Research on Personnel Image Segmentation Based on MobileNetV2 H-Swish CBAM PSPNet in Search and Rescue Scenarios by Di Zhao, Weiwei Zhang, Yuxing Wang

“…By substituting ResNet50 with the more efficient MobileNetV2 as the model backbone, the computational complexity is significantly reduced. Furthermore, replacing the ReLU6 activation function in MobileNetV2 with H-Swish enhances segmentation accuracy without increasing the parameter count. …”
Get full text

INTEGRATING ACOUSTIC MODULATION AND LISTENER DEMOGRAPHICS FOR ENHANCED PODCAST EMOTIONAL RESONANCE by Jun Ji, Kotchaphan Youngmee, Khachakrit Liamthaisong, Narisara Brikshavana

“…The research contradicts conventional views in previous studies by including an overall framework for the improvement of auditory features in podcasts. The underlying framework combines analytical methods, computational modelling, and machine learning in order to systematically enhance audio quality and consequently increase listener engagement.  …”
Get full text

Innovative Ghost Channel Spatial Attention Network with Adaptive Activation for Efficient Rice Disease Identification by Yang Zhou, Yang Yang, Dongze Wang, Yuting Zhai, Haoxu Li, Yanlei Xu

“…Additionally, the model incorporates the Ghost Module as a replacement for traditional 1 × 1 convolutions, further reducing computational overhead. Innovatively, we introduce a Channel Spatial Attention Mechanism (CSAM) that significantly enhances feature extraction and generalization aimed at rice disease detection. …”
Get full text

TLDDM: An Enhanced Tea Leaf Pest and Disease Detection Model Based on YOLOv8 by Jun Song, Youcheng Zhang, Shuo Lin, Huijie Han, Xinjian Yu

“…Initially, the C2f-Faster-EMA module is employed to reduce the number of parameters and model complexity while enhancing image feature extraction capabilities. …”
Get full text

Bioinformatic Analysis of WNT Family Proteins by Konstantin Midlovets, Natalia Volkova, Mykyta Peka

“…Furthermore, in silico modeling and molecular dynamics simulations were employed to study the tertiary structure of WNT2B and to assess the significance of O-acylation at serine for the behavior of the mature protein in an aqueous environment. Thus, using computational approaches, new data were obtained on the structural features and dynamic properties of this group of regulatory proteins.…”
Get full text

Flood Image Classification using Convolutional Neural Networks by Olusogo Julius Adetunji, Ibrahim Adepoju Adeyanju, Adebimpe Omolayo Esan, Adedayo Aladejobi Sobowale Sobowale

Get full text

Lightweight and robust ship detection method driven by self-attention mechanism by Feng MA, Zihui SHI, Jie SUN, Chen CHEN, Xianbin MAO, Xinping YAN

Get full text

Online Traffic Crash Risk Inference Method Using Detection Transformer and Support Vector Machine Optimized by Biomimetic Algorithm by Bihui Zhang, Zhuqi Li, Bingjie Li, Jingbo Zhan, Songtao Deng, Yi Fang

Get full text

PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection by Weijia Chen, Jiaming Liu, Tong Liu, Yaoming Zhuang

“…Finally, we integrate an Efficient Up-Convolution Block to sharpen decoder feature maps, enhancing small object recall with minimal computational overhead. …”
Get full text

Fracture identification and 3D reconstruction of coal-rock combinations based on VRA-UNet network by Dengke WANG, Longhang WANG, Yaguang QIN, Le WEI, Tanggen CAO, Wenrui LI, Lu LI, Xu CHEN, Yuling XIA

“…Firstly, the VGG16 module is used as the backbone feature extraction network to enhance the model’s generalization ability and prevent the initialization of model parameters from being too random. …”
Get full text

TransferBAN-Syn: a transfer learning-based algorithm for predicting synergistic drug combinations against echinococcosis by Haitao Li, Haitao Li, Yuanyuan Chu, Yuanyuan Chu, Liyuan Jiang, Liyuan Jiang, Lei Li, Lei Li, GuoDong Lv, Yuansheng Liu, Chunhou Zheng, Chunhou Zheng, Yansen Su, Yansen Su

“…TransferBAN-Syn is designed and initially trained on the abundant data from the 21 parasitic diseases, which serves as the source domain. The parameters in the feature representation modules of drug interactions and diseases are preserved from this source domain, and those in the prediction module are then fine-tuned to specifically identify the synergistic drug combinations for echinococcosis in the target domain. …”
Get full text

Digital Twin-Supported Battery State Estimation Based on TCN-LSTM Neural Networks and Transfer Learning by Kai Zhao, Ying Liu, Yue Zhou, Wenlong Ming, Jianzhong Wu

“…In this study, we propose a DT-supported battery state estimation method, in collaboration with the temporal convolutional network (TCN) and the long short-term memory (LSTM), to address the challenge of feature extraction. Firstly, we introduce a 4-layer hierarchical DT to overcome computational and data storage limitations in conventional battery management systems. …”
Get full text

Machine and Deep Learning–driven Angular Momentum Inference from BHEX Observations of the n = 1 Photon Ring by Joseph Farah, Jordy Davelaar, Daniel Palumbo, Michael Johnson, Jonathan Delgado

“…Developing this capability can be achieved by building a sample of n = 1 subring simulations, as well as by performing feature extraction on this high-volume sample to track changes in the geometry, which presents significant computational challenges. …”
Get full text

Shape factor analysis of water and aluminium oxide nanoparticles in a porous medium with slip effects by Prasun Choudhary, K. Loganathan, Kavita Jat, Kalpna Sharma, S. Eswaramoorthi

Get full text

Rumor Detection Based on Knowledge Enhancement and Graph Attention Network by Wanru Wang, Yuwei Lv, Yonggang Wen, Xuemei Sun

Get full text

HUMAn, a Real-Time Evolutive Patient Model for Major Incident Simulation: Development and Validation Study by Maxence Laurent, Arnaud Jaccard, Laurent Suppan, Elio Erriquez, Xavier Good, Eric Golay, Dominique Jaccard, Mélanie Suppan

“…During the relevance phase, the team defined the needed features of the model: clinically realistic, able to compute the evolution of prehospital vital signs, yet simple enough to allow real-time computation for several simulated patients on regular computers or tablets. …”
Get full text

Beyond labels: determining the true type of blood gas samples in ICU patients through supervised machine learning by Johan Helleberg, Anna Sundelin, Johan Mårtensson, Olav Rooyackers, Ragnar Thobaben

Get full text

Binocular stereo vision-based relative positioning algorithm for drone swarm by Qing Cheng, Yazhe Wang

“…Finally, the extracted feature points from UAVs are input into a binocular vision localization model to compute their three-dimensional coordinates. …”
Get full text

Sub-milliwatt threshold power and tunable-bias all-optical nonlinear activation function using vanadium dioxide for wavelength-division multiplexing photonic neural networks by Jorge Parra, Juan Navarro-Arenas, Pablo Sanchis

“…Abstract The increasing demand for efficient hardware in neural computation highlights the limitations of electronic-based systems in terms of speed, energy efficiency, and scalability. …”
Get full text

Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection by Hang Fei, Hongfu Zuo, Han Wang, Yan Liu, Zhenzhen Liu, Xin Li

“…The demonstrated reductions in computational effort and parameter count underscore the model’s efficiency, fortifying its relevance in broader contexts.…”
Get full text