Fishing operation type recognition based on multi-branch convolutional neural network using trajectory data by Bohui Jiang, Weifeng Zhou

“…The multi-branch structure significantly outperforms single-branch counterparts, and MB-1dCNN demonstrates superior performance over multi-branch model with fully connected layers (MB-FCNN), achieving additional gains in accuracy and F1-score. …”
Get full text

Quantitative study on the color of traditional dwellings in Jianxi River Basin, Fujian Province, based on the lab color space model by Deyi Kong, Xinyue Lin, Zexuan Lu, Xinhui Fei, Yanqiu Xie, Zujian Chen

“…The findings reveal that earth yellow (average Lab (50.35,7.40,19.63)) constitutes the main color of rammed earth walls, complemented by dark brown (average Lab (38.72,2.97,8.58)) tiled roofs and gray-brown (average Lab (41.95,4.30,12.75)) stone wall bases as accent color; additionally, gray-yellow (average Lab (49 .82,1 .93,10.98)) brick gatehouses serve as accent colors. The integration between these colors and nature is harmonious; however, the absence of distinct color layers and highlights in the traditional dwellings necessitates incorporating bright architectural decorations along with arrangements of flowering plants. …”
Get full text

Optimizing security and energy efficiency in IoT-Based health monitoring systems for wireless body area networks by Mohammed Naif Alatawi

“…To address these issues, a novel multi-layered framework is proposed. First, an energy-efficient mechanism is introduced using a threshold-based transmission controller. …”
Get full text

Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments by Xin Xu, Haiyang Zhang, Jiangchuan Lu, Ziyi Guo, Juanjuan Zhang, Jibo Yue, Hongbo Qiao, Xinming Ma

“…Further optimizes the loss function system by replacing traditional IoU with Scylla Intersection over Union (SIoU) metric, enhancing bounding box regression through dynamic focus factors, and adding high-resolution small-object detection layers to mitigate dense spikelet feature loss. Results Independent test set validation shows the improved model achieves 83.9% contour integrity recognition rate and 92.4% mAP@0.5, exceeding baseline by 3.2 and 5.3% points respectively. …”
Get full text

Nystromformer based cross-modality transformer for visible-infrared person re-identification by Ranjit Kumar Mishra, Arijit Mondal, Jimson Mathew

“…The fused features are subsequently refined through projection layers and optimized for re-identification using a classification head. …”
Get full text

Main controlling factors and characterization of overburden fracture damage based on energy conduction mechanism by Cun ZHANG, Baiqiang FAN, Zhaopeng REN, Jianqi MA, Yixin ZHAO, Quansheng LI, Yongqiang ZHAO

“…An innovative method has been proposed for calculating the total energy of overlying rock layers with gravity potential energy imparted by coal seam excavation. …”
Get full text

Advanced tarnish-resistant silver alloys using Cu, Al, Zn, and Be: composition optimization and surface passivation by Harsha Kozhakkattil, Mukaddar Sk, Ranjit Thapa, G.S. VinodKumar

Get full text

Dynamic Agricultural Pest Classification Using Enhanced SAO-CNN and Swarm Intelligence Optimization for UAVs by Shiwei Chu, Wenxia Bao

“…The SAO-CNN innovatively combines adaptive convolutional layers, self-supervised learning, and ConvLSTM to optimize spatial-temporal feature extraction, while swarm algorithms (ACO and PSO) enhance UAV path planning and task allocation. …”
Get full text

EDM-based analysis of Fe-based shape memory alloys using Cu-W electrodes with multiple output optimization and microstructural validation by Ranjit Singh, Sambit Satpathy, Dhirendra Kumar Shukla, Ravi Pratap Singh, Rajeev Trehan, Jibitesh Kumar Panda, Biplab Bhattacharjee

“…Scanning Electron Microscopy (SEM) of machined surfaces showcased craters, micro-cracks, and recast layers, elucidating the correlation between process parameters and surface integrity. …”
Get full text

A Spatio-Temporal Deep Learning Approach for Efficient Deepfake Video Detection by Raman Z. Khudhur, Marwan A. Mohammed

“…By means of a pre-trained EfficientNetV2-B0 model, the proposed framework efficiently extracts spatial characteristics from each frame, subsequently, and Bidirectional Long Short-Term Memory layers help to capture temporal relationships from video sequences. …”
Get full text

YOLO-SAD: Enhancing Small Aircraft Detection With Multi-Scale Context and Improved Gradient Flow by Xin Ning, Hongchang Ding, Xiaoqiang Guo

