Wearable accelerometers and gyroscopes capture fine-grained behavioral signatures that can inadvertently reveal user identities, making privacy protection essential for healthcare applications. We present C-AAE, a lightweight compressive anonymizing autoencoder that performs on-device privacy filtering at the sensor edge. The core idea of C-AAE is to integrate two complementary privacy filters: a learned, sensor-specific anonymization module, the Anonymizing AutoEncoder (AAE), and a learning-free, generic anonymization module, Adaptive Differential Pulse-Code Modulation (ADPCM). The AAE locally learns to suppress identity cues while preserving activity-relevant representations, whereas ADPCM provides training-free anonymization through compression, further masking residual identity information and reducing communication cost. Experiments on the MotionSense and PAMAP2 datasets show that C-AAE cuts user re-identification F1 scores by 10–15 percentage points relative to AAE alone, while keeping activity-recognition F1 within 5 percentage points of the unprotected baseline. Implementation on a small-scale edge device (ESP32-WROOM-32) demonstrates real-time performance with markedly lower memory usage, latency, and power consumption. Unlike differential-privacy mechanisms that rely on randomized noise, C-AAE offers a complementary, representation-level approach, enabling practical and resource-efficient on-device anonymization that remains compatible with formal DP frameworks for hybrid deployment on edge healthcare devices.

This paper presents ZEL+, a wearable lifelogging system designed to operate with net-zero energy consumption by leveraging multiple energy harvesting technologies for continuous context sensing. Self-powered wearable devices often encounter difficulties in environments with inconsistent or low-intensity ambient energy, particularly in indoor settings. To address this challenge, ZEL+ incorporates three key design features. First, it employs a power-switching mechanism based on dual comparators and a capacitor to manage surplus energy and support operation under varying lighting conditions. Second, the system integrates heterogeneous energy harvesters not only as power sources but also as sensing elements. Specifically, a dye-sensitized solar cell provides stable responses under low-light indoor environments, while an amorphous solar cell exhibits sensitivity to changes in ambient illumination; together with a piezoelectric element capturing motion-induced signals, these components contribute complementary cues for location and activity recognition. Third, a Spatial Consistency-Based Correction (SCC) algorithm is applied as a post-processing step to mitigate transient recognition errors and improve the coherence of inferred lifelogs. The system is implemented as a 192 g nametag-shaped wearable device and evaluated in a real-world office environment with 11 participants. Under a person-dependent setting, ZEL+ achieved an accuracy of 96.62% for 8-location place recognition and 97.09% for static/dynamic activity recognition, while maintaining robust performance on more fine-grained tasks. In terms of energy sustainability, the device sustained autonomous operation using harvested energy alone for approximately 93.97% of a standard 8-hour office workday. These results indicate that ZEL+ provides a practical and energy-sustainable solution for continuous lifelogging in indoor mobile computing environments.

Decentralized Machine Learning (DML) enhances machine learning by improving scalability, adaptability, and privacy. Federated Learning (FL), a DML approach, boosts privacy by transmitting model gradients from local training to a central server instead of raw data. However, FL encounters challenges like potential privacy risk through gradient inference and communication bottlenecks. Several studies implement Differential Privacy (DP) to tackle these issues by adding random noise to gradients before aggregation. This approach safeguards sensitive information but can decrease model accuracy due to the introduced noise. Adaptive clipping helps by dynamically adjusting clipping bounds based on data, minimizing noise, and preserving data utility. However, in a decentralized system, noise application may be inconsistent across nodes, leading to learning inefficiencies. Our solution involves clustering, enabling local node collaboration and model aggregation to reduce DP noise impact and decentralize aggregation, minimizing bottlenecks caused by the central server. We also use data sharding to balance datasets across nodes, ensuring each processes representative data portions. This improves the signal-to-noise ratio, addresses data imbalance, and enhances accuracy. Experiments with MNIST and Fashion-MNIST datasets demonstrate that our method achieves better accuracy than conventional DP-SGD algorithms.

Since office work has become large-scale and diversified in companies or organizations, work engagement and efficiency have been always an important index of a team's or group's evaluation because it is directly connected to their outcomes. In order to identify the group work context, we first need to recognize for what and how long the individual members are spending their time at their desks, but without privacy concerns and underestimation of their actual work. In this paper, we propose and evaluate the base system of personal desk activity recognition by using a low-cost compact WiFi node and its WiFi channel state information (CSI), which can lead to a lightweight group work context identification system. As a result, we achieved 94.2% desk activity recognition accuracy using the on-desk receiver, in recognizing five different classes.

