Neural network application in Japanese sign language: distinction of similar Yubimoji gestures

In a previous paper, the authors built a neural network model to recognize Japanese sign language syllabary or yubimoji. One of the problems encountered in that study was the accurate digital representation and distinction of similar yubimoji gestures, i.e. gestures with the same finger flexure positions but with different hand/finger orientations. This study focuses on these yubimoji gestures. Using data from a glove interface with bend sensors and accelerometers, a neural network was built, trained and tested. The network performed well and good results were obtained.     

A comprehensive comparison of simple step counting techniques using wrist- and ankle-mounted accelerometer and gyroscope signals

The goal of this work is to compare the differences between various step counting algorithms using both accelerometer and gyroscope measurements from wrist and ankle-mounted sensors. Participants completed four different conditions on a treadmill while wearing an accelerometer and gyroscope on the wrist and the ankle. Three different step counting techniques were applied to the data from each sensor type and mounting location. It was determined that using gyroscope measurements allowed for better performance than the typically used accelerometers, and that ankle-mounted sensors provided better performance than those mounted on the wrist.     

Neural network application in Japanese sign language: distinction of similar Yubimoji gestures

In a previous paper, the authors built a neural network model to recognize Japanese sign language syllabary or yubimoji. One of the problems encountered in that study was the accurate digital representation and distinction of similar yubimoji gestures, i.e. gestures with the same finger flexure positions but with different hand/finger orientations. This study focuses on these yubimoji gestures. Using data from a glove interface with bend sensors and accelerometers, a neural network was built, trained and tested. The network performed well and good results were obtained.     

Systematic characterisation of silicon-embedded accelerometers for mechanomyography

Silicon soft suction sockets (roll-on sleeves) currently used in passive prostheses for below-elbow amputees could also be used in externally powered prostheses, enhancing their functionality and comfort. However, as it is extremely difficult to hold currently used electromyography (EMG) sensors in place reliably within a silicon socket, an alternative measurement of muscular activity as the control input is necessary. Mechanomyography (MMG) is the epidermal measurement of the low-frequency vibrations produced by a contracting muscle. MMG sensors do not have to be in direct contact with the skin. Moreover, the embedding of sensors in the roll-on sleeve may also solve attachment issues, making sensor placement flexible. Therefore the objective was to determine the feasibility of recording MMG signals using silicon-embedded, micro-machined accelerometers. Fifteen embedded accelerometers were excited with predefined vibration patterns. The signal-to-noise ratio (SNR) and frequency response of each sample were measured and compared with those of non-embedded accelerometers. The SNR of embedded samples (≊19 dB) was significantly higher than that of non-embedded samples (≊12 dB), owing to the considerable mechanical damping effect of the silicon in the 300–900 Hz bandwidth (p=0.0028). This has implications for the application of silicon-embedded accelerometers for externally powered prosthesis control.     

磁场方式的内窥镜体内三维定位与追踪方法研究

本研究以磁场方式来测定内窥镜探头在人体内的三维位置及姿态角。根据三个互相正交的圆环线圈在其周围空间任意点产生的三维磁感应强度表达式 ,以及附着于内窥镜探头上的三个相互正交的磁场传感器在该磁场空间任意点以任意姿态感应磁场时所获得信号的表达式 ,建立以空间位置 (x ,y ,z) ,姿态角 (a ,b ,c)为未知数的六元非线性方程组。使用具有全局收敛特性的牛顿 拉夫森算法求解非线性方程组 ,由磁场传感器所获得的测量数据计算出对应的一组位置和姿态 (x ,y ,z ,a ,b,c) ,从而实现内窥镜探头的三维定位和跟踪     

Physiological Acoustic Sensing Based on Accelerometers: A Survey for Mobile Healthcare

This paper reviews the applications of accelerometers on the detection of physiological acoustic signals such as heart sounds, respiratory sounds, and gastrointestinal sounds. These acoustic signals contain a rich reservoir of vital physiological and pathological information. Accelerometer-based systems enable continuous, mobile, low-cost, and unobtrusive monitoring of physiological acoustic signals and thus can play significant roles in the emerging mobile healthcare. In this review, we first briefly explain the operation principle of accelerometers and specifications that are important for mobile healthcare. Applications of accelerometer-based monitoring systems are then presented. Next, we review a variety of accelerometers which have been reported in literatures for physiological acoustic sensing, including both commercial products and research prototypes. Finally, we discuss some challenges and our vision for future development.     

