Online Machine Learning Experiments in HTML5

This work in progress paper describes software that enables online machine learning experiments in an undergraduate DSP course. This software operates in HTML5 and embeds several digital signal processing functions. The software can process natural signals such as speech and can extract various features, for machine learning applications. For example in the case of speech processing, LPC coefficients and formant frequencies can be computed. In this paper, we present speech processing, feature extraction and clustering of features using the K-means machine learning algorithm. The primary objective is to provide a machine learning experience to undergraduate students. The functions and simulations described provide a user-friendly visualization of phoneme recognition tasks. These tasks make use of the Levinson-Durbin linear prediction and the K-means machine learning algorithms. The exercise was assigned as a class project in our undergraduate DSP class. The description of the exercise along with assessment results is described.

[1]  Karthikeyan Natesan Ramamurthy,et al.  Undergraduate Signal Processing Laboratories for the Android Operating System , 2015, ArXiv.

[2]  Zohar Dvir.  Web-Based Remote Digital Signal Processing (DSP) Laboratory Using The Integrated Learning Methodology (ILM) , 2006, ITRE.

[3]  Alfred O. Hero,et al.  Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure , 2014, IEEE Transactions on Signal Processing.

[4]  Douglas D. O'Shaughnessy,et al.  Speech Processing , 2018 .

[5]  Andreas Spanias,et al.  Speech coding: a tutorial review , 1994, Proc. IEEE.

[6]  Lijuan Liu,et al.  The Design and Implementation of Digital Signal Processing Virtual Lab Based on Components , 2005, ICWL.

[7]  A. Spanias,et al.  Perceptual coding of digital audio , 2000, Proceedings of the IEEE.

[8]  Gustavo Ribeiro Alves,et al.  An Integrated Reusable Remote Laboratory to Complement Electronics Teaching , 2010, IEEE Transactions on Learning Technologies.

[9]  Andreas Spanias,et al.  On-line simulation modules for teaching speech and audio compression techniques , 2003, 33rd Annual Frontiers in Education, 2003. FIE 2003..

[10]  Andreas Spanias,et al.  A Java-DSP interface for analysis of the MP3 algorithm , 2011, 2011 Digital Signal Processing and Signal Processing Education Meeting (DSP/SPE).

[11]  Richard G. Baraniuk,et al.  MOOC Adventures in Signal Processing: Bringing DSP to the era of massive open online courses , 2016, IEEE Signal Processing Magazine.

[12]  Andreas Spanias,et al.  A brief survey of machine learning methods and their sensor and IoT applications , 2017, 2017 8th International Conference on Information, Intelligence, Systems & Applications (IISA).

[13]  R. Zwitserloot,et al.  Active Learning of Introductory Machine Learning , 2006, Proceedings. Frontiers in Education. 36th Annual Conference.

[14]  Karthikeyan Natesan Ramamurthy,et al.  Teaching Earth Signals Analysis Using the Java-DSP Earth Systems Edition: Modern and Past Climate Change , 2014 .

[15]  Cameron H. G. Wright,et al.  A systematic model for teaching DSP , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  Andreas Spanias,et al.  Interactive online undergraduate laboratories using J-DSP , 2005, IEEE Transactions on Education.

[17]  Z. Markov,et al.  Enhancing undergraduate AI courses through machine learning projects , 2005, Proceedings Frontiers in Education 35th Annual Conference.

[18]  Andreas Spanias,et al.  Development of signal processing online labs using HTML5 and mobile platforms , 2017, 2017 IEEE Frontiers in Education Conference (FIE).

[19]  Cameron H. G. Wright,et al.  Signal processing concepts help teach optical engineering , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[20]  Garvit Juniwal,et al.  CPSGrader: Synthesizing temporal logic testers for auto-grading an embedded systems laboratory , 2014, 2014 International Conference on Embedded Software (EMSOFT).

[21]  J. Makhoul,et al.  Linear prediction: A tutorial review , 1975, Proceedings of the IEEE.

[22]  Yosi Shibberu.  Introduction to Deep Learning: A First Course in Machine Learning , 2017 .

[23]  Athanasios Kalantzopoulos,et al.  Online Laboratory Sessions in System Design with DSPs using the R-DSP Lab , 2014, Int. J. Online Eng..

[24]  Andreas Spanias,et al.  A Stem Reu Site on the Integrated Design of Sensor Devices and Signal Processing Algorithms , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[25]  Andreas Spanias,et al.  Interactive DSP laboratories on mobile phones and tablets , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[26]  Shihong Huang,et al.  Work in progress: A machine learning approach for assessment and prediction of teamwork effectiveness in software engineering education , 2012, 2012 Frontiers in Education Conference Proceedings.