We present a secure decentralized learning framework suitable for resource-constrained devices within a cluster environment. Our approach focuses on enhancing privacy preservation during model aggregation by utilizing Differential Privacy. This technique adds random noise to gradients obtained from local training on edge devices before sending them for aggregation. This noise addition ensures that sensitive information within the gradients remains distorted, thus safeguarding user privacy. We showcase the implementation of our system on a cluster system employing Raspberry Pi 4 Model B devices, illustrating its feasibility and effectiveness in real-world scenarios. Through this demonstration, we highlight the practical applicability of our system in enabling secure decentralized learning within resource-constrained environments.

Indoor activity recognition using WiFi sensing is expected to have a wide range of applications, such as monitoring the elderly and home security. The state of radio wave propagation is called Channel State Information (CSI) and can be obtained using specific devices. By collecting CSI and applying machine learning, it is possible to recognize activities. However, CSI is sensitive to changes in the environment, so whenever the arrangement of furniture or the layout of the room changes, it is necessary to re-collect sample data and retrain the model. Retraining a model requires annotation work, which is costly in terms of time and effort. To address this issue, this paper proposes an annotation system that uses backscatter tags to reduce the cost of data collection and model training. In this system, a backscatter tag that generates a frequency shift depending on its angle is attached to a person during data collection, and activity recognition is performed by detecting the presence of the frequency shift. The backscatter tag-based recognition results are then used as pseudo-ground truth for model update.

Federated learning (FL) has gained widespread attention as a distributed machine learning (ML) technique that offers data protection when training on local devices. Unlike conventional centralized training in traditional ML, FL incorporates privacy and security measures as it does not share raw data between the client and server, thereby safeguarding potentially sensitive information. However, there are still vulnerabilities in the FL field, and commonly used approaches, such as encryption and blockchain technologies, often result in significant computational and communication costs, making them impractical for devices with restricted resources. To tackle this challenge, we present a privacy-preserving FL system specifically designed for resource-constrained devices, leveraging compressive sensing and differential privacy (DP) techniques. We implemented the weight-pruning-based compressive sensing method with an adaptive compression ratio based on resource availability. In addition, we employ DP to introduce noise to the gradient before sending it to a central server for aggregation, thereby protecting the gradient’s privacy. Evaluation results demonstrate that our proposed method achieves slightly better accuracy when compared to state-of-the-art methods like DP-federated averaging, DP-FedOpt, and adaptive Gaussian clipping-DP (AGC-DP) for the MNIST, Fashion-MNIST, and Human Activity Recognition data sets. Furthermore, our approach achieves this higher accuracy with a lower total communication cost and training time than the current state-of-the-art methods. Moreover, we comprehensively evaluate our method’s resilience against poisoning attacks, revealing its better resistance than existing state-of-the-art approaches.

In this paper, we propose ToonMeet, a hybrid frame-work for high-resolution and style-controllable online meeting toonification that ensures real-time operation speed. ToonMeet applies video frame interpolation to traditional portrait toonification pipelines, allowing for the synthesis of intermediate frames between adjacent toonified keyframes, significantly accelerating the overall process and saving computational resources. However, this approach brings a new problem, where prevailing flow-based video frame interpolation methods tend to cause more ghost and blur artifacts in toonified scenes compared to non-toonified scenes, especially when fast-moving objects exist. We study this previously undiscussed problem and explore its causes. To address this, we introduce a new dataset called TM3B (Toonified Multi-modal Meeting Behaviors), offering high-resolution and cross-platform multi-modal stylized meeting data of Japanese youth in various scenarios. Then, we fine-tune ToonMeet on these tailored data and the resulting model presents improved optical flow estimation ability on toonified videos. Extensive experiments demonstrate that ToonMeet can achieve great spatiotemporal performance and perform high-quality toonification of online meetings with real-time operation speed.

Federated learning has gained popularity as a distributed machine learning approach that provides security and privacy for data trained on local devices. However, vulnerabilities still exist in this approach, and common solutions such as encryption and blockchain techniques often suffer from high computation and communication costs, making them impractical for resource-constrained devices. To solve this problem, we propose a privacy-preserving federated learning system that leverages compressive sensing and differential privacy, specifically designed for devices with limited computational resources. In this paper, we demonstrate the capabilities of our proposed system in resource-limited environments. We outline the features, infrastructure, and algorithm of our proposed system, and simulate its performance using image datasets on a Raspberry Pi 4 and an Android smartphone in a cloud environment. Our approach offers a practical solution for secure and privacy-preserving federated learning in resource-constrained scenarios, with potential applications in various domains such as healthcare, IoT, and edge computing.

