IMPROVING SMART HOME SAFETY WITH FACE RECOGNITION USING MACHINE LEARNING
Bibliographic record
Abstract
Smart home devices can be programmed to optimize energy usage and reduce waste, leading to lower energy bills. IoT devices allow for remote control and automation of home systems such as lighting, temperature, and security, making daily life more convenient. IoT devices can provide real-time insights into household usage and patterns, allowing for improved awareness and decision making. IoT devices such as smart locks and security cameras can provide real-time monitoring and alerts, improving home security. Nowadays users face many inconveniences in usage of electronic fingerprint door locks such as False rejections, Limited user capacity, vulnerability to environmental factors such as moisture, dirt, and oil, leading to decreased accuracy, cost and maintenance. As there are many drawbacks found in existing methods in alteration to that, we use face recognition technology in smart homes, where it has the potential to greatly improve safety and security. By using machine learning algorithms, smart home devices equipped with cameras and facial recognition software can identify and authenticate authorized users, reducing the risk of unauthorized access. The technology can also alert homeowners of potential intruders and provide real-time monitoring of the home. With its ability to learn and adapt to new faces, face recognition technology has the potential to provide a high level of accuracy and security for smart homes. This technology can be integrated into various smart home systems such as security cameras, door locks, and access control systems. The implementation of face recognition technology in smart homes can not only enhance safety but also provide a more convenient and personalized user experience. In this research work we use a hybrid machine learning algorithm for face recognition in a home automation system that could be a combination of Convolutional Neural Networks (CNN) and Support Vector Machines (SVM). The CNN can be used for feature extraction from face images, while the SVM can be used for classification and identification of individual faces. This hybrid approach can take advantage of the strengths of both algorithms, providing robust and accurate face recognition performance. Additionally, this hybrid approach can be easily trained on large datasets and can handle variations in lighting, facial expressions, and angles, making it suitable for real-world face recognition applications in home automation systems.\n\n
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".