Investigating effects of Levenshtein distance algorithm on accuracy performance in EEG based communication system

Abstract

In our study, we investigated the effects of the Levenshtein distance algorithm on the eye-blink communication system that we developed based on EEG signals for people with severe motor disabilities, such as Amyotrophic Lateral Sclerosis, stroke, and locked-in syndrome. The developed system analyzes eye-blink signals to extract information and vocalize it. EEG signals were obtained from an electrode above the left eye using a NeuroSky MindWave Mobile device. Morse-coded eye-blink words were input to the system and feature vectors were extracted using the Wavelet Transform method. Support vector machines were trained with these vectors and the Levenshtein distance algorithm was used to reduce classification errors. Finally, the system was completed with a text-to-speech synthesis algorithm. The experiments, which used 20 words for self-expression, obtained highly successful results.

Keywords

• EEG
• Brain-Computer interface
• Wavelet transform
• Support vector machine
• Levenshtein distance algorithm
• Eye-Blink detection

EEG tabanlı haberleşme sisteminde Levenshtein mesafe algoritmasının doğruluk performansına etkisinin incelenmesi

Öz

Çalışmamızda, amyotrofik lateral skleroz, felç ve kilitli kalma sendromu gibi motor engeli olan kişiler için, EEG sinyalleri kullanarak geliştirdiğimiz göz-kırpma iletişim sistemi üzerinde Levenshtein mesafe algoritmasının etkilerini araştırdık. Sistem, göz-kırpma sinyallerini analiz ederek bilgi çıkarmakta ve seslendirmektedir. EEG sinyalleri, kablosuz NeuroSky MindWave cihazı kullanılarak sol gözün üzerine yerleştirilmiş bir elektrottan elde edilmiştir. Göz-kırpmalarla oluşturulan Mors kodlu kelimeler sisteme giriş olarak verilmiş ve Dalgacık Dönüşümü kullanılarak öznitelik vektörleri çıkarılmıştır. Bu vektörlerle Destek Vektör Makineleri eğitilmiş ve sınıflandırma hatalarını azaltmak için Levenshtein mesafe algoritması kullanılmıştır. Son olarak, Metin-Konuşma sentezi algoritması ile sistem tamamlanmıştır. Kendini ifade etmek için 20 kelimenin kullanıldığı deneyler oldukça başarılı sonuçlar vermiştir.

Anahtar Kelimeler

• EEG
• Beyin-bilgisayar arayüzü
• Dalgacık dönüşümü
• Destek vektör makineleri
• Levenshtein mesafe algoritması
• göz-kırpma tespiti

Kaynakça

1. [1] Arthur KC, Calvo A, Price TR, Geiger JT, Chio A, Traynor BJ. “Projected increase in amyotrophic lateral sclerosis from 2015 to 2040”. Nature Communications, 7(1), 1-6, 2016.
2. [2] Soman S, Murthy BK. “Using brain computer interface for synthesized speech communication for the physically disabled”. Procedia Computer Science, 46, 292-298, 2015.
3. [3] García L, Ron-Angevin R, Loubière B, Renault L, Le Masson G, Lespinet-Najib V, André JM. “A comparison of a braincomputer interface and an eye tracker: Is there a more appropriate technology for controlling a virtual keyboard in an ALS patient?”. In Advances in Computational Intelligence: 14th International Work-Conference on Artificial Neural Networks, IWANN, Cadiz, Spain, 14-16 June 2017.
4. [4] de Lima Medeiros PA, da Silva GVS, dos Santos Fernandes FR, Sánchez-Gendriz I, Lins HWC, da Silva Barros DM, de Medeiros Valentim RA. “Efficient machine learning approach for volunteer eye-blink detection in real-time using webcam”. Expert Systems with Applications, 188, 116073, 2022.
5. [5] Królak A, Strumiłło P. “Eye-blink detection system for human–computer interaction”. Universal Access in the Information Society, 11, 409-419, 2012.
6. [6] Francis WC, Umayal C, Kanimozhi G. “Brain-computer interfacing for wheelchair control by detecting voluntary eye blinks”. Indonesian Journal of Electrical Engineering and Informatics (IJEEI), 9(2), 521-537, 2021.
7. [7] Ekim G, Atasoy A, İkizler N. “A new approach for eye-blink to speech conversion by dynamic time warping”. Traitement du Signal, 38(2), 369-377, 2021.
8. [8] Ekim G, İkizler N, Atasoy A. “A Study on eye-blink detection-based communication system by using knearest neighbors classifier”. AECE Advances in Electrical and Computer Engineering, 23(1), 71-78, 2023.

