An SVM fall recognition algorithm based on a gravity acceleration sensor

Hou, Mengqi; Wang, Haixia; Xiao, Zechen; Zhang, Guilin

doi:10.1080/21642583.2018.1547888

Cited by 11 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen, in general, SVM (under different configurations of the kernels) and, to a lesser extent, KNN, are the algorithms that offer the best classification of the patterns. This conclusion is consistent with most of the comparative analyses carried out in the literature that have compared the performance of ML classifiers in FDSs (see, for example, the studies in 52 , 60 , 61 ). Likewise, the results show that the selection of the 12 characteristics (‘own selection’) commented in “ Selection of input features ” section (which have a clear physical interpretation in the characterization of the activities) can even lead to a better behavior than the choice of 12 features based on the massive test of ‘abstract’ statistical features offered by the hctsa tool.…”

Section: Resultssupporting

confidence: 90%

A study on the impact of the users’ characteristics on the performance of wearable fall detection systems

Santoyo-Ramón

Casilari

Cano-García

2021

Sci Rep

View full text Add to dashboard Cite

Wearable Fall Detection Systems (FDSs) have gained much research interest during last decade. In this regard, Machine Learning (ML) classifiers have shown great efficiency in discriminating falls and conventional movements or Activities of Daily Living (ADLs) based on the analysis of the signals captured by transportable inertial sensors. Due to the intrinsic difficulties of training and testing this type of detectors in realistic scenarios and with their target audience (older adults), FDSs are normally benchmarked against a predefined set of ADLs and emulated falls executed by volunteers in a controlled environment. In most studies, however, samples from the same experimental subjects are used to both train and evaluate the FDSs. In this work, we investigate the performance of ML-based FDS systems when the test subjects have physical characteristics (weight, height, body mass index, age, gender) different from those of the users considered for the test phase. The results seem to point out that certain divergences (weight, height) of the users of both subsets (training ad test) may hamper the effectiveness of the classifiers (a reduction of up 20% in sensitivity and of up to 5% in specificity is reported). However, it is shown that the typology of the activities included in these subgroups has much greater relevance for the discrimination capability of the classifiers (with specificity losses of up to 95% if the activity types for training and testing strongly diverge).

show abstract

Section: Resultssupporting

confidence: 90%

A study on the impact of the users’ characteristics on the performance of wearable fall detection systems

Santoyo-Ramón

Casilari

Cano-García

2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The experimental findings show that the sensor data are helpful for detecting fall events. In a study of fall detection Hou et al [12] proposed a Smartphone device by using embedded acceleration sensors to record human motion. In their study they found that the accuracy of the SVM can reach 96.072%.Commodity based Smart watch sensor can reach 93.33% accuracy in a real world setting of fall detection by adjusting screaming data, sliding window and a Naïve machine learning method [20].…”

Section: Related Workmentioning

confidence: 99%

A Machine Learning Based Fall Detection for Elderly People with Neurodegenerative Disorders

2020

View full text Add to dashboard Cite

Fall is one of the most serious clinical problems faced by the elderly people. Elder people with neurodegenerative disorders like Parkinson disease often fall. This leads to the damage of physical condition and also mental condition. Therefore, elderly people should be taken care of all the time. However, it is not possible to take care of them every moment. Therefore, an automatic fall detection system is required to track elderly at any time. An automated fall detection system will provide timely assistance and hence, it will reduce medical care costs significantly. The recent developments in motion-sensor technologies have allowed the e cient use of wearable sensors in the overall treatment of the elderly. The paper presents a machine learning framework consisting of data collection, preprocessing of data, feature extraction and machine learning classifiers. They comprise C4.5, Random Forest, RepTree, and LMT (Logistic Model Tree). Dataset used in this research has been collected by using 3-axis accelerometer sensors which are mounted on a person's waist. Features have been extracted from this dataset which are used by these classifiers. C4.5 gives the highest accuracy which is 97.36% in comparison to other classifiers.

show abstract

“…Mengqi Hou et al [1], suggested that the acceleration signals have a certain deviation due to the difference in the position of the mobile phone. For better results the device was tied to the subject's waist where the centre of gravity of the human body lies.…”

Section: Introductionmentioning

confidence: 99%

Elcare: Elderly Care With Fall Detection

Jawale¹,

Joshi²,

Gogate³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Continuous growth in the aged population over the years around the globe suggests advancements in medical facilities to ensure good medical health of people. The elder population is vulnerable to many medical problems as the immune system as well as the musculoskeletal system weakens with time. Falls are the major cause leading to serious medical conditions such as paralysis or even death for elders. Early fall detection can help in reducing the severity of these accidents and provide immediate medical assistance. To detect falls this paper discusses the use of pose estimation and sensor-based mobile devices. The system makes use of MediaPipe’s Pose Detection method to form a skeletal structure of the person. Exploiting the features such as drastic change in coordinate axes, angle of inclination while falling, and the sudden change in velocity during a fall helps to verify the authenticity of the fall. The sensor-based method makes use of mobile sensors and records the change in their values to decide whether the activity is a fall or not. The combination of both these methods allows for an accurate fall detection mechanism where the system finally notifies the concerned authorities via real-time feedback techniques such as text, message, or push notification.

show abstract

An SVM fall recognition algorithm based on a gravity acceleration sensor

Cited by 11 publications

References 21 publications

A study on the impact of the users’ characteristics on the performance of wearable fall detection systems

A study on the impact of the users’ characteristics on the performance of wearable fall detection systems

A Machine Learning Based Fall Detection for Elderly People with Neurodegenerative Disorders

Elcare: Elderly Care With Fall Detection

Contact Info

Product

Resources

About