Enhanced Environmental Awareness and Security for Smart Devices using WiFi-Sensing
Bibliographic record
Abstract
With the current advancements generative AI. Applications across many fields are being integrated with AI agents to provide a better experience to the users. One of these applications is personal assistants which can be integrated with AI to support Natural Language Understanding (NLU). In this work we introduce the architecture and evaluation of an AI-powered smart home device. The role of the role of the presenteddeviceevice is to be a personal assistant which is accessible across different platforms (web, desktop, mobile, and wearable devices), using multiple communication methods (text, voice, notification). The device will be able to collect and process multi-modal data from different platforms including sensory data which is analyzed to predict human activity, bridging the digital and the physical worlds.We assess the performance for three key tasks: Human identification and activity tracking using wifi sensing, storytelling using large language models, and text-to-speech synthesis. We evaluate the three tasks using a combination of objective performance metrics and user studies. Statistical analysis was conducted to evaluate different state-of-the-art Large Language Models (LLM) and Text-To-Speech (TTS) models. We performed deep learning across different data learning paradigms including local, central, and federated learning ensuring privacy and high accuracy.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".