Machine learning anomaly detection of lost and unaccounted for gas in natural gas networks by Omar Fayez Mohamed ElMahdy, Mohamed Ezz Hassan, Sayed M. Metwalli

“…Although the metrics F1score, Precision, and Accuracy have substantially lower values than that of the Recall, they were useful in detecting data inhomogeneity. The PCA was used for better visualization and understanding of the networks under consideration. …”
Get full text

Multidimensional State Data Reduction and Evaluation of College Students’ Mental Health Based on SVM by Han Peiqing

“…A model experiment containing internal and external personality tendency classification, anxiety, and depression dichotomy was designed using logistic regression analysis, information entropy, and SVM algorithm to construct the feature dimensions of the network behavior data, combined with the labeled data of mental state to derive the sample data set for model experiments. …”
Get full text

Multifractal-Aware Convolutional Attention Synergistic Network for Carbon Market Price Forecasting by Liran Wei, Mingzhu Tang, Na Li, Jingwen Deng, Xinpeng Zhou, Haijun Hu

“…The multi-scale convolution (MSC) module employs multi-layer dilated convolutions constrained by shared convolution kernel weights to construct a scale-invariant convolutional network. By projecting and reconstructing time series data within a multi-scale fractal space, MSC enhances the model’s ability to adapt to complex nonlinear fluctuations while significantly suppressing noise interference. …”
Get full text

Differential dynamic functional network connectivity in different motor subtypes of Parkinson's disease by Yu Pan, Hang Qu, Yi Zhao, Zhaoxia Qin, Jiangbing Liu, Wei Wang

“…Resting-state functional magnetic resonance imaging (fMRI) data were obtained from all participants. Independent component analysis (ICA) and graph theory analyses were used to calculate the three groups’ dynamic functional network connectivity characteristics. …”
Get full text

Fatigue Characterization of EEG Brain Networks Under Mixed Reality Stereo Vision by Yan Wu, Chunguang Tao, Qi Li

“…Since visual fatigue involves multiple brain regions, our study aims to explore the topological characteristics of brain networks derived from electroencephalogram (EEG) data. …”
Get full text

Simulation and Empirical Studies of Long Short-Term Memory Performance to Deal with Limited Data by Khusnia Nurul Khikmah, Kusman Sadik, Khairil Anwar Notodiputro

“…This research is proposed to determine the performance of time series machine learning in the presence of noise, where this approach is intended to forecast time series data. The approach method chosen is long short-term memory (LSTM), a development of recurrent neural network (RNN). …”
Get full text

YOLOv8m for Automated Pepper Variety Identification: Improving Accuracy with Data Augmentation by Madalena de Oliveira Barbosa, Fernanda Pereira Leite Aguiar, Suely dos Santos Sousa, Luana dos Santos Cordeiro, Irenilza de Alencar Nääs, Marcelo Tsuguio Okano

“…Comparative analysis reveals that training with the augmented dataset yielded significant improvements across key performance indicators, particularly in box precision, recall, and mean average precision (mAP50 and mAP95), underscoring the effectiveness of data augmentation. …”
Get full text

Performance characterization and relationship modeling of in-situ asphalt mortar and mixture using data mining by Liheng Shu, Qiao Dong, Fujian Ni, Jiwang Jiang, Shuheng Yu, Bin Shi

Get full text

Efficient Method for Robust Backdoor Detection and Removal in Feature Space Using Clean Data by Donik Vrsnak, Marko Subasic, Sven Loncaric

“…The steady increase of proposed backdoor attacks on deep neural networks highlights the need for robust defense methods for their detection and removal. …”
Get full text

CORRELATION OF RADON AND SEISMIC ACTIVITY IN THE BAIKAL RIFT ZONE ACCORDING TO EMANATION MONITORING DATA by K. Zh. Seminsky, А. А. Bobrov

“…The obtained results, besides confirming the previously proposed model of radon field formation in the Baikal Region under the influence of external and internal forces, provide the for the identification of further stable precursors of strong earthquakes based on a comprehensive analysis of data from a branched emanation monitoring network.…”
Get full text

A hybrid deep learning-based approach for optimal genotype by environment selection by Zahra Khalilzadeh, Motahareh Kashanian, Saeed Khaki, Lizhi Wang

