arXiv subjects

Noboru Koshizuka

Publications and source records attributed to Noboru Koshizuka.

18 recordsLinked to original sources

arXiv2026

Cyberspace Search Intentions as Leading Indicators for Proactive Traffic Hotspot Detection

This study proposes a cyber-physical data-driven framework for proactive detection of highway traffic hotspots and hot regions. The proposed framework bridges users' online search records in cyberspace as early indicator. To handle large-scale and irregular search records, we propose an Origin Destination Time (ODT) tensor model to represent the spatio-temporal structure of route search data and accelerate computation. Using destination-wise inflow sequences derived from these records, we develop a systematic method to automatically identify anomalous surges that indicate emerging traffic hotspots and further the regions. To validate the framework, we conduct experiments using a one-year real-world dataset covering 2,728 interchange (IC) nodes within a highway network. Furthermore, we integrate and compare search data with actual traffic volumes for evaluation. The results reveal a strong correlation between search intensity and traffic flow, demonstrating that online search behavior serves as a reliable proxy for anticipating traffic dynamics. These findings suggest that route search records in cyberspace can be effectively utilized for proactive traffic monitoring and highlight the potential for early prediction of congestion patterns.

cs.NI↗

arXiv2026

Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven Agent

Individual-level mobility prediction is central to urban simulation, transportation planning, and policy analysis. Supervised sequence models achieve strong accuracy but require task-specific training and offer limited decision-level transparency. Recent LLM-based methods improve interpretability, yet mostly rely on static prompts and single-pass inference, limiting their ability to seek additional evidence when mobility signals are weak or conflicting. We propose \method{}, a training-free LLM-driven agent framework that formulates next-location prediction as adaptive evidence-controlled decision making. \method{} resolves routine cases through a fast path based on historical regularity, while ambiguous cases trigger iterative tool use over recent trajectories, historical behavior, stay-move likelihood, and geographical evidence. Across three mobility datasets, AgentMob achieves the strongest overall performance among training-free LLM-based methods, with GPT-5.4 reaching 71.42\% Acc@1 on BW, 33.14\% on YJMob100K, and 33.50\% on Shanghai ISP. On BW non-fast-path cases, the LLM controller improves Acc@1 from 30.65\% to 48.62\% over a same-tool statistical baseline, showing that its main benefit lies in resolving ambiguous predictions through adaptive evidence gathering. Our code is available at https://github.com/Unknown-zoo/AgentMob.

cs.LG↗

arXiv2026

TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models

The importance of mobile phone GPS trajectory data is widely recognized across many fields, yet the use of real data is often hindered by privacy concerns, limited accessibility, and high acquisition costs. As a result, generating pseudo-GPS trajectory data has become an active area of research. Recent diffusion-based approaches have achieved strong fidelity but remain limited in spatial scale (small urban areas), transportation-mode diversity, and efficiency (requiring numerous sampling steps). To address these challenges, we introduce TrajFlow, which to the best of our knowledge is the first flow-matching-based generative model for GPS trajectory generation. TrajFlow leverages the flow-matching paradigm to improve robustness and efficiency across multiple geospatial scales, and incorporates a trajectory harmonization and reconstruction strategy to jointly address scalability, diversity, and efficiency. Using a nationwide mobile phone GPS dataset with millions of trajectories across Japan, we show that TrajFlow or its variants consistently outperform diffusion-based and deep generative baselines at urban, metropolitan, and nationwide levels. As the first nationwide, multi-scale GPS trajectory generation model, TrajFlow demonstrates strong potential to support inter-region urban planning, traffic management, and disaster response, thereby advancing the resilience and intelligence of future mobility systems.

cs.LG↗

arXiv2026

TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer

Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research introduces a transformative framework for generating large-scale urban mobility trajectories, employing a novel application of a transformer-based model pre-trained and fine-tuned through a two-phase process. Initially, trajectory generation is conceptualized as an offline reinforcement learning (RL) problem, with a significant reduction in vocabulary space achieved during tokenization. The integration of Inverse Reinforcement Learning (IRL) allows for the capture of trajectory-wise reward signals, leveraging historical data to infer individual mobility preferences. Subsequently, the pre-trained model is fine-tuned using the constructed reward model, effectively addressing the challenges inherent in traditional RL-based autoregressive methods, such as long-term credit assignment and handling of sparse reward environments. Comprehensive evaluations on multiple datasets illustrate that our framework markedly surpasses existing models in terms of reliability and diversity. Our findings not only advance the field of urban mobility modeling but also provide a robust methodology for simulating urban data, with significant implications for traffic management and urban development planning. The implementation is publicly available at https://github.com/Wangjw6/TrajGPT_R.