Federated learning provides techniques for training algorithms using mobile or decentralized devices, in contrast to traditional machine learning in which algorithm training is performed on centralized devices. In addition, federated learning provides privacy and security features, as the client and server do not share raw data, which may contain confidential information. A number of studies have shown, however, that using federated learning alone is not enough to protect data privacy in certain situations. To overcome this problem, differential privacy is proposed, which is a technique in which artificial noise is added to the raw data. By implementing this method, a high level of privacy protection can be obtained, however this added noise also reduces model accuracy. To address this issue, this paper proposes a new approach to implement differential privacy in federated learning using adaptive Gaussian clipping. We implemented the method by tightening the privacy budget, and introducing dynamic sampling probability, adaptive clipping based on hyperparameters, and a new privacy loss calculation. Our method’s main objective is to adaptively change the amount of noise given to the model, thereby maximizing the model’s accuracy performance, while maintaining privacy protection levels. Evaluation results show that our proposed method presents slightly better accuracy when compared to other existing differential privacy variants such as RDP, DP-SGD, and ZcDP, for both balanced (i.i.d.) and unbalanced datasets (non-i.i.d.), for a lower total communication cost than some variants.

Recently, the studies of wireless device-free human sensing technology have dramatically advanced with enabling a variety of applications, from activity recognition to vital sign monitoring. In this paper, we propose Wi-Nod which leverages the Wi-Fi Channel State Information (CSI) to detect head nodding gestures for each Morse code symbol based on time-frequency features for accurate recognition accuracy in multi-human context environment. The system consists of three basic modules: data collection, data preprocessing, and learning part based on the inception model. The model was trained to perform the head movement detection based on the CSI spectrogram collected by the ESP32 nodes. We evaluated the performance of the system on four different data sets collected in two different sessions. Our system achieves over 95% recognition accuracy that reveals the feasibility of Wi-Nod system for real-life deployment.

In the COVID-19 epidemic, balancing a trade-off between preventing the spread of infection and maintaining economic activity is a global challenge. Based on the idea that avoiding crowds leads to the prevention of the spread of infection, we propose to leverage a dynamic pricing method to level out congestion with an aim to balance the trade-off between preventing the spread of infection and economic activity. In our method, reward points are provided according to the degree of congestion in stores to encourage customers to visit stores at less crowded times to avoid crowds. Since store congestion is greatly affected by movement restrictions such as a state of emergency, we propose a demand prediction model that takes into account the biases of the data acquisition circumstances. In an offline evaluation, we validated the effectiveness of the proposed unbiased demand prediction model based on the data from an actual campaign conducted for more than 7 months in Kyushu University. The evaluation results showed that our unbiased model reduced the prediction error by up to relatively 25.0% compared with the model that does not consider biases. Our system has been deployed in our closed service since December, 2021. Online evaluation result showed that our application improved conversion rate by 12.0% and reduced cost per acquisition by up to 11.6%.

We present ZEL, the first net-zero-energy lifelogging system that allows office workers to collect semi-permanent records of when, where, and what activities they perform on company premises. ZEL achieves high accuracy lifelogging by using heterogeneous energy harvesters with different characteristics. The system is based on a 192-gram nametag-shaped wearable device worn by each employee that is equipped with two comparators to enable seamless switching between system states, thereby minimizing the battery usage and enabling net-zero-energy, semi-permanent data collection. To demonstrate the effectiveness of our system, we conducted data collection experiments with 11 participants in a practical environment and found that the person-dependent (PD) model achieves an 8-place recognition accuracy level of 87.2% (weighted F-measure) and a static/dynamic activities recognition accuracy level of 93.1% (weighted F-measure). Additional testing confirmed the practical long-term operability of the system and showed it could achieve a zero-energy operation rate of 99.6% i.e., net-zero-energy operation.

