tag:blogger.com,1999:blog-3326773214329183284.comments2024-03-26T01:13:52.297-04:00Ham Radio Blog by AG1LEag1lehttp://www.blogger.com/profile/16415319751367496314noreply@blogger.comBlogger214125tag:blogger.com,1999:blog-3326773214329183284.post-64675083136616161442023-02-13T23:46:43.386-05:002023-02-13T23:46:43.386-05:00Hi JeffH - it is PowerSDR (I had Flex-3000 rig at ...Hi JeffH - it is PowerSDR (I had Flex-3000 rig at the time). See https://ke9ns.com/flexpage.htmlag1lehttps://www.blogger.com/profile/16415319751367496314noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-27767674103061190692023-02-12T22:00:48.120-05:002023-02-12T22:00:48.120-05:00Hi! I know this article is several years old... ...Hi! I know this article is several years old... I was curious about the screenshot you have for "Figure 1". What application is providing the waterfall display along the bottom third of the page? I see two waterfalls - the one that's built into fldigi, but I do not recognize the other one. Is it from an SDR application or a fldigi plugin? Thanks!JeffH - W4JEWhttps://www.blogger.com/profile/03296229027221455446noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-35857961868751961722022-03-14T21:34:08.349-04:002022-03-14T21:34:08.349-04:00This is very interesting work. Could it be trained...This is very interesting work. Could it be trained to decode multiple channels of morse code being sent in parallel at different starting intervals, frequencies and rates? Kidz Viewzhttps://www.blogger.com/profile/00469008066455748047noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-63020749935595098492021-12-04T14:24:10.327-05:002021-12-04T14:24:10.327-05:00Mauri, you're right, making fldigi is an aweso...Mauri, you're right, making fldigi is an awesome effort, and I'm aware of needed knowledge just for this cw decoder. Your new approach, using machine learning, seems promising, and it's very cool you don't call it "artificial intelligence" as this kind of methods is so often called ;-)<br /><br />Unfortunately, I realize that I'm very far from being able to provide any help for this dev.<br /><br />I will comment on your post about amchine learning...<br /><br />tnxf1rumhttps://f1rum.frnoreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-86368778211948912442021-12-04T14:02:31.383-05:002021-12-04T14:02:31.383-05:00Hi, I don't know if it could help, but maybe y...Hi, I don't know if it could help, but maybe you could have an overlapping frame : if your frame is during 8 seconds, you could start the next 2 seconds before the end of the previous and decode the overlapping part twice. This way you may be certain that a character not ended in the first frame will be found in the next. To avoid duplicate characters, you could store an absolute starting time, if you get 2 characters starting at the time (and frequency, of course), you keep only the longer one.<br />f1rumhttps://f1rum.frnoreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-18922549382092754262021-12-03T11:06:51.240-05:002021-12-03T11:06:51.240-05:00Hi Jean-Pierre, the morse decoder in FLDIGI requir...Hi Jean-Pierre, the morse decoder in FLDIGI requires manual tuning of parameters to work better. I did work on a few features like matched filter and SOM decoding to improve the accuracy that were accepted to FLDIGI CW decoder. <br /><br />However, the Bayesian decoder had quite a lot of new code and I got it to alpha level with a few testers helping to find issues. We never got the code to be accurate enough for real world signals, so eventually I abandoned this approach and started looking alternatives, such as experimenting with Machine Learning algorithms to train a model with a lot of noisy CW. <br /><br />You can check this http://ag1le.blogspot.com/2020/04/new-real-time-deep-learning-morse.html where I did document one such experiment. If I would have more time available, this might be the way forward but integrating to FLDIGI would be quite a lot of work. <br /><br />Dave W1HKL has done a monumental work pulling FLDIGI together, and there are some really talented people who have contributed their skills to create FLDIGI open source software. My hat off the the FLDIGI team who have spent so much of their time to give this package for free to the ham community. <br /><br />What comes to CW Skimmer and Android Morse Expert, Alex VE3NEA has the "secret sauce" that he has spent many years to make perfect. They are the golden standard at the moment what comes to accuracy, for sure. Even if Alex would provide his algorithms as an open source it would be still a lot of work to integrate those to FLDIGI and make it seamless CW decoder experience for the users. <br /><br />I hope this gives you the perspective and some ideas how to help. If you really want to build a better CW decoder for FLDIGI you need to invest a lot of time and energy to make it happen. I spent probably hundreds of hours reading research papers, learning digital signal processing, bayesian probability and related math, read multiple Ph.D. thesis written by very smart people, and re-learned how to write C and C++ code again. <br /><br />For me the learning is the journey, and this blog is an attempt to document some of my experiments along the way. <br /><br />73 <br />Mauri AG1LE ag1lehttps://www.blogger.com/profile/16415319751367496314noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-731668737712535382021-12-03T09:13:17.061-05:002021-12-03T09:13:17.061-05:00Thanks Mauri,
