| 0:00:14 | a mind then these heroes you guys too |
|---|
| 0:00:16 | yeah and the whole |
|---|
| 0:00:18 | also uh i |
|---|
| 0:00:19 | to see something like that |
|---|
| 0:00:20 | yeah |
|---|
| 0:00:22 | we still go you best about a week right on the technology to file |
|---|
| 0:00:25 | my project |
|---|
| 0:00:26 | uh tied to the title my presentational |
|---|
| 0:00:30 | hayes class case um by waiting for specific case you component well but signal three commode a much |
|---|
| 0:00:37 | yeah |
|---|
| 0:00:38 | uh |
|---|
| 0:00:40 | the application a well what is that is the brain computer interface |
|---|
| 0:00:44 | uh |
|---|
| 0:00:44 | oh what is that it to reconstruct |
|---|
| 0:00:46 | ding |
|---|
| 0:00:47 | extract the future it's also sit rank condition |
|---|
| 0:00:51 | wrong brain signals |
|---|
| 0:00:53 | to exploit the bci |
|---|
| 0:00:55 | as sort of features correspond to break conditional |
|---|
| 0:00:58 | uh |
|---|
| 0:00:59 | such as |
|---|
| 0:01:00 | uh as as bp |
|---|
| 0:01:02 | uh are four where |
|---|
| 0:01:04 | and can be observed by observational system |
|---|
| 0:01:07 | such as the G |
|---|
| 0:01:09 | and fmri |
|---|
| 0:01:11 | a piece yeah it's kept yeah such speech at and uh saying that the base command |
|---|
| 0:01:15 | i correspond to each plane condition |
|---|
| 0:01:19 | in this study we focus on but uh it's measurement missile |
|---|
| 0:01:23 | and that our future |
|---|
| 0:01:24 | induced but i |
|---|
| 0:01:26 | imaging environmental forty |
|---|
| 0:01:29 | yeah yeah we show uh try your uh |
|---|
| 0:01:32 | what they match the deepest pca |
|---|
| 0:01:34 | yeah we call me might be see i |
|---|
| 0:01:36 | fran |
|---|
| 0:01:37 | i use them |
|---|
| 0:01:38 | you meant in the movement of the hand |
|---|
| 0:01:41 | uh |
|---|
| 0:01:43 | set i'm feature |
|---|
| 0:01:44 | can be able seven inning |
|---|
| 0:01:46 | brain signal |
|---|
| 0:01:50 | weighted reports da electricity they sell |
|---|
| 0:01:53 | i might fit for that |
|---|
| 0:01:55 | in this example we use |
|---|
| 0:01:57 | uh some electoral |
|---|
| 0:01:59 | and the system called electoral so it's a photograph E E G |
|---|
| 0:02:05 | uh observed signal uh |
|---|
| 0:02:08 | transform to a device command |
|---|
| 0:02:10 | so |
|---|
| 0:02:11 | cms processing step |
|---|
| 0:02:13 | for feature extraction and tone recognition |
|---|
| 0:02:19 | so |
|---|
| 0:02:20 | uh |
|---|
| 0:02:21 | by this system |
|---|
| 0:02:22 | bci |
|---|
| 0:02:24 | uh but it's |
|---|
| 0:02:25 | speed it uh |
|---|
| 0:02:27 | uh and uh face |
|---|
| 0:02:28 | uh can |
|---|
| 0:02:30 | jen control |
|---|
| 0:02:31 | any device |
|---|
| 0:02:32 | for |
|---|
| 0:02:33 | so that for example for it yeah and mascot or a computer display |
|---|
| 0:02:39 | without |
|---|
| 0:02:40 | muster |
|---|
| 0:02:42 | muscle movement |
|---|
| 0:02:47 | yeah we |
|---|
| 0:02:48 | uh |
|---|
| 0:02:49 | three briefly |
|---|
| 0:02:50 | explaining the future |
|---|
| 0:02:53 | yeah feature to be explicitly by |
|---|
| 0:02:56 | in in maybe see i |
|---|
| 0:02:57 | it is known that uh energy in frequency band called mu reason this desynchronized by |
|---|
| 0:03:03 | means a movement |
|---|
| 0:03:04 | uh well well |
|---|
| 0:03:06 | that is synchronise the location |
|---|
