IoT-Edge Hybrid Architecture with Cross-Modal Transformer and Federated Manifold Learning for Safety-Critical Gesture Control in Adaptive Mobility Platforms by Xinmin Jin, Jian Teng, Jiaji Chen

“…The system architecture establishes a three-tier IoT network: a perception layer with 60 GHz FMCW radar and TOF infrared arrays (12-node mesh topology, 15 cm baseline spacing) for real-time motion tracking; an edge intelligence layer deploying a time-aware neural network via NVIDIA Jetson Nano to achieve up to 99.1% recognition accuracy with latency as low as 48 ms under optimal conditions (typical performance: 97.8% ± 1.4% accuracy, 68.7 ms ± 15.3 ms latency); and a federated cloud layer enabling distributed model synchronization across 32 edge nodes via LoRaWAN-optimized protocols (κ = 0.912 consensus). …”
Get full text

Manufacturing Process of Stealth Unmanned Aerial Vehicle Exhaust Nozzles Based on Carbon Fiber-Reinforced Silicon Carbide Matrix Composites by Byeong-Joo Kim, Jae Won Kim, Man Young Lee, Jong Kyoo Park, Nam Choon Cho, Cheul Woo Baek

“…The proposed nozzle structure was fabricated using a multilayer configuration consisting of an inner C/SiC layer for thermal and oxidation resistance, a silica–phenolic insulation layer to suppress heat transfer, and an outer carbon fiber-reinforced polymer matrix composite (CFRPMC) for mechanical reinforcement. …”
Get full text

HYDROCHEMICAL STUDIES OF THE PARTIZANSKAYA RIVER ESTUARY (NAKHODKA BAY, JAPAN SEA) IN SUMMER SEASON OF LOW WATER DISCHARGE by P. Yu. Semkin, P. A. Tishchenko, T. A. Mikhailik, Yu. A. Barabanshchikov, G. Yu. Pavlova, S. G. Sagalaev, P. P. Tishchenko, M. G. Shvetsova, E. M. Shkirnikova

“…By dynamical signs, the estuary could be divided into two zones: i) zone of active exchange between the surface freshwater layer and the bottom salted layer on the distance 5.5 km from the river mouth to the first sandy riverbank that the fresh river water passed in 12 hours, and ii) the upper part of the estuary with limited water exchange. …”
Get full text

An Optimization Method for PCB Surface Defect Detection Model Based on Measurement of Defect Characteristics and Backbone Network Feature Information by Huixiang Liu, Xin Zhao, Qiong Liu, Wenbai Chen

“…PCB surface defects are diverse, complex, low in feature resolution, and often resemble the background, leading to detection challenges. …”
Get full text

Modern state of irrigated soils at the south of the Volga upland by E. V. Zinchenko, I. N. Gorokhova, N. G. Kruglyakova, N. B. Khitrov

“…Detailed morphological description of soil profiles, granulometric composition, content of soluble salts in soils and sediments of the vadoze zone up to the depth of 3.5 m, dynamics of salts in the layer of 0-50 cm for 2011-2019 are presented. Until the autumn of 2015, the studied soils were deep saline, being no saline in the layer of 0-100 cm. …”
Get full text

Multi-Modal Temporal Dynamic Graph Construction for Stock Rank Prediction by Ying Liu, Zengyu Wei, Long Chen, Cai Xu, Ziyu Guan

“…The framework of the MTDGraph method consists of the stock-level sequential embedding layer, the inter-stock relation embedding layer based on temporal dynamic graph construction and the multi-model information fusion layer. …”
Get full text

Bilevel Programming Model of Urban Public Transport Network under Fairness Constraints by Jingjing Hao, Xinquan Liu, Xiaojing Shen, Nana Feng

“…In this paper, the bilevel programming model of the public transport network considering factors such as the per capita occupancy area and travel cost of different groups was established, to alleviate the urban transportation equity and optimize the urban public transport network under fairness constraints. The upper layer minimized the travel cost deprivation coefficient and the road area Gini coefficient as the objective function, to solve the optimization scheme of public transport network considering fairness constraints; the lower layer was a stochastic equilibrium traffic assignment model of multimode and multiuser, used to describe the complex selection behavior of different groups for different traffic modes in the bus optimization scheme given by the upper layer. …”
Get full text

Underground helmet detection algorithm based on improved YOLOv8s by Jiaru YANG, Yinan QIN, Tianxu LI, Han ZHUANG

“…The safety helmet belongs to small target detection, and the underground operation environment is complex, and dust and light noise have a great impact on camera detection. …”
Get full text

