Artificial Neural Networks for Material Identification, Mineralogy and Analytical Geochemistry Based on Laser-Induced Breakdown Spectroscopy
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
Artificial Neural Networks (ANN) are used nowadays in a broad range of areas such as pattern recognition, finances, data mining, battle scene analysis, process control, robotics, etc. Application of ANN in the field of spectroscopy has generated a long-standing interest of scientists, engineers and application specialists. The ANN' capability of producing fast, reliable and accurate spectral data processing has become, in many cases, a bridging mechanism between science and application. A particular example of how ANN can transform plasma emission spectroscopy, that is quit challenging to model, into a turnkey ready to use device is described in this Chapter. Laser-Induced Breakdown Spectroscopy (LIBS) is a material-composition analytical technique gaining increased interest last decade in various application fields, such as geology, metallurgy, pharmaceutical, bio-medical, environmental, industrial process control and others (Cremer & Radziemski, 2006; It is in essence a spectroscopic analysis of light emitted by the hot plasma created on a sample by the laser-induced breakdown. LIBS offers numerous advantages as compared to the standard elemental analysis techniques (X-ray fluorescence or X-ray diffraction spectroscopy, inductively coupled plasma spectroscopy, etc.), such as: capability of remote analysis in the field, compact instrumentation, detection of all elements and high spatial resolution. Such features as minimum or no sample preparation requirement and dust mitigation using "cleaning" laser shots are especially important for field geology and remotely operated rover-based instruments. As result, LIBS instruments have been selected as payloads for the 2011 Mars Science Laboratory mission led by the National Aeronautics and Space Administration Despite of the advantages, the main challenge is still the retrieval of accurate information from measured spectra. LIBS spectral signals, composed mostly of narrow emission lines, are complex nonlinear functions of concentrations of measured constituents and instrument 1 Government of Canada 2010 www.intechopen.com Artificial Neural Networks -Industrial and Control Engineering Applications 92
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 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 | 0.001 | 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