Recognition of human activities using machine learning methods with wearable sensors

Cheng, Long; Guan, Yani; Zhu, Kecheng; Li, Yiyang

doi:10.1109/ccwc.2017.7868369

Cited by 44 publications

(25 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work of acknowledging ADL using machine learning that mostly focuses on static activities such as walking, standing, sitting, climbing stairs and downstairs [4]. Some study includes transitional activities such as standing up, sitting down and lying down [6] [3].…”

Section: A Activity Daily Livingmentioning

confidence: 99%

“…The effect of a machine learning model that is trained by using data with very few number of individuals can be observed by a study conducted by Cheng [3]. In his study, Cheng uses dataset collected from four individuals to conduct two types of classification experiment, 1-vs-own and 1-vs-all.…”

Section: Adl Classificationmentioning

confidence: 99%

“…The use of abundant numbers of features in training data does not necessarily contribute to a better training effect with lower testing error because some of the attributes might be not relevant to the classification process. Instead, when too many features are used it will require more processing time for a computer program to perform the classification [3].…”

Section: Adl Classificationmentioning

confidence: 99%

“…As we know, when we do some activities, different people will have a different posture and pattern. Thus, if the machine learning model trained with only a few subjects, classifying and differentiating activities for other people may be inaccurate [3]. Previous research also neglects to select the most relevant features to enhance the efficiency and accuracy of the results of the classification [4].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Recognizing the Activity Daily Living (ADL) for Subject Independent

Zainudin¹,

Kee²,

Idris³

et al. 2019

IJRTE

View full text Add to dashboard Cite

Recently, Human Activity Recognition (HAR) has gained meaningful information for a human being. A wearable sensor like an accelerometer, small and simple to perform, has opened the room for scientists to explore an initial understanding of ubiquitous computing. The wearable sensor has begun to receive attention among researchers in some respects to conduct their studies in a wide area of recognition of human activity. Recent ADL discusses not only simple activities but also cater to the broad categories of complex activities. However, when involving enormous numbers of a subject, the accuracy of recognition tends to reduce. Although a different subject performed the same activity, the acceleration signal acquired considerably differs. This is due to the distinct pattern of action for each subject based on various factors such as subject age, gender, emotion and personality. Thus, by enhancing the accuracy of recognition of ADL, this article proposes the framework for addressing the subject independent matter. The signal acquired from an accelerometer sensor will undergo a segmentation process to extract important features. Some of the characteristics may be meaningless in some instances to determine the class. Therefore, proposing a variety of features to select the most relevant features that can lead to accuracy above 90%. Also, this article outlined a brief empirical evaluation of previous related work. Using several machine learning algorithms, this preliminary work will be examined and analyzed.

show abstract

Section: A Activity Daily Livingmentioning

confidence: 99%

Section: Adl Classificationmentioning

confidence: 99%

Section: Adl Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recognizing the Activity Daily Living (ADL) for Subject Independent

Zainudin¹,

Kee²,

Idris³

et al. 2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Theoretically speaking, when doing the same activities, different people will have a different posture and pattern. Also, when only a few subjects are involved in the training process using machine learning, it may be inaccurate to classify activities for other subjects [3]. On top of that, previously reported work also not performing feature selection to choose the most relevant attribute for improving the efficiency and accuracy of classification results [4].…”

Section: Introductionmentioning

confidence: 99%

Activity Recognition on Subject Independent Using Machine Learning

Chaudhari

Aparna

Rane³

2020

Cybernetics and Information Technologies

View full text Add to dashboard Cite

Recent Activity Daily Living (ADL) not only tackles simple activities, but also caters to a wide range of complex activities. Although the same activity has been carried out under the same environmental conditions, the acceleration signal obtained from each subject considerably differs. This happens due to the pattern of action generated for each subject is diverse based on several aspects such as subject age, gender, emotion and personality. This project therefore compares the accuracy of various machine learning models for ADL classification. On top of that, this research work also scrutinizes the effectiveness of various feature selection methods to identify the most relevant attribute for ADL classification. As a result, Random Forest was able to achieve the highest accuracy of 83.3% on subject independent matter in ADL classification. Meanwhile, CFS Subset Evaluator is considered to be a good feature selector as it successfully selected the 8 most relevant features compared with Correlation and Information Gain Evaluator.

show abstract

Human Activity Identification Using Novel Feature Extraction and Ensemble-Based Learning for Accuracy

S¹,

Eranna²

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Recognition of human activities using machine learning methods with wearable sensors

Cited by 44 publications

References 10 publications

Recognizing the Activity Daily Living (ADL) for Subject Independent

Recognizing the Activity Daily Living (ADL) for Subject Independent

Activity Recognition on Subject Independent Using Machine Learning

Human Activity Identification Using Novel Feature Extraction and Ensemble-Based Learning for Accuracy

Contact Info

Product

Resources

About