Impact of training data composition on the generalizability of convolutional neural network aortic cross-section segmentation in four-dimensional magnetic resonance flow imaging by Chiara Manini, Markus Hüllebrand, Lars Walczak, Sarah Nordmeyer, Lina Jarmatz, Titus Kuehne, Heiko Stern, Christian Meierhofer, Andreas Harloff, Jennifer Erley, Sebastian Kelle, Peter Bannas, Ralf Felix Trauzeddel, Jeanette Schulz-Menger, Anja Hennemuth

Get full text

Land cover changes in grassland landscapes: combining enhanced Landsat data composition, LandTrendr, and machine learning classification in google earth engine with MLP-ANN scenario forecasting by Cecilia Parracciani, Daniela Gigante, Onisimo Mutanga, Stefania Bonafoni, Marco Vizzari

Get full text

Interval price prediction of livestock product based on fuzzy mathematics and improved LSTM. by Weimin Ma, Lingling Peng, Hu Chen, Haisheng Yan

“…Three main steps are taken: (1) data composition and reconstruction, to extract a set of relatively stationary subsequence components by complementary ensemble empirical mode decomposition (CEEMD) from original signal, and divide these components into three groups according to fuzzy entropy (FE) value. (2) characteristics categorization, determining the lower bound, mean, and upper bound of the rebuilt data via fuzzy information granulation (FIG) to better characterize the price fluctuation range. (3) price prediction, including point and interval predictions with attention mechanism long short-term memory (AM-LSTM). …”
Get full text

Predicting Rainfall for Farming in the Bantul Region Using an Artificial Neural Network by Salsalbilla Septya, Riyadi Slamet, Zaki Ahmad, Nursetiawan Nursetiawan

“…The test results show that the comparison of the actual data results of rainfall prediction using the Levenberg Marquart algorithm with 1,080 training data of 80% data composition, validation data 10 and test data 10 with layer 4 size with layer 10 hidden neural produces predictions with a good level of accuracy and obtains a value of R = 0.900.…”
Get full text

Characterizing Heterogeneity within Head and Neck Lesions Using Cluster Analysis of Multi-Parametric MRI Data. by Marco Borri, Maria A Schmidt, Ceri Powell, Dow-Mu Koh, Angela M Riddell, Mike Partridge, Shreerang A Bhide, Christopher M Nutting, Kevin J Harrington, Katie L Newbold, Martin O Leach

“…Principal component analysis and cluster validation were employed to investigate data composition and to independently determine the optimal number of clusters. …”
Get full text

Quantifying Gender Bias in Large Language Models Using Information-Theoretic and Statistical Analysis by Imran Mirza, Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari

“…These findings demonstrate how architectural decisions, training data composition, and token embedding strategies critically influence gender representation. …”
Get full text

Lower-Complexity Multi-Layered Security Partitioning Algorithm Based on Chaos Mapping-DWT Transform for WA/SNs by Tarek Srour, Mohsen A. M. El-Bendary, Mostafa Eltokhy, Atef E. Abouelazm, Ahmed A. F. Youssef, Ali M. El-Rifaie

“…The lower-complexity cryptographic algorithm is proposed, based on merging the data composition tools utilizing data transforms and chaos mapping techniques. …”
Get full text

PHILDER: Lightweight Framework for Intelligent Phishing Detection on Resource-Limited Devices by Guilherme Dantas Bispo, Cesar Augusto Borges de Andrade, Gabriela Mayumi Saiki, Raquel Valadares Borges, Andre Luiz Marques Serrano, Geraldo Pereira Rocha Filho, Vinicius Pereira Goncalves

“…The main contributions of this paper include the application of computational efficiency metrics for model evaluation, which not only consider traditional metrics but also enable assessment in real-world applications under hardware computational constraints, and the exploration of different data composition strategies for training. The use of PHILDER (TinyBERT combined with data balancing techniques) demonstrates a promising approach for the automatic detection of phishing in emails, contributing to strengthening digital security against social engineering attacks.…”
Get full text

Safe AI for coral reefs: Benchmarking out-of-distribution detection algorithms for coral reef image surveys by Mathew Wyatt, Sharyn Hickey, Ben Radford, Manuel Gonzalez-Rivero, Nader Boutros, Nikolaus Callow, Nicole Ryan, Arjun Chennu, Mohammed Bennamoun, James Gilmour

“…We show with a comparative analysis that the performance of OOD detection algorithms is variable, and highly dependent on in-distribution and out-of-distribution data composition. We show that KNN (K-Nearest Neighbour) distance was the most consistent across datasets, followed by Virtual-logit matching (ViM). 3. …”
Get full text

Have Indigenous regions been left behind? Three decades of development and disparity in Odisha, India by Laxmikanta Gual, Amarendra Das

“…Using district-level data, Composite Development Indices (CDIs) are constructed from 11 consistent socioeconomic indicators to analyze patterns of regional development and disparity over nearly three decades. …”
Get full text

Composite likelihood inference for analysis of individual animal identification data by Xueli Xu, Xiaoyue Zhang, Hal Whitehead, Dehan Kong, Ximing Xu

Get full text

Predictive machine learning and multimodal data to develop highly sensitive, composite biomarkers of disease progression in Friedreich ataxia by Susmita Saha, Louise A. Corben, Louisa P. Selvadurai, Ian H. Harding, Nellie Georgiou-Karistianis

Get full text

Estimation of Lunar FeO and TiO₂ with Support Vector Regression Analysis and Evaluation of the Stokes Parameter Using M3 and LRO Mini RF Data by A. K. Padinharethodi, S. Kumar, Advaith CA

“…Catharina crater of the lunar near side is taken as the study area and FeO and TiO₂ wt% of the crater are estimated with M3 data. Composite chemical content (FeO wt%+ TiO₂ wt %) of the Catharina crater is estimated. …”
Get full text

PERAMALAN INDEKS HARGA SAHAM GABUNGAN (IHSG) DENGAN METODE FUZZY TIME SERIES MARKOV CHAIN by Y Aristyani, E Sugiharti

“…Historical data is taken from Data Composite Index (JCI) in the period of January 2010 to February 2014. …”
Get full text

Deep learning of the particulate and mineral-associated organic carbon fractions using a compositional transform and mid-infrared spectroscopy by Mingxi Zhang, Zefang Shen, Lewis Walden, Farid Sepanta, Zhongkui Luo, Lei Gao, Oscar Serrano, Raphael A. Viscarra Rossel

“…We used the centred log ratio (CLR) method to transform the data compositionally and then modelled POCmac, POCmic, POC (POCmac + POCmic), and MAOC with the spectra, using convolutional neural networks (CNN) and cubist for benchmarking. …”
Get full text

Screening Elite Genotypes of Durum Wheat Based on Univariate and Multivariate Stability Models under Unpredictable Environments by Sharyar Sasani, Armin Saed-Moucheshi

“…After adjusting the data, composite variance analysis was performed considering year × genotype in relation to grain yield. …”
Get full text