Recently, data utilisation and digital service offerings are becoming primary methods of value creation. In this context, designing and offering ‘digital service systems’ (DSSs) that integrate physical elements (e.g., products, facilities, and physical infrastructure) and digital service elements (e.g., digital services, data, apps, and cloud systems) are important to create sustainable social values and achieve the United Nations’ Sustainable Development Goals 9 and 11. In this study, we propose a novel method for designing a DSS that simultaneously consider three system domains, namely social, physical, and digital domains. Specifically, we developed design models and a design process to support the DSS design. The proposed method was applied to an actual DSS design case. The results revealed that the proposed method could effectively consider components in the social system domain in addition to those in the digital and physical system domains in the DSS design. In particular, we identified that the proposed design models were useful for enabling the systematic management of a long-term collaborative design process among various stakeholders. They also enabled value-oriented thinking in DSS design and encouraged designers to consider different types of value in the DSS.

Falls in older adults is a major public health issue with approximately one-third of individuals aged 65 or older experiencing at least one fall event annually. Accordingly, there is a need for methods to identify elderly individuals at risk of falls. Methods allowing automated and instantaneous assessment of fall risk would have considerable utility in hospitals and nursing care facilities with staff shortage or time pressure. The present study evaluated models for estimating fall risk from gait characteristics measured during a single gait cycle. As gait images are affected by clothing, skeletal data was recorded using motion capture imaging. Fall risk was determined according to the history of falls within the preceding year. Of 80 healthy subjects aged over 65 years who participated in this study, 45 had experienced falls in the preceding year. Gait features, time series data, and gait energy images were recorded. The area under the receiver operating characteristic curve (AUC) was utilized as a performance measure to evaluate machine learning models. The input of Gait Energy Image data into a 6-layer convolutional neural network (CNN) provided higher accuracy (AUC = 0.67) than other inputs. Visual explanations from the 6-layer CNN created using Eigen-CAM demonstrated that areas associated with step length were predictor for estimating fall risk. Arm swing at heel strike and feet movements were also predictors of fall risk. The models evaluated in this study can be utilized to estimate fall risk from instantaneous measurements, with promising applications in various industries including medical care.

Materials informatics requires large-scale collection and analysis of material synthesis procedures described in the literature for designing materials using computational methods. However, existing studies have not performed the paragraph-level analysis of the procedures. Moreover, since most of the synthesis procedures are described in natural language in articles and technical documents, it is necessary to structure them in a format that can be handled by computers through information extraction. Therefore, in this study, we construct a pipeline system that extracts synthesis procedures from text in the form of a flow graph and analyzes each procedure as a flow graph rather than a set of processes. The extraction system extracts entities by the deep learning model and relations between entities by the rule-based extractor from all paragraphs in the literature and selects procedures that include valid structures of entities and relations. Our evaluation of a benchmark dataset gave micro-averaged F-scores of 0.807, 0.830, and 0.609 for the entity extractor, relation extractor, and pipeline extractor, respectively. We applied this system to a large amount of literature and extracted approximately 90,000 flow graphs (procedures) containing approximately 4 million entities and 3 million relations. We performed several analyses, including taking statistics of the extracted graphs and checking frequent subgraphs for the extracted graphs. Commonly used methods in materials science were confirmed from our analyses; for example, ethanol is often dried by heating at 60 °C, and less-reactive noble gases are rarely included in the products. As a result, we experimentally confirmed that the extracted procedures were reasonable.

In this paper, we propose a 6-DOF haptic interface with force feedback capability for foot-based interaction. To direct a "third arm" to any position that the operator wants to reach while both hands are busy, the controller needs 6-DOF input from a modality that does not rely on the hands. We focus on foot-based operation and propose a device that is composed of a parallel link and omni wheel. We evaluated the operating performance of this device during a robot manipulation task, an obstacle avoidance task, and a Fitts' Law task. The results show the precision of the 6-DOF manipulations to be 1.83 cm. The performance of the obstacle avoidance task is significantly higher with force feedback. The performance measure of the Fitts' Law task, the throughput, differed depending on the plane of operation. In comparison with prior study, the throughput of 1.21 bits/s, the average of all planes, was higher than the prior study. The proposed device could be effective as an interface to control the third arm.

