检索结果-内蒙古大学图书馆

Molecule Generation from Input-Attributions over Graph Convolutional Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Savoia, Dylan Ragno, Alessio Capobianco, Roberto Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Sony AI

It is well known that Drug Design is often a costly process both in terms of time and economic effort. While good Quantitative Structure-Activity Relationship models (QSAR) can help predicting molecular properties without the need to synthesize them, it is still required to come up with new molecules to be tested. This is mostly done in lack of tools to determine which modifications are more promising or which aspects of a molecule are more influential for the final activity/property. Here we present an automatic process which involves Graph Convolutional Network models and input-attribution methods to generate new molecules. We also explore the problems of over-optimization and applicability, recognizing them as two important aspects in the practical use of such automatic tools. © 2022, CC BY.

关键词： Molecules

Physics-Informed Neural Networks: A Step Towards Data-Driven Optimization of Additive Manufacturing

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks: A Step Towards Data-Driven...

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Fabio Depaoli Stefano Felicioni Francesco Ponzio Alessandro Aliberti Enrico Macii Federica Bondioli Elisa Padovano Santa Di Cataldo Dept. of Control and Computer Engineering Politecnico di Torino Italy Dept. of Applied Science and Technology Politecnico di Torino Italy Interuniv. Dept. of Reg. and Urban Studies and Planning Politecnico di Torino Italy

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

Laser powder bed fusion (L-PBF) is the most popular Additive Manufacturing (AM) process for metals. It builds a 3D object layer-by-layer, by spreading metal powder on top of the previous layer and selectively melting it with a laser. Despite its many advantages, large-scale production may be hampered by the large number of process parameters and the challenges associated with their optimization. We propose an automated parameter selection approach based on process signatures extracted from a parameterized simulation of the process. Specifically, we outline a rapid data-driven simulation method based on Physics-Informed Neural Network (PINN). This approach involves training a neural network to solve the partial differential equation describing the process at varying values of a parameter of interest (for example, the laser power), thus eliminating the need for repeated Finite Elements Method (FEM) simulations. Our preliminary experiments demonstrate the feasibility of our approach.

关键词： Training Powders Three-dimensional displays Neural networks Metals Production Three-dimensional printing Finite element analysis Laser fusion Optimization

An Efficient GPU-based Implementation for Noise Robust Sound Source Localization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Zirui Takigahira, Masayuki Terakado, Naoya Gulzar, Haris Busto, Monikka Roslianna Eda, Takeharu Itoyama, Katsutoshi Nakadai, Kazuhiro Amano, Hideharu Dept. of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo Japan Honda Research Institute Japan Co. Ltd. Saitama Japan NTT Software Innovation Center Tokyo Japan Dept. of Information and Computer Science Keio University Kanagawa Japan

Robot audition, encompassing Sound Source Localization (SSL), Sound Source Separation (SSS), and Automatic Speech Recognition (ASR), enables robots and smart devices to acquire auditory capabilities similar to human hearing. Despite their wide applicability, processing multi-channel audio signals from microphone arrays in SSL involves computationally intensive matrix operations, which can hinder efficient deployment on Central Processing Units (CPUs), particularly in embedded systems with limited CPU resources. This paper introduces a GPU-based implementation of SSL for robot audition, utilizing the Generalized Singular Value Decomposition-based Multiple Signal Classification (GSVD-MUSIC), a noise-robust algorithm, within the HARK platform, an open-source software suite. For a 60-channel microphone array, the proposed implementation achieves significant performance improvements. On the Jetson AGX Orin, an embedded device powered by an NVIDIA GPU and ARM®Cortex™-A78AE v8.2 64-bit CPUs, we observe speedups of 4645.1× for GSVD calculations and 8.8× for the SSL module, while speedups of 2223.4× for GSVD calculation and 8.95× for the entire SSL module on a server configured with an NVIDIA A100 GPU and AMD EPYC™ 7352 CPUs, making real-time processing feasible for large-scale microphone arrays and providing ample capacity for real-time processing of potential subsequent machine learning or deep learning tasks. © 2025, CC BY-NC-ND.