Due to the spread of COVID-19, we are desired to avoid crowded places including public transportation. Kyushu University has the largest campus in Japan, called "Ito campus", and the population there is about 20,000 in which 23% of students and 46% of staff use a bus for reaching the campus. The lectures in the first half of 2020 have been conducted online, but we plan to resume face-to-face lectures gradually. At that time, we expect the bus stops and buses to be crowded, especially during rush hour. In this paper, we introduce a system, called Itocon, to visualize the human congestion of bus stops around the campus.

Our objective is to achieve a city where everyone can move safely and comfortably by developing and implementing ICT-based mobile support system at the actual transport hub. Our system uses cameras installed at the transport hub to detect people who have difficulty moving, and notifies this information to the transportation staff in real time to help them move more smoothly. This system makes it possible to aggregate and provide information on places that is useful for COVID-19 measures, such as measuring the congestion of places and the social distances of the people who gather there.

As society becomes increasingly interconnected, the need for sophisticated signal processing and data analysis techniques becomes increasingly apparent, particularly in the field of Intelligent Transportation Systems (ITS) where various sensing applications generate data at an exponential rate. In this paper, we put a forward a compressive sensing-based system to extract information from passing vehicle sounds sampled at sub-Nyquist rates for Acoustic Vehicle Detection and Identification (AVDI) applications. The obtained compressive measurements are used to detect and identify passing vehicles. Initial evaluation performed using data obtained from roads on a university campus presents an accuracy of 86.2 % with a back-end ADC sample rate of 3 kHz.

By the spread of active learning and group work, the ability to collaborate and discuss among the participants becomes more important than before. Although several studies have reported on that micro facial expressions and body movements give psychological effects to others during conversation, most of them are lacking in quantitative evaluation and there are few datasets about group discussion. In this research, we proposed a highly reproducible system that helps to make datasets of group discussions with multiple devices such as an omnidirectional camera (360-degree camera), an eye tracker and a motion sensor. Our system operates those devices in one-stop to realizing synchronized recording. To confirm the feasibility, we built the proposed system with an omnidirectional camera, 4 eye trackers, and 4 motion sensors. Finally, we succeeded to make a dataset by recording 8 times group meeting by using our developed system easily.

A wearable based long-term lifelogging system is desirable for the purpose of reviewing and improving users lifestyle habits. Energy harvesting (EH) is a promising means for realizing sustainable lifelogging. However, present EH technologies suffer from instability of the generated electricity caused by changes of environment, e.g., the output of a solar cell varies based on its material, light intensity, and light wavelength. In this paper, we leverage this instability of EH technologies for other purposes, in addition to its use as an energy source. Specifically, we propose to determine the variation of generated electricity as a sensor for recognizing "places" where the user visits, which is important information in the lifelogging system. First, we investigate the amount of generated electricity of selected energy harvesting elements in various environments. Second, we design a system called EHAAS (Energy Harvesters As A Sensor) where energy harvesting elements are used as a sensor. With EHAAS, we propose a place recognition method based on machine-learning and implement a prototype wearable system. Our prototype evaluation confirms that EHAAS achieves a place recognition accuracy of 88.5% F-value for nine different indoor and outdoor places. This result is better than the results of existing sensors (3-axis accelerometer and brightness). We also clarify that only two types of solar cells are required for recognizing a place with 86.2% accuracy.

Abstract In recent years, many types of research and developments on behavior change have been conducted. The purpose of behavior change is to improve people's lifestyle pattern or to maintain the improvement for a long time with the aim to achieve a goal such as promoting health condition improvement. To achieve the foundation of a new lifestyle, it is necessary to recognize the daily life patterns of users and give triggers for behavior change to users in their daily life. To realize this, in our research, we develop an interactive signage which is able to identify and actively talk to the passing user and try to induce behavior change by sending visual and auditory stimulation. Then, we record users' reactions and upload them to the server. In this paper, we report the investigation result on users' reactions and feelings to the developed interactive signage. As a survey experiment, we set up four interactive signs on a floor of our university and asked 15 participants to carry a name tag with a Bluetooth Low Energy beacon during their daily life. Five kinds of tasks based on dialogue scenarios are posted to the approaching participants. Participants can respond to these tasks through a touchscreen. The period of the experiment was three weeks. To get the data in an ideal environment, during the first week, we asked all the participants to respond to the utterance from the interactive signage whenever they hear the voice message. During the next two weeks, participants were not asked to respond to the task definitely to get the data in the real environment. The result of the experiment showed that our proposed interactive signage could induce behavior change effectively. Based on the result of experiment, we updated our interactive signage system by adding response time (the time passed from showing contents until user respond), record function, and voice feedback function. Furthermore, to collect the data of response time that is considered as a part of users' reactions, we conducted an additional experiment with the same participants in previous experiment (except for one missing participant) for one week after updating the system. In the additional experiment, the participants were not asked to respond to the utterance definitely. As a result, it is shown that the behavior change by the proposed signage is still effectively induced. We also analyzed the relationship between the day passed and the response rate of each task type. The result shows that the number of ignorance of personal task and check task does not rise even as the time passes.

