 okay now should be working let's try to check it independently in my phone as well right okay we are live to as per usual a tweet in as well yeah post that quickly yeah talk about this later i forgot to turn a webcam thing on do it right now yeah we're using this i don't know that's for video processing i know we had a different tool called something clone yeah digital twin of course and this avatar code that again gpt a made for us just to make sure it's using the correct camera webcam input just run it in here quickly right yeah it's using my nvidia as expected can close it here release the camera need to run it in a separate python things just so we can a you know use the id and everything and i noticed yeah when i don't have the lights on don't have the lights on the mouth is not yeah it's not very responsive to my face right also pop it in the obs down the bottom so you should see it somewhere somewhere on the screen then just turn on the light just so it works better yeah now when i open my mouth it's more i think it's a bit more respond yeah i need to look at the camera as well it's sick yeah i just adjusted my microphone so i can look a bit up towards the camera so it's yeah it's kind of working okay it's fine i was actually thinking putting a sam altman or someone in here i actually started started doing this yeah it was working with a base base avatar and now i can't use it because i'm using the camera using actually both cameras i don't know why it should be working okay it should have and recognition as well we need some thumbnails for future videos you can have one of those i can't it's not getting my mouth right but you get the gist okay so we can close that one right someone was actually asking about the bland altman plot so we can do a quick just warming up thing so we have this two chats one of them should have an example yeah there's an example there so he generated it in like two seconds in a python with the code and everything the code works obviously locally as well just great so i can reproduce the example and i can actually obviously use my own data for it as well so that's the code you can add more more data there you can run it locally yeah and it's creating this bland altman plot which is difference between two measurements versus average of two measurements so yes in this case when i have those extra extra ones there yes the average between 110 and 120 is 115 and the difference between the measurements is minus 10 so it's putting another dot over here so it's working as expected now i was thinking doing something more interesting with it well first of all is a potential bland almond plot in e g blah blah blah so yeah when we are particularly using comparing two different e g channels in the same recording so let me know what you think of that and we can turn it into another web application that will look something similar to to this e g noise removal except you will choose two channels and we'll show you the bland altman plot as a comparison between two channels but actually just relevant actually have a tool like that already which is actually using cross coherence function yes we can improve on this interface quite a bit and yeah this showing a coherence function it's a cross sorry for that cross correlation so it meant to be yeah coherence is cross correlation in frequency domain between two channels is lecture two channels yeah this interface is not great is it and it will show you the cross coherence between them it's actually the same does that we know if you had the chance to look at the website as well because i'm open for any feedback so yeah so we might later turn this into a web application a flask web application as well but for now let's stick to what we were doing last time and that's this spectrogram close that for now get back to it let's do a spectrogram there are no questions in the chat keep going right so this tool is just called spectrum and we were already to remember how many sessions worked on that spectrogram yeah over here and let's close everything else close all we had this info file just a description and some prompts from memory it was working kind of okay already let's run it so this is a flask application is indicated by this line here it's running locally it's not in production yet and that's what it looks like it still has the well not still i mean i might leave it there and the feature for wavelet noise removal this will this chart actually shows both right and that's what we were trying to do last time without much success is also changing what the e g spectrogram shows when you toggle this switch so this should we have a prompt for it here at the end we can't program i can't program anyone can please do let me know happy to collaborate for me to program anything i need to ever use a github core pilot which i had a mixed success with and i had a better success with gpt4 so start on our chat start popping stuff in so obviously we have the python code we have also this shell script css and index html so let's start from the x html and it has at the bottom confirm ring because it will generate anything else sometimes this gets ignored let's put some exclamation marks if that prompt let's see what it says to have this voice wave gpt voice control thing i haven't donated yet because has this mixed success using it right so it trades through the text then that's great maybe exclamation marks did help some of the times it just ignored me why this has a template this has a template don't like it it's kind of obvious that there's previous code there and yet don't like this one otherwise it looks okay so this one actually never being used can remove it right let's pop it in as again confirm reading the code and do not generate anything else exclamation mark and sometimes this button now disappears there you know the one that just scrolls with the thing