International audience

Yoga pose classification is critical for intelligent environments, health, and fitness applications. This study investigates resource-efficient implementations of classification models using contrastive learning frameworks, including SimCLR, MoCo, and BYOL. We evaluate their performance across varying levels of labeled data, focusing on accuracy, computational efficiency, and robustness. MoCo offers a balanced tradeoff with 87.59% accuracy at 50% labeled data, while BYOL achieves strong results with faster inference. SimCLR, suitable for real-time applications due to faster training, consumes more memory and has slower inference. We apply data augmentation and normalization in the preprocessing pipeline to enhance generalization and address challenges like limited data and class imbalance. These techniques improve the model’s resilience and learning efficiency. Our findings guide scalable, energy-efficient, user-centered yoga pose classification models for intelligent environments.

Radio frequency fingerprinting (RFF) is a technique that identifies wireless devices by exploiting unique hardware-induced imperfections measured in their transmitted RF signals. We propose a lightweight RFF method by leveraging temporal variations in RF signals. By combining multi-scale feature extraction through coarse and fine segmentation with DTW-based similarity features, our approach achieves an accuracy of 0.9882 and a Macro-F1 score of 0.988 in our experiment using the Wi-Fi RF data collected from 120 devices.

Video cameras are prevalent in large cities but their use outside of public safety remains limited due to legitimate privacy concerns. Nevertheless, the rich information they can capture appears incredibly promising for large-scale smart city applications, as they can function as very powerful and versatile sensors. This ambivalence raises the question of whether such image data can be used in a privacy-responsible manner. Encryption-based solutions assume the end server can be trusted with keeping data safe; data leaks show us this assumption does not necessarily hold true. Traditional image obfuscation methods such as pixelization or blurring on the other hand fail to offer both sufficient privacy and utility. As such, privacy approaches that can provide privacy protection directly on the data itself while retaining practical utility are required. We here extend two such notions, differential privacy and \( k \) -anonymity, to image data, and extensively evaluate the resulting privacy-utility tradeoff on cross-camera person re-identification and attribute recognition data. Our results show that our proposed approaches can significantly reduce the privacy-sensitivity of image data at source while retaining decent utility for vision-based smart city applications.

In risk management and investment strategy formulation within financial markets, successfully predicting the Volatility Index (VIX) is crucial. While prediction methods leveraging social media texts have been considered promising, they predominantly rely on Twitter data, leaving the potential of online forums underexplored. However, online forums are rich sources of investor discussions and can provide valuable information for VIX prediction. In this study, we propose a deep learning architecture called ForumPFN that effectively captures the complex discussion structures and contextual dependencies unique to online forums, thereby enhancing financial market predictions. At its core, the Discussion Aggregator Module comprises two main components: a Topic Align Algorithm that classifies and reorganizes posts by topic, and a Multi-Scale 1D-Convolutional Path that integrates features at different scales. This design allows for precise modeling of the discussion flows and dynamics specific to Online Forum, maximizing the utilization of information obtained from online forums. We conduct experiments on directional prediction of the Nikkei 225 Volatility Index (Nikkei 225VI)—a representative VIX of Japanese stocks—using data from Yahoo Finance Message Boards, Japan’s largest online forum. The experimental results confirm that ForumPFN outperforms traditional baseline methods. Furthermore, through ablation studies, we demonstrate the effectiveness of each module in detail and explain the module’s operation via visualization of the attention matrix.

Engaging in discussions that involve diverse perspectives and exchanging arguments on a controversial issue is a natural way for humans to form opinions. In this process, the way arguments are presented plays a crucial role in determining how engaged users are, whether the interaction takes place solely among humans or within human-agent teams. This is of great importance as user engagement plays a crucial role in determining the success or failure of cooperative argumentative discussions. One main goal is to maintain the user’s motivation to participate in a reflective opinion-building process, even when addressing contradicting viewpoints. This work investigates how non-verbal agent behavior, specifically co-speech gestures, influences the user’s engagement and interest during an ongoing argumentative interaction. The results of a laboratory study conducted with 56 participants demonstrate that the agent’s co-speech gestures have a substantial impact on user engagement and interest and the overall perception of the system. Therefore, this research offers valuable insights for the design of future cooperative argumentative virtual agents.

It is our great pleasure to welcome you to the 8th IEEE International Workshop on Big Data and IoT Security in Smart Computing (BITS 2024) co-located with the 10th IEEE International Conference on Smart Computing (SMARTCOMP 2024). This year, the BITS 2024 is held in person in Osaka, Japan.

Mental health has a huge impact on humans, affecting both psychological and physical well-being. Excessive stress can lead to depression, reduced productivity, and even suicidal tendencies. Stress also impacts appetite and sleep quality, potentially leading to other health issues. However, stress accumulation often goes unnoticed until it severely impacts health, highlighting the need for daily stress level assessment. This study aims to estimate daily distress levels through natural conversations with a smart speaker. We utilize the audio-visual data of users interacting with a smart speaker on a daily basis, extract features from different modalities through analysis, and predict distress changes in daily life using questionnaire responses as labels. In the experiment, participants interacted with a smart speaker placed in their bedrooms, simulating daily life. Webcam recordings captured facial expressions, voice, and heart rate data, which were preprocessed for analysis. Predictions for happiness, depression, and anxiety levels were made using data from questionnaires filled out after each recording session, with scores ranging from 0 to 18. Results from the 14-day experiment with seven participants, aged 22 to 24, revealed MAEs of 2.04, 2.59, and 2.31 for happiness, depression, and anxiety levels, respectively. The corresponding RMSEs were 2.63, 3.20, and 2.91.

To achieve smart cities, leveraging data from cameras, which are often readily-installed IoT devices, can offer precious insights on the behavior of pedestrians and play a crucial role in designing and maintaining efficient transportation, appropriate infrastructure, or attractive tourism facilities. Such pedestrian flow data collection is often achieved through cross-camera person re-identification. This task is heavily privacy-invasive task by design, benefiting from rich visual data, which thus carries highly sensitive personal details about individuals. We here study how image data can be protected upfront, and introduce a novel image differential privacy mechanism leveraging both pixelization and color quantization for this purpose. Our extensive experiments show that through its random noise additions, our mechanism can obfuscate data more effectively than standard image obfuscation methods while retaining high utility for cross-camera re-identification, preserving reasonable re-identification metrics and demographic information even under low privacy budgets.

Enabling federated learning in opportunistic networks unlocks the potential for machine learning in challenging environments like disaster zones and remote regions. However, the divergent models induced by dynamic node encounters, combined with complete parameter overlap in model-homogeneous training lead to catastrophic interference, which disrupts training progress. Furthermore, when whole models must be transmitted, nodes with shorter contact duration are limited from participating in the training process. To address these challenges, we propose a different approach for training neural networks in opportunistic settings that leverages independent subnetworks and sequential training. We partition the original neural network into non-overlapping subnetworks and assign each to a unique node. These subnetworks are then trained and exchanged repeatedly during node encounters, exposing them further to diverse datasets. As a consequence, we achieve parallel and conflict-free progress while minimizing participation costs. Our experiments demonstrate that continuous training and subnetwork accumulation foster the development of a more robust model. Moreover, by utilizing pre-trained backbones as feature extractors, we achieve a test accuracy of 75.06% on MEDIC's disaster damage severity assessment task, demonstrating that the approach can be adopted in resource-constrained and dynamic scenarios in the real world.

Regulating human flow is essential to reducing congestion in areas where people gather. A digital twin that realistically simulates human flow helps for this purpose. To realize a realistic human flow simulation mechanism, it is essential to take into account people's attributes. However, existing simulation methods use only location-specific information to predict people's behavior, thus do not reflect the routines that appear in people's actual lives. In this paper, we propose a human flow simulation using synthetic population data that help extract the attributes of people living in a target area. In the proposed method, we simulate the movement of people with each attribute like office workers, students, etc. every 15 minutes using the synthetic population data and the hourly transition probability matrix between PoIs (Points of Interest) by computing the transition probability matrix from hourly PoI-level congestion (people count) in the target area using people trajectory data included in the point-type fluid population data commercially available and applying a Markov chain to the congestion. The proposed simulation mechanism is based on the data assimilation of the actual PoI congestion vector (how many people were staying in each PoI) obtained from the point-type fluid population data and the virtual PoI congestion vector generated from the prediction of people's movement using the attribute information in the synthetic population data at regular time intervals. The data are assimilated at regular intervals to obtain highly accurate PoI-level congestion forecasts. The results of the mobility simulation for office workers showed that the maximum cosine similarity with the actual PoI congestion was 0.96 after 12 hours even when the actual PoI congestion vector is known only for a part of the area (one mesh).

