A User-Centered Active Learning Approach for Appliance Recognition

Shin, Eura; Khamesi, Atieh R.; Bahr, Zachary; Silvestri, Simone; Baker, Denise A.

doi:10.1109/smartcomp50058.2020.00047

Cited by 7 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare KAN to three diferent SAL strategies proposed in [26], [38], and [44], respectively. 4.2.1 OBAL and SVM Classifier.…”

Section: Comparison Approachesmentioning

confidence: 99%

“…We also compare KAN to the algorithm proposed in the conference version of this paper, denoted as SMARTCOMP [38]. he SMARTCOMP querying strategy only adopts the () score, deined as (x ) = max{ (x ), (x )}, (i.e., it does not use the conidence score) along with the user response distribution.…”

Section: Smartcompmentioning

confidence: 99%

“…Some promising approaches introduced to manage energy consumption at the residential level are obtained through ine-grained electricity billing, demand-response programs, and electrical power load balancing [28,32]. A well-recognized key enabler for such energy management techniques is the knowledge about when each appliance is used and its consumption [5,9,17,22,27,38,39]. he problem of recognizing an appliance from its electric signature is known as appliance recognition.…”

mentioning

confidence: 99%

“…Previous studies on appliance recognition using smart outlets adopt passive machine learning, in which a set of labeled data is given to train the model before it is deployed, and then the ixed trained model is used for classiication [2]. his approach is not practical in a smart home for several reasons [38]: (i) oline classiication is not lexible to new appliances subsequently available on the market; (ii) similar appliances (e.g., diferent brands) may have very diferent consumption paterns, making it hard to perform oline training. To illustrate this point, we collected the signatures (paterns of current over time) of two computer monitors, Fig.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Learning from Non-experts: An Interactive and Adaptive Learning Approach for Appliance Recognition in Smart Homes

Codispoti

Khamesi

Penn

et al. 2022

ACM Trans. Cyber-Phys. Syst.

Self Cite

View full text Add to dashboard Cite

With the acceleration of ICT technologies and the Internet of Things (IoT) paradigm, smart residential environments , also known as smart homes are becoming increasingly common. These environments have significant potential for the development of intelligent energy management systems, and have therefore attracted significant attention from both academia and industry. An enabling building block for these systems is the ability of obtaining energy consumption at the appliance-level. This information is usually inferred from electric signals data (e.g., current) collected by a smart meter or a smart outlet, a problem known as appliance recognition . Several previous approaches for appliance recognition have proposed load disaggregation techniques for smart meter data. However, these approaches are often very inaccurate for low consumption and multi-state appliances. Recently, Machine Learning (ML) techniques have been proposed for appliance recognition. These approaches are mainly based on passive MLs, thus requiring pre-labeled data to be trained. This makes such approaches unable to rapidly adapt to the constantly changing availability and heterogeneity of appliances on the market. In a home setting scenario, it is natural to consider the involvement of users in the labeling process, as appliances’ electric signatures are collected. This type of learning falls into the category of Stream-based Active Learning (SAL). SAL has been mainly investigated assuming the presence of an expert , always available and willing to label the collected samples. Nevertheless, a home user may lack such availability, and in general present a more erratic and user-dependent behavior. In this paper, we develop a SAL algorithm, called K -Active-Neighbors (KAN), for the problem of household appliance recognition. Differently from previous approaches, KAN jointly learns the user behavior and the appliance signatures. KAN dynamically adjusts the querying strategy to increase accuracy by considering the user availability as well as the quality of the collected signatures. Such quality is defined as a combination of informativeness , representativeness , and confidence score of the signature compared to the current knowledge. To test KAN versus state-of-the-art approaches, we use real appliance data collected by a low-cost Arduino-based smart outlet as well as the ECO smart home dataset. Furthermore, we use a real dataset to model user behavior. Results show that KAN is able to achieve high accuracy with minimal data, i.e., signatures of short length and collected at low frequency.

show abstract

“…We compare KAN to three diferent SAL strategies proposed in [26], [38], and [44], respectively. 4.2.1 OBAL and SVM Classifier.…”

Section: Comparison Approachesmentioning

confidence: 99%

Section: Smartcompmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Learning from Non-experts: An Interactive and Adaptive Learning Approach for Appliance Recognition in Smart Homes

Codispoti

Khamesi

Penn

et al. 2022

ACM Trans. Cyber-Phys. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Building automation and management systems require real-time, end to end solitons for appliance recognition as internet of things device [14]. Smart outlets are easiest way to measure and identify each individual appliance with simple machine learning techniques [15].…”

Section: Introductionmentioning

confidence: 99%

A comparative study on appliance recognition with power parameters by using machine learning algorithms

Güven

2021

International Advanced Researches and Engineering Journal

View full text Add to dashboard Cite

Recently, machine Learning algorithms are widely used in many fields. Especially, they are really good to create prediction models for problems which are not easy to solve with conventional programming techniques. Although, there are many different kinds of machine learning algorithms, results of applications are varying depend on type of data and correlation of information. In this study, different machine learning algorithms have been used for appliance recognition. The measurement data of Appliance Consumption Signatures database and some derivative values have been used for training and testing. Additionally, a data pre-processing technique and its effects on results have been presented. Filtering corrupted data and removing uncertain measurement value has improved the quality of machine learning. Combination of machine learning algorithms is best way to work with uncertain values. Different feature extraction methods and data pre-processing techniques are crucial in machine learning. Therefore, this study aims to develop a high accurate appliance recognition technique by combining grey relational analysis and an ensemble classification method. The results of this new method have been presented comparatively to show the improvement for itself and previous studies that uses the same database.

show abstract

Human Activity Recognition Using Spectrograms of Binary Motion Sensor Data

Seyedtalebi,

Silvestri

2024

2024 20th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT)

View full text Add to dashboard Cite

A User-Centered Active Learning Approach for Appliance Recognition

Cited by 7 publications

References 11 publications

Learning from Non-experts: An Interactive and Adaptive Learning Approach for Appliance Recognition in Smart Homes

Learning from Non-experts: An Interactive and Adaptive Learning Approach for Appliance Recognition in Smart Homes

A comparative study on appliance recognition with power parameters by using machine learning algorithms

Human Activity Recognition Using Spectrograms of Binary Motion Sensor Data

Contact Info

Product

Resources

About