File size: 16,180 Bytes
9b8b5a0 8834675 9b8b5a0 8834675 9b8b5a0 8834675 9b8b5a0 8834675 9b8b5a0 8834675 9b8b5a0 8834675 9b8b5a0 064b936 9b8b5a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 |
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Conversational LLM-Based Decision Support for Defect Classification in AFM Images</title>
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.5.0/css/all.min.css">
<style>
:root {
--primary-color: #0f172a;
--secondary-color: #1e293b;
--accent-color: #3b82f6;
--text-primary: #e2e8f0;
--text-secondary: #94a3b8;
--border-color: #334155;
--gradient: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
--card-bg: rgba(30, 41, 59, 0.7);
--glass-bg: rgba(255, 255, 255, 0.05);
--blur: blur(10px);
}
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family: 'Inter', -apple-system, BlinkMacSystemFont, sans-serif;
background: var(--primary-color);
color: var(--text-primary);
line-height: 1.6;
overflow-x: hidden;
}
.hero {
min-height: 100vh;
display: grid;
place-items: center;
position: relative;
background: var(--gradient);
overflow: hidden;
}
.hero::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: url('data:image/svg+xml,<svg width="60" height="60" viewBox="0 0 60 60" xmlns="http://www.w3.org/2000/svg"><g fill="none" fill-rule="evenodd"><g fill="%23ffffff" fill-opacity="0.05"><circle cx="30" cy="30" r="1"/></g></svg>') repeat;
animation: float 20s ease-in-out infinite;
}
@keyframes float {
0%, 100% { transform: translateY(0) rotate(0deg); }
50% { transform: translateY(-20px) rotate(180deg); }
}
.hero-content {
text-align: center;
z-index: 1;
max-width: 800px;
padding: 2rem;
}
.hero h1 {
font-size: clamp(2.5rem, 5vw, 4rem);
font-weight: 700;
margin-bottom: 1rem;
background: linear-gradient(to right, #fff, #cbd5e1);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
background-clip: text;
}
.hero p {
font-size: 1.25rem;
color: rgba(255, 255, 255, 0.8);
margin-bottom: 2rem;
}
.authors {
display: block;
max-width: 900px;
margin: 2rem auto;
text-align: center;
font-size: 1.1rem;
line-height: 1.5;
color: #ffffff;
}
.authors strong {
color: #ffffff;
}
.authors sup {
color: #a0c4ff;
font-size: 0.8em;
vertical-align: super;
}
.affiliations {
margin-top: 1.5rem;
font-size: 0.95rem;
color: #d1d5db;
line-height: 1.6;
}
.affiliations span {
display: block;
margin-bottom: 0.5rem;
}
.abstract {
max-width: 1000px;
margin: 4rem auto;
padding: 2rem;
}
.abstract-card {
background: var(--card-bg);
border: 1px solid var(--border-color);
border-radius: 1.5rem;
padding: 2.5rem;
position: relative;
overflow: hidden;
}
.abstract-card::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
height: 3px;
background: var(--gradient);
}
.section-title {
font-size: 2rem;
margin-bottom: 1.5rem;
display: flex;
align-items: center;
gap: 1rem;
}
.section-title i {
color: var(--accent-color);
}
.framework {
margin: 4rem 0;
}
.framework-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(300px, 1fr));
gap: 2rem;
margin: 2rem 0;
}
.framework-step {
background: var(--card-bg);
border: 1px solid var(--border-color);
border-radius: 1rem;
padding: 2rem;
text-align: center;
transition: transform 0.3s ease, box-shadow 0.3s ease;
position: relative;
overflow: hidden;
}
.framework-step:hover {
transform: translateY(-5px);
box-shadow: 0 10px 30px rgba(0, 0, 0, 0.3);
}
.framework-step::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: var(--gradient);
opacity: 0;
transition: opacity 0.3s ease;
}
.framework-step:hover::before {
opacity: 0.1;
}
.step-icon {
font-size: 3rem;
margin-bottom: 1rem;
background: var(--gradient);
-webkit-background-clip: text;
-webkit-text-fill-color: transparent;
background-clip: text;
}
.results {
margin: 4rem 0;
}
.metrics-grid {
display: grid;
grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
gap: 1.5rem;
}
.metric-card {
background: var(--card-bg);
border: 1px solid var(--border-color);
border-radius: 1rem;
padding: 1.5rem;
text-align: center;
transition: all 0.3s ease;
}
.metric-card:hover {
transform: scale(1.05);
border-color: var(--accent-color);
}
.metric-value {
font-size: 2.5rem;
font-weight: 700;
color: var(--accent-color);
margin-bottom: 0.5rem;
}
.chat-demo {
margin: 4rem 0;
}
.chat-window {
background: var(--card-bg);
border: 1px solid var(--border-color);
border-radius: 1rem;
overflow: hidden;
max-width: 600px;
margin: 0 auto;
