Optimized DenseNet Architectures for Precise Classification of Edible and Poisonous Mushrooms by Jay Prakash Singh, Debolina Ghosh, Jagannath Singh, Anurag Bhattacharjee, Mahendra Kumar Gourisaria

“…Methods The study analyzes the basic DenseNet-121 model as well as a modified DenseNet-121 with frozen upper layers which preserve important lower level features. …”
Get full text

Parametric evaluation as a tool for evaluating shell geodesic domes. Modelling the Fuller Dome with ReSa mobile recreational facility panels by Anna Berbesz, Kajetan Sadowski, Jakub Onyszkiewicz

“…Combining a system of layered self-supporting panels with the geometry of geodesic domes was one of the significant construction and material challenges as part of the ReSa research and the respective implementation project carried out at the Wroclaw University of Technology in 2021–2023 as part of a competition organized by The National Center of Research and Development. …”
Get full text

Application of deep neural networks to forecast 60Co soil to plant transfer factor values based in pedological parameters by Lucas Iwahara, Cláudio Pereira, Maria Angélica Wasserman, Flávia Bartoly

“…Learning sets were structured and due to the complexity of the search space and the small amount of available data, deep ANN with regularization (dropout) layers were required to achieve good prediction and avoid overfitting. …”
Get full text

Decision Support System to Solve Single-Container Loading Problem Considering Practical Constraints by Natalia Romero-Olarte , Santiago Amézquita-Ortiz, John Willmer Escobar, David Álvarez-Martínez

“…The constructive phase builds the loading pattern in vertical layers (columns or walls), while respecting all practical constraints. …”
Get full text

Detection and Recognition of Underwater Acoustic Communication Signal Under Ocean Background Noise by Mengyi Li, Jilong Li, Haihong Feng

“…Both methods exhibit strong generalization ability, feature fewer model parameters, and have lower computational complexity.…”
Get full text

Le fonctionnement hydrodynamique et géochimique des aquifères jurassique et crétacé dans le bassin versant du Nahr El-Bared (Liban Nord) by Souheil Awad, Douha Akkari

“…This study exposes the complexity of the hydrological functioning of the two Jurassic and Cretaceous karstic systems in the El-Bared watershed. …”
Get full text

A University-Stakeholder Collaborative Approach to Designing Early Childhood Mentor Teacher Training by Edith Nicolas, Cristina Guarrella, Parian Madanipour

“…These dynamic processes of information sharing resulted in a layering of knowledges that led to the creation of genuinely contextual professional learning resources. …”
Get full text

Contextual ITSM Adoption Across Educational Levels: A University and a Secondary School in Jakarta by Marcel Marcel, Nur Chalik Azhar

“…Three primary implementation challenges emerged: resource limitations, structural complexity, and cultural resistance. Based on these findings, we propose a phased transformation model (Stabilization, Standardization, Development) accommodating "layered maturity" - allowing institutions to operate at different maturity levels across ITSM domains rather than uniform advancement. …”
Get full text

Parametric evaluation and predictive modelling of formability in μ-SPIF process by Sahu Vijay Kumar, Das Purnendu, Adhikary Avishek, Bandyopadhyay Kaushik

“…Localised deformation in terms of bending stretching and through thickness shears add the complexity in SPIF which intensifies in case of µ-SPIF due to size effect. …”
Get full text

RDM-YOLO: A Lightweight Multi-Scale Model for Real-Time Behavior Recognition of Fourth Instar Silkworms in Sericulture by Jinye Gao, Jun Sun, Xiaohong Wu, Chunxia Dai

“…Second, standard convolutional layers are replaced with distribution shifting convolution (DSConv), leveraging dynamic sparsity and quantization mechanisms to reduce computational complexity. …”
Get full text

Inverse binary optimization of convolutional neural network in active learning efficiently designs nanophotonic structures by Jaehyeon Park, Zhihao Xu, Gyeong-Moon Park, Tengfei Luo, Eungkyu Lee