关键词： Acoustic generators

Semi-Supervised GCN for learning Molecular Structure-Activity Relationships

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ragno, Alessio Savoia, Dylan Capobianco, Roberto Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Sony AI

Since the introduction of artificial intelligence in medicinal chemistry, the necessity has emerged to analyse how molecular property variation is modulated by either single atoms or chemical groups. In this paper, we propose to train graph-to-graph neural network using semi-supervised learning for attributing structure-property relationships. As initial case studies we apply the method to solubility and molecular acidity while checking its consistency in comparison with known experimental chemical data. As final goal, our approach could represent a valuable tool to deal with problems such as activity cliffs, lead optimization and de-novo drug design. © 2022, CC BY.

关键词： Graph neural networks

Enhancing 6G-Satellite Network Integration with Artificial Intelligence: A Future Communication Paradigm

学校读者我要写书评

暂无评论

Enhancing 6G-Satellite Network Integration with Artificial I...

Learning and Technology Conference (L&T)

作者： Ibrahim Salah Aziza I. Hussein Mostafa Wageh Lotfy Mohamed Mourad Mabrook Control and Computer Department College of Engineering Almaaqal University Basrah Iraq College of Engineering Energy and Technology Research Center Effat University Saudi Arabia Dept. of Process Control Technology Faculty of Technology and Education Beni-Suef University Beni-Suef Egypt Space Communication Dept. Faculty of Navigation Science & Space Technology Beni-Suef University Beni-Suef Egypt

ISBN: (数字)9798331532215

ISBN: (纸本)9798331532222

The integration of 6G networks and satellite communications is set to revolutionize global connectivity, offering seamless coverage across terrestrial and non-terrestrial environments. Artificial Intelligence (AI) is essential for improving this integration, addressing challenges such as dynamic resource management, latency reduction, and network optimization. AI techniques like machine learning, deep learning, and reinforcement learning offer innovative solutions to handle the complexities of 6G-satellite networks. These advancements promise to significantly improve network efficiency, enhance data transmission reliability, and ensure seamless connectivity across different areas. Potential use cases include smart cities, autonomous vehicles, and Internet of Things (IoT) applications, where AI-driven 6G-satellite integration will be crucial. The proposed AI-enhanced 6G-satellite framework not only addresses current challenges but also lays the groundwork for a resilient, scalable, and globally interconnected communication infrastructure, offering a promising future.

关键词： 6G mobile communication Wireless communication Smart cities Resource management Reliability Internet of Things Stakeholders Artificial intelligence Vehicle dynamics Satellite communications

Automated Optical Inspection for Quality control in PCBA assembly lines: a case study for Point of Sale Devices Production Lines

学校读者我要写书评

暂无评论

Automated Optical Inspection for Quality Control in PCBA ass...

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Kerem Aras Syed Saad Saif Alessandro Giuseppi Vedat Coskun R&D Center Token Financial Technologies Istanbul Türkiye Dept. of Computer Control and Management of Rome La Sapienza Rome Italy Dept. of Software Engineering Istanbul Atlas University Istanbul Turkiye

ISBN: (数字)9798350394634

ISBN: (纸本)9798350394641

This paper reports on the design and development of a customized Automated Optical Inspection (AOI) solution aimed at detecting defects in a production line related to the correct mounting of integrated circuits. Contrary to most solutions avail- able on the market, the developed system relies on deep learning to be able to perform detailed real-time visual inspections of components without the need to compare the captured photos with any reference images/golden sample. The proposed solution was designed to also provide good generalization capabilities, accommodating visual changes in the environment and in the structure of the component being produced. A custom testing machine was built in order to perform real-time inferences and validate the simulation results in a real-world setting.

