Exploring the Possibility of Photoplethysmography-Based Human Activity Recognition Using Convolutional Neural Networks.

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.

Robotic Kinesthesia: Estimating Object Geometry and Material With Robot's Haptic Senses.

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.

A Dual Level Analysis with Evolutionary Computing and Swarm Models for Classification of Leukemia.

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.

A Holistic Strategy for Classification of Sleep Stages with EEG.

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.

iApp: An Autonomous Inspection, Auscultation, Percussion, and Palpation Platform.

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.

Estimation of Fine-Grained Foot Strike Patterns with Wearable Smartwatch Devices.

People who exercise may benefit or be injured depending on their foot striking (FS) style. In this study, we propose an intelligent system that can recognize subtle differences in FS patterns while walking and running using measurements from a wearable smartwatch device. Although such patterns could be directly measured utilizing pressure distribution of feet while striking on the ground, we instead focused on analyzing hand movements by assuming that striking patterns consequently affect temporal movements of the whole body. The advantage of the proposed approach is that FS patterns can be estimated in a portable and less invasive manner. To this end, first, we developed a wearable system for measuring inertial movements of hands and then conducted an experiment where participants were asked to walk and run while wearing a smartwatch. Second, we trained and tested the captured multivariate time series signals in supervised learning settings. The experimental results obtained demonstrated high and robust classification performances (weighted-average F1 score > 90%) when recent deep neural network models, such as 1D-CNN and GRUs, were employed. We conclude this study with a discussion of potential future work and applications that increase benefits while walking and running properly using the proposed approach.

Braille Display for Portable Device Using Flip-Latch Structured Electromagnetic Actuator.

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.

Knocking and Listening: Learning Mechanical Impulse Response for Understanding Surface Characteristics.

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.

Unexpected complication during extracorporeal membrane oxygenation support: Ventilator associated systemic air embolism.

Systemic air embolism through a bronchovenous fistula (BVF) has been described in patients undergoing positive-pressure ventilation. However, no report has mentioned the potential risks of systemic air embolism through a BVF in patients undergoing extracorporeal membrane oxygenation (ECMO). Positive-pressure ventilation and ECMO support in patients with lung injury can increase the risk of systemic air embolism through a BVF. Increased alveolar pressure, decreased pulmonary venous pressure, and anticoagulation are thought to be the factors that contribute to this complication. Here, we present a case of systemic air embolism in a patient with ECMO and mechanical ventilator support.

L-carnosine induces apoptosis/cell cycle arrest via suppression of NF-κB/STAT1 pathway in HCT116 colorectal cancer cells.

L-carnosine, a dipeptide of the amino acids ß-alanine and histidine, is found in various tissues, such as the central nervous system and skeletal muscles. Recently, L-carnosine has been reported to possess anti-tumor activity; however, the molecular mechanism underlying its activity in colorectal cancer is still unknown. Therefore, we investigated the effect of L-carnosine using a human colorectal cancer cell line, HCT116. Treatment with L-carnosine (0, 100, or 200 mM) for 24 h gradually reduced cellular proliferation according to immunochemistry and 7-aminoactinomycin D (7-AAD) analyses and induced G0/G1 phase arrest. In the RT-PCR analysis, L-carnosine decreased the mRNA levels of cell cycle-related genes in HCT116 cells. In the Western blot analysis, levels of the cyclin D1, BAX/Bcl-2, cleaved caspase-3, p21, and p53 proteins were significantly increased in cells treated with L-carnosine. We next determined whether STAT1/NF-κB pathway is involved in regulation of cell cycle arrest- and cell death-associated gene in HCT116. The L-carnosine treatment significantly inhibited the phosphorylation of STAT1 on Tyr701 and NF-κB p65 on Ser276 and Ser536, and then, we exogenously blocked the NF-κB phosphorylation using Bay 11-7082. Based on our findings, L-carnosine induces cell cycle arrest and apoptosis in human colorectal cancer cells by suppressing of NF-κB/STAT1 signaling.

