Design and implementation of a system for body posture recognition

Under Ambient Intelligence auspice, many researchers have studied the area of context recognition such as location, users’ identity and activities, and other parameters related to users’ situation in the environment. One aspect of context that is pertained to the users’ situation is body posture of a sitting person. The aim of this paper is the design and development of a novel Aware Chair system that recognizes sitting body postures. The Aware Chair is based on digital sensors mounted on the sitting and back area of the chair. The chair is tested using 50 people with different gender, body mass, and height. The design details of the system as well as test results are presented in this paper.     

Cardiovascular and metabolic responses of active sitting while performing work-related tasks

Abstract

Stability balls and active-balance sitting chairs have recently emerged as a way to reduce sedentary behaviours in office settings. The purpose of this study was to determine differences in caloric expenditure and heart rate between a standard chair (SC), stability ball (SB) and active balanced sitting chair (ST) while performing work-related tasks. Participants (n?=?20) performed a 10-minute randomised reading and typing task while sitting on the SC, SB and ST. For both the reading and typing tasks, heart rate (HR), caloric expenditure per minute and metabolic equivalents were all significantly greater (i.e. 6–13%; 19–40%; 18–39%, respectively) while using the ST when compared to the SC and SB. No significant differences were observed between the SB and SC for any of the comparisons. The ST produced a greater HR response and caloric expenditure than the SC or SB, indicating that active balanced sitting may be a feasible way to increase energy expenditure in an office setting.

Practitioner summary: The purpose of this study was to determine differences in cardiovascular and metabolic responses to various forms of office chairs. The key finding was that active sitting on a balance chair significantly increased heart rate and caloric expenditure as compared to a stability ball and standard chair.

Abbreviations: SC: standard chair; SB: stability ball; ST: active balanced chair; HR: heart rate; kcalmin: caloric expenditure per minute; MET: metabolic equivalents     

Lumbar posture and trunk muscle activation during a typing task when sitting on a novel dynamic ergonomic chair

Low back pain (LBP) is a common musculoskeletal disorder and prolonged sitting often aggravates LBP. A novel dynamic ergonomic chair (‘Back App’), which facilitates less hip flexion while sitting on an unstable base has been developed. This study compared lumbar posture and trunk muscle activation on this novel chair with a standard backless office chair. Twelve painfree participants completed a typing task on both chairs. Lumbar posture and trunk muscle activation were collected simultaneously and were analysed using paired t-tests. Sitting on the novel dynamic chair significantly (p < 0.05) reduced both lumbar flexion and the activation of one back muscle (Iliocostalis Lumborum pars Thoracis). The discomfort experienced was mild and was similar (p > 0.05) between chairs. Maintaining lordosis with less muscle activation during prolonged sitting could reduce the fatigue associated with upright sitting postures. Studies with longer sitting durations, and in people with LBP, are required.

Practitioner Summary: Sitting on a novel dynamic chair resulted in less lumbar flexion and less back muscle activation than sitting on a standard backless office chair during a typing task among pain-free participants. Facilitating lordotic sitting with less muscle activation may reduce the fatigue and discomfort often associated with lordotic sitting postures.     

Specific flexion-related low back pain and sitting: comparison of seated discomfort on two different chairs

No study has examined the effectiveness of prescribing seating modifications according to the individual clinical presentation of people with low back pain (LBP). A dynamic, forward-inclined chair (‘Back App’) can reduce seated paraspinal muscle activation among pain-free participants. This study examined 21 participants whose LBP was specifically aggravated by prolonged sitting and was eased by standing. Low back discomfort (LBD) and overall body discomfort (OBD) were assessed every 15 min while participants sat for 1 h on both the dynamic, forward-inclined chair and a standard office chair. LBD increased significantly more (p = 0.005) on the standard office chair, with no significant difference (p = 0.178) in OBD between the chairs. The results demonstrate that, in a specific flexion-related subgroup of people with LBP, increased LBD during sitting can be minimised through modifying chair design. Mechanisms that minimise seated discomfort may be of relevance in LBP management, as part of a biopsychosocial management plan.

Practitioner summary: This study examined low back discomfort (LBD) during a typing task among people with low back pain (LBP). Sitting on a dynamic, forward-inclined chair resulted in less seated LBD than sitting on a standard office chair. Further research is required to examine the long-term effectiveness of ergonomics interventions in LBP.     

