A windowing approach for activity recognition in sensor data streams

Machot, Fadi Al; Mayr, Heinrich C.; Ranasinghe, Suneth

doi:10.1109/icufn.2016.7536937

Cited by 14 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These "best fitting sensors" for each activity were then streamed online in the dataset using a custom algorithm to window the data based on these sensor groups firing. Statistical and spatial features were then extracted as inputs to support the classification of the activities contained within the dataset [9].…”

Section: Related Workmentioning

confidence: 99%

“…The Aruba dataset, from the well-established CASAS project [20], was selected to evaluate and validate three different windowing techniques. This dataset was chosen as it has also been used in many previous experiments by other researchers to validate their research, specifically the DW approach that part of this experiment is based upon [9], and the worked based on the SEW approach in [6] that extends these features to achieve a higher classification accuracy [8]. The Aruba dataset was collected in the home of a single female adult occupant who undertook her normal daily routine for seven months that included regular visits from family members.…”

Section: Datasetmentioning

confidence: 99%

“…Using this approach, issues can occur if the source dataset contains portions of the data are not annotated correctly (or annotated at all), making it more difficult to correctly identify and classify the target activities. Furthermore, an additional downfall when using this approach is the inefficiency to model complex activities [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…This paper presents findings from a comparison of windowing approaches, applied to a single data source. Previous researchers [7][8][9][10][11][12] have compared various windowing techniques pair-wise, however, there does not appear to have been a direct comparison based on a single dataset from which to benchmark and objectively compare results. This prompted the current study, to objectively benchmark a dynamic approach against older, more conventional approaches using a single data source.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Comparative Analysis of Windowing Approaches in Dense Sensing Environments

Quigley

Donnelly

et al. 2018

UCAmI 2018

View full text Add to dashboard Cite

Windowing is an established technique employed within dense sensing environments to extract relevant features from sensor data streams. Among the established approaches of Explicit, Time-based and Sensor-Event based windowing, Dynamic windowing approaches are beginning to emerge. These dynamic approaches claim to address the inherent shortcomings of the aforementioned established approaches by determining the appropriate window length for live sensor data streams in real-time, thereby offering the potential to optimize and increase the recognition of these sensor represented activities. Beyond these potential benefits, dynamic approaches can also support anomaly detection by actively uncovering new, unknown window patterns within a trained model. This paper presents findings from a study which utilizes data from a single source dataset, towards benchmarking and comparing more traditional windowing approaches against a dynamic windowing approach. The experiments conducted on a real-world smart home dataset suggest Time-based windowing is the best approach. Through evaluation of results, Dynamic windowing approaches may benefit from carefully annotated datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Analysis of Windowing Approaches in Dense Sensing Environments

Quigley

Donnelly

et al. 2018

UCAmI 2018

View full text Add to dashboard Cite

show abstract

“…Baseline approach of fixed length Sliding window [20] SWTW Fixed length sensors windows with time based weighting sensors [20] SWMI Fixed length sensors windows with mutual information weighting sensors [21] DW Sensor windows where the window size determined dynamically [22] The results of the proposed method as well as the results of other methods are reported in Table 5. The numbers represent the efficiency of the algorithm based on the accuracy criterion.…”

Section: ) Threshold Parametermentioning

confidence: 99%

Activity Recognition Using Hierarchical Hidden Markov Models on Streaming Sensor Data

Asghari

Nazerfard

2018

2018 9th International Symposium on Telecommunications (IST)

View full text Add to dashboard Cite

Activity recognition from sensor data deals with various challenges, such as overlapping activities, activity labeling, and activity detection. Although each challenge in the field of recognition has great importance, the most important one refers to online activity recognition. The present study tries to use online hierarchical hidden Markov model to detect an activity on the stream of sensor data which can predict the activity in the environment with any sensor event. The activity recognition samples were labeled by the statistical features such as the duration of activity. The results of our proposed method test on two different datasets of smart homes in the real world showed that one dataset has improved 4% and reached (59%) while the results reached 64.6% for the other data by using the best methods.

show abstract

Real-Time Human Activity Recognition in Smart Home on Embedded Equipment: New Challenges

Najeh

Lohr

Leduc³

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Building Energy Management (BEM) and monitoring systems should not only consider HVAC systems and building physics but also human behaviors. These systems could provide information and advice to occupants about the significance of their practices with regard to the current state of a dwelling. It is also possible to provide services such as assistance to the elderly, comfort and health monitoring. For this, an intelligent building must know the daily activities of its residents and the algorithms of the smart environment must track and recognize the activities that the occupants normally perform as part of their daily routine. In the literature, deep learning is one of effective supervised learning model and cost-efficient for real-time HAR, but it still struggles with the quality of training data (missing values in time series and non-annotated event), the variability of data, the data segmentation and the ontology of activities. In this work, recent research works, existing algorithms and related challenges in this field are firstly highlighted. Then, new research directions and solutions (performing fault detection and diagnosis for drift detection, multi-label classification modeling for multi-occupant classification, new indicators for training data quality, new metrics weighted by the number of representations in dataset to handle the issue of missing data and finally language processing for complex activity recognition) are suggested to solve them respectively and to improve this field.

show abstract

A windowing approach for activity recognition in sensor data streams

Cited by 14 publications

References 7 publications

A Comparative Analysis of Windowing Approaches in Dense Sensing Environments

A Comparative Analysis of Windowing Approaches in Dense Sensing Environments

Activity Recognition Using Hierarchical Hidden Markov Models on Streaming Sensor Data

Real-Time Human Activity Recognition in Smart Home on Embedded Equipment: New Challenges

Contact Info

Product

Resources

About