Reset
Showing 20 of 246 academic articles

Interpretability-preserving knowledge distillation via multi-granular feature alignment for resource-efficient CNNs

Shiv Singh, Neelu Jyothi Ahuja • Discover Computing (2026)

Abstract The application of deep learning models in resource-constrained environments requires a trade-off among accuracy, efficiency, and interpretability a trilemma frequently neglected in conventional knowledge distillation (KD) approach...

DOAJ Open Access (DOAJ) DOI: 10.1007/s10791-026-10123-y

HIFU Tissue Degeneration Classification Based on Multifractal Detrending Fluctuation Analysis and Vision Transformer

Hu Dong, Xin Tong, Gang Liu • Fractal and Fractional (2026)

For high-intensity focused ultrasound (HIFU) thermal ablation to be safe and effective, real-time, high-precision monitoring of tissue coagulative necrosis is essential. However, decoding the ultra-long, non-stationary radio frequency (RF) ...

DOAJ Open Access (DOAJ) DOI: 10.3390/fractalfract10090609

Decentralized Distributed Sequential Neural Networks Inference on Low-Power Microcontrollers in Wireless Sensor Networks: A Predictive Maintenance Case Study

Yernazar Bolat, Iain Murray, Yifei Ren, Nasim Ferdosian • Sensors (2025)

The growing adoption of IoT applications has led to increased use of low-power microcontroller units (MCUs) for energy-efficient, local data processing. However, deploying deep neural networks (DNNs) on these constrained devices is challeng...

DOAJ Open Access (DOAJ) DOI: 10.3390/s25154595

Automated cell type annotation and exploration of single-cell signaling dynamics using mass cytometry

Dimitrios Kleftogiannnis, Sonia Gavasso, Benedicte Sjo Tislevoll, Nisha van der Meer et al. • iScience (2024)

Summary: Mass cytometry by time-of-flight (CyTOF) is an emerging technology allowing for in-depth characterization of cellular heterogeneity in cancer and other diseases. Unfortunately, high-dimensional analyses of CyTOF data remain quite d...

DOAJ Open Access (DOAJ) DOI: 10.1016/j.isci.2024.110261

High temperature Nb-Si alloys using data science: optimization of fracture toughness and high-temperature strength

Chao Xu, Dezhi Chen, Xiaofu Zhang, Qi Wang et al. • Nature Communications (2026)

Abstract High temperature Nb-Si based alloys face a critical challenge: achieving adequate room-temperature fracture toughness ( > 18 MPa·m1/2) for processing while maintaining high-temperature strength, properties that typically compete wi...

DOAJ Open Access (DOAJ) DOI: 10.1038/s41467-026-75353-6

Stacking Ensemble Approach for Churn Prediction: Integrating CNN and Machine Learning Models with CatBoost Meta-Learner

Tan Yan Lin, Pang Ying Han, Ooi Shih Yin, Khoh Wee How et al. • Journal of Engineering Technology and Applied Physics (2023)

In the telecom industry, predicting customer churn is crucial for improving customer retention. In literature, the use of single classifiers is predominantly focused. Customer data is complex data due to class imbalance and contain multiple...

DOAJ Open Access (DOAJ) DOI: 10.33093/jetap.2023.5.2.12

High-throughput laboratory evolution reveals evolutionary constraints in Escherichia coli

Tomoya Maeda, Junichiro Iwasawa, Hazuki Kotani, Natsue Sakata et al. • Nature Communications (2020)

Understanding evolutionary constraints in antibiotic resistance is crucial for prediction and control. Here, the authors use high-throughput laboratory evolution of Escherichia coli alongside machine learning to identify trade-off relations...

DOAJ Open Access (DOAJ) DOI: 10.1038/s41467-020-19713-w

Assessing climate and land use impacts on surface water yield using remote sensing and machine learning

Amanuel Kumsa Bojer, Muluneh Woldetsadik Abshare, Fitsum Mesfin, Ayad M. Fadhil Al-Quraishi • Scientific Reports (2025)

Abstract Climate and land use changes are critical factors affecting watershed water yields, with significant implications for water resources at both local and regional levels. This study examined the combined effects of temporal and spati...

DOAJ Open Access (DOAJ) DOI: 10.1038/s41598-025-03493-8

Insights into the entire building life cycle assessment (LCA): existing trends, challenges and prospective framework

Erikas Lenkevičius, Jolanta Tamošaitienė • Journal of Environmental Engineering and Landscape Management (2026)

Building sustainability assessment increasingly demands life cycle coverage that captures environmental burdens and trade-offs beyond operational energy, including embodied impacts and end of life (EoL) outcomes under circular economy (CE) ...

DOAJ Open Access (DOAJ) DOI: 10.3846/jeelm.2026.27214

Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy

Nan Zheng, Yongchao Cai, Zehua Zhang, Huimin Zhou et al. • Nature Communications (2025)

Abstract The pursuit of obtaining enzymes with high activity and stability remains a grail in enzyme evolution due to the stability-activity trade-off. Here, we develop an isothermal compressibility-assisted dynamic squeezing index perturba...

DOAJ Open Access (DOAJ) DOI: 10.1038/s41467-025-55944-5

Occupational exposures, complementarity and the potential consequences of A.I. for the labour market: some evidence from Ireland

Harry Williamson, Dermot Coates, Kevin Daly, Keith FitzGerald et al. • Journal for Labour Market Research (2025)

Abstract The adoption of AI technology by industry could significantly disrupt our current understanding of “typical” economic activity. As AI comes to pervade more sectors and occupations over time, it is likely that this technology will g...

DOAJ Open Access (DOAJ) DOI: 10.1186/s12651-025-00418-w

Guarding against artificial intelligence – hallucinated citations: The case for full-text reference deposit.

Alex Glynn • European Science Editing (2025)

The tendency of generative artificial intelligence (AI) to ‘hallucinate’ false information is well known; AI-generated citations to non-existent sources have penetrated the bibliographies of peer-reviewed publications. D...

DOAJ Open Access (DOAJ) DOI: 10.3897/ese.2025.e153973

Current Signature-Based Bearing Fault Severity Classification Using a Robust Multilevel Cascaded Framework

Korawege N. C. Jayasena, Battur Batkhishig, Babak Nahid-Mobarakeh, Ali Emadi • IEEE Access (2025)

Bearing faults are a critical concern in electrical machines, particularly permanent magnet synchronous motors (PMSMs), commonly used in electric vehicles. Early and accurate classification of bearing fault severity is essential for predict...

DOAJ Open Access (DOAJ) DOI: 10.1109/ACCESS.2025.3589750

Predictive digital twin for optimizing patient-specific radiotherapy regimens under uncertainty in high-grade gliomas

Anirban Chaudhuri, Graham Pash, David A. Hormuth, David A. Hormuth et al. • Frontiers in Artificial Intelligence (2023)

We develop a methodology to create data-driven predictive digital twins for optimal risk-aware clinical decision-making. We illustrate the methodology as an enabler for an anticipatory personalized treatment that accounts for uncertainties ...

DOAJ Open Access (DOAJ) DOI: 10.3389/frai.2023.1222612

Economic Policy for Artificial Intelligence

Ajay K. Agrawal, Joshua S. Gans, Avi Goldfarb B • Innovation Policy and the Economy (2018)

Recent progress in artificial intelligence (AI)—a general purpose technology affecting many industries—has been focused on advances in machine learning, which we recast as a quality-adjusted drop in the price of prediction. How will this sh...

OPENALEX DOI: https://doi.org/10.1086/699935