A Hierarchical Multitask Learning Approach for the Recognition of Activities of Daily Living Using Data from Wearable Sensors.

Machine learning with deep neural networks (DNNs) is widely used for human activity recognition (HAR) to automatically learn features, identify and analyze activities, and to produce a consequential outcome in numerous applications. However, learning robust features requires an enormous number of labeled data. Therefore, implementing a DNN either requires creating a large dataset or needs to use the pre-trained models on different datasets.

Explainable Artificial Intelligence (XAI) in Pain Research: Understanding the Role of Electrodermal Activity for Automated Pain Recognition.

Artificial intelligence and especially deep learning methods have achieved outstanding results for various applications in the past few years. Pain recognition is one of them, as various models have been proposed to replace the previous gold standard with an automated and objective assessment. While the accuracy of such models could be increased incrementally, the understandability and transparency of these systems have not been the main focus of the research community thus far.

Biosynthesis of dillapiole/apiole in dill (Anethum graveolens): characterization of regioselective phenylpropene O-methyltransferase.

The phenylpropene volatiles dillapiole and apiole impart one of the characteristic aromas of dill (Anethum graveolens) weeds. However, very few studies have been conducted to investigate the chemical composition of volatile compounds from different developmental stages and plant parts of A. graveolens.

A new pairwise deep learning feature for environmental microorganism image analysis.

Environmental microorganism (EM) offers a highly efficient, harmless, and low-cost solution to environmental pollution. They are used in sanitation, monitoring, and decomposition of environmental pollutants. However, this depends on the proper identification of suitable microorganisms.

Sleep stage classification for child patients using DeConvolutional Neural Network.

Studies from the literature show that the prevalence of sleep disorder in children is far higher than that in adults. Although much research effort has been made on sleep stage classification for adults, children have significantly different characteristics of sleep stages. Therefore, there is an urgent need for sleep stage classification targeting children in particular.

Deep Transfer Learning for Time Series Data Based on Sensor Modality Classification.

The scarcity of labelled time-series data can hinder a proper training of deep learning models. This is especially relevant for the growing field of ubiquitous computing, where data coming from wearable devices have to be analysed using pattern recognition techniques to provide meaningful applications. To address this problem, we propose a transfer learning method based on attributing sensor modality labels to a large amount of time-series data collected from various application fields.

Analysis of Pattern Formation by Colored Petri Nets With Quantitative Regulation of Gene Expression Level.

Modeling and simulation are becoming indispensable tools for studying multicellular events such as pattern formation during embryonic development. In this paper, we propose a new approach for analyzing multicellular biological phenomena by combining colored hybrid Petri nets (ColHPNs) with newly devised biological experiments that can control level of a gene quantitatively. With this approach, we analyzed patterning of the boundary cells in the Drosophila large intestine, where one-cell-wide domain of boundary cells differentiate through Delta-Notch signaling.

The role of the functional independence measure score in predicting the home discharge of inpatients with cerebrovascular diseases in convalescent rehabilitation wards.

[Purpose] To clarify the cutoff point of the Functional Independence Measure tool for predicting home discharge of patients in convalescent rehabilitation wards. [Participants and Methods] This retrospective observational study analyzed the data of 91 inpatients with cerebrovascular disease who received rehabilitation treatment at a convalescent rehabilitation ward. We categorized the participants into two groups: the home-discharged group and the non-home discharged group.

Rank Pooling Approach for Wearable Sensor-Based ADLs Recognition.

This paper addresses wearable-based recognition of Activities of Daily Living (ADLs) which are composed of several repetitive and concurrent short movements having temporal dependencies. It is improbable to directly use sensor data to recognize these long-term because two examples (data sequences) of the same ADL result in largely diverse sensory data. However, they may be similar in terms of more semantic and meaningful short-term .

Multiple Diffusion-Freezing Mechanisms in Molecular-Hydrogen Films.

Molecular hydrogen is a fascinating candidate for novel bosonic and fermionic superfluids. We have studied diffusion dynamics of thin films of H_{2}, HD, and D_{2} adsorbed on a glass substrate by measurements of elasticity. The elasticity shows multiple anomalies well below the bulk triple point temperature.

A case of delirium in Tolosa-Hunt syndrome during corticosteroid therapy.

Background: Corticosteroid therapy is useful for the resolution of pain and paresis in Tolosa-Hunt syndrome; however, there is no definitive protocol for appropriate dosing, route of administration, or duration of therapy. Steroid psychosis is an adverse reaction to corticosteroid therapy; in severe cases, it can develop into psychiatric disorders such as delirium, depression, and mania. In this case study, we report a patient with Tolosa-Hunt syndrome who developed delirium while receiving corticosteroid therapy.

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors.

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches-in particular deep-learning based-have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use.

A general framework for sensor-based human activity recognition.

