Search

Various sensing modalities, including external and internal sensors, have been employed in research on human activity recognition (HAR). Among these, internal sensors, particularly wearable technologies, hold significant promise due to their lightweight nature and simplicity. Recently, HAR techniques leveraging wearable biometric signals, such as electrocardiography (ECG) and photoplethysmography (PPG), have been proposed using publicly available datasets. However, to facilitate broader practical applications, a more extensive analysis based on larger databases with cross-subject validation is required. In pursuit of this objective, we initially gathered PPG signals from 40 participants engaged in five common daily activities. Subsequently, we evaluated the feasibility of classifying these activities using deep learning architecture. The model's performance was assessed in terms of accuracy, precision, recall, and F-1 measure via cross-subject cross-validation (CV). The proposed method successfully distinguished the five activities considered, with an average test accuracy of 95.14%. Furthermore, we recommend an optimal window size based on a comprehensive evaluation of performance relative to the input signal length. These findings confirm the potential for practical HAR applications based on PPG and indicate its prospective extension to various domains, such as healthcare or fitness applications, by concurrently analyzing behavioral and health data through a single biometric signal. [ABSTRACT FROM AUTHOR]

One of the major reasons of mortality in human beings is cancer, and there is an absolute necessity for doctors to identify and treat a person suffering from it. Leukemia is a group of blood cancers that usually originates in the bone marrow and results in very high number of abnormal cells. For the diagnosis of cancer, microarray data serves as an important clinical application and serves as a great aid to the entire medical community. The dimensionality of the microarray data is too high, and so selection of suitable genes is quite an important step for the improvement of data classification. Therefore, for the prediction and diagnosis of cancer, there is an utmost necessity to select the most informative genes. In this work, Minimum Redundancy Maximum Relevance (MRMR), Signal to Noise Ratio (SNR), Multivariate Error Weight Uncorrelated Shrunken Centroid (EWUSC), and multivariate correlation-based feature selection (CFS) are chosen as initial feature selection techniques. Then, to select the most informative genes, five different kinds of evolutionary optimization techniques too are incorporated here such as African Buffalo Optimization (ABO), Artificial Bee Colony Optimization (ABCO), Cockroach Swarm Optimization (CSO), Imperialist Competitive Optimization (ICO), and Social Spider Optimization (SSO). Finally, the optimized values are fed through classification process and the best results are obtained when multivariate CFS with SSO is utilized and classified with Probabilistic Neural Network (PNN), and a high classification accuracy of 95.70% is obtained. [ABSTRACT FROM AUTHOR]

Manual sleep stage scoring is usually implemented with the help of sleep specialists by means of visual inspection of the neurophysiological signals of the patient. As it is a very hectic task to perform, automated sleep stage classification systems were developed in the past, and advancements are being made consistently by researchers. The various stages of sleep are identified by these automated sleep stage classification systems, and it is quite an important step to assist doctors for the diagnosis of sleep-related disorders. In this work, a holistic strategy named as clustering and dimensionality reduction with feature extraction cum selection for classification along with deep learning (CDFCD) is proposed for the classification of sleep stages with EEG signals. Though the methodology follows a similar structural flow as proposed in the past works, many advanced and novel techniques are proposed under each category in this work flow. Initially, clustering is applied with the help of hierarchical clustering, spectral clustering, and the proposed principal component analysis (PCA)-based subspace clustering. Then the dimensionality of it is reduced with the help of the proposed singular value decomposition (SVD)-based spectral algorithm and the standard variational Bayesian matrix factorization (VBMF) technique. Then the features are extracted and selected with the two novel proposed techniques, such as the sparse group lasso technique with dual-level implementation (SGL-DLI) and the ridge regression technique with limiting weight scheme (RR-LWS). Finally, the classification happens with the less explored multiclass Gaussian process classification (MGC), the proposed random arbitrary collective classification (RACC), and the deep learning technique using long short-term memory (LSTM) along with other conventional machine learning techniques. This methodology is validated on the sleep EDF database, and the results obtained with this methodology have surpassed the results of the previous studies in terms of the obtained classification accuracy reporting a high accuracy of 93.51% even for the six-classes classification problem. [ABSTRACT FROM AUTHOR]

