Modern mobility platforms have stored vast streams of GPS trajectories, temporal metadata, free-form textual notes, and other unstructured data. Privacy statutes such as the GDPR require that any individual's contribution be unlearned on demand, yet retraining deep models from scratch for every request is untenable. We introduce MobText-SISA, a scalable machine-unlearning framework that extends Sharded, Isolated, Sliced, and Aggregated (SISA) training to heterogeneous spatio-temporal data. MobText-SISA first embeds each trip's numerical and linguistic features into a shared latent space, then employs similarity-aware clustering to distribute samples across shards so that future deletions touch only a single constituent model while preserving inter-shard diversity. Each shard is trained incrementally; at inference time, constituent predictions are aggregated to yield the output. Deletion requests trigger retraining solely of the affected shard from its last valid checkpoint, guaranteeing exact unlearning. Experiments on a ten-month real-world mobility log demonstrate that MobText-SISA (i) sustains baseline predictive accuracy, and (ii) consistently outperforms random sharding in both error and convergence speed. These results establish MobText-SISA as a practical foundation for privacy-compliant analytics on multimodal mobility data at urban scale.

This doctoral research proposes a framework for developing sociallyaware robot navigation systems by integrating the cognitive capabilities of Large Language Models (LLMs) with the demands of real-world Human-Robot Interaction (HRI).Our work follows a four-stage plan that systematically addresses the challenges of applying LLMs to time-sensitive, safety-critical tasks.This paper details the completion of the first two stages, wherein we developed and evaluated a foundational navigation model.Our system features a meticulously designed multimodal fusion pipeline that integrates LiDAR and camera data, processed by a YOLO model and a Hungarian algorithm for semantic association, providing rich, contextual input to the LLM.Through knowledge distillation and fine-tuning on data from a custom simulator, our model demonstrates robust spatial reasoning and superior performance in low-frequency decision-making scenarios compared to traditional reinforcement learning methods.We successfully validated this foundational model and identified its inference latency as a key challenge.These results establish a solid basis for our future work.This includes developing a "brain-cerebellum" hybrid architecture for real-time performance and exploring multi-robot social compliance.This research contributes to HRI by creating more predictable and trustworthy robots, and to the LLM field by investigating the symbol grounding problem through embodied intelligence.

Due to global climate change, developing robust and accurate disaster prediction systems has become essential worldwide, as severe disasters are increasingly occurring even in previously safe regions.Two key technical challenges in disaster prediction are data scarcity and regional heterogeneity.Disasters are rare and extreme, resulting in limited data, which hinders data-driven approaches like machine learning (ML).Moreover, hydro-meteorological disasters depend on region-specific factors such as rainfall patterns, soil, vegetation, and infrastructure.These, combined with dynamic environmental changes from earthquakes, climate, and urbanization, complicate the generalization of models across time and space.We propose a self-adaptive physics-hybrid disaster prediction system that autonomously adapts to diverse and evolving environments to address this.Our system consists of: (1) a physics-hybrid disaster prediction model integrating physics-based hydro-meteorological simulation and multi-modal ML models, and (2) an environmental adaptation utilizing test-time adaptation (TTA) to update parameters without labeled disaster data(i.e., disaster event data).Our physics-hybrid model is anchored in the physics model to balance stability and adaptability, leveraging strengths from both physics and ML models.Furthermore, the strong inductive bias of the physics model mitigates overfitting and catastrophic forgetting during TTA, enabling robust adaptation to unseen regions.

Electric scooters (e-scooters) are reshaping urban mobility, providing eco-friendly and cost-effective transport.However, the surge in their usage in mixed-traffic environments poses significant safety risks, especially for vulnerable road users (VRUs).This paper presents a lightweight vision-based safety assistance system optimized for real-time inference on edge devices.The core modules include semantic segmentation enhanced by semi-supervised learning, accurate bird's-eye view (BEV) transformation, real-time motion prediction, and adaptive path planning.Extensive evaluations demonstrate high segmentation accuracy and low-latency execution suitable for resource-constrained hardware.Future research directions include knowledge distillation for model adaptability, cooperative multi-scooter perception, intersection-based AI infrastructure, and the application of large language models (LLMs) to optimize urban traffic flows.

