ANALYZING THE EFFECTIVE FACTORS IN REDUCING APPLE WASTES IN WEST AZARBAIJAN PROVINCE by Hazhar PANAH, Loghman RASHIDPOUR, Soleiman RASOULIAZAR

“…The reliability of the questionnaire was confirmed by Cronbach Alfa coefficient (83%). The data was analyzed by using descriptive and inferential methods (percent, mean, correlation coefficient and regression analysis) by using SPSS statistical software. …”
Get full text

Age assessment at the time of death based on panoramic radiography by Đurić Marija, Rakočević Zoran, Ranković Nenad

“…With the four parameters included in equations, the error was ± 2.55 years. Conclusion. This preliminary analysis showed that the conventional regression technique could be appropriate for the age estimation based on panoramic radiography, and that an additional study with a larger sample and on wider population was required.…”
Get full text

Factors Predicting Fertility Rate in Indonesia by Yusni Maulida, H Harlen, Delfi Ranta Sari, Tehubijuluw Zacharias

“…Multiple regression analysis methods with Error Correction Model (ECM) analysis technique were applied. …”
Get full text

IRRIGATED YIELD ESTIMATION OF Populus Nigra STANDS IN NINEVEH PLANTATION by Muzahim .S. younis

“…Consequence of the use of Non-Linear function in this study, which is believed to be in harmonic with the characteristics of tree stand, twelve trees were selected which represents different location over an area planted with Populus nigra trees ,and after data analysis of variable values , three mathematical equations were obtains which link the yield per area ,a dependent variable and age ,mean height of stand quadratic mean diameter as the independent variable , in order to obtain yield table of revocable densities for Populus nigra , selecting the best model , different measures of precision , such as , coefficient of determination, standard error of estimate and residual analysis test, so following regressions selected : Y= 4.1356 G1.12355 R2= 0.9796 S.E=1.8 Y= 0.12788H2.27 R2= 0.913 S.E=3.54 Y= -0.64168+0.34744A2+0.063183Dq2.4 R2= 0.9674 S.E=2.29 Since there are good values of precision measures , so we will be able to use equations to prepare yield table at different densities of Populus nigra stands in Nineveh, depending on mean height or basal area per hectare or for age and quadratic mean. …”
Get full text

Towards responsible artificial intelligence in education: a systematic review on identifying and mitigating ethical risks by Haotian Zhu, Yao Sun, Junfeng Yang

“…In the technology dimension, risks include privacy invasion, data leakage, algorithmic bias, the black box algorithm, and algorithmic error. …”
Get full text

Predicting Flight Delays with Machine Learning: A Case Study from Saudi Arabian Airlines by Meshal Alfarhood, Rakan Alotaibi, Bassam Abdulrahim, Ahmad Einieh, Mohammed Almousa, Abdulrhman Alkhanifer

“…To achieve this, we collected flight information from September 2017 to April 2023, along with weather data, and performed extensive feature engineering to extract informative features to train our model. …”
Get full text

Probabilistic Forecasting of Crude Oil Prices Using Conditional Generative Adversarial Network Model with Lévy Process by Mohammed Alruqimi, Luca Di Persio

“…This paper introduces a Crude Oil-Driven Conditional GAN (CO-CGAN), a hybrid model for enhancing crude oil price forecasting by combining advanced AI frameworks (GANs), oil market sentiment analysis, and stochastic jump-diffusion models. By employing conditional supervised training, the inherent structure of the data distribution is preserved, thereby enabling more accurate and reliable probabilistic price forecasts. …”
Get full text

Computed Tomography-Based Estimation of Facial Soft-Tissue Thickness for Forensic Facial Reconstruction among Manipuri Population by Dhimi Nongmeikapam, Smitha Rani, Swathi Kumareswar, Nitin V. Muralidhar, K. Stavelin Abhinandithe, N. Divyashree

“…Descriptive statistics were applied and 10 samples were selected randomly to check the inter-observer variability by two examiners, technical error of measurement (TEM) was calculated, and paired t-test and correlation analysis were adopted. …”
Get full text

COMPARISONS BETWEEN ROBUST REGRESSION APPROACHES IN THE PRESENCE OF OUTLIERS AND HIGH LEVERAGE POINTS by Anwar Fitrianto, Sim Hui Xin

