Asif Hasan’s Post

Excited to Present at WCCM 2024! I'm attending the 16th World Congress on Computational Mechanics / 4th Pan American Congress on Computational Mechanics (WCCM-PANACM 2024) this week. Yesterday, I had the opportunity to see some remarkable works in additive manufacturing from around the world. Our research group, PDOL, is presenting three works: 1. "Online update of digital twin and its application to metal additive manufacturing" by Yifan Tang, July 23, 10:25 AM, Session 1101, Room 118. 2. "Adaptive online learning with physics-informed neural networks for enhanced thermal prediction in metal additive manufacturing" by Pouyan Sajadi, July 24, 10:25 - 10:45 AM, Session 1825, Room 213. 3. "Low-cost melt pool temperature prediction using visible light camera and machine learning techniques" by myself, July 25, 4:30 - 4:50 PM, Session 1106, Room 117. If you're attending, we would be honored to have you at our presentations. Let's connect and share insights at WCCM 2024. #WCCM2024 #ComputationalMechanics #AdditiveManufacturing #DigitalTwin #MachineLearning #PDOL #Research #Networking #Innovation

🌟 Exciting Announcement from CMC-Computers, Materials & Continua 🌟 The latest issue Vol. 81, No. 2 is now live! Dive into this collection of high-impact review papers covering cutting-edge topics in computational science, AI, and materials research. 📚 Featured articles include: 1️⃣ First Principles Calculations for Corrosion in Mg-Li-Al Alloys with Focus on Corrosion Resistance: A Comprehensive Review 2️⃣ A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learning 3️⃣ Computing Challenges of UAV Networks: A Comprehensive Survey 4️⃣ A Review of Generative Adversarial Networks for Intrusion Detection Systems: Advances, Challenges, and Future Directions 5️⃣ AI-Driven Pattern Recognition in Medicinal Plants: A Comprehensive Review and Comparative Analysis 6️⃣ AI-Powered Innovations in High-Tech Research and Development: From Theory to Practice 7️⃣ Discrete Choice Models and Artificial Intelligence Techniques for Predicting the Determinants of Transport Mode Choice—A Systematic Review 🔗 Read & cite now: https://lnkd.in/gvCrRSwZ 📢 Call for Papers CMC is actively seeking innovative submissions in computational science, materials research, and intelligent algorithms. Join us in shaping the future of interdisciplinary research! 🔗 Submit your work: https://lnkd.in/e3g27KmC #Research #ArtificialIntelligence #FederatedLearning #GANs #UAVNetworks #MaterialsScience

 ✅ Just accepted! ✅ 📣 We are thrilled to announce that a research paper authored by our PhD students, Yannick Kirchhoff, Maximilian Rokuss, and Saikat Roy has been accepted at #ECCV, a tier-1 research venue (CORE Ranking: A*) in Computer Vision! ❓ What’s the paper about? Segmenting thin tubular structures like vessels, nerves, roads, or concrete cracks is vital in computer vision but challenging with standard deep learning loss functions. These often compromise structural connectivity, leading to errors in downstream tasks like flow calculation and navigation. While existing topology-focused losses improve accuracy, they are computationally intensive, especially for 3D data and multi-class segmentation. 📝 Their paper, “Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures,” addresses this issue by using inexpensive CPU operations, cutting computational overheads by over 90% and excelling in multi-class segmentation. It achieves overall state-of-the-art results on five different datasets and tops the TopCoW and Toothfairy MICCAI challenge leaderboards. 👏 Huge congratulations to Yannick Kirchhoff, Maximilian R., Saikat Roy, and the team: Bálint Kovács, Constantin Ulrich, Tassilo Wald, Maximilian Zenk, supported by seniors Philipp Vollmuth, Jens Kleesiek, Fabian Isensee, and Klaus Maier-Hein! DKFZ Deutsches Krebsforschungszentrum HIDSS4Health - Helmholtz Information & Data Science School For Health 🔍 Curious about the details? Read the preprint: https://lnkd.in/eCpwQDad. #eccv #eccv24 #eccv2024 #deeplearning #ai #medicalai #medicalimage #computervision #cvpr #machinelearning

