Dielectric constant prediction in polymers: A chemical structure based approach by S. Sharifi, S. Bonardd, L.A. Miccio

“…We employed a curated dataset of nearly 1000 polymeric materials, from which we extracted unit cell parameters, atomic features, and tokenized atom-wise descriptors. …”
Get full text

Investigation of Geometric Characteristics on the Lubricant Performance of Thrust Bearing with Cavitation by L. Kailei, C. Jiayuan, Z. Haoran, Z. Lin, W. Xuze, C. Yu

“…The simulation model considers the impact of geometric characteristics and operational conditions, including the viscoelastic effect, transformation feature, and flow state, to enhance calculation ability. …”
Get full text

A Deep Learning Approach for Extracting Cyanobacterial Blooms in Eutrophic Lakes From Satellite Imagery by Nan Wang, Zhenyu Tan, Chen Yang, Jinge Ma, Hongtao Duan

“…MBAUNet was crafted as a lightweight network by integrating elements of MobileNetV3 and UNet, reducing learnable parameters and training time, while the introduction of spatial and channel attentions enhanced feature extraction. …”
Get full text

Microstrip Patch Antenna Design Using a Four-Layer Feed Forward Artificial Neural Network Trained by Levenberg-Marquardt Algorithm by Jitu Prakash Dhar, Maodudul Hasan, Eisuke Nishiyama, Ichihiko Toyoda

“…Therefore, patch antennas with three fundamental geometrical shapes can be designed using the same ANN removing computational complexity for the designers. The ANN contains a multi-layered network architecture that learns and generalizes complex patterns through the LM algorithm and weight optimization based on the datasets without any feature extraction like Deep Neural Network (DNN). …”
Get full text

IEDSFAN: information enhancement and dynamic-static fusion attention network for traffic flow forecasting by Lianfei Yu, Ziling Wang, Wenxi Yang, Zhijian Qu, Chongguang Ren

Get full text

24 Hours Ahead Forecasting of the Power Consumption in an Industrial Pig Farm Using Deep Learning by Boris Evstatiev, Nikolay Valov, Katerina Gabrovska-Evstatieva, Irena Valova, Tsvetelina Kaneva, Nicolay Mihailov

Get full text

Traffic safety and dynamic properties of the bridge deck of high-speed railway lines by V. Yu. Polyakov, Dang Ngoc Thanh

“…The urgent task is to ensure the sustainable motion of the wheel along the rail over the bridges in high-speed traffic. A feature of high-speed lines (HS lines) is the practical achievement of critical speeds that cause resonance of bridge deck structures. …”
Get full text

Machine Learning Models for Predicting Seismic Response of a Novel Two-Stage Friction Pendulum Isolated Bridge Structure by Hanzlah Akhlaq, Tianbo Peng, Kawsu Jitteh, Muhammad Salman Khan

“…Furthermore, a comparison of different surrogate models was conducted for global feature interpretation, while SHAP analysis was used for local interpretation to identify the influence of input parameters on individual structural responses. …”
Get full text

Development of the structure of a computerized information and measurement system based on the analysis of the problems of using an asynchronous electric drive in pumping equipment by Yu.O. Podchashynskyi, Ya.V. Mahaletskyi

“…The article analyzes the features of using an asynchronous electric drive in pumping equipment. …”
Get full text

An efficient method for early Alzheimer’s disease detection based on MRI images using deep convolutional neural networks by Samia Dardouri

Get full text

Experimental assessment and data-driven hybrid machine learning quantification with parametric optimization of compressive strength of ceramic waste concrete by Mihir Mishra, Md. Habibur Rahman Sobuz, Md. Kawsarul Islam Kabbo, M Jameel, Turki S. Alahmari, Naim Ahmad, Md. Munir Hayet Khan

Get full text

Variational autoencoder-based multipath clustering algorithm for terahertz channels by HAO Xinyu, LIAO Xi, ZHENG Xiangquan, WANG Yang, LIN Feng, CHEN Qianbin, ZHANG Jie

“…To address the shortcomings of multipath clustering algorithms in terahertz channel modeling, particularly in terms of multidimensional parameter adaptability and unsupervised feature separation, a variational autoencoder-based latent space multipath clustering (VAE-LMC) model was proposed. …”
Get full text

A multi-dimensional data-driven ship roll prediction model based on VMD-PCA and IDBO-TCN-BiGRU-Attention by Huifeng Wang, Jianchuan Yin, Jianchuan Yin, Nini Wang, Lijun Wang, Lijun Wang

Get full text

An improved method of AUD-YOLO for surface damage detection of wind turbine blades by Li Zou, Anqi Chen, Xinhua Yang, Yibo Sun

“…Firstly, the ADown module is integrated into the YOLOv8 backbone to replace some conventional convolutional down-sampling operations, decreasing the parameter count while boosting the model’s capability to extract image features. …”
Get full text

The First-Principles Investigation of Structural Stability, Mechanical, Vibrational, Thermodynamic, and Optical Properties of CaHfS3 for Optoelectronic Application by Mulugetta Kassa, Nebiyu Debelo, Menberu Woldemariam

“…In this study, the structural, electronic, elastic, phonon vibration, thermodynamic features, and optical properties of the orthorhombic phase of (space group Pnma) CaHfS3 were examined by first-principles calculations utilizing the plane wave ultrasoft pseudopotentials in generalized gradient approximations (GGAs) and with Hubbard on-site correction (DFT + U). …”
Get full text

Research on the Classification of Sun-Dried Wild Ginseng Based on an Improved ResNeXt50 Model by Dongming Li, Zhenkun Zhao, Yingying Yin, Chunxi Zhao

“…First, each convolutional layer in the Bottleneck structure is replaced with the corresponding Ghost module, reducing the model’s computational complexity and parameter count without compromising performance. …”
Get full text

Dynamic equivalent modelling for active distributed network considering adjustable loads charging characteristics by Jingwen Wang, Jiehui Zheng, Zhigang Li, Qing‐Hua Wu

“…Subsequently, a four‐layer, tri‐stage deep reinforcement learning approach is used to solve the relevant key parameters of the proposed equivalent model. The method proposed in this paper fully utilizes the superiority of reinforcement learning in decision making, while the method combines the excellent feature extraction capability of deep learning. …”
Get full text

MFD-KD: Multi-Scale Frequency-Driven Knowledge Distillation by Tao Dai, Rongliang Huang, Hang Guo, Jinbao Wang, Bo Li, Zexuan Zhu

“…Knowledge Distillation (KD), which focuses on transferring semantic knowledge from a parameter-heavy teacher network to a more compact student network, has been widely and successfully used across plenty of computer vision tasks like image/video recognition and segmentation. …”
Get full text

AI-driven hybrid rehabilitation: synergizing robotics and electrical stimulation for upper-limb recovery after stroke by Ismail Ben Abdallah, Ismail Ben Abdallah, Yassine Bouteraa, Yassine Bouteraa, Ahmed Alotaibi, Ahmed Alotaibi

Get full text

Use of Smartphone-Based Experimental Data for the Calibration of Biodynamic Spring-Mass-Damper (SMD) Pedestrian Models by Chiara Bedon, Martina Sciomenta, Alessandro Mazelli

“…Among various walking features, the vertical reaction force that a pedestrian transfers to the supporting structure during motion is a key input for design, but results from the combination of multiple influencing parameters and dynamic interactions. …”
Get full text