Predicting crowd flow is crucial for decision-making to mitigate various risks. For instance, in social problems such as traffic congestion and over-tourism, countermeasures can be taken by predicting crowd flows in advance. Typically, people visit multiple Points of Interest (PoI) for various purposes. Previous work has proposed methods to incorporate the behavioral characteristics of people in different areas, such as dining areas or office areas, into machine learning models. However, they have not considered the specific behavioral characteristics associated with each PoI, such as when restaurants or train stations experience peak periods. Recently, there has been an increase in the ability to handle large amounts of location information, leading to a growth in the volume of individual trace data. In this study, we propose a crowd flow prediction method that aggregates large-scale individual trace data of movements between PoIs and considers the behavioral characteristics associated with each PoI. We define this information as time series PoI stay counts generated from trace data collected from mobile phones. Using this, we developed a machine learning model to predict the number of people in an area (mesh) over the next several minutes to hours. This prediction is based on the number of people staying at each PoI (category) in neighboring areas (meshes). We applied this approach to densely populated areas in central Tokyo, where congestion is a significant concern, and conducted validation. The results showed that the method utilizing time series PoI stay counts improved prediction accuracy by up to 50% compared to methods that did not use it. Additionally, the Mean Absolute Percentage Error (MAPE) for predicting the number of people staying 1 hour later was only 2.57%.

Counterfeit medicines present a severe public health threat, especially in low-resource countries where consumers lack reliable means to verify the medicines they purchase. Visual inspection of medicine packaging images through keypoint matching techniques offers a promising approach for detecting design inconsistencies that could indicate counterfeit products. However, conventional methods often struggle with high computational costs and reduced accuracy when processing images of varying quality and perspectives. To address these limitations, we propose the Angle and Scale Voting (ASVote) method, which enhances keypoint-based image matching by introducing a 2D voting mechanism that leverages relative angles and scales of the keypoints to eliminate false matches(outliers) while identifying consistent matches (inliers). This approach significantly improves both processing time and accuracy. Experiments on a real-world dataset of medicine packages show that ASVote improves processing time and accuracy, outperforming conventional methods.

For reducing investment risks, predicting the volatility of financial markets is crucial. We propose a method for effectively embedding social media posts to facilitate accurate predictions of financial market trends. While discussions on social media inherently consist of paired information - a topic and its sentiment mood - most conventional studies have produced embeddings focusing only on either topic or sentiment information. This approach tends to neglect the intertwined nature of topic and sentiment, thereby overlooking potentially valuable information for market predictions. In this study, we overcome this challenge by introducing a novel document embedding technique that explicitly leverages both topics and sentiments collaboratively for market forecasting. The obtained embeddings are co-trained with financial time series data in a machine learning model, and their efficacy is evaluated through a market prediction task. Benchmarking against various existing document embedding techniques, our model demonstrated superior performance in terms of F-1 Score and Matthews correlation coefficient. The proposed model was further assessed from a practical viewpoint, utilizing investment simulations based on its predictions. These simulations confirmed the model’s potential to generate profits even during heightened market volatility, demonstrating its effectiveness as a real-world investment risk mitigation model. Model interpretation using SHapley Additive exPlanations revealed that while some topic-sentiment pairs on social media consistently contribute to market forecasting, others have only a transient impact. The SHapley Additive exPlanations experiment was also compared to the ablation model and showed that the proposed embedding allows for effective prediction by treating topics and sentiment jointly.

Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. In this article, we first propose a scalable data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. Second, using cluster-level detection, we propose a folded Gaussian classifier to pinpoint the particular segment in a cluster where the incident happened in an automated manner. We perform extensive experimental validation using mobility data collected from four cities in Tennessee and compare with the state-of-the-art ML methods to prove that our method can detect incidents within each cluster in real-time and outperforms known ML methods.

Recently, with the spread of smart houses, the smartness of housing equipment and home appliances has progressed, and the functionality and usability of interfaces between people and equipment and between people and home appliances have become important factors. Currently, the main interfaces are remote controls, smartphone applications, and even voice recognition. Furthermore, research is also being conducted on interfaces that can be operated without having the device at hand using cameras and radio waves. However, special equipment must be installed for operation, and compatibility with room design has become an issue. In this research, we proposed a system to transform existing furniture into an interface rather than providing a new interface. The proposed system focused on vibration sensors that are small, inexpensive, and can be attached to existing furniture or hidden from view. To evaluate the proposed system, an experiment was conducted to transform existing furniture into an interface for swiping by simply attaching the vibration sensor to the existing furniture. Specifically, the system attaches four vibration sensors with synchronized output signals to a table and uses a CNN to learn the vibration data obtained from the sensors to predict the direction of the swipe. As a result, when the table and person swiping were fixed, the system could predict the swipe with an accuracy of over 0.86.

A typical CS1 class involves students working on solving programming problems. Before the pandemic, this occurred in a computer laboratory with a teacher who could quickly assist students having difficulty with their work. Sometimes, there is a need for this intervention even without the student asking for help. An experienced teacher can sense the growing frustration of a student through their overall demeanor. A teacher can also watch how a student codes to provide quick hints to address potential problems. This kind of intervention is challenging to do in an online learning setting. A typical online meeting software provides a small and limited view of a student, often crowded with all the other students. As such, the visual cues of frustration can be easily lost in the noise. Not being able to see the student's code easily is also a problem. The system we are developing aims to create an online IDE that leverages gaze tracking and code logging to automatically identify these struggling students. In the first phase of the research, a learning model will be trained on students' gaze and code logs in line with their overall class performance. The second phase of the research will then use this model to predict the frustration level of student users. Collaboration and gamification strategies will be explored in the final stage of the research that would assist interventions of not just teachers but also classmates who are willing to help.

Human users tend to selectively ignore information that contradicts their pre-existing beliefs or opinions in their process of information seeking.These "self-imposed filter bubbles" (SFB) pose a significant challenge for cooperative argumentative dialogue systems aiming to build an unbiased opinion and a better understanding of the topic at hand.To address this issue, we develop a strategy for overcoming users' SFB within the course of the interaction.By continuously modeling the user's position in relation to the SFB, we are able to identify the respective arguments which maximize the probability to get outside the SFB and present them to the user.We implemented this approach in an argumentative dialogue system and evaluated in a laboratory user study with 60 participants to show its validity and applicability.The findings suggest that the strategy was successful in breaking users' SFBs and promoting a more reflective and comprehensive discussion of the topic.

Route Planning Systems (RPS) are a core component of autonomous personal transport systems essential for safe and efficient navigation of dynamic urban environments with the support of edge-based smart city infrastructure, but they also raise concerns about user route privacy in the context of both privately owned and commercial vehicles. Numerous high-profile data breaches in recent years have fortunately motivated research on privacy-preserving RPS, but most of them are rendered impractical by greatly increased communication and processing overhead. We address this by proposing an approach called Hierarchical Privacy-Preserving Route Planning (HPRoP), which divides and distributes the route-planning task across multiple levels and protects locations along the entire route. This is done by combining Inertial Flow partitioning, Private Information Retrieval (PIR), and Edge Computing techniques with our novel route-planning heuristic algorithm. Normalized metrics were also formulated to quantify the privacy of the source/destination points ( endpoint location privacy ) and the route itself ( route privacy ). Evaluation on a simulated road network showed that HPRoP reliably produces routes differing only by ≤ 20% in length from optimal shortest paths, with completion times within ∼ 25 seconds, which is reasonable for a PIR-based approach. On top of this, more than half of the produced routes achieved near-optimal endpoint location privacy (∼ 1.0) and good route privacy (≥ 0.8).

Abstract To improve the QoL of the elderly, it is essential to predict their stress states. In general, the stress state varies from day to day or time to time depending on what activities are performed and how long/strong. However, most existing studies predict the stress state using biometric data and specific activities (e.g., sleep time, exercise time and amount) as explanatory variables, but do not consider all daily living activities. Therefore, it is necessary to predict the stress state by linking various daily living activities and biometric information. In this paper, we propose a method to improve the prediction accuracy of stress estimation by linking daily living activities data and biometric data. Specifically, we construct a machine learning model in which the objective variable is the result of a stress status questionnaire obtained every morning and evening, and the explanatory variables are the types of daily living activities performed in the 24 h prior to the questionnaire and the feature values calculated from the biometric data during each of the performed activities. The results of the evaluation experiments using the one month data collected from five elderly households, show that the proposed method (using per-activity biometric features) improves the prediction accuracy by more than 10% from the baseline methods (with biometric features without considering activities).