Today's wearable devices like smartphones, smartwatches and intelligent glasses collect a large amount of data from their built-in sensors like accelerometers and gyroscopes. These data can be used to identify a person's current activity and in turn can be utilised for applications in the field of personal fitness assistants or elderly care. However, developing such systems is subject to certain restrictions: (i) since more and more new sensors will be available in the future, activity recognition systems should be able to integrate these new sensors with a small amount of manual effort and (ii) such systems should avoid high acquisition costs for computational power.

Codebook-based electrooculography data analysis towards cognitive activity recognition.

With the advancement in mobile/wearable technology, people started to use a variety of sensing devices to track their daily activities as well as health and fitness conditions in order to improve the quality of life. This work addresses an idea of eye movement analysis, which due to the strong correlation with cognitive tasks can be successfully utilized in activity recognition. Eye movements are recorded using an electrooculographic (EOG) system built into the frames of glasses, which can be worn more unobtrusively and comfortably than other devices.

TAKASAGO-6 apparatus for cryogenic coherent X-ray diffraction imaging of biological non-crystalline particles using X-ray free electron laser at SACLA.

Coherent X-ray diffraction imaging (CXDI) is a technique for structure analyses of non-crystalline particles with dimensions ranging from micrometer to sub-micrometer. We have developed a diffraction apparatus named TAKASAGO-6 for use in single-shot CXDI experiments of frozen-hydrated non-crystalline biological particles at cryogenic temperature with X-ray free electron laser pulses provided at a repetition rate of 30 Hz from the SPring-8 Angstrom Compact free-electron LAser. Specimen particles are flash-cooled after being dispersed on thin membranes supported by specially designed disks.

Internal tandem duplication and tyrosine kinase domain mutations in alter the response to daunorubicin in Ba/F3 cells.

Internal tandem duplication (ITD) and activating point mutations, mainly at aspartic acid 835 in the tyrosine kinase domain (TKD), are frequently identified in the Fms-related tyrosine kinase 3 () receptor gene in acute myeloid leukemia. The ITD in (-ITD) confers resistance to several chemotherapeutic drugs; however, the relative effects of -ITD and -TKD mutations on the efficacy of these drugs have not been reported. In the present study, ITD or TKD mutant forms of in Ba/F3 cells were expressed, as in the absence of interleukin-3 (IL-3) the growth of these cells is completely dependent on oncogenic signals.

KOTOBUKI-1 apparatus for cryogenic coherent X-ray diffraction imaging.

We have developed an experimental apparatus named KOTOBUKI-1 for use in coherent X-ray diffraction imaging experiments of frozen-hydrated non-crystalline particles at cryogenic temperature. For cryogenic specimen stage with small positional fluctuation for a long exposure time of more than several minutes, we here use a cryogenic pot cooled by the evaporation cooling effect for liquid nitrogen. In addition, a loading device is developed to bring specimens stored in liquid nitrogen to the specimen stage in vacuum.

[Disseminated varicella-zoster virus infection complicated with severe abdominal pain and colonic pseudo-obstruction].

A 48-year-old man was admitted to our hospital complaining of acute severe abdominal pain and constipation. He had received bone marrow transplantation for acute myelogenous leukemia 5 months previously and immunosuppressant treatment for chronic graft-versus-host disease. Abdominal X-ray and CT scan films revealed his large intestine widely dilated and filled with air, and colonic pseudo-obstruction was diagnosed.

[Russell body gastritis].

A 63-year-old woman who presented with chest and back pain underwent an upper gastrointestinal endoscopy which revealed elevated legion in the antrum mucosa. Histologic examinations of gastric biopsies were showing monoclonal proliferation plasma cells containing Russell bodies. Differential diagnosis from B-cell lymphoma and plasmacytoma is difficult, because of monoclonality.

Recurrence of embolic stroke during intravenous thrombolysis.

An 81-year-old man with atrial fibrillation presented with embolic stroke in the right middle cerebral artery. During intravenous thrombolysis, he became comatose and developed a recurrent embolism in the top of the basilar artery. Intra-arterial mechanical disruption of the embolus failed to recanalize.

Gigantic maximum of nanoscale noncontact friction.

We report measurements of noncontact friction between surfaces of NbSe2 and SrTiO3 and a sharp Pt-Ir tip that is oscillated laterally by a quartz tuning fork cantilever. At 4.2 K, the friction coefficients on both the metallic and insulating materials show a giant maximum at the tip-surface distance of several nanometers.

Thermodynamic evidence for nanoscale bose-einstein condensation in (4)He confined in nanoporous media.

We report the measurements of the heat capacity of (4)He confined in nanoporous Gelsil glass that has nanopores of 2.5-nm diameter at pressures up to 5.3 MPa.

Microwave-resonance-induced resistivity: evidence of ultrahot surface-state electrons on liquid 3He.

Measurements of the dc resistivity of surface-state electrons on liquid helium exposed to microwave radiation are reported. It is shown that the resonant microwave excitation of surface-state electrons is accompanied by a strong increase in their resistivity, which is opposite to the result expected from the previously used two-level model. We show that even a very small fraction of electrons excited to the first excited state and decaying back due to vapor-atom scattering strongly heat the electron system, causing a population of higher subbands.