Terahertz nanospectroscopy of plasmon polaritons for the evaluation of doping in quantum devices by Guo Xiao, He Xin, Degnan Zachary, Chiu Chun-Ching, Donose Bogdan C., Bertling Karl, Fedorov Arkady, Rakić Aleksandar D., Jacobson Peter

“…The presence of the THz surface plasmon polariton indicates the existence of a thin film doped layer on the device. Using a multilayer extraction procedure utilising vector calibration, we quantitatively probe the doped surface layer and determine its thickness and complex permittivity. …”
Get full text

Construction and Validation of a Digital Twin-Driven Virtual-Reality Fusion Control Platform for Industrial Robots by Wenxuan Chang, Wenlei Sun, Pinghui Chen, Huangshuai Xu

“…The high-precision twin environment is constructed from the three dimensions of the physical layer, digital layer, and information fusion layer. …”
Get full text

Results of Experimental Studies of the Seed Drill for Row Sowing SZD­4.0 by S. I. Kambulov, G. G. Parkhomenko, I. V. Bozhko, A. A. Boyko

“…Sowing units are considered to be the most complex agricultural machines, as they perform many operations - both sequentially and simultaneously. …”
Get full text

iNClassSec-ESM: Discovering potential non-classical secreted proteins through a novel protein language model by Yizhou Shao, Taigang Liu

“…Existing NCSP prediction methods mainly use traditional handcrafted features to represent proteins from sequence information, which limits the models' ability to capture complex protein characteristics. In this study, we proposed a novel NCSP predictor, iNClassSec-ESM, which combined deep learning with traditional classifiers to enhance prediction performance. iNClassSec-ESM integrates an XGBoost model trained on comprehensive handcrafted features and a Deep Neural Network (DNN) trained on hidden layer embeddings from the protein language model (PLM) ESM3. …”
Get full text

Cheating Detection in Online Exams Using Deep Learning and Machine Learning by Bahaddin Erdem, Murat Karabatak

“…As a result of this study, it has been shown that the application of the most appropriate layer functions and parameter selection that will increase performance can be effective in estimating complex problems and target values that cannot be solved using classical mathematical models. …”
Get full text

Structural and Functional Reorganization of the Sensorimotor Cortex During Ligation of the Common Carotid Arteries (Experimental Study) by L. M. Makarieva, V. A. Akulinin, M. S. Korzhuk, S. S. Stepanov, A. Y. Shoronova, D. B. Avdeev, I. G. Tsuskman

“…Layer III (secondary projection complex) of the SMC was affected to a greater extent. …”
Get full text

Printable nanocomposites of polymers and silver nanoparticles for antibacterial devices produced by DoD technology. by Nicole Barrera, Lizeth Guerrero, Alexis Debut, Petrus Santa-Cruz

“…An important advantage in using the DoD process is the possibility of printing, layer by layer or side by side, more than one active principle, allowing an interleaved or simultaneous release of silver NP and other molecules of interest as for example with a second functional fluid to ensure effectiveness of Ag activity.…”
Get full text

Supply Chain Data Governance Optimization Based on Fuzzy DEMATEL-ISM by Yaoxi Liu, Jinyu Wei, Xiaoxuan Wang

“…It provides authorities with a layered progression of supply chain data governance optimization thinking and the actions to be taken at each layer.…”
Get full text

Mathematical modeling unveils the timeline of CAR-T cell therapy and macrophage-mediated cytokine release syndrome. by Daniela S Santurio, Luciana R C Barros, Ingmar Glauche, Artur C Fassoni

“…By disentangling the timeline of macrophage activation, the model identified distinct contributions of each activation mechanism, suggesting the CD40-CD40L axis as a major driver of cytokine release and a clinically feasible target to control the activation process and modulate cytokine peak height. Our multi-layer model provides a comprehensive framework for understanding the complex interactions between CAR-T cells, tumor cells, and macrophages during therapy.…”
Get full text

Computer Numerical Controlled Grinding and Physical Vapor Deposition for Fused Deposition Modelled Workpieces by Fulvio Lavecchia, Gianluca Percoco, Eujin Pei, Luigi Maria Galantucci

“…This layer-by-layer method results in a poor surface finish, and as a result, manual finishing is often required, which consequentially reduces the definition of the geometrical features. …”
Get full text

Grouped multi-scale vision transformer for medical image segmentation by Zexuan Ji, Zheng Chen, Xiao Ma

“…However, existing ViT-based segmentation models often struggle to effectively capture multi-scale variations within a single attention layer, limiting their capacity to model complex anatomical structures. …”
Get full text

Multi-scale inference of genetic trait architecture using biologically annotated neural networks. by Pinar Demetci, Wei Cheng, Gregory Darnell, Xiang Zhou, Sohini Ramachandran, Lorin Crawford

“…This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. …”
Get full text