Road traffic censuses have been carried out manually for many years since measurements by machines were not widely spread due to the difficulty of installation. To solve installation difficulty, the size issues of the necessary equipment, and privacy issues of the existing traffic counter, we are conducting research and development of portable traffic counters using a vibration sensor and machine learning. However, vehicle type classification was not realized in the previous work, hence it was not possible to survey traffic volume by vehicle types. In addition, to the best of our knowledge, there is no existing study that can detect and classify vehicles based on road vibrations with a single sensor. In this paper, we propose a method of vehicle type classification that is capable of binary classification of small and large vehicles by machine learning combined with Support Vector Machine and Random Forest for vibrations of passing vehicles. We evaluated the proposed method by conducting measurements for up to 12 hours at two actual road locations. We tested over 5 hours of data and confirmed that small vehicles classified with the F-measure of 0.96 and large vehicles with the F-measure of 0.83.

Systems that detect vehicles passing through roads play a significant role in ITS (Intelligence Transport Systems), due to their wide applicability to traffic monitoring and analysis for road construction/repair planning, congestion, and prediction. Among various systems using cameras, doppler sensors etc., a system that uses road vibration to detect passing vehicles is promising since it has advantages in terms of weather conditions and deployment/operation costs. However, it suffers from the human labor to prepare ground truth labels for training models. In this paper, we propose PAVEMENT, a novel Autonomous Incremental Learning based traffic-census sensor system using a piezoelectric vibration sensor and a video camera without human intervention. PAVEMENT consists of two models: the video-based model which detects vehicles by using bounding boxes (detected by YOLOv3 and DeepSORT) and the vibration-based model which uses road vibrations to detect passing vehicles. To reduce the burden of collecting ground truth labels, we apply linear discriminant analysis and incremental learning to train the vibration-based model by using the result of the video-based model as ground truth. Once the vibration-based model is trained, it can be used for traffic census on roads without the video camera for various conditions (weather, lighting, and other environmental factors). We collected the video and vibration data of more than 4,000 passing vehicles on roads in different places and applied our method to the data. As a result, PAVEMENT achieved over 98.4% accuracy and 98.0% f1-score in detecting passing vehicles using the model trained with 15 incremental learning steps in 1 minute interval.

In recent years, the use of energy harvesting (EH) sensors has led to the proposal of activity sensing systems that are easy to install and do not require maintenance such as battery replacement. In this study, we aim to construct a system that can not only sense but also recognize activities of daily living (ADLs) using only power generated by EH sensors. To achieve this goal, in this paper, we propose a fully EH-based ADL recognition system called Batterfly, which consists of EH analog PIR sensor nodes that can operate with indoor light, continuously senses human movement, and recognizes daily activities through machine learning. We applied the distributed execution method of the activity recognition model with five sensor nodes to five types of activities by five participants, and found that the system could recognize them with an average accuracy of 63.59%, comparable to the performance of the centralized model running on a gateway.

In the field of crowd estimation, most non-visual approaches confine their objective to only crowd counting, whereas there are a number of vision-based researches which can estimate both the number and location of people. By observation, we figured out that the WiFi channel state information (CSI) also contains the potential characteristics for both estimations. In this paper, we propose a user-device-free simultaneous crowd estimation system that enables both crowd counting and localization simultaneously, by WiFi CSI and Machine Learning. The originality of this study is that we leverage the CSI bundles as the source for extracting features that contain characteristics depending on the dynamic state (counting) and static state (localization). By experiments during three different-time sessions, we confirm that we could achieve up to 94% counting accuracy and 95% localization accuracy by k-fold cross-validation.

Maintaining hand hygiene is the one of the most effective way to prevent the spread of germs during a pandemic. This paper focuses on encouraging people to use a hand sanitizer more frequently by applying the nudge theory to improve hand hygiene behavior in private organizations. We propose a system that recognizes hand hygiene behavior using face recognition and detects hand sanitizer use. The system responds to the user's personal hand hygiene behavior with animation of a virtual bonsai as an interactive agent. To preserve user privacy, we implemented the system on an edge device and conducted experiments for 4 case studies in 2 real-world organizations. The results showed that the system improved the hand hygiene behavior of people in a private organization.

The realization of edge-based cyber-physical systems (CPS) poses important challenges in terms of performance, robustness, security, etc. This paper examines a novel approach to providing a user-centric adaptive route planning service over a network of Road Side Units (RSUs) in smart cities. The key idea is to adaptively select routing task parameters such as privacy-cloaked area sizes and number of retained intersections to balance processing time, privacy protection level, and route accuracy for privacy-augmented distributed route search while also handling per-query user preferences. This is formulated as an optimization problem with a set of parameters giving the best result for a set of queries given system constraints. Processing Throughput, Privacy Protection, and Travel Time Accuracy were developed as the objective functions to be balanced. A Multi-Objective Genetic Algorithm based technique (NSGA-II) is applied to recover a feasible solution. The performance of this approach was then evaluated using traffic data from Osaka, Japan. Results show good performance of the approach in balancing the aforementioned objectives based on user preferences.

Recent advancements in cloud computing have driven rapid development in data-intensive smart city applications by providing near real time processing and storage scalability. This has resulted in efficient centralized route planning services such as Google Maps, upon which millions of users rely. Route planning algorithms have progressed in line with the cloud environments in which they run. Current state of the art solutions assume a shared memory model, hence deployment is limited to multiprocessing environments in data centers. By centralizing these services, latency has become the limiting parameter in the technologies of the future, such as autonomous cars. Additionally, these services require access to outside networks, raising availability concerns in disaster scenarios. Therefore, this paper provides a decentralized route planning approach for private fog networks. We leverage recent advances in federated learning to collaboratively learn shared prediction models online and investigate our approach with a simulated case study from a mid-size U.S. city.

We present an approach to evaluate argument search techniques in view of their use in argumentative dialogue systems by assessing quality aspects of the retrieved arguments. To this end, we introduce a dialogue system that presents arguments by means of a virtual avatar and synthetic speech to users and allows them to rate the presented content in four different categories (Interesting, Convincing, Comprehensible, Relation). The approach is applied in a user study in order to compare two state of the art argument search engines to each other and with a system based on traditional web search. The results show a significant advantage of the two search engines over the baseline. Moreover, the two search engines show significant advantages over each other in different categories, thereby reflecting strengths and weaknesses of the different underlying techniques.

In the tourism sector, user-generated information and communication among tourists are perceived to be more effective and reliable contents. In addition, the collection of dynamic tourism information with high spatio-temporal resolution is required to provide comfortable tourism in response to the changing tourism style with the advancement of information technology. Participatory sensing, which can collect various types of information, is a useful method by which to collect these contents. However, continuous participation of users is essential in participatory sensing, and it is one of the most important points to stimulate participation motivation. In the tourism situation, we also need to pay attention to the total tourist satisfaction of participants. In this study, we investigate the effects of task allocation interfaces and user types on the efficiency of tourism information collection, tourism behavior and satisfaction in gamified participatory sensing. Two types of task allocation interfaces (free selection and agent interaction) were designed and implemented, and a sightseeing experiment was conducted with 10 participants at an actual sightseeing spot (Nara, Japan). As a result, we found that there was no difference in the effect of each interface on sightseeing satisfaction, but the characteristics of the collected data that, free selection allows for the collection of quantitative data and agent interaction allows for the efficient collection of data needed by the system, were different. In addition, we found that different user types had different tendencies for their contribution to sensing and their interface preferences.

Street parking in prohibited areas has become a social problem, especially in urban and tourist areas. In addition, because street parking can cause traffic congestion and accidents, real-time detection is required. The detection of street parking has been previously implemented on the basis of comparisons of videos recorded by fixed-point cameras. However, this approach has a limited detection area and low accuracy. In this demonstration, we present a system that recognizes street parking in real-time using a model trained by dashboard camera videos, which are widely used. The trained model was constructed by collecting data on 1,765 vehicles from dashboard camera videos. We use the Jetson TX2 as an edge device for vehicle recognition and processing. We create and demonstrate a dashboard camera device by attaching a camera and sensor module to the Jetson TX2.

In recent years, many studies and development of Cyber Physical Systems (CPS) have been carried out to feed back analysis results to human users in a physical space by using machine learning, aiming to analyze a huge amount of information obtained from physical space in a cyber space. To apply CPS to sports, a lot of studies have been conducted on sensing and recognizing actions and movements of athletes using machine learning. In this study, we focus on fishing as a sport, and propose a fishing CPS that recognizes anglers' actions in real-time and provides information on the past useful actions that are linked to fishing results depending on time and place as a decision support when the anglers do not make catch. In addition, this paper reports on the development of an IoT (Internet of Things) device that acquires positional information, acceleration and gyroscope information, and a web system that displays results of real-time activity recognition along with the place and time by animation for realizing the fishing CPS. We have evaluated the developed IoT device and web system from the viewpoint of practical use. As a result, we have confirmed that the GPS and acceleration sensors, in the actual breakwater environment, were constantly transmitting data to a server via UDP communication for 4 hours and 40 minutes.