| 0:03:08 | in the brain depends on imagine but |
|---|
| 0:03:12 | and therefore |
|---|
| 0:03:13 | if we know a change over the energy in something frequency band |
|---|
| 0:03:17 | and the special locational we it's energy |
|---|
| 0:03:20 | change |
|---|
| 0:03:21 | uh we can recognise |
|---|
| 0:03:22 | imagine the part of uh body movement from easy signal |
|---|
| 0:03:28 | uh in it might be see i |
|---|
| 0:03:32 | the most bizarre buttons |
|---|
| 0:03:34 | csp missile |
|---|
| 0:03:35 | uh is by the use |
|---|
| 0:03:37 | and especially |
|---|
| 0:03:39 | uh to grasp |
|---|
| 0:03:40 | program |
|---|
| 0:03:42 | but where might be vision |
|---|
| 0:03:45 | and yeah we |
|---|
| 0:03:46 | a a and it is |
|---|
| 0:03:47 | out out we show that the line of the but it wouldn't it |
|---|
| 0:03:51 | fast |
|---|
| 0:03:52 | uh |
|---|
| 0:03:54 | a the red uh it is signal |
|---|
| 0:03:56 | uh |
|---|
| 0:03:58 | a was out by but it's and it with them of the system |
|---|
| 0:04:01 | and uh signal |
|---|
| 0:04:03 | but post filter |
|---|
| 0:04:04 | and you know |
|---|
| 0:04:05 | the plus on the but this pond post filter |
|---|
| 0:04:08 | a a set of the say but this that it hurt |
|---|
| 0:04:10 | records |
|---|
| 0:04:11 | uh the |
|---|
| 0:04:13 | the case you bounce |
|---|
| 0:04:14 | all the separate is that it had |
|---|
| 0:04:16 | uh contains a a a pretty K C bound |
|---|
| 0:04:20 | a codes |
|---|
| 0:04:21 | um you and the it |
|---|
| 0:04:24 | uh a that signal |
|---|
| 0:04:26 | oh wait it |
|---|
| 0:04:27 | by W |
|---|
| 0:04:28 | and this is a special weight |
|---|
| 0:04:30 | and uh we get that doing a competition |
|---|
| 0:04:34 | like this |
|---|
| 0:04:37 | so |
|---|
| 0:04:38 | is S P |
|---|
| 0:04:39 | as as the weight if this has its from so weights W decided from running it |
|---|
| 0:04:46 | uh |
|---|
| 0:04:47 | the by this of the my this program |
|---|
| 0:04:49 | uh |
|---|
| 0:04:52 | uh this stuff in this of program |
|---|
| 0:04:54 | take that you expect a shell with a body as of a special so weight |
|---|
| 0:04:58 | it signal |
|---|
| 0:04:59 | a but on the T they don't need to class C |
|---|
| 0:05:02 | is minimize |
|---|
| 0:05:03 | where she is that of sectors about it |
|---|
| 0:05:06 | and this lies see a set of a |
|---|
| 0:05:08 | data but on to belonging don't to class C |
|---|
| 0:05:11 | and the E X P expectation of a all by C D |
|---|
| 0:05:15 | grass K shall we can use the body as |
|---|
| 0:05:17 | oh but extract signal |
|---|
| 0:05:19 | uh as each about |
|---|
| 0:05:23 | oh uh they a P need band post filtering |
|---|
| 0:05:26 | uh as processing |
|---|
| 0:05:28 | a hyper |
|---|
| 0:05:29 | uh a like this |
|---|
| 0:05:30 | i have a doubt them a three can see bound depends |
|---|
| 0:05:33 | on on um it's "'em" at the member i matt |
|---|
| 0:05:36 | and toss up |
|---|
| 0:05:37 | the |
|---|
| 0:05:38 | we won't |
|---|
| 0:05:39 | that just fitted that take is direct component that most D contain |
|---|
| 0:05:44 | to just the eight to to a |
|---|
| 0:05:46 | what the image |
|---|
| 0:05:49 | uh some muscle |
|---|
| 0:05:50 | have been proposed to |
|---|
| 0:05:52 | design the filter |
|---|
| 0:05:54 | uh a fast super missile |
|---|
| 0:05:57 | uh |
|---|
| 0:05:58 | we set |
|---|
| 0:05:59 | this uh |
|---|
