A Mean Weighted Squared Error-based Neural Classifier for Intelligent Pattern Recognition in Smart Grids
Bibliographic record
Abstract
Supervised learning is widely used in pattern recognition and classification due to its strong ability to enhance data accuracy. Loss functions have proven to be a critical factor in enhancing the predictive accuracy of intelligent classifiers with diverse architectures and characteristics. This paper introduces a new extension of the conventional Mean Squared Error loss function, called Mean Weighted Squared Error (MWSE), specifically designed for renewable energy classification purposes. In the proposed MWSE, unequal weights are assigned to each estimated data point, unlike the conventional version. In this paper, Multilayer Perceptron Neural Networks (MLPs) are employed to implement the proposed MWSE loss function. To assess the effectiveness of the proposed MWSE-MLP classifier, a total of four benchmark datasets related to the renewable energy have been utilized. The empirical findings demonstrate that the proposed classifier consistently outperforms conventional shallow/deep intelligent classifier across all case studies. On average, the proposed MWSE-MLP classifier achieved an impressive classification rate of 96.21%, which is 1.98% higher than that of the classic MLPs. In addition, numerical results of an extensively reviewed case study indicate that the proposed classifier can also yield more accurate results than some other well-known shallow intelligent classifiers such as support vector machine, random forest, and decision tree by 2.72%, 3.34%, and 3.82% improvement, respectively. These improvements are not limited to shallow intelligent classifiers, but also repeated for deep learning classifiers, such as the long short-term memory, transformers and convolutional deep neural networks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".