Mechanical Vibration Influences the Perception of Electrovibration.

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.

Comparison of three rapid influenza diagnostic tests with digital readout systems and one conventional rapid influenza diagnostic test.

BACKGROUND: Rapid influenza diagnostic tests (RIDTs) show variable sensitivities in clinical settings. We aimed to compare three digital RIDTs and one conventional RIDT. METHODS: We assessed 218 nasopharyngeal swabs from patients between neonates and 90 years old in 2016. Three digital RIDTs were BUDDI, Sofia Influenza A+B Fluorescence Immunoassay, Veritor System Flu A+B assay. One conventional test was the SD Bioline Influenza Ag A/B/A(H1N1/2009). All test results were compared with those from the Anyplex Flu A/B Typing Real-time Detection real-time PCR. The four RIDTs were tested with diluted solutions from the National Institute for Biological Standards and Control (NIBSC) to compare lower detection limit. Cross-reactivity of four RIDTs within other respiratory viruses was identified. RESULTS: For influenza A, BUDDI, Sofia, Veritor, and Bioline showed 87.7%, 94.5%, 87.7%, and 72.6% sensitivity, and 100%, 97.7%, 96.5%, and 100% specificity. For influenza B, BUDDI, Sofia, Veritor, and Bioline showed 81.7%, 91.7%, 81.7%, and 78.3% sensitivity, and 100%, 95.3%, 100%, and 100% specificity, respectively. Each RIDT could detect diluted NIBSC solution, according to the level of dilution and specific influenza subtypes. Cross-reactivity of four RIDTs with other respiratory viruses was not noted. CONCLUSIONS: Sofia showed the highest sensitivity for influenza A and B detection. BUDDI and Veritor showed higher detection sensitivity than a conventional RIDT for influenza A detection, but similar results for influenza B detection. Further study is needed to compare the test performance of RIDTs according to specific, prevalent influenza subtypes.

Advanced Age as a Predictor of Survival and Weaning in Venoarterial Extracorporeal Oxygenation: A Retrospective Observational Study.

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.

Analysis of the effect of renal replacement therapy: in the prolonged extracorporeal membrane oxygenation patients.

BACKGROUND: This paper aimed to verify the effects of renal replacement therapy on changing the levels of serum creatinine for different veno-arterial and veno-venous configurations in prolonged extracorporeal membrane oxygenation (ECMO) patients. METHODS: The subjects were chosen 71 patients who had undergone more than 1,440 minutes (24 hours) of the therapy from among 117 patients who had undergone ECMO insertion between January 2008 and December 2012. The patients were separated into the veno-arterial configuration group I (51 patients) and the veno-venous configuration group II (20 patients). The difference in the level of serum creatinine (ΔCr) between before or just after ECMO insertion (CrI) and the level when the pump time was between 2,880 and 4,320 minutes (CrF) was checked (ΔCr=CrF-CrI), and the average ΔCr for each group was compared using a Student t-test at the confidence interval (CI) of 95%. RESULTS: The change in the level of serum creatinine was an increase of 0.341 mg/dL (σ=0.9202) for group I and a decrease of 0.120 mg/dL (σ=1.5292) for group II. The change was significantly high for group I (p=0.011, CI=95%). Meanwhile, within group I, when renal replacement therapy was not done, there was a significant increase in the level of serum creatinine (p=0.009, CI=95%). CONCLUSION: For ECMO insertion patients whose pump time was more than 1,440 minutes, there was a significant change in the level of serum creatinine when renal replacement therapy was not done, for the veno-arterial configuration of group I.

A treatment case of delayed aortic injury: the patient with posterior rib fracture.

