Human activity recognition (HAR) in industrial domains is important for workflow optimization, throughput estimation, and bottleneck detection. Skeleton-based models achieve high HAR accuracy by exploiting rich spatial and temporal cues, but they are difficult to deploy in industrial sites due to occlusions, camera placement, and privacy concerns. IMU sensors, especially smartwatches, are practical for deployment but lack spatial awareness, resulting in weaker performance. This work aims to enable robust HAR using only a wrist-worn IMU by distilling knowledge from richer modalities. Knowledge distillation allows transferring information from a skeleton teacher to a single-IMU student, but the large modality gap has limited the success of prior teacher–student approaches. To address this issue, we propose a teacher-assistant-student (TAS) learning framework, in which a multi-IMU assistant model bridges the skeleton-based teacher and the single-IMU student. To support TAS, we develop the following techniques: (i) Dense temporal Contrastive Learning, aligning structural representations of skeleton and IMU segments; (ii) Spatial Relationship Learning, guiding models to capture spatial priors from skeleton data; and (iii) Temporal Attention Transfer, distilling attention patterns for key atomic actions. We further boost the robustness to behavioral variation with motion-guided IMU data diversification using physics-based simulation. Experiments on industrial HAR sensor data show that our framework consistently improves single-IMU recognition across diverse operational scenarios, highlighting its potential for practical deployment.

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 prediction system, harnessing the strengths of multiview graph neural networks to capture spatial-temporal dependencies and patterns in urban environments. Additionally, the proposed systemCROSS-Netemploys a spatially transferable approach, enabling it to train a model that can be deployed to previously unseen regions. To achieve this, the framework incorporates the power of a Variational Autoencoder to disentangle the input features into region-specific and region-agnostic components. The region-agnostic features facilitate cross-region taxi demand predictions, allowing the model to generalize well across different urban areas. Experimental results demonstrate the effectiveness ofCROSS-Netin 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.

Indoor localization of Unmanned Vehicles is critical for tasks requiring low latency and low power consumption. Channel State Information (CSI) systems provide a promising approach by capturing fine-grained signal features, but often suffer from limited accuracy in complex environments or high computational cost. To address this, we propose MambaLoc, an indoor localization framework that balances efficiency and precision by leveraging Mamba architectures with cross-modal knowledge distillation. In offline training, a Transformer based on Ultra-Wideband (UWB) data acts as a teacher to guide the CSI-based Mamba student, improving robustness to multipath effects without relying on UWB during inference. The distillation process is further enhanced using a Gaussian Mixture Model (GMM) in both teacher and student, enabling effective transfer of UWB-derived spatial representations. Evaluations on real-world environments show that MambaLoc reduces MAE by 22.53% over a baseline Mamba, while cutting FLOPs by 65.1% and inference time by 58% compared to a Transformer model, making it a practical and deployable solution for UV localization.

Despite significant advances in autonomous driving, cross-city deployment remains challenging due to variations in traffic patterns, urban driving environments, and local regulations that require expensive retraining for each new location. Existing end-to-end driving systems trained on specific cities exhibit poor generalization when deployed elsewhere, limiting scalability. In this paper, we propose GeoDrive, a meta-learning framework that enables rapid adaptation to new cities with minimal local data. We combine Model-Agnostic Meta-Learning (MAML) with spatial context from OpenStreetMap to learn generalized driving policies that rapidly adapt to city-specific traffic dynamics. GeoDrive integrates a Large Language Model (LLM) module for interpretable decision-making that incorporates region-specific regulations and behavioral patterns. Experimental results show 18% and 32% improvements in trajectory prediction for intra-city and cross-city settings, respectively.

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 paper presents a privacy-preserving monitoring system for elderly individuals living alone, utilizing collaborative lightweight Large Language Model (LLM) agents deployed on edge devices. The system integrates non-invasive sensors with a novel three-agent architecture: an activity recognition agent processes sensor data, an hourly summarization agent generates intermediate reports in 3-hour segments, and a daily summarization agent produces comprehensive summaries. Our evaluation on real-world data from two elderly households demonstrates that the system achieves 95.8% accuracy in activity recognition and generates natural language summaries comparable to GPT-4o, while maintaining privacy through local processing on affordable Raspberry Pi hardware. The results indicate that our approach effectively balances monitoring accuracy, summary quality, and practical deployment constraints, making it suitable for widespread adoption in elderly care applications.