Comparison of four specific dynamic office chairs with a conventional office chair: impact upon muscle activation, physical activity and posture

Prolonged and static sitting postures provoke physical inactivity at VDU workplaces and are therefore discussed as risk factors for the musculoskeletal system. Manufacturers have designed specific dynamic office chairs featuring structural elements which promote dynamic sitting and therefore physical activity. The aim of the present study was to evaluate the effects of four specific dynamic chairs on erector spinae and trapezius EMG, postures/joint angles and physical activity intensity (PAI) compared to those of a conventional standard office chair. All chairs were fitted with sensors for measurement of the chair parameters (backrest inclination, forward and sideward seat pan inclination), and tested in the laboratory by 10 subjects performing 7 standardized office tasks and by another 12 subjects in the field during their normal office work. Muscle activation revealed no significant differences between the specific dynamic chairs and the reference chair. Analysis of postures/joint angles and PAI revealed only a few differences between the chairs, whereas the tasks performed strongly affected the measured muscle activation, postures and kinematics. The characteristic dynamic elements of each specific chair yielded significant differences in the measured chair parameters, but these characteristics did not appear to affect the sitting dynamics of the subjects performing their office tasks.     

Active sitting with backrest support: Is it feasible?

Abstract

Ergonomics science recommends office chairs that promote active sitting to reduce sitting related complaints. Since current office chairs do not fulfill this recommendation, a new chair was developed by inverting an existing dynamic chair principle. This study compares active sitting on the inverted chair during a simulated computer-based office task to two existing dynamic office chairs (n?=?8). Upper body stability was analysed using Friedman ANOVA (p?=?.01). In addition, participants completed a questionnaire to rate their comfort and activity after half a working day.

The inverted chair allowed the participants to perform a substantial range of lateral spine flexion (11.5°) with the most stable upper body posture (≤11?mm, ≤2°, p?≤?.01). The results of this study suggest that the inverted chair supports active sitting with backrest support during computer-based office work. However, according to comfort and activity ratings, results should be verified in a future field study with 24 participants.

Practitioner Summary: This experimental laboratory study analyses the feasibility of active sitting with a backrest support during common office work on a new type of dynamic office chair. The results demonstrate that active sitting with a backrest support is feasible on the new but limited on existing chairs.     

Static and dynamic postural loadings during computer work in females: Sitting on an office chair versus sitting on an exercise ball

Seated computer work results in prolonged static loading, which has been associated with the development of musculoskeletal disorders. A popular alternative to sitting on an office chair while performing computer work is to sit on an exercise ball. Sitting on an exercise ball might affect static and dynamic aspects of working posture. We monitored posture, muscle activation and spinal shrinkage in 10 females performing a 1-h typing task, while sitting on an office chair with armrests and while sitting on an exercise ball. Sitting on an exercise ball resulted in 33% more trunk motion and in 66% more variation in lumbar EMG. Both of these findings can be considered to be an advantage for the exercise ball. However, the fifth percentile and average lumbar EMG were also higher when sitting on an exercise ball, with 38% and 78%, respectively. In addition, more spinal shrinkage occurred when sitting on an exercise ball than when sitting on an office chair. Arm flexion was reduced, but trapezius activation was unaffected when sitting on an exercise ball. It is concluded that the advantages with respect to physical loading of sitting on an exercise ball may not outweigh the disadvantages.     

Assessing sedentary body movement with accelerometers and domain specific cognitive function during active sitting

The potential physiological and psychological consequences of active sitting are not self-evident. The purpose of this study was to determine how active sitting affects hip motion, as well as domain specific cognitive function. Thirty-seven participants sat for 10 min in three different sitting conditions including a chair with a backrest, chair without a backrest, and an exercise ball. Hip acceleration was monitored using an ActiGraph GT9X Link triaxial accelerometer, and cognitive function was assessed using three different tasks including typing, reading comprehension, and spatial direction estimates. A significant difference in hip acceleration was found between participants that sat on the exercise ball compared to a stool. Additionally, the participants sitting on the ball attempted fewer total direction estimates and fewer egocentric-based direction estimates than the participants who sat on the stool. There may be little or no cognitive benefit to active sitting for many typical work tasks.     

Spinal shrinkage with three different types of chair whilst performing video display unit work

The aim of the study was to investigate the magnitude of spinal shrinkage during video display unit (VDU) work when subjects were sitting on chairs with different design with forward-sloping seats with or without backrest, armrest or knee support and when using a conventional chair with horizontal seat. Three different chairs were investigated: A “Conventional chair” with horizontal seat, B “Ullman chair” with front half of seat sloping forward and back half horizontal, and C “Balans chair” with forward-sloping seat plus knee support. Eight healthy subjects used to professional VDU work volunteered to participate in this field study, which was performed at their own workplaces. The median shrinkage after a three-hour period was 1.3, 1.8 and 3.1 mm for chairs A, B and C, respectively. All subjects shrank more (p < 0.05) when sitting on the chair with knee support (C) than when sitting on the conventional chair. There was no statistically significant difference in shrinkage between chairs A and B, or between chairs B and C.     