“…Using a new yield dataset containing 93,028 records of soybean hybrids across 159 locations, 28 states, and 13 years, with 5,838 distinct genotypes and daily weather data over a 214-day growing season, we developed two convolutional neural network (CNN) models: one that integrates CNN and fully-connected neural networks (CNN model), and another that incorporates a long short-term memory (LSTM) layer after the CNN component (CNN-LSTM model). …”
Get full text

A novel fusion of Sentinel-1 and Sentinel-2 with climate data for crop phenology estimation using Machine Learning by Shahab Aldin Shojaeezadeh, Abdelrazek Elnashar, Tobias Karl David Weber

“…We proposed a thorough feature selection analysis to find the best combination of RS and climate data to detect phenological stages. …”
Get full text

Enhanced Signal-to-Noise Ratio Estimation in Optical Fiber Communications: A Pilot-Based Approach by Mohamed Al-Nahhal, Ibrahim Al-Nahhal, Sunish Kumar Orappanpara Soman, Octavia A. Dobre

“…Additionally, features are directly extracted from the received data signal, such as average absolute deviation, entropy, and arithmetic mean, to capture its statistical dispersion characteristics. …”
Get full text

A Model for Predicting IoT User Behavior Based on Bayesian Learning and Neural Networks by Xin Xu, Chengning Huang, Yuquan Zhu

“…In this paper, the data are preprocessed by data merging and format processing, and then the association rules are mined by association rules analysis. …”
Get full text

Inventory control strategy based on neural network and fuzzy algorithm in intelligent warehousing system by Chunmei Xie, Cong Xie

“…Ablation analysis reveals that after removing the RBFNN module, the comprehensive average turnover rate decreases to 15.65, while the comprehensive average out-of-stock rate increases to 6.93%. …”
Get full text

Speed Grade Evaluation of Public-Transportation Lines Based on an Improved T-S Fuzzy Neural Network by Shunfeng Zhang, Peiqing Li, Biqiang Zhong, Jin Wu

“…The six-dimensional data of morning peak/evening peak average speed, average speed at peak, average station distance, proportion of dedicated lanes, and nonlinear coefficients were selected as input data for the neural network to output the operating speed grade of bus lines. …”
Get full text

Estimates of reference evapotranspiration in the municipality of Ariquemes (RO) using neural networks GMDH-type by Roberto L. da S. Carvalho, Angel R. S. Delgado

“…In order to contribute to the climatic understanding of Ariquemes, Rodônia state, Brazil, the study aims to model the behavior of the time series of reference evapotranspiration using a GMDH-type (Group Method of Data Handling) artificial neural network (ANN) and to compare it with the SARIMA (Seasonal Autoregressive Integrated Moving Average) methodology. …”
Get full text

Comprehensive Outlier Detection in Wireless Sensor Network with Fast Optimization Algorithm of Classification Model by Haiqing Yao, Heng Cao, Jin Li

“…Since the nonstationary distribution of the detected objects is general in the real world, the accurate and efficient outlier detection for data analysis within wireless sensor network (WSN) is a challenge. …”
Get full text

Analyzing crises in global financial indices using Recurrent Neural Network based Autoencoder. by Mimusa Azim Mim, Md Kamrul Hasan Tuhin, Ashadun Nobi

“…By training the RNN-AE with normalized stock returns, we derive correlations embedded in the model's weight matrices. To explore the network structure, we construct threshold networks based on the middle-layer weights for each year and examine key topological metrics, such as entropy, average clustering coefficient, and average shortest path length, providing new insights into the dynamic evolution of global stock market interconnections. …”
Get full text

Research on end-to-end network link delay inference based on link reconstruction-destruction by Yong-sheng LIANG, Bo GAO, Yue ZOU, Ji-hong ZHANG, Nai-tong ZHANG

“…Based on two assumptions,inference model and end-to-end delay data acquisition,an approach to end-to-end network internal link delay inference based on link reconstruction-deconstruction (LRD) was proposed.Pseudo likelihood estimation (PLE) was adopted and the inference problem was divided into independent sub-problems.Inference units with definite solution are determined by LRD.By means of controlling average sampling precision and decreasing inference unit links,the computation complexity of link delay inference was significantly lowered.Experimental study was performed based on model computation and NS2 simulation platform.Theoretical analysis and experimental results show that the approach is accurate and effective.…”
Get full text