Article
Engineering, Multidisciplinary
Jian Tang, Siddhant Kumar, Laura De Lorenzis, Ehsan Hosseini
Summary: We propose Neural Cellular Automata (NCA) for simulating microstructure development in the solidification process of metals. NCA, based on convolutional neural networks, can learn essential features of solidification and are much faster than conventional Cellular Automata (CA). Notably, NCA can make reliable predictions beyond their training range, indicating their understanding of the physics of solidification. While CA data is used for training in this study, NCA can be trained on any microstructural simulation data, such as phase-field models.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Seungchul Jung, Hyungwoo Lee, Sungmeen Myung, Hyunsoo Kim, Seung Keun Yoon, Soon-Wan Kwon, Yongmin Ju, Minje Kim, Wooseok Yi, Shinhee Han, Baeseong Kwon, Boyoung Seo, Kilho Lee, Gwan-Hyeob Koh, Kangho Lee, Yoonjong Song, Changkyu Choi, Donhee Ham, Sang Joon Kim
Summary: This paper presents a 64 x 64 crossbar array based on MRAM cells that overcomes the low-resistance issue and successfully implements analogue multiply-accumulate operations in artificial neural networks. The researchers achieved high classification accuracy and face detection using this array for tasks involving 10,000 digits.
Article
Forestry
Albina Jegorowa, Jaroslaw Kurek, Izabella Antoniuk, Wioleta Dolowa, Michal Bukowski, Pawel Czarniak
Summary: Based on improvements made in a drill wear recognition algorithm, this paper successfully distinguished between green and red classes to reduce misclassifications. The algorithm, using an ensemble of diverse models, performed best under specific conditions and achieved a relatively high overall accuracy.
WOOD SCIENCE AND TECHNOLOGY
(2021)
Review
Engineering, Biomedical
Mohd Faizal Ali Akhbar, Akmal Wani Sulong
Summary: Research has shown that improving drill bit design is a feasible and cost-effective solution to reduce bone drilling damage. This review emphasizes the importance of systemizing information on drill design and provides insights into advances in drill bit design and their impacts on bone damage.
ANNALS OF BIOMEDICAL ENGINEERING
(2021)
Article
Engineering, Mechanical
Jaroslaw Gonera, Oleksandr Vrublevskyi, Jerzy Napiorkowski
Summary: This study analysed and modelled damage to floorpan structures using artificial neural networks, identifying characteristics and stages of wear. Results indicated the possibility of predicting stages of floorpan wear development through network parameter adjustments and data analysis.
ENGINEERING FAILURE ANALYSIS
(2021)
Article
Mathematics
Fei Wei
Summary: This article discusses the importance of tourism human resource performance management and introduces the method of evaluating it through data mining technology. It also analyzes the existing problems in human resource management in the tourism industry and proposes solutions.
JOURNAL OF MATHEMATICS
(2022)
Article
Neurosciences
Mikolaj Kegler, Tobias Reichenbach
Summary: Transcranial alternating current stimulation (tACS) can modulate neuronal activity in the cerebral cortex, particularly in speech processing, but the exact mechanisms and effects are still poorly understood. A computational model study extended to investigate different stimulation waveforms found that current stimulation can alter speech decoding accuracy and identify parameters for enhancing speech processing in noise.
Review
Engineering, Mechanical
Xiaogang Zhang, Yali Zhang, Zhongmin Jin
Summary: Various medical devices face significant tribological issues that affect their performance and service life. Understanding and improving the bio-tribological behavior is essential for enhancing the functionality of these devices and advancing their development for future applications.
Article
Biodiversity Conservation
Guoli Zhang, Ming Wang, Kai Liu
Summary: This paper compares and analyzes the application of two feedforward neural network models (CNNs and MLPs) in global wildfire susceptibility prediction, and explores the interpretability of the CNNs model. By constructing response variables and monthly wildfire predictors, four MLPs and CNNs architectures were built, and five statistical measures were used to evaluate the prediction performance of the models. The contextual-based CNN-2D model was found to have the highest accuracy, while the MLPs model was more suitable for pixel-based classification, and the performance ranking of the four models was CNN-2D > MLP-1D > MLP-2D > CNN-1D.
ECOLOGICAL INDICATORS
(2021)
Article
Mathematics
Anass Bouchnita, Anastasia Mozokhina, Patrice Nony, Jean-Pierre Llored, Vitaly Volpert
Summary: This study proposes a methodology that uses computational modeling and machine learning to identify COVID-19 patients with a high thromboembolism risk. Through numerical simulations and mathematical modeling, it is shown that COVID-19 increases the size of thrombus formation and the peak concentration of thrombin generation. Finally, a dataset of hemostatic responses from virtual COVID-19 patients and healthy subjects is used to train machine learning algorithms for predicting the risk of thrombosis in COVID-19 patients.
