Hierarchical Sensing Framework for Polymer Degradation Monitoring: A Physics-Constrained Reinforcement Learning Framework for Programmable Material Discovery by Xiaoyu Hu, Xiuyuan Zhao, Wenhe Liu

“…Our method combines three key innovations: (1) a dual-channel sensing architecture that fuses spectroscopic signatures from Graph Isomorphism Networks with temporal degradation patterns captured by transformer-based models, enabling comprehensive molecular state detection across multiple scales; (2) a physics-constrained policy network that ensures sensor measurements adhere to thermodynamic principles while optimizing the exploration of degradation pathways; and (3) a hierarchical signal processing system that balances multiple sensing modalities through adaptive weighting schemes learned from experimental feedback. …”
Get full text

Integrating cyber-physical systems with embedding technology for controlling autonomous vehicle driving by Manal Abdullah Alohali, Hamed Alqahtani, Abdulbasit Darem, Monir Abdullah, Yunyoung Nam, Mohamed Abouhawwash

“…Deep reinforcement learning (DRL) has emerged as a strong tool for dealing with such uncertainty, yet current DRL models struggle to ensure safety and optimal behaviour in indeterminate settings due to the difficulties of understanding dynamic reward systems. …”
Get full text

An upgraded high-precision gridded precipitation dataset for the Chinese mainland considering spatial autocorrelation and covariates by J. Hu, C. Miao, J. Su, Q. Zhang, J. Gou, J. Gou, Q. Sun, Q. Sun

“…Specifically, it achieves a mean absolute error of 1.48 mm d<span class="inline-formula">⁻¹</span> and a Kling-Gupta efficiency of 0.88, representing improvements of 12.84 % and 12.86 %, respectively, compared to the previously optimal dataset. …”
Get full text

Impact of imbalanced features on large datasets by Waleed Albattah, Rehan Ullah Khan

“…Distributed Gaussian (D-GA) and Distributed Poisson (D-PO) are found to be the most effective techniques, especially in improving Random Forest (RF) and SVM models. The deep learning experiments also show an improvement as such.…”
Get full text

Machine Learning Applications in Road Pavement Management: A Review, Challenges and Future Directions by Tiago Tamagusko, Matheus Gomes Correia, Adelino Ferreira

“…We discuss the limitations of conventional PMS and explore how Artificial Intelligence (AI) algorithms can overcome these shortcomings by improving the accuracy of pavement condition assessments, enhancing performance prediction, and optimizing maintenance and rehabilitation decisions. …”
Get full text

Literature Review of Prognostic Factors in Secondary Generalized Peritonitis by Valerii Luțenco, Adrian Beznea, Raul Mihailov, George Țocu, Verginia Luțenco, Oana Mariana Mihailov, Mihaela Patriciu, Grigore Pascaru, Liliana Baroiu

“…Emerging evidence suggests that machine learning algorithms may improve early risk stratification and individualized outcome prediction when integrated with conventional scoring systems. …”
Get full text

Exploration of heterogeneity of treatment effects across exercise-based interventions for knee osteoarthritis by Paul A. Dennis, Livia Anderson, Cynthia J. Coffman, Sara Webb, Kelli D. Allen

“…Results: The regression tree model outperformed all 9 metalearner models. Tree results suggested group-based PT yielded the largest improvement in mean WOMAC score. …”
Get full text

Saliva-derived transcriptomic signature for gastric cancer detection using machine learning and leveraging publicly available datasets by Catarina Lopes, Andreia Brandão, Manuel R. Teixeira, Mário Dinis-Ribeiro, Carina Pereira

“…Leveraging transcriptomic data from the Gene Expression Omnibus (GEO), we constructed and validated predictive models through machine learning algorithms within the tidymodels framework. …”
Get full text

Secure and efficient batch authentication scheme based on dynamic revocation mechanism in space information network by Yinghui ZHANG, Lingyun HU, Yixin LI, Jianting NING, Dong ZHENG

“…A secure and efficient batch authentication scheme based on dynamic revocation mechanism was proposed for the problem of cross-domain authentication of a large number of mobile users in space information networks.Early key negotiation was achieved by predicting the satellite trajectory and updating the session key in real time.Algorithms were designed for a single as well as a large number of mobile terminals to perform signing and verification, which effectively reduce the computational burden of satellites.Cuckoo filters were adopted by the new scheme to achieve dynamic revocation and malicious access control of mobile terminals.Finally, under the Diffie-Hellman assumption, the proposed scheme was proved to be resistant to replay and man-in-the-middle attacks based on a random oracle model and automated validation of internet security protocols and applications.Security goals such as traceability and revocability were achieved by the scheme, thus improving the efficiency of transmission and computation by more than 80% and 20%, respectively, compared with the existing optimal scheme.…”
Get full text