cs.LG↗

arXiv2026

Place with Intention: An Empirical Attendance Predictive Study of Expo 2025 Osaka, Kansai, Japan

Accurate forecasting of daily attendance is vital for managing transportation, crowd flows, and services at large-scale international events such as Expo 2025 Osaka, Kansai, Japan. However, existing approaches often rely on multi-source external data (such as weather, traffic, and social media) to improve accuracy, which can lead to unreliable results when historical data are insufficient. To address these challenges, we propose a Transformer-based framework that leverages reservation dynamics, i.e., ticket bookings and subsequent updates within a time window, as a proxy for visitors' attendance intentions, under the assumption that such intentions are eventually reflected in reservation patterns. This design avoids the complexity of multi-source integration while still capturing external influences like weather and promotions implicitly embedded in reservation dynamics. We construct a dataset combining entrance records and reservation dynamics and evaluate the model under both single-channel (total attendance) and two-channel (separated by East and West gates) settings. Results show that separately modeling East and West gates consistently improves accuracy, particularly for short- and medium-term horizons. Ablation studies further confirm the importance of the encoder-decoder structure, inverse-style embedding, and adaptive fusion module. Overall, our findings indicate that reservation dynamics offer a practical and informative foundation for attendance forecasting in large-scale international events.

cs.LG↗

arXiv2025

Realizing Space-oriented Control in Smart Buildings via Word Embeddings

This paper presents a novel framework for implementing space-oriented control systems in smart buildings. In contrast to conventional device-oriented approaches, which often suffer from issues related to development efficiency and portability, our framework adopts a space-oriented paradigm that leverages natural language processing and word embedding techniques. The proposed framework features a chat-based graphical user interface (GUI) that converts natural language inputs into actionable OpenAI API calls, thereby enabling intuitive space level (e.g., room) control within smart environments. To support efficient embedding-based search and metadata retrieval, the framework integrates a vector database powered by Elasticsearch. This ensures the accurate identification and invocation of appropriate smart building APIs. A prototype implementation has been tested in a smart building environment at the University of Tokyo, demonstrating the feasibility of the approach.

eess.SY↗

arXiv2025

A Proposal for High-Level Architectural Model Capable of Expressing Various Data Collaboration Platform and Data Space Concepts

This paper proposes "Data Space High-Level Architecture Model" (DS-HLAM) for expressing diverse data collaboration platforms across regional implementations. The framework introduces mathematically rigorous definitions with success conditions formalized through finite state automata theory, enabling interoperability while preserving digital sovereignty requirements.

cs.DC↗

arXiv2025

Origin-Destination Extraction from Large-Scale Route Search Records for Tourism Trend Analysis

This paper presents a novel method for transforming large-scale historical expressway route search records into a three-dimensional (3D) Origin-Destination (OD) map, enabling data compression, efficient spatiotemporal sampling and statistical analysis. The study analyzed over 380 million expressway route search logs to investigate online search behavior related to tourist destinations. Several expressway interchanges (ICs) near popular attractions, such as those associated with spring flower viewing, autumn foliage and winter skiing, are examined and visualized. The results reveal strong correlations between search volume trends and the duration of peak tourism seasons. This approach leverages cyberspace behavioral data as a leading indicator of physical movement, providing a proactive tool for traffic management and tourism planning.

cs.CY↗

arXiv2025

Simulation of Emergency Evacuation in Large Scale Metropolitan Railway Systems for Urban Resilience

This paper presents a simulation for traffic evacuation during railway disruptions to enhance urban resilience. The research focuses on large-scale railway networks and provides flexible simulation settings to accommodate multiple node or line failures. The evacuation optimization model is mathematically formulated using matrix computation and nonlinear programming. The simulation integrates railway lines operated by various companies, along with external geographical features of the network. Furthermore, to address computational complexity in large-scale graph networks, a subgraph partitioning solution is employed for computation acceleration. The model is evaluated using the extensive railway network of Greater Tokyo. Data collection included both railway network structure and real-world GPS footfall data to estimate the number of station-area visitors for simulation input and evaluation purposes. Several evacuation scenarios were simulated for major stations including Tokyo, Shinjuku, Shibuya and so on. The results demonstrate that both evacuation passenger flow (EPF) and average travel time (ATT) during emergencies were successfully optimized, while remaining within the capacity constraints of neighboring stations and the targeted disruption recovery times.