| 0:06:00 | we set is uh was to to every button out of the a candidate |
|---|
| 0:06:04 | uh uh running that the by cross |
|---|
| 0:06:06 | and this to D so |
|---|
| 0:06:10 | E to file |
|---|
| 0:06:11 | designed uh i hope to my for that mike is endings |
|---|
| 0:06:15 | a C P |
|---|
| 0:06:16 | uh |
|---|
| 0:06:18 | i well yes this P cannot provide that a complete get three cases selected |
|---|
| 0:06:22 | and the C S S as P |
|---|
| 0:06:24 | and introduced thus the of the coffee C N or or or a a a i on filter |
|---|
| 0:06:30 | a high bar |
|---|
| 0:06:32 | uh |
|---|
| 0:06:32 | you know the might this |
|---|
| 0:06:33 | shown |
|---|
| 0:06:35 | oh to my the complex |
|---|
| 0:06:36 | and time consuming |
|---|
| 0:06:38 | and the specs just V is design |
|---|
| 0:06:41 | the this be designs uh |
|---|
| 0:06:43 | filter |
|---|
| 0:06:44 | in for casing domain |
|---|
| 0:06:46 | i have a that's an get T that that of to my addition can |
|---|
| 0:06:52 | so in this paper we propose a use improve missile to design the specific case see filter |
|---|
| 0:06:58 | uh |
|---|
| 0:06:59 | i as fast |
|---|
| 0:07:00 | i fast fast idea |
|---|
| 0:07:01 | we uh the in do the cost function just P |
|---|
| 0:07:05 | i put that's that the rates for frequency component |
|---|
| 0:07:09 | and do we look to you |
|---|
| 0:07:11 | uh to optimize |
|---|
| 0:07:12 | that was function |
|---|
| 0:07:15 | the proposed cost functional |
|---|
| 0:07:16 | we |
|---|
| 0:07:18 | uh there but then need to at up the my patient for both |
|---|
| 0:07:21 | and specific filter |
|---|
| 0:07:23 | and a free case for freedom |
|---|
| 0:07:24 | and then zack cost function can but because we use |
|---|
| 0:07:28 | well these the cost |
|---|
| 0:07:32 | a a mobile a top to my addition supplements romance |
|---|
| 0:07:35 | in a the in team up to my addition |
|---|
| 0:07:37 | uh did use to denies the a but you program |
|---|
| 0:07:44 | so we |
|---|
| 0:07:46 | yeah i expanding |
|---|
| 0:07:47 | to will propose missile |
|---|
| 0:07:49 | oh |
|---|
| 0:07:50 | for at understanding under standing we you don't to late uh |
|---|
| 0:07:54 | and a mental a signal |
|---|
| 0:07:56 | uh like |
|---|
| 0:07:57 | but uh of the blocks |
|---|
| 0:07:58 | like this |
|---|
| 0:08:00 | uh |
|---|
| 0:08:01 | the crime of a |
|---|
| 0:08:04 | oh by X is then not channel |
|---|
| 0:08:06 | and uh a low uh a low you that time |
|---|
| 0:08:12 | oh it's pretty demon only |
|---|
| 0:08:14 | uh processing |
|---|
| 0:08:16 | we define the uh |
|---|
| 0:08:18 | we |
|---|
| 0:08:19 | the spectrum all move that windowed signal |
|---|
| 0:08:21 | a fast we |
|---|
| 0:08:23 | defined that window signal |
|---|
| 0:08:25 | add to the X |
|---|
| 0:08:26 | and the |
|---|
| 0:08:28 | that |
|---|
| 0:08:29 | to the X to it's a transform the spectral |
|---|
| 0:08:33 | uh to the Y |
|---|
| 0:08:34 | a by the speed of on a school |
|---|
| 0:08:41 | like is |
|---|
| 0:08:42 | uh we define in then you feature value |
|---|
| 0:08:45 | using a spectrum |
|---|
| 0:08:47 | uh |
|---|
| 0:08:48 | and this that yes |
|---|
| 0:08:49 | a a rate that |
|---|
| 0:08:51 | how to act to W on the eight |
|---|
| 0:08:54 | because uh is uh |
|---|
| 0:08:57 | and |
|---|
| 0:08:59 | since |
|---|
| 0:09:00 | uh the current Y |
|---|