Check this out 🚀

🎥 Recap from VSC Users Day 2024: "CFD, HPC, and AI: Ingredients for the Next-Generation Flow Solvers" by Andrea Beck, University of Stuttgart 🎥 In this insightful session, Andrea explores the synergy of CFD, HPC, and AI in advancing flow solver technology. This presentation explores innovative methods that combine AI-driven approaches with CFD to enhance simulation accuracy, efficiency, and scalability, revolutionizing the future of fluid dynamics. Key topics covered: 🌊 Cutting-edge advancements in CFD modeling and simulation 🚀 The crucial role of HPC in scaling CFD applications 🤖 How AI is reshaping flow solver development for complex, multiscale environments Catch this presentation to gain a new perspective on the transformative potential of AI and HPC in fluid dynamics. ➡️ Watch the recorded presentation or access the PDF here: https://lnkd.in/eUF6TSS4 #supercomputer #hpc #data #cfd #AI #modeling #simulation #dynamics #event #brussels #belgium #europe #airbus #airline #session #innovate #presentation #application #ScientificResearch #Engineering

📢Excited to announce the publication of our latest research article titled “Physics-based reduced order modeling for uncertainty quantification of guided wave propagation using Bayesian optimization” in Engineering Applications of Artificial Intelligence! 🔍 Our study presents a machine learning-based reduced order model, annotated as BO-ML-ROM, used to decrease the computational time of the guided wave propagation simulation. The BO-ML-ROM is applied for forward uncertainty quantification of the guided waves in an aluminum plate and a composite panel under varying material properties. Moreover, a sensitivity analysis is performed using the variance-based Sobol’ indices and the Shapley additive explanations to study the individual contribution of each material property. Huge thanks to my co-authors and especially George Drakoulas for their invaluable contributions. 📚 You can read the full article here: https://lnkd.in/d9fa4Z99 #ML #Explainable_AI #Computational_mechanics #Reduced_order_models #Uncertainty_quantification #Sensitivity_analysis #Wave_propagation

I'm thrilled to return to Universidad Carlos III de Madrid this Friday, October 18th, to present a seminar "PredictiveIQ: Bridging #Physics and #AI for Industrial #Innovation." I'll be discussing how we're integrating advanced #MachineLearning and #PhysicsInformedAI models at PredictiveIQ to drive #IndustrialInnovation and overcome traditional AI limitations. The seminar will be streamed online. Find all the details below! Looking forward to connecting with fellow #Engineers, #Researchers, and #Students interested in the fusion of #AI and #Engineering.

This is a must watch thought-provoking webinar from PredictiveIQ given by Fermín Mallor showcasing the links between #physics and #AI. #engineering #acceleration #digitaltwins #performance #optimized #ml #predictiveanalytics #smalldata

SafeLegs Exoskeleton at the EXOberlin 2024 From April 15th to 17th, the IAS team showcased the SafeLegs exoskeleton demonstrator at the EXOberlin exposition and conference. The team featured Marius Häcker focused on integrating ROS2 for a comprehensive control solution and Arman A. Attar who contributed to the Deep Learning component for anomaly detection and fault mitigation. Philipp Grimmeisen, another PhD from our team, supported in presenting and engaging with industry professionals and academics. The modular lower-limb exoskeleton is central to Tagir Fabarisov’s PhD research, which aims to efficiently tailor Deep Learning anomaly detectors to complex robotic systems using digital twins. This approach has successfully reduced inference times while maintaining high error detection accuracy in complex environments. Key features demonstrated included: - Fault Injection experiments using MATLAB Simulink and FIBlock. - Reinforcement Learning to identify critical fault parameters on a Simulink Digital Twin. - Machine Learning to source and process data for sensor validation and training. This research is supported by funds from the Bundesanstalt für Arbeitsschutz und Arbeitsmedizin (BAuA, Germany), project F 2497. The original ExoLegs were developed by our colleagues from KIT, Ilshat Mamaev, and got the second live in our lab @ IAS for Fault Injection and Anomaly Detection.

I'm excited to share that I'll be presenting my work at the Computational Mechanics / 4th Pan American Congress on Computational Mechanics (WCCM-PANACM 2024) conference! During my presentation, I'll be discussing: - The application of physics-informed neural networks (PINNs) for metal additive manufacturing - Techniques to enhance temperature prediction accuracy and process adaptability - The integration of real-time data for improved thermal modeling and control in AM processes Title: "Adaptive online learning with physics-informed neural networks for thermal prediction in metal additive manufacturing" Authors: Pouyan Sajadi, Mostafa Rahmani Dehaghani, Yifan Tang, and Prof. Gary Wang Date & Time: July 24, 10:25 - 10:45 AM Session: 1825 Room: 213 If you're attending the conference, I would love for you to join my session. Alternatively, let's catch up over a coffee to discuss this research. Looking forward! #ComputationalMechanics #WCCM2024 #PANACM2024 #MetalAM #AdditiveManufacturing #PhysicsInformed #PINNs