Building a system for extracting information from the scientific literature is an important research topic in the field of inorganic materials science. However, conventional extraction systems have a limitation in that they do not extract characteristic values from nontextual components, such as charts, diagrams, and tables, which provide key information in many scientific documents. Although there have been several studies on identifying the characteristic values of graphs in the literature, there is no general method that classifies graphs according to the property conditions of the values in the field of materials science. Therefore, in this study, we focus on graphs that are figures representing graphically numerical data, such as a bar graph and line graph, as the first step toward developing a framework for extracting material property information from such noncontextual components. We propose deep-learning-based classification models for identifying the types of graph properties, such as temperature and time, by combining graph images, text in graphs, and captions in neural networks. To train and evaluate the models, we construct a material graph dataset with different types of material properties from a large collection of data from journals in the field of materials science. By using cloud sourcing, we annotate 16,668 images. Our experimental results demonstrate that the best model can achieve high performance with a microaveraged F-score of 0.961.

In the field of inorganic materials science, there is a growing demand to extract knowledge such as physical properties and synthesis processes of materials by machine-reading a large number of papers. This is because materials researchers refer to produce promising terms of experiments for material synthesis. However, there are only a few systems that can extract material names and their properties. This study proposes a large-scale natural language processing (NLP) pipeline for extracting material names and properties from materials science literature to enable the search and retrieval of results in materials science. Therefore, we propose a label definition for extracting material names and properties and accordingly build a corpus containing 836 annotated paragraphs extracted from 301 papers for training a named entity recognition (NER) model. Experimental results demonstrate the utility of this NER model; it achieves successful extraction with a micro-F1 score of 78.1 _2 ,” a material used in perovskite solar cells, has been increasing rapidly in China but decreasing in the United States. Further, according to the conditions-by-year analysis, the processing temperature of the catalyst material “PEDOT:PSS” is shifting below 200 ^∘ C, and the number of reports with a processing time exceeding 5 h is increasing slightly.

In the field of virtual reality, there are many researches on haptic force presentation. We suppose these haptic devices can be applied to training. Our goal is to make a training system which can control exercise load during walking and can make the exercise variable according to user’s purpose automatically. In this study, we propose a method to control hip torque as a measure of exercise load during walking by wire tension attached to thigh. The control profile of the wire to exhibit a desired hip torque is generated from database composed of pairs of control profile and hip torque. We proposed two algorithms to generate the control profile. One is based on simple matching using cross-correlation, the other is based on classification using Support Vector Machine. We evaluated the effectiveness of these two algorithms.

The synthesis process is essential for achieving computational experiment design in the field of inorganic materials chemistry. In this work, we present a novel corpus of the synthesis process for all-solid-state batteries and an automated machine reading system for extracting the synthesis processes buried in the scientific literature. We define the representation of the synthesis processes using flow graphs, and create a corpus from the experimental sections of 243 papers. The automated machine-reading system is developed by a deep learning-based sequence tagger and simple heuristic rule-based relation extractor. Our experimental results demonstrate that the sequence tagger with the optimal setting can detect the entities with a macro-averaged F1 score of 0.826, while the rule-based relation extractor can achieve high performance with a macro-averaged F1 score of 0.887.

In this study, we propose a method for estimating lower extremity strength from daily gait movement. Gait movement is affected by sex and gait environment. Therefore, we examined correlation coefficient between lower extremity strength and gait movement based on sex and environment and created models for estimating lower extremity strength. As a result, when only male or female data were used for model constructing, the correlation coefficient between estimates and actual measurements of lower extremity strength were approximately 0.7 and the precision had a mean absolute error of approximately 0.1 N/kg. The accuracy of the estimates was higher than that when sex was considered.

In this study, we proposed a method to determine the assist timing for wire type assist suit. In this method, since the assist timing is determined based on the hip joint angular acceleration by the IMU sensor, the assist can be performed at the optimal timing for each user. As a result of the experiment that in some trials, the maximum hip extension torque were reduced compared to normal walking can be observed. That is the effectiveness of this method can be expected.

