Improving the Detection of Explosives in a MOX Chemical Sensors Array With LSTM Networks
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Entities throughout the world face the problem of detecting hidden explosives, where human and canine inspection might not be a viable solution. Therefore, it is important to develop fast, reliable, and portable integrated inspection systems by means of automated methods, such as electronic noses. The goal of the work presented here is to develop an accurate, fast and light-weight machine/deep learning classification model to be used in a MOX chemical sensors array (electronic nose), in order to identify explosive substances. For this paper, 140 samples were taken, combining TNT or gunpowder with either soap or toothpaste, or acquiring raw samples of those substances in amounts ranging from 0.1 g to 2 g. For the classification problem, among the different options in machine learning techniques, five models were evaluated. The implemented LSTM version of a LeNet-5 based network, classifies accurately the compounds in 100% of the cases when using only 30 seconds from the 360 obtained by the sensor array per each sample. The results of this work indicate that the proposed LSTM-based deep learning model could be easily implemented into an embedded system.
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.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it