I understand, however, actual morse...Thanks Mauri,<br /><br />I understand, however, actual morse decoder in fldigi is not efficient at all. Android Morse Expert (and certainly CW Skimmer that I can't install on my Linux machine) is really awesome compare to fldigi.<br /><br />Is there a mean to help you to try to improve fldigi cw decoder ? fldigi is certainly the best ham software I use, and thanks again for the good work with Dave W1HKJ.<br />f1rumhttps://f1rum.frnoreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-46531286535634975092021-12-03T03:49:37.772-05:002021-12-03T03:49:37.772-05:00No, Bayesian method was not included in the last v...No, Bayesian method was not included in the last versions of FLDigi. I didn't get the performance to a satisfactory level. ag1lehttps://www.blogger.com/profile/16415319751367496314noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-18101395072204149442021-12-03T03:35:43.142-05:002021-12-03T03:35:43.142-05:00Hi Mauri,
I don't understand if your devs abo...Hi Mauri,<br /><br />I don't understand if your devs about bayesian method morse decoder are included in last versions of fldigi ?<br /><br />Could you tell me ?<br /><br />Jean-Pierre - F1RUM<br />f1rumhttps://f1rum.frnoreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-48989252699240700582021-07-06T18:24:31.694-04:002021-07-06T18:24:31.694-04:00Hi K5KHK - I haven't figured out all the techn...Hi K5KHK - I haven't figured out all the technical details how to do bidirectional audio using only web browser. With webRTC protocol it should be possible. This project was about two weekends worth of effort to pull together as a working solution. If anyone has some good open source repos, I would be happy to investigate feasibility of integrating webRTC to this setup.ag1lehttps://www.blogger.com/profile/16415319751367496314noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-50180661162036046562021-07-05T22:46:05.288-04:002021-07-05T22:46:05.288-04:00Are you planning on making the audio bidirectional...Are you planning on making the audio bidirectional for true remote operation? <br /><br />de K5KHK K5KHKhttps://www.blogger.com/profile/09491849383274535358noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-54724982702021999392021-07-05T11:19:35.638-04:002021-07-05T11:19:35.638-04:00Hi kt4wo - Thanks for reaching out - I sent you a...Hi kt4wo - Thanks for reaching out - I sent you an email. ag1lehttps://www.blogger.com/profile/16415319751367496314noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-17063158602102015752021-07-05T00:45:31.788-04:002021-07-05T00:45:31.788-04:00I have a IC-7100 and 7200 I could use to help test...I have a IC-7100 and 7200 I could use to help test.<br />As well as 1/2 dozen Pi's.<br />Trip - KT4WO<br />kt4wo67@gmail.comkt4wohttps://www.blogger.com/profile/04187236864304054122noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-26054801369567164872021-06-12T00:58:16.066-04:002021-06-12T00:58:16.066-04:00Thanks for your sincere reply. In addition to your...Thanks for your sincere reply. In addition to your solutions, I've also thought about learning a model that recognizes spaces between strings, but it's going to be too complicated.<br /> Speech recognition technologies are being commercialized these days, so there must be the simple solutions. I'll let you know after I find out.<br /><br />Thank youadhoc0909https://www.blogger.com/profile/14144856245663964915noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-87927877877259496372021-06-11T14:45:21.981-04:002021-06-11T14:45:21.981-04:00Hi Unknown
Thanks for your feedback. I have not ...Hi Unknown<br />Thanks for your feedback. I have not solved the problem of current image frame cutting Morse character in parts yet. I have tested a few possible solutions: (1) make the image frame much longer so that one frame can contain many Morse characters. This way the overall decoding error rate is lower, as the problem appears less frequently. (2) Have overlapping image frames and use text post processing to find overlapping decoded characters and eliminate mis-decoded characters in between the frames. These methods provide some improvements but don't eliminate the problem. <br /><br />Do you have some other / better ideas? ag1lehttps://www.blogger.com/profile/16415319751367496314noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-90554942919535823952021-06-11T06:43:03.136-04:002021-06-11T06:43:03.136-04:00Dear mauri,
