Development of A Smart Database for Construction Inventory Management Using Deep Learning to Eliminate Supply Chain Bottlenecks Post COVID-19
Bibliographic record
Abstract
The COVID-19 pandemic has sent shockwaves down the supply chains of industries. The Architecture, Engineering, and Construction (AEC) industry is used to cyclical downturns, but the speed and strength with which COVID-19 has struck are unprecedented. Projects are being delayed or canceled. Supply chains are under threat. National and International policies are being revamped to deal with the transformed landscape. In 2019, the USA receives more than 530 thousand metric tons of steel from Russia, Germany, Italy, Canada, Mexico, and other such countries. The US building industry is dependent largely on other countries for the supply of raw materials, which make the construction industry at risk due to trade restrictions that have ensued in the post COVID world. One way to deal with such a changing environment is to diversify the dependence portfolio in supply chains to reduce shocks. The other alternative is to look to build an inventory based on predictive analytics. This research aims to implement the two reactionary measures of portfolio diversification and inventory infrastructure development by leveraging predictive analytics and big data. The project will be mainly divided into three phases – PHASE 1 will be mainly focused on the gathering of the relevant manufacturer and supplier data of construction materials both within and external to geographical borders of the USA. PHASE 2 will focus on the selection and integration of algorithms with the live database that has been created in phase 1. PHASE 3 will be devoted to the creation of custom-made user interfaces for the project owners. This phase will also focus on the automation of live reports, notifications,s, etc. to be sent to project owners. The deep learning algorithms would need continuous feedback and improvement to increase their credibility and reliance on a continuous basis. Thus, it will help to reduce the risks generated through uncertainties by developing a resilient smart responsive database that will provide stockholders accurate data and predictions in response to the market and industry behavior.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".