| 0:09:02 | uh uh three guys component |
|---|
| 0:09:04 | and the |
|---|
| 0:09:05 | little or why |
|---|
| 0:09:07 | he |
|---|
| 0:09:08 | the case C component |
|---|
| 0:09:09 | uh that we do |
|---|
| 0:09:10 | act |
|---|
| 0:09:11 | that's the so wait |
|---|
| 0:09:12 | and the H like the spectral weight |
|---|
| 0:09:14 | but it at is uh |
|---|
| 0:09:16 | because for |
|---|
| 0:09:18 | uh |
|---|
| 0:09:19 | in a "'cause" we will show how to find of W |
|---|
| 0:09:22 | and eight |
|---|
| 0:09:26 | uh we designed this of to mine is a program |
|---|
| 0:09:29 | uh for four was weight picked up by extending this just cost |
|---|
| 0:09:34 | i |
|---|
| 0:09:36 | in this |
|---|
| 0:09:36 | to my that program |
|---|
| 0:09:38 | uh uh but a C on and it's yeah this a |
|---|
| 0:09:41 | decide such that station all with future |
|---|
| 0:09:44 | which each i that |
|---|
| 0:09:46 | uh they don't the class C it to minimize the |
|---|
| 0:09:49 | in nineteen data |
|---|
| 0:09:51 | and and as a a normal vision or all sampled |
|---|
| 0:09:55 | we see that i |
|---|
| 0:09:57 | of not cross rubber |
|---|
| 0:10:02 | so we sort of |
|---|
| 0:10:04 | the uh |
|---|
| 0:10:05 | program |
|---|
| 0:10:06 | however it did this got to estimate and the city a to my |
|---|
| 0:10:10 | uh both W and eight |
|---|
| 0:10:12 | so we they by |
|---|
| 0:10:13 | to that problem we into two stop program |
|---|
| 0:10:17 | uh the program |
|---|
| 0:10:19 | to optimize |
|---|
| 0:10:20 | W while fixing eight |
|---|
| 0:10:23 | and the to optimize H where thing that way |
|---|
| 0:10:28 | not think that can be transformed to the a |
|---|
| 0:10:31 | G is for |
|---|
| 0:10:32 | we can define an to supplement |
|---|
| 0:10:35 | oh yeah O R is a whole body has what the ticks |
|---|
| 0:10:38 | i don't to |
|---|
| 0:10:39 | and a channel component |
|---|
| 0:10:41 | and the Q |
|---|
| 0:10:43 | but it also co but it's not the ticks alone two |
|---|
| 0:10:46 | uh uh |
|---|
| 0:10:48 | and i two because component |
|---|
| 0:10:50 | it isn't a |
|---|
| 0:10:51 | well known |
|---|
| 0:10:52 | that's uh |
|---|
| 0:10:54 | D supplements can be deduced to by this to generalise at "'em" body problem |
|---|
| 0:10:59 | i by proof |
|---|
| 0:11:02 | a |
|---|
| 0:11:02 | and this is somebody of that |
|---|
| 0:11:04 | of the bat um process it but C |
|---|
| 0:11:07 | as the flat |
|---|
| 0:11:08 | is eyes |
|---|
| 0:11:09 | the eight |
|---|
| 0:11:10 | and the step to |
|---|
| 0:11:11 | uh |
|---|
| 0:11:12 | of them that but you by serving being program well |
|---|
| 0:11:16 | and the step C D |
|---|
| 0:11:17 | of is eight |
|---|
| 0:11:18 | by a serving supper made to |
|---|
| 0:11:22 | so we did P |
|---|
| 0:11:23 | as step to to and the steps three |
|---|
| 0:11:25 | and do post function it's |
|---|
| 0:11:27 | combined |
|---|
| 0:11:32 | oh mobile we will do so |
|---|
| 0:11:35 | uh reports |
|---|
| 0:11:37 | you also propose that a |
|---|
| 0:11:39 | classification do |
|---|
| 0:11:41 | uh a cross lie |
|---|
| 0:11:43 | and the be did that a |
|---|
| 0:11:47 | yeah i of the one you is uh |
|---|
| 0:11:49 | you these different to affiliate the eight between classes |
|---|
| 0:11:53 | uh |
|---|
| 0:11:55 | we use that one on the H mount H to |
|---|
| 0:11:59 | in this |
|---|
| 0:12:00 | lou |
|---|