First of all, thank you for your arti...Dear mauri,<br /><br />First of all, thank you for your article and I read it very interestingly.<br /><br />I have one question for you. One of the problems with the real-time decoder you mentioned in the text is the problem when the current image frame cuts the Morse character into parts. Have you solved this problem by any chance? Or have you tought about how to solve it?adhoc0909https://www.blogger.com/profile/14144856245663964915noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-83092050306267716072021-04-03T16:35:54.063-04:002021-04-03T16:35:54.063-04:00Will the SNR improve with the application of a lit...Will the SNR improve with the application of a little gravy?Anonymoushttps://www.blogger.com/profile/16880087578150041250noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-17696865796021211502021-04-01T21:39:44.210-04:002021-04-01T21:39:44.210-04:00I am very interested in the software. Your AI (Apr...I am very interested in the software. Your AI (April Ingenuity) software is so lifelike, it is uncanny. How many FFT-KFC buckets did you use?<br /><br />Have you sone any sonic modeling of the crunch of southern fried chicken?<br /><br />73,<br />Dan<br />W1CHIX<br /><br />dbhttps://www.blogger.com/profile/14864786294007969228noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-40512484122478248952021-04-01T09:46:35.271-04:002021-04-01T09:46:35.271-04:00I'm curious, how long have you *really* been w...I'm curious, how long have you *really* been working on this? This is the signal that I've been hearing in my head for *years*. Now that I know what it is, I'm going to try to decode it. It repeats over and over, and drives me *crazy*.Anonymoushttps://www.blogger.com/profile/01573176327496859993noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-83254847848836949262020-08-18T17:13:36.252-04:002020-08-18T17:13:36.252-04:00Hi Mauri,
If you decide to develop in C ++ (or s...Hi Mauri, <br /><br />If you decide to develop in C ++ (or something else that gives a binary under linux), I would be very interested to test it on our beacon server :)<br />Unfortunatly, the pyaudio library get the input sound card from asoundrc config... and it will difficult to use standard alsa désignation or plug as dsnoop...<br /><br />So we have actualy 6 receiver with 384khz bandwith (kernel and alsa mod for up to 256 soudncards and 384khz bandwith)... on 2220m 630m 160m 80m and 6m at the moment and plan to extend on other bands.<br />It's a long time i search some equivalent as cwskimmer under linux directly...it's really annoying to use wine ... and it use cpu time for nothing.<br />If it can run headless with an option to hide some screen it will be perfect!<br /><br />This is why I am very interested in your project! <br />73 Olivier F4HTB<br /><br />F4HTBhttps://www.blogger.com/profile/14724272337272687893noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-44227752457410931012020-08-03T16:18:53.639-04:002020-08-03T16:18:53.639-04:00I just saw your answer by chance ... I don't k...I just saw your answer by chance ... I don't know why I missed it.<br />Thank you for your work, I will review this and follow your work closely.<br />:) 73 F4HTBF4HTBhttps://www.blogger.com/profile/14724272337272687893noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-17982958485631947272020-06-30T10:42:58.095-04:002020-06-30T10:42:58.095-04:00This is an excellent example of ML application. CW...This is an excellent example of ML application. CW is fun and very useful in long distance HF. But Human beings capacity to learn CW varies person to person. Even lack of time is another factor. If it becomes possible that I can take my RPI running the ML software and ask it to listen to receiving audio to decode it then i think this is a breakthrough. This will revive the CW communication in amateur radio. Please continue your work on this. I will like to make such system for my own use. ASHOK DAShttps://www.blogger.com/profile/06114788607671010959noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-13686592316306926862020-06-05T08:14:26.782-04:002020-06-05T08:14:26.782-04:00Thanks this is a very interesting article!!!Thanks this is a very interesting article!!!Luca Biondihttps://www.blogger.com/profile/03009695404507420941noreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-84369178459881370982020-05-05T14:29:21.750-04:002020-05-05T14:29:21.750-04:00http://www.vk6fh.com/vk6fh/fractal.htm ... 73'...http://www.vk6fh.com/vk6fh/fractal.htm ... 73's from F5JTM also menelik34 - 14OA372Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-3326773214329183284.post-37065959190527344802020-05-05T14:26:04.384-04:002020-05-05T14:26:04.384-04:00https://www.facebook.com/groups/1042998442388744/ ...https://www.facebook.com/groups/1042998442388744/ by F5JTMAnonymousnoreply@blogger.com