yep read the code didn't generate much else that's great okay we also have this python code we definitely don't need that it's just for testing field field spectrum are not being used might use them later pop it in as well okay now in info have these two lines what did it say i've read through the flask python code you provided it's designed for a web application that visualizes eeg electroencephalography data the code includes routes for loading and processing eeg data applying wavelet denoising generating spectrograms and calculating metrics like signal to noise ratio s n r and mean squared error m s e what specific aspects would you like to discuss or need assistance with regarding this code yeah that's great so yeah we need assistance with this wavelet denoise on when the wavelet denoise is turned on the spectrogram should display the spectrum of the eeg signal after noise reduction this means the spectrogram will show the frequencies present in the signal after the noise components have been minimized or removed by the wavelet denoising process wavelet denoise off when the wavelet denoise is turned off the spectrogram should display the original unaltered spectrum of the eeg signal this will include all the frequencies present in the signal including the noise your description of how the wavelet denoise feature should affect the spectrogram in the eeg data visualization application is clear here's how it can be implemented in the existing flask python code modify the spectrogram underscore data route to account for wavelet denoise when wavelet denoising is enabled apply the apply underscore wavelet underscore denoising function to the eeg data before generating the spectrogram when wavelet denoising is disabled use the original eeg data for the spectrogram yeah okay let's see i haven't actually didn't listen should listen to what the pot says be obedient let's listen to it again spectrogram underscore data route to account for wavelet denoise when wavelet denoising is enabled apply the apply underscore wavelet underscore denoising function to the eeg data before generating the spectrogram when wavelet denoising is disabled use the original eeg data for the spectrogram right so spectrogram data is in our python script always go python spectrogram right we already have wavelet denoise there yeah we also want to take levels we have levels yes we did have levels that's for the levels up there yeah the changing you can tell the bloom the denoise thing essentially how detailed the denoising function is the wavelet transform is that's fine yeah we want to take those as well they're not yet being used that's okay start sample line window size key eeg data sample and sample channel if wavelet denoise with changing eeg data changing eeg data generate a spectrogram this line expected to be the same yeah we have some parameters that we later can make inputs as well so we can play around I think this one remains the same that's preparing response and then turning it into a chase and instead it looks let's actually end and instead of reading that let's the best way let's just test it okay we need to read that because it's not actually changing we save it's yeah because it's in debugging mode so any changes make should take effect immediately there's just not much change between noise denoise and to expect this to change just lightly but it doesn't yet to expect changes there let's read that ensure that the front end sends the wavelet denoise wavelet transform and levels parameters in a request to spectrogram underscore data update the spectrogram visualization based on the response yeah okay so we need to adjust the front end as well okay can you can you just do that for the front end adjustments to work with the wavelet denoising feature in your eeg data visualization application you need to modify the javascript that interacts with the flashback end here are the key steps to ensure the front end correctly sends requests and updates the spectrogram based on the wavelet denoise setting modify the javascript functions that send requests the spectrogram underscore data endpoint to include the wavelet denoise wavelet transform and levels parameters this is crucial for the back end to know whether to apply wavelet denoising and with which parameters okay in the function that fetches and displays the spectrogram include the logic to send the state of the wavelet denoising toggle and the selected wavelet transform and levels right so we're already doing that we need those constants yes it has a placeholder in there so it's not the full function you have to be careful that those things this line right so we're taking um wavelet denoise transform and levels into account as well so we can comment that one out the event listener there are more changes add event listeners to the wavelet denoise toggle and other related controls like wavelet type and level selectors to update the spectrogram whenever these settings are changed do we already have this line yes do i still need to do that okay why do i need another function i do i need another function add event listeners to the wavelet denoise toggle and other related controls like wavelet type and level selectors to update the spectrogram whenever these settings are changed do i have to add another function update spectrogram and what no no no do i need to add another function yep if you're asking whether you need to add another function in your javascript code for handling the wavelet denoise feature in the EEG data visualization application it depends on how your current code is structured and what functionality you want to achieve based on the previous discussion here's a quick assessment it's not that for a sec to edit this do i must have this function yeah because we're really doing this kind of thing in the context of your application the update spectrogram function is