Activities of daily life recognition using process representation modelling to support intention analysis

Naeem, Usman; Bashroush, Rabih; Anthony, Richard; Azam, Muhammad Awais; Tawil, Abdel-Rahman H.; Lee, Sin Wee; Wong, M. L. Dennis

doi:10.1108/ijpcc-01-2015-0002

Cited by 9 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Work in [31] presents an event filtering approach by adding preconditions with probabilities on the phases when carrying out each ADL in order to segment the incoming events. It is unclear how the algorithm can detect new activity when an action is shared amongst more than one activities and it can either be part of a main activity or precondition actions for another activity.…”

Section: Pragmatic Approach: Precondition and Evidential Theorymentioning

confidence: 99%

A semantics-based approach to sensor data segmentation in real-time Activity Recognition

Triboan

Chen

et al. 2019

Future Generation Computer Systems

View full text Add to dashboard Cite

Activity Recognition (AR) is key in context-aware assistive living systems. One challenge in AR is the segmentation of observed sensor events when interleaved or concurrent activities of daily living (ADLs) are performed. Several studies have proposed methods of separating and organising sensor observations and recognise generic ADLs performed in a simple or composite manner. However, little has been explored in semantically distinguishing individual sensor events directly and passing it to the relevant ongoing/new atomic activities. This paper proposes Semiotic theory inspired ontological model, capturing generic knowledge and inhabitant-specific preferences for conducting ADLs to support the segmentation process. A multithreaded decision algorithm and system prototype were developed and evaluated against 30 use case scenarios where each event was simulated at 10sec interval on a machine with i7 2.60GHz CPU, 2 cores and 8GB RAM. The result suggests that all sensor events were adequately segmented with 100% accuracy for single ADL scenarios and minor improvement of 97.8% accuracy for composite ADL scenario. However, the performance has suffered to segment each event with the average classification time of 3971ms and 62183ms for single and composite ADL scenarios, respectively.

show abstract

Section: Pragmatic Approach: Precondition and Evidential Theorymentioning

confidence: 99%

A semantics-based approach to sensor data segmentation in real-time Activity Recognition

Triboan

Chen

et al. 2019

Future Generation Computer Systems

View full text Add to dashboard Cite

show abstract

“…In recent studies, the KD approach is commonly used but ranges in the methods that are employed. For instance, studies in [14]- [20] adopt ontological models to describe ADLs, environmental entities and their relations along with other methods to classify and infer unfolding activities. These methods include: description logics (DLs), temporal relationship of activities, static/dynamic timing window protocol, Semantic Web Rule Language (SWRL) based rules, SPARQL Protocol and RDF Query Language (SPARQL) queries and reasoning tools.…”

Section: Related Workmentioning

confidence: 99%

“…These methods include: description logics (DLs), temporal relationship of activities, static/dynamic timing window protocol, Semantic Web Rule Language (SWRL) based rules, SPARQL Protocol and RDF Query Language (SPARQL) queries and reasoning tools. Work in [20] presents an event filtering approach by adding preconditions with probabilities on the phases when carrying out each ADL in order to segment the incoming events. It is unclear how the algorithm can detect new activity when an action is shared or part of a precondition for one activity but is not for the new activity.…”

Section: Related Workmentioning

confidence: 99%

“…Meanwhile, other studies in [14]- [20], do not directly inspect each sensor event as they arrive and then segment to the appropriate queue related to ongoing activities. Instead, the events are queried from the database and then rules/continuous queries are executed along with the ontology by the reasoner before inferring the activity and its execution complexity.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Real-time sensor observation segmentation for complex activity recognition within smart environments

Triboan

Chen

et al. 2017

2017 IEEE SmartWorld, Ubiquitous Intelligence &Amp; Computing, Advanced &Amp; Trusted Computed, Scalable Computing &Amp; Commun

View full text Add to dashboard Cite

Activity Recognition (AR) is at the heart of any types of assistive living systems. One of the key challenges faced in AR is segmentation of the sensor events when inhabitant performs simple or composite activities of daily living (ADLs). In addition, each inhabitant may follow a particular ritual or a tradition in performing different ADLs and their patterns may change overtime. Many recent studies apply methods to segment and recognise generic ADLs performed in a composite manner. However, little has been explored in semantically distinguishing individual sensor events and directly passing it to the relevant ongoing/new atomic activities. This paper proposes to use the ontological model to capture generic knowledge of ADLs and methods which also takes inhabitant-specific preferences into considerations when segmenting sensor events. The system implementation was developed, deployed and evaluated against 84 use case scenarios. The result suggests that all sensor events were adequately segmented with 98% accuracy and the average classification time of 3971ms and 62183ms for single and composite ADL scenarios were recorded, respectively.

show abstract

“…Daily life activities are often composed of several steps [11]. For example; the activity wash clothes implies the following actions: get clothes from basket, fill up washing machine, turn on washing machine.…”

Section: Introductionmentioning

confidence: 99%

Abnormal Behaviour Detection for Dementia Sufferers via Transfer Learning and Recursive Auto-Encoders

Arifoǧlu

Bouchachia

2019

2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)

View full text Add to dashboard Cite

Cognitive impairment is one of the crucial problems elderly people face. Tracking their daily life activities and detecting early indicators of cognitive decline would be necessary for further diagnosis. Depending on the decline magnitude, monitoring may need to be done over long periods of time to detect abnormal behaviour. In the absence of training data, it would be helpful to learn the normal behaviour and daily life patterns of a (cognitively) healthy person and use them as a basis for tracking other patients. In this paper, we propose to investigate Recursive Auto-Encoders (RAE)-based transfer learning to cope with the problem of scarcity of data in the context of abnormal behaviour detection. We present a method for generating synthetic data to reflect on some behavior of people with dementia. An RAE model is trained on data of a healthy person in a source household. Then, the resulting RAE is used to detect abnormal behavior in a target house. To evaluate the proposed approach, we compare the results with the-state-ofthe-art supervised methods. The results indicate that transfer learning is promising when there is lack of training data.

show abstract

Activities of daily life recognition using process representation modelling to support intention analysis

Cited by 9 publications

References 36 publications

A semantics-based approach to sensor data segmentation in real-time Activity Recognition

A semantics-based approach to sensor data segmentation in real-time Activity Recognition

Real-time sensor observation segmentation for complex activity recognition within smart environments

Abnormal Behaviour Detection for Dementia Sufferers via Transfer Learning and Recursive Auto-Encoders

Contact Info

Product

Resources

About