关键词： Visualization Production Optical fiber networks Optical imaging Adaptive optics Real-time systems Automatic optical inspection

Fuzzy Logic controller for the Chemotherapy of Brain Tumor

学校读者我要写书评

暂无评论

Fuzzy Logic Controller for the Chemotherapy of Brain Tumor

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Muhammad Zubair Daniela Iacoviello Iqra Shafeeq Mughal Dept. Computer Control and Management Engineering Sapienza University of Rome Rome Italy Dept. di Ingegneria Electrica Electronica e Informatica DIEEI University of Catania Catania Italy

An advanced Fuzzy Logic controller (FLC) that considers all the states of the brain tumor system is designed for the chemotherapy treatment. A Mamdani-type FLC is proposed for dynamically controlling the chemotherapy drug for the tumor system; the chemotherapy treatment of brain tumors requires advanced strategies which mainly depend upon the severity of the tumor. In this work, the advanced FLC designed aims both at determining the amount of chemotherapy to eliminate tumor cells, and at preserving the minimum amount of healthy and immune cells. The controller's performance is verified using MATLAB software based on different control parameters, showing its effectiveness in reducing the tumor cells. It has shown favorable results in terms of steady-state error, rate of convergence, and amount of drug consumed.

关键词：

Computationally efficient predictive control based on ANN state-space models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hoekstra, Jan H. Cseppento, Bence Beintema, Gerben I. Schoukens, Maarten Kollár, Zsolt Tóth, Roland Dept. of Measurement and Information Systems The Budapest University of Technology and Economics Hungary The Dept. of Electrical Engineering The Eindhoven University of Technology Netherlands Institute for Computer Science and Control Budapest Hungary

Artificial neural networks (ANN) have been shown to be flexible and effective function estimators for identification of nonlinear state-space models. However, if the resulting models are used directly for nonlinear model predictive control (NMPC), the resulting nonlinear optimization problem is often overly complex due the size of the network, requires the use of high-order observers to track the states of the ANN model, and the overall control scheme exploits little of the structural properties or available autograd tools for these models. In this paper, we propose an efficient approach to auto-convert ANN state-space models to linear parameter-varying (LPV) form and solve predictive control problems by successive solutions of linear model predictive problems, corresponding to quadratic programs (QPs). Furthermore, we show how existing ANN identification methods, such as the SUBNET method that uses a state encoder, can provide efficient implementation of MPCs. The performance of the proposed approach is demonstrated via a simulation study on an unbalanced disc system. © 2023, CC BY-SA.

关键词： Neural networks

Study of the Influence of Rolling Modes on the Operation of Interconnected Electric Drives of a Rolling Mill 4

学校读者我要写书评

暂无评论

Study of the Influence of Rolling Modes on the Operation of ...

4th IEEE KhPI Week on Advanced Technology, KhPI Week 2023

作者： Tytiuk, Valerii Busher, Victor Kalinin, Alexey Chornyi, Oleksii Druzhinin, Valeriy Halushko, Dmytro Department of Electromechanics Kryvyi Rih National University Kryvyi Rih Ukraine Dept. of Electrical Engineering and Electronics National University "Odessa Maritime Academy" Odessa Ukraine Department of Informative computer systems Abylkas Saginov Karaganda Technical University NPJSC Karaganda Kazakhstan Institute of Electromechanics Energy Saving and Automatic Control Systems Kremenchuk Mykhailo Ostrogradskyi National University Kremenchuk Ukraine Department of Power Engineering Karaganda Industrial University NPJSC Temirtau Kazakhstan Dept. of Electrical Engineering Ukrainian State University of Science and Technologies Dnipro Ukraine

ISBN: (纸本)9798350395532

The paper is devoted to study of the influence of rolling modes on the performance of powerful interconnected electric drives of a hot rolling mill under the action of an electromagnetic coupling circuit between the electric drives of the roughing and finishing groups. The action of the electromagnetic coupling circuit manifests itself in the form of the influence of impact loads of synchronous electric drives on the angular velocity of direct current electric drives of the finishing group of the mill. The parameters of the electromagnetic coupling circuit are determined by the power supply scheme and equipment parameters. Values of impact loads applied to a synchronous motor depend on the rolling process parameters, in particular, the chemical composition of the rolled steel and the temperature of the ingot. The paper presents the results of calculating the rolling power for various rolling mode parameters. Using mathematical modeling in Simulink, numerical estimates of the influence of rolling modes on the magnitude of the voltage drop in the power supply unit and the drop in the angular velocity of the electric drive of the finishing group were obtained on the example of a wide-strip hot rolling mill 1700 of ArcelorMittal Temirtau JSC. © 2023 IEEE.

关键词： Hot rolling