Dual smart sensor data-based deep learning network for premature infant hypoglycemia detection
Bibliographic record
Abstract
In general, deficient birth weight neonates suffer from hypoglycemia, and this can be quite disadvantageous. Like oxygen, glucose is a building block of life and constitutes the significant share of energy produced by the fetus and the neonate during gestation. The fetus receives glucose from the placenta continuously during gestation, but this substrate delivery changes abruptly, and the fetus's metabolism changes significantly at birth. Hypoglycemia is one of the most frequent pathologies affecting the change of newborns in neonatal critical care units. This work is now introducing a system, HAPI-BELT, empowered by dual intelligent sensors and Deep Learning (DL) algorithms for tracking and continuously detecting hypoglycemia in preterm newborns. This article comprises a smart belt with an intelligent camera and photoplethysmography (PPG) attached. This device tracks changes in the infant's motion, skin colour, and breathing patterns; this is done through a PPG sensor strapped either on the belly or chest of an infant, logging information on heart functioning. The digital data gathered by this PPG sensor and image data captured from the smart camera are then processed by a Raspberry Pi Zero 2 W. It does most of the data analysis and decision-making. Feature Extraction (FE) is done through CAT-Swarm Optimization. Based on features, the sorted-out data gets evaluated through a GRU-LSTM (Gated Recurrent Unit - Long Short-Term Memory) network to identify the state of the infant as usual and suggestive of hypoglycemia-blood glucose below 70 mg/dL, pale complexion, profuse perspiration. When hypoglycemia is identified, an alert is sent to the medical professionals to take necessary action with utmost urgency. Therefore, an integrated approach ensuring timely medical interventions and real-time monitoring can help better outcomes for preterm newborns.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 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".