Disease symptoms often contain features that are not routinely recognized by patients but can be identified through indirect inspection or diagnosis by medical professionals. Telemedicine requires sufficient information for aiding doctors' diagnosis, and it has been primarily achieved by clinical decision support systems (CDSSs) utilizing visual information. However, additional medical diagnostic tools are needed for improving CDSSs. Moreover, since the COVID-19 pandemic, telemedicine has garnered increasing attention, and basic diagnostic tools (e.g., classical examination) have become the most important components of a comprehensive framework. This study proposes a conceptual system, iApp, that can collect and analyze quantified data based on an automatically performed inspection, auscultation, percussion, and palpation. The proposed iApp system consists of an auscultation sensor, camera for inspection, and custom-built hardware for automatic percussion and palpation. Experiments were designed to categorize the eight abdominal divisions of healthy subjects based on the system multi-modal data. A deep multi-modal learning model, yielding a single prediction from multi-modal inputs, was designed for learning distinctive features in eight abdominal divisions. The model's performance was evaluated in terms of the classification accuracy, sensitivity, positive predictive value, and F-measure, using epoch-wise and subject-wise methods. The results demonstrate that the iApp system can successfully categorize abdominal divisions, with the test accuracy of 89.46%. Through an automatic examination of the iApp system, this proof-of-concept study demonstrates a sophisticated classification by extracting distinct features of different abdominal divisions where different organs are located. In the future, we intend to capture the distinct features between normal and abnormal tissues while securing patient data and demonstrate the feasibility of a fully telediagnostic system that can support abnormality diagnosis. [ABSTRACT FROM AUTHOR]

In this letter, we propose a multivariate time-series classification system that fuses multirate sensor measurements within the latent space of a deep neural network. In our network, the system identifies the surface category based on audio and inertial measurements generated from the surface impact, each of which has a different sampling rate and resolution in nature. We investigate the feasibility of categorizing ten different everyday surfaces using a proposed convolutional neural network, which is trained in an end-to-end manner. To validate our approach, we developed an embedded system and collected 60 000 data samples under a variety of conditions. The experimental results obtained exhibit a test accuracy for a blind test dataset of 93%, taking less than 300 ms for end-to-end classification in an embedded machine environment. We conclude this letter with a discussion of the results and future direction of research. [ABSTRACT FROM AUTHOR]

This article proposes an automatic fall detection method for a wearable device that can promptly alert caregivers when a fall is detected, which could reduce the injuries of elder people. To do this, we propose a novel generative adversarial network (GAN-) based fall detection method using a heart rate sensor and an accelerometer. Acquiring fall data compared with normal behavioral data can be an arduous process. Instead, we introduce a compelling GAN-based anomaly detection partially surrounded with User Initial information features (UI-GAN). Although GAN-based anomaly detection methods have been previously proposed, each model has its adequate suitability for each anomaly detection application. Therefore, this study firstly evaluates suitable GAN-based anomaly detection models for fall detection from among nine recently proposed GAN-based models. From UI-GAN, performance improvements are observed in the fall detection when using the UI information. To objectively demonstrate the competitive performance of UI-GAN, we compare it with eight other recently presented fall detection studies and have observed that it leads to better results. Lastly, since the target application in this study is the use of UI-GAN with a wearable device, the sufficiently satisfied latency of UI-GAN on the smartwatch is estimated. This study is the first attempt to use the initial information of users in GAN, and we hope that the effectiveness of the UI information is expected to be seen in other applications. [ABSTRACT FROM AUTHOR]

Humans have the extraordinary ability to identify objects by listening to the sound that is produced when hitting the objects’ surface. In this study, we propose an integrated sensor-actuator system that has the capability to identify the surface on which it is placed. The system contacts (i.e., taps or hits) the surface by generating a mechanical impact and then analyzes the resulting sound waveform to decipher the intrinsic characteristics of the surface on which it is placed. Further, a machine learning pipeline based on recent deep learning techniques was introduced to identify ten different everyday surfaces. The results demonstrated that the proposed system can successfully recognize various surfaces with a test accuracy of 91.73%. Furthermore, it was found that the proposed machine learning pipeline can be implemented in an embedded machine with an inference time of less than 300 ms. We conclude this paper with limitations and discussion of future work. [ABSTRACT FROM AUTHOR]

Recently, methods and devices that simultaneously utilize two or more tactile feedback types have been proposed for more immersive interaction with virtual objects. However, the masking effect, which makes us less sensitive to various stimuli presented at the same time, has scarcely been explored. In this study, we propose a novel tactile rendering algorithm that can eliminate the mutual masking effect at the user's sensation level, when mechanical vibration and electrovibration are applied simultaneously. First, the masking functions of the two stimuli were investigated for various stimulus combinations. Based on these, a generalized form of the masking function was derived. We then tested and confirmed that the proposed algorithm, which calculates the required stimulus intensity to compensate for the mutual masking effect, could render the arbitrary stimulus intensity desired to be perceived by the users. The results of the user test revealed that the proposed rendering algorithm significantly improved the virtual object recognition rate by approximately 23% when geometry and texture were presented jointly. This finding suggests principal guidelines for the combined use of mechanical vibration and electrovibration, as well as for other combinations of different tactile feedback types. [ABSTRACT FROM AUTHOR]