eess.SY↗

arXiv2025

Deep Unfolding for MIMO Signal Detection

In this paper, we propose a deep unfolding neural network-based MIMO detector that incorporates complex-valued computations using Wirtinger calculus. The method, referred as Dynamic Partially Shrinkage Thresholding (DPST), enables efficient, interpretable, and low-complexity MIMO signal detection. Unlike prior approaches that rely on real-valued approximations, our method operates natively in the complex domain, aligning with the fundamental nature of signal processing tasks. The proposed algorithm requires only a small number of trainable parameters, allowing for simplified training. Numerical results demonstrate that the proposed method achieves superior detection performance with fewer iterations and lower computational complexity, making it a practical solution for next-generation massive MIMO systems.

cs.LG↗

arXiv2025

Happiness Finder: Exploring the Role of AI in Enhancing Well-Being During Four-Leaf Clover Searches

A four-leaf clover (FLC) symbolizes luck and happiness worldwide, but it is hard to distinguish it from the common three-leaf clover. While AI technology can assist in searching for FLC, it may not replicate the traditional search's sense of achievement. This study explores searcher feelings when AI aids the FLC search. In this study, we developed a system called ``Happiness Finder'' that uses object detection algorithms on smartphones or tablets to support the search. We exhibited HappinessFinder at an international workshop, allowing participants to experience four-leaf clover searching using potted artificial clovers and the HappinessFinder app. This paper reports the findings from this demonstration.

cs.HC↗

arXiv2025

Causality-Aware Next Location Prediction Framework based on Human Mobility Stratification

Human mobility data are fused with multiple travel patterns and hidden spatiotemporal patterns are extracted by integrating user, location, and time information to improve next location prediction accuracy. In existing next location prediction methods, different causal relationships that result from patterns in human mobility data are ignored, which leads to confounding information that can have a negative effect on predictions. Therefore, this study introduces a causality-aware framework for next location prediction, focusing on human mobility stratification for travel patterns. In our research, a novel causal graph is developed that describes the relationships between various input variables. We use counterfactuals to enhance the indirect effects in our causal graph for specific travel patterns: non-anchor targeted travels. The proposed framework is designed as a plug-and-play module that integrates multiple next location prediction paradigms. We tested our proposed framework using several state-of-the-art models and human mobility datasets, and the results reveal that the proposed module improves the prediction performance. In addition, we provide results from the ablation study and quantitative study to demonstrate the soundness of our causal graph and its ability to further enhance the interpretability of the current next location prediction models.

cs.LG↗

arXiv2025

A Traffic Evacuation Model for Enhancing Resilience During Railway Disruption

This paper introduces a traffic evacuation model for railway disruptions to improve resilience. The research focuses on the problem of failure of several nodes or lines on the railway network topology. We proposed a holistic approach that integrates lines of various operator companies as well as external geographical features of the railway system. The optimized evacuation model was mathematically derived based on matrix computation using nonlinear programming. The model also takes into account the capacity of the surrounding evacuation stations, as well as the travel cost. Moreover, our model can flexibly simulate disruptions at multiple stations or any number of stations and lines, enhancing its applicability. We collected the large-scale railway network of the Greater Tokyo area for experimentation and evaluation. We simulated evacuation plans for several major stations, including Tokyo, Shinjuku, and Shibuya. The results indicate that the evacuation passenger flow (EPF) and the average travel time (ATT) during emergencies were optimized, staying within both the capacity limits of the targeted neighboring stations and the disruption recovery time.

math.NA↗

arXiv2025

CausalMob: Causal Human Mobility Prediction with LLMs-derived Human Intentions toward Public Events

Large-scale human mobility exhibits spatial and temporal patterns that can assist policymakers in decision making. Although traditional prediction models attempt to capture these patterns, they often interfered by non-periodic public events, such as disasters and occasional celebrations. Since regular human mobility patterns are heavily affected by these events, estimating their causal effects is critical to accurate mobility predictions. Although news articles provide unique perspectives on these events in an unstructured format, processing is a challenge. In this study, we propose a causality-augmented prediction model, called CausalMob, to analyze the causal effects of public events. We first utilize large language models (LLMs) to extract human intentions from news articles and transform them into features that act as causal treatments. Next, the model learns representations of spatio-temporal regional covariates from multiple data sources to serve as confounders for causal inference. Finally, we present a causal effect estimation framework to ensure event features remain independent of confounders during prediction. Based on large-scale real-world data, the experimental results show that the proposed model excels in human mobility prediction, outperforming state-of-the-art models.

