CosPoint Transformer: Enhancing 3-D Semantic Segmentation With Cosine Similarity Attention and Cross-Attention by Thien Huynh-The, Minh-Thanh Le, Won Jae Ryu, Anh-Kiet Vo

Get full text

A Comprehensive Analysis of the Loss Mechanism and Thermal Behavior of a High-Speed Magnetic Field-Modulated Motor for a Flywheel Energy Storage System by Qianli Mai, Qingchun Hu, Xingbin Chen

“…Experimental validation confirms model accuracy with mean absolute percentage errors below 4.2%. …”
Get full text

Spatio-temporal Variation and Influencing Factors of CO2 Emission at County Scale in Shaanxi Province Based on Land Use Change by Cao Zhouliang, Zhang Xinrong, Yuan Xuefeng, Chen Jinhong

“…The evolution of carbon emission can be divided into two stages (substantial growth and slow growth). ② The carbon emission center gradually moved to the northeast from 2000 to 2020, and the spatial distribution range showed an expansion trend. …”
Get full text

TCCDNet: A Multimodal Pedestrian Detection Network Integrating Cross-Modal Complementarity with Deep Feature Fusion by Shipeng Han, Chaowen Chai, Min Hu, Yanni Wang, Teng Jiao, Jianqi Wang, Hao Lv

“…Specifically, the efficient multi-scale attention C2f (EMAC) is designed for the backbone, which combines the C2f structure with an efficient multi-scale attention mechanism to achieve feature weighting and fusion, thereby enhancing the model’s feature extraction capacity. Subsequently, the cross-modal complementarity (CMC) module is proposed, which enhances feature discriminability and object localization accuracy through a synergistic mechanism combining channel attention and spatial attention. …”
Get full text

Built environment characteristics and driving speed in 30 km/h zones: a Dutch national analysis by Paul Schepers, Werner van Loo, Wouter Mieras, Hans Drolenga, Dick de Waard, Marco Helbich

“…This requires understanding how built environment characteristics are associated with driving speeds, but only a few studies, typically based on small samples, focus on 30 km/h streets. Using a spatial error model, this study examines the relationship between built environment factors and 85th percentile speeds on 47,000 km of Dutch 30 km/h streets (N=159.000). …”
Get full text

Semantic SLAM using laser-vision data fusion: Enhancing autonomous navigation in unstructured environments by Ning Chen, Dong Wei, Dongsheng Lin, Linhan Lin

“…For semantic segmentation, the PSPNet_CBAM network framework was developed, achieving improvements of 0.73 %, 0.14 %, and 0.92 % in mean Accuracy (mAcc), Pixel Accuracy (PAcc), and mean Intersection over Union (mIoU), respectively, on the Cityscapes dataset compared to the original PSPNet model. For the fusion of visual and laser information, NN-SLAM demonstrated a reduction in filter processing time by 0.2440 ms and 3.6497 ms on the KITTI 0011 and 0093 datasets, respectively, when compared to the Visual-Lidar Odometry and Mapping (ALOAM) algorithm. …”
Get full text

Community Engagement in the Management of Urban Green Spaces: Prospects from a Case Study in an Emerging Economy by Adriano Bressane, Anna Isabel Silva Loureiro, Ricardo Almendra

Get full text

Patterns of dolphin bycatch in a north-western Australian trawl fishery. by Simon J Allen, Julian A Tyne, Halina T Kobryn, Lars Bejder, Kenneth H Pollock, Neil R Loneragan

“…Over the entire datasets, observer reported bycatch rates (n = 52 dolphins in 4,124 trawls, or 12.6 dolphins/1,000 trawls) were ca. double those reported by skippers (n = 180 dolphins in 27,904 trawls, or 6.5 dolphins/1,000 trawls). Generalised Linear Models based on observer data, which better explained the variation in dolphin bycatch, indicated that the most significant predictors of dolphin catch were: (1) vessel--one trawl vessel caught significantly more dolphins than three others assessed; (2) time of day--the lowest dolphin bycatch rates were between 00:00 and 05:59; and (3) whether nets included bycatch reduction devices (BRDs)--the rate was reduced by ca. 45%, from 18.8 to 10.3 dolphins/1,000 trawls, after their introduction. …”
Get full text

Influence of crosspolarization of dual-polarized antenna elements on the ergodic capacity of a multichannel system by Ekaterina V. Averina, Ksenia V. Smuseva, Pavel A. Tokarev, Grigory K. Uskov

“…These effects can lead to a significant reduction in communication system capacity. Aim. Derive relationships based on the Kronecker model that allow to take into account the polarization properties of antenna elements when calculating the ergodic capacity of a multi-channel communication system. …”
Get full text

YOLO-BCD: A Lightweight Multi-Module Fusion Network for Real-Time Sheep Pose Estimation by Chaojie Sun, Junguo Hu, Qingyue Wang, Chao Zhu, Lei Chen, Chunmei Shi