}
.chat-header {
background: var(--secondary-color);
padding: 1rem;
border-bottom: 1px solid var(--border-color);
display: flex;
align-items: center;
gap: 0.5rem;
}
.chat-header i {
color: #10b981;
}
.chat-messages {
height: 300px;
overflow-y: auto;
padding: 1rem;
}
.message {
margin-bottom: 1rem;
padding: 0.75rem 1rem;
border-radius: 1rem;
max-width: 80%;
}
.message.user {
background: var(--accent-color);
margin-left: auto;
}
.message.assistant {
background: var(--secondary-color);
border: 1px solid var(--border-color);
}
.links {
text-align: center;
margin: 4rem 0;
}
.cta-button {
display: inline-flex;
align-items: center;
gap: 0.5rem;
background: var(--gradient);
color: white;
padding: 1rem 2rem;
border-radius: 2rem;
text-decoration: none;
font-weight: 600;
transition: all 0.3s ease;
box-shadow: 0 4px 15px rgba(59, 130, 246, 0.3);
}
.cta-button:hover {
transform: translateY(-2px);
box-shadow: 0 6px 20px rgba(59, 130, 246, 0.4);
}
.floating-particles {
position: fixed;
top: 0;
left: 0;
width: 100%;
height: 100%;
pointer-events: none;
z-index: -1;
}
.particle {
position: absolute;
width: 2px;
height: 2px;
background: var(--accent-color);
border-radius: 50%;
animation: particle-float 10s linear infinite;
}
@keyframes particle-float {
0% {
transform: translateY(100vh) rotate(0deg);
opacity: 0;
}
10% {
opacity: 1;
}
90% {
opacity: 1;
}
100% {
transform: translateY(-100vh) rotate(360deg);
opacity: 0;
}
}
@media (max-width: 768px) {
.hero {
padding: 1rem;
}
.authors {
grid-template-columns: 1fr;
}
.abstract-card {
padding: 1.5rem;
}
.framework-grid {
grid-template-columns: 1fr;
}
}
.scroll-indicator {
position: absolute;
bottom: 2rem;
left: 50%;
transform: translateX(-50%);
animation: bounce 2s infinite;
color: rgba(255, 255, 255, 0.6);
}
@keyframes bounce {
0%, 100% { transform: translateX(-50%) translateY(0); }
50% { transform: translateX(-50%) translateY(-10px); }
}
</style>
</head>
<body>
<div class="floating-particles" id="particles"></div>
<section class="hero">
<div class="hero-content">
<h1>Conversational LLM-Based Decision Support for Defect Classification in AFM Images</h1>
<p>Revolutionizing nanoscale imaging through AI-powered defect detection and real-time guidance</p>
<div class="authors">
<strong>ANGONA BISWAS<sup>1§</sup>, JAYDEEP RADE<sup>1§</sup>, NABILA MASUD<sup>1</sup>, MD HASIBUL HASAN HASIB<sup>1</sup>, ADITYA BALU<sup>3</sup>, JUNTAO ZHANG<sup>2</sup>, SOUMIK SARKAR<sup>2</sup>, ADARSH KRISHNAMURTHY<sup>1,2</sup>, JUAN REN<sup>2</sup>, and ANWESHA SARKAR<sup>1</sup></strong>
<div class="affiliations">
<span><sup>1</sup>Department of Electrical and Computer Engineering, Iowa State University, 2520 Osborn Dr., Ames, 50011, IA, USA</span>
<span><sup>2</sup>Department of Mechanical Engineering, Iowa State University, 2025 Black Engineering, Ames, IA 50011, USA</span>
<span><sup>3</sup>Translational AI Center, Black Engineering, 2529 Union Dr Suite 2024, Ames, IA 50011, USA</span>
<span><sup>§</sup>Equal Contribution</span>
</div>
<p style="margin-top:1rem;font-size:1rem;">
<i class="fas fa-envelope"></i> <strong>CORRESPONDING AUTHOR:</strong> Anwesha Sarkar (e-mail: anweshas@iastate.edu)
</p>
</div>
</div>
<div class="scroll-indicator">
<i class="fas fa-chevron-down fa-2x"></i>
</div>
</section>
<main style="max-width: 1200px; margin: 0 auto; padding: 2rem;">
<div style="text-align:center;margin-bottom:1.5rem;">
<a href="https://github.com/idealab-isu/AFM-LLM-Defect-Guidance" target="_blank" class="cta-button">
<i class="fab fa-github"></i> GitHub
</a>
<a href="https://ieeexplore.ieee.org/document/11096088" target="_blank" class="cta-button" style="margin-left:1rem;">
<i class="fas fa-file-alt"></i> Paper
</a>
</div>
<section class="abstract">
<div class="abstract-card">
<h2 class="section-title">
<i class="fas fa-file-alt"></i>
Abstract
</h2>
<p>
Atomic Force Microscopy (AFM) has emerged as a powerful tool for nanoscale imaging and quantitative characterization of organic (e.g., live cells, proteins, DNA, lipid bilayers) and inorganic (e.g., silicon wafers, polymers) specimens. However, image artifacts in AFM height and peak force error images directly affect the precision of nanomechanical measurements. Experimentalists face considerable challenges in obtaining high-quality AFM images due to the requirement of specialized expertise and constant manual monitoring.
