The study of indoor localization has been extensively studied, either in terms of wireless technologies or localization techniques.The accuracy is then challenged when the monitored object is actively moving.Previously, we studied a continuous and low-power fingerprint-based indoor localization system using IEEE 802.15.4 (FILS15.4),which has been integrated into a smart environmental IoT platform.Although fingerprint-based localization offers a great advantage in its simplicity, it relies on real-time signal strength measurements and databases.Thus, it suffers challenges in accuracy when the object is continuously moving.In this study, we focus on developing dynamic positioning, where users continuously move from one room to another.Due to human movements, the fluctuation of the link quality indicator (LQI) can affect the detection accuracy.To avoid false detection, we propose a movement validation method by checking the variance of the LQI and accelerometer to differentiate the cause of fluctuations and increase the detection accuracy.For experiments, we run the test-bed of FILS15.4 on a two-floor layout.Five to six receivers were allocated to detect multiple users.The results show that the system yields 96.2% accuracy using six receivers simultaneously.Thus, it gives sufficient detection accuracy even for dynamic conditions.

Traditionally, portrait drawing has been a basic skill of painting. To help novices practice drawing portraits using digital technologies, we have developed a Portrait Drawing Learning Assistant System (PDLAS). By providing the auxiliary lines of a human face, PDLAS can guide portrait drawing of novices. In this paper, we propose an algorithm to generate the auxiliary lines from a given face photo. It adopts OpenCV and OpenPose with Python, which have been commonly used in computer vision studies including human pose estimations, to extract facial features that are necessary for generating them. To evaluate the proposal, we applied it to 50 face photos of people with different genders, ages, and complexions, and generated the auxiliary lines from them. The results proved the validity of the algorithm.

Parameters often take key roles in determining the accuracy of algorithms, logics, and models for practical applications. Previously, we have proposed a general-purpose parameter optimization algorithm, and studied its applications in various practical problems. This algorithm optimizes the parameter values by repeating small changes of them based on a local search method with hill-climbing capabilities. In this paper, we present three diverse applications of this algorithm to show the versatility and effectiveness. The first application is the fingerprint-based indoor localization system using IEEE802.15.4 devices called FILS15.4 that can detect the location of a user in an indoor environment. It is shown that the number of fingerprints for each detection point, the fingerprint values, and the detection interval are optimized together, and the average detection accuracy exceeds 99%. The second application is the human face contour approximation model that is described by a combination of half circles, line segments, and a quadratic curve. It is shown that the simple functions can well approximate the face contour of various persons by optimizing the center coordinates, radii, and coefficients. The third application is the computational fluid dynamic (CFD) simulation to estimate temperature changes in a room. It is shown that the thermal conductivity is optimized to make the average temperature difference between the estimated and measured 0.22∘C.

Nowadays, portrait drawing has become important in cultivating sentiments of a person. With developments of digital technologies, it becomes possible to use an electronic device such as a tablet or a PC, a digital pen, and a drawing software to create diverse and innovative portraits for portrait drawing. In this context, currently, we are studying a Portrait Drawing Learning Assistant System (PDLAS) to help beginners learn drawing portraits by themselves. PDLAS provides auxiliary lines to help the user draw the face accurately that are generated by the auxiliary line generation algorithm that adopts OpenPose and OpenCV to recognize the facial features and the outlines. In this paper, we conduct a preliminary evaluation using iPad with a drawing software Procreate in order to confirm the validity of our proposal that a novice user can easily and comfortably practice drawing using auxiliary lines in PDLAS. In this evaluation, we asked nine students in Okayama University to draw portraits of the given face photos using the system, and asked them to answer 10 questions as the questionnaire. The SUS score of the answer results show that the system can meet their needs.