In an era where billions of IoT devices are deployed, edge/fog computing paradigms are attracting attention for their ability to reduce processing delays and mitigate waste of communication resources. However, since the computing system assumed by edge/fog paradigms have heterogeneity (in terms of the computing power of devices, network performance between devices, device density, etc.), provisioning computational resources according to computational demand becomes a challenging constrained optimization problem. In this paper, we propose in-situ resource provisioning method consisting of insitu resource area selection with adaptive scale out and in-situ task scheduling based on tabu search algorithm. We conducted a simulation study in a target regional area where 2,000 IoT devices and 10 IoT services are deployed to evaluate the effectiveness of the proposed algorithm. The simulation results show that our proposed algorithm can obtain higher user QoS compared to conventional resource provisioning algorithms.

Following the increase in demand for "smart tourism," various tourist information becomes available. Current tourist guidance systems can provide many possible routes around the city, which are usually based on an optimal distance and time or popularity of the place. To design more enjoyable tourist routes, we should be aware of tourist's perception of the urban environment. In this paper, we propose the methodology of estimating the tourist emotions and satisfaction level by analysing physiological features, such as head movement and eye gaze. Features derived from raw sensor data have the correlation up to 0.58 with emotion and satisfaction labels. This study also shows the differences in feature/label dependencies between different touristic areas and highlights the challenges of tourist satisfaction estimation.

These days, smart home applications such as a concierge service for residents, home appliance control and so on are attracting attention. In order to realize these applications, we strongly believe that we need a system which recognizes the various human activities accurately with a low cost device. There are many studies which work on the activity recognition in the smarthome. Moreover, we also have proposed the activity recognition technique in the smarthome by utilizing the digitaloutput-PIR sensor, door sensor, watt meter. However, the study has the challenge: we cannot distinguish between the similar tiny activities at the same place: “eating” and “reading” with sitting on a sofa. In order to cope with this challenge, we introduce ALPAS: analog-output-PIR-sensor-based activity recognition technique which recognizes the detailed activities of the user. Our technique recognizes the activity of the user by utilizing the machine learning. We evaluated the proposed technique in a smarthome which belongs to the authors' university. In the evaluation, three subjects performed four different activities with sitting on a sofa. As a result, we achieved F-Measure: 57.0%.

Recently, as elderly people population grows, the burdens on caretakers are getting larger. In daycare centers, caretakers make a daycare report aiming to improve the senior citizen's Quality of Life. However, in the present situation, it is difficult for caretakers to record the senior citizen's activity in detail, since each caretaker needs to take care of several senior citizens at the same time. To reduce the burden of caretakers, many elderly monitoring systems have been proposed so far, but most of them are not effective in the sense that they force the senior citizen to use dedicated devices such as smart phone and/or particular applications that are obtrusive and cumbersome for care receivers. In this paper, we propose a semi-automatic care-taking report generation system which can monitor movements/activity of senior citizens in daycare centers. Our proposed system estimates multiple locations (areas) where senior citizens are located with the BLE beacon, by utilizing RSSI of the Bluetooth radio wave. Also, the accelerometer implemented in the tag estimates the activity of the elderly. The information of the estimated area and activity is stored in a server with time stamp. The server generates the daycare report based on it. In order to evaluate the proposed system, we have deployed our system in a daycare center: Ikoi-no-ie 26. Evaluation result in Ikoi-no-ie 26 showed that our system estimated the subject's present area with F-measure: 80.6% and activity with F-measure: 73.8% and generated the daycare report.

This paper shows the concept and design of an ongoing project about "behavior change", that is one of the keywords for realizing a sustainable society based on information technology such as IoT and AI. "Stand" function that Apple Watch has is a touchstone of the arrival of a new age. The watch commands a human to stand up or meditate. It is a start of intervention to our behavior from AI. However, it is not so bad because we know that this suggestion must be good for our health. Based on this experience, we started an empirical research on behavior change that consists of activity recognition, just-in-time intervention, and gamification.