“…The error term in the regression model must be identically and independently comes from a Normal distribution. …”
Get full text

Investigating the Impact of Supply Chain Dynamics on Financial Performance with Supply Chain Disruption Structure Approach by Ebrahim Farbod, Alireza Hamidieh, Hootan Amininia

“…Analysis of variance-based structural equations has been used to analyze the data.Findings: The study results show that the dynamics and flexibility of the supply chain in the face of disruptions affect financial performance with the mediating role of supply chain resilience. …”
Get full text

Rapid Assessment of the Fatigue Limit Using an Iterative Algorithm Applied to Intrinsic Dissipation by Luca Santoro, Raffaella Sesana, Francesca Maria Curà

“…The algorithm seeks to minimize the error between experimental data and the fitted curves, ensuring continuity at the estimated fatigue limit. …”
Get full text

Long-Term Solar Irradiance Forecasting by Braga D., Chicco G., Golovanov N.

“…The modeling includes pre-processing of historical data used for forecasting and post-processing of the types of days resulted from the clustering analysis. …”
Get full text

The short video platform recommendation mechanism based on the improved neural network algorithm to the mainstream media by Mengruo Qi

“…Therefore, in order to address the data sparsity and high-dimensional feature extraction, this study proposes a novel short video platform recommendation model. …”
Get full text

Adaptive Autoencoder-Based Intrusion Detection System with Single Threshold for CAN Networks by Donghyeon Kim, Hyungchul Im, Seongsoo Lee

“…The proposed autoencoder model was trained exclusively on normal data. A portion of the attack data was utilized to determine the optimal detection threshold using a Gaussian kernel density estimation function, while the frame count was selected based on error rate analysis. …”
Get full text

An Ultra-Short-Term Wind Power Prediction Method Based on the Fusion of Multiple Technical Indicators and the XGBoost Algorithm by Xuehui Wang, Yongsheng Wang, Yongsheng Qi, Jiajing Gao, Fan Yang, Jiaxuan Lu

Get full text

Kernel Density Estimated Linear Regression by Roshan Kalpavruksha, Rohan Kalpavruksha, Teryn Cha, Sung-Hyuk Cha

“… Regression analysis is a cornerstone of predictive modeling, with linear regression and kernel regression standing as two of its most prominent paradigms. …”
Get full text

Improved integral neural distinguisher model for lightweight cipher PRESENT by Wanqing Wu, Mingyu Guo

“…Simultaneously, this paper incorporates MBConv module into the convolutional layers of DenseNet, which enable the neural network to identify a greater variety of features in ciphertext. The data format of the paper is analysed. The results of the analysis show that the data format in this paper is able to identify more features compared to Zahednejad’s data format. …”
Get full text

Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain by Pratixita Bhattacharjee, Piotr Augustyniak

“…Then, the ECG-ID database for real data analysis was used. Filtering to remove baseline wander followed by evaluation and testing were carried out in the real patient data. …”
Get full text

Substation Modelling and Network Security Monitoring Based on Scene Replication Technology by Xiaohu WANG, Guangxin Guo, Jiahan DONG, Lei WANG, Can CAO

“…The repetition structures in the IOT safety scenario are automatically recognized to realize data augmentation and structure modelling. The proposed algorithm can minimize the fitting error between the model and the original point cloud, so that the three-dimensional model of the power equipment objects can be obtained quickly, and the intelligent understanding and high quality reconstruction of the large scene of transmission and transformation can be realized finally. …”
Get full text

Weld seam location with adaptive fracture repair on minor-caliber pipe by Yong Yan, Jingyu Zhang, Lingjiang Guo, Heming Zhao, Fan Zhang

“…The framework consists of three primary stages: (1) Image preprocessing utilizes a hybrid median filter and fixed threshold segmentation to enhance contrast, suppress salt-and-pepper noise, and preserve edge details. (2) Centerline extraction employs an improved maximal disk-based skeleton algorithm to generate single-pixel-width centerlines, followed by Freeman chain code tracking and data storage. Connectivity analysis via BFS ensures topological consistency among fragment skeletons. (3) Adaptive repair and smoothing method adopts least squares optimization to integrate broken skeleton segments through geometric constraints, achieving continuous sub-pixel trajectories. …”
Get full text