SUMMIT: A SAR foundation model with multiple auxiliary tasks enhanced intrinsic characteristics by Yuntao Du, Yushi Chen, Lingbo Huang, Yahu Yang, Pedram Ghamisi, Qian Du

“…SUMMIT is pre-trained on the Multi-sensor SAR Image Dataset (MuSID), which contains over 560,000 SAR images. To enhance its feature extraction capability, we introduce a masked image modeling (MIM) framework with self-supervised auxiliary tasks (SSATs): (1) MIM for learning robust structural representations, (2) self-supervised denoising to improve the model’s noise resistance, and (3) space scattering feature enhancement to preserve geometric consistency. …”
Get full text

ViTMa: A Novel Hybrid Vision Transformer and Mamba for Kinship Recognition in Indonesian Facial Micro-Expressions by Ike Fibriani, Eko Mulyanto Yuniarno, Ronny Mardiyanto, Mauridhi Hery Purnomo

“…Thus, the ViTMa model with our proposed B16 quadratic feature fusion and multiplicative fusion strategy achieves the best performance and achieves better accuracy outperforming previous studies.…”
Get full text

Enhancing the YOLOv8 model for realtime object detection to ensure online platform safety by Mohammed Kawser Jahan, Fokrul Islam Bhuiyan, Al Amin, M. F. Mridha, Mejdl Safran, Sultan Alfarhood, Dunren Che

“…Our key contributions include enhancing the cross-stage partial fusion blocks and incorporating three additional convolutional blocks into the model head, leading to better feature extraction and detection capabilities. …”
Get full text

Deep learning model for hair artifact removal and Mpox skin lesion analysis and detection by Edeh Michael Onyema, B. Gunapriya, Balasubramanian Prabhu Kavin, Mueen Uddin, Priyan Malarvizhi Kumar, Tehseen Mazhar, Mamoon M. Saeed

“…Experimental evaluations indicate that the proposed approach significantly improves the accuracy of Mpox detection, surpassing the performance of existing models. The achieved accuracy, recall, and F1 scores for Mpox detection were 90%, 89%, and 86%, respectively. …”
Get full text

Mathematical Modelling Approaches for Integrated Single Machine Scheduling and Electric Vehicle Routing Problem by İclal Bağcı, Hande Öztop, Zeynel Abidin Çil

“…Numerical results indicate that the CP model has superior performance than the MILP model for the problem.…”
Get full text

An MILP Model for Optimizing Quality Inspection Allocation with Technology Selection and Variable Sampling Rates by Michele Ronchi, Cristian Cafarella, Matteo Gabellini, Alberto Regattieri, Mauro Gamberi

“…Motivated by gaps in the existing research, this paper proposes a novel MILP model that introduces several previously unaddressed capabilities in inspection planning. …”
Get full text

Numerical modeling of solid particles reduction in water clarifiers using Lattice Boltzmann method by E. Jaiuan, Y. Khunatorn

“…Particles with 13 different diameter sizes ranged from 20 μm to 850 μm were accounted for suspended solid modeling via discrete phase model (DPM). The numerical model presents the overall solid settling efficiency as 46 % and 78 % for CLR47 and CLR89 respectively. …”
Get full text

Optimized deep learning models for stress-based stroke prediction from EEG signals by Sivasankaran Pichandi, Gomathy Balasubramanian, Venkatesh Chakrapani, J. Samuel Manoharan

“…The effectiveness of the proposed model is validated through experiments conducted with the benched mark DEAP dataset, demonstrating its robust performance in both stress and stroke prediction.…”
Get full text

Establishment and Test Effect of Artificial Intelligence Optimization Model Based on Convolutional Neural Network by Chunrong Zhou, Zhenghong Jiang

“…In this paper, the optimized model (AL-CNN) is tested for noise image recognition, and the AL-CNN model is established by using activation functions, matrix operations, and feature recognition methods, and the noisy images are processed after custom configuration. …”
Get full text

Smart intrusion detection model to identify unknown attacks for improved road safety and management by Faisal Alshammari, Abdullah Alsaleh

“…Key parameters used for benchmarking include accuracy, detection rate, false alarm rate, precision, F1-Score and AUC-ROC, demonstrating the model’s balanced performance and computational efficiency. …”
Get full text

Surrogate modeling of passive microwave circuits using recurrent neural networks and domain confinement by Kaustab C. Sahu, Slawomir Koziel, Anna Pietrenko-Dabrowska