9. [9] Kaur A. “Wheelchair control for disabled patients using EMG/EOG based human ma-chine interface: A review”. Journal of Medical Engineering & Technology, 45(1), 61-74, 2021.
10. [10] Tamura H, Yan M, Sakurai K, Tanno K. “EOG-sEMG human interface for communication”. Computational Intelligence and Neuroscience, 2016(1), 7354082, 2016.
11. [11] Mukherjee K, Chatterjee D. “Augmentative and alternative communication device based on eye-blink detection and conversion to morse-code to aid paralyzed individuals”. In 2015 International Conference on Communication, Information & Computing Technology (ICCICT), Mumbai, India, 15-17 January 2015.
12. [12] Singh J, Miglani R, Goel C. “Encrypted morse communication using eye blinks and light bulb”. Proceedings of the International Conference on Innovative Computing & Communication (ICICC) (online), Vallodoid, Spain, 3 July 2021
13. [13] Chareonsuk W, Kanhaun S, Khawkam K, Wongsawang D. “Face and Eyes mouse for ALS Patients”. In 2016 Fifth ICT International Student Project Conference (ICT-ISPC), Nakhonpathom, Thailand, 27-28 May 2016.
14. [14] Rashid M, Sulaiman N, Mustafa M, Bari BS, Sadeque MG, Hasan MJ. “Wink based facial expression classification using machine learning approach”. SN Applied Sciences, 2, 1-9, 2020.
15. [15] Groll MD, Hablani S, Vojtech JM, Stepp CE. "cursor click modality in an accelerometer-based computer access device". IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(7), 1566-1572, 2020.
16. [16] Wang J, Xu S, Dai Y, Gao S. “An eye tracking and braincomputer interface based human-environment interactive system for amyotrophic lateral sclerosis patients”. IEEE Sensors Journal, 23(20), 24095-24106, 2022.
17. [17] Cipresso P, Meriggi P, Carelli L, Solca F, Meazzi D, Poletti B, Lulé D, Ludolph A, Riva G, Silani V. “The combined use of Brain Computer Interface and Eye-Tracking technology for cognitive assessment in Amyotrophic Lateral Sclerosis”. 5th International Conference on Pervasive Computing Technologies for Healthcare (Pervasive Health) and Workshops, Dublin, Ireland, 23-26 May 2011.
18. [18] Ma X, Yao Z, Wang Y, Pei W, Chen H. “Combining braincomputer interface and eye tracking for high-speed text entry in virtual reality”. In 23rd International Conference on Intelligent User Interfaces, Tokyo, Japan, 7-11 March 2018.
19. [19] Awais MA, Yusoff MZ, Yahya N, Ahmed SZ, Qamar MU. “Brain controlled wheelchair: A smart prototype”. In Journal of Physics: Conference Series, Volume 1529, The 2nd Joint International Conference on Emerging Computing Technology and Sports (JICETS), Bandung, Indonesia, 25-27 November 2019.
20. [20] Carron LP. Morse Code: The Essential Language, 2nd ed. Newington, USA, Amer Radio Relay League, 1996.
21. [21] Fisch, BJ. Fisch and Spehlmann’s EEG Primer: Basic Principles of Digital and Analog EEG. 3rd ed. New York, USA, Elsevier Science Publishing Company,1999.
22. [22] Subaşı A. “EEG signal classification using wavelet feature extraction and a mixture of expert model”. Expert Systems with Applications, 32(4), 1084-1093, 2007.
23. [23] Übeyli ED, Güler İ. “Feature extraction from Doppler ultrasound signals for automated diagnostic systems”. Computers in Biology and Medicine, 35(9), 735-764, 2005.
24. [24] Ekim G, İkizler N, Atasoy A. “The effects of different wavelet degrees on epileptic seizure detection from EEG signals”. In 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Gdynia, Poland, 3-5 July 2017.
25. [25] Chang CC, Lin CJ. “LIBSVM: A library for support vector machines”. ACM Transactions on Intelligent Systems and Technology (TIST), 2(3), 1-27, 2011.
26. [26] Ekim G, Atasoy A, İkizler N. “Statistical comparison of classification methods in EEG signals”. In 2017 25th Signal Processing and Communications Applications Conference (SIU), IEEE, Antalya, Turkey, 15-18 May 2017.
27. [27] Günay M, Alkan A. “Classifications of EMG signals by spectral methods and SVM classifier”. Kahramanmaras Sutcu Imam University Journal of Engineering Sciences, 13(2), 63-80, 2010.
28. [28] Tuncer SA, Alkan A. “Classifications of EMG signals taken from arm with hybrid CNN-SVM architecture”. Concurrency and Computation: Practice and Experience, 34(5), e6746, 2022.