In recent years, there has been a growing interest in travel applications that provide on-site personalized tourist spot recommendations. While they are generally useful, most of the available apps are focused on helping tourists make decisions only on the next spot to visit. This may cause that the tourists miss attractive spots to visit in the future. Due to the lack of awareness on the spots to go afterwards, they are unable to visit the spots they wanted to visit later, hence their overall tourism satisfaction decreases. In this study, we introduce an on-site tourism recommendation system, ISO-Tour, which can be used on the spot during the tour and allows users to consider multiple spots to visit next taking into account the trade-off between satisfaction of the next spot and that of the subsequent spots visited in the future.

In this paper, we aim to reveal the relationship between the number of people infected with COVID-19 in each ward in Tokyo and the changes in human mobility behavior using demographic information (population density, number of restaurants, etc.) and mobility data collected from GPS data of residents in Tokyo's 23 wards. The results confirmed that changes in human mobility behavior extracted from mobility data in each ward were an important feature related to the number of people infected by COVID-19 on the previous day's difference. These results suggest that the transition of the number of infected people in COVID-19 is largely due to human mobility behavior.

As an increasing demand for human activity monitoring in many smart services such as elderly monitoring, there is a keen need of an activities of daily living (ADL) recognition system. which can be easily deployed in ordinary homes and does not require periodic maintenance such as battery replacement for long time. In this paper, we propose an ADL recognition system which can run continuously without feeding power from outlets by intermittent sensing and distributed processing of energy harvesting (EH) sensor modules. Specifically, we have designed and developed an EH sensor node composed of (i) a micro-controller board with an analog PIR sensor which senses human activity as analog signals and form a BLE mesh network with other sensor nodes and (ii) an energy harvest module with solar panels and a rechargeable battery. We have also implemented a simple distributed random forest (RF) classifier consisting of multiple RF classifiers trained independently and running on different nodes which exchange the classification results with each other via BLE and make a final decision based on majority vote. Through experiments with five sensor nodes deployed in our smart home testbed, the distributed RF classifier classified the collected data of up to five different activities with average accuracy of over 90%.

In response to the Coronavirus 2019 (COVID-19) pandemic, the World Health Organization (WHO) has published preventive measures such as performing hand hygiene frequently, wearing a medical mask, trying to avoid touching face and so on. This paper presents a nudge-based system to promote hand hygiene in a private organization. The proposed system consists of a hand sanitizer station equipped with a magnetic sensor to sense user presses. We conducted 4 case studies to compare the effects of nudging on the frequency of hand sanitizer use: no nudging, traditional nudging, non-personalized nudging, and personalized nudging. The results reveal that using nudge-based methods offer a significant increase in the frequency hand sanitizer use.

Recently smart homes equipped with many sensors and IoT devices are widespread. However, when smart home users receive smart home services like elderly monitoring, they need to upload their privacy sensitive data to potentially untrusted cloud servers where the service quality (user's benefit) depends on the amount/frequency of the uploaded data. In this paper, aiming to minimize the risk of privacy leakage and maximize users' benefit obtained through services, we propose a novel privacy-aware data management method that works on a smart-home system composed of smart homes with sensors, edge computing servers, and a cloud server. We formulate a combinatorial optimization problem which determines the best choice of data type (raw or activity label recognized at the edge) and upload frequency in each time slot taking into account the constraints of edge server resources and users' budgets as well as the k-anonymity of activities and users' preferences. Since the target problem is NP-hard, we propose a heuristic algorithm to derive semi-optimal solutions by determining choices with better objective function values in a greedy manner. Through experiments using smart-home open dataset, we confirmed that the proposed method outperforms the conventional methods using only a cloud server.

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.

Edge and Fog computing paradigms are used to process big data generated by the increasing number of IoT devices. These paradigms have enabled cities to become smarter in various aspects via real-time data-driven applications. While these have addressed some flaws of cloud computing some challenges remain particularly in terms of privacy and security. We create a testbed based on a distributed processing platform called the Information flow of Things (IFoT) middleware. We briefly describe a decentralized traffic speed query and routing service implemented on this framework testbed. We configure the testbed to test countermeasure systems that aim to address the security challenges faced by prior paradigms. Using this testbed, we investigate a novel decentralized anomaly detection approach for time-sensitive distributed smart transportation systems.

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.

Information and communication technologies (ICTs) has enabled growth in developed countries and urban cities through improvements in communication systems, devices and applications. In rural areas, especially in developing countries, ICT penetration is not as high, often due to lack of available infrastructure and funding. With the increasing availability of Internet-of-Things (IoT) devices, low-cost large-scale deployments have become possible even in rural areas. We design, develop and implement, Near Cloud, a cloud-less platform that allows users and IoT devices to communicate and share information. This is built on top of a wireless mesh network (WMN) of low-cost, low-power IoT devices and deployed in areas where there is little to no Internet connectivity. To inject ICT and help bridge the digital divide in rural areas, Near Cloud provides functionalities such as web servers on nodes, accessibility to all users via Wi-Fi, and various data processing including image processing and machine learning. We will show applicability of Near Cloud in improving rural education, health care facilities, disaster response and agriculture.

Human Activity Recognition (HAR) with body-worn sensors has been studied intensively in the past decade. Existing approaches typically rely on data from inertial sensors. This paper explores the potential of using point cloud data gathered from wearable depth cameras for on-body activity recognition. We discuss effects of different granularity in the depth information and compare their performance to inertial sensor based HAR. We evaluated our approach with a total of sixteen participants performing nine distinct activity classes in three home environments. 10-fold cross-validation results of KNN and Random Forests classification exhibit a significant increase in F-score from inertial data to depth information (by > 12 percentage points) and show a further improvement when combining low-resolution depth matrices and sensor data. We discuss the performance of the different sensor types for different contexts and show that overall, depth sensors prove to be suitable for HAR.

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.

We propose a method of predicting an increase in the Nikkei VI index by analyzing social media based on the premise that investor sentiment is posted on social media. Since the VI index expresses the fear of investors, it is a closely related index to the risk of depression. Therefore, the VI index is an important indicator as an instrument for investment judgment. To predict the increase in the VI index more accurately, we divide messages by topic models specific to social media of stock trading and predict such the increase by machine learning using those topics. As a result of leave-one-day-out cross-validation, precision of our method was 0.45. We also found that the daily fluctuation in the VI index and the number of messages are as effective as feature quantities as the topic-posting frequency.

Recently, several researches concerning with smart and connected communities have been studied. Soon the 4G / 5G technology becomes popular, and cellular base stations will be located densely in the urban space. They may offer intelligent services for autonomous driving, urban environment improvement, disaster mitigation, elderly/disabled people support and so on. Such infrastructure might function as edge servers for disaster support base. In this paper, we enumerate several research issues to be developed in the ICDCS community in the next decade in order for building safe, smart cities resistant to disasters. In particular, we focus on (A) up-to-date urban crowd mobility prediction and (B) resilient disaster information gathering mechanisms based on the edge computing paradigm. We investigate recent related works and projects, and introduce our on-going research work and insight for disaster mitigation.

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.

Wireless sensor networks (WSNs) that periodically collect the environmental information such as temperature, humidity, and so on require the coverage of a given target field anytime and the operation lifetime longer than an expected duration by the minimum number of sensor nodes. For these WSNs, we propose a method deciding a schedule of node movement to cover the target agricultural field from plant to harvest by the minimal number of nodes in order to reduce the node deployment cost. The proposed method computes a moving schedule of each mobile sensor node so that all the nodes cover the target field without depleting battery of some of the nodes by predicting solar power generation at each point of the target field where shadow areas change depending on time, orbit of the sun, and height of crops. We conducted computer simulations and compared the performance of the proposed method with a conventional method. As a result, our method achieves 4% reduction of the number of nodes and 10% extension of the operation lifetime compared to the method without estimation of power generation amount.

In this paper, we propose SakuraSensor, a participatory sensing system which automatically extracts scenic routes information from videos recorded by car-mounted smart-phones and shares the information among users in quasirealtime. As scenic routes information, we target flowering cherries along roads since the best period of flowering cherries is rather short and uncertain from year to year and from place to place. To realize SakuraSensor, we face two technical challenges: (1) how to accurately detect flowering cherries and its degree, and (2) how to efficiently find good places of flowering cherries (PoIs) using the participatory sensing technique. For the first challenge, we develop an image analysis method for detecting image pixels that belong to flowering cherries. To exclude artificial objects with similar color to flowering cherries, we also employ fractal dimension analysis to filter out unnecessary image areas. For the second challenge, we propose a method called k-stage sensing. In this method, the interval for sensing (taking a still image and applying the image analysis) by each car is dynamically shortened so that the roads near the already found PoIs are more densely sensed. We implemented SakuraSensor consisting of client-side software for iOS devices and server-side software for a cloud server and conducted experiments to travel cherry-lined roads and record videos by several cars. As a result, we confirmed that our method can identify flowering cherries at about 74 % precision and 84 % recall. We also confirmed that our k-stage sensing method could achieve the comparable PoI detection rate with half sensing times compared to a conventional method.