These days, the proposition that various applications in local indoor navigation have attracted significant attention recently is the provocative one. In order to improve and optimize the indoor navigation applications, we have to obtain the accurate floor plan of target place such as building and home environments. However, the belief that all the buildings provide us with accurate floor plan for indoor navigation is groundless. In this paper, we present a floor plan generator tool utilizing a smartphone integrated with an ultrasonic sensor gadget. In the measurement, the user completes a lap along the walls of all rooms. Then, the system estimates the accurate shape and size of the rooms. It leverages the inertial sensors, implemented in the smartphone, to track the user in the walking path. Moreover, the ultrasonic sensor in the gadget measures the distance between the path and walls. There are two main challenges to achieve optimized performance. The first challenge is that adjacent objects to, such as bookshelves, affect the accuracy in spatial layout estimation. To cope with this problem, we use a mixed Gaussian filter. The second challenge is that the narrow room, such as corridors, leads to the low accuracy. To alleviate this challenge, we implement two ultrasonic sensors in the reverse direction, and measure the distance between walls directly. The results from experimentations report improvement in shape and size estimation accuracy.

EdgeComputing and Fog Computing are new paradigms where data processing is executed in or on the edge of networks to mitigate cloud server load. However, EdgeComputing and Fog Computing still need powerful servers on the edge of networks which impose additional costs for deployments. We proposed a platform called IFoT (Information Flow of Things) that efficiently performs distributed processing as well as distribution and analysis of data streams near their sources based on "Process On Our Own (PO3)" concept. In IFoT, processing of tasks for cloud servers is delegated to an ad-hoc distributed system consisting of proximity IoT devices for distributed real-time stream processing. In this demonstration, we show a face recognition system for person tracking developed on top of IFoT middleware which locally processes video streams in real-time and in a distributed manner by using computational resources of IoT devices.

Family Tracing and Reunification (FTR) is the process whereby families separated by disasters are reunited. Current FTR systems use either inefficient paper-based forms and notice boards or digital registries that need the Internet, which may be unavailable during disasters. In this demonstration we present Milk Carton: a system that aids in FTR. Milk Carton creates a registry containing evacuee records. To find separated persons, Milk Carton uses Eigenfaces face recognition to match queries with existing records. Milk Carton uses a clustered architecture of Computing Nodes to handle data storage and execute the Eigenfaces algorithm. To operate under challenged-network environments, Milk Carton uses response patrol vehicles as data ferries to deliver data. In this demonstration, we show how Milk Carton uses Eigenfaces to locate separated persons and how data ferries and Computing Nodes function.

These days, smart home applications such as a concierge service for residents, home appliance control and so on are attracting attention. In order to realize these applications, we strongly believe that we need an indoor positioning system which fulfills the following requirements: Req 1: high accuracy; Req 2: low installation cost; Req 3: small burden on the user; Req 4: low privacy invasion. There are several studies which work on the indoor positioning system. However, these previous works do not accomplish the requirements. In this paper, we present a piezo sensor-based indoor positioning system which estimates the position of the user by utilizing a piezo component attached on the floor. To realize the proposed positioning system, we have tackled two challenges. First challenge is the development of an indoor positioning technique. We cannot utilize TDoA technique that is used to estimate the distance from the target, since the calculation of vibration velocity is difficult. To cope with this challenge, we have developed a new technique which estimates the position of the user from floor vibrations caused by their actions. Second challenge is the selection of the feature vector to estimate the vibration type accurately. We have selected MFCC, FFT, and Envelope shape features from preliminary experiments. We have implemented the proposed system in our smart home testbed. We have evaluated the performance of the vibration type estimation technique. As a result, we have confirmed that our technique estimates the type with F-measure: 93.9%.

In this paper, we propose an indoor localization method using a distance-illuminance model of lighting devices and trilateration. We propose a method that estimates distance from three controllable lighting devices based on the illuminance at the target point, by alternately turning on each of the devices. Then, the proposed method estimates the position of the target point based on trilateration. The proposed method are two merits. First, it can be realized at low cost because only three lighting devices and an illuminance sensor are required. Second, it is robust against influences by external lighting devices (or sunlight) since the proposed method measures the difference of the illuminance before and after turning on a lighting device. We conducted experiments in a room in an ordinary home environment and confirmed that the proposed method could estimate the position of the illuminance sensor within 0.5m error on average.

