Drainage Pipeline Multi-Defect Segmentation Assisted by Multiple Attention for Sonar Images by Qilin Jin, Qingbang Han, Jianhua Qian, Liujia Sun, Kao Ge, Jiayu Xia

“…The test precision and accuracy of MAP@50 reach 96.0% and 90.9%, respectively, in the segmentation prediction. Compared to the coordinate attention and convolutional block attention module attention models, it had a significant precision advantage, and the weight file size is merely 7.0 MB, which is far smaller than the Yolov9 model segmentation weight size. …”
Get full text

Investigation of the application of an automated monitoring system for detecting transmission cable deterioration in Nigeria: A case study of transmission cable lines between Offa... by C.S. Omoniabipi, R. Agbadede, K.C. Emmanuel, O.J. Adewuni, I. Allison

“…The study successfully demonstrated the prediction of overload conditions using neural networks, with minimal errors illustrated through confusion matrices and performance plots.…”
Get full text

Adept Domestic Energy Load Profile Development Using Computational Intelligence-Based Modelling by Olawale Popoola, Agnes Ramokone, Ayokunle Awelewa

“…The aptitude to improve on energy prediction and evaluation accuracy, especially in these periods, makes it a highly suited tool for demand-side management, power generation, and distribution planning activity. …”
Get full text

An investigation into the impact of diapir structures on formation pressure systems: a case study of the Yinggehai Basin, China by An Jintao, Li Jun, Honglin Huang, Hui Zhang, Hongwei Yang, Geng Zhang, Sainan Chen

“…The characteristics of high temperature and high pressure are obvious, the prediction is difficult, and complex accidents such as well kick and leakage are frequent, which seriously restrict the efficient development of oil and gas resources. …”
Get full text

Effect of bending load on electrical conductivity of carbon/epoxy composites filled with nanoparticles using design of experiment and artificial neural networks by Ali Sadollah, Seyed Morteza Razavi, Abobakr Khalil Al-Shamiri

“…The ANNs and ELM models prove effective in accurately predicting data, and the model generated by DOE is statistically valid with a confidence level exceeding 95 %. …”
Get full text

A New Big Data Approach to Understanding General Traffic Impacts on Bus Passenger Delays by Yaiza Montero-Lamas, Margarita Novales, Alfonso Orro, Graham Currie

“…For that purpose, in the first place, a travel time prediction model per vehicle trip has been developed. …”
Get full text

Identification and dipeptidyl peptidase IV (DPP-IV) inhibitory activity verification of peptides from mouse lymphocytes by Juan Wang, Yujia Xie, Yuanyuan Luan, Tingting Guo, Shanshan Xiao, Xingxing Zeng, Shaohui Zhang

“…After compared with peptides reported, 131 novel peptides were discovered, which then were predicted bioactivity by Peptide Ranker and 6 peptides with high bioactivity were predicted function by BIOPEP-UMW database. …”
Get full text

Evaluation of Geomembrane Effect Based on Mobilized Shear Stress due to Localized Sinking by Weihua Lu, Yongxing Zhang, Weizheng Liu, Cheng Liu, Haibo Wang

“…In routine design work, the geomembrane effect must be well estimated and the tensile strain should be precisely predicted. Conventional analytical methods often adopt the limit state method to calculate the overlying load on the deflected geosynthetic. …”
Get full text

Research on credit card transaction security supervision based on PU learning by Renfeng CHEN, Hongbin ZHU

“…The complex and ever-evolving nature of credit card cash out methods and the emergence of various forms of fake transactions present challenges in obtaining accurate transaction information during customer interactions.In order to develop an accurate supervision method for detecting fake credit card transactions, a PU (positive-unlabeled learning) based security identification model for single credit card transactions was established.It was based on long-term transaction label data from cashed-up accounts in commercial banks’ credit card systems.A Spy mechanism was introduced into sample data annotation by selecting million positive samples of highly reliable cash-out transactions and 1.3 million samples of transactions to be labeled, and using a learner to predict the result distribution and label negative samples of non-cash-out transactions that were difficult to identify, resulting in 1.2 million relatively reliable negative sample labels.Based on these samples, 120 candidate variables were constructed, including credit card customer attributes, quota usage, and transaction preference characteristics.After importance screening of variables, nearly 50 candidate variables were selected.The XGBoost binary classification algorithm was used for model development and prediction.The results show that the proposed model achieve an identification accuracy of 94.20%, with a group stability index (PSI) of 0.10%, indicating that the single credit card transaction security identification model based on PU learning can effectively monitor fake transactions.This study improves the model discrimination performance of machine learning binary classification algorithm in scenarios where high-precision sample label data is difficult to obtain, providing a new method for transaction security monitoring in commercial bank credit card systems.…”
Get full text

