Electronics and Communications in Japan最新文献

This study deals with the task of segmentation of SEM images of fine ceramics sintered bodies by using deep neural network (DNN). In particular, we focus on misclassification caused by the blurriness of grain boundaries(boundaries between particles). Therefore, we utilize the frequency distribution of brightness gradient of grain boundaries and give higher weights to pixels with lower gradient values. Experiments confirmed that the model trained with proposed loss function gave the best prediction results.

Text input, which is essential for a variety of applications, is one of the most difficult operations for older people. So, we propose a prototype to automatically detect and input text from a natural image taken from a user's smartphone. For the evaluation of the system, 232 photo data taken by the actual people were prepared. When all data was processed on the server, the average processing time was less than 10 seconds, and the overall recognition rate was over 94%. For user study, 20 healthy older people aged 65 years or older were collected. And, after conducting a simulation with the conventional typing system, the prototype in this proposal was asked to be used. The time required to complete each work was recorded, and the usability was evaluated using System Usability Scale (SUS).

As a result, both the healthy older group and the MCI older group tended to shorten the task execution times and increase their SUS scores by using our application, compared to the conventional method. Also, comparing the SUS score with other Web applications, it is considered that usability is high as a prototype.

There is a growing interest to introduce energy-saving algorithms which balance energy efficiency with residents’ comfortability into a building energy management system (BEMS). However, the following issues hinder penetration of the energy-saving algorithms into markets: difficulties both in embedding the algorithms into the BEMS, and in turning the algorithms suitably to fit varieties of installed equipment in each building. In this paper, A BEMS on micro-service architecture, and software service modules for the BEMS, were proposed. The micro-services architecture improves flexibility to introduce newly developed energy-saving algorithms into the BEMS and software service modules manipulate whole roles (modeling, planning, doing, and action) required for tuning the algorithms on-line to fit the algorithms to each building. Each software service module was implemented and integrated as elements of BEMS on micro-service architecture. The BEMS on micro-service architecture was applied to an actual building for evaluation, and its availability was confirmed through the field test.

In this study, we measured the enzymatic activity of acetylcholinesterase (AChE) using the Light Addressable Amperometric Sensor (LAAS), an electrochemical sensor that can easily measure redox current values of multiple samples. Acetylthiocholine (ATCh) was used as a substrate. ATCh is hydrolyzed by AChE and releases electrons, making it possible to measure current values in accordance with the amount of substrate using LAAS. When KCl solution was used as the supporting electrolyte and an Ag/AgCl reference electrode as the counter electrode, a correlation between substrate concentration and reaction was confirmed in the range of 1 μM–10 mM. Malathion was then used as an inhibitor of AChE. Malathion phosphorylates and inactivates AChE, which prevents substrate hydrolysis and is expected to decrease the current value. Experimental results showed a decrease in sensor response correlated with inhibitor concentration.

A polyclonal antibody against the analog of piperine, which is a typical pungent taste substance, was produced, and its binding ability to piperine was evaluated using a surface plasmon resonance sensor. The antibody was labeled with glucose oxidase (GOx), and the hydrogen ions produced by the enzymatic reaction were measured at a lipid polymer membrane electrode for sourness in a taste sensor. The results showed that piperine could be detected by that polyclonal antibody; the response of the sourness sensor increased in dependence on the GOx-labeled antibody concentration when the GOx of GOx-labeled antibody was reacted with glucose. Thus, it was shown that uncharged pungent compounds can be converted into hydrogen ions. Pungent taste can be measured by the taste sensor using GOx-labeled antibodies, and GOx-labeled antibodies can be used as a pretreatment.

This paper presents a method for forecasting the change direction of nonstationary time series using the improved leading indicator. The leading indicator is a method developed by Ehlers that translates a time series mathematically in the future direction with respect to the time axis and calculates the leading value of the time series. However, this method has the problem that the leading value can be calculated only in the low frequency region with a normalized frequency of 0.06 or more (normalized period of 17 or more) at the maximum. In order to solve this problem, by the gentle slope the amplitude characteristics in the low frequency region of the leading indicator, it is possible to calculate the leading value in the frequency domain with a normalized frequency of 0.25 or more (normalized period of four or more) at the maximum. By applying the preceding value to the instantaneous periodic time series by the improved sine wave indicator developed by Ehlers, it is possible to forecast the change direction of the non-stationary time series in the short term.