Currently, the User-PC computingsystem (UPC) has been studied as a low-cost and high-performance distributed computing platform. It uses idling resources of personal computers (PCs) in a group. The job-worker assignment for minimizing makespan is critical to determine the performance of the UPC system. Some applications need to execute a lot of uniform jobs that use the identical program but with slightly different data, where they take the similar CPU time on a PC. Then, the total CPU time of a worker is almost linear to the number of assigned jobs. In this paper, we propose a static assignment algorithm of uniform jobs to workers in the UPC system, using simultaneous linear equations to find the lower bound on makespan, where every worker requires the same CPU time to complete the assigned jobs. For the evaluations of the proposal, we consider the uniform jobs in three applications. In OpenPose, the CNN-based keypoint estimation program runs with various images of human bodies. In OpenFOAM, the physics simulation program runs with various parameter sets. In code testing, two open-source programs run with various source codes from students for the Android programming learning assistance system (APLAS). Using the proposal, we assigned the jobs to six workers in the testbed UPC system and measured the CPU time. The results show that makespan was reduced by 10% on average, which confirms the effectiveness of the proposal.

Nowadays, human indoor localization services inside buildings or on underground streets are in strong demand for various location-based services. Since conventional GPS cannot be used, indoor localization systems using wireless technologies have been extensively studied. Previously, we studied a fingerprint-based indoor localization system using IEEE802.15.4 devices, called FILS15.4, to allow use of inexpensive, tiny, and long-life transmitters. However, due to the narrow channel band and the low transmission power, the link quality indicator (LQI) used for fingerprints easily fluctuates by human movements and other uncontrollable factors. To improve the localization accuracy, FILS15.4 restricts the detection granularity to one room in the field, and adopts multiple fingerprints for one room, considering fluctuated signals, where their values must be properly adjusted. In this paper, we present a fingerprint optimization method for finding the proper fingerprint parameters in FILS15.4 by extending the existing one. As the training phase using the measurement LQI, it iteratively changes fingerprint values to maximize the newly defined score function for the room detecting accuracy. Moreover, it automatically increases the number of fingerprints for a room if the accuracy is not sufficient. For evaluations, we applied the proposed method to the measured LQI data using the FILS15.4 testbed system in the no. 2 Engineering Building at Okayama University. The validation results show that it improves the average detection accuracy (at higher than 97%) by automatically increasing the number of fingerprints and optimizing the values.

Previously, we have studied the fingerprint-based indoor localization system using IEEE 802.15.4 wireless devices as low-power and compact ones suitable for continuous possessions of the users. For its practical applications, this FILS15.4 limits the detection resolution to one room in the target field. Unfortunately, human movements often cause the fluctuation of the receiving signal strength by affecting wireless propagation dynamics, which decreases the room detection accuracy of FILS15.4. To overcome the problem, in this paper, we investigate the detection accuracy improvement of FILS15.4, when the number of allocated receivers is increased in the field, and the number of fingerprints is increased for each room where the proper values are selected using the parameter optimization method. For the evaluation, we conducted extensive experiments using the FILS15.4 testbed system with three to five receivers at two floors of #2 Engineering Building in Okayama University. The results show that the use of five receivers achieves the accuracy up to 99.71% on average, whereas the use of three or four receivers does 82.64% and 97.37% respectively.

In this paper, we describe a new air-conditioning system that takes human behavior into account. We introduce a method of predicting the indoor comfort level distribution by combining computational fluid dynamics (CFD) and Internet of Things (IoT), and a concept of air-conditioning guidance that encourages human behavior by using this method. In particular, we discuss the method of optimizing parameter for the CFD analysis used in the system, which ensures acceptable computational speed and accuracy in the proposed guidance system, by comparing the results of experiments using a small room model.

The increasing popularity of indoor localization systems brings the need of providing energy and cost-efficient service. Currently, we are developing the fingerprint-based indoor localization system using IEEE 802.15.4 named FILS15.4. It uses a small transmitter powered by a coin battery, limits the detection resolution by one room, allocates several receivers on the field, and assigns multiple fingerprints using the parameter optimization method. It has been evaluated only for one-floor environments. This paper investigates the applicability of FILS15.4 in a two-floors environment of the #2 Engineering Building in Okayama University. The receivers allocated on both floors are used together for localization. The experiment results confirm sufficient detection accuracy.