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.

The explosive growth of mobile data traffic causes immense pressure on the limited spectrum of cellular networks (3G/4G) and the deterioration in the quality of wireless communication. Even though mobile network operators deploy WiFi access points (WiFi APs) to offload the traffic from 3G/4G to WiFi, WiFi connectivity is far from ubiquitous. To increase opportunities of offloading, some methods leveraging delay tolerance are proposed. These methods, however, cause a poor performance on delay sensitive applications like Web browsing and streaming of video and audio. To address this problem, we introduce a WiFi offloading method using prefetching. While a user stays in a WiFi area, our method predicts the Web pages that will be requested by the user over 3G/4G after leaving from the WiFi area, and performs prefetching of those pages over WiFi. This allows the user to browse prefetched pages instantly without downloading them over 3G/4G. The simulation results show that our method achieved approximately 11% of offloading of data traffic, suppressing energy consumption within the amount consumed when performing communication only over 3G/4G.

To optimize overlay networks on the Internet, it is useful to estimate the qualities of each overlay link. Existing tools for measuring link qualities send probe packets from one end of the network to the other, but this requires the execution of measurement software at both end nodes. Besides, these tools need to send many probe packets to measure quality accurately, and this can disrupt other communication. In this paper, we propose a technique based on supervised learning for estimating link quality based on the quality observed for other similar links. Since our technique does not require sending probe packets, we can quickly estimate the qualities of many links without disrupting other communication or wasting processing time at many nodes. Through experiments on PlanetLab, the proposed method showed better performance on path latency estimation than the estimating results based on path length.

Aiming to realize the application which supports users to enjoy walking with an appropriate physical load, we propose a method to estimate physical load and its variation during walking only with available functions of a smartphone. Since physical load has a linear relationship with heart rate, our purpose is to estimate heart rate with a smartphone. To this end, we build heart rate prediction models which predict heart rate variation from walking data including acceleration and walking speed by machine learning. In order to track unexpected change of physical load, we focus attention on oxygen uptake which has a similar property to heart rate and devise a novel technique to estimate the oxygen uptake from acceleration and GPS data so that it is used as an input of the model. Moreover, to adapt to difference of heart rate variation among individuals, we devise techniques to optimize parameters for each profile-based category of users and to normalize heart rate to absorb individual difference. We applied the proposed method to actual walking data on various routes by different persons and confirmed that the method estimates heart rate variation with the mean error of less than 7 beat per minute.

This paper describes a system enabling automatic indoor floor map generation using a smart phone equipped with an ultrasonic sensor gadget. First, it estimates the size, shape and direction of the room by exploiting the ultrasonic sensors and builtin accelerometer and geomagnetic sensor of the smart phone. Second, it estimates the rough location of each room by using WiFi indoor localization and generates an accurate floor map by estimating the contiguity relationship between rooms. We implemented a prototype of the proposed system and estimated the room size, shape and direction through an experiment. As a result, the system could estimate the lengths of the room sides with errors of about 6.1% and about 18.9%.

We propose a method for dynamic load balancing in wireless LANs (WLANs), which adapts association topology dynamically based on traffic conditions, while keeping the handoff overhead negligible using virtualized wireless network interfaces (WNICs). In large-scale WLANs, there are many locations that each station (STA) can discover multiple access points (APs). In these locations, the conventional approach to the AP selection in which each station connects to the AP with the strongest Received Signal Strength Indication (RSSI) may suffer from imbalanced load among APs. To address this issue, a number of AP selection schemes have been proposed, which achieve load balancing by changing some STA-AP associations. However, since stations cannot communicate during handoff, frequent changes of STA-AP associations will result in serious deterioration of the communication quality. Therefore, in the existing schemes, we face a problem that it is difficult to decide appropriate timing of association changes. Nevertheless, this problem was not considered as a major concern in the literature. In this paper, we propose a method for trigger-based dynamic load balancing in WLANs. In the proposed method, to minimize the handoff overhead, the WNIC on a station is virtualized and connected to multiple APs simultaneously. Using this approach, we propose a method that continuously monitors changes in traffic conditions and that switches STA-AP associations at appropriate timing based on the monitored results. We evaluate the effectiveness of our method in terms of aggregated throughput and fairness using the ns-3 simulator. Compared with the result in the traditional AP selection method, aggregated throughput is improved by about 11%, while increasing the Jain's fairness index by about 19% in our method.

Finding a vacant parking space in a large crowded parking facility takes long time. In this paper, we propose a navigation method that minimizes the parking time based on collected real-time positional information of cars. In the proposed method, a central server in the parking facility collects the information and estimates the occupancy of each parking zone. Then, the server broadcasts the occupancy data to the cars in the parking facility. Each car then computes a parking route with the shortest expected parking waiting time and shows it to the driver. We conducted simulation-based evaluations of the proposed method using a realistic model based on trace data taken from a real parking facility. We confirmed that the proposed method reduced parking waiting time by 20%-70% even with low system penetration.

When disasters occur, a common characteristic is the partial or complete failure of the telecommunications infrastructure so the usual means of communication are often not available. However, accurate and timely information of the disaster area is important. In this paper, a data collection method from an area of interest (AoI) within the disaster zone is proposed that uses the mobile phones of the people to serve as sensing nodes. To achieve maximum AoI coverage while minimizing delay, we propose a DTN-based data aggregation method. Mobile phone users create messages containing disaster-related information and merge them with their respective coverage areas into a new message with the merged coverage to reduce message size and to minimize the overall message collection delay. However, simply merging messages may result in duplicate counting thus, to prevent this, a Bloom filter is constructed for each aggregated message. Also, to reduce further the message delivery time, the expected time of a node to reach its destination is introduced as a routing metric. Through computer simulation with a real geographical map, we confirmed that the proposed method achieved a smaller delay in message delivery than epidemic routing.

In this paper, aiming to reduce cellular network load, we propose a cooperative download method by which user terminals exchange fragments of a content called chunks through short-range wireless communication like Bluetooth or Wi-Fi with other user terminals who want the same content. In order to reduce the cellular network load, it is necessary to receive as many chunks as possible via short-range wireless communication. Our basic idea is to predict contact time when other user terminals get within a range of short-range wireless communication and to obtain chunks efficiently from other user terminals. To predict the contact time, each terminal periodically registers information of its location and retaining and requiring chunks with a server in the fixed network. The server calculates for each terminal the probability and time to contact other terminals so that the terminal can determine its communication schedule with those meeting terminals to obtain chunks efficiently. Through computer simulations with measured energy consumption parameters, we confirmed that terminals using our method obtained from other terminals 50% more chunks with 20 % less energy consumption than the method of greedily collecting chunks by always turning on the wireless device.

In this paper, we tackle the problem to achieve k-coverage of a target indoor space with obstacles, that is, any point in the target monitoring area has a line-of-sight to and is located in the sensing range rsof at least k sensors. We propose heuristic algorithms for computing a deployment pattern achieving the k-coverage in an arbitrary 3D target space with stationary and mobile obstacles, while minimizing the overall deployment cost. For the case with only stationary obstacles, we propose a greedy algorithm that puts sensor nodes one by one on a grid point of the deployable area in the descending order of the cost-performance value (i.e., how many monitoring points are covered by putting a sensor at the deployment point per unit deployment cost). In order to extend the algorithm for the case with a mobile obstacle, we define mobile k-coverage that guarantees k-coverage of a target space for arbitrary position of a mobile obstacle, then provide a sufficient condition for the mobile k-coverage: the half-sphere of radius rscentered at a monitoring point bounded by the vertical plane containing the point includes at least k sensor nodes. Based on this condition, we propose a heuristic algorithm that puts at least one sensor node in each π over k+1 spherical wedge for each monitoring point. With the proposed algorithms, we have computed the sensor nodes position in an existing indoor environment and confirmed that the obtained WSN deployment in the real space accurately achieves k-coverage.