This paper presents a novel autonomous navigation framework that integrates Large Language Models (LLMs) with multimodal sensor fusion to enable dynamic obstacle avoidance and human-aware path planning in diverse environments. The proposed system leverages an FPGA-accelerated fusion pipeline, combining LiDAR and vision data for real-time perception. A Hungarian algorithm-based object matching technique ensures robust tracking, while a bird's-eye view (BEV) representation enhances spatial reasoning and occlusion handling. The fused sensory inputs are processed by a fine-tuned LLM, which contextualizes pedestrian behavior and environmental constraints to generate adaptive, human-centric navigation strategies. Unlike traditional rule-based methods, LLMs provide generalization capabilities to novel scenarios, significantly improving interaction with vulnerable pedestrians such as children, elderly individuals, and wheelchair users. Extensive evaluations in both simulated and real-world scenarios confirm the system's ability to reduce collisions and enhance navigation efficiency in high-density environments. By bridging semantic reasoning and robotic control, this work lays the foundation for next-generation intelligent navigation systems that are both safety-aware and scalable across autonomous platforms.

Schistosomiasis remains a significant public health challenge in Africa, where it is considered endemic, particularly in areas with inadequate access to clean water. This study focuses on mitigating the spread of schistosomiasis by monitoring the physicochemical parameters of water sources to detect the proliferation of infected snails, which serve as the intermediate host for the parasite. We propose a system that leverages sensing technology to monitor water physicochemical parameters, e.g., temperature (Temp), pH, and electrical conductivity (EC) and uses AI to predict their future values, alongside the dynamics of the infected snail population, which are crucial for schistosomiasis transmission. By forecasting these trends, the system facilitates proactive interventions, such as water treatment and sanitation improvements. To accomplish this, we leverage FNet, a model that effectively captures temporal features through discrete Fourier transforms (DFT), delivering Transformer-level accuracy while being more resource-efficient. While FNet is originally tailored for language processing tasks, we adapt it for time series analysis by employing a quantization technique. This approach is particularly advantageous in contexts where computational and operational efficiency is critical, making it well-suited for environments with limited infrastructure or financial flexibility. Our evaluation demonstrates that the FNet model outperforms transformers in terms of resource efficiency while maintaining similar performance, making it a promising tool for real-time monitoring and early detection of schistosomiasis risk. The results highlight the potential of this approach to enhance disease control efforts and contribute to improved public health outcomes in endemic regions.

Digital Twins (DTs) are rapidly emerging as a transformative paradigm for real-time monitoring, simulation, and decision-making across domains such as smart mobility, industrial automation, and intelligent infrastructure. However, current DT implementations often rely on computationally intensive deep learning pipelines and vision-based sensing, which hinder their deployment in resource-constrained or privacy-sensitive environments. In this work, we introduce RadarVision-Twin, a lightweight, interpretable, and edge-deployable Digital Twin system that fuses mmWave radar and RGB camera inputs for real-time anomaly detection and feedback-driven visualization. Unlike traditional camera-centric systems, RadarVision-Twin leverages radar spectrograms to extract motion energy and camera frames to estimate edge density—two physically meaningful features that capture dynamic behavior and scene structure, respectively. These features are fused and fed into an XGBoost classifier, chosen for its efficiency and explainability, to detect motion anomalies in real-time. Our system supports synchronized multimodal visualization, live anomaly flagging, and operator feedback, forming a closed-loop DT that evolves with its environment. We validate our approach on a large-scale multimodal dataset comprising over 14,000 radar-camera frames, demonstrating that our fusion strategy achieves macro F1-scores of 98%, surpassing unimodal baselines. Furthermore, the system runs at low latency on commodity hardware and requires no GPU acceleration, making it suitable for embedded or edge deployments. By eliminating the need for deep models while maintaining interpretability and responsiveness, RadarVisionTwin paves the way for transparent, low-power, and privacy-aware Digital Twins in future 6G-enabled environments.

This paper introduces a novel approach for coordinated evacuation route planning during disasters, focusing on guiding groups of individuals-such as families or neigh-bors-who are spatially separated but socially connected. Recognizing the importance of group cohesion during evacuations, we designed and implemented a prototype system, which was validated through a real-world evacuation drill conducted in Kobe City during the 30th memorial year of the Great HanshinEarthquake. We introduce and formulate a new problem, termed the ‘Evacuation Routing Problem’ (ERP), using integer linear programming (ILP). Our system recommends that group members rendezvous at specific points along their evacuation routes. The core idea is to model each evacuation route as a tree on a predefined road network, where the leaves correspond to evacuees (group members) and the root corresponds to the shelter. This problem can be viewed as a variant of the Steiner Tree Problem, augmented with an additional constraint to ensure that members of a group meet at an optimal rendezvous node while en route to the shelter. To validate our method, we conducted a pilot experiment in Kobe City, Japan. We developed a prototype system featuring a web-based interface that generates high-quality evacuation routes derived from ILP solutions. The experiment involved two family groups, and the developed system navigated a real road network that included various points of interest such as parks, shopping malls, offices, and schools. The results showed that one family successfully gathered at the proposed rendezvous point and evacuated together, while the other group was unable to meet due to a suggested detour. Drawing from these experimental outcomes and user feedback, we analyze system limitations and discuss potential improvements from a user-centric perspective.