not strictly necessary but it does provide a clean and organized way to handle updates to the spectrogram does it this function serves as a centralized handler for various events that require the spectrogram to be updated here are a few points to consider yeah consistently easy debugging that's fine alternatively you could directly call fetch and display spectrogram within each event listener like this how many times do we do that i'm just trying to understand the structure of the code if your application is relatively simple and you don't anticipate the need for more complex update logic in the future directly calling fetch and display spectrogram in each event listener is a viable option where is the f edge and display edge and display spectrogram false scroller yes so that will be replaced would have it's a question if i'm if i keep this one yeah do i need to replace this wave a new function then i will assume so no what why no you don't need to replace all instances of fetch and display spectrogram channel start second window size with update spectrogram the function fetch and display spectrogram is specifically designed to fetch and display the spectrogram based on the provided parameters channel start second window size it's used in various parts of your script where these specific parameters are known and need to be passed directly the update spectrogram function on the other hand is more of a convenience function for event listeners it's designed to be called when there's a change in any of the controls that affect the spectrogram like the wavelet denoise toggle wavelet transform selector or level selector this function retrieves the current values of these controls along with the channel start second and window size and then calls fetch and display spectrogram with these values well right because i also need to be updated in here but then why not just take the original or denoise signal in raw eg and turn it into spectrogram that is plotted in double t does matter signal chart yeah there's like a weird logic to the whole to the whole thing my original it's because my original prompt is not great using the original or denoised signal from the raw eg signal chart to generate the spectrogram is indeed a viable and logical approach this method would ensure consistency between the displayed raw signal and its corresponding spectrogram here's why this approach can be beneficial and how it can be implemented consistency the spectrogram directly corresponds to the raw signal being displayed ensuring that any changes on noise reduction applied to the raw signal are accurately reflected in the spectrogram efficiency reduces the need to process the data twice for the raw signal and the spectrogram separately this can be more efficient especially for large datasets or complex wavelet transformations simplicity simplifies the data flow in your application you process the data once and use it for both the raw signal plot and the spectrogram making the system easier to maintain and debug yes i wasn't listening properly distracting messages using the original or denoised signal from the raw eg signal chart to generate the spectrogram is indeed a viable and logical approach this method would ensure consistency between the displayed raw signal and its corresponding spectrogram here's why this approach can be beneficial and how it can be implemented consistency the spectrogram directly corresponds to the raw signal being displayed ensuring that any changes on noise reduction applied to the raw signal are accurately reflected in the spectrogram efficiency reduces the need to process the data twice for the raw signal and the spectrogram separately this can be more efficient especially if a large datasets or complex wavelet transformations simplicity simplifies the data flow in your application you process the data once and use it for both the raw signal plot and the spectrogram making the system easier to maintain and debug okay we'll have to make quite a few changes just save what we got so far old style old school um what's called version control yeah i wouldn't be able to use a github co-pilot for this um let's do complicated so we need to do something with the back end the process is the eeg data both original and denoised and makes it available in a format suitable for both plotting the raw signal and generating the spectrogram someone is asking about the eeg signal generator there's a couple of those for synthetic eg yeah this one yeah it's pretty basic thing sorry for the ads yeah it's actually can be much improved we had a better version of it before moving to linux to a different server i'll see later how we can update this create a different version for it as well instead of the bar charts just create those overlay the spectrum a energy plot that will actually be overlaid you'll have the actual frequency in there instead of having those frequency bands you know the classical yes those are classical yeah depends who you talk to some people love those a delta theta alpha beta but yeah this is literally just changing the energy in each band very simple you can change the window size and obviously on different window size you will see more details in different bands because yeah because the yeah different frequencies so so having a smaller window size helps to see what's what we have another yeah we have the ecg signal generator as well and memory yeah we could do a better version of it we had some old yeah from the old tool the only thing that is left is videos of how it was working and it was slightly better so we can definitely improve this one as well and where is it the eg signal generator and writes just back to what we are so this is real eg if you were wondering this is recorded from the surface of the brain recorded from an implant can fetch the data from eg.org if you like think pretty sure anyone