Intelligent Skiing Posture Detection and Recognition through Internet of Bodies

The training of special ability of skiing should start from the control of body posture ability to highlight the characteristics of the sports. Thus, the athletes can have the sports ability in the process of high-speed skiing. This paper establishes a system to automatically recognize the skiing posture which can help athletes grasp the skiing postures. First, the skiing images are collected by distributed camera. Second, the skeleton features are extracted to learn a classification model which is used to recognize and adjust skiing postures. Lastly, the analytical results of posture recognition is returned to athletes through Internet of bodies. The framework can effectively recognize the skiing postures and provide athletes with training advices.

Decoding Emotion in Drug Abusers: Evidence for Face and Body Emotion Recognition and for Disgust Emotion

Background: Different drugs damage the frontal cortices, particularly the prefrontal areas involved in both emotional and cognitive functions, with a consequence of decoding emotion deficits for people with substance abuse. The present study aims to explore the cognitive impairments in drug abusers through facial, body and disgust emotion recognition, expanding the investigation of emotions, processing, measuring accuracy and response velocity. Method: We enrolled 13 addicted to cocaine and 12 alcohol patients attending treatment services in Italy, comparing them with 33 matched controls. Facial emotion and body posture recognition tasks, a disgust rating task, and the Barrat Impulsivity Scale were included in the experimental assessment. Results: We found that emotional processes are differently influenced by cocaine and alcohol, suggesting that these substances impact diverse cerebral systems. Conclusion: The contribution made by the duration of consumption on emotional processing seems far less important than for cognitive processes. Drug abusers seem to be slower on elaboration of emotions and, in particular, of disgust emotion. Considering that the participants were not impaired in cognition, our data support the hypothesis that emotional impairments emerge independently from damage to cognitive functions.

Stretchable Filler/Solid Rubber Piezoresistive Thread Sensor for Gesture Recognition

Recently, the stretchable piezoresistive composites have become a focus in the fields of the biomechanical sensing and human posture recognition because they can be directly and conformally attached to bodies and clothes. Here, we present a stretchable piezoresistive thread sensor (SPTS) based on Ag plated glass microspheres (Ag@GMs)/solid rubber (SR) composite, which was prepared using new shear dispersion and extrusion vulcanization technology. The SPTS has the high gauge factors (7.8~11.1) over a large stretching range (0–50%) and approximate linear curves about the relative change of resistance versus the applied strain. Meanwhile, the SPTS demonstrates that the hysteresis is as low as 2.6% and has great stability during 1000 stretching/releasing cycles at 50% strain. Considering the excellent mechanical strain-driven characteristic, the SPTS was carried out to monitor posture recognitions and facial movements. Moreover, the novel SPTS can be successfully integrated with software and hardware information modules to realize an intelligent gesture recognition system, which can promptly and accurately reflect the produced electrical signals about digital gestures, and successfully be translated into text and voice. This work demonstrates great progress in stretchable piezoresistive sensors and provides a new strategy for achieving a real-time and effective-communication intelligent gesture recognition system.

Upper Body Posture Recognition Using Inertial Sensors and Recurrent Neural Networks

Inadequate sitting posture can cause imbalanced loading on the spine and result in abnormal spinal pressure, which serves as the main risk factor contributing to irreversible and chronic spinal deformity. Therefore, sitting posture recognition is important for understanding people’s sitting behaviors and for correcting inadequate postures. Recently, wearable devices embedded with microelectromechanical systems (MEMs) sensors, such as inertial measurement units (IMUs), have received increased attention in human activity recognition. In this study, a wearable device embedded with IMUs and a machine learning algorithm were developed to classify seven static sitting postures: upright, slump, lean, right and left bending, and right and left twisting. Four 9-axis IMUs were uniformly distributed between thoracic and lumbar regions (T1-L5) and aligned on a sagittal plane to acquire kinematic information about subjects’ backs during static-dynamic alternating motions. Time-domain features served as inputs to a signal-based classification model that was developed using long short-term memory-based recurrent neural network (LSTM-RNN) architecture, and the model’s classification performance was used to evaluate the relevance between sensor signals and sitting postures. Overall results from performance evaluation tests indicate that this IMU-based measurement and LSTM-RNN structural scheme was appropriate for sitting posture recognition.

Enhancing the differentiation of walking and standing via the ratio of plantar pressures

Differentiation of standing and walking based on plantar pressures is helpful in developing strategies to reduce health risks in the workplace. In order to improve the differentiation ability, the paper proposes a new metric for posture differentiation, that is, the pressure ratio on the two anatomical plantar regions. The plantar pressures were collected from 30 persons during walking and standing. After verifying the normal distribution of the pressure ratio by the Monte Carlo method, two-way repeated-measures ANOVA was conducted for the pressure ratios. The advantage of the pressure ratio over two conventional pressure metrics (the average pressure and the peak pressure) is demonstrated by its much larger size effect. Furthermore, the pressure ratio permits to establish value ranges corresponding to walking and standing, which are less influenced by specific person factors, thus facilitating the design of a standardized posture recognition system. The underlying mechanism underlying the pressure ratio is discussed from the aspect of biomechanics of movement.