Accurate indoor positioning is essential for mobile computing, human-computer interaction, and next-generation smart environments, enabling applications in indoor navigation, augmented reality, personalized services, healthcare, and emergency response. Cellular signal fingerprinting has emerged as a widely adopted solution, with deep learning models achieving state-of-the-art performance. However, existing approaches face critical deployment challenges, including labor-intensive fingerprinting, sparse reference points, and missing RSS values caused by environmental interference, hardware variability, and dynamic signal fluctuations. These limitations hinder their scalability, adaptability, and real-world usability in complex indoor environments. To address these challenges, we present GPT2Loc a novel indoor localization framework that integrates LLM with label-aware contrastive learning, improving accuracy while reducing reliance on extensive fingerprinting. LLMs effectively extract meaningful spatial features from incomplete and noisy RSS data, enabling robust localization even in sparsely finger-printed areas. Our label-aware contrastive learning approach further enhances generalization by aligning latent representations with spatial relationships, allowing GPT2Loc to interpolate user locations in unseen areas and mitigate signal inconsistencies.

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.

Electric scooters (e-scooters) are increasingly used in urban areas but face serious safety concerns, especially in mixed traffic environments. This paper presents a real-time vision-based safety assistance system designed for e-scooters and optimized for edge deployment. The system uses a lightweight segmentation model trained via semi-supervised learning to detect sidewalks and road areas from non-vehicle perspectives. Dynamic objects such as pedestrians and cyclists are tracked using Kalman filtering, and potential risks are assessed in real time. A hybrid path planning module uses A* and artificial potential fields to recommend safe forward paths. Experimental results show that the system achieves real-time performance on Jetson Orin NX while improving perception accuracy and navigation safety in sidewalk environments.

Millimeter-Wave radar has emerged as a promising sensing modality for autonomous vehicles due to its robustness in adverse environmental conditions such as fog, rain, and low light. However, traditional radar processing pipelines relying on range-Doppler and angle-of-arrival estimation often produce sparse and noisy outputs, making object detection challenging. In this paper, we propose FouriDAR, a lightweight radar-only object detection network that, for the first time in this domain, applies the Fourier Network architecture for global frequency-domain modeling. By replacing the attention mechanism in Transformer-Based designs with Fourier transforms, our approach captures long-range spatial dependencies with significantly lower computational complexity. In addition, a self-learned MIMO preprocessing pipeline restructures radar input into learnable feature tensors, enhancing angular and Doppler cues for robust detection. Evaluated on the RADIal benchmark, FouriDAR achieves 72.3% average precision and 75.8% recall, outperforming existing radar-only models, while requiring only 1.2M parameters and 3.5 GFLOPs. These results demonstrate that introducing the Fourier Network to radar-based perception, coupled with adaptive MIMO-aware preprocessing, provides a new and efficient foundation for autonomous driving.

Abstract Accurate human counting in indoor environments is essential for optimizing people-centric applications, such as crowd management, disaster response, and monitoring in settings like shopping malls and healthcare facilities. Traditional vision approaches face challenges with poor lighting conditions and raise privacy concerns. WiFi-based solutions enable device-free human counting by detecting disruptions in wireless signals caused by human presence. However, methods using received signal strength indicator are unreliable due to physical obstructions, multipath fading, radio interference, and fluctuating access point power. While WiFi channel state information-based systems are more sensitive to environmental changes, they lack standardization, limiting their practicality. To overcome these limitations, this paper presents Time4Count, an innovative device-free indoor human counting system that leverages round trip time measurements to achieve high accuracy and scalability. Time4Count capitalizes on human-induced fluctuations in signal propagation time to accurately estimate the number of individuals in a space. By employing a multivariate transformer-based feature extraction method, the system effectively mitigates non-line-of-sight errors and signal distortions, ensuring robust performance even in cluttered indoor environments. Additionally, Time4Count integrates spatial discretization and multi-label classification techniques, enabling it to count an unlimited number of individuals in real-time. The system was rigorously evaluated in two realistic, cluttered environments using commodity hardware, involving up to 15 participants. Experimental results reveal that Time4Count achieves an high counting accuracy of 92.7%. To our knowledge, Time4Count is the first RTT-based indoor counting system, providing a precise solution for indoor monitoring. Implementation is available at: https://github.com/mclab-osaka/time4count .