A 66-year-old male patient arrived at the emergency room with a crush injury to his chest. Multiple rib fractures, hemothorax on both sides, left scapular fracture, liver laceration, and retroperitoneal hematoma were found upon the radiologic examination. After closed thoracostomy, the patient had been initially admitted to the intensive care unit, but he was transferred to the general ward on the next day. On the 4th post-trauma day, the patient complained of severe pain and there was bloody drainage through the chest tube. This case is an exploration with the consideration of the possibility of major bleeding and the subsequent repair of the descending thoracic aorta. This case is regarded as a case in which the aorta wall was damaged as the sharp margin of the fractured ribs caused continuous irritation.

A treatment case of endoscopic removal of left ventricular thrombus, during coronary artery bypass graft.

Left ventricular thrombus is a common complication related to acute myocardial infarction. Removing this with an incision of the free wall of the left ventricle may cause fatal cardiac dysfunction or arrhythmias. Furthermore, performing incision and suture on the fragile myocardium of an acute myocardial infarction patient may cause serious bleeding complications. If there is a patient with left ventricular thrombus who needs thoracotomy for another reason, the case is attempted with the thought that if effective intraventricular visualization and manipulation can be done, fatalities caused by incision and suture may be reduced. For patients undergoing cardiopulmonary bypass, if intracardiac manipulation is required, an endoscope can be used, and given the potential complications after the incision and suturing of the infarcted tissue, the benefits are deemed sufficient.

Nicotine inhibits the proliferation by upregulation of nitric oxide and increased HDAC1 in mouse neural stem cells.

Cigarette smoking (CS) is considered one of the major risk factors to cause neurodegenerative disorders. Nicotine is the main chemical in CS which is responsible for dysfunction of the brain as a neuroteratogen. Also, nicotine dependency is a real mental illness and disease. Recently, chronic nicotine exposure has been shown to cause oxidative/nitrosative stress leading to a deleterious condition to cellular death in different brain regions. However, little is known about the effects of nicotine on mouse neural stem cells (mNSCs). The aim of this study is to investigate the effects of nicotine on mNSCs and elucidate underlying mechanisms involved in expression of a diversity of genes regulated by nicotine. When mNSCs were isolated from the whole brain of embryonic day 16 mice treated with nicotine at vehicle, 100, 400, and 800 µM for 5 d, nicotine significantly decreased the number and size of neurospheres. In immunocytochemistry, nicotine-exposed mNSCs expressing nestin showed the shortened filaments and condensed nuclei. In RT-PCR, messenger RNA (mRNA) levels of proliferating cell nuclear antigen (PCNA) and sirtuin1 (SIRT1) were significantly decreased, while the production of nitric oxide and mRNA levels of cyclooxygenase2 (COX-2), tumor necrosis factor-alpha TNF-α, and histone deacetylase 1 (HDAC1) were increased in a dose-dependent manner. In addition, sodium butyrate and valproic acid, HDAC inhibitors, partially rescue proliferation of mNSCs via inhibition of HDAC1 expression and NO production. Taken together, these data demonstrate that prolonged exposure of nicotine decreased proliferation of mNSCs by increased NO and inflammatory cytokine through increased HDAC1. Furthermore, this study could help in the development of a therapy for nicotine-induced neurodegenerative disorder and drug abuse.

Nonaneurysmal infectious aortitis.

Infectious aortitis is a rare disease in the antibiotic era. Only a small number of cases of nonaneurysmal infectious aortitis are discussed in literature, and its true incidence and natural history are not well defined. We present here a case of typical nonaneurysmal infectious aortitis with literature review of 19 cases of aortic infection in which the aorta is initially normal in caliber.

Cardiac tamponade complicated by acupuncture: hemopericardium due to shredded coronary artery injury.

We report a case of 62-year-old man with cardiac tamponade due to coronary artery injury after acupuncture into the substernum. After resuscitation of cardiac arrest, we performed emergent pericardiocentesis. Nevertheless, the cardiac arrest recurred, and the emergent operation on cardiopulmonary bypass was performed. We identified hemopericardium due to shredded acute marginal branch of right coronary artery, and it was ligated leading to termination of bleeding. The patient was discharged without any other complications.