Aiming at the control of a powered prosthetic hand, this paper compares methods for the classification of intended hand motions using muscle bulging patterns caused by muscle contraction. Two sheets of Polyvinylidene Difluoride (PVDF) film were used as sensors to detect the muscle bulging on the forearm caused by intended hand motions. A neural network had been successfully trained for the classification of six types of hand motions using the muscle bulging pattern detected by the two PVDF sensors. In this paper, we further studied the motion classification methods of back propagation neural network (BPNN), k-nearest neighbor algorithm (k-NN), and support vector machine (SVM) to compare their classification performance. We found that all three methods had a similar classification rate of about 95% for six types of hand motions. Moreover, a regressive analysis comparison of the time for each classification method to converge to 95% of the total classification rate showed that SVM converged significantly earlier than BPNN and k-NN. The time it takes for SVM to converge the classification rate to 95% is less than 0.1 s, suggesting that real-time motion classification is possible by using SVM. In a similar manner, we found that SVM requires the least training data of the three methods at only nine trials for a type of motion. Furthermore, SVM had the highest classification rate at about 90% in practical experimental conditions. In conclusion, SVM was found to be the most practical of the three methods.

A social issue that leads to the safety and security of people is the network that monitors the safety of people living alone in remote areas. Various research and developments of indoor human activity recognition using IoT sensor nodes have been conducted in recent years. In this research, we focus on turning on and off indoor lighting and propose an activity recognition system at home using an illuminance sensor. An IoT sensor node with a built-in illuminance sensor is attached to the wall near the indoor lighting equipment. The living activities of people in the room are estimated from changes in the illuminance. We assume a significant change in the illuminance of the indoor lighting is observed at least once a day at the sampling interval of the IoT sensor node. In that case, it is possible to estimate the operation of the indoor lighting due to daily activities and to confirm the safety of people living alone in remote areas. The activity recognition system was evaluated for a total of 380 days, excluding the missing period. The estimation of indoor lighting manipulation by daily activities was accurate for 376 days. Precision, Recall, and F-measure score values, which are evaluation indices for activity estimation, were 94.9%, 98.2%, and 96.5%, respectively.

In recent years, resilience-enhanced building buildings have been attracting increasing attention, in which photovoltaic (PV) power generation and storage batteries are installed in office buildings to continue operations even during a grid outage. PV power generation and storage batteries can be introduced to office buildings to continue commercial operations in the case of grid outages. When introducing PV power generation and storage batteries into a building, the total cost, which is the sum of the equipment installation cost and the damage cost in the event of a disaster, is crucial. When installing PV power generation and storage batteries in a building and calculating the total cost of using these facilities in the event of a disaster, it is necessary to consider the uncertainty of power demand and the amount of power generated by PV power generation. Monte Carlo Simulation is a method to consider uncertainty. However, it has a problem that the combination of conditions becomes enormous, and the calculation load is high when the total cost is calculated. Therefore, in this study, we propose convolution as a method to reduce the computational load generated when calculating the probability distribution of the total cost generated by strengthening the resilience of the building.

Peripheral sensitization, decrease in pain threshold in sensory neurons, can cause chronic pain. Little is known about how peripheral sensitization led to chronic pain. Here, we aimed to develop a method for evaluating peripheral sensitization in cultured sensory neurons with electrical recording. Sensory neurons from rat dorsal root ganglion were cultured on high-density microelectrode arrays (HD-MEA), and their activity was evoked by capsaicin stimulation with or without substance P. Fluorescent imaging-based electrode selection effectively selected five times as many capsaicin-sensitive sensory neurons as the existing method. Peripheral sensitization by substance P was detected from 31.9% of selected sensory neurons, and majority of these neurons co-expressed capsaicin and substance P receptors. These results indicate that our method is suitable for evaluating peripheral sensitization by substance P in cultured sensory neurons.