Prediction of elderly seating comfort from physical condition, chair type and gender

Many persons over 60 years of age have unique problems sitting on chairs. These problems which are caused by decreased mobility, strength or disease suggest that the chairs should be selected carefully with some scientific basis that incorporates the varying demands of the elderly community. Identification of the proper chair for a particular individual, especially if it has to be low cost and nonmotorized, is a difficult job for institutions, elderly themselves, their families and the furniture industry. Keeping in view these problems a prediction model is developed using established statistical methods to predict comfort of sitting of a particular individual sitting in a particular chair. The study is based on experimental data collected on 18 male and female subjects over the age of 64. The equation uses chair type, body fat %, i.e. above average fat etc., body size, i.e. lean etc., and gender as inputs. The equation was tested on new female and male elderly subjects sitting on two new chairs. The model holds out excellent on the validation despite a low coefficient of determination value obtained for the equation. The paper not only presents a comfort prediction model but also shows a new direction for elderly seating research by employing statistical methods and elderly variables which do not appear in the published literature on elderly seating in the manner presented in this paper. This model will have wide applications especially for practioners (e.g., human factors engineers, occupational therapists, product developers) who need such information in a hurry. This approach also has heuristic value for the researcher in providing guidelines for the testing of other critical variables that may impact on the use of a chair or of other pieces of equipment.     

Estimating layout of cluttered indoor scenes using trajectory-based priors

Given a surveillance video of a moving person, we present a novel method of estimating layout of a cluttered indoor scene. We propose an idea that trajectories of a moving person can be used to generate features to segment an indoor scene into different areas of interest. We assume a static uncalibrated camera. Using pixel-level color and perspective cues of the scene, each pixel is assigned to a particular class either a sitting place, the ground floor, or the static background areas like walls and ceiling. The pixel-level cues are locally integrated along global topological order of classes, such as sitting objects and background areas are above ground floor into a conditional random field by an ordering constraint. The proposed method yields very accurate segmentation results on challenging real world scenes. We focus on videos with people walking in the scene and show the effectiveness of our approach through quantitative and qualitative results. The proposed estimation method shows better estimation results as compared to the state of the art scene layout estimation methods. We are able to correctly segment 90.3% of background, 89.4% of sitting areas and 74.7% of the ground floor.     

A parallel decision tree-based method for user authentication based on keystroke patterns

We propose a Monte Carlo approach to attain sufficient training data, a splitting method to improve effectiveness, and a system composed of parallel decision trees (DTs) to authenticate users based on keystroke patterns. For each user, approximately 19 times as much simulated data was generated to complement the 387 vectors of raw data. The training set, including raw and simulated data, is split into four subsets. For each subset, wavelet transforms are performed to obtain a total of eight training subsets for each user. Eight DTs are thus trained using the eight subsets. A parallel DT is constructed for each user, which contains all eight DTs with a criterion for its output that it authenticates the user if at least three DTs do so; otherwise it rejects the user. Training and testing data were collected from 43 users who typed the exact same string of length 37 nine consecutive times to provide data for training purposes. The users typed the same string at various times over a period from November through December 2002 to provide test data. The average false reject rate was 9.62% and the average false accept rate was 0.88%.     

The effect on sitting posture of a desk with a ten-degree inclination using an adjustable chair and table

By means of continuous recording of the positions of the trunk and head, an investigation was carried out to examine the effect of the Erasmus office-desk - a desk with a 10 degrees inclination - on sitting posture whilst reading and writing, sitting in an adjustable chair at an adjustable table. The posture assumed by a person who is doing mixed reading and writing work at a table with the Erasmus office-desk is more upright than the posture of the same person doing the same work without the desk. This applies for both the head and the trunk. The average position of the trunk was changed from 26.0 degrees to 18.2 degrees when working with the desk placed on the table. The moment of force caused by gravity is proportional to the sine of the angle. Therefore the change of angle results in a decrease of the average moment of force on the back at L5-S1 of 29%. The largest individual decrease found was 86%. The average change of the position of the head was changed from 38.5 degrees to 29.6 degrees , resulting in an average decrease of the moment of force, on C7-T1, of 21%. The largest individual decrease was 51%. Lateroflexion of the back was less often assumed when the subjects were using the desk. The posture assumed by the subjects when they were doing writing work only was generally more upright when working at a desk with a 10 degrees inclination than when working at a flat desk. Marked differences were found between the postures of the subjects. The change of posture while using the desk also showed marked differences for each subject individually.     