Effect of accelerometer location on mechanomyogram variables during voluntary,constant-force contractions in three human muscles

To understand better the features of the mechanomyogram (MMG) with different force levels and muscle architectures, the MMG signals detected at many points along three muscles were analysed by the application of a linear array of MMG sensors (up to eight) over the skin. MMG signals were recorded from the biceps brachii, tibialis anterior and upper trapezius muscles of the dominant side of ten healthy male subjects. The accelerometers were aligned along the direction of the muscle fibres. One accelerometer was located over the distal muscle innervation zone, and the other six or seven accelerometers were placed over the muscle, forming an array of sensors with fixed distances between them. The array covered almost the entire muscle length in all cases. MMG signals detected from adjacent accelerometers had similar shapes, with correlation coefficients ranging from about 0.5 to about 0.9. MMG amplitude and characteristic spectral frequencies significantly depended on accelerometer location. The MMG amplitude was maximum at the muscle belly for the biceps brachii and the tibialis anterior. Higher MMG characteristic spectral frequencies were associated with higher amplitudes in the case of the biceps brachii, whereas the opposite was observed for the tibialis anterior muscle. In the upper trapezius, the relationship between characteristic spectral frequencies, MMG amplitude and contraction force depended on the accelerometer location. This suggested that MMG spectral features do not only reflect the mechanical properties of the recruited muscle fibres but depend on muscle architecture and motor unit territorial distribution. It was concluded that the location of the accelerometer can have an influence on both amplitude and spectral MMG features, and this dependence should be considered when MMG signals are used for muscle assessment.     

A smartphone-driven methodology for estimating physical activities and energy expenditure in free living conditions

This paper introduces a function dedicated to the estimation of total energy expenditure (TEE) of daily activities based on data from accelerometers integrated into smartphones. The use of mass-market sensors such as accelerometers offers a promising solution for the general public due to the growing smartphone market over the last decade. The TEE estimation function quality was evaluated using data from intensive numerical experiments based, first, on 12 volunteers equipped with a smartphone and two research sensors (Armband and Actiheart) in controlled conditions (CC) and, then, on 30 other volunteers in free-living conditions (FLC). The TEE given by these two sensors in both conditions and estimated from the metabolic equivalent tasks (MET) in CC served as references during the creation and evaluation of the function. The TEE mean gap in absolute value between the function and the three references was 7.0%, 16.4% and 2.7% in CC, and 17.0% and 23.7% according to Armband and Actiheart, respectively, in FLC. This is the first step in the definition of a new feedback mechanism that promotes self-management and daily-efficiency evaluation of physical activity as part of an information system dedicated to the prevention of chronic diseases.     

Temporal feature estimation during walking using miniature accelerometers: an analysis of gait improvement after hip arthroplasty

A new method for the detection of gait cycle phases using only two miniature accelerometers together with a light, portable digital recorder is proposed. Each subject is asked to walk on a walkway at his/her own preferred speed. Gait analysis was performed using an original method of computing the values of temporal parameters from accelerometer signals. First, to validate the accelerometric method, measurements are taken on a group of healthy subjects. No significant differences are observed between the results thus obtained and those from pressure sensors attached under the foot. Then, measurements using only accelerometers are performed on a group of 12 patients with unilateral hip osteo-arthritis. The gait analysis is carried out just before hip arthroplasty and again, three, six and nine months afterwards. A mean decrease of 88% of asymmetry of stance time and especially a mean decrease of 250% of asymmetry of double support time are observed, nine months after the operation. These results confirm the validity of the proposed method for healthy subjects and its efficiency for functional evaluation of gait improvement after arthroplasty.     

