A deep learning-driven multi-layered steganographic approach for enhanced data security by Yousef Sanjalawe, Salam Al-E’mari, Salam Fraihat, Mosleh Abualhaj, Emran Alzubi

“…Extensive evaluations using benchmark datasets, including Tiny ImageNet, COCO, and CelebA, demonstrate the approach’s superior performance. …”
Get full text

Anomaly detection in multidimensional time series for water injection pump operations based on LSTMA-AE and mechanism constraints by Mei Wang, Xinyuan Zhu, Guangyue Zhou, Kewen Li, Qingshan Wu, Wankai Fan

“…Experimental results demonstrate that this approach significantly outperforms methods such as polynomial interpolation, random forest, and LSTM-AE in terms of anomaly detection accuracy on field datasets from oilfields, accompanied by a notably lower false alarm rate.…”
Get full text

Collaborative Knowledge Infusion for Low-Resource Stance Detection by Ming Yan, Tianyi Zhou Joey, W. Tsang Ivor

“…To assess the effectiveness of our method, we conduct extensive experiments on three public stance detection datasets, including low-resource and cross-target settings. …”
Get full text

Preliminary Results on Irradiance Measurements from Lyra and Swap by S. T. Kumara, R. Kariyappa, M. Dominique, D. Berghmans, L. Damé, J. F. Hochedez, V. H. Doddamani, Lakshmi Pradeep Chitta

“…The first and preliminary results of the photometry of Large Yield Radiometer (LYRA) and Sun Watcher using Active Pixel system detector and Image Processing (SWAP) onboard PROBA2 are presented in this paper. …”
Get full text

A phenotype-based AI pipeline outperforms human experts in differentially diagnosing rare diseases using EHRs by Xiaohao Mao, Yu Huang, Ye Jin, Lun Wang, Xuanzhong Chen, Honghong Liu, Xinglin Yang, Haopeng Xu, Xiaodong Luan, Ying Xiao, Siqin Feng, Jiahao Zhu, Xuegong Zhang, Rui Jiang, Shuyang Zhang, Ting Chen

“…The AI system was developed and evaluated on diverse, multi-country rare disease datasets, comprising 2271 cases with 431 rare diseases. …”
Get full text

Robust and Sparse Kernel-Free Quadratic Surface LSR via L_2,p-Norm With Feature Selection for Multi-Class Image Classification by Yongqi Zhu, Zhixia Yang, Junyou Ye, Yongxing Hu

“…Extensive experiments on synthetic and real datasets validate the effectiveness of our method, surpassing other state-of-the-art methods in terms of classification accuracy and feature selection performance.…”
Get full text

Modeling compositional heterogeneity resolves deep phylogeny of flowering plants by Yongli Wang, Yan-Da Li, Shuo Wang, Erik Tihelka, Michael S. Engel, Chenyang Cai

“…Under site-heterogeneous models, the approximately unbiased test favored our preferred tree recovered from various datasets: Ceratophyllales (coontails) are robustly recovered as sister to monocots, and they together are sister to the clade comprising magnoliids, Chloranthales, and eudicots. …”
Get full text

MLDFNet: A Multilabel Dual-Flow Network for Change Detection in Bitemporal Remote Sensing Images by Daniyaer Sidekejiang, Panpan Zheng, Liejun Wang

“…Extensive experiments demonstrate that MLDFNet significantly outperforms existing state-of-the-art methods, achieving outstanding F1 scores of 91.72%, 97.84%, and 94.85% on the LEVIR-CD, CDD, and BCDD datasets, respectively. These results validate its superior performance and potential value in real-world remote sensing applications.…”
Get full text

PPARG Could Work as a Valid Therapeutic Strategy for the Treatment of Lung Squamous Cell Carcinoma by Shunbin Shi, Guiping Yu, Bin Huang, Yedong Mi, Yan Kang, Julia Pia Simon

“…First, we used mega-analysis and partial mega-analysis to analyze the effects of PPARG on LSCC by using 12 independent LSCC expression datasets (285 healthy controls and 375 LSCC cases). …”
Get full text

Secretary bird optimization algorithm based on quantum computing and multiple strategies improvement for KELM diabetes classification by Yu Zhu, Mingxu Zhang, Qinchuan Huang, Xianbo Wu, Li Wan, Ju Huang

“…Comparative experiments with other classification models are conducted on diabetes datasets. The experimental results indicate that the QHSBOA-KELM classification model outperforms other comparative models in four evaluation metrics: accuracy (ACC), Matthews correlation coefficient (MCC), sensitivity, and specificity. …”
Get full text

Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework by Jiahua Sun, Jiawen Li, Jiawen Li, Jiawen Li, Jiawen Li, Ronghui Li, Ronghui Li, Ronghui Li, Langtao Wu, Liang Cao, Liang Cao, Liang Cao, Liang Cao, Molin Sun, Molin Sun, Molin Sun

“…The experimental results indicate that the proposed framework achieves the highest level of ship monitoring accuracy when evaluated on three distinct ship monitoring datasets. Even in the case of unfamiliar ships, where the detection performance of conventional models significantly deteriorates, the framework maintains stable and efficient detection capabilities. …”
Get full text