In this paper, we report an integrated soft and transparent visuo-haptic interface, which is compatible with flexible devices and wearable gadgets. The visuo-haptic interface is composed of a touch-sensitive visual display based on polymer waveguides and a dielectric elastomer microactuators (DEMA) array. The touch-sensitive visual display, formed via continuative multistep photolithography, is a multilayered structure with a tactile-sensing layer stacked onto a visual-imaging layer. The dual-functional layer is thin (total thickness: <200 μm) and transparent (transmittance: as high as 90%). The DEMA forming a unit cell of the array is designed as multiple three-dimensional structures with silver nanowires (AgNWs) compliant electrode. When an electric voltage is applied across compliant electrodes formed on the sides, individual microactuators expand directly in an upward direction. Thanks to the vertically deformable design, the DEMA produces programmable large normal forces up to about 30 times of thresholds at a localized area. An output force response of the DEMA is reversible, fast (<1 ms delay), durable (output force degradation: <8% during a million cycles), and large enough to be used in human tactile interfaces. Due to the synergetic benefits from the functional layers, the visuo-haptic interface allows demonstration of programmable tactile response with visual information while being intimately attached on human skin. [ABSTRACT FROM AUTHOR]

We propose an electromagnetic-based braille display that can represent two-dimensional information. The key principle is a flip-latch structure, which allows satisfying requirements of both protrusion force for braille recognition and low power consumption. A magnet-inserted flip-latch has an eccentric shape, and is driven by and flips over the protruded voice coil and pushing the braille pin. Then it acts as a latch to lock and maintain the pin protrusion without additional energy consumption. We manufacture braille display modules and arrange them into a braille display with a total of 192 pins (16 columns and 12 rows). The pin-to-pin spacing is 2.5 mm, and the thickness of the display is about 5.5 mm. Each pin can switch states in 5 ms of operating time with 1W of power. In this paper, we describe the design and operating mechanism of the proposed actuator and perform operation tests to obtain stable driving conditions for the display. Finally, applications and limitations of the proposed braille display are analyzed. [ABSTRACT FROM AUTHOR]

Background. In most reports on ECMO treatment, advanced age is classified as a contraindication to VA ECMO. We attempted to investigate whether advanced age would be a main risk factor deciding VA ECMO application and performing VA ECMO support. We determined whether advanced age should be regarded as an absolute or relative contraindication to VA ECMO and could affect weaning and survival rates of VA ECMO patients. Methods. VA ECMO was performed on 135 adult patients with primary cardiogenic shock between January 2010 and December 2014. Successful weaning was defined as weaning from ECMO followed by survival for more than 48 hours. Results. Among the 135 patients, 35 survived and were discharged uneventfully, and the remaining 100 did not survive. There were significant differences in survival between age groups, and older age showed a lower survival rate with statistical significance (P = .01). By multivariate logistic regression analysis, age was not significantly associated with in-hospital mortality (P = .83) and was not significantly associated with VA ECMO weaning (P = .11). Conclusions. Advanced age is an undeniable risk factor for VA ECMO; however, patients of advanced age should not be excluded from the chance of recovery after VA ECMO treatment. [ABSTRACT FROM AUTHOR]

This study presents a miniature haptic actuator (10 mm (L) × 10 mm (W) × 6.5 mm (H)) based on magnetorheological fluids, which is designed to provide realistic touch sensations to users. Its primary goals are to evaluate mechanical or actuation performances of the prototype magnetorheological actuator and to assess its effectiveness in conveying haptic sensations to users by conducting the psychophysical experiments. The mechanical performance study evaluated the prototype’s output forces from haptic perspectives using a dynamic test frame. The psychophysical experiments studied human subjects’ perceptions on haptic sensations produced by the prototype. The mechanical test results show that the magnetorheological actuator is capable of generating a wide range of frequency-dependent output forces (from 1.5 N to nearly 9 N). The psychophysical experiments show that the actuator offers various kinesthetic and vibrotactile sensations to human operators. Overall, the results suggest a feasibility of using the magnetorheological haptic actuator in real-world applications, such as a haptic keypad and functional buttons in small consumer electronics and hand-held devices. [ABSTRACT FROM AUTHOR]

This article presents a novel design of a miniature haptic actuator based on magnetorheological fluids for mobile applications with the aim of providing various haptic sensations to users in mobile devices. The primary design goal for a haptic actuator for mobile applications is to miniaturize its size while achieving large forces and low power consumption. To this end, this study proposes to design the actuator’s piston head (or plunger) in cone shape and activate multiple modes of magnetorheological fluids. A prototype actuator was designed and fabricated based on a simulation model. Using a dynamic test frame, the performance of the prototype actuator was evaluated in terms of the force (resistive force) produced by the prototype. The results show that the small actuator (10 mm × 10 mm × 6.5 mm) produced a maximum resistive force of about 5 N and the force rate of nearly 80% at 0.3 W. This change in resistive force or the force rate is sufficient to provide several steps of force variation that is explicitly perceivable for operators, depending on the input power. The results demonstrate a feasibility of using the proposed actuator’s applications in mobile devices, conveying realistic haptic sensations to users. [ABSTRACT FROM AUTHOR]