“…These can be mitigated by employing surrogate modeling methods, especially to expedite design workflows like local/global optimization or uncertainty quantification. …”
Get full text

Microscopic cracks identification and nonlinear creep model of shale under creep-disturbance loading by Jun-guang Wang, Zheng Ma, Yi-ran Cong, Qing-rong Yu, Lei Dong, Li-xuan Wang

“…Under the increase of disturbance amplitude of 2.5∼5.5MPa, the crack width and weighted average area at the fracture site decrease, while under the increase of disturbance frequency of 1∼3Hz, the crack width and weighted average area at the fracture site increase. A nonlinear creep model of rock disturbance based on the geometrical characteristics of cracks was established, and the overall performance of the model's fitting degree was excellent, and the fitting degree was approximately 93%. …”
Get full text

A vision-language model for predicting potential distribution land of soybean double cropping by Bei Gao, Yuefeng Liu, Yanli Li, Hongmei Li, Meirong Li, Wenli He

“…AgriCLIP employs advanced techniques including multi-scale data processing, self-supervised learning, and cross-modality feature fusion enabling comprehensive analysis of factors influencing crop suitability.Results and discussionExtensive evaluations on four diverse remote sensing datasets-RSICap RSIEval, MillionAID, and HRSID-demonstrate AgriCLIP’s superior performance over state-of-the-art models. …”
Get full text

Lactate-related lncRNAs assessment model predicts the prognosis of pancreatic ductal adenocarcinoma by Jing Sun, Tao Zhang, Shuai Zhu

“…Four LA-DElncRNAs were selected to develop clinical model, which demonstrated strong performance in survival prediction. …”
Get full text

Development of a model of an electrical complex for gas air cooling devices of gas field №1 gazprom dobycha Yamburg LLC with a centralized power supply system in the MATLAB/SIMULIN... by L. R. Maskov, V. Y. Kornilov

“…To analyze the energy efficiency of MMD ETC ACHE. To perform the experimental research of the EMD EMD ETC ACHE model in the dynamic modes in order to determine the regularity of the influence of single (group) starts on the power supply source overload. …”
Get full text

GraphGIM: rethinking molecular graph contrastive learning via geometry image modeling by Chaoyi Li, Hongxin Xiang, Wenjie Du, Tengfei Ma, Haowen Chen, Xiangxiang Zeng, Lei Xu

“…Results In this work, we revisit existing graph-based contrastive methods and find that these methods have limited diversity in the constructed sample pairs, resulting in insufficient performance gains. To alleviate the above challenge, we propose a novel molecular graph contrastive learning method via geometry image modeling, called GraphGIM, which enhances the diversity between sample pairs. …”
Get full text

Large multimodal model‐based standardisation of pathology reports with confidence and its prognostic significance by Ethar Alzaid, Gabriele Pergola, Harriet Evans, David Snead, Fayyaz Minhas

“…We have analysed the extraction performance in terms of accuracy and kappa scores, and the quality of the confidence scores assigned by the model. …”
Get full text

Comparative Analysis of Automated Machine Learning for Hyperparameter Optimization and Explainable Artificial Intelligence Models by Muhammad Salman Khan, Tianbo Peng, Hanzlah Akhlaq, Muhammad Adeel Khan

“…Furthermore, the insights from SHapley Additive exPlanations (SHAP) are also compared with those derived from alternative explainability methods, including Local interpretable model-agnostic explanations (LIME), partial dependence plots (PDP), and sklearn permutation importance rankings to examine the contributions of individual parameters to the ultimate moment capacity predictions of UHPC beams using the best-performing AutoML model. …”
Get full text

DVAEGMM: Dual Variational Autoencoder With Gaussian Mixture Model for Anomaly Detection on Attributed Networks by Wasim Khan, Mohammad Haroon, Ahmad Neyaz Khan, Mohammad Kamrul Hasan, Asif Khan, Umi Asma Mokhtar, Shayla Islam

“…DVAEGMM helps in the simultaneous optimization of the mixture model, generative adversarial network, and variational autoencoder parameters. …”
Get full text

A Comparative Study of Loan Approval Prediction Using Machine Learning Methods by Vahid Sinap

“…In addition, determining the effect of K-Best and Recursive Feature Elimination feature selection methods on model performances is another important objective of the research. …”
Get full text