Recently, as elderly people population grows, the burdens on caretakers are getting larger. In daycare center, caretakers make a daycare report aiming to improve the senior citizen's Quality of Life. However, in the aged society, it is difficult for caretakers to record the senior citizen's activity in detail, since each caretaker needs to take care of several senior citizens at the same time. In this paper, we propose a semi-automatic day-care report generation system. Our proposed system estimates the present area and activity of the senior citizen by utilizing the accelerometer-implemented-BLE-beacon tags and generate the daycare report. Based on the generated report, the caretaker works effectively. Evaluation result in a daycare center showed that our system estimated the subject's present area with F-measure: 80.6% and activity with F-measure: 73.8% and automatically generated the daycare report.

In this paper, we aim to develop a method to create personalized and high-presence multi-channel contents for a sport game through realtime content curation from various media streams captured/created by spectators. We use the live TV broadcast as a ground truth data and construct a machine learning-based model to automatically conduct curation from multiple videos which spectators captured from different angles and zoom levels. The live TV broadcast of a baseball game has some curation rules which select a specific angle camera for some specific scenes (e.g., a pitcher throwing a ball). As inputs for constructing a model, we use meta data such as image feature data (e.g., a pitcher is on the screen) in each fixed interval of baseball videos and game progress data (e.g., the inning number and the batting order). Output is the camera ID (among multiple cameras of spectators) at each point of time. For evaluation, we targeted Spring-Selection high-school baseball games. As training data, we used image features, game progress data, and the camera position at each point of time in the TV broadcast. We used videos of a baseball game captured from 7 different points in Hanshin Koshien Stadium with handy video cameras and generated sample data set by dividing the videos to fixed interval segments. We divided the sample data set into the training data set and the test data set and evaluated our method through two validation methods: (1) 10-fold crossvalidation method and (2) hold-out methods (e.g., learning first and second innings and testing third inning). As a result, our method predicted the camera switching timings with accuracy (F-measure) of 72.53% on weighted average for the base camera work and 92.1% for the fixed camera work.

A critical problem with location fingerprinting is the considerable time and effort spent measuring received signal strengths at all location candidates to create the survey database. To reduce this cost, existing methods use a signal path loss model to interpolate part of the survey database from data actually measured at location candidates. However, the positioning accuracy can become degraded, especially in an indoor area delimited by walls. In this paper, we confirm the degradation in accuracy of the existing method through a preliminary experiment, and propose an accurate interpolation method for survey databases. In the proposed method, part of the survey data is interpolated using a path loss model containing wall attenuation. Furthermore, to confirm the effectiveness of the proposed method, we evaluate the location estimation performance with the interpolated survey database and also verify the interpolated data. The proposed method improves the positioning accuracy by 25% over that of the existing method.

We have developed an adhoc wireless positioning network (AWPN) scheme for information-oriented construction that can temporarily and easily provide a positioning area in both indoor and outdoor environments. The particular requirements of AWPNs are easy deployment and easy configuration because the network should be removed on completion of construction and must frequently accompany the active construction section as it shifts from area to area. In this paper, we propose a localization scheme based on the multilateration method to fulfill the requirements of such AWPNs. The proposed scheme locally and dynamically calibrates the attenuation coefficient defined in the path loss model for radio wave propagation in order to reflect local, fresh propagation characteristics. The results of evaluations conducted on the efficacy of our proposed scheme indicate that it reduces the average error by 30% relative to the conventional approach.

This paper proposes a mechanism to share and utilize various sensors among multiple Android terminals for a functional enhancement and a battery life extension. The most important contribution is how to emulate the value from remote sensor as a value from a local sensor. By this emulation, all the other applications existed on Google Play Market can utilize remote sensors without any modification.

In this paper, we propose a dynamic channel assignment method that utilizes location information of mobile terminals to calculate the optimal channel scheme in indoor WLAN positioning systems. Our method could achieve two goals: (a) the optimal channel scheme can guarantee a maximum throughput of overall wireless network. (b) terminals can communicate and be located simultaneously in our system. By taking advantage of positioning system, we can know the location of terminals, and such location information can be used to optimize network capacity through assigning appropriate channels. Assigning different channel to neighbouring APs is not only for optimizing network capacity, but also for improving the positioning accuracy due to that it can immigrate the interference among APs and receive accurate signal strength. To confirm its effectiveness, we evaluate our approach by simulation. We compare our method with the single, random, and static methods and the LCCS method. The results illustrate that the throughput of our channel assignment method is higher than other methods.