Article
Computer Science, Information Systems
Bekhzod Olimov, Seok-Joo Koh, Jeonghong Kim
Summary: Image segmentation has significantly improved with the emergence of deep learning methods, particularly with the use of deep convolutional neural networks. The proposed AEDCN-Net model utilizes sophisticated preprocessing and rich model architecture to achieve superior performance in both accuracy and computational time, compared to existing state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Francisco Erivaldo Fernandes Jr, Gary G. Yen
Summary: The study introduces a two-phase algorithm, DNNDeepeningPruning, for automatically generating DNN architectures in the field of medical imaging diagnosis. This algorithm unifies the separate fields of DNN architecture searching and pruning under a single framework, and it has been tested on two medical imaging datasets with satisfactory results.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Engineering, Geological
Yinlin Ji, Lu Wang, Yanlong Zheng, Wei Wu
Summary: Thermo-mechanical drilling combines flame thermal treatment and rotary head drilling to achieve high penetration rates and low drill bit wear in granitic rocks. The Cerchar abrasivity test results indicate that overheating rocks may lead to increased abrasive minerals exposure and enhanced drill bit wear.
Article
Multidisciplinary Sciences
Qing Yang, Abdullah Al Mamun, Naeem Hayat, Mohd Fairuz Md Salleh, Gao Jingzu, Noor Raihani Zainol
Summary: Digital technologies empower users to manage their health and the mass adoption of wearable medical devices promotes confidence and convenience for users. This study empirically evaluates the factors influencing the adoption of wearable medical devices among Chinese adults and finds that perceived product value plays a mediating role in the intention to use WMDs. The results show that compatibility, usefulness, and technology accuracy have a significant positive effect on perceived product value.
Article
Computer Science, Artificial Intelligence
Guido Novati, Hugues Lascombes de Laroussilhe, Petros Koumoutsakos
Summary: Researchers have used multi-agent reinforcement learning to improve the discovery of turbulence models, with promising results. This approach can estimate unresolved subgrid-scale physics and generalize well across different grid sizes and flow conditions.
NATURE MACHINE INTELLIGENCE
(2021)
Article
Engineering, Mechanical
Miho Klaic, Zrinka Murat, Tomislav Staroveski, Danko Brezak
Review
Engineering, Biomedical
Goran Augustin, Tomislav Zigman, Slavko Davila, Toma Udilljak, Tomislav Staroveski, Danko Brezak, Slaven Babic
CLINICAL BIOMECHANICS
(2012)
Article
Automation & Control Systems
Josip Kasac, Branko Novakovic, Dubravko Majetic, Danko Brezak
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
(2008)
Article
Orthopedics
Goran Augustin, Slavko Davila, Toma Udilljak, Tomislav Staroveski, Danko Brezak, Slaven Babic
INTERNATIONAL ORTHOPAEDICS
(2012)
Article
Computer Science, Artificial Intelligence
Danko Brezak, Dubravko Majetic, Toma Udiljak, Josip Kasac
JOURNAL OF INTELLIGENT MANUFACTURING
(2012)
Article
Engineering, Mechanical
Danko Brezak, Dubravko Majetic, Toma Udiljak, Josip Kasac
JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY
(2010)
Article
Automation & Control Systems
Josip Kasac, Dubravko Majetic, Danko Brezak
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2018)
Article
Engineering, Biomedical
Zoran Domitran, Danko Brezak, Tomislav Staroveski, Miho Klaic, Tomislav Bruketa
MEDICAL ENGINEERING & PHYSICS
(2018)
Article
Engineering, Mechanical
Miho Klaic, Danko Brezak, Tomislav Staroveski, Zrinka Murat
TRANSACTIONS OF FAMENA
(2019)
Article
Engineering, Multidisciplinary
Tomislav Staroveski, Danko Brezak, Toma Udiljak
TEHNICKI VJESNIK-TECHNICAL GAZETTE
(2013)
Proceedings Paper
Computer Science, Artificial Intelligence
Tomislav Bacek, Josip Kasac, Dubravko Majetic, Danko Brezak
2012 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE)
(2012)
Proceedings Paper
Computer Science, Artificial Intelligence
Danko Brezak, Tomislav Bacek, Dubravko Majetic, Josip Kasac, Branko Novakovic
2012 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR FINANCIAL ENGINEERING & ECONOMICS (CIFER)
(2012)
Proceedings Paper
Automation & Control Systems
Danko Brezak, Dubravko Majetic, Toma Udiljak, Tomislav Staroveski
ANNALS OF DAAAM FOR 2009 & PROCEEDINGS OF THE 20TH INTERNATIONAL DAAAM SYMPOSIUM
(2009)
Article
Automation & Control Systems
J Kasac, B Novakovic, D Majetic, D Brezak
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2006)