can do it can get the data just requires a simple login and yes they will have a viewer on the website as well but that's nothing as good as this one obviously I'm biased so don't listen to that so actually it's working now yeah there's just not much difference going on you can see it's slightly changing you can only see it with very small window size check that's actually working okay and yes some well it's definitely changing it's just the it just has a minute difference there maybe some other channels and yeah increasing the levels should well anyway the interface is working so that's a good sign keep me sick someone's asking if the tools or the couple of questions there's still questions can improve it straight away you can show you the source code right now eg gen silly ads so I'm gonna call the eg gen 2 yet this one the source code should be on this side as well actually no if you do try this before okay that didn't work there's actually should be like description to it and everything that I forgot to put in so what was the question can control the width of the oscillator there's no what are the we are okay yeah the bandwidth that's the width of the oscillator yes so that's controlling the bandwidth of within each band which will obviously increase the energy of it well not necessarily well anyway that's the source code for it is pretty straightforward actually need to improve on it quite a bit can also pop it into a chgpt it will explain the code to you when chgpt wrote it for me to begin with if you have the prompts which are really yeah those are the prompts so we can pop the code in here you can probably share and this chat as well yeah because we forgot the description on the page have to put it in the html and what was the question can you control the width of the oscillator and other features of the wave being generated on theory can control everything from what parameters yeah window side we have yeah we have window size up top we have the amplitude of each band and yes we have the bandwidth as well so it's kind of hard to see when it's actually changing it would have been easier to see if this chart was actual plots instead of bar charts like we had previously so we can actually do that that all the video of that stuff and find that should be still public a e g chain something yeah this one here we got a simple g g signal generator you can set it right so yeah this one is better we can quickly change this tool to have the same plot such as a matter of changing this plot from a bar chart into I think that looks like that we actually have it in another application don't we yeah we have it in here no it's removal yeah with e g spectrum yeah this one here it's the same because well this is real e e g and yeah this spectrum and you can also select if you want the whole whoops sorry for that annoying ads I was actually thinking putting all this on the on the now website domain that I have by only cloud.com that's currently doesn't have much and there you will have some sort of login thing so if say Alex is interested it could be a simple login and then you could see this the tools with no advertisement but anyway yes that so it's actually but the controls are the same you also have window size okay this one you can't control because it's already pre-recorded the e g a real e g the vasigia everything and the other one is yes so those controls are the same controls as you have here that they change the bandwidth of the thing so hopefully that answers the question that yes you can change the width I assume you mean bandwidth within each frequency band yeah just display it better over there so yes for example yeah if you had all those as zeros so say you only looking at alpha that's not zero why is f something there there is not not going completely zero so why okay this is weird yeah I think this is like an edge condition that should not be anyway so this one's changing the bandwidth within that specific what's that 8 to 12 hertz yeah if you're adding beta need to add some amplitude to it and this bandwidth okay there's something check the code there's something weird a random uniform yes this one generating components for your frequency band and explain this with chpd code snippet rather crucial part yeah of course it is yeah it's looking through the bands yep taking the amplitude for each band and yeah just random number generator yes not all random number generators created equal so you have to be careful with that but then it's also not a real data so it might as well and random frequency yes well right there is also noise on top of the whole thing so maybe that's what's making yeah noise will make things behave in a weird fashion but generally it should be working okay you can try sharing the link like this put it in the in the chat and I actually never try this before I don't know if you need the gpt4 I hope not or you do actually see it you can try in there yeah I can try it out see see if it works it should just literally make you see that's the source code the back end so the fighting code that actually does the calculation for different bands so hopefully that helps I was sure you can actually because this is published on the server and the server is accessible via this link so so somehow I assumed you can just get access to all these files on it but yeah have to double check anyway hopefully it will become a bit clearer as we because this is fresh in my mind so I can it's actually related as well if you're doing synthetic eg and you have the spectrogram you kind of can see what's going on in a more precise fashion what happened there right now this working in it like a page page refresh right so that that's the eg beats this 100 seconds of eg has a seizure in it so if you look at say 18 seconds or so you can scroll through it and it shows you the spectrum so yeah it will be good if you had