Accurate monitoring of indoor environments via wireless sensing is essential for applications such as adaptive crowd flow control, energy management in smart buildings, and rapid response in healthcare and emergency scenarios.Traditional vision-based methods suffer from lighting issues, occlusion, and privacy concerns, while RSSI-based approaches are vulnerable to multipath fading and device inconsistencies, and CSI-based systems lack interoperability.We present a device-free and device-independent framework that continuously records round-trip signal delays as a rich time series, supporting both occupancy estimation and spatial localization without specialized hardware.A deep feature extraction strategy suppresses environmental noise and non-line-of-sight distortions, delivering accurate real-time performance on commodity WiFi equipment even in cluttered spaces.This approach establishes a foundation for ubiquitous privacy-preserving indoor environment monitoring with potential extensions to multimodal sensor fusion and integration with next-generation wireless standards.

Accurate taxi-demand prediction is essential for optimizing taxi operations and enhancing urban transportation services. However, using customers' data in these systems raises significant privacy and security concerns. Traditional federated learning addresses some privacy issues by enabling model training without direct data exchange but often struggles with accuracy due to varying data distributions across different regions or service providers. In this paper, we propose CC-Net: a novel approach using collaborative learning enhanced with contrastive learning for taxi-demand prediction. Our method ensures high performance by enabling multiple parties to collaboratively train a demand-prediction model through hierarchical federated learning. In this approach, similar parties are clustered together, and federated learning is applied within each cluster. The similarity is defined without data exchange, ensuring privacy and security. We evaluated our approach using real-world data from five taxi service providers in Japan over fourteen months. The results demonstrate that CC-Net maintains the privacy of customers' data while improving prediction accuracy by at least 2.2% compared to existing techniques.

Indoor localization has become a critical area of research with increasing relevance in applications. While numerous technologies have been explored, WiFi-based fingerprinting solutions using Received Signal Strength Indicators from multiple access points have garnered substantial attention due to the ubiquity of WiFi networks. However, these methods often encounter challenges, including fluctuation of access points and their noise signal measurements. Furthermore, they struggle to adapt effectively to cluttered or dynamically changing environments. In this paper, we introduce GraphLy: a Graph Neural Network-based model explicitly designed to tackle these challenges. GraphLy captures complex spatial relationships between different locations and adapts to environmental complexities and clutter, offering a robust solution for indoor localization. Our experiments demonstrate that GraphLy outperforms state-of-the-art WiFi-based localization techniques in two cluttered and propagation complex testbeds. In particular, we achieved a performance improvement of at least 37% and 65% in the two environments, respectively. These findings underscore the potential of GraphLy to enhance indoor localization accuracy and reliability for various real-world applications.

The growing demand for ride-hailing services has led to an increasing need for accurate taxi demand prediction. Existing systems are limited to specific regions, lacking generalizability to unseen areas. This paper presents a novel taxi demand forecasting system that leverages a graph neural network to capture spatial dependencies and patterns in urban environments. Additionally, the proposed system employs a region-neutral approach, enabling it to train a model that can be applied to any region, including unseen regions. To achieve this, the framework incorporates the power of Variational Autoencoder to disentangle the input features into region-specific and region-neutral components. The region-neutral features facilitate cross-region taxi demand predictions, allowing the model to generalize well across different urban areas. Experimental results demonstrate the effectiveness of the proposed system in accurately forecasting taxi demand, even in previously unobserved regions, thus showcasing its potential for optimizing taxi services and improving transportation efficiency on a broader scale.

The growing demand for ride-hailing services has led to an increasing need for accurate taxi demand prediction. However, the use of real passenger data to train predictive models raises serious privacy concerns. To address this challenge, we present a privacy-preserving taxi demand prediction system that employs a generative model to synthesize synthetic trajectory data, preserving privacy while retaining the statistical properties of the original data. The system also overcomes the challenge of location dependence of latitude-longitude values by encoding the representation into region-independent space, making it more general and applicable to different geographical areas. The system was evaluated on real-world data collected from a major taxi service provider in Japan over a period of six months. The results showed that the system can effectively defend against 98% of all attempted attacks on passenger data and against 60% of state-of-the-art attacks on the learning-based prediction models. Additionally, the proposed system ensures the prediction performance, with a barely noticeable decrease of 2.9% compared to using the original data.