The increasing need for pedestrian tracking within public and commercial domains necessitates innovative solutions that respect privacy concerns. Traditional surveillance methods employing RGB video footage for the monitoring of pedestrian movements have raised significant privacy issues, attributed to their capability to easily identify individuals. This paper shifts focus towards the utilization of 3D point cloud data as a less intrusive alternative for pedestrian monitoring, which inherently minimizes the risk of individual identification. Notwithstanding, traditional tracking methodologies frequently encounter difficulties in environments characterized by high pedestrian density, where occlusions caused by individuals obscuring one another from the sensors’ perspective are commonplace. This research introduces an advanced approach leveraging 3D point cloud data to address the challenges inherent in pedestrian tracking. A particular obstacle addressed is the frequent obstruction caused by pedestrians, who may be accompanied by objects such as baby strollers and/or luggage, thus complicating their detection and tracking when positioned behind others or in close proximity to the sensors. Such scenarios significantly undermine the efficacy of pedestrian segmentation and tracking, particularly in the context of Kalman-Filter-based methodologies. To mitigate these challenges, the proposed solution incorporates a method to spatially enhance the missing segments within the framework of Kalman-Filter-based multi-object tracking. The effectiveness of this approach has been rigorously assessed through the application of 3D point cloud data derived from diverse real-world settings, including laboratory environments, shopping mall entrances, and a densely populated urban area in Kita-ku, Osaka City, during a festival event.

Machine learning and deep learning are becoming more popular in the area of indoor localization leveraging the Wi-Fi Received signal strength demonstrating high performance and scalability. However, such models usually perform poorly in noisy environments, leading to reduced trust in their reliability. In this work, we propose a novel framework that enhances trust in AI-based localization by using explainable AI techniques for automatic real time auditing of model behavior. Our approach detects and corrects any unusual behavior on-the-fly. Experiments in a testbed and two challenging real-world settings demonstrate that our framework effectively stabilizes performance and maintains trust in the localization models.

WiFi-based indoor localization is essential but often hampered by its dependence on specific environments and network configurations. We propose a novel solution using Language Models, like BERT, to overcome these limitations. Our approach transforms WiFi RSSI data into a language-like format, enabling the system to generalize across different buildings and AP setups. Key to our method is the Virtual Space Mapper, which standardizes user and Access Point (AP) locations into a common coordinate system, and then the system adapts BERT to predict locations within this virtual space. This design allows for robust, accurate localization without the need for extensive recalibration. Our results show significant improvements in adaptability and accuracy, making our approach a scalable, flexible alternative to traditional WiFi localization methods.

Indoor localization is critical for enabling a wide range of location-based services such as navigation, security, and contextual computing in complex indoor environments. Despite significant advances, the deployment of indoor localization systems in real-world settings remains limited due to challenges posed by non-independent and identically distributed (non-IID) data and device heterogeneity. In this paper, we propose SimDeep, a novel Federated Learning (FL) framework designed to tackle these challenges. SimDeep introduces a Similarity Aggregation Strategy to aggregate model updates based on client similarity, thereby effectively addressing the non-IID issue. Experimental results demonstrate that SimDeep achieves 92.89% accuracy, outperforming traditional federated and centralized techniques, making it a promising solution for practical deployment.

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.

Human Activity Recognition (HAR) systems hold great potential in aiding disabled and elderly individuals to live independently. Various approaches have been suggested for identifying human activities, including sensors, cameras, wearables, and contactless microwave sensing. This latter method is gaining significant attention due to its ability to address privacy concerns arising from cameras and alleviate discomfort caused by wearables. However, current microwave sensing techniques have a key limitation, requiring controlled and ideal conditions to achieve accurate activity detection. In this paper, we propose RISense, a deep learning-aided system for HAR using Re-configurable Intelligent Surface (RIS). RISense introduces novel modules designed to generate a human activity representational space that ensures separability between activity classes, even in the presence of noisy and distorted Channel State Information (CSI) measurements. These representations are then fed into a Recurrent Neural Network (RNN), which learns the sequential changes in features to accurately estimate the user activity. The evaluation of RISense across two realistic settings, encompassing both non-line-of-sight and multi-floor scenarios, showcases its efficacy. Specifically, RISense achieves an activity recognition accuracy of 98.7%. This performance overcomes the accuracy of state-of-the-art systems by over 15%. These findings highlight the superior efficacy of the proposed methodologies, including integrating RIS and advanced learning 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.

