Multimodal rapid identification of growth stages and discrimination of growth status for Morchella by Ning Jia, Chunjun Zheng

“…During the rapid identification process of the growth stage of Morchella, the Multi Stage Vision Enhanced Position Encoding Vision Transformer (MS-EP ViT) model is adopted. …”
Get full text

An EWS-LSTM-Based Deep Learning Early Warning System for Industrial Machine Fault Prediction by Fabio Cassano, Anna Maria Crespino, Mariangela Lazoi, Giorgia Specchia, Alessandra Spennato

“…This research details the creation and evaluation of an EWS that incorporates deep learning methods, particularly using Long Short-Term Memory (LSTM) networks enhanced with attention layers to predict critical machine faults. The proposed system is designed to process time-series data collected from an industrial printing machine’s embosser component, identifying error patterns that could lead to operational disruptions. …”
Get full text

SUPERMAGOv2: Protein Function Prediction via Transformer Embeddings and Bitscore-Weighted Features by Gabriel Bianchin de Oliveira, Helio Pedrini, Zanoni Dias

“…Our machine learning-based model (SUPERMAGOv2) utilizes transformer-based backbones to extract features from multiple layers, which are then processed by six multilayer perceptrons that incorporate a novel bitscore-weighted input derived from DIAMOND alignments, and by an image classification model that converts the extracted feature vectors into images. …”
Get full text

Innovative data augmentation strategy for deep learning on biological datasets with limited gene representations focused on chloroplast genomes by Mohammad Ali Abbasi-Vineh, Shirin Rouzbahani, Kaveh Kavousi, Masoumeh Emadpour

“…A hybrid model of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) layers was applied across augmented datasets comprising genes and proteins from eight microalgae and higher plant chloroplasts. …”
Get full text

A Coupling Error Compensation Approach Concerning Constrained Space Coordinate Precision of a Heavy-Load Longitudinal and Transversal Swing Table by Manxian Liu, Rui Bao, Shuo Li, Liang Ji, Suozhuang Li, Xiaoqiang Yan, Wei Li

“…The key geometric parameters of pitch and roll layers are determined according to the machining process and assembly relationship, and the kinematic model is modified to effectively reduce the impact of contour error on the system’s accuracy. …”
Get full text

Petrogenetic evidences in geodynamics and placement of Nordoz intrusive masses in Alborz-Azerbaijan structural zone by Shahryar Mahmoudi, Shiva Lavi, Shohreh Hassanpour, Amir Ali Tabakh Shabani, Mehran Yegane Far

“…These processes have occurred as a result of events such as slab failure or lithosphere layer separation during the Eocene-Oligocene period, which have resulted in some degrees of partial melting. …”
Get full text

Research on LiDAR Clear Air Turbulence Recognition Based on Improved SE-ResNet50 by Zibo ZHUANG, Jun CHEN, Peilin HE, Hongying ZHANG, Guohua JIN, Xiong LUO

“…To address the issue of LiDAR’s low turbulence recognition rate at airports in low-altitude areas, a clear air turbulence recognition method based on an improved Squeeze-and-Excitation Residual Network with 50 layers (SE-ResNet50) is proposed. By introducing the squeeze-and-excitation module and improving the network structure, the model’s excessive sensitivity to feature location is reduced, thereby enabling the network to selectively highlight useful information features during the learning process. …”
Get full text

Explainable light-weight deep learning pipeline for improved drought stress identification by Aswini Kumar Patra, Aswini Kumar Patra, Lingaraj Sahoo

“…This visualization approach sheds light on the internal workings of the deep learning model, often regarded as a ”black box”. By revealing the model’s focus areas within the images, it enhances interpretability and fosters trust in the model’s decision-making process.Results and discussionOur proposed framework achieves superior performance, particularly with the DenseNet121 pre-trained network, reaching a precision of 97% to identify the stressed class with an overall accuracy of 91%. …”
Get full text

Graph-based reinforcement learning for software-defined networking traffic engineering by Jingwen Lu, Chaowei Tang, Wenyu Ma, Wenjuan Xing

“…GRL-TE introduces three key innovations: (1) TopoFlowNet, a graph neural network architecture that models WANs as bipartite graphs with edge nodes representing physical links and path nodes representing candidate paths, enabling efficient bidirectional information propagation through GINConv layers while MLP modules handle collaborative relationships among paths serving the same demand; (2) A one-step A2C mechanism specifically designed for TE with immediate reward structure, eliminating the need for future state estimation and significantly simplifying training; (3) Integration of ADMM as a post-processing step to iteratively reduce constraint violations while improving solution quality. …”
Get full text

Restoration-oriented multi-tiered framework for ecosystem degradation diagnosis: a coastal bay case study by Dian Zhang, Weiwei Yu, Bin Chen, Huamei Huang, Jianji Liao, Lingyang Feng, Guangcheng Chen, Zhiyuan Ma, Qinhua Fang, Shunyang Chen, Bin Xie, Zhiyi Kan, Shangke Su, Ge Feiyang, Hanmeng Yuan