“…However, due to their second-order nature, FM-based surrogate functions struggle to fully capture the complexity of the hypervolume. In this paper, we introduce an inverse binary optimization (IBO) scheme that optimizes a surrogate function based on a convolutional neural network (CNN) within an active learning framework. …”
Get full text

Optimised Extension of an Ultra-Low-Power RISC-V Processor to Support Lightweight Neural Network Models by Qiankun Liu, Sam Amiri

“…Three custom instructions are proposed for convolution, pooling, and fully connected layers, integrating XNOR, POPCOUNT, and threshold operations. …”
Get full text

A Multi-Scale Deep Learning Framework Combining MobileViT-ECA and LSTM for Accurate ECG Analysis by Abduljabbar S. Ba Mahel, Mehdhar S. A. M. Al-Gaashani, Reem Ibrahim Alkanhel, Dina S. M. Hassan, Mohammed Saleh Ali Muthanna, Ammar Muthanna, Ahmed Aziz

“…However, the variability and complexity of ECG signals make AF classification challenging, highlighting the need for more accurate and reliable methods. …”
Get full text

Tomography Method of Cemented Sand Based on Constant Gradient Coded 1D T2 Spectrum by WU Turong, CHEN Jinding, ZHANG Qun, ZHAO Xichun, GUO Minling, CHENG Fanggui

“…Nuclear magnetic resonance (NMR) imaging is an advanced technology for core-scale heterogeneity analysis. Affected by rock complexity and encoding technology, existing methods are not really effective. 2D/3D nuclear magnetic resonance technology based on gradient fields is easy to image but has a low signal-to-noise ratio. …”
Get full text

Transferring Fire Modelling Sciences into Augmented Reality: A Realistic and Safe Reconstructed Fire Scenario by Jason C. S. Wong, Peter S. P. Wong, Raj Das, Anthony C. Y. Yuen, Sherman C. P. Cheung

“…This enables a high-fidelity representation of flame structures and smoke layers, providing an interactive tool for studying evacuee behaviour. …”
Get full text

Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network by Jian Song, Yingzhong Tian, Xiang Wan

“…In order to solve these problems, this study combines traditional visual detection methods and deep neural network technology to propose a transfer learning multi-channel fusion decision network without significantly increasing the number of network layers or the structural complexity. Each channel of the network is designed according to the characteristics of different types of defects. …”
Get full text

A Joint Network of 3D-2D CNN Feature Hierarchy and Pyramidal Residual Model for Hyperspectral Image Classification by Hongwei Wei, Yufan Wang, Yu Sun, Jianfeng Zheng, Xiaodong Yu

“…However, the performance of many CNN models is constrained by the complexity of hyperspectral pictures. The typical 2D-CNN method is unable to capture the discriminant spectral-spatial features due to the massive dimensionality of HSI data as well as potential noise and redundancy, while the 3D-CNN method significantly increases the computational burden of the model. …”
Get full text

WaterSAM: Adapting SAM for Underwater Object Segmentation by Yang Hong, Xiaowei Zhou, Ruzhuang Hua, Qingxuan Lv, Junyu Dong

“…Inspired by Low-Rank Adaptation (LoRA), WaterSAM incorporates trainable rank decomposition matrices into the Transformer’s layers, specifically enhancing the image encoder. …”
Get full text

Improving P-Doped DBRs Operation at Cryogenic Temperatures: Investigating Different Mirror Geometry by Behzad Namvar, Topi Uusitalo, Heikki Virtanen, Mircea Guina, Jukka Viheriala

“…Furthermore, we explored different mirror geometries to optimize both current flow and the growth complexity of the DBR. DBR layers with various interface shapes, such as uni-parabolic grading and three to five steps with different Al mole fractions, have been investigated. …”
Get full text

A hybrid AI-Blockchain security framework for smart grids by Yazeed Yasin Ghadi, Tehseen Mazhar, Tariq Shahzad, Ines Hilali Jaghdam, Sanwar khan, Muhammad Amir Khan, Habib Hamam

“…A categorization and analysis of cyberattacks against smart grids will be conducted, focusing on those targeting their communication layers. The main goal of the work is to address the challenges in this area by implementing novel detection and defense strategies. …”
Get full text