| 0:12:01 | and ms of to D is calm of filter |
|---|
| 0:12:04 | H |
|---|
| 0:12:05 | being or thought or seeds |
|---|
| 0:12:07 | uh |
|---|
| 0:12:09 | fast fast we find uh |
|---|
| 0:12:11 | W the |
|---|
| 0:12:12 | and at G |
|---|
| 0:12:13 | in the we had to outside "'cause" rubber |
|---|
| 0:12:17 | after after thus |
|---|
| 0:12:18 | be sort of a sub one with a T G |
|---|
| 0:12:22 | in other that class |
|---|
| 0:12:25 | and G but |
|---|
| 0:12:26 | and the we get stuff you but |
|---|
| 0:12:29 | so |
|---|
| 0:12:30 | in this dismissal |
|---|
| 0:12:31 | we |
|---|
| 0:12:33 | yeah |
|---|
| 0:12:34 | we use |
|---|
| 0:12:35 | W one on the bridge to and the a G |
|---|
| 0:12:41 | oh |
|---|
| 0:12:42 | uh we |
|---|
| 0:12:44 | experiment |
|---|
| 0:12:45 | uh |
|---|
| 0:12:46 | uh to off on the uh |
|---|
| 0:12:48 | propose missile |
|---|
| 0:12:50 | we |
|---|
| 0:12:50 | but this dataset set |
|---|
| 0:12:52 | uh name data set four we have from bci competition three |
|---|
| 0:12:56 | and |
|---|
| 0:12:57 | this data sets contains that's a C G signals |
|---|
| 0:13:00 | cross the cross is are right hand and right foot motor imagery cross |
|---|
| 0:13:05 | and five subjects but at |
|---|
| 0:13:08 | and the easy signal a a what it to be |
|---|
| 0:13:10 | well hundred eight vector all |
|---|
| 0:13:13 | and sampling for K C |
|---|
| 0:13:15 | i is a hundred ten |
|---|
| 0:13:19 | the subject |
|---|
| 0:13:20 | but home of the |
|---|
| 0:13:22 | uh task |
|---|
| 0:13:23 | uh |
|---|
| 0:13:25 | two hundred eighty times |
|---|
| 0:13:27 | so the number of out of in each class is more hundred forty |
|---|
| 0:13:31 | and do a shell beach prior three point five second uh that's it tough sing |
|---|
| 0:13:36 | that it's thus |
|---|
| 0:13:37 | signal ranks |
|---|
| 0:13:39 | he's |
|---|
| 0:13:40 | so hundred |
|---|
| 0:13:41 | fifty some |
|---|
| 0:13:45 | a |
|---|
| 0:13:45 | we can be as uh |
|---|
| 0:13:47 | problem is all we |
|---|
| 0:13:49 | this |
|---|
| 0:13:50 | uh a few text task meant to texas some feature extraction missile |
|---|
| 0:13:54 | uh says be one |
|---|
| 0:13:56 | use use a bunch was with uh with the past bound of separate is that to have |
|---|
| 0:14:00 | and the P to |
|---|
| 0:14:02 | you'd use the bound was create that when idea optimized by a C B |
|---|
| 0:14:08 | and do you also used |
|---|
| 0:14:09 | a that uh that are designed to by C S S P and the specs |
|---|
| 0:14:13 | S P |
|---|
| 0:14:15 | a a in the in the missile |
|---|
| 0:14:17 | we adapt to simply classification blue |
|---|
| 0:14:20 | at to compare yeah a future value correspond to |
|---|
| 0:14:25 | uh it's class |
|---|
| 0:14:26 | uh |
|---|
| 0:14:28 | for example you S |
|---|
| 0:14:30 | csp P |
|---|
| 0:14:30 | we use discuss kitchen |
|---|
| 0:14:35 | this a the cross case and is that |
|---|
| 0:14:39 | uh this there was so that |
|---|
| 0:14:42 | uh chris case accuracy |
|---|
| 0:14:43 | uh a given by a five five five by five cross what addition |
|---|
| 0:14:50 | for a subject and each missile |
|---|
| 0:14:53 | you know but eight |
|---|
| 0:14:54 | uh |
|---|
| 0:14:55 | the proposed mess |
|---|
| 0:14:59 | a to home |
|---|
| 0:15:00 | as a miss |
|---|
| 0:15:03 | and uh and the kissed we show that uh |
|---|
| 0:15:06 | we show the uh a a a filter |
