Morse Code Learning Machine Catching on with Hams. Post #4483



Experimenter Mauri Niininen (AG1LE) of Lexington, Massachusetts, reports that  his Morse Learning Machine Challenge has been catching  on on among members of the Amateur Radio Community.  The goal of the competition is to build a machine that can learn how to decode audio files containing Morse code–a better “code trap,” if you will.  Niininen said his project has been approved by Kaggele, which bills itself as “the world’s largest community of data scientists.”  Niininen said that it takes humans many months of effort to learn Morse Code, and, after years of practice, the most proficient operators can decode Morse Code up to 60 or more words per minute.

Article excerpt:

Niininen says, “Humans have extraordinary ability to quickly adapt t varying conditions, speed and rhythm.  We want to find out if it is possible to create a machine leaning algorithm that exceeds human performance and adaptability in Morse decoding.”

The computer-generated Morse data for the competition includes various levels of added noise.  The signal-to-noise ratio, speed, and message content of the files vary randomly to simulate real-life ham radio HF Morse communication.

Niininen added that “I hope to attract people from the Kaggle community,who are interested in solving  new, difficult challenges using their predictive data modeling, computer science and machine learning expertise.”

During the competition, participants will build a learning system capable of decoding Morse Code, using development data consisting of 200 WAV audio files containing short sequences of randomized Morse.  Data labels are provided for a training set, so participants can self evaluate their systems.

Niininen stated, “To evaluate their progress and compare themselves with others, they can submit their prediction results online to get immediate feedback.”  Niininen has provided a sample Python Morse decoder to make it easier to get started.

Niininen said that within the first 24 hours of the competition, he had 33 downloads, noting that participation since 05 September 2014 “is growing by the hour, as the word about this challenge is spreading.



It’s good to see Morse Code gaining popularity through events such as this.  Our first digital mode really never went away when the FCC removed the Morse Code requirement for Amateur Radio Licenses.  I believe more people, including myself, are using Morse Code than ever before.  If you want some exotic DX these days, check out the lower 25 kHz of 80, 40, and 20 meters.  That’s one of the reasons I took the Extra Class exam (and passed it)–Morse Code is very much alive in those bottom segments of the amateur radio bands.  I think ole Samuel B. Morse would be proud of Mauri  Niininen,who has rekindled the spark of Morse Code among scientific professionals.

For the latest Amateur Radio news and events, please check out the blog sidebars.  These news feeds are updated daily.

You can follow our blog community with a free email subscription or by tapping into the blog RSS feed.

Until next time,

Russ Roberts (KH6JRM).

Site Administrator.

%d bloggers like this: