PARE: Profile-Applied Reasoning Engine for Context-Aware System

Hoque, M. Robiul; Seo, Hyungyu; Yang, Sung-Hyun

doi:10.1177/155014775389091

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The user status is changed to none, when the condition for the high-level context is failed. More detailed description of the reasoning engine with preliminary testing results can be found in [20]. Profile Manager.…”

Section: Fig 2 Context Acquisition Module In Detailmentioning

confidence: 99%

Development of middleware architecture to realize context-aware service in smart home environment

Kim¹,

Hoque²,

Seo³

et al. 2016

COMSIS J

Self Cite

View full text Add to dashboard Cite

A smart home provides automated services based on the context of the home environment and user activity. Context acquiring, processing, reasoning, and disseminating to the services are complex tasks for a context-aware system. An appropriate middleware architecture could handle such complexity. In this paper, we proposed a middleware architecture for a context-aware system in smart home environment. Here, the context is modeled based on ontology using Web Ontology Language (OWL). In addition, a profile applied improved rule-based reasoning algorithm is integrated into this middleware to infer high-level contexts from available low-level contexts. Experimental result shows that the middleware provides more accurate and faster reasoning outcome compare with the traditional rule-based reasoning method. Moreover, context-aware service is also selected using the rule-based algorithm, where the service can be extended easily by adding new service rules in the service rule base.

show abstract

Section: Fig 2 Context Acquisition Module In Detailmentioning

confidence: 99%

Development of middleware architecture to realize context-aware service in smart home environment

Kim¹,

Hoque²,

Seo³

et al. 2016

COMSIS J

Self Cite

View full text Add to dashboard Cite

show abstract

“…Multi-binary classifiers can detect parallel activity [15,16], but this fails for many activities. The hidden Markov model (HMM) [17], condition random field [18], and various other types of machine learning approaches [19] and probability inference algorithms [20] are widely used for parallel activity detection. However, they cannot handle a large number of spatio-temporal data sequences.…”

Section: Introductionmentioning

confidence: 99%

Adapted Long Short-Term Memory (LSTM) for Concurrent\\ Human Activity Recognition

Thapa¹,

Zubaer²,

Yang³

2021

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In this era, deep learning methods offer a broad spectrum of efficient and original algorithms to recognize or predict an output when given a sequence of inputs. In current trends, deep learning methods using recent long short-term memory (LSTM) algorithms try to provide superior performance, but they still have limited effectiveness when detecting sequences of complex human activity. In this work, we adapted the LSTM algorithm into a synchronous algorithm (sync-LSTM), enabling the model to take multiple parallel input sequences to produce multiple parallel synchronized output sequences. The proposed method is implemented for simultaneous human activity recognition (HAR) using heterogeneous sensor data in a smart home. HAR assists artificial intelligence in providing services to users according to their preferences. The sync-LSTM algorithm improves learning performance and sees its potential for real-world applications in complex HAR, such as concurrent activity, with higher accuracy and satisfactory computational complexity. The adapted algorithm for HAR is also applicable in the fields of ambient assistive living, healthcare, robotics, pervasive computing, and astronomy. Extensive experimental evaluation with publicly available datasets demonstrates the competitive recognition capabilities of our approach. The sync-LSTM algorithm improves learning performance and has the potential for real-life applications in complex HAR. For concurrent activity recognition, our proposed method shows an accuracy of more than 97%.

show abstract

“…The machine learning method solves these kinds of problems. Necessarily, many different probabilistic and non-probabilistic machine learning methods [11][12][13] have been hot-figure for activity recognition in recent years. However, difficulties confronted by traditional machine learning approaches are overcome by deep learning and led to numerous enhancement in activity recognition.…”

Section: Introductionmentioning

confidence: 99%

A Deep Machine Learning Method for Concurrent and Interleaved Human Activity Recognition

Thapa

Zubaer

Lamichhane

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Human activity recognition has become an important research topic within the field of pervasive computing, ambient assistive living (AAL), robotics, health-care monitoring, and many more. Techniques for recognizing simple and single activities are typical for now, but recognizing complex activities such as concurrent and interleaving activity is still a major challenging issue. In this paper, we propose a two-phase hybrid deep machine learning approach using bi-directional Long-Short Term Memory (BiLSTM) and Skip-Chain Conditional random field (SCCRF) to recognize the complex activity. BiLSTM is a sequential generative deep learning inherited from Recurrent Neural Network (RNN). SCCRFs is a distinctive feature of conditional random field (CRF) that can represent long term dependencies. In the first phase of the proposed approach, we recognized the concurrent activities using the BiLSTM technique, and in the second phase, SCCRF identifies the interleaved activity. Accuracy of the proposed framework against the counterpart state-of-art methods using the publicly available datasets in a smart home environment is analyzed. Our experiment’s result surpasses the previously proposed approaches with an average accuracy of more than 93%.

show abstract

PARE: Profile-Applied Reasoning Engine for Context-Aware System

Cited by 7 publications

References 17 publications

Development of middleware architecture to realize context-aware service in smart home environment

Development of middleware architecture to realize context-aware service in smart home environment

Adapted Long Short-Term Memory (LSTM) for Concurrent\\ Human Activity Recognition

A Deep Machine Learning Method for Concurrent and Interleaved Human Activity Recognition

Contact Info

Product

Resources

About