|---|
| 0:15:08 | do |
|---|
| 0:15:09 | yeah given by |
|---|
| 0:15:11 | each missile |
|---|
| 0:15:13 | in this case |
|---|
| 0:15:14 | uh |
|---|
| 0:15:17 | in in this case yeah we use a |
|---|
| 0:15:20 | in this case uh W one to that |
|---|
| 0:15:23 | uh |
|---|
| 0:15:24 | in each each that i is same |
|---|
| 0:15:26 | bit doing we to that of the one with the because |
|---|
| 0:15:29 | uh i ms of that that we use |
|---|
| 0:15:32 | we said to G |
|---|
| 0:15:34 | we set D other one |
|---|
| 0:15:37 | cross well |
|---|
| 0:15:38 | and we show that class |
|---|
| 0:15:40 | we show uh |
|---|
| 0:15:43 | we show W wanted up W |
|---|
| 0:15:45 | W one day about |
|---|
| 0:15:47 | uh since |
|---|
| 0:15:48 | this right |
|---|
| 0:15:49 | this right |
|---|
| 0:15:58 | that this C D S shows a few to |
|---|
| 0:16:01 | and given by dismissal |
|---|
| 0:16:03 | uh |
|---|
| 0:16:04 | a a kind of to characteristic of the field that |
|---|
| 0:16:07 | given by this missile |
|---|
| 0:16:09 | uh |
|---|
| 0:16:09 | the propose a not give the same about of the are you |
|---|
| 0:16:13 | my |
|---|
| 0:16:14 | and in subject to yeah |
|---|
| 0:16:19 | and in this |
|---|
| 0:16:20 | uh is subject to a |
|---|
| 0:16:22 | and uh propose missile also have a large you eight |
|---|
| 0:16:25 | in but |
|---|
| 0:16:26 | in band high at uh |
|---|
| 0:16:29 | i manually any optimize to plus one |
|---|
| 0:16:32 | i |
|---|
| 0:16:32 | and this |
|---|
| 0:16:33 | uh a high yeah bad looks uh a looks the how many "'cause" or this bound |
|---|
| 0:16:40 | this it is a a a a we show |
|---|
| 0:16:43 | spectral |
|---|
| 0:16:44 | uh to look at a show |
|---|
| 0:16:47 | all this |
|---|
| 0:16:47 | fig |
|---|
| 0:16:48 | it's away way |
|---|
| 0:16:51 | in subject a a a or miss not came almost same space way |
|---|
| 0:16:56 | a last |
|---|
| 0:16:57 | in use of a just a one |
|---|
| 0:16:59 | uh we |
|---|
| 0:17:00 | we are able serve that difference |
|---|
| 0:17:02 | define an |
|---|
| 0:17:03 | us bits are but that |
|---|
| 0:17:04 | so a different frequency component |
|---|
| 0:17:07 | yeah a different is to but that |
|---|
| 0:17:13 | a good job |
|---|
| 0:17:14 | uh we propose a missile to |
|---|
| 0:17:17 | designed to for channel now and the frequency component using running data |
|---|
| 0:17:22 | that's so show over the way top to by this |
|---|
| 0:17:24 | wait |
|---|
| 0:17:25 | oh the weight of the my this shown can be obtained at thing so |
|---|
| 0:17:29 | the sort sort of being some |
|---|
| 0:17:31 | and then i say can body problem |
|---|
| 0:17:33 | program |
|---|
| 0:17:34 | uh uh can adapt |
|---|
| 0:17:36 | can be tough |
|---|
| 0:17:37 | that |
|---|
| 0:17:38 | then the cost function is don't increasing in each iteration |
|---|
| 0:17:41 | the proposed missile |
|---|
| 0:17:42 | see how yet "'cause" case accuracy in what they the best is yet |
|---|
| 0:17:47 | a lot |
|---|
| 0:17:48 | payment |
|---|
| 0:17:49 | so |
|---|
| 0:17:50 | i |
|---|
| 0:17:53 | or present like we already developed to the temporal fit that design miss |
|---|
| 0:17:58 | and uh and corpus was a temporal filter |
|---|
| 0:18:02 | design result |
|---|
| 0:18:03 | uh a uh |
|---|
| 0:18:04 | to be present |
|---|
| 0:18:07 | thank Q |
|---|
| 0:18:30 | i |
|---|
| 0:18:30 | oh |
|---|