Wearable sensor based human posture recognition

Zhang²,

2020 IEEE 32nd International Conference on Tools With Artificial Intelligence (ICTAI)

et al. 2020

Self Cite

Artificial intelligence (AI)-based decision-making systems are employed nowadays in an ever growing number of online as well as offline services-some of great importance. Depending on sophisticated learning algorithms and available data, these systems are increasingly becoming automated and data-driven. However, these systems can impact individuals and communities with ethical or legal consequences. Numerous approaches have therefore been proposed to develop decisionmaking systems that are discrimination-conscious by-design. However, these methods assume the underlying data distribution is stationary without drift, which is counterfactual in many realworld applications. In addition, their focus has been largely on minimizing discrimination while maximizing prediction performance without necessary flexibility in customizing the tradeoff according to different applications. To this end, we propose a learning algorithm for fair classification that also adapts to evolving data streams and further allows for a flexible control on the degree of accuracy and fairness. The positive results on a set of discriminated and non-stationary data streams demonstrate the effectiveness and flexibility of this approach.

Section: B Data Stream Learningmentioning

confidence: 99%

Flexible and Adaptive Fairness-aware Learning in Non-stationary Data Streams

Zhang²,

2020 IEEE 32nd International Conference on Tools With Artificial Intelligence (ICTAI)

et al. 2020

Self Cite

Int. J. Mach. Learn. & Cyber.

“…There are several main methods for posture recognition. One is to use wearable sensors [39], such as wearing accelerometer [2,3,16] and pressure sensor [11]. However, wearing such a device makes subjects feel a sense of burden, which compromises the interactive experience.…”

Section: Introductionmentioning

confidence: 99%

Human posture recognition based on multiple features and rule learning

Ding

Liu

et al. 2020

The use of skeleton data for human posture recognition is a key research topic in the human-computer interaction field. To improve the accuracy of human posture recognition, a new algorithm based on multiple features and rule learning is proposed in this paper. Firstly, a 219-dimensional vector that includes angle features and distance features is defined. Specifically, the angle and distance features are defined in terms of the local relationship between joints and the global spatial location of joints. Then, during human posture classification, the rule learning method is used together with the Bagging and random subspace methods to create different samples and features for improved classification performance of sub-classifiers for different samples. Finally, the performance of our proposed algorithm is evaluated on four human posture datasets. The experimental results show that our algorithm can recognize many kinds of human postures effectively, and the results obtained by the rule-based learning method are of higher interpretability than those by traditional machine learning methods and CNNs.

“…Traditional human posture detection methods can mainly be divided into two categories: computer vision [3,4,5,6,7,8,9,10,11,12] and acceleration sensor data analysis [13,14,15,16]. Methods based on acceleration sensors have the disadvantage of complex data processing steps, but their invasion of privacy is well tolerated.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, human posture detection technology based on acceleration sensor data analysis has been proposed in [13,14,15,16]. In [13], a waist-mounted device to detect possible falls of elderly people is presented, and four accelerometer sensors are combined to achieve good performances.…”

Section: Introductionmentioning

confidence: 99%

“…This method asks the elderly to use a high cost smartphone. Reference [16] presents wearable sensor devices to recognize human postures, and they conducts their experiments with participants wearing three sensors which can reach 90% overall accuracy of human postures. Caroppo et al [17] described a multi-sensor platform for anomalies, which acquires postures by both ambient and wearable sensors that are a time-of-flight 3D vision sensor, UWB radar sensor and a 3-axis accelerometer.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Posture Recognition Method Based on Indoor Positioning Technology

Huang

Wang

et al. 2019

Sensors

Posture recognition has been widely applied in fields such as physical training, environmental awareness, human-computer-interaction, surveillance system and elderly health care. The traditional methods consist of two main variations: machine vision methods and acceleration sensor methods. The former has the disadvantages of privacy invasion, high cost and complex implementation processes, while the latter has low recognition rate for still postures. A new body posture recognition scheme based on indoor positioning technology is presented in this paper. A single deployed indoor positioning system is constructed by installing wearable receiving tags at key points of the human body. The distance measurement method with ultra-wide band (UWB) radio is applied to position the key points of human body. Posture recognition is implemented by positioning. In the posture recognition algorithm, least square estimation (LSE) method and the improved extended Kalman filtering (iEKF) algorithm are respectively adopted to suppress the noise of the distances measurement and to improve the accuracy of positioning and recognition. The comparison of simulation results with the two methods shows that the improved extended Kalman filtering algorithm is more effective in error performance.