Aiming to achieve sensing coverage for a given Area of Interest (AoI) in a People-Centric Sensing (PCS) manner, we propose a concept of (α, T)-coverage of the target field where each point in the field is sensed by at least one node with probability of at least α during the time period T. Our goal is to achieve (α, T)-coverage by a minimal set of mobile sensor nodes for a given AoI, coverage ratio α, and time period T. We model pedestrians as mobile sensor nodes moving according to a discrete Markov chain. Based on this model, we propose two algorithms: the inter-location and inter-meeting-time algorithms, to meet a coverage ratio α in time period T. These algorithms estimate the expected coverage of the specified AoI for a set of selected nodes. The inter-location algorithm selects a minimal number of mobile sensor nodes from nodes inside the AoI taking into account the distance between them. The inter-meeting-time selects nodes taking into account the expected meeting time between the nodes. We conducted a simulation study to evaluate the performance of the proposed algorithms for various parameter setting including a realistic scenario on a specific city map. The simulation results show that our algorithms achieve (α, T)-coverage with good accuracy for various values of α, T, and AoI size.

In this paper, we propose a method for improving the playback quality of one segment terrestrial television broadcasting (called 1seg, hereafter) at mobile terminals staying in a weak 1seg radio reception area (called WRA terminals) by wireless multi-hop video streaming from terminals in strong 1seg radio area (called SRA terminals). First, we formulate the problem to derive the set of video forwarding paths that maximize the number of WRA terminals to be “relieved” by receiving the forwarded video, under the constraints on the wireless bandwidth and the maximum number of hops. Since this problem is NP-hard and deriving the optimal solution in real-time is infeasible, we propose a greedy algorithm that each WRA terminal find a video forwarding path from a SRA terminal receiving the required 1seg channel based on the information periodically exchanged among neighboring terminals. In order to increase the number of relieved terminals, we introduce a technique to let a SRA terminal change its watching 1seg channel, forward the video to a WRA terminal, and ask for the relief for itself. Through computer simulations, we confirme that the proposed algorithm with 2-hop relief paths improved the video playback quality in more than 60% of the total WRA staying time.

For accident prevention at intersections, it is useful for drivers to grasp the position of vehicles in blind spots. This can be achieved without infrastructure if some vehicles passing near the intersection capture and share live video of the intersection through inter-vehicle communications. However, such video streaming requires a congestion control mechanism. In this paper, aiming to let a driver grasp the situation at an intersection, we propose a method to select vehicles that send a video in order to generate a live bird's-eye-view video of the intersection. In our method, each vehicle at an intersection exchanges information with others, such as the sub-areas of the intersection it captures, the quality of its video, and its position and speed. Based on the exchanged information, each vehicle autonomously judges whether it should send its video or not. Through simulation with a QualNet simulator, we confirm that our method achieves a good video arrival rate and video quality sufficient for practical use.

In vehicular ad hoc networks (VANETs), delivering messages to a specific location is difficult due to the high mobility of vehicles. In this paper, we propose a method for efficient message delivery in VANETs utilizing the route information in car navigation systems. In the proposed method, each car periodically exchanges the information on its current position and scheduled route in the car navigation system with neighboring cars within radio range. By referring to the exchanged information, each car forwards messages to the neighboring car that will most closely approach the destination. Through simulations, we confirm that the proposed method achieves a better delivery rate with low bandwidth usage than a geocast-based method and epidemic routing.

In this paper, we propose a framework named ``UbiREMOTE'' for controlling information appliances connected to a home network with a unified and intuitive user interface from a remote place.The UbiREMOTE framework provides users with a way to control appliances in a home through a virtual space drawn on a mobile terminal screen which reflects the latest conditions of the real appliances and the rooms in the home. With UbiREMOTE, a user controls appliances by (1) moving to the front of an appliance, (2) choosing the appliance to control and (3) pushing buttons on the virtual remote controller which imitates the real remote controller for the appliance or the real console.In this paper, we propose a method to improve the drawing speed of 3D virtual space on mobile terminals and a method for automatically reflecting condition changes of the real space in the virtual space.We implemented the methods and evaluated the performance. The results showed that the proposed methods can be practically used on small mobile terminals.

In this paper, we propose a method for video ads dissemination through a hybrid network consisting of WiFi and cellular networks, in order to provide timely delivery of video ads with preferred content to users according to the users' contexts. In recent years, video download/streaming services for cellular phones have already become popular. Among various video delivery services, a service for disseminating video ads according to the users' contexts is expected to achieve high advertising effects. However, context-aware video ads dissemination will consume large bandwidth since the size of video ad is rather large and the same ad is required at different time from various users. We propose a new video ads dissemination method for mobile terminals which utilizes both WiFi and cellular networks. In the proposed method, a file of video ad is divided into pieces and each node exchanges the pieces with neighbor nodes using WiFi ad hoc communication so that the usage of cellular network is reduced. In order to make the method works effectively for a large number of nodes, we propose an algorithm where mobile nodes autonomously and probabilistically decide their actions without a central control. Through simulations, we confirmed that our method reduces cellular network usage by about 93% compared with a case that all nodes download video ads via cellular network, and works effectively in cases with a large number of nodes and high mobility.

Mobile ad hoc networks (MANETs) can be used to provide mobile users temporary infrastructure to use services such as database retrieval service when traditional infrastructure-based networks are unavailable in infrastructure-less situations (e.g. after a destructive disaster like an earthquake). The challenging task in such dynamic environments is how we can improve the service availability. An effective strategy is replicating a service at some nodes distributed across the network. However, service replication can considerably impact the system energy consumption. Since mobile devices have a limited amount of battery, a dynamic and efficient service replication is necessary to support such environments. In this paper, we propose a distributed service replication scheme for achieving high service availability with reasonable energy consumption for MANETs. The proposed method called distributed adaptive service replication (DAR) divides the whole network into disjoint zones of at most 2-hops in diameter and builds a dynamic replication mechanism which puts replicas only in zones with high service demand. Through simulations, we have confirmed that our approach can achieve higher service availability and lower energy consumption than an existing method.

One of the important issues in wireless sensor network (WSN) is to k-cover the target sensing field and to extend its lifetime. We propose a method to k-cover the field and maximize the WSN lifetime by moving mobile sensor nodes to appropriate positions for a WSN consisting of both static and mobile sensor nodes which periodically collect environmental information. Our target problem is NP-hard. So, we propose a genetic algorithm (GA) based scheme to find a near optimal solution in practical time. In order to speed up the calculation, we devised a method to check a sufficient condition of k-coverage of the field. For the problem that nodes near the sink node have to forward the data from farther nodes, we make a tree where the amount of communication traffic is balanced among all nodes, and add this tree to the initial candidate solutions of our GAbased algorithm. Through computer simulations, we confirmed that our method achieves much longer k-coverage lifetime than conventional methods for 100 to 300 node WSNs.

In this paper, we propose a framework which allows remote users to form conversation groups based on spatial relationship in a shared virtual space. Our proposed framework can transport awareness information of real world by capturing and transferring user's audio visual information. Our framework also provides functions useful to CSCW, which allow each user to simultaneously join different conversation groups, and communicate with others asynchronously exchanging awareness information. We show a reference implementation architecture to realize the framework in an ordinary computing and networking environment.

The 3D tele-immersive (3DTI) environments are emerging as the next generation technique for tele-communication. In this paper, we present a novel and generic interface for view control in 3D environments. The interface uses Wii Remote, a wireless controller for a video game console. It allows the user to manipulate the virtual camera and 3D objects intuitively with buttons and through motions (pitch and roll). We conducted user studies to evaluate the interface with a professional dancer and average audiences. The results demonstrate that the Wii Remote interface is much better suited to view control in 3DTI environments since it is much easier to use, more effective, and more accurate than the conventional mouse-based interfaces.

This paper presents a cost-efficient video multicast method for live video streaming to heterogeneous mobile terminals over a content delivery network (CDN), where CDN consists of a video server, several proxies with wireless access points, and overlay links among the server and proxies. In this method, the original video sent from the server is converted into multiple versions with various qualities by letting proxies execute transcoding services based on the users' requirements, and delivered to mobile terminals along video delivery paths. To suppress the required computation and transfer costs in CDN, we propose an algorithm to calculate cost-efficient video delivery paths which minimizes the sum of the computation cost for proxies and the transfer cost on overlay links. Our basic idea for deriving cost-efficient delivery paths is to place transcoding service on different proxies in load-balancing manner, and to construct a minimal Sterner tree from all transcoding points of requested qualities. The overall goal of the placement is the balance between computation and transfer cost. Through simulations, we show that our algorithm can calculate more cost-efficient video delivery paths and achieve lower request rejections than other algorithms.

We have proposed FAIRVIEW, a framework for realizing 3D graphics-based interaction between mobile users in real world and remote network users. In order to realize FAIRVIEW in an ordinary wireless LAN and Internet environment, a QoS adaptation mechanism is essential. The QoS adaptation mechanism of FAIRVIEW regulates, for each user, update frequency of his/her observable objects depending on the importance values associated with regions of his/her sight within available bandwidth. In this demonstration, we show how our QoS adaptation mechanism changes the quality of each observable object as the user moves his/her sight.