The increasing use of trajectory data and machine learning has advanced our understanding of human behavior. Specifically, in situations such as team sports, in which multiple players form a group and interact with each other, predicting performance using their trajectory data as input has been attracting attention. However, understanding the role and contributions of individuals in the group by a deep understanding of the whole trajectory has not yet been well-investigated. In this study, we propose a method to quantitatively evaluate the single player’s contribution based on a deep learning model that predicts shooting success from the trajectory data of all players and a ball, leveraging official data of a professional basketball league. We use the difference of two output values by the prediction model when the trajectory data of the target player is given or not given as the model inputs. Our evaluation using the professional basketball dataset for one season confirmed that the predictive model had an accuracy of AUC=0.92. We also confirmed that the scoring contribution of each player calculated from this predictive model was significantly correlated with an existing player’s overall performance metric (R = 0.37, p < 0.001). The results suggest that our proposed method could be a new method to quantify a player's contribution to the team performance from trajectory data only instead of conventional experience-based player performance metrics.

In this demonstration paper, we present STM: a new system for securing and management of vehicle trajectory data using a generative model that balances privacy and utility. For instance, traditional methods for taxi-demand prediction pose the risk of privacy breaches from both the data and the model. To address this challenge, we deploy Spatiotemporal-GAN to generate synthetic trajectories that meet privacy regulations such as GDPR. We assess the quality of the generated data by constructing several taxi-demand prediction models. Moreover, we evaluate the privacy risk by implementing trajectory user linking attacks against the generated data and membership inference attacks against the prediction model. Our system is designed with rich interactivity and visualization, enabling the audience to use these modules. Overall, our approach demonstrates the potential of generative models in preserving privacy while maintaining data utility in the context of taxi-demand prediction.

Taxi demand prediction is an essential process for enabling efficient taxi operations and customer satisfaction. However, most existing solutions are vulnerable to leakage of passengers' privacy or membership inference attack. In this study, we propose a privacy-preserving taxi-demand system built without real customer data. Specifically, we employ LSTM-GANs to generate synthetic trajectories reflecting the typical Spatio-temporal semantics of the original data without privacy leakage. The system evaluation was held on a real taxi service provider in Japan for six months. The results show the ability of the system to keep privacy with 86% of the cases with barely a negligible decrease in the prediction performance compared to using the original data.

Location-based services have undergone massive improvements over the last decade. Despite intense efforts in industry and academia, a pervasive infrastructure-free localization is still elusive. Towards making this possible, cellular-based systems have recently been proposed due to the wide-spread availability of the cellular networks and their support by commodity cellphones. However, these systems only consider locating the user in a 2D single floor environment, which reduces their value when used in multi-story buildings.

Robust and accurate indoor localization has been the goal of several research efforts over the past decade. Towards achieving this goal, WiFi fingerprinting-based indoor localization systems have been proposed. However, fingerprinting involves significant effort; especially when done at high density; and needs to be repeated with any change in the deployment area. While a number of recent systems have been introduced to reduce the calibration effort, these still trade overhead with accuracy.

We present PassActiv, a mobile sensing system for the automatic activity recognition of railway passengers. Our key observations show that certain passengers' activities (e.g., purchasing tickets, etc) present identifiable signatures on one or more cell-phone sensors which can be leveraged to automatically recognize those activities. Evaluation of PassActiv through a field experiment in major train and subway stations in Japan shows that PassActiv can detect different activities accurately with at most 3% false positive rate and 4% false negative rate for all types of passengers' activities.

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 paper, we propose an application layer multicast protocol called Emma/QoS. Emma/QoS manages multiple multicast video streaming flows in a fully distributed manner so that the user gain in receiving those flows can be maximized. Emma/QoS assumes that each end-host is capable of filtering streaming flows when relaying them to the other end-hosts. Using this functionality, Emma/QoS (a) accommodates a request of a new video source by degrading the bit-rates of the existing video streams, and (b) adjusts their transmission rates according to given user benefit functions, which can be application-specific. Simulation results have shown the efficiency of Emma/QoS.

In this paper, we evaluate the performance of real-time data transmission by our routing protocol GVGrid. In Ref. [5], we have presented GVGrid, a position-based routing protocol for multi-hop mobile ad hoc networks constructed by vehicles. GVGrid constructs a route on demand from a source (a fixed node or a station) to vehicles that exist in a destination region. The experimental results have shown that GVGrid could achieve high quality data transmission in a region of a medium and high density of vehicles.