Temporal feature estimation during walking using miniature accelerometers: an analysis of gait improvement after hip arthroplasty

A new method for the detection of gait cycle phases using only two miniature accelerometers together with a light, portable digital recorder is proposed. Each subject is asked to walk on a walkway at his/her own preferred speed. Gait analysis was performed using an original method of computing the values of temporal parameters from accelerometer signals. First, to validate the accelerometric method, measurements are taken on a group of healthy subjects. No significant differences are observed between the results thus obtained and those from pressure sensors attached under the foot. Then, measurements using only accelerometers are performed on a group of 12 patients with unilateral hip osteo-arthritis. The gait analysis is carried out just before hip arthroplasty and again, three, six and nine months afterwards. A mean decrease of 88% of asymmetry of stance time and especially a mean decrease of 250% of asymmetry of double support time are observed, nine months after the operation. These results confirm the validity of the proposed method for healthy subjects and its efficiency for functional evaluation of gait improvement after arthroplasty.     

Development of an <Emphasis Type="Italic">In Vitro</Emphasis> 3D Brain Tissue Model Mimicking <Emphasis Type="Italic">In Vivo</Emphasis>-Like Pro-inflammatory and Pro-oxidative Responses

To analyze complex inflammatory responses in an in vitro system, we constructed a new 3D in vitro brain tissue model that exhibits in vivo-like tissue responses (e.g. immune cell phenotypes, and molecular response) to inflammatory stimuli. Finite element modeling of oxygen diffusion and cellular oxygen consumption predicted the oxygen profile within 3D structures, consisting of Type I collagen hydrogel embedded with murine microglia. Viability and cytotoxicity analyses supported the mathematical analysis, determining optimal cell growth conditions for 3D construct development. Real-time RT-PCR and ELISA demonstrated significant up-regulation of pro-inflammatory mediators, such as TNF-α, MCP-1, IL-6 and IL-1β, in lipopolysaccharide (LPS)-stimulated in vitro cell culture (2D and 3D) and in vivo mouse model systems. Interestingly, levels of inflammatory responses from the in vitro 3D model system were more similar to in vivo than in vitro 2D. Additionally, in situ dihydroethidium (DHE) assay and immunofluorescence staining revealed that levels of LPS-stimulated reactive oxygen species (ROS) generation and microglial activation from in vitro 3D model system were closer to in vivo than in vitro 2D. These results demonstrated that an in vitro 3D model provides more physiologically relevant pro-oxidative and pro-inflammatory environments in brain than an in vitro 2D model.     

Sensor systems for lower limb functional electrical stimulation (FES) control

Two sensor systems comprising clusters of accelerometers, magnetic sensors, a rate gyroscope, and a strain gauge were designed. For one system, the clusters were located at the belt and AFO. In the other system, the clusters were located at the AFO and the thigh. The maximum cluster size was 14 cm(3) and 75 g. The clusters of each sensor system were interconnected by a single flexible wire bus, which minimized the effects of cabling. The sensors detected five phases of normal gait to a resolution of 40 ms in an able bodied test. Using a threshold method, the sensor system repeatedly predicted an incipient knee buckle in a paraplegic individual by a minimum of 30 ms. One system detected knee flexion angle analytically to an accuracy of 3.2 degrees during sit to stand trials. The second system determined knee and hip flexion angle to an accuracy of 3.8 degrees during sit to stand trials through neural networks. The signal processing of the acquired sensor signals in each system was performed on a MC68332 microcomputer in conjunction with the data sampling, and suggested the possibility for each sensor system to be used in real time control of FES.     

Contamination of bar soaps under "in-use" conditions

Bar and liquid soaps from 26 public lavatories were investigated for microbial colonies. Of 84 samples obtained from bar soaps, 100% yielded positive cultures; liquid soaps were essentially negative (3/39). Where quantitative data were gathered, bar soaps were found to contain as few as 100-200 CFU/ml but ranged to a high of greater than 6000 CFU/ml. Although laboratory-challenged bar soaps showed a quick loss of microorganisms (less than 6 hours), "in-use" bars continued to contain high levels of organisms, even after more than 48 hours. Qualitatively, bar soaps were found to harbour 2 to 9 different genera of organisms per bar. The microbial population obtained from bar soap represented over 16 different genera. The discovery of so many and such different microorganisms on bar soaps indicates that this form of soap may be a potential reservoir for the spread of cross-infection in public institutions.     