Smartphones have seamlessly integrated into our lives, serving as versatile tools for myriad tasks. Leveraging their ubiquitous presence and advanced sensors, recent research aims to replace costly dedicated hardware with smartphone-based solutions. In this poster, we introduce SmartScale, a novel system that estimates objects' weight using smartphone sensors. Our approach combines the smartphone's accelerometer and vibration motor to form the foundation of our methodology. By orchestrating the interplay between controlled oscillations and motion sensitivity, we detect dynamic responses to varying loads with precision. SmartScale leverages Recurrent Neural Networks to accurately compute mass, eliminating the need for specialized equipment and making weight detection accessible and cost-effective. To validate our approach, we created a dataset of a diverse range of weights across various phone models, achieving a 92% accuracy. This finding not only demonstrates the efficacy of our approach but also emphasizes smartphones' evolution from communication devices to intelligent assistants, reshaping our interaction with the world.

WiFi-based human sensing has exhibited remarkable potential to analyze user behaviors in a non-intrusive and device-free manner. However, most previous works focus on single-user sensing, which has limited practicability in scenarios involving multiple users. In this paper, we introduce YOSO a novel system employing a multi-label multi-view Transformer-based architecture to address these issues, enabling simultaneous localization and activity recognition. By applying advanced preprocessing techniques and utilizing the Transformer's self-attention mechanism, our system effectively learns high-dimensional representations of human activities and locations from CSI data. This approach overcomes traditional sequential data processing limitations, offering precise activity recognition and localization in multiperson environments. Our experimental results showcase superior performance in both localization and activity recognition tasks, surpassing existing methods. The real-time processing capability of our system paves the way for applications in smart environments, security, and healthcare monitoring, providing an efficient tool for situational awareness and advancing wireless sensing technology.

Vehicle recognition approaches have recently gained remarkable interest in improving intelligent transportation systems, especially in harsh weather or insufficient illumination conditions. Vehicle recognition using seismic waves is a novel technique that records the vibrations of vehicles using geophones. Hence, SeismicSense is introduced, a deep learning-based system that is trained using vehicle vibrations. Moreover, the proposed system includes different modules that ensure its robustness against noise. A real data set is collected and leveraged to implement our proposed SeismicSense. Evaluation Results ensure its remarkable accuracy in precise vehicle recognition.

Poster: This study focuses on automatically identifying and classifying objects within indoor environments. Traditional methods struggle with this task due to the high cost of manually labeling each object and the inherent ambiguity of written descriptions. To overcome these limitations, we propose a novel instance segmentation approach that utilizes a visual-language model. This system is trained on extensive indoor environment data, including detailed point clouds (3D representations) and RGB images, readily collected by modern smartphone sensors. By eliminating the need for pre-defined labels, the system allows users to search for items using natural language. We evaluate the system's effectiveness through experiments analyzing performance metrics like accuracy and efficiency with public datasets, demonstrating its practicality and potential usefulness.

Precise disaster prediction plays a critical role in saving lives. Traditional landslide prediction methods have predominantly relied on deep neural networks such as CNNs and LSTMs. However, these methods face two main challenges. The first is the class imbalance issue, as landslides are rare, disrupting the training process. The second challenge stems from decentralized data management, with variations in volume and characteristics across regions. Typically, local municipalities manage disaster data within their regions, and sharing or migrating this data is not straightforward. This paper presents SlideSafe: a novel landslide prediction system that combines spatio-temporal contrastive learning and collaborative learning11Our implementation is available here (https://github.com/mclab-osaka/slidesafe). It begins by training a contrastive learning model to extract meaningful representations of land characteristics in each region. Subsequently, these trained models are merged among regions with similar characteristics, leveraging federated learning. The federated models are then fine-tuned and customized for the landslide event prediction using the data specific to each region. Experimental results indicate that the proposed system achieves higher precision under 100% recall compared to state-of-the-art federated learning methods, which are often adversely affected by non-iid data and data scarcity.