</p>
<br>
<p>
Another challenge is the lack of high-quality AFM datasets to train machine learning models for automated defect detection. In this work, we propose a two-step AI framework that combines a vision-based deep learning (DL) model for classifying AFM image defects with a Large Language Models (LLMs)-based conversational assistant that provides real-time corrective guidance in natural language, making it particularly valuable for non-AFM experts aiming to obtain high-quality images.
</p>
<br>
<p>
We curated an annotated AFM defect dataset spanning organic and inorganic samples to train the defect detection model. Our defect classification model achieves <strong>91.43% overall accuracy</strong>, with a recall of <strong>93% for tip contamination</strong> and <strong>60% for not-tracking defects</strong>.
</p>
</div>
</section>
<section class="framework">
<h2 class="section-title">
<i class="fas fa-sitemap"></i>
Two-Step AI Framework
</h2>
<div class="framework-grid">
<div class="framework-step">
<div class="step-icon">
<i class="fas fa-eye"></i>
</div>
<h3>Vision Model</h3>
<p>Deep learning model classifies defects in AFM images with 91.43% accuracy</p>
</div>
<div class="framework-step">
<div class="step-icon">
<i class="fas fa-comments"></i>
</div>
<h3>LLM Assistant</h3>
<p>Conversational AI provides real-time guidance in natural language</p>
</div>
<div class="framework-step">
<div class="step-icon">
<i class="fas fa-desktop"></i>
</div>
<h3>Unified Interface</h3>
<p>Seamless interaction between DL model and LLM-based guidance</p>
</div>
</div>
</section>
<section class="results">
<h2 class="section-title">
<i class="fas fa-chart-bar"></i>
Model Performance
</h2>
<div class="metrics-grid">
<div class="metric-card">
<div class="metric-value">91.43%</div>
<p>Overall Accuracy</p>
</div>
<div class="metric-card">
<div class="metric-value">93%</div>
<p>Tip Contamination Recall</p>
</div>
<div class="metric-card">
<div class="metric-value">60%</div>
<p>Not-Tracking Recall</p>
</div>
</div>
</section>
<section class="chat-demo">
<h2 class="section-title">
<i class="fas fa-robot"></i>
Interactive Demo
</h2>
<div class="chat-window">
<div class="chat-header">
<i class="fas fa-circle fa-xs"></i>
<span>AFM Assistant</span>
</div>
<div class="chat-messages">
<div class="message user">
I see flat lines in my topography image that suggest tracking failure —what environmental or scanner factors could be contributing to this, and how do I address them?
</div>
<div class="message assistant">
1. Adjust feedback parameters: increase the proportional/integral gains cautiously<br><br>
2. Increase setpoint force to maintain better tip-sample contact<br><br>
3. For persistent problems, try changing scan direction or starting position<br><br>
4. Decrease scan speed to give the feedback loop more time
</div>
</div>
</div>
</section>
<section class="links">
<a href="https://github.com/idealab-isu/AFM-LLM-Defect-Guidance" class="cta-button" target="_blank">
<i class="fab fa-github"></i>
View on GitHub
</a>
</section>
</main>
<script>
// Floating particles animation
const particlesContainer = document.getElementById('particles');
const particleCount = 50;
for (let i = 0; i < particleCount; i++) {
const particle = document.createElement('div');
particle.className = 'particle';
particle.style.left = Math.random() * 100 + '%';
particle.style.animationDelay = Math.random() * 10 + 's';
particle.style.animationDuration = (Math.random() * 10 + 10) + 's';
particlesContainer.appendChild(particle);
}
// Smooth scroll
document.querySelector('.scroll-indicator').addEventListener('click', () => {
document.querySelector('.abstract').scrollIntoView({ behavior: 'smooth' });
});
// Intersection Observer for animations
const observerOptions = {
threshold: 0.1,
rootMargin: '0px 0px -50px 0px'
};
const observer = new IntersectionObserver((entries) => {
entries.forEach(entry => {
if (entry.isIntersecting) {
entry.target.style.opacity = '1';
entry.target.style.transform = 'translateY(0)';
}
});
}, observerOptions);
document.querySelectorAll('.framework-step, .metric-card').forEach(el => {
el.style.opacity = '0';
el.style.transform = 'translateY(20px)';
el.style.transition = 'opacity 0.6s ease, transform 0.6s ease';
observer.observe(el);
});
</script>
</body>
</html> |