the same option for when generating a synthetic eg when you change your bandwaves and things a spectrum could tell you in a much more detailed fashion what's going on with the signal but yeah the current tool needs lots of improvement that's why the website is called chaos anyway currently I'm just testing this one I'm gonna get it right and move on I want to publish this as well on the side so we might be doing this next time just take a short break and we'll continue from there do you know if there's any questions or anything I wish there was like yeah in previously I had like a play button so it could just keep scrolling through the file while I'm taking a break you have to be careful with auto scaling here as well yeah it's still a bit the flask application you provided is designed to visualize eg electroencephalography data it serves as a back end for a web-based tool that allows users to interactively view and analyze eg signals and the corresponding spectrograms here's a breakdown of its components and functionalities flask setup the the application is built using flask a lightweight wsgi web application framework in python the eg data is loaded from a text file i 004 underscore a 002 underscore d 001 underscore day seven dot txt into a pandas data frame it preprocesses the data such as by setting the time column based on the sampling frequency 400 hertz apply underscore wavelet underscore denoising this function applies wavelet denoising to the eg data it uses the pie wavelets library to perform the wavelet decomposition and reconstruction filtering out noise in the process two functions butter underscore band pass and butter underscore band pass underscore filter are defined to create an apply but with band pass filter this filter is used to isolate specific frequency bands in the eg signal index root renders the main html page index html data fetching root get underscore data handles requests for eg data it processes the eg signal based on the provided parameters like window size channel the trending wavelet denoising etc and returns the process data for visualization spectrogram data root spectrogram underscore data provides the spectrogram data of the eg signal for a given channel and time window it supports wavelet denoising and returns frequency time and spectrogram intensity data eg data is processed according to user inputs like channel selection window size the trend toggle wavelet denoising etc spectral analysis is performed using fast Fourier transform fft for the spectrogram calculate signal to noise ratio snr and mean squared error mse for the process signals interactive data visualization the app allows users to interactively view eg data users can choose different channels set the window size toggle the trending and apply wavelet denoising spectrogram visualization it provides a spectrogram view of the eg data allowing users to analyze the frequency components of the signal over time dynamic data processing the back end dynamically processes the eg data based on user inputs ensuring that the visualizations are updated in real time signal analysis tools the inclusion of snr and mse calculations provides users with quantitative tools to analyze the eg signal quality yeah you get the picture hello vladislav arlov it's a nice name now it's taking a break just having something to eat yeah we can improve that previous tool quite a bit and i was just saying if for the what's called where is it the synthetic eg generator yeah this can be improved quite a bit and also if we have a spectrogram you can then see better what's going on when you change bandwidths or the different frequency components because currently yeah there's some noise introduced into into it so you can't actually tell what's what's going on but yeah we're currently focusing on this one i was just saying to be careful with numbers auto scaling like here because this file has a seizure in it eg with a seizure 16 channel eg you can select your channel i don't know what's happening with this one from memory channel 10 had a nice seizure in it a yes i do pay for gpt4 plus and it's totally worth it and i'm really skeptical i won't be selling you like cryptocurrency or anything like that like i don't normally fall into this but yeah seriously this thing worth way more than what they actually charge for it i would have paid the much more don't tell such cover that i said this because yes they will start charging more you know back to this and just saying those spectrogram plots have to be careful with the colors there the numbers the scale auto scaling because during seizure just refresh the page will go to default 10 second default so you have those 1500 that's what's going on during baseline and then when you have the seizure so this is the epicenter of the seizure you see this number going up to a 4000 5000 so yeah just have to be careful with this kind of auto scaling stuff so you can differentiate between baseline eg and something else like seizure in this case and check the side put this back into here yeah so we'll have a eg annotation so this annotation that used to work in levio doesn't work anymore have to redo it in python and i don't know python that's what gpt4 is doing for me and i'm also paying for github copilot i'm not able to get much done with it i think because it's again geared for developers so i haven't figured out how to maximize usage with github copilot yes you need something minor changed i guess it's good for that but for something major gpt4 is good because it's actually holding context for well in this case four different files so about the don't remember what do we have about 50 lines of no already what 200 lines of html how come ah because it has the description and the description is wrong by the way so we need to replace this because this was from a different flask application so essentially we