“…YOLO-SAD comprises three core modules: The Cross-Scale Attention Kernel Aggregation Module enhances small object feature representation by leveraging complementary channel information through a cross-attention mechanism, improving feature fusion and context enhancement; The Feature Highway Aggregation Structure seamlessly integrates features from different network levels while preserving critical information and improving gradient flow behavior in the shallow layers by utilizing auxiliary training branches during training; The Mixed Spectral Feature Compression Module combines multiple downsampling strategies, introduces multi-scale contextual factors, and retains more original details, effectively reducing information loss. …”
Get full text

Unveiling the Frailty Spatial Patterns Among Chilean Older Persons by Exploring Sociodemographic and Urbanistic Influences Based on Geographic Information Systems: Cross-Sectional... by Yony Ormazábal, Diego Arauna, Juan Carlos Cantillana, Iván Palomo, Eduardo Fuentes, Carlos Mena

“…Current evidence suggests that geomatic tools integrating geolocation can provide valuable information for implementing preventive measures by enhancing the urban physical environment. …”
Get full text

Federated Deep Learning Model for False Data Injection Attack Detection in Cyber Physical Power Systems by Firdous Kausar, Sambrdhi Deo, Sajid Hussain, Zia Ul Haque

“…Cyber-physical power systems (CPPS) integrate information and communication technology into conventional electric power systems to facilitate bidirectional communication of information and electric power between users and power grids. …”
Get full text

Biomimetic Full-Thickness Artificial Skin Using Stromal Vascular Fraction Cells and Autologous Keratinocytes in a Single Scaffold for Wound Healing by Jung Huh, Seong-Ho Jeong, Eun-Sang Dhong, Seung-Kyu Han, Kyung-Chul Moon

“…We developed biomimetic full-thickness artificial skin using stromal vascular fraction (SVF) cells and autologous keratinocytes for the dermal and epidermal layers of skin, respectively. Full-thickness artificial skin scaffolds were fabricated using 4% porcine collagen and/or elastin in a low-temperature three-dimensional printer. …”
Get full text

Biodiversity Dynamics in a Ramsar Wetland: Assessing How Climate and Hydrology Shape the Distribution of Dominant Native and Alien Macrophytes by Fabio A. Labra, Eduardo Jaramillo

“…We modeled suitable habitat areas using MaxEnt software with Landsat 8 spectral bands and indices as predictive layers. We found significant recent decreases in temperature, river flow, and water level, with a nonsignificant shift in precipitation. …”
Get full text

OTM-HC: Enhanced Skeleton-Based Action Representation via One-to-Many Hierarchical Contrastive Learning by Muhammad Usman, Wenming Cao, Zhao Huang, Jianqi Zhong, Ruiya Ji

“…Our proposed One-to-Many Hierarchical Contrastive Learning (OTM-HC) framework maps the input into multi-layered feature vectors, creating a hierarchical contrast representation that captures various granularities within a human skeleton sequence temporal and spatial domains. …”
Get full text

Enhanced urban driving scene segmentation using modified UNet with residual convolutions and attention guided skip connections by Siddhant Arora, Ahaan Banerjee, Nitish Katal

“…The proposed work evaluates the integration of the residual connections and the attention gate for segmentation; the residual connections enable deeper models, and the inclusion of attention gate in the skip layers of the UNet enables the model to decisively prioritize the critical information to enhance the overall capability. …”
Get full text

Flood hazard analysis and risk assessment using remote sensing, GIS, and AHP techniques: a case study of the Gidabo Watershed, main Ethiopian Rift, Ethiopia by Dechasa Diriba, Tariku Takele, Shankar Karuppannan, Musa Husein

“…A weighted overlay analysis tool has been utilized to integrate the thematic layers to identify both flood hazard and flood risk zones. …”
Get full text

Multi-task glioma segmentation and IDH mutation and 1p19q codeletion classification via a deep learning model on multimodal MRI by Erin Beate Bjørkeli, Morteza Esmaeili

“…Future work will focus on addressing class imbalance and exploring feature integration to enhance classification performance.…”
Get full text

Fabrication of antimicrobial platinum-graphene/polypropylene Pt-GNPs/PP nanofilter for PMs capturing and high quality air by Amjed R. Qarahgouli, Khalid A. Sukkar, Alaa M. Ali

“…In addition, it was found when the GNPs/PP nanofilter was combined with other layers of sponge and cotton as auxiliary filters the efficiency increased to 99.03 %. …”
Get full text