Towards the Development of an Adaptive System for Detecting Anomaly in Human Activities
Bibliographic record
Abstract
As the global population of older adults increases, measures are put in place to monitor their well-being, promote independent living and improve their quality of life. Among those measures are in-house monitoring system that allows for the collection of data in a non-invasive form to identify the activities of daily living of the older adults and detect abnormalities in their daily routines. Abnormalities can be an early sign of health decline or other related challenges, thereby informing the family and carers of the need for intervention. However, existing anomaly detection systems are unable to adapt to the dynamic nature of human activities which are subject to changes due to different factors, resulting in an increased false prediction rate. To address this deficiency, the anomaly detection system must be adaptive to the changes in human routines as well as factors leading to the changes. This paper presents a consolidation of the achievements recorded in the development of an adaptive anomaly detection system. This system consists of a data collection and interpretation component, anomaly detection component and a feedback component. An ensemble of novelty detection model based on a consensus approach is utilised for the anomaly detection while the feedback component is based on a gesture recognition model implemented on an assistive robot platform. The results of our proposed approach for anomaly detection and gesture recognition performs better when compared to other existing approaches. The obtained results for the different system components show the potential of the system for in-house monitoring of older adults.
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 | 0.000 |
| 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 | 0.001 |
| Open science | 0.001 | 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".