Predicting smart home lighting behavior from sensors and user input using very fast decision tree with Kernel Density Estimation and improved Laplace correction

Dinata, Ida Bagus Putu Peradnya; Hardian, Bob

doi:10.1109/icacsis.2014.7065885

Cited by 7 publications

(3 citation statements)

References 6 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, synthetic datasets can pose as slightly unrealistic and oversimplified scenarios for testing and validation. For example, Dinata et al [19] propose an improvement to the Very Fast Decision Tree (VFDT) [21] algorithm (to which it was called VFDT++), which proved to be the best at predicting a simple luminaire's state (ON or OFF) when compared to other algorithms. The tests were performed on the dataset CASAS [20] with some modifications and restricted to one month of data, where it is assumed that the dataset is station- [20] Simulation ary, non-temporal, and there are no changes in user habits.…”

Section: Related Workmentioning

confidence: 99%

Voice-Activated Smart Home Controller Using Machine Learning

2021

View full text Add to dashboard Cite

The emergence of the Internet of Things concept has provided a great vision for the technological future, intending to enable the extraction and comprehension of information from the environment around us, making use of the interaction and cooperation between several technological devices. The example of Smart Homes, in particular, aims to integrate these devices into households, enabling the automation of tasks previously performed by humans, to simplify their daily lives and create a more comfortable environment. However, many of these devices fail to keep their promise, since they were not developed taking into account the frequent change of habits and tastes of the user, being necessary reprogramming of the device to follow the new behaviors. Taking this problem into account, this article presents the design and end-to-end implementation of a voice-activated smart home controller for intelligent devices, deployed in a real environment and validated in an experimental setup of motorized blinds. The architecture of the proposed solution integrates evolvable intelligence with the use of an Online Learning framework, enabling it to automatically adapt to the user's habits and behavioral patterns. The results obtained from the various evaluation tests provide a validation of the operation and usefulness of the developed system. The main contributions of this work are: I) design of a smart home controller's architecture; II) end-to-end implementation of a smart home controller and respective guidelines; III) opensource dataset of user behavior from the smart blinds scenario; IV) comparison between Online and Offline Learning approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Voice-Activated Smart Home Controller Using Machine Learning

2021

View full text Add to dashboard Cite

show abstract

“…Here, change detection mechanisms are of great importance [18,25]. Online learning has also been used in smart home environments for activity recognition [40] or to detect lighting behavior [15]. In the field of preference learning, the goal of a classifier is to predict the preferences of humans.…”

Section: Related Research Areasmentioning

confidence: 99%

Collaborative Interactive Learning -- A clarification of terms and a differentiation from other research fields

Hanika¹,

Herde²,

Kühn³

et al. 2019

Preprint

View full text Add to dashboard Cite

The field of collaborative interactive learning (CIL) aims at developing and investigating the technological foundations for a new generation of smart systems that support humans in their everyday life. While the concept of CIL has already been carved out in detail (including the fields of dedicated CIL and opportunistic CIL) and many research objectives have been stated, there is still the need to clarify some terms such as information, knowledge, and experience in the context of CIL and to differentiate CIL from recent and ongoing research in related fields such as active learning, collaborative learning, and others. Both aspects are addressed in this paper.

show abstract

“…In 2014, the Very Fast Decision Tree (VFDT) was introduced to predict smart home lighting using sensors and user input [3]. The project's focus was to improvise the VFDT, namely VFDT++, which uses Kernel Density Estimation (KDE) and Laplace correction.…”

Section: Related Workmentioning

confidence: 99%

Personalized ambience: An integration of learning model and intelligent lighting control

Yin

Keoh

2016

2016 IEEE 3rd World Forum on Internet of Things (WF-IoT)

View full text Add to dashboard Cite

Abstract-The number of households and offices adopting automation system is on the rise. Although devices and actuators can be controlled through wireless transmission, they are mostly static with preset schedules, or at different times it requires human intervention. This paper presents a smart ambience system that analyzes the user's lighting habits, taking into account different environmental context variables and user needs in order to automatically learn about the user's preferences and automate the room ambience dynamically. Context information is obtained from Yahoo Weather and environmental data pertaining to the room is collected via Cubesensors to study the user's lighting habits. We employs a learning model known as the Reduced Error Prune Tree (REPTree) to analyze the users' preferences, and subsequently predicts the preferred lighting condition to be actuated in real time through Philips Hue. The system is able to ensure the user's comfort at all time by performing a closed feedback control loop which checks and maintains a suitable lighting ambience at optimal level.

show abstract

Predicting smart home lighting behavior from sensors and user input using very fast decision tree with Kernel Density Estimation and improved Laplace correction

Cited by 7 publications

References 6 publications

Voice-Activated Smart Home Controller Using Machine Learning

Voice-Activated Smart Home Controller Using Machine Learning

Collaborative Interactive Learning -- A clarification of terms and a differentiation from other research fields

Personalized ambience: An integration of learning model and intelligent lighting control

Contact Info

Product

Resources

About