Molecular characterization and genetic diversity of bovine <Emphasis Type="Italic">Kobuvirus</Emphasis>, Brazil

It is suggested that Bovine kobuvirus (BKV) is involved in the etiology of gastroenteric diseases especially among calves; however, this association remains unknown. This study evaluated 216 fecal samples from cattle with and without diarrhea symptoms obtained from different regions of Brazil. A 216 bp fragment of the BKV 3D gene was amplified by RT-PCR in 14.4 % (31/216) of the studied samples, and 17 samples were subjected to nucleotide sequencing. All positive samples were obtained from animals aged less than 5 months, and most of animals presented diarrhea (p < 0.05). Phylogenetic analyses showed that the obtained sequences were grouped within the genogroup 2 of BKV forming subclades specific for each Brazilian municipality sampled. In addition, the alignment of the sequences revealed differences of nucleotides between sequences from different locations. Our results indicate for the first time that there is a regional genotypic differentiation of BKV in Brazil.     

Development of an "early warning" sensor for encrustation of urinary catheters following Proteus infection

Biofilm formation in long-term urinary catheterized patients can lead to encrustation and blockage of urinary catheters with serious clinical complication. Catheter encrustation stems from infection with urease-producing bacteria, particularly Proteus mirabilis. Urease generates ammonia from urea, and the elevated pH of the urine results in crystallization of calcium and magnesium phosphates, which block the flow of urine. The aim of this research is to develop an "early warning" silicone sensor for catheter encrustation following bacterial infection of an in vitro bladder model system. The in vitro bladder model was infected with a range of urease positive and negative bacterial strains. Developed sensors enabled catheter blockage to be predicted ~17-24 h in advance of its occurrence. Signaling only occurred following infection with urease positive bacteria and only when catheter blockage followed. In summary, sensors were developed that could predict urinary catheter blockage in in vitro infection models. Translation of these sensors to a clinical environment will allow the timely and appropriate management of catheter blockage in long-term catheterized patients.     

Reaction–diffusion modelling for microphysiometry on cellular specimens

Using modeling and simulation, we quantify the influence of spatiotemporal dynamics on the accuracy of data obtained from sensors placed in microscaled reaction volumes. The model refers to cellular reaction (i.e. proton extrusion and oxygen consumption) in complex, buffering solutions. Whole cells or viable tissues cultured in such devices are monitored in real time with integrated sensors for pH and dissolved oxygen. A 3D finite element model of diffusion and metabolic reaction was set up. With respect to pH, the effect of buffering species on proton diffusion is analysed in detail. To account for the delayed time response of real sensors, the sensor impulse response time was implemented by linear convolution. A validation of the model has been achieved by an electrochemical approach. The model reveals significant deviations of measured pH and O₂, and values of these parameters actually occurring at different sites of the cell culture volume. It is applicable to any setting of (bio-) sensors involving reaction and diffusion of dissolved gases and particularly H⁺ ions in buffered solutions.     

Classification Accuracies of Physical Activities Using Smartphone Motion Sensors

Background

Over the past few years, the world has witnessed an unprecedented growth in smartphone use. With sensors such as accelerometers and gyroscopes on board, smartphones have the potential to enhance our understanding of health behavior, in particular physical activity or the lack thereof. However, reliable and valid activity measurement using only a smartphone in situ has not been realized.

Objective

To examine the validity of the iPod Touch (Apple, Inc.) and particularly to understand the value of using gyroscopes for classifying types of physical activity, with the goal of creating a measurement and feedback system that easily integrates into individuals’ daily living.

