MOCVD Grown InGaAs/InAlAs Quantum Cascade Lasers Emitting at 7.7 μm by Maciej Bugajski, Andrzej Kolek, Grzegorz Hałdaś, Włodzimierz Strupiński, Iwona Pasternak, Walery Kołkowski, Kamil Pierściński

“…The grown structures were processed into mesa Fabry-Perot lasers using dry etching RIE ICP processing technology. …”
Get full text

Numerical simulation of seismicity potential resulting from the injection of CO2 into depleted reservoir in Wilbarger County field, Texas by Dorcas S. Eyinla, Hossein Emadi, Steven K. Henderson, Humza Bin Navaid, Abir Kebir, Aman Arora

“…The model effectively captures the complex interplay between geological features and fault failure processes. …”
Get full text

The effect of microflocculant MBFA9 and the mechanism of Pb(II) and Zn(II) removal from an aqueous solution by Jiaqi Zhang, Binhui Jiang, Bo Zhang, Yu Li, Ping Fang and, Xiaomin Hu

“…Both the adsorption kinetics and adsorption equilibrium, usually described as adsorption isotherms, showed that this process of Pb(II) or Zn(II) capture by MBFA9 involved simple adsorption of a single molecular layer. …”
Get full text

Aging-Friendly Design Research: Knowledge Graph Construction for Elderly Advantage Applications by Xiaoying Li, Xingda Wang, Guangran Li

“…Next, the elderly advantages knowledge graph was constructed by following these steps: (1) The KJ-AHP method was used to process raw data, making them structured and quantitative. (2) The ontology of the knowledge graph was reverse-engineered based on the functional requirements of the graph, allowing the construction of the knowledge graph model layer. (3) The processed data were applied to the knowledge graph ontology through AHP-ontology mapping rules, allowing the knowledge content construction. (4) The programming language Cypher was used for the functional verification of the elderly advantages knowledge graph, and a satisfaction survey was conducted through questionnaires to assess the verification process. …”
Get full text

Monitoring soil salinization in Arid cotton fields using Unmanned Aerial Vehicle hyperspectral imagery by Jinming Zhang, Jianli Ding, Jiao Tan, Jinjie Wang, Zihan Zhang, Zeyuan Wang, Xiangyu Ge

“…The results indicate: (1) SG smoothing and FOD technology effectively enhanced the spectral characteristics of cotton field soils and crop canopies. (2) The soil salinity prediction model constructed using 0.7-order FOD combined with the BOSS algorithm yields the best performance, with an R2 of 0.92, RMSE of 0.15 dS m−1, and RPD of 3.54 on the test set. (3) The soil salinity distribution map generated from the optimal model clearly revealed the spatial distribution characteristics of salinity in the 0–10 cm topsoil layer, with significant differences observed under different cover conditions. …”
Get full text

Reservoir permeability prediction based artificial intelligence techniques by Hayder Mahdi Ghargan, Omar Al-Fatlawi, Yasir Bashir

“…This model goes beyond simply predicting lithology to provide a detailed quantification of primary minerals (e.g., calcite and dolomite) as well as secondary ones (e.g., shale and anhydrite). …”
Get full text

Design and Simulation of Chinese Cabbage Harvester by Simo Liu, Xuhui Yang, Zhe Zhang, Jianing Xu, Ping Zhao, Subo Tian, Lihua Wei, Xiaofeng Ning

“…Secondly, simulation tests were conducted on the Chinese cabbage harvesting process; a 3D model of Chinese cabbage using SolidWorks 2022 was established and filled with particles using the three-layer stacking method. …”
Get full text

A study of massive multidimensional data sharing and interaction algorithms based on cloud-edge collaboration by Xiaodong Zhang, Jing Wang, Ke Yang

“…The improved DPoS will select proxy nodes. Cloud layers share and access data lake models through smart contracts. …”
Get full text

Human and environmental feature-driven neural network for path-constrained robot navigation using deep reinforcement learning by Nabih Pico, Estrella Montero, Alisher Amirbek, Eugene Auh, Jeongmin Jeon, Manuel S. Alvarez-Alvarado, Babar Jamil, Redhwan Algabri, Hyungpil Moon

“…The representation, combined with weighted features from humans and environmental limitations, is processed through three multi-layer perceptrons (MLP) to calculate the value function and optimal policy, thereby enhancing navigation tasks. …”
Get full text

Lightweight YOLOv8s-Based Strawberry Plug Seedling Grading Detection and Localization via Channel Pruning by CHEN Junlin, ZHAO Peng, CAO Xianlin, NING Jifeng, YANG Shuqin

“…To improve the detection efficiency and reduce the model's computational cost, the layer-adaptive magnitude-based pruning(LAMP) score-based channel pruning algorithm was applied to compress the base YOLOv8s model. …”
Get full text

Buckling Analysis of Functionally Graded Sandwich Beam Based on Third-Order Zigzag Theory by simmi gupta, H Chalak

“…The present model shows an accurate variation of transverse stresses in thickness direction due to the inclusion zigzag factor in assumed displacements and is independent of the number of layers in computing the results. …”
Get full text

Detection of water-rich areas and seepage channels via the transient electromagnetic method, electrical resistivity tomography, and self-potential method by Peng Wang, Fan Li, Kai Lu, Wei Huang

“…The subsequent post-processing of these detection results facilitated the construction of a comprehensive three-dimensional model of the groundwater system. …”
Get full text

Enhancing tool condition monitoring in friction stir welding with probabilistic neural network algorithm by Balachandar Krishnamurthy, Jegadeeshwaran Rakkiyannan