have about 150 lines of html another 150 of javascript another 200 lines for python code close this one some css which we haven't loaded yet and seem to be able to hold everything in memory and because it does have context for the whole thing one thing though in the recent update this button have just disappeared the one that makes the windows sync with the more recent output it's not there i don't know why anyhow so that that's the description for the flask a jungle no this is flask uh i don't know if i'm using no don't use i haven't used jungle before but this is a flask it's uh doing is this one doing a fetch uh i don't remember i had one application using a jj query which is like yeah i know it's i can hold stuff this one actually doesn't one it's all json json files so using the json fi a flask that's how it's communicating with the front end if that what the question is so no jungle no jungle mango no trying to kind of minimize the number of um because you always have someone saying oh you must use this new grade two what happened to my something happened to my face the camera timed out what what could possibly time out start again know something the camera being held up by something yeah the camera right being held up it must be be obs that's annoying that's good my cpu usage went down came quite there as well the gpu is not going crazy just turn on the regular i think i know what happened that sound is not right yep the microphone better finish this stream but i'll just try fix this quickly i don't know what happened yeah now it's the right the microphone sometimes need to actually go obs okay right and now the camera is not being used so we can actually i should have just go regular camera well actually working yeah having trouble with my usb devices yep not much success anyway the avatar no the avatar is also not working now i had a lot of success with flask it's being really good to me um so this web application should soon go on to the site to replace this thing here just to have more details in the spectrum i don't know what happened so probably ready to deploy to publish this can we do it do we have time yes can do it probably straight away here so let's send this spectrogram in the index html send it up top it's called spectrogram yes well we can check all the other tools that should be available on this slide apologies for the ads in advance trying to recoup some electricity costs the server is quite the power power hungry little thing in live server right so that's now at the top this is actually showing the files well because it's once you turn it into flask application it should show this a couple things that we need to check first need all that stuff that's to do with checking if we i'm calling the application from production or locally so we have that and just make sure actually using it everywhere and point base should have two of those now well because we have two URLs this thing we have two functions bunch of event listness a wavelength noise right so we have yeah the rest of the code common can go now there's something wrong JavaScript so we have this API a URL with parameters so how many of those fetch right we have the fetch API URL and this is the one once Jason right and this we have another now this one called spectrum data wait what happened to the flask application now we had another window yeah so this will return the spectrum data but this also needs to check if we are in production or not yes we have get that can i'm a bit confused i have to get data in the back right so we need to actually check the back end don't we so we have the regular route what the whole thing we have get data we have tools to be three and we have another one spectrum data yes the one i was looking for so this spectrum data yes we should have another one of those would keep up copilot and sort us out no it would not production that okay it did actually do it but just add to the line with something and now where do we use this one a control i where to use currently it's not being used we can use this code the same way in the same file okay yeah yeah of course we use this in the same file yeah obvious really doesn't like my usb camera okay cancel that i still don't know to use this exactly this bitch you are real i can't minimize that right over here we need a control just fix fix this what's the issue the code well that it needs a to be changed to use spectrogram endpoint base change to use speck is it called again on tight okay let's check this too can't ah it's over here right so that's the old one a this is the new one looks legit so we'll accept a yeah we should have a file called my app wsgi this one here to change the name of the application yeah those are commented out but just change it anyway should be fine should have some prompts the instructions on how to and not here okay yeah we need to add another flask application to a config test as well so using g edit i'll just do it on the separate screen quickly right well i can show it to you it doesn't matter it's an open source project and so it's the flask uh no so that's the configuration of the of the website and we should have yeah we have 10 flask applications running we need to add a new one configuration what the last one instead of this feature extraction called spectrogram is need to change those with spectrogram so that's what this web app is called you can save that need to do a config test that syntax is okay syntax is okay what else do we need to do do we just deploy do we need to check anything else okay deploying in a live stream it's always a good idea isn't it so the website will go down for a bit it's normally takes a few like five seconds or so to get updated we restart their patches server as well fingers crossed so check the youtube analytics if anyone's interested happy to go over that as well okay so the site is back