29. [29] Meyer D, Wien FT. “Support vector machines”. The Interface to Libsvm in Package e1071, 28(20), 597, 2015.
30. [30] Levenshtein VI. “Binary codes capable of correcting deletions, insertions, and reversals”. In Soviet physics doklady, 10(8), 707-710, 1966.
31. [31] Heeringa WJ. Measuring Dialect Pronunciation Differences Using Levenshtein Distance. PhD Thesis, University of Groningen, Groningen, Holland, 2004.
32. [32] Farwell LA, Donchin E. “Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials”. Electroencephalography Neurophysiology and Clinical, 70(6), 510-523, 1998.
33. [33] Meinicke P, Kaper M, Hoppe F, Heumann M, Ritter H. “Improving transfer rates in brain computer interfacing: A case study”. In Advances in Neural Information Processing Systems, 15, 1131-1138, 2003.
34. [34] Kaper M, Ritter H. “Generalizing to new subjects in braincomputer interfacing”. The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Francisco, CA, USA, 1-5 September 2004.
35. [35] Amcalar A, Cetin M. “A Brain-Computer interface system for online spelling”. IEEE 18th Signal Processing and Communication Applications Congress, Diyarbakir, Turkey, 22-24 April 2010.
36. [36] Akram F, Seung Moo H, Tae-Seong K. "An efficient word typing P300-BCI system using a modified T9 interface and random forest classifier". Computers in Biology and Medicine, 56, 30-36, 2015.
37. [37] Oralhan Z. “The effect of interstitial time and stimulus structure on performance in P300 based brain computer interface systems”. Düzce University Journal of Science and Technology, 7(3), 1834-1846, 2019.
38. [38] Miniotas D, Spakov O, Evreinov GE. “Symbol creator: an alternative Eye-based text entry technique with low demand for screen space”. INTERAC, 3, 137-143, 2003.
39. [39] Majaranta P, Aula A, Raiha KJ. “Effects of feedback on eye typing with a short dwell time”. In Proceedings of the 2004 Symposium on Eye tracking Research & Applications, Texas, San Antonio, 22-24 March 2004.
40. [40] Usakli AB, Gurkan S. “Design of a novel efficient humancomputer interface: An electrooculogram based virtual keyboard”. IEEE Transactions on Instrumentation and Measurement, 59(8), 2099-2108, 2009.
41. [41] MacKenzie IS, Ashtiani B. “BlinkWrite: efficient text entry using eye blinks”. Universal Access in the Information Society, 10(1), 69-80, 2011.
42. [42] Zhang C, Yao R, Cai J.” Efficient eye typing with 9-direction gaze estimation”. Multimedia Tools, and Applications, 77(15), 19679-19696, 2018.
43. [43] Porta M, Turina M. “Eye-S: a full-screen input modality for pure eye-based communication”. In Proceedings of the 2008 Symposium on Eye Tracking Research & Applications, Georgia, Savannah, 26-28 March 2008.
44. [44] Tsai J, Lee C, Wu C, Wu J, Kao K. “A feasibility study of an eye-writing system based on electro-oculography”. Journal of Medical and Biological Engineering, 28(1), 39, 2008.
45. [45] Lee KR, Chang WD, Kim S, Im CH. “Real-time “eye-writing” recognition using electrooculogram”. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(1), 37-48, 2016.
46. [46] Fang F, Shinozaki T. “Electrooculography-based continuous eye-writing recognition system for efficient assistive communication systems”. PloS one, 13(2), e0192684, 2018.
47. [47] Ozbek Ulkutas H. Development of Computer-Based EyeWriting System by Using EOG. M.Sc. Thesis, Department of Biomedical Engineering, Başkent University, Ankara, Turkey, 2015.
48. [48] Soman S, Murthy BK. “Using brain computer interface for synthesized speech communication for the physically disabled”. Procedia Computer Science, 46, 292-298, 2015.
49. [49] Mukherjee K, Chatterjee D. “Augmentative and alternative communication device based on eye-blink detection and conversion to Morse-code to aid paralyzed individuals”. In 2015 International Conference on Communication, Information & Computing Technology (ICCICT), IEEE, Mumbai, India, 15-17 January 2015.
50. [50] İkizler N, Ekim G, Atasoy A. “A Novel Approach on Converting Eye Blink Signals in EEG to Speech with Cross Correlation Technique”. AECE Advances in Electrical & Computer Engineering, 23(2), 29-38, 2023.