IoT enabled Dermoscopy Image Classification using Optimized Deep Convolutional Neural Networks and Biosignal Fusion for enhanced Skin Lesion Diagnosis
Bibliographic record
Abstract
Melanoma is the most aggressive type of skin cancer, making early detection critical.This study introduces an Optimized Deep Convolutional Neural Network (ODCNet) for accurate melanoma diagnosis in dermatoscopic images, enhanced with biosignal fusion and Internet of Things (IoT) technologies for real-time remote screening.The framework includes: (i) thresholding and augmentation to suppress noise and expand data samples; (ii) Principal Component Analysis (PCA) to reduce dimensionality of features from dermoscopic images and biosignals such as skin temperature, Galvanic Skin Response (GSR), and PhotoPlethysmography (PPG) captured via IoT wearables; (iii) a two-phase segmentation combining Otsu's thresholding and the Chan-Vese method for refined lesion boundaries; (iv) a Deep CNN that classifies pixels as melanoma or benign, strengthened by multimodal feature fusion; and (v) the Adam optimizer for efficient convergence.The model was evaluated on the HAM10000 dataset and biosignal inputs from IoT health sensors.Results demonstrate superior performance over existing classifiers, achieving 95.1% accuracy, 96.6% sensitivity, 81.8% specificity, 95.4% precision, and 95.4% F1-score.The integration of biosignals and IoT enhances reliability, offering a robust solution for early melanoma detection in both clinical and smart healthcare environments.
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 | 0.000 | 0.001 |
| 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 | 0.000 |
| 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 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".