Problem description
Given a labeled source dataset \(\left\{ \left( \textbf{x}_{i}^{s}, y_{i}^{s}\right) \right\} _{i=1}^{n^{s}}\) sampled from distribution \(\mathcal {D}^{s}\) with class labels \(y_{i}^{s} \in \{1,2, \ldots , K\}\) , and an…
Category: 7. Maths
-
A knowledge-informed neural network integrating fuzzy AHP and PCA for SME credit risk assessment
This chapter aims to present the empirical results obtained by applying the research methodology established in Chap. 3 to the 202 valid survey questionnaires. The content of this chapter is divided into two core parts: first, a macro-diagnosis…
Continue Reading
-
Integrated groundwater quality assessment using geochemical modelling and machine learning approach in Northern India
Ali, S., Mohammadi, A. A., Ali, H., Alinejad, N. & Maroosi, M. Qualitative assessment of ground water using the water quality index from a part of Western Uttar Pradesh North India. Desalin. Water Treat. 252, 332–338 (2022).
…
Continue Reading
-
Sports injury risk prediction based on temporal graph encoding and graph neural networks: A cross-sport transfer learning framework
Dataset and preprocessing
This study uses multiple public sports injury datasets to validate the proposed cross-sport transfer learning framework. Data sources include: the Dutch competitive runners dataset (
Continue Reading
-
Heuristic computational approach for nonlinear reaction–diffusion kinetics in catalytic systems
Catalysts play an important role in accelerating various reactions thereby improving the efficiency of reactants. Traditional catalysts are mostly solid materials of specific shapes and other characteristics, but due to recent developments, other…
Continue Reading
-
Estimation of protein content in wheat samples using NIR hyperspectral imaging and 1D-CNN
This study implemented a 1D-CNN to estimate protein content in wheat seeds using spectral data. The 496 training samples were subjected to 5-fold cross-validation to ensure robust model performance by selecting optimal hyperparameters and…
Continue Reading
-
A scalable cloud-integrated AI platform for real-time optimization of EV charging and resilient microgrid energy management
EVs charging and managing the grid might be drastically improved with the integration of AI, ML and cloud computing. To improve grid stability, optimize charging infrastructure, and guarantee sustainability, smart technologies are essential in…
Continue Reading
-
Spintronic digital compute-in-memory macro for efficient artificial intelligence
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Li, H. et al. A lossless and fully parallel spintronic compute-in-memory macro for…
Continue Reading
-
Intelligent scheduling for distributed-level island integrated energy systems considering multi-energy utilization and incentive-penalty stepped carbon trading mechanism
Wu, X., Tian, Z. & Guo, J. A review of the theoretical research and practical progress of carbon neutrality. Sustain. Oper.Comput. 3, 54–66 (2022).
Almoghayer, M. A., Woolf, D. K., Kerr, S. &…
Continue Reading
-
A dual-channel hyperspectral classification method based on NAS and transformer
To validate the effectiveness of the CTMixer-NAS model, experiments were conducted on several publicly available datasets, including the Indian Pine (IP) dataset, the PaviaU (PU) dataset, the KSC dataset, the WHU_Hi_LongKou dataset,and Salinas…
Continue Reading