Parametric Study Of Friction Stir Spot Welding (FSSW) For Polymer Materials Case Of High Density Polyethylene Sheets: Experimental And Numerical Study by Djilali Benyerou, El Bahri Ould Chikh, Habib Khellafi, Hadj Miloud Meddah, Ali Benhamena, Kaddour Hachelaf, Abdellah Lounis

“…Three-dimensional numerical modeling by the finite element method makes it possible to determine the best representation of the weld joint for a good prediction of its behavior. Comparison of the results shows that there is a good agreement between the numerical modeling predictions and the experimental results.…”
Get full text

Task offloading optimization in mobile edge computing based on a deep reinforcement learning algorithm using density clustering and ensemble learning by Yi Qin, Junyan Chen, Lei Jin, Rui Yao, Zidan Gong

“…It trains multiple models using ensemble learning methods to obtain a combination of prediction results. Secondly, DCEDRL utilizes an optimized density clustering method to identify and classify computing tasks with similar characteristics to improve subsequent task scheduling and resource allocation efficiency. …”
Get full text

Developing the US Wildland Fire Decision Support System by Erin K. Noonan-Wright, Tonja S. Opperman, Mark A. Finney, G. Thomas Zimmerman, Robert C. Seli, Lisa M. Elenz, David E. Calkin, John R. Fiedler

“…WFDSS accesses national weather data and forecasts, fire behavior prediction, economic assessment, smoke management assessment, and landscape databases to efficiently formulate and apply information to the decision making process. …”
Get full text

A Cosmic Ray Acceleration Mechanism Based on Background Flow Velocity Inhomogeneities Yielding Power-law Spectra by J.-F. Wang, G. Qin

Get full text

Effect of Rotation Speed and Flow Rate on Slip Factor in a Centrifugal Pump by Bo Chen, Baolin Song, Bicheng Tu, Yiming Zhang, Xiaojun Li, Zhigang Li, Zuchao Zhu

“…The modified model is suitable for the correction of slip factor at part-load flow rates and serves as a guide for the hydraulic performance design and prediction of centrifugal pumps.…”
Get full text

Approaches to evaluate nutrition of minerals in food by Xuan Wang, Yifan He, Qian Gao, Dong Yang, Jianfen Liang

“…Chemical methods are first developed, and mainly simulating the digestion environment to give a rough prediction of mineral bioavailability. In vitro models mainly used different cells to simulate the process and environment of food digestion to assess the availability of minerals. …”
Get full text

Polluting potential of post-Fenton products in landfill leachate treatment by M.R. Sabour, A. Amiri

“…The results were in good agreement with determination coefficient (R2) of 0.94–0.97, prediction R2 of 0.80–0.93 and coefficient of variation less than 10.…”
Get full text

Novel Optimization Algorithms Usage to Model the Compressive Strength of Ultra-High-Performance Concrete in Machine Learning Technique: Support Vector Regression by Tianhua Zhou, Dorota Mozyrska

“…This study suggested a machine learning method for predicting the CS of UHPC including support vector regression (SVR). …”
Get full text

Experimental Study of Site-Specific Soil Water Content and Rainfall Inducing Shallow Landslides: Case of Gakenke District, Rwanda by Martin Kuradusenge, Santhi Kumaran, Marco Zennaro, Albert Niyonzima

“…These values are used as thresholds for LEWS for that specific site to improve predictions.…”
Get full text

Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth by Haewon Byeon, Azzah AlGhamdi, Ismail Keshta, Mukesh Soni, Sultonali Mekhmonov, Gurpreet Singh

“…It preserved shared power distribution characteristics and outperformed traditional and multi-model approaches in efficiency and prediction accuracy.DiscussionDLUPLF effectively addresses data imbalance and model complexity challenges, making it a promising solution for urban power load forecasting. …”
Get full text

Austenite Grain Growth Kinetics in API X65 and X70 Line-Pipe Steels during Isothermal Heating by Asiful Hossain Seikh, Mahmoud S. Soliman, Abdulhakim AlMajid, Khaled Alhajeri, Waleed Alshalfan

“…Good agreement is obtained between the prediction of the model and the experimental grain size values.…”
Get full text