3D point clouds from LiDAR sensors have emerged as a powerful representation for understanding and interacting with the surrounding environment in smart computing systems. This tutorial aims to provide an overview of fundamental techniques, considerations, and applications of 3D point cloud recognition, with a focus on both deep learning and nondeep learning approaches. We will begin by introducing the unique characteristics and challenges of point cloud processing, highlighting the differences from traditional image-based approaches. Through the example of PointNet [1], a pioneering deep learning model for point cloud recognition, we will discuss the specific considerations and best practices for handling point cloud data. Recognizing the limitations of deep learning in resource-constrained and mobile environments, we will also explore alternative statistical and probabilistic techniques, such as Fisher Vector-based approaches, which enable efficient and lightweight point cloud processing and context recognition. These techniques are particularly relevant for smart computing applications that require real-time processing on edge devices and in Internet of Things scenarios.

Mobile technologies, particularly smartphones, have become integral to human life, influencing nearly every aspect of daily activities. Their ubiquity and advanced capabilities have led to them being a solution to a wide range of problems. Recent research has focused on leveraging the existing sensors in smartphones to supplant more costly and less accessible dedicated hardware. In this vein, we introduce MobiScale, a novel system designed to measure the weight of light objects using the built-in accelerometer and vibration motor of smartphones. This system utilizes advanced feature extraction techniques to effectively capture the temporal and spectral characteristics of the weight data. The core of MobiScale is its CNN-LSTM architecture, which processes these features to estimate weights accurately. The implementation of various regularization techniques has been vital in enhancing the system's ability to generalize, thereby improving its performance. Tested across multiple devices and under various conditions, MobiScale has shown consistent and precise performance, achieving a mean square error of just 12 grams in weight estimation, underscoring its potential as a versatile and reliable tool for weight measurement using smartphone technology.

Locating the persons moving through an environment without the necessity of them being equipped with special devices has become vital for many applications, including security, IoT, healthcare, etc. Existing device-free indoor localization systems commonly rely on the utilization of received signal strength indicator (RSSI) and WiFi channel state information (CSI) techniques. However, the accuracy of RSSI is adversely affected by environmental factors like multipath interference and fading. Additionally, the lack of standardization in CSI necessitates the use of specialized hardware and software. In this article, we present TimeSense, a deep learning-based multiperson device-free indoor localization system that addresses these challenges. TimeSense leverages Time of Flight information acquired by the fine-time measurement protocol of IEEE 802.11-2016 standard. Specifically, the measured round trip time between the transmitter and receiver is influenced by the dynamic changes in the environment induced by human presence. TimeSense effectively detects this anomalous behavior using a stacked denoising auto-encoder model, thereby estimating the user’s location. The system incorporates a probabilistic approach on top of the deep learning model to ensure seamless tracking of the users. The evaluation of TimeSense in two realistic environments demonstrates its efficacy, achieving a median localization accuracy of 1.57 and 2.65 meters. This surpasses the performance of state-of-the-art techniques by 49% and 103% in the two testbeds.

Tracking pedestrian flow in large public areas is vital, yet ensuring privacy is paramount. Traditional visual-based tracking systems are raising concerns for potentially obtaining persistent and permanent identifiers that can compromise individual identities. Moreover, in areas such as the vicinity of restrooms, any form of data acquisition capturing human behavior should be refrained from, making it also crucial to appropriately address and complement these blind spots for a comprehensive analysis of pedestrian movement in the entire area. In this paper, we present our pedestrian tracking algorithm using distributed 3D LiDARs (Light Detection and Ranging), which capture pedestrians as 3D point clouds, omitting identifiable features. Our system bridges blind spots by leveraging historical movement data and 3D point cloud features, complemented by a generative diffusion model to predict trajectories in unseen areas. In a large-scale testbed with 70 LiDARs, the system achieved a 0.98 F-measure, highlighting its potential as a leading privacy-preserving tracking solution.

WiFi fingerprinting systems for indoor localization have improved drastically with the advent of deep learning. However, these systems are often designed to be used on the same testbeds they are trained on, making generalizations to unknown testbeds hard. Additionally, any changes to Access Point configurations can drastically impact system performance. These systems often require collecting new data, retraining, and/or fine-tuning, which are time-consuming and costly. To address these issues, we propose a novel localization framework that can adapt to varying environments without recalibration. This is achieved by utilizing a "virtual space" via Graph Neural Networks, enhancing adaptability and system performance.

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.

