IoT BASED REAL-TIME VOICE ANALYSIS AND SMART MONITORING SYSTEM FOR DISABLED PEOPLE
Bibliographic record
Abstract
This research emphasizes on Internet of Things (IoT) based affordable platforms to take proper and timely measures for disabled people. It is usually observed that people with different disabilities face difficulties in all walks of life, and adequate caretaking measures are not adopted in most cases. Real time and consistent caretaking for such handicapped people is a tedious task. This paper introduces an IoT based real time analysis and alerting system for the disabled people. The proposed standalone system consistently monitors voice activity of person and in case of any abnormality in analysis outcomes, the system automatically notifies concerned hospital or caregiver to prompt for the patient's situation. The voice features are extracted from analysed voice by employing Discrete Cosine Transform (DCT), and classified through Support Vector Machine (SVM). The prototype has been developed by using Raspberry Pi single board along with voice recording module, Wi-Fi module and LCD Screen. Cloud web services have been used to store the real time activity and performing voice analysis. Montreal Affective Voices (MAV) dataset has been utilized for training and testing of voice recognition. The designed system can be regarded as a rescue system for people suffering from various life threatening health conditions including bipolar disorder, hysteria, cardiac arrest, etc. An accuracy of 81.74% has been achieved for MAV dataset, whereas an accuracy of 67.90% is achieved for real time voice input as depicted in the analysed results.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 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) | 0.004 | 0.002 |
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".