 So we have this flask application using flask numpy scipy skfuzzy is the fuzzy logic toolbox for python. I'm still not sure how well this works. There was something similar for javascript as well, but it wasn't updated in the last like six, seven years or something. So let's run this one quickly. Right, so we have this game. If you haven't tried it out already, please go try it out. It's scrolling ECG on the screen and you have to click on the normal waveforms over there. I'll explain that in a sec. It actually should appear in here, but it doesn't for some reason. So it's the kind of stuff we have to resolve. All right, it's technical boring stuff. It still has to be done. Anyway, so hopefully you know how to play this game already. Let me know if I need to go over this again. And currently we're trying to create a bot that will play this game for us. And then I mean, you could compete with the bot or something, something like that. We're using it with fuzzy logic. By the way, is the bot still going? Yep. Sure thing. Let's get started with GitHub co-pilot for your biomedical engineering project. If you've been using fast API alongside SK5Z logic toolbox for Python, that's a good choice. As for JavaScript tools, it's essential to stay up to date for compatibility. Short responses are great. Don't mind you trying to be funny. I mean, not funny, just smart, casual, funny, not like ha ha ha funny. You know what I mean? And now, yeah, so we are having a few issues with the tool will be trying. Did you want to generate the code or should I get GitHub co-pilot to do it? We're having some things not displaying onto the front panel HTML. Got it. I'll keep it smart casual. If you want to generate code, GitHub co-pilot can certainly help. But feel free to let me know where you need assistance and we can tackle the issues with your front end HTML or any other problems you're facing in your project. Just point me in the right direction and we'll work on it together. Okay, so let's let's actually do both a workspace. And what was the problem? So the problem was the output of the fuzzy logic algorithm is not displayed on the front panel HTML page, even though we have all the components for it. Yeah, talking to two boards, it's a bit hard to try to figure out how co-pilot is actually deciding what code to look at. It's positive when you put this workspace, it will look at all the files or not. Yeah, I'm still testing that bit. Right, so we have the fuzzy logic analysis, our returning results, we must do, yeah, returning result, a front end, there's no link, you can just click on like the blue one there. It's a bit annoying, but this will be game logic in Ajax request. Do we have anything Ajax? No, why not? I'm sure you're making Ajax call to the server to get the result, fuzzy logic algorithm, and then displaying it on the HTML page. Okay, why aren't we doing this already? Let's show we have a fuzzy logic analysis, no, we do not. Okay, this is not, I have a patch request to only get, get done by, you know, that's not it. So I suspect it's giving me something generic. So based on the previous response, how to update this code, I do not currently have an Ajax request, but I do have some get from HTML. Yeah, we're using fetch API. That's right in the display. Now, why those are not clickable. It's pretty annoying. This should be clickable function. Okay, we're getting the element by D and that should be okay. Check the IDs. Those IDs do not match. Do we always need that workspace? Can we show, can we make sure the IDs match in JavaScript to what we have in this HTML? It should have been obvious, but it's not actually looking at the code. Your HTML JavaScript, you have row frequency, normalize frequency, row peaks. We do want to display essentially all the output of the fuzzy logic algorithm. So we know how the decision is made. Can you change? And so if you put this workspace, it's determining what the structure deciding which information to collect supposedly from all the files, but then seem to be either hallucinating or I just don't understand how it works. This play all the output fuzzy logic algorithm you need to ensure the server sends blah, blah. So unless it's a clickable link that doesn't actually work out, click on that fly, right, have to wait for it to finish. Okay, so invite sure that the analysis data function. This is the wrong analysis data, all the output. It's like, this is all wrong. Is it actually looking at the code or what is it doing? So we have analysis data is currently not the function. We have it mentioned six times just a variable. This is wrong. We have process data, spawns data return. While we're returning it as JSON, not convinced it's actually looking at the whole code. I was still timed out from GPT-4, are we? Yes, until another 20 