WiFi localization systems have become increasingly popular owing to the ubiquity of WiFi-enabled devices. However, traditional WiFi networks were not originally designed for localization purposes, and changes to the Access Point locations can significantly drop localization performance. Moreover, these systems are unable to generalize models trained in one building to other buildings due to dependencies on building characteristics and their WiFi configurations. To address this challenge, we propose GlobLoc: the first global indoor positioning system that can function in any environment in a plug-and-play manner without requiring recalibration. Towards this end, we introduce a novel concept called the “virtual environment” in which users are tracked rather than the physical counterpart. This enables the localization model trained on one environment to function in another, regardless of changes occurring in the network environment, as they share the same virtual environment. Our experiments demonstrate that GlobLoc outperforms existing state-of-the-art propagation- and fingerprinting-based systems by at least 65%. This superior accuracy is due to its robustness to changes in the WiFi environment and its adaptability to different building configurations.

Intelligent transportation systems have become increasingly important for efficient traffic management and road safety. Vehicle classification is a fundamental task in these systems, enabling various applications such as traffic monitoring, congestion management, and accident prevention. Traditional methods for vehicle classification heavily rely on visual or sensor-based data, such as images or radar signals. However, these methods may encounter limitations in adverse weather conditions, poor lighting, or occlusion scenarios. To address these limitations, this paper introduces a novel approach for vehicle classification using seismic data, which captures the vibrations generated by vehicles and is less susceptible to environmental factors. The proposed approach leverages the fractional wavelet domain to extract both time and frequency signatures of vehicles from the seismic data effectively. These signatures are then used to train a recurrent neural network that captures the temporal features of the input, thereby facilitating vehicle classification. Additionally, the proposed approach incorporates various modules to improve the generalization and robustness of the deep model against noise. The implementation of the proposed approach on realistic data demonstrated its ability to classify vehicles with an accuracy of 98%, improving upon the state-of-the-art techniques.

Indoor localization systems have become increasingly important in a wide range of applications, including industry, security, logistics, and emergency services. However, the growing demand for accurate localization has heightened concerns over privacy, as many localization systems rely on active signals that can be misused by an adversary to track users’ movements or manipulate their measurements. This paper presents PassiFi, a novel passive Wi-Fi time-based indoor localization system that effectively balances accuracy and privacy. PassiFi uses a passive WiFi Time Difference of Arrival (TDoA) approach that ensures users’ privacy and safeguards the integrity of their measurement data while still achieving high accuracy. The system adopts a fingerprinting approach to address multi-path and non-line-of-sight problems and utilizes deep neural networks to learn the complex relationship between TDoA and location. Evaluation in real-world testbed demonstrates PassiFi’s exceptional performance, surpassing traditional multilateration by 128%, achieving sub-meter accuracy on par with state-of-the-art active measurement systems, all while preserving privacy.

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.

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.

The growing demand for intelligent environments unleashes an extraordinary cycle of privacy-aware applications that makes individuals' life more comfortable and safe. Examples of these applications include pedestrian tracking systems in large areas. Although the ubiquity of camera-based systems, they are not a preferable solution due to the vulnerability of leaking the privacy of pedestrians. In this paper, we introduce a novel privacy-preserving system for pedestrian tracking in smart environments using multiple distributed LiDARs of non-overlapping views. The system is designed to leverage LiDAR devices to track pedestrians in partially covered areas due to practical constraints, e.g., occlusion or cost. Therefore, the system uses the point cloud captured by different LiDARs to extract discriminative features that are used to train a metric learning model for pedestrian matching purposes. To boost the system's robustness, we leverage a probabilistic approach to model and adapt the dynamic mobility patterns of individuals and thus connect their sub-trajectories. We deployed the system in a large-scale testbed with 70 colorless LiDARs and conducted three different experiments. The evaluation result at the entrance hall confirms the system's ability to accurately track the pedestrians with a 0.98 F-measure even with zero-covered areas. This result highlights the promise of the proposed system as the next generation of privacy-preserving tracking means in smart environments.

Taxi-demand prediction is an important application of machine learning that enables taxi-providing facilities to optimize their operations and city planners to improve transportation infrastructure and services. However, the use of sensitive data in these systems raises concerns about privacy and security. In this paper, we propose the use of federated learning for taxi-demand prediction that allows multiple parties to train a machine learning model on their own data while keeping the data private and secure. This can enable organizations to build models on data they otherwise would not be able to access. Evaluation with real-world data collected from 16 taxi service providers in Japan over a period of six months showed that the proposed system can predict the demand level accurately within 1% error compared to a single model trained with integrated data.