Previously, we have studied the air-conditioning guidance system (AC-Guide) to optimize the use of AC in the room using the indoor/outdoor discomfort index. Currently, the epidemic of COVID-19 is spreading around the world, and the ventilation of the room becomes critical to avoid the infection, which should be properly guided together. In this paper, we study the ventilation guidance function using the measured CO2 density in AC-Guide. The opening/closing state of the door and window is automatically detected using the web camera, where the image processing procedures are newly implemented. Experiment results in an Okayama University building confirm the effectiveness.

Nowadays, digital transformation (DX) is the key concept to change and improve the operations in governments, companies, and schools. Therefore, any data should be digitized for processing by computers. Unfortunately, a lot of data and information are printed and handled on paper, although they may originally come from digital sources. Data on paper can be digitized using an optical character recognition (OCR) software. However, if the paper contains a table, it becomes difficult because of the separated characters by rows and columns there. It is necessary to solve the research question of "how to convert a printed table on paper into an Excel table while keeping the relationships between the cells?" In this paper, we propose a printed table digitization algorithm using image processing techniques and OCR software for it. First, the target paper is scanned into an image file. Second, each table is divided into a collection of cells where the topology information is obtained. Third, the characters in each cell are digitized by OCR software. Finally, the digitalized data are arranged in an Excel file using the topology information. We implement the algorithm on Python using OpenCV for the image processing library and Tesseract for the OCR software. For evaluations, we applied the proposal to 19 scanned and 17 screenshotted table images. The results show that for any image, the Excel file is generated with the correct structure, and some characters are misrecognized by OCR software. The improvement will be in future works.

In this paper, we propose a new air conditioning system that predicts the indoor comfort distribution by computational fluid dynamics (CFD) and the Internet of Things (IoT), and incorporates human behavior patterns to adjust to the appropriate indoor comfort level. In this air conditioning system, the temperature as well as the airflow distribution in the room needs to be predicted and then a solution is proposed based on the prediction results. In this paper, we present the experimental model we used and the related experiments for the analysis.

Nowadays, indoor localization systems using IEEE 802.11 have been actively explored for location-based services, since GPS cannot identify floors or rooms in buildings. However, the user-side device is usually large and consumes high energy. In this paper, the authors propose a fingerprint-based indoor localization system using IEEE 802.15.4 that allows the use of a small device with a long-life battery, named FILS15.4. A user carries a small transmitter whose signal is received by multiple receivers simultaneously. The received signal strengths are compared with the fingerprints to find the current location. To address signal fluctuations caused by the low-power narrow-band signal, FILS15.4 limits one room as the localization unit, prepares plural fingerprints for each room, and allocates a sufficient number of receivers in the field. For evaluations, extensive experiments were conducted at #2 Engineering Building in Okayama University and confirmed high detection accuracy with sufficient numbers of receivers and fingerprints.

To achieve the high accuracy while wearing an inexpensive, tiny, and long-life transmitter, we have developed a fingerprint-based indoor localization system. It adopts IEEE802.15.4 devices and restricts the detection granularity to one room in an indoor environment. Unfortunately, wireless signals of the devices often fluctuate due to human movements and other uncontrollable factors. It has been observed that it can be solved by assigning plural fingerprints to one room. However, their values need to be properly selected. In this paper, we study the parameter optimization method for this indoor localization system. An existing parameter optimization tool is employed where the score function is newly defined to estimate the optimality of the current parameters. For evaluations, we apply the method to the measured data using the system in #2 Engineering Building of Okayama University. The results show that the detection accuracy becomes higher than 95% for any room by increasing the number of fingerprints and optimizing the parameter values by the proposal.