Towards representation learning of radar altimeter waveforms for sea ice surface classification by L. Happ, L. Happ, S. Patil, S. Hendricks, R. Fellegara, L. Kaleschke, A. Gerndt, A. Gerndt

“…Moreover, machine learning models for sea ice classification often depend on supervised training, which is vulnerable to uncertainties in labeled data, especially in polar regions. …”
Get full text

Cervical cancer demystified: exploring epidemiology, risk factors, screening, treatment modalities, preventive measures, and the role of artificial intelligence by N. Mohammad, M. Khan, M. Maqsood, A. H. K. Naseeb

“…AI-driven technologies, including deep learning algorithms and machine learning models, are emerging as valuable tools in cervical cancer detection, risk assessment, and treatment planning. …”
Get full text

Multi-omics derivation of a core gene signature for predicting therapeutic response and characterizing immune dysregulation in inflammatory bowel disease by Mingming Wang, Liping Liang, Zibo Tang, Jimin Han, Lele Wu, Le Liu, Le Liu, Ye Chen, Ye Chen

“…Validation employed ten algorithms and nomogram construction. Immune infiltration (CIBERSORT/ssGSEA), single-cell RNA sequencing, and DSS-colitis models characterized immune dynamics, cellular specificity, and therapeutic response modulation.ResultsWe identified 536 differentially expressed genes significantly enriched in IL-17 signaling, TNF signaling, and cytokine-cytokine receptor interactions. …”
Get full text

Contributions to the Development of Tetrahedral Mobile Robots with Omnidirectional Locomotion Units by Anca-Corina Simerean, Mihai Olimpiu Tătar

“…The second prototype is presented as an advanced and improved version of the first model, integrating significant modifications in both the structural design and the robot’s functionality. …”
Get full text

Designing CITOBOT: A portable device for cervical cancer screening using human-centered design, smart prototyping, and artificial intelligence by Marcela Arrivillaga, Paula C. Bermúdez, Juan Pablo García-Cifuentes, Hernán Darío Vargas-Cardona, Daniela Neira, Maria del Mar Torres, Mérida Rodríguez-López, Daniela Morales, Bleider Arizala

“…Additionally, we developed AI algorithms using the Inception V3 network, optimized with Transfer Learning and Fine Tuning, for cervical image classification and offline-operating software that guides the physician through the examination and provides a risk assessment for cervical cancer. …”
Get full text

Comparative Analysis of Facial Expression Recognition Methods by Denys - Florin COT

“…The integration of such solutions can contribute to the development of decision support systems in psychiatry, optimizing therapeutic strategies, and improving the quality of care for patients with neuropsychological conditions. …”
Get full text

Comparison of Machine Learning Methods for Predicting Electrical Energy Consumption by Retno Wahyusari, Sunardi Sunardi, Abdul Fadlil

“…Data pre-processing, specifically min-max normalization, is crucial for improving the accuracy of distance-based algorithms like KNN. …”
Get full text

Development and Training of a Neural Network Filter for Satellite Images Processing by N. Andriyanov, A. Kim

“…As part of the study, the architecture of the autoencoder was developed, optimal hyperparameters were selected and the resulting neural network model was trained. …”
Get full text

Postmarketing safety evaluation of pemetrexed using FAERS and JADER databases by Luo Lv, Xiangyang Wu, Yubo Ren, Yuli Guo, Haixiong Wang, Xiaofang Li

“…Continuous pharmacovigilance is essential to optimize its clinical use and improve patient safety.…”
Get full text

Pertinence of contact duration as edge feature for epidemic spread analysis by Ramya D. Shetty, Shrutilipi Bhattacharjee

“…In this study, we mainly aim to generate weighted networks to model the pathogen spread by optimal calculation of the edge weight in terms of contact duration (time spent) between individual contacts. …”
Get full text

Know your competitor! Analyzing and predicting the location of competing stores: The case study of Valora at Swiss railway stations by Thomas Wieland

“…Machine learning algorithms are used to check and optimize the predictive ability of the models. …”
Get full text