This paper proposes a fast fault recovery method for the wide area Ethernet. To achieve fast recovery, a pre-established forwarding table is introduced. The pre-established table is looked up when a fault occurs, and frames are forwarded without frame loss. Ethernet lacks of fault recovery features required in Wide Area Network (WAN) since it is originated as Local Area Network (LAN) technology. Protection or restoration is a typical method for fault recovery, but a lot of frame losses are inevitable. Our proposal can decrease frame losses since frames are forwarded without waiting for path switching to be completed to use the pre-preparation table. In addition, the proposed method can be operated with the legacy forwarding method seamlessly. The simulation results show that frame loss decreases to 40% or less with our proposed method.

A sensor network covering a large area enables connection to various types of sensors and actuators, but application development becomes complicated because of the uncontrollable behavior of such a large number of devices. We propose the u Tuple Space model for uniform and indirect communication with two extensions to the original tuple space model. The extensions enable efficient range search for multi-dimensional keys and bi-directional communications. Our implementation of our proposed model also integrates load balancing by using a distributed hash table, and the experimental results indicate good scalability in multiple servers. The trial application of gathering and plotting GPS sensor data works well in the field.

This paper proposes a parallel shortest path-searching algorithm and implements it on a newly structured parallel reconfigurable processor, DAPDNA-2 (IPFlex Inc). Routing determines the shortest paths from the source to the ultimate destination through intermediate nodes. In open shortest path first (OSPF), Dijkstra's shortest path algorithm, which is the conventional one, finds the shortest paths from the source on a program counter-based processor. The calculation time for Dijkstra's algorithm is O(N2) when the number of nodes is N. When the network scale is large, calculation time required by Dijkstra's algorithm increases rapidly. It's very difficult to compute Dijkstra's algorithm in parallel because of the need for previous calculation results, so Dijkstra's algorithm is unsuitable for parallel processors. Our proposed scheme finds the shortest paths using a simultaneous multi-path search method. In contrast with Dijkstra's algorithm, several nodes can be determined at one time. Moreover, we partition the network into different groups (network groups) and find the all-node pair's shortest path in each group using a pipeline operation. Networks can be abstracted, and the shortest paths in very large networks can be found easily. The proposed scheme can decrease calculation time from O(N2) to O(N) using a pipeline operation on DAPDNA-2. Our simulations show that the proposed algorithm uses 99.6% less calculation time than Dijkstra's algorithm. The proposed algorithm can be applied to the very large Internet network designs of the future.

A deadline-aware scheduling scheme for the lambda grid system is proposed to support a huge computer grid system based on an advanced photonic network technology. The assignment of wavelengths to jobs in order to efficiently carry various services is critical in lambda grid networks. Such services have different requirements such as the job completion deadlines and wavelength assignment must consider the job deadlines. The conventional job scheduling approach assigns a lot of time-slots to a call within a short period in order to finish the job as quickly as possible. This raises the blocking probability of short deadline calls. Our proposal assigns wavelengths in lambda grid networks so as to meet QoS (quality of service) guarantees. The proposed scheme assigns time-slots to a call over time according to its deadline, which allows it to increase the system performance in handling short deadline calls, for example, lowering their blocking probability. Computer simulations show that the proposed scheme can reduce the blocking probability by a factor of 100 compared with the conventional scheme under the low load condition in which the ratio of long deadline calls is high. The proposed scheduling scheme can realize more efficient lambda grid networks.

In this paper, we propose a new wavelength assignment scheme that improves the blocking probability of WDM networks that use limited-range wavelength converters. Limited-range wavelength converters are attractive for wavelength-routed networks given current technology since they offer good utilization of the wavelength resource and improved blocking probability. However, their conversion ranges are limited, the maximum difference between the input and output wavelengths is restricted. Thus, we must take into account the existence of these limited-range wavelength converters. In our proposed scheme, each connection request is assigned a different wavelength according to its hop number. We tend to use different wavelengths for connection requests with different hop numbers. As a result, we can reduce the blocking probability by two decades compared to simply assigning the shortest available wavelengths. In addition, it allows the number of wavelength converters used in each node to be reduced with almost no degradation in blocking probability. Simulation results show that the proposed scheme can reduce the wavelength converters by about 20%.