A new system for assistance and guidance in smart homes based on electrical devices identification
Bibliographic record
Abstract
The increasing needs for support services offered to cognitively-impaired people have serious social and economic impact on our societies. Assistive technology is often see as a potential answer to this issue that may help giving more autonomy to these people. This paper presents a new assistive system for smart homes, which is based on the analysis of electrical load signatures at the steady-state, in order to provide supervision and assistance in carrying out activities of daily living for people with cognitive impairment. The proposed system exploits a new algorithmic approach to determine the erroneous behavior related to cognitive deficits and to guide the person through the completion of his ongoing task. We implemented and deployed our system in a real size smart home prototype where we used only a single power analyzer at the main electric panel which is invisible to end-users. Then, a complete experiment has been conducted on this new assistive system using breakfast sequences reproduced with electrical appliances. The simulated sequences included some cognitive errors modeled from real case scenarios coming from previous experiments with Alzheimer patients. The system showed very promising and robust results, both for activity recognition and guidance. It demonstrated that it is possible, using nonintrusive hardware like a simple power analyser, to compete with other assistive systems presented in the literature, which require intrusive equipment to properly monitor and guide.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".