High-resolution X-ray phase-contrast tomography of human placenta with different wavefront markers by Sara Savatović, Davis Laundon, Fabio De Marco, Mirko Riedel, Jörg U. Hammel, Madleen Busse, Murielle Salomé, Lorella Pascolo, Irene Zanette, Rohan M. Lewis, Julia Herzen, Pierre Thibault

“…Within this study, we assess reconstruction quality achieved with all three evaluated phase-contrast methods. Both MBI datasets are processed with the Unified Modulated Pattern Analysis (UMPA) model, a pattern-matching algorithm. …”
Get full text

Assessing Methods to Measure Stem Diameter at Breast Height with High Pulse Density Helicopter Laser Scanning by Matthew J. Sumnall, Ivan Raigosa-Garcia, David R. Carter, Timothy J. Albaugh, Otávio C. Campoe, Rafael A. Rubilar, Bart Alexander, Christopher W. Cohrs, Rachel L. Cook

“…The stem classification method required comparatively little development of statistical models to provide estimates, which ultimately had a similar level of accuracy (RMSE < 1 cm) to PREV. HALS datasets can measure broad-scale forest plantations and reduce field efforts and should be considered an important tool for aiding in inventory creation and decision-making within forest management.…”
Get full text

Surface runoff estimation in an upper watershed using geo-spatial based soil conservation service-curve number method by C.A. Odiji, O.M. Aderoju, M.C. Ekwe, D.T. Oje, J.O. Imhanfidon

“…The study estimates the surface runoff of Upper Benue watershed using a geospatial based soil conservation service curve number model. Datasets utilized for this purpose are; Rainfall, land use, digitial elevation model and FAO-Soil. …”
Get full text

Advances in bioinformatics and multi-omics integration: transforming viral infectious disease research in veterinary medicine by Alyaa Elrashedy, Walid Mousa, Mohamed Nayel, Akram Salama, Ahmed Zaghawa, Ahmed Elsify, Mohamed E. Hasan

“…With significant advancements in bioinformatics and NGS, researchers can now identify contigs, which are contiguous sequences of DNA that are assembled from overlapping fragments, assemble a complete genome, perform phylogenetic analysis to diagnose, investigate the risk of viral diseases in animals, handle and share large biological datasets across various species. Additionally, multi-omics data integration further deepens our understanding of homology, divergence, mutations, and evolutionary relationships, providing a comprehensive perspective on the molecular mechanisms driving animal pathogens infections. …”
Get full text

Effects of climate change on wet and dry spells in Kelantan River basin using physically-based hydrological model and CMIP6 scenarios by Nurul Afiqah Mohamad Arbai, Masayasu Irie

“…Study focus: This study integrated CMIP6 datasets with the Rainfall-Runoff-Inundation (RRI) model to assess the influence of the four main Shared Socio-economic Pathways (SSPs) on the temporal discharge of the Kelantan River. …”
Get full text

The Use of Multiple Correspondence Analysis to Explore Associations between Categories of Qualitative Variables in Healthy Ageing by Patrício Soares Costa, Nadine Correia Santos, Pedro Cunha, Jorge Cotter, Nuno Sousa

“…The main focus of this study was to illustrate the applicability of multiple correspondence analysis (MCA) in detecting and representing underlying structures in large datasets used to investigate cognitive ageing. Principal component analysis (PCA) was used to obtain main cognitive dimensions, and MCA was used to detect and explore relationships between cognitive, clinical, physical, and lifestyle variables. …”
Get full text

Textural analysis and artificial intelligence as decision support tools in the diagnosis of multiple sclerosis – a systematic review by Filip Orzan, Ştefania D. Iancu, Laura Dioşan, Zoltán Bálint

“…Evaluation metrics such as Accuracy, Dice score, and Sensitivity are commonly employed, with some models demonstrating robustness across multi-center datasets. However, most studies lack validation in clinical scenarios.DiscussionThe absence of consensus on the optimal model for MS lesion segmentation highlights the need for standardized methodologies and clinical validation. …”
Get full text

Using a YOLO Deep Learning Algorithm to Improve the Accuracy of 3D Object Detection by Autonomous Vehicles by Ramavhale Murendeni, Alfred Mwanza, Ibidun Christiana Obagbuwa

“…The adapted model, tested on real-world datasets, demonstrates a significant increase in 3D detection accuracy, achieving a mean average precision (mAP) of 85%, intersection over union (IoU) of 78%, and near real-time performance at 93–97% for detecting vehicles and 75–91% for detecting people. …”
Get full text

Multi-Step Forecasting of Chlorophyll Concentration with Multi-Attention Collaborative Network by Yingying Jin, Feng Zhang, Xia Wang, Lei Wang, Kuo Chen, Liangyu Chen, Yutao Qin, Ping Wu

“…T-net works on the target variable, and both its encoder and decoder are related to NP-net to use the output of NP-net for assistance in learning and prediction. Two actual datasets are used in the experiments, which show that the MACN performs better than various kinds of state-of-the-art techniques.…”
Get full text