Embedding-based real-time change point detection with application to activity segmentation in smart home time series data

Bermejo, Unai; Almeida, Aitor; Bilbao-Jayo, Aritz; Azkune, Gorka

doi:10.1016/j.eswa.2021.115641

Cited by 24 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, this article designs to use the smoke sensor MQ2 to detect the smoke concentration. The gas sensor has high sensitivity and adjustable sensitivity, and can respond to most smoke [ 14 ], especially for methane (CH4), the main component of natural gas used in the family. Table 1 shows the detection range of some smoke by MQ2.…”

Section: Smart Home Control and Managementmentioning

confidence: 99%

Smart Home Control and Management Based on Big Data Analysis

Chi¹,

Chi²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to improve the effect of smart home control and management, a new smart home control and management method based on big data analysis is designed. The basic hardware of smart home control and management is designed, including smoke sensor hardware, temperature and humidity sensor hardware, and infrared sensor hardware, so as to collect smart home data and realize data visualization and buzzer alarm. The collected data are transmitted through the indoor wireless network of smart home gateway equipment, and the data distributed cache architecture based on big data analysis is used to store smart home data. Based on the relevant data, the hybrid particle swarm optimization algorithm is used to schedule the control and management tasks of smart home to complete the control and management of smart home. The experimental results show that the device control and scenario management effect of this method is better, and the communication performance is superior and has high practical application value.

show abstract

Section: Smart Home Control and Managementmentioning

confidence: 99%

Smart Home Control and Management Based on Big Data Analysis

Chi¹,

Chi²

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Multiple challenges need to be addressed in order to achieve proper human behavior prediction, both from the machine learning [ 12 ] and the intelligent environments [ 13 ] perspectives. In our previous research, we proved two beneficial approaches to behavior modeling in intelligent environments: behavior is better represented as a complex structure with different behavior models [ 14 ], and representing user actions as embeddings improves the tasks of activity recognition [ 15 ] and activity change-point detection [ 16 ]. In this paper, we explore the applications of those approaches to the behavior prediction task in intelligent environments.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Analysis of Human Behavior Prediction Approaches in Intelligent Environments

Almeida

Bermejo

Bilbao-Jayo

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Behavior modeling has multiple applications in the intelligent environment domain. It has been used in different tasks, such as the stratification of different pathologies, prediction of the user actions and activities, or modeling the energy usage. Specifically, behavior prediction can be used to forecast the future evolution of the users and to identify those behaviors that deviate from the expected conduct. In this paper, we propose the use of embeddings to represent the user actions, and study and compare several behavior prediction approaches. We test multiple model (LSTM, CNNs, GCNs, and transformers) architectures to ascertain the best approach to using embeddings for behavior modeling and also evaluate multiple embedding retrofitting approaches. To do so, we use the Kasteren dataset for intelligent environments, which is one of the most widely used datasets in the areas of activity recognition and behavior modeling.

show abstract

“…In recent years, the detection and prediction of changes in time series data obtained from observations of a monitored system has become a relevant research topic in various fields [1,2,3]. In particular, change-point detection has attracted considerable interest in medical and neurological fields, where the accurate determination of changes in physiological parameters is particularly critical [4,5].…”

Section: Introductionmentioning

confidence: 99%

Behavioral Change Prediction from Physiological Signals Using Deep Learned Features

Diraco¹,

Siciliano²,

Leone³

2022

Preprint

View full text Add to dashboard Cite

Predicting change from multivariate time series has relevant applications ranging from medical to engineering fields. Multisensory stimulation therapy in patients with dementia aims to change the patient’s behavioral state. For example, patients who exhibit a baseline of agitation may be paced to change their behavioral state to relaxed. This study aims to predict changes in behavioral state from the analysis of the physiological and neurovegetative parameters to support the therapist during the stimulation session. In order to extract valuable indicators for predicting changes, both handcrafted and learned features were evaluated and compared. The handcrafted features were defined starting from the CATCH22 feature collection, while the learned ones were extracted using a Temporal Convolutional Network, and the behavioral state was predicted through Bidirectional Long Short-Term Memory Auto-Encoder, operating jointly. From the comparison with the state-of-the-art, the learned features-based approach exhibits superior performance with accuracy rates of up to 99.42% with a time window of 70 seconds and up to 98.44% with a time window of 10 seconds.

show abstract

Embedding-based real-time change point detection with application to activity segmentation in smart home time series data

Cited by 24 publications

References 32 publications

Smart Home Control and Management Based on Big Data Analysis

Smart Home Control and Management Based on Big Data Analysis

A Comparative Analysis of Human Behavior Prediction Approaches in Intelligent Environments

Behavioral Change Prediction from Physiological Signals Using Deep Learned Features

Contact Info

Product

Resources

About