Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
A Markov Random Fields Approach to the Gating o...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Kevin Brosnan
June 15, 2016
Research
150
0
Share
A Markov Random Fields Approach to the Gating of Flow Cytometry Data
Reasearch Students Conference Dublin 2016. Best talk prize awarded.
Kevin Brosnan
June 15, 2016
More Decks by Kevin Brosnan
See All by Kevin Brosnan
Automated Gating for Flow Cytometry
significantstats
0
210
False Starts in Athletics: Are they truly fair?
significantstats
0
110
False Starts in Athletics: Are they truly fair?
significantstats
0
110
False Start Detection in Elite Athletics
significantstats
0
140
A Markov Random Fields Approach to the Gating of Flow Cytometry Data
significantstats
0
150
Challenges for tertiary level mathematics tutors
significantstats
0
100
Elite Athletics: Is the false start disqualification rule appropriate?
significantstats
0
130
Quantile Regression
significantstats
0
160
Forward Modelling of UK Gas Prices
significantstats
0
62
Other Decks in Research
See All in Research
R&Dチームを起ち上げる
shibuiwilliam
1
250
SoftMatcha 2: 1兆語規模コーパスの超高速かつ柔らかい検索
e869120_sub
6
3.3k
LLM Compute Infrastructure Overview
karakurist
2
1.3k
Ankylosing Spondylitis
ankh2054
0
170
はじまりの クエスチョンブック —余暇と豊かさにあふれた社会とは?
culturaltransition
PRO
0
420
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
530
正規分布と最適化について
koide3
0
190
Harness Engineering and Al Agent
kzinmr
1
520
Sequences of Logits Reveal the Low Rank Structure of Language Models
sansantech
PRO
1
240
2026年3月1日(日)福島「除染土」の公共利用をかんがえる
atsukomasano2026
0
590
National high-resolution cropland classification of Japan with agricultural census information and multi-temporal multi-modality datasets
satai
2
120
AIを叩き台として、 「検証」から「共創」へと進化するリサーチ
mela_dayo
0
260
Featured
See All Featured
How to Think Like a Performance Engineer
csswizardry
28
2.6k
Agile Leadership in an Agile Organization
kimpetersen
PRO
0
150
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
1
180
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
28
3.5k
Bootstrapping a Software Product
garrettdimon
PRO
307
120k
The Invisible Side of Design
smashingmag
302
52k
Discover your Explorer Soul
emna__ayadi
2
1.1k
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
0
150
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
2.7k
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
marketingsoph
0
140
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
800
My Coaching Mixtape
mlcsv
0
130
Transcript
A M A R KO V R A N D
O M F I E L D S A P P ROA C H T O T H E GAT I N G O F F LO W C Y T O M E T R Y DATA K e v i n B r o s n a n , U n i v e r s i t y O f L i m e r i c k
P R E S E N TAT I O N
OU T L I N E Flow Cytometry Existing methods Markov Random Fields Identifying Clusters Results Further Work
F LO W C Y T O M E T
R Y …
W h at i s f lo w c y
to m et r y ?
W h at i s f lo w c y
to m et r y ? Flow
W h at i s f lo w c y
to m et r y ? Flow Cyto
W h at i s f lo w c y
to m et r y ? Flow Cyto metry
F lo w c y to m et r y
d at a … Mean St. Dev. Min Max FSC.H 287.08 178.19 59 1, 023 SSC.H 251.83 186.65 11 1, 023 FL1.H 349.16 234.35 0 974 FL2.H 126.40 90.84 0 705 FL3.H 258.34 192.26 1 1, 023 FL1.A 73.46 195.15 0 1, 023 FL1.W 17.60 56.39 0 444
F lo w c y to m et r y
d at a …
S p ars i t y … Statistic N Mean
St. Dev. Min Max FSC.H 1, 545 71.40 44.53 14 255 SSC.H 1, 545 62.57 46.65 2 255 FL1.H 1, 545 86.93 58.58 0 243 FL2.H 1, 545 31.27 22.66 0 176 FL3.H 1, 545 64.20 48.03 0 255 FL1.A 1, 545 18.25 48.65 0 255 FL1.W 1, 545 4.33 14.01 0 111 time 1, 545 294.04 177.55 2 598
S p ars i t y …
E X I S T I N G M E
T H O D S …
I n d u s t r y S t
a n d ar d …
I n d u s t r y S t
a n d ar d … 6= Expert 2 Expert 1
M o d e l B a s e d
C lu s t er i ng …
t- d i s t r i b u t
i o n M i x t u re s …
t- d i s t r i b u t
i o n M i x t u re s …
M A R KO V R A N D O
M F I E L D S …
X0,0 X1,0 X2,0 X3,0 X0,1 X1,1 X2,1 X3,1 X0,2 X1,2
X2,2 X3,2 X0,3 X1,3 X2,3 X3,3
X0,0 X1,0 X2,0 X3,0 X0,1 X1,1 X2,1 X3,1 X0,2 X1,2
X2,2 X3,2 X0,3 X1,3 X2,3 X3,3
X0,0 X1,0 X2,0 X3,0 X0,1 X1,1 X2,1 X3,1 X0,2 X1,2
X2,2 X3,2 X0,3 X1,3 X2,3 X3,3
X0,0 X1,0 X2,0 X3,0 X0,1 X1,1 X2,1 X3,1 X0,2 X1,2
X2,2 X3,2 X0,3 X1,3 X2,3 X3,3
Wo r k i ng E xam p le …
Wo r k i ng E xam p le …
I D E N T I F Y I N
G C LU S T E RS …
C o n n e ct e d - C
o m p o n e nt s …
C o n n e ct e d - C
o m p o n e nt s …
R E S U LT S …
6 -b i t co n f i g u
r at i o n …
6 -b i t co n f i g u
r at i o n …
6 -b i t co n f i g u
r at i o n …
F U RT H E R WO R K …
None
None
None
None
T H A N K S F O R L
I S T E N I N G ! A N Y Q U E S T I O N S ?