korürek, “EMG işaretlerini dalgacık dönüşümü ve\r\nbulanık mantık sınıflayıcı kullanarak sınıflama,” İstanbul Teknik\r\nÜniversitesi Dergisi, vol. 4(3), pp. 25-31, 2005.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 20, "raw": "G. Özmen, Y. Özbay ve A.H. Ekmekçi, “EMG sinyallerinde kas\r\nyorgunluğunun YSA ile sınıflandırılması,” Tıp Teknolojileri Ulusal\r\nKongresi, Nevşehir, 25 – 27 Eylül 2014, p.279- 282.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 21, "raw": "A. Dobrowolski, M. Wierzbowski, and K. Tomczykiewicz,\r\n“Multiresolution MUAPs decomposition and DVM-based analysis in\r\nthe classification of neuromuscular disorders,” Comput Methods Prog\r\nBiomed, vol. 107(3), pp. 393-403, 2012.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 22, "raw": "Y. Kutlu, Y. Isler, D. Kuntalp ve M. Kuntalp, “Çok katmanlı ağ\r\nyapıları kullanılarak diken dalgaların algılanması,” IEEE 14. Sinyal\r\nİşleme ve İletişim Uygulamaları Kurultayı, Antalya, 17-19 Nisan\r\n2006, p. 95.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null }, { "order": 23, "raw": "R.O. Duda, P.E. Hart, and D.G. Stork, Pattern classification. 2nd Ed.\r\nNew York: John Wiley and Sons, 2001.", "doi": null, "title": null, "authors": null, "source": null, "year": null, "volume": null, "pages": null } ], "statements": { "acknowledgements": null, "conflict_of_interest": null, "data_availability": null, "ai_disclosure": null }, "credit": [], "history": { "published": "2019-12-22" } }