The purpose of this study is for a robot to learn picking motions in a logistics warehouse environment. The picking operation performed by a robot often fails owing to the inclination of items placed on a shelf, as well as the minimum clearance between the products and their vinyl packaging. Therefore, we considered acquiring a specific motion trajectory by reinforcement learning. However, because numerous types of items are handled in logistics warehouses, efficient learning is required. Therefore, in this research, we propose a method to efficiently exploration for learning picking an object by determining a focus exploration area for learning based on previous results of different objects.

This paper presents the lifestyle analyses of users via the appliance logs of our IoT coffee roasting service combined with a questionnaire survey on their lifestyles. We found that there is a difference in lifestyle trends between subscribed and non-subscribed users of the service. We also found that users showing a certain lifestyle have specific usage patterns of the roaster. In addition, we confirmed differences between the lifestyles of some users who quit the service and those who did not. Finally, we defined a service continuity index and discussed examples of measures to enhance service continuity by lifestyle analysis.

In recent years, various devices supporting the movements of elderly people and workers have been taken a dramatic leap forward. Traditional powered exoskeleton suit as one of them is a wearable machine that can be challenging to perfectly align with a wearer’s biological joints and can have large inertias. On the other hand, wire type Assist suit is constructed with wire attached in parallel with the muscles, enabling wearers to move the lower limb joints freely. Wire type is less restrictive than powered exoskeleton and it is possible to support walking in correspondence with human's flexible movements. Conventionally, it is widely used as a method of evaluating the assistance effect of the wire type on human that comparison of energy metabolism amount measured by exhalation gas measurement. This evaluation method, however, can evaluate changes in the metabolism of whole exercise, it is not possible to evaluate the degree of assistance the assist suit performs for user’s each lower limb joint. In this study, we evaluated the effect of the assist suit loading assist torque to flexion direction on hip joint by analyzing gait dynamics. We calculated hip joint angle, moment, power duration assist walking as kinetic and kinematic parameters with use of human body model simulation taken account of assist torque generated by the wire. The result showed that max hip flexion angle, step length, total hip joint torque and hip consumption energy decreased.

Cyber-Physical Systems (CPSs) are attracting significant attention from a number of industries, including social infrastructure, manufacturing, retail, among others. We can easily gather big datasets of people and transportation movements by utilizing camera and sensor technologies, and create new industrial applications by optimizing and simulating social mobility in the cyberspace. In this paper, we develop the system which automatically performs a series of processes, including object detection, multiple object tracking, and mobility optimization. The mobility of humans and objects is one of the essential components in the real world. Therefore, our system can be widely applied to various application fields. Our major contributions to this paper are remarkable performance improvement of multiple object tracking and building the new mobility optimization engine. In the former, we improve the multiple object tracker using K-Shortest Paths (KSP), which achieves significant data reduction and acceleration by specifying and deleting unnecessary nodes. Numerical experiments show that our proposed tracker is over three times faster than the original KSP tracker while keeping the accuracy. We formulate the mobility optimization problem as the SATisfiability problem (SAT) and the Integer Programming problem (IP) in the latter. Numerical experiments demonstrate that the total transit time can be reduced from 30 s to 10 s. We discuss the characteristics of solutions obtained by the two formulations. We can finally select the appropriate optimization method according to the constraints of calculation time and accuracy for real applications.

Probabilistic Occupancy Map (POM) is a method to estimate a location of multiple people, given images taken by multiple cameras from different angles set at a head level. It is useful even in the case of significant occlusion and can derive a location of people without an appearance model and prerequisite knowledge about the number of people in a detection space. However, the computation time of POM increases according to the area of detection space and number of cameras, which limits its performance. In this paper, we report performance enhancement of POM by applying OpenMP and GPGPU. As a result of evaluating test videos with different area size and cameras, we confirm that OpenMP implementation marks 1.8 to 2.7 times speedup compared to single CPU core implementation for all videos, whereas GPU implementation provides speedup in case of large grid size by a maximum of 7.6 times.