Designing a cased based reasoning decision support system for ice management operations using expert knowledge
Bibliographic record
Abstract
Prevention of safety hazards plays an important role in the offshore and maritime industries, especially in offshore ice management operations as the safety of these operations depends on the judgment and decision making of experienced captains and their bridge teams. To address safety challenges that may arise in the context of ice management operations, this study focused on a human-centered approach to develop an early-stage decision support system (DSS) for offshore ice management operations by applying a case-based reasoning (CBR) method. The aim of this research is to (i) capture knowledge from expert seafarers to be used in the development of a DSS; and (ii) propose a DSS employing a CBR model to be used onboard ships in a real-time basis for ice management operations. To capture seafarers’ experience, this study employed semi-structured interviews and bridge simulator exercises. The results of the knowledge capture exercises were translated into an ice management DSS using a CBR model. The case-based reasoning (CBR) model develops solutions to new problems by using similar problems in the past. The DSS employs a decision tree algorithm to retrieve a case to match observations from the current situation with an unknown outcome to a case base with known outcomes. This thesis describes the methods used in the development of the onboard DSS to provide tactical guidance for ice management operations. It also outlines the methods used to test the DSS software’s suggested ice management strategies and adjustments during a series of simulator exercises.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".