cs.LG↗

arXiv2024

FRTP: Federating Route Search Records to Enhance Long-term Traffic Prediction

Accurate traffic prediction, especially predicting traffic conditions several days in advance is essential for intelligent transportation systems (ITS). Such predictions enable mid- and long-term traffic optimization, which is crucial for efficient transportation planning. However, the inclusion of diverse external features, alongside the complexities of spatial relationships and temporal uncertainties, significantly increases the complexity of forecasting models. Additionally, traditional approaches have handled data preprocessing separately from the learning model, leading to inefficiencies caused by repeated trials of preprocessing and training. In this study, we propose a federated architecture capable of learning directly from raw data with varying features and time granularities or lengths. The model adopts a unified design that accommodates different feature types, time scales, and temporal periods. Our experiments focus on federating route search records and begin by processing raw data within the model framework. Unlike traditional models, this approach integrates the data federation phase into the learning process, enabling compatibility with various time frequencies and input/output configurations. The accuracy of the proposed model is demonstrated through evaluations using diverse learning patterns and parameter settings. The results show that online search log data is useful for forecasting long-term traffic, highlighting the model's adaptability and efficiency.

cs.AI↗

arXiv2024

Time-Probability Dependent Knowledge Extraction in IoT-enabled Smart Building

Smart buildings incorporate various emerging Internet of Things (IoT) applications for comprehensive management of energy efficiency, human comfort, automation, and security. However, the development of a knowledge extraction framework is fundamental. Currently, there is a lack of a unified and practical framework for modeling heterogeneous sensor data within buildings. In this paper, we propose a practical inference framework for extracting status-to-event knowledge within smart building. Our proposal includes IoT-based API integration, ontology model design, and time probability dependent knowledge extraction methods. The Building Topology Ontology (BOT) was leveraged to construct spatial relations among sensors and spaces within the building. We utilized Apache Jena Fuseki's SPARQL server for storing and querying the RDF triple data. Two types of knowledge could be extracted: timestamp-based probability for abnormal event detection and time interval-based probability for conjunction of multiple events. We conducted experiments (over a 78-day period) in a real smart building environment. The data of light and elevator states has been collected for evaluation. The evaluation revealed several inferred events, such as room occupancy, elevator trajectory tracking, and the conjunction of both events. The numerical values of detected event counts and probability demonstrate the potential for automatic control in the smart building.

cs.IR↗

arXiv2024

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation

This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and effective personal mobility generation. LLMs overcome the limitations of previous models by effectively processing semantic data and offering versatility in modeling various tasks. Our approach addresses three research questions: aligning LLMs with real-world urban mobility data, developing reliable activity generation strategies, and exploring LLM applications in urban mobility. The key technical contribution is a novel LLM agent framework that accounts for individual activity patterns and motivations, including a self-consistency approach to align LLMs with real-world activity data and a retrieval-augmented strategy for interpretable activity generation. We evaluate our LLM agent framework and compare it with state-of-the-art personal mobility generation approaches, demonstrating the effectiveness of our approach and its potential applications in urban mobility. Overall, this study marks the pioneering work of designing an LLM agent framework for activity generation based on real-world human activity data, offering a promising tool for urban mobility analysis.

cs.AI↗

arXiv2023

Efficient Compressed Ratio Estimation Using Online Sequential Learning for Edge Computing

Owing to the widespread adoption of the Internet of Things, a vast amount of sensor information is being acquired in real time. Accordingly, the communication cost of data from edge devices is increasing. Compressed sensing (CS), a data compression method that can be used on edge devices, has been attracting attention as a method to reduce communication costs. In CS, estimating the appropriate compression ratio is important. There is a method to adaptively estimate the compression ratio for the acquired data using reinforcement learning (RL). However, the computational costs associated with existing RL methods that can be utilized on edges are often high. In this study, we developed an efficient RL method for edge devices, referred to as the actor--critic online sequential extreme learning machine (AC-OSELM), and a system to compress data by estimating an appropriate compression ratio on the edge using AC-OSELM. The performance of the proposed method in estimating the compression ratio is evaluated by comparing it with other RL methods for edge devices. The experimental results indicate that AC-OSELM demonstrated the same or better compression performance and faster compression ratio estimation than the existing methods.

cs.LG↗