XpressO: An explanatory deep learning pipeline for the prediction and visualization of gene expression heterogeneity in breast tumors DOI
Shrey Sukhadia, Digvijay Yadav,

V. Madhusudhan Rao

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Июнь 5, 2025

Abstract Spatial genetic heterogeneity plays a critical role in tumor evolution and therapeutic resistance, yet traditional histopathological characterization remains challenging time-consuming. Here, we present an explainable deep learning pipeline “XpressO” that predicts visualizes gene expression directly from whole slide images (WSIs), providing spatial resolution of transcriptomics. Using image features WSIs invasive breast cancer as data associated bulk RNA sequencing The Cancer Genome Atlas (TCGA) labels, our model forms complex associations between tissue phenotype expression. By generating high-resolution maps, approach reveals both variation predicted activity across samples, capturing patterns are often lost profiling. interpretability framework further highlights histological regions contribute to specific signals, bridging the gap histology heterogeneity. This method offers promising tool for integrating imaging transcriptomics, enabling data-driven biomarker discovery advancing precision oncology through spatially-informed molecular

Язык: Английский

A Novel Forecasting Framework Leveraging Large Language Model and Machine Learning for Methanol Price DOI
Wenyang Wang,

Yuping Luo,

Mingrui Ma

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 135123 - 135123

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

3
A Spatiotemporal Graph Transformer Network for real-time ball trajectory monitoring and prediction in dynamic sports environments DOI Creative Commons
Z. Li, Dan Yu

Alexandria Engineering Journal, Год журнала: 2025, Номер 119, С. 246 - 258

Опубликована: Фев. 5, 2025

Язык: Английский

Процитировано

2
Utilizing Feature Selection Techniques for AI-Driven Tumor Subtype Classification: Enhancing Precision in Cancer Diagnostics DOI Creative Commons
Jihan Wang,

Zhengxiang Zhang,

Yangyang Wang

и другие.

Biomolecules, Год журнала: 2025, Номер 15(1), С. 81 - 81

Опубликована: Янв. 8, 2025

Cancer's heterogeneity presents significant challenges in accurate diagnosis and effective treatment, including the complexity of identifying tumor subtypes their diverse biological behaviors. This review examines how feature selection techniques address these by improving interpretability performance machine learning (ML) models high-dimensional datasets. Feature methods-such as filter, wrapper, embedded techniques-play a critical role enhancing precision cancer diagnostics relevant biomarkers. The integration multi-omics data ML algorithms facilitates more comprehensive understanding heterogeneity, advancing both personalized therapies. However, such ensuring quality, mitigating overfitting, addressing scalability remain limitations methods. Artificial intelligence (AI)-powered offers promising solutions to issues automating refining extraction process. highlights transformative potential approaches while emphasizing future directions, incorporation deep (DL) integrative strategies for robust reproducible findings.

Язык: Английский

Процитировано

1
Strength prediction of recycled concrete using hybrid artificial intelligence models with Gaussian noise addition DOI
Yaqin Geng, Yongcheng Ji, Dayang Wang

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 149, С. 110566 - 110566

Опубликована: Март 18, 2025

Язык: Английский

Процитировано

1
Machine learning insights into scapular stabilization for alleviating shoulder pain in college students DOI Creative Commons

Omar M. Mabrouk,

Doaa A. Abdel Hady, Tarek Abd El‐Hafeez

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 18, 2024

Abstract Non-specific shoulder pain is a common musculoskeletal condition, especially among college students, and it can have negative impact on the patient’s life. Therapists used scapular stabilization exercises (SSE) to enhance control mobility. This study investigates prediction of stability in treating non-specific pain, leveraging advanced machine learning techniques for comprehensive evaluation analysis. Using diverse range regression models, including Gamma Regressor, Tweedie Poisson others, examines relationship between effectiveness various their management. Furthermore, employs optimization techniques, such as Hyperopt, scikit-optimize, optunity, GPyOpt, Optuna, fine-tune exercise protocols optimal outcomes. The results reveal that exercises, when optimized using algorithms, significantly contribute reducing students. Among scikit-optimize demonstrated best performance, resulting mean squared error 0.0085, absolute 0.0712, an impressive R2 score 0.8501. indicates approach yielded most accurate predictions effectively captured findings highlight critical role interventions ameliorating underscore potential optimizing therapeutic strategies health utilization particular, showcases its fine-tuning study’s serve crucial stepping stone developing personalized rehabilitation programs emphasizing importance integrating methodologies assessment treatment disorders

Язык: Английский

Процитировано

4
Decision-Making and Clustering Algorithms Based on the Scored-Energy of Hesitant Fuzzy Soft Sets DOI Creative Commons
José Carlos R. Alcantud, Nenad Stojanović,

Ljubica Djurović

и другие.

International Journal of Fuzzy Systems, Год журнала: 2025, Номер unknown

Опубликована: Фев. 19, 2025

Язык: Английский

Процитировано

0
Audio Deepfake Detection Using Deep Learning DOI Creative Commons
Ousama A. Shaaban, Remzi Yıldırım

Engineering Reports, Год журнала: 2025, Номер 7(3)

Опубликована: Март 1, 2025

ABSTRACT This study introduces an enhanced Siamese convolutional neural network (Siamese CNN) architecture with a novel StacLoss function and self‐attention modules for efficient identification of audio deepfakes. Our module directly compares unprocessed original modified by initially applying operations dual branches to extract complex characteristics from raw signals. These are followed residual connections, which enhance the network's performance. The trained in layered way alongside these fundamental layers detect multi‐headed attention within frames. output represents customized version contrastive loss function. It aids distinguishing between audios minimizing pairs that have same identity while maximizing distance manipulated samples enhances process extracting features compared standard techniques. efficacy method has been verified examining range modifications, its resilience thoroughly assessed on ASVspoof2019 dataset comprehensive testing across all possible manipulation situations. proposed (CNN) outperformed both machine deep learning models, achieving impressive metrics. achieved remarkable accuracy 98%, precision 97%, recall 96%, F 1 score 96.5%, ROC‐AUC 99%, equal error rate (EER) 2.95%.

Язык: Английский

Процитировано

0
Deep learning for algorithmic trading: A systematic review of predictive models and optimization strategies DOI Creative Commons
Mohiuddin Ahmed Bhuiyan, Md. Oliullah Rafi,

Gourab Nicholas Rodrigues

и другие.

Array, Год журнала: 2025, Номер unknown, С. 100390 - 100390

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
A Probabilistic Hesitant Fuzzy Multi-Criteria Decision-Making Method Based on CSOGRMILP and Borda-CoCoSo DOI
Jiafu Su, Baojian Xu, Hongyu Liu

и другие.

International Journal of Fuzzy Systems, Год журнала: 2025, Номер unknown

Опубликована: Апрель 7, 2025

Язык: Английский

Процитировано

0
Switched Control for Uncertain Switched Fuzzy Time-Varying Delay Systems with Actuator Saturation DOI
Liang Yu, Hong Yang, Hongyuan Ma

и другие.

International Journal of Fuzzy Systems, Год журнала: 2025, Номер unknown

Опубликована: Апрель 22, 2025

Язык: Английский

Процитировано

0