Ensemble Model for Multiclass Imbalanced Data Using Cluster Computing of Spark
Bibliographic record
Abstract
Big data analysis using machine learning has become a challenging problem today.Classification problems become more challenging when class distribution is imbalanced.In this paper, we propose a distributed ensemble model with an intelligence technique based on Particle Swarm Optimization to overcome the imbalanced problem.For compensating the class imbalance, first SMOTE is used to balance the minority class samples, and then sampling based on Particle Swarm Optimization is applied.Here, to perform fast processing, the whole model is implemented using spark-cluster computing, which uses the underlying concept of parallel programming of spark RDD.Results of the proposed system have shown consistent improvements on several evaluation metrics and overall processing time.Evaluation of the proposed system has been done using different performance metrices also comparison between sequential and distributed ensemble models.Most of the existing techniques show different performances for different datasets, while the proposed method has shown better generalization property, which improves the data-model dependency issue.The proposed model has been evaluated using KDD-CUP'99 intrusion detection and insect sensor datasets.For the datasets, it shows better improvement over traditional sampling techniques.F-Measure value is 99% for KDD'cup dataset and 92% for insect dataset.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".