“…Comparative evaluations demonstrate significant improvements over baseline models, achieving 91.7% recognition accuracy with 389 FPS processing speed while maintaining 19.2% parameter reduction and 32.1% lower computational load compared to standard YOLOv8. …”
Get full text

First Basic Problem of Elasticity Theory for a Composite Layer with Two Thick-Walled Tubes by Oleksandr Yu. Denshchykov, Valentyn P. Pelykh, Yaroslav V. Hrebeniuk, Vitalii Yu. Miroshnikov

“…The spatial problem of elasticity theory for a fibrous composite in the form of a layer with two thick-walled cylindrical tubes is solved. …”

Dual Graph for Traffic Forecasting by Long Wei, Zhengxu Yu, Zhongming Jin, Liang Xie, Jianqiang Huang, Deng Cai, Xiaofei He, Xian-Sheng Hua

“…It is challenging due to the complex spatial-temporal correlation on road networks. Most existing research works use sequential Graph Neural Networks (GNN) to model traffic inference. …”
Get full text

Evaluating Groundwater Quality to Determine the Feasibility of Modern Irrigation Techniques (Case Study: Bam-Narmashir Plain) by Hadi Dehghan, Maryam Safavi, Somayeh Galdavi, Mohammad Naderianfar

Get full text

L-ENet: An Ultralightweight SAR Image Detection Network by Yutong Wang, Min Miao, Shiliang Zhu

Get full text

Effective Adaptation Options to Alleviate Nuisance Flooding in Coastal Megacities—Learning From Ho Chi Minh City, Vietnam by Leon Scheiber, Nivedita Sairam, Mazen Hoballah Jalloul, Kasra Rafiezadeh Shahi, Christian Jordan, Jan Visscher, Tara Evaz Zadeh, Laurens J. N. Oostwegel, Danijel Schorlemmer, Ngo Thanh Son, Hong Nguyen Quan, Torsten Schlurmann, Matthias Garschagen, Heidi Kreibich

“…Because sustainable flood risk management requires detailed spatial information, we analyze the local risk and its components based on a chain of novel models previously calibrated and validated for Ho Chi Minh City. …”
Get full text

Developing a semi-automated technique of surface water quality analysis using GEE and machine learning: A case study for Sundarbans by Sheikh Fahim Faysal Sowrav, Sujit Kumar Debsarma, Mohan Kumar Das, Khan Mohammad Ibtehal, Mahfujur Rahman, Noshin Tabassum Hridita, Atika Afia Broty, Muhammad Sajid Anam Hoque

“…The predictive framework leverages Google Earth Engine (GEE) and AutoML, utilizing deep learning libraries to create dynamic, adaptive models that enhance prediction accuracy. …”
Get full text

Evolution Law of Longitudinal Deformation Curve and Release Coefficient of Viscoelastic Rock by WANG Jiachen, MENG Lingzan, ZHANG Dingli, LU Song, WEN Ming

“…Empirical formulas are fitted for the longitudinal deformation curve, including time, spatial, and spatiotemporal factors. The research conclusion can provide a more convenient method for predicting the deformation of soft rock tunnels.…”
Get full text

AAMS-YOLO: enhanced farmland parcel detection for high-resolution remote sensing images by Binyao Wang, Ya’nan Zhou, Weiwei Zhu, Li Feng, Jinke He, Tianjun Wu, Jiancheng Luo, Xin Zhang

“…To improve detection accuracy in these contexts, this study proposes AAMS-YOLO, a YOLO-based farmland parcel detection model. In the feature extraction stage, the model incorporates an Adaptive Mix Attention (AMA) Block, balancing robust feature extraction with low computational overhead through spatial mixing and Efficient Multi-Scale Attention (EMA). …”
Get full text

Building extraction from unmanned aerial vehicle imagery using Mask-RCNN (case study: Institut Teknologi Sepuluh Nopember, Surabaya) by Ramadhani Anisa, Alya Nurul Fitri

“…In this paper, a dataset consisting of aerial photography images acquired by aircraft in the urban and educational area of Institut Teknologi Sepuluh Nopember Surabaya to explore the potential of using Mask R-CNN, the art model, for instance, segmentation to automatically detect building footprints, which are essential attributes that define the urban fabric (which is critical to accelerating land cover updates with high highly accurate in terms of area and spatial assessment). …”
Get full text

Monitoring the Impacts of Human Activities on Groundwater Storage Changes Using an Integrated Approach of Remote Sensing and Google Earth Engine by Sepide Aghaei Chaleshtori, Omid Ghaffari Aliabad, Ahmad Fallatah, Kamil Faisal, Masoud Shirali, Mousa Saei, Teodosio Lacava

“…Although storage is conceptually a volumetric quantity, expressing it as depth allows for spatial comparison and enables conversion to volume by multiplying by the corresponding surface area.…”
Get full text