minutes. Yeah, 20 minutes. See if GPT-3.5 can write code. I need to probe that context for this thing. And obviously the GitHub co-pilot wasn't works with a function. Can you explain the structure of the whole project? Okay, we have the waveforms, J, let's see if it's able to resolve basic stuff, generate, contains, code, okay. We have the Python static, we have game logic, waveforms, templates, index HTML, test by which we're not currently using. The problem was, so we're trying to display the feature values for frequency peaks amplitude and the abnormality likelihood. Essentially, what we have in here is this meant to be displayed on the front panel. Okay, GPT-3.5, the same question. Copies as the meant to be displayed on the front panel, process data object contains the raw, normally the frequency peaks, blah, blah, blah. Normal developers present the output of the fuzzy logic. That's, yes, that's correct. You can display this data in your HTML using JavaScript. Yep. Why aren't these clickable stuff in display results? I need an example. I need you to tell me how to do it. If I ask to copilot peaks, you end up getting based on the shit discussion. What nerve is it doing showing in there? Well, at least this is a bad list of showing the actual output of the fuzzy logic. The amplitude is not changing. It should be one of those, or maybe this one has this high amplitude, there is one waveform, pre-recorded waveform that has a, not pre-recorded, it's a simulated, so it's all synthetic data. But one of them is different, not this one. Yeah, the peaks should not be normalized. The amplitude is changing, but yeah, get abnormality and defined. Yeah, we really had some prompts for this thing to improve. Okay, the peaks should not be normalized, the peaks. Okay, again, the peaks should not be normalized. I don't want just to not show them, but I also don't want the fuzzy logic algorithm to use the normalized peaks. But suggesting me just to hide them, but obviously that won't do it based on symbols. So it's still generating, why can't I click on it? Save that. No, it's not generating, it should be able to click on those, I don't know, it's not working. So fuzzy logic algorithm is in a normalized positive peaks, the normalized function, process data, analyze waveform, fuzzy logic analysis, this one. How is it getting it wrong? There is no function called the fuzzy logic algorithm, there is a function called fuzzy logic analysis. So it's this, we'll make sure this is actually using the not normalized peaks because we don't need to normalize them. Process data. Yeah, this one is taking the normalized stuff. So positive peaks, negative peaks, it should be a raw, wait a second, so it's taking the whole positive peaks and it has a subcomponent of raw and normalized. So the question is, when we do the fuzzy logic analysis, since the API for the fuzzy logic analysis, okay, I'm confused by this one. How do we make sure that for the fuzzy logic analysis, we use the raw, negative and positive peaks, not the normalized version? No, no, no, no, it's not good. Yeah, it's not good. The frequency is wrong as well. The frequency would not work anyway, would it? Yes, no, so if we're looking at amplitude, we're looking at a number of negative and positive peaks, we should be looking at the distances between the different ECG components, the PQRST waves, and those should be within a certain range. Currently we have abnormality undefined. And what that is, we have an abnormality value, that's what should be displayed. Okay, if we select workspace and the error, it should look at all the files in theory. So it's used six references. Pretty sure we have abnormality defined, okay, I think it's a case sensitivity. It might be a case sensitivity issue. No, that one is okay, it's just a text in the printout, then everywhere else. That should be fine. Okay, let's go html again, the id in the game logic, that line there. Okay, that's a good idea. Here's the return of this thing, fuzzy logic analysis. It's called result, just change it like this. Right, this is better, and that's working, should be 0.83. What? It's super weird. Okay, can I get read of that, just play it all the time. Anyway, hopefully, so this tool is already on the website. You can go check it out. It's in the ECG game. You can play this game yourself. There's a video of me getting up to 1000 points. You can see if you can beat that or reach that or do any better. It becomes, it starts going faster and faster. I think every 50 points it will increase the speed. And hopefully, sometime soon, we'll have another tool that will show how a machine learning algorithm and explainable AI in the form of fuzzy logic will be playing this game. So you could compete with a bot labelling ECG data. And I'll see you next time. Bye.