We demonstrate a robust flexible tactile actuator that is capable of working under high external pressures. The tactile actuator is based on a pyramidal microstructured dielectric elastomer layer inducing variation in both mechanical and dielectric properties. The vibrational performance of the actuator can be modulated by changing the geometric parameter of the microstructures. We evaluated the performance of the actuator under high-pressure loads up to 25 kPa, which is over the typical range of pressure applied when humans touch or manipulate objects. Due to the benefit of nonlinearity of the pyramidal structure, the actuator could maintain high mechanical output under various external pressures in the frequency range of 100–200 Hz, which is the most sensitive to vibration acceleration for human finger pads. The responses are not only fast, reversible, and highly durable under consecutive cyclic operations, but also large enough to impart perceivable vibrations for haptic feedback on practical wearable device applications. [ABSTRACT FROM AUTHOR]

Background: Digital therapeutics are emerging as treatments for diseases and disabilities. In chronic kidney disease (CKD), gait is a potential biomarker for health status and intervention effectiveness. This study aims to analyze gait characteristics in CKD patients, providing baseline data for digital therapeutics development., Methods: At baseline and after an 8-week intervention, we performed bioimpedance analysis measurements, the Timed Up and Go, Tinetti, and grip strength tests, and gait analysis in 217 healthy individuals and 276 patients with CKD. Demographic and clinical information was collected, including underlying diseases and medications, laboratory tests, and quality of life satisfaction surveys. Gait analysis was performed using skeleton data, which involved acquiring three-dimensional skeleton data of a walker using a single Kinect sensor. The performance of an artificial intelligence-based classification model in distinguishing between healthy individuals and those with CKD was then investigated. Simultaneously, inertia measurement unit analysis was conducted using measurements taken from the wrist and waist., Results: Most subjects received a health intervention via an app, and their gait was assessed for improvements after an 8-week period. Incidents such as falls, fractures, hospitalizations, and deaths will be investigated in years 1 and 3., Conclusion: This study confirmed that the gaits of healthy individuals and CKD patients were different, and the effect of the 8-week app-based health intervention will be analyzed. The study will yield important baseline data for creating digital therapeutics for CKD patients' diet/exercise in the future.

Humans excel at determining the shape and material of objects through touch. Drawing inspiration from this ability, we propose a robotic system that incorporates haptic sensing capability into its artificial recognition system to jointly learn the shape and material types of an object. To achieve this, we employ a serially connected robotic arm and develop a supervised learning task that learns and classifies target surface geometry and material types using multivariate time-series data from joint torque sensors. Additionally, we propose a joint torque-to-position generation task to derive a one-dimensional surface profile based on torque measurements. Experimental results successfully validate the proposed torque-based classification and regression tasks, suggesting that a robotic system can employ haptic sensing (i.e., perceived force) from each joint to recognize material types and geometry, akin to human abilities.

Inspired by spiders that can generate and sense vibrations to obtain information regarding a substrate, we propose an intelligent system that can recognize the type of surface being touched by knocking the surface and listening to the vibrations. Hence, we developed a system that is equipped with an electromagnetic hammer for hitting the ground and an accelerometer for measuring the mechanical responses induced by the impact. We investigate the feasibility of sensing 10 different daily surfaces through various machine-learning techniques including recent deep-learning approaches. Although some test surfaces are similar, experimental results show that our system can recognize 10 different surfaces remarkably well (test accuracy of 98.66%). In addition, our results without directly hitting the surface (internal impact) exhibited considerably high test accuracy (97.51%). Finally, we conclude this paper with the limitations and future directions of the study.

Recently, various methods using, simultaneously, two types of tactile feedback have been proposed to emulate a real object. However, the possible masking effect when providing two types of tactile feedback has been scarcely reported. In this study, we investigated the masking effect caused by mechanical vibration on the perception of electrovibration. The absolute and difference thresholds of the electrovibration were measured according to the presence/absence, frequency, and intensity of the mechanical vibration. The absolute threshold of electrovibration tended to increase in the form of a ramp function, as the intensity of the masking stimulus (mechanical vibration) increased. Particularly, the masking effect was more remarkable when the frequency of both the target and the masking stimulus was the same (up to 13 dB increase with 25 dB SL masker). Furthermore, the difference in the threshold (average of 1.21 dB) did not significantly change due to the masking stimulus, when the sensation level intensity of the target stimulus was within the section following the Weber's law. The results further indicated that electrovibration contributes to the activation of slowly adapting afferents as well. This investigation will provide important guidelines for the design of haptic interface that employs multiple types of tactile feedback.