In this paper, we propose a method which efficiently collects, retains and propagates traffic information using inter- vehicle communication with "message ferrying" technique used in vehicular ad hoc network (VANET). In the proposed method, we use buses as message ferries which travel along regular routes. In order to improve information propagation efficiency in low- density areas, buses collect as much traffic information as possible from cars in their proximity, and periodically disseminate the collected information to neighboring cars. We have implemented the proposed system on the traffic simulator NETSTREAM and compared information propagation efficiency between our proposed method and a method which uses inter-vehicle communication among only ordinary cars. In the simulation, the proposed method improved the efficiency up to 50%.

In this paper, we propose a new method to construct a semi-optimal QoS-aware multicast tree on MANET using distributed computation of the tree based on genetic algorithm (GA). This tree is sub-optimal for a given objective (e.g., communication stability and power consumption), and satisfies given QoS constraints for bandwidth and delay. In order to increase scalability, our proposed method first divides the whole MANET to multiple clusters, and computes a tree for each cluster and a tree connecting all clusters. Each tree is computed by GA in some nodes selected in the corresponding cluster. Through experiments using network simulator, we confirmed that our method outperforms existing on-demand multicast routing protocol in some useful objectives.

Multi-objective genetic algorithms (MOGAs) are approximation techniques to solve multi-objective optimization problems. Since MOGAs search a wide variety of pareto optimal solutions at the same time, MOGAs require large computation power. In order to solve practical sizes of the multi objective optimization problems, it is desirable to design and develop a hardware implementation method for MOGAs with high search efficiency and calculation speed. In this paper, we propose a new method to easily implement MOGAs as high performance hardware circuits. In the proposed method, we adopt simple Minimal Generation Gap (MGG) model as the generation model, because it is easy to be pipelined. In order to preserve diversity of individuals, we need a special selection mechanism such as the niching method which takes large computation time to repeatedly compare superiority among all individuals in the population. In the proposed method, we developed a new selection mechanism which greatly reduces the number of comparisons among individuals, keeping diversity of individuals. Our method also includes a parallel execution architecture based on Island GA which is scalable to the number of concurrent pipelines and effective to keep diversity of individuals. We applied our method to multi-objective Knapsack Problem. As a result, we confirmed that our method has higher search efficiency than existing method.

In this paper, the authors propose a technique to flexibly implement genetic algorithms (GAs) for various problems on FPGAs. For the purpose, the authors propose a common architecture for GA. The proposed architecture allows designers to easily implement a GA as a hardware circuit consisting of parallel pipelines which execute GA operations. The proposed architecture is scalable to increase the number of parallel pipelines. The architecture is applicable to various problems and allows designers to estimate the size of resulting circuits. The authors give a model for predicting the size of resulting circuits from given parameters. Based on the proposed method, the authors have implemented a tool to facilitate GA circuit design and development. Through experiments using knapsack problem and traveling salesman problem (TSP), the authors show that the FPGA circuits synthesized based on the proposed method run much faster and consume much lower power than software implementation on a PC and the model can predict the size of the resulting circuit accurately enough

Genetic algorithms (GAs) are useful since they can find near optimal solutions for combinatorial optimization problems quickly. Although there are many mobile/home applications of GAs such as navigation systems, QoS routing and video encoding systems, it was difficult to apply GAs to those applications due to low computational power of mobile/home appliances. In this paper, we propose a technique to flexibly implement genetic algorithms for various problems on FPGAs. For the purpose, we propose a basic architecture which consists of several modules for GA operations to compose a GA pipeline, and a parallel architecture consisting of multiple concurrent pipelines. The proposed architectures are simple enough to be implemented on FPGAs, applicable to various problems, and easy to estimate the size of the resulting circuit. We also propose a model for predicting the size of resulting circuit from given parameters consisting of the problem size, the number of concurrent pipelines and the number of candidate solutions for GA. Based on the proposed method, we have implemented a tool to facilitate GA circuit design and development. This tool allows designers to find appropriate parameter values so that the resulting circuit can be accommodated in the target FPGA device, and to automatically obtain RTL VHDL description. Through experiments using Knapsack Problem and TSP, we show that the FPGA circuits synthesized based on the proposed method run much faster and consume much lower power than software implementation on a PC and that our model can predict the size of the resulting circuit accurately enough.

In urban areas including shopping malls and stations with many people, it is important to utilize various information which those people have obtained. In this paper, we propose a method for information registration and retrieval in MANET which achieves small communication cost and short response time. In our method, we divide the whole application field into multiple sub-areas and classify records into several categories so that mobile terminals in an area holds records with a category. Each area is associated with a category so that the number of queries for the category becomes the largest in the area. Thus, mobile users search records with a certain category by sending a query to nodes in the particular area using existing protocol such as LBM (Location-Based Multicast). Through simulations supposing actual urban area near Osaka station, we have confirmed that our method achieves practical communication cost and performance for information retrieval in MANET.

We have proposed realistic mobility models and developed a network simulator called MobiREAL for performance evaluation of MANET applications. Simulator users can easily generate a mobility scenario on any city section with the support tool of MobiREAL and can easily analyze the impact of mobility through the simulation visualization tool of MobiREAL. In this demonstration, we will show the usefulness of MobiREAL and importance to simulate MANET applications in realistic environments.

In this demonstration, we present cellular phone applications developed on top of our middleware, and show the usefulness of the proposed group formation mechanism based on user’s context and group communication. Our middleware allows application programmers to efficiently develop cooperative applications consisting of a large number of cell phone terminals. To cope with several restrictions of cellular phones, our middleware allows application software to be executed separately on a server and user terminals. Group communication is implemented as interprocess communication on the server, and only the userinterface parts are executed on the cellular phones.

In this paper, we propose a method to realize traffic information sharing among cars using inter-vehicle communication. When traffic information on a target area is retained by ordinary cars near the area, the information may be lost when the density of cars becomes low. In our method, we use the message ferrying technique together with the neighboring broadcast to mitigate this problem. We use buses which travel through regular routes as ferries. We let buses maintain the traffic information statistics in each area received from its neighboring cars. We implemented the proposed system, and conducted performance evaluation using traffic simulator NETSTREAM. As a result, we have confirmed that the proposed method can achieve better performance than using only neighboring broadcast.

In this demonstration, we show an energy-aware video streaming system which allows users to play back video for the specified duration within the remaining battery amount. In the system, we execute a proxy server on an intermediate node in the network. It receives the video stream from a content server, transcodes it to the videos with appropriate quality, and forwards it to a PDA or a laptop PC. Here, suitable parameter values of the video (such as picture size, frame rate and bitrate) which enable playback for the specified duration are automatically calculated on the proxy using our battery consumption model. The system also allows users to play back video segments with different qualities based on the importance specified to each video segment.

In this paper, we propose a method for cars to autonomously and cooperatively collect traffic jam statistics to estimate arrival time to destination for each car using inter-vehicle communication. In the method, the target geographical region is divided into areas, and each car measures time to pass through each area. Traffic information is collected by exchanging information between cars using inter-vehicle communication. In order to improve accuracy of estimation, we introduce several mechanisms to avoid same data to be repeatedly counted. Since wireless bandwidth usable for exchanging statistics information is limited, the proposed method includes a mechanism to categorize data, and send important data prior to other data. In order to evaluate effectiveness of the proposed method, we implemented the method on a traffic simulator NETSTREAM developed by Toyota Central R&D Labs conducted some experiments and confirmed that the method achieves practical performance in sharing traffic jam information using inter-vehicle communication

In this paper, we propose middleware for efficient and robust distributed network monitoring. In our technique, we specify network monitoring items, detection methods of viruses and DDoS attacks and the corresponding reactive actions as a management scenario. At the same time, we specify logical neighboring relations between separate network segments so that we can efficiently detect problems occurring in multiple segments. When a problem occurs in multiple network segments, the corresponding monitoring nodes form a group dynamically using logical relations. Based on the pre-defined management scenario, the nodes in the group carry out the reactive actions autonomously. We have designed and implemented our middleware consisting of several useful APIs. We have confirmed effectiveness of our technique through ns-2 simulation

In order to allow every user to extract aggregated computational power from idle PCs in the Internet, we propose a distributed architecture to achieve a market based resource sharing among users. The advantages of our proposed architecture are the following: (i) aggregated resources can be bought by one order; (ii) resource prices are decided based on market principles; and (iii) the load is balanced among multiple server nodes to make the architecture scalable w.r.t. the number of users. Through simulations, we have confirmed that the proposed method can mitigate the load at each server node to a great extent.