Methods

We collected accelerometer and gyroscope data for 16 participants on 13 activities with an iPod Touch, a device that has essentially the same sensors and computing platform as an iPhone. The 13 activities were sitting, walking, jogging, and going upstairs and downstairs at different paces. We extracted time and frequency features, including mean and variance of acceleration and gyroscope on each axis, vector magnitude of acceleration, and fast Fourier transform magnitude for each axis of acceleration. Different classifiers were compared using the Waikato Environment for Knowledge Analysis (WEKA) toolkit, including C4.5 (J48) decision tree, multilayer perception, naive Bayes, logistic, k-nearest neighbor (kNN), and meta-algorithms such as boosting and bagging. The 10-fold cross-validation protocol was used.

Results

Overall, the kNN classifier achieved the best accuracies: 52.3%–79.4% for up and down stair walking, 91.7% for jogging, 90.1%–94.1% for walking on a level ground, and 100% for sitting. A 2-second sliding window size with a 1-second overlap worked the best. Adding gyroscope measurements proved to be more beneficial than relying solely on accelerometer readings for all activities (with improvement ranging from 3.1% to 13.4%).

Conclusions

Common categories of physical activity and sedentary behavior (walking, jogging, and sitting) can be recognized with high accuracies using both the accelerometer and gyroscope onboard the iPod touch or iPhone. This suggests the potential of developing just-in-time classification and feedback tools on smartphones.     

Measuring orientation of human body segments using miniature gyroscopes and accelerometers

In the medical field, there is a need for small ambulatory sensor systems for measuring the kinematics of body segments. Current methods for ambulatory measurement of body orientation have limited accuracy when the body moves. The aim of the paper was to develop and validate a method for accurate measurement of the orientation of human body segments using an inertial measurement unit (IMU). An IMU containing three single-axis accelerometers and three single-axis micromachined gyroscopes was assembled in a rectangular box, sized 20×20×30 mm. The presented orientation estimation algorithm continuously corrected orientation estimates obtained by mathematical integration of the 3D angular velocity measured using the gyroscopes. The correction was performed using an inclination estimate continuously obtained using the signal of the 3D accelerometer. This reduces the integration drift that originates from errors in the angular velocity signal. In addition, the gyroscope offset was continuously recalibrated. The method was realised using a Kalman filter that took into account the spectra of the signals involved as well as a fluctuating gyroscope offset. The method was tested for movements of the pelvis, trunk and forearm. Although the problem of integration drift around the global vertical continuously increased in the order of 0.5°s ⁻¹, the inclination estimate was accurate within 3° RMS. It was shown that the gyroscope offset could be estimated continuously during a trial. Using an initial offset error of 1 rads ⁻¹, after 2 min the offset error was roughly 5% of the original offset error. Using the Kalman filter described, an accurate and robust system for ambulatory motion recording can be realised.     

Requirements for Coregistration Accuracy in On-Scalp MEG

Recent advances in magnetic sensing has made on-scalp magnetoencephalography (MEG) possible. In particular, optically-pumped magnetometers (OPMs) have reached sensitivity levels that enable their use in MEG. In contrast to the SQUID sensors used in current MEG systems, OPMs do not require cryogenic cooling and can thus be placed within millimetres from the head, enabling the construction of sensor arrays that conform to the shape of an individual’s head. To properly estimate the location of neural sources within the brain, one must accurately know the position and orientation of sensors in relation to the head. With the adaptable on-scalp MEG sensor arrays, this coregistration becomes more challenging than in current SQUID-based MEG systems that use rigid sensor arrays. Here, we used simulations to quantify how accurately one needs to know the position and orientation of sensors in an on-scalp MEG system. The effects that different types of localisation errors have on forward modelling and source estimates obtained by minimum-norm estimation, dipole fitting, and beamforming are detailed. We found that sensor position errors generally have a larger effect than orientation errors and that these errors affect the localisation accuracy of superficial sources the most. To obtain similar or higher accuracy than with current SQUID-based MEG systems, RMS sensor position and orientation errors should be \(< 4\,\hbox {mm}\) and \(< 10^\circ\), respectively.