Multimodal person detection system

Person detection is often critical for personal safety, property protection, and national security. Most person detection technologies implement unimodal classification, making predictions based on a single sensor data modality, which is most often vision. There are many ways to defeat unimodal person detectors, and many more reasons to ensure technologies responsible for detecting the presence of a person are accurate and precise. In this paper, we design and implement a multimodal person detection system which can acquire data from multiple sensors and detect persons based on a variety of unimodal classifications and multimodal fusions. We present two methods of generating system-level predictions: (1) device perspectives which makes a final decision based on multiple device-level predictions and (2) system perspectives which combines data samples from multiple devices into a single data sample and then makes a decision. Our experimental results show that system-level predictions from system perspectives are generally more accurate than system-level predictions from device perspectives. We achieve an accuracy of 100%, zero false positive rate and zero false negative rate with fusion of system perspectives motion and distance data.

     

Design and testing of a low-cost robotic wheelchair prototype

Many people who are mobility impaired are, for a variety of reasons, incapable of using an ordinary wheelchair. In some instances, a power wheelchair also cannot be used, usually because of the difficulty the person has in controlling it (often due to additional disabilities). This paper describes two low-cost robotic wheelchair prototypes that assist the operator of the chair in avoiding obstacles, going to pre-designated places, and maneuvering through doorways and other narrow or crowded areas. These systems can be interfaced to a variety of input devices, and can give the operator as much or as little moment by moment control of the chair as they wish. This paper describes both systems, the evolution from one system to another, and the lessons learned.     

Length of the spine while sitting on a new concept for an office chair

Changes in spinal length were used to evaluate a new concept for an office chair. This so-called dynamic chair imparts passive forced motion to the seated subject. The passive forced motion is a rotary movement about an axis, perpendicular to the seat with amplitude of 0.6 degrees and a frequency of 0.08 Hz. Change of stature is assumed to provide a measure for spinal load. Eight subjects were measured in two situations: static (without motion) and dynamic. In both situations the same office tasks were performed and the duration of the sitting period was 1 h. To allow for the normal shrinkage curve the starting time was the same on each of the measurement days. The results indicated a significant difference: when sitting on the dynamic chair the average spinal length increased in comparison to the spinal length in the static chair, where average spinal length decreased. It was concluded that there is spinal distress relief due to the passive motion of the chair.     

Application of Zen sitting principles to microscopic surgery seating

This paper describes the application of an alternative seating concept for surgeons that reflects the research of Zen sitting postures, which require Zazen meditators to maintain fixed postures for long durations. The aim of this alternative approach is to provide sitters with a seat pan with sacral support(1) that provides a more even distribution of seat pressures, induces forward pelvic rotation and improves lumbar, buttock and thigh support. This approach was applied to the development of a chair for microscopic surgery. The experimental chair is a seat pan that closely matches the three-dimensional contours of the user's buttocks. Seat comfort was evaluated by comparing both changes in pelvic tilt and seat pressure distributions using Regionally-Differentiated Pressure Maps (RDPM) with subjective ratings of surgeons while operating in prototype and conventional chairs. Findings include that the sacral support of the prototype chair prevents backward pelvic rotation, as seen in zazen (Zen sitting postures). Preliminary data suggests that the prototype provided greater sitting comfort and support for constrained operating postures than did the conventional chair. These findings support the selective application of concave-shaped seat pans that conform to users' buttocks and reflect Zen sitting principles.     

The effect of posture on the responses to cycle ergometer exercise

Nine male subjects performed submaximal and maximal exercise on a cycle ergometer while sitting on the saddle or on a chair behind the cycle ergometer with the legs horizontal. Data for oxygen uptake, respiratory variables, heart rate, and systolic blood pressure during exercise showed that there are no essential differences between these two positions.     

Posture and cycle ergometer exercise

Nine male subjects performed submaximal and maximal exercise on a cycle ergometer while sitting on the saddle or on a chair behind the cycle ergometer with the legs horizontal. Data for oxygen uptake, respiratory variables, heart rate, and systolic blood pressure during exercise showed that there are no essential differences between these two positions.     

基于流形学习的用户身份认证

本文基于等距映射（ISOMAP）非线性降维算法, 提出了一种新的基于用户击键特征的用户身份认证算法, 该算法用测地距离代替传统的欧氏距离, 作为样本向量之间的距离度量,在用户击键特征向量空间中挖掘嵌入的低维黎曼流形,进行用户识别。用采集到的1500个击键模式数据进行实验测试,结果表明,该文的算法性能优于现有的同类算法,其错误拒绝率（FRR）和错误通过率（FAR）分别是1.65%和0%,低于现有的同类算法。