In this paper, we propose RAVITAS, a framework for realistic voice chat among multiple users in a virtual space reproducing the cocktail party effect. RAVITAS utilizes context-aware voice filtering (CAVF), pub/sub-based locality management, and controlled voice streaming to achieve this effect. Our preliminary experiments show that RAVITAS achieves satisfactory perception-based subjective results for a small group of users.

In this paper, we propose a probabilistic rule-based model to describe behavior of mobile nodes for accurately evaluating performance of MANET applications. The proposed model allows us to describe how mobile nodes change their destinations, routes and speeds/directions based on their positions, surroundings (e.g. neighboring nodes), information obtained from applications, and so on. We have designed and developed a network simulator called MobiREAL based on the proposed methodology. Through experiments, we show importance to simulate MANET applications in realistic environments.

In order for precise evaluation of MANET applications, more realistic mobility models are needed in wireless network simulations. In this paper, we focus on the behavior of pedestrians in urban areas and propose a new method to generate a mobility scenario called Urban Pedestrian Flows (UPF). In the proposed method, we classify pedestrians in a simulation field into multiple groups by their similar behavior patterns (simply called flows hereafter, which indicate how they move around geographic points). Given the observed road density in the target field, we derive using linear programming techniques how many pedestrians per minute follow each flow. Using the derived flows, we generate a UPF scenario which can be used in network simulators. In particular, we have enhanced a network simulator called MobiREAL, which has been developed in our research group, so that we can generate and use the UPF scenario. MobiREAL simulator has three main facilities: the behavior simulator, network simulator and animator. The behavior simulator can generate/delete mobile nodes according to the UPF scenario. The network simulator can simulate MANET protocols and applications. The animator offers elegant visualization of simulation traces as well as graphical user interfaces for facilitating derivation of UPF scenarios. Through several case studies, we show similarity of the derived flows to the observed ones, as well as the metrics that characterize the mobility of the scenario.

We propose a personal navigation system (called PNS) which navigates a tourist through multiple destinations efficiently. In our PNS, a tourist can specify multiple destinations with desired arrival/stay time and preference degree. The system calculates the route including part of the destinations satisfying tourist's requirements and navigates him/her. For the above route search problem, we have developed an efficient route search algorithm using a genetic algorithm. We have designed and implemented the PNS as a client-server system so that the portable device users can use the PNS through the Internet. Experiments using general map data and PDAs show that our PNS can calculate a semioptimal route almost in real-time.

We propose a QoS adaptation method for streaming video playback for portable computing devices where the playback quality of each video fragment is automatically adjusted from the remaining battery amount, desirable playback duration and the user's preference for each fragment. In our method, we assume that video segments (or shots) are classified into some predefined categories. Each user specifies the relative importance among categories and preferred video properties, such as proportion between motion speed and vividness for each category. From this information, playback quality and the properties of each category are determined so that the video playback can last for the specified duration within the battery amount. We have implemented a video streaming system consisting of a transcoder for PCs and a video player for PDAs.

In this paper, we propose a middleware library for efficiently developing distributed cooperative applications consisting of a large number of cellular phone users. Our middleware provides: (1) a dynamic group formation mechanism depending on users' locations and preferred subjects; and (2) a group communication mechanism called multiway synchronization for multicasting, synchronization and mutual exclusion. Most of Java executors on cellular phones do not support direct communication among user programs. Usable resources are also restricted. Therefore, in our middleware, most of user programs are executed on their servers as agents. Group communication is implemented as inter-process communication on the server, and only the user-interface parts are executed on the cellular phones.

We propose an energy-aware video streaming system for portable computing devices, in which the video can be played back for the specified duration within the remaining battery amount. To save power, we introduce techniques (i) to reduce playback quality of a video at an intermediate proxy and (ii) to shorten working time of the network I/F card using periodic bulk transfer of the video data on the wireless LAN. To enable playback for the specified duration, we have developed a power consumption model for portable devices using parameters on playback quality, playback duration, battery amount, and so on. We have also developed an algorithm to assign different playback quality among multiple video segments based on the user's preference.within the battery amount. Our experiments using PDAs and laptop PCs on 802.11b WLAN show that our system achieves less than 6 prediction error in playback duration while adapting playback quality among video segments.

In this paper, we propose a flexible and high-reliable HW/SW co-design method for real-time systems consisting of multiple functional modules using general purpose components such as DSP, CPU and memory. In our method, we specify a system as a parallel composition of concurrent periodic EFSMs with timing constraints. As communication primitives among EFSMs, multi-way synchronization mechanism can be specified. Here, we propose a technique for efficient development of real-time embedded systems considering both reliability and cost-performance. For the purpose, using a parametric model checking technique, we derive a parameter condition which must hold for the system to proceed without deadlocks and satisfy given timing constraints. Based on the derived parameter condition and cost-performance characteristic of available components, an appropriate combination of components is automatically selected so that the total cost is minimized. We have developed a design support tool based on the proposed technique. By applying our method to development of a basic functionality of a cellular phone, we could decide which functional modules should be implemented as dedicated HW units or on-chip-CPUs' software, and select suitable DSPs and memories with low costs.

In this paper, we present a new application level multicast protocol called Emma (end-user multicast for multi-party applications) suitable for communication systems where multiple video sources are exchanged in real-time among end-hosts, such as video-conferencing. The primal feature of Emma is that video sources with the higher priority given by users are prioritized among others for the provision of quality of service at the user level and that all the operations in Emma are done in a distributed manner. Our experimental results have shown that Emma achieves reasonable performance on overlay networks with high user satisfaction.

In this paper, we propose a selection technique for replicated multicast video servers. We assume that each replicated video server transmits the same video source as different quality levels of multicast streams. Using an IGMP facility like m-trace, each receiver monitors packet count information of those streams on routers and periodically selects the one which is expected to provide low loss rate and to be suitable for the current available bandwidth of receivers. Moreover, collection of packet count information is done in a scalable and efficient manner by sharing the collected information across receivers. Our experimental results using the network simulator have shown that our method could achieve much higher quality satisfaction of receivers, under the reasonable amount of tracing traffic.

In this paper, we propose a technique to implement communication protocols as hardware circuits using a model of concurrent EFSMs with multi-way synchronization. Since use of multi-way synchronization enables simple and comprehensible specifications of recent communication protocols which frequently use complicated mechanisms such as mutual exclusion and dynamic job assignment, the proposed model is expected to reduce development cost in designing/developing such protocols. We implement specifications described in the model so that EFSMs work synchronously with the same clock, and that the synchronization mechanism for checking executability of each tuple of synchronizing transitions is implemented as a combinational logic circuit. Through some experiments, we have confirmed that the proposed technique can synthesize hardware circuits with relatively good performances for practical use.

In this paper, we propose a receiver-cooperative bandwidth management method for layered multicast streams, considering not only bandwidth requirements but also receivers' preference. In the method, we assume that each receiver has a preference value for each layer of streams. When a receiver requests an additional layer and required bandwidth is not available on links, it can let other receivers release a part of the layers of streams which they receive if it increases the sum of the satisfied preference values of all receivers as a total. We give an algorithm to calculate an optimal way of releasing layers in a polynomial time under some assumption. We did an experiment to transmit JPEG video over a private IP network and confirmed that the method could control bandwidth among the video streams within a second.

In this paper, we propose a new bandwidth allocation technique where a new stream can preempt an appropriate amount of bandwidth from other existing streams, considering both quality and priority requirements of users. The existing preemption-based technique has focused on the preemption among the streams with the same user. However, in multi-party multimedia applications, there would be a case where we would like to raise the quality of a specific stream (e.g. in a video conference, the video stream of a new chair may become more important than those of the existing participants). Therefore the preemption should be allowed among streams with different users and the best preemption in terms of their requirements should be provided. In our technique, using the algorithm for solving the minimum flow cost problem, the preemption is calculated so that the total loss of quality and priority of the existing streams can be minimized. We have implemented the proposed technique and evaluated it through the experiment using MPEG1 video streams, and have confirmed that our technique can keep a high frame rate for each existing MPEG1 video stream even when accommodating a lot of new streams.

In this paper, we propose a method for visualizing LOTOS specifications using multi-rendezvous mechanism. For visualization, we have extended LOTOS by introducing some primitive animation events. Using the extended LOTOS, we describe a visualization scenario for events where we would like to visualize their execution. Then, we execute the original specification and its visualization scenario in parallel under LOTOS multi-rendezvous mechanism so that the corresponding animation is activated when each event is executed. The pair of the original specification and its visualization scenario is converted into the multi-threaded object code using our LOTOS compiler. In our visualization method we can specify the visualization scenario without modifying the original specification, and we can derive an object code which animates the original specification in real time. We have tried to visualize a LOTOS specification of "Dijkstra's dining philosophers", and evaluated the usefulness of our approach.