up okay this is the old one control f it's loading something right okay it's loaded stuff why so thanks forever and where's the main thing where's the spectrogram control five so now it's not a cgn problem it's actually loading and fine yeah there's some sort of weird delay thingy the main thing is where's the spectrogram that's not cool this is what it should have looked like packed we're getting the errors yes each spectrum failed to load resources server responded with four or four so is the yeah i don't know what's up my theory is it calling no it's calling the wrong yeah for the spectrogram data function it's calling the wrong thing problem is no what will it take to fix yes it will be in java script yeah this thing okay let's do you know just the brutal just bombard a gpt ppt put the whole java script which is confirmed yeah just do your thing let it loose the java script code you've provided is part of a web application that visualizes EEG data this script is executed once the DOM document object model is fully loaded as indicated by the DOM content loaded event listener it sets up interactive elements and data fetching mechanisms to render EEG signals and their spectrograms here's a breakdown of its key parts element references the script begins by obtaining references to various DOM elements like sliders file scroller window size input selectors channel selector wavelet transform levels toggles the trend toggle wavelet denoise display elements for snr and mse scenario wavelet denoise default setting the wavelet denoise checkbox is set to check by default indicating that wavelet denoising is enabled when the page loads endpoint URLs it defines URLs for fetching data differentiating between a production and a development environment endpoint base and spectrogram endpoint base initial execution finally the script performs an initial data fetch and render operation when the page loads it fetches and displays both the raw EEG signal and the initial spectrogram based on default or initial settings the error message you're encountering indicates a problem with the fetch and display spectrogram function in your java script file EEG JS specifically the URL being constructed for the GET request is including undefined values for start second and window size this issue typically arises when the function is called without properly retrieving or defining these values the fetch and display spectrogram function expects channel start second and window size as arguments if this function is called without these arguments or if the arguments are not correctly retrieved from their respective DOM elements undefined will be passed in their place the resulting URL constructed with undefined values leads to a 404 error because the server cannot find a root matching this incorrect query string ensure correct argument passing make sure that when fetch and display spectrogram is called it has passed the correct values for channel start second and window size check for undefined values before constructing the URL check if start second or window size are undefined if they are you should either provide default values or hold the function execution with an appropriate error message debugging log statements add console dot log statements before the URL is constructed in fetch and display spectrogram to log the values of channel start second and window size this can help you identify where the undefined values are coming from yes it is kind of obvious so i shouldn't have even used the gpt at all to solve this problem it's obviously a github copilot made a mistake well i'm copied i copied the thing from it will be able to fix it this is so this is the wrong wrong folder we'll be able to pick up i'm not sure if i understand anything at all kind of thing i changed this to be the current folder now i know i can do it manually of course but that's what we paying a bot for no it doesn't get it no this guy there yeah don't get it yeah this thing only called twice so we can just have to change it manually i mean that's okay just annoying that uh couldn't should be like a simple that should have just sorted out itself right now it's redeploying test so it's still running locally okay yeah because we'll keep developing this thing so we do need it to to run the locally as well let's redeploy though let's forget doing control shift v into the terminal instead of just control v so the site should be going down yep site is down website is down oh no it's starting it should be restarting though so the front page the landing page started okay this one loading takes too long still loading something control f5 okay what's up where's the spectrum okay now we really have lots of errors let's just refresh one so we get a one of those it's still going to okay this one i think and it's too we need to go cloud flare and put it in development mode obviously when we making these changes they might be not taken into account development mode again and yeah let's fix the problem that was the cdn the cdn can one of this log is taking the entire screen is a mystery because that was not the case in on the local server should be just tiny thing over there yeah we later will be adding more controls there anyway otherwise it's working yeah this is up and running you can check it out yourself let me know what you think just happened there like a jumpy business yeah i have to keep testing but yeah this file has a seizure in it yeah there's some sort of weird delays that don't not get on this on when running locally it's much smoother scrolling everything but yeah the server might be overloaded with me live streaming so i might finish that finish the live stream hopefully that tool will be more responsive for you and we'll go from there don't forget to subscribe like comment requests complaints and check the sites provide your feedback and i'll see you next time bye