“…A feature importance study is conducted using a decision tree algorithm, which selects only the most significant features to reduce computational complexity.ResultFeature classification is then performed using various machine learning and deep learning algorithms, including Support Vector Machines (SVM), Multi-Layer Perceptron (MLP), Cascade Correlation, GMDH Polynomial Neural Networks, and Linear Discriminant Analysis Among these classifiers, Probabilistic Neural Networks (PNN) consistently deliver the best results as 91.25% under 1,400 rpm.DiscussionBased on these findings, the Probabilistic Neural Network algorithm is identified as a robust and reliable prediction model for monitoring FSW tool conditions.…”
Get full text

MFH-LPI: based on multi-view similarity networks fusion and hypergraph learning for long non-coding RNA-protein interactions prediction by Zengwei Xing, Shaoyou Yu, Shuzu Liao, Peng Wang, Bo Liao

“…The experimental findings indicate that the suggested model is effective compared to existing processes and outperforms other approaches.…”
Get full text

Detecting schizophrenia, bipolar disorder, psychosis vulnerability and major depressive disorder from 5 minutes of online-collected speech by Julianna Olah, Win Lee Edwin Wong, Atta-ul Raheem Rana Chaudhry, Omar Mena, Sunny X. Tang

“…Linguistic and paralinguistic features were extracted and ensemble learning algorithms (e.g., XGBoost) were used to train models. A 70–30% train-test split and 30-fold cross-validation was used to validate the model performance. …”
Get full text

Objective Weather Classification and Potential Source Analysis of Ozone Pollution during Summer in Chengdu Plain Urban Agglomeration by Ningsheng LU, Xiaoling ZHANG, Yunsong DU, Ping KANG, Junhui CHEN, Ming HUA, Yu LEI, Hong QI

“…The analysis of the surface ozone pollution in 8 cities in the Chengdu Plain urban agglomeration during the summer of 2015 to 2019 showed that the O3 pollution area in plain has expanded in the summer of the past 5 years.The 90th percentile concentration of O3_8 h and O3 over-standard days in Chengdu are both the largest， Ya'an and Mianyang have lower concentrations but a significant upward trend.Using PCT objective weather classification method， the geopotential height field of different layers over Chengdu Plain and its surrounding were objectively classified in the summer for the past five years， the results showed that： （1）The 700 hPa ozone pollution weather classification was the high pressure system type， and the 500 hPa was the rear of the westerly trough and the flat vertical zonal type， and the 100 hPa was the central and eastern of asia high type； （2）The high and low altitude weather conditions of the typical ozone pollution process in the summer of the past 5 years are divided into the rear of the westerly trough， high pressure development and high pressure control type.During the pollution process， Chengdu Plain is mostly affected by the northwest airflow behind the westerly trough or the sinking airflow near the ridge of the subtropical high pressure； （3）The polluted weather pattern had the characteristics of high temperature and low humidity， strong radiation in small winds， and high mixed layer during the day.The effects of airflow subsidence and warming and local circulation inhibit the diffusion of pollutants to upper layers， and promote the downward transmission of O3 in the upper boundary layer and accumulation in the Chengdu Plain.Using HYSPLIT backward trajectory model and potential source contribution analysis （PSCF）， explored the trajectory clustering and potential source areas of different weather patterns that affect the O3 concentration in the Chengdu Plain.The results showed that the local and transportations among cities in the Sichuan Basin contribute to the ozone pollution.The most important potential source of ozone is located in the local urban area.The main potential source areas of Chengdu， Meishan and Ziyang are also concentrated in northern Sichuan and western Chongqing， while the main source of Deyang is concentrated in Chengdu and Meishan.The rear of the westerly trough and high-pressure development， the regional transport of ozone is more obvious， and high-pressure control type shows significant local accumulation.…”
Get full text

Exploring MediaPipe optimization strategies for real-time sign language recognition by Phuoc Thanh Nguyen, Thanh Hoang Nguyen, Ngoc Xuan Nguyen Hoang, Huynh Thanh Binh Phan, Hoang Son Hai Vu, Hieu Nhan Huynh

“…We introduce an innovative multi-modal methodology, amalgamating four distinct Long Short-Term Memory (LSTM) models dedicated to processing skeletal coordinates ascertained from the MediaPipe framework. …”
Get full text

A numerical investigation of heat and mass transfer in the bioconvective Oldroyd B nanofluid flow through the porous stretching Riga surface with gyrotactic microorganism by Muhammad Zulfiqar, Muhammad Bilal Arain, Muhammad Zubair, Usman, Hadil Alhazmi

“…The Riga plate's flexible layer can mimic microbial movement driven by bioconvection, making it a useful model for studying this phenomenon. …”
Get full text

Hydrogen Leakage Location Prediction in a Fuel Cell System of Skid-Mounted Hydrogen Refueling Stations by Leiqi Zhang, Qiliang Wu, Min Liu, Hao Chen, Dianji Wang, Xuefang Li, Qingxin Ba

“…After multiple adjustments to the network structure and hyperparameters, a final model with two hidden layers was selected. Each hidden layer consisted of 10 neurons. …”
Get full text

RMDNet: RNA-aware dung beetle optimization-based multi-branch integration network for RNA–protein binding sites prediction by Jiangbo Zhang, Yunhui Peng, Feifei Cui, Zilong Zhang, Shankai Yan, Qingchen Zhang

“…We assess biological interpretability by extracting candidate binding motifs from the first-layer CNN kernels. Several motifs closely match experimentally validated RBP motifs, confirming the model’s capacity to learn biologically meaningful patterns. …”
Get full text