“…Although many approaches have been proposed to identify the degradation status of an ecosystem, the heavy data burden required lacks targeted degradation information to inform such decision-making restoration policies.MethodsThis study proposes a multi-tiered decision-making framework to diagnose ecosystem degradation based on the most common restoration models that link degradation to restoration. The degradation diagnosis process can be executed step-by-step (i.e., in a physical to chemical to biological order). …”
Get full text

Corneal safety assessment of germicidal far UV-C radiation by Daniela F. Zamudio Díaz, Patricia Hülse, Johannes Schleusener, Anja A. Kühl, Anna Lena Klein, Loris Busch, Lalita Roscetti, Martin Guttmann, Sascha Rohn, Thomas A. Fuchsluger, Martina C. Meinke

Get full text

Evaluation of Evaporative Degradation of Arc Torch Cathodes in Hydrocarbon-Containing Plasmas for Spraying, Thermal Protection Testing and Related Technologies by A. V. Gorbunov, V. A. Gorbunova, O. G. Devoino, G. Petraconi Filho, A. A. Halinouski

“…This effect is inconsistent with measured cathode composition, which shows a probability of nonequilibrium character of thermal and diffusion processes in near-electrode plasma and surface layer (~1 mm) of the electrode, at least in the modes with arc current in the torch near 300 A. …”
Get full text

From design to 3D printing: A proof-of-concept study for multiple unit particle systems (MUPS) printed by dual extrusion fused filament fabrication by Lee Roy Oldfield, Aaron Felix Christofer Mentrup, Stefan Klinken-Uth, Tobias Auel, Anne Seidlitz

“…In this study, a modular four-particle-layered tablet computer model containing 196 cylindrical particles with a diameter of 1.4 mm, a height of 1.0 mm and a total tablet size of 22.6 × 8.5 × 6.0 mm is proposed. …”
Get full text

A microenvironment-modulating dressing with proliferative degradants for the healing of diabetic wounds by Lianghui Cheng, Zhiyong Zhuang, Mingming Yin, Yuan Lu, Sujuan Liu, Minle Zhan, Liyuan Zhao, Zhenyan He, Fanling Meng, Sidan Tian, Liang Luo

“…Here we report a rational double-layered dressing design based on chitosan and a degradable conjugated polymer polydiacetylene, poly(deca-4,6-diynedioic acid) (PDDA), that can meet this intricate requirement. …”
Get full text

Integrating unsupervised domain adaptation and SAM technologies for image semantic segmentation: a case study on building extraction from high-resolution remote sensing images by Mengyuan Yang, Rui Yang, Min Wang, Haiyan Xu, Gang Xu

“…During the training process, an iterative training strategy and a noise-weighted loss are applied to further improve the accuracy of the model on unlabeled images. …”
Get full text

Developing tunable machine learning workflow for traffic analysis in SDN by Samaan Sama Salam, Jeiad Hassan Awheed

“…Traffic monitoring is a critical issue in networking in general, especially in SDN due to its layered architecture in which the control plane represents a single point of failure. …”
Get full text

Management of energy-efficient technologies of certification system in forestry industry by Oleynik Pavel, Kazaryan Ruben, Doroshin Ivan, Kisel Vadim

“…The purpose of the study is to assess the positive impact of certification standards on the final characteristics of load-bearing layers of asphalt concrete pavements on the basis of statistical information obtained in the process of using certification standards. …”
Get full text

Enhancing Neural Network Interpretability Through Deep Prior-Guided Expected Gradients by Su-Ying Guo, Xiu-Jun Gong

“…In these high-stakes applications, understanding the decision-making processes of models is essential for ensuring trust and safety. …”
Get full text

Critical analysis and digital documentation of the transformations of heritage buildings by İrem Bekar, Izzettin Kutlu

“…Today, this building is remarkable for its cultural transformation and historical layers. The study aims to address the transformation processes of the Hagia Sophia Mosque in the light of international conservation criteria, to understand the history of the building and to reveal the digital perspectives of this historical place. …”
Get full text

Incomplete mass closure in atmospheric nanoparticle growth by Dominik Stolzenburg, Nina Sarnela, Federico Bianchi, Jing Cai, Runlong Cai, Yafang Cheng, Lubna Dada, Neil M. Donahue, Hinrich Grothe, Sebastian Holm, Veli-Matti Kerminen, Katrianne Lehtipalo, Tuukka Petäjä, Juha Sulo, Paul M. Winkler, Chao Yan, Juha Kangasluoma, Markku Kulmala

“…However, the huge variety of different organics present in the continental boundary layer makes it challenging to predict nanoparticle growth rates from gas-phase measurements. …”
Get full text