In this paper, we propose KissLoc: a system that leverages onboard micro-size sensors of consumer eyewear devices for the dual purpose of activity recognition and localization. Specifically, the system trains a deep learning model for recognizing kissing activity and simultaneously identifying the timestamped location of its occurrence. Consequently, several predefined actions could be taken, including logging or controlling the smart environment. The evaluation shows that KissLoc can recognize the kissing activity with 82% accuracy while locating its occurrence with a median localization error of 1.25m.

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.

We propose SoLoc, a lightweight probabilistic fingerprinting-based technique for energy-free device-free indoor localization. The system harnesses photovoltaic currents harvested by the photovoltaic cells in smart environments for simultaneously powering digital devices and user positioning. The basic principle is that the location of the human interferes with the lighting received by the photovoltaic cells, thus producing a location fingerprint on the generated photocurrents. To ensure resilience to noisy measurements, SoLoc constructs probability distributions as a photovoltaic fingerprint at each location. Then, we employ a probabilistic graphical model for estimating the user location in the continuous space. Results show that SoLoc can localize the user at sub-meter accuracy in a real indoor environment.

Recently, commercially available off-the-shelf devices support the IEEE 802.11-2016 standard that implements a fine-time measurement (FTM) protocol for measuring the WiFi signal round trip time (RTT). This opens the door for a practical time-based localization where the clock synchronization problem between the transmitter and the receiver no longer exists. However, time-based techniques are highly affected by multipath propagation and non-line-of-sight transmissions. To combat these challenges, we present MagttLoc, a hybrid deep-learning-based indoor localization system that fuses magnetic measurements with WiFi RTT. MagttLoc yields a stable localization performance of decimeter-level accuracy improving upon the state-of-the-art systems in all experiments.

The technology of 3D recognition is evolving rapidly, enabling unprecedented growth of applications towards human-centric intelligent environments. On top of these applications human segmentation is a key technology towards analyzing and understanding human mobility in those environments. However, existing segmentation techniques rely on deep learning models, which are computationally intensive and data-hungry solutions. This hinders their practical deployment on edge devices in realistic environments. In this paper, we introduce a novel micro-size LiDAR device for understanding human mobility in the surrounding environment. The device is supplied with an on-device lightweight human segmentation technique for the captured 3D point cloud data using density-based clustering. The proposed technique significantly reduces the computational complexity of the clustering algorithm by leveraging the Spatiotemporal relation between consecutive frames. We implemented and evaluated the proposed technique in a real-world environment. The results show that the proposed technique obtains a human segmentation accuracy of 99% with a drastic reduction of the processing time by 66%.

As the demand for location-based services increases, several research efforts have aimed for robust and accurate indoor localization, especially 3D localization. Due to the widespread availability of cellular networks and their support by commodity cellphones, cellular-based systems have recently been proposed as a means of achieving this. However, because of the inherent noise and instability of wireless signals, localization accuracy typically degrades and is not robust to the dynamic heterogeneity of mobile devices.In this paper, we present a CellStory, a deep learning-based floor estimation system that achieves a fine-grained and robust accuracy in the presence of noise. CellStory combines stacked denoising autoencoder learning models, and a probabilistic framework to handle noise in the received signal and capture the complex relationship between the signals detected by the mobile phone and its location. Evaluation using different Android phones in a real testbed shows that CellStory can accurately estimate the user’s floor 98.7% of the time and within one floor error 100% of the time. This accuracy demonstrates CellStory’s superiority over state-of-the-art systems as well as its robustness to heterogeneous devices.

In this paper, we demonstrate OmniCells: a cellular-based indoor localization system designed to combat the device heterogeneity problem. OmniCells is a deep learning-based system that leverages cellular measurements from one or more training devices to provide consistent performance across unseen tracking phones. In this demo, we show the effect of device heterogeneity on the received cellular signals and how this leads to performance deterioration of traditional localization systems. In particular, we show how OmniCells and its novel feature extraction methods enable learning a rich and device-invariant representation without making any assumptions about the source or target devices. The system also includes other modules to increase the deep model's generalization and resilience to unseen scenarios.

In this paper, we demonstrate a brand new design of a wearable device that enables privacy-preserving human activity recognition based on light-weight compact-size LiDAR. The device scans and represents the surrounding environment in 3D point clouds form. The system further processes this representation to define discriminative features that facilitate recognizing human activity on edge. These features are extracted using Spatio-temporal probabilistic clustering and fisher vector representations and then used to train a classification model for activity recognition purposes. Implementation and evaluation of the proposed system confirm its efficient ability to identify human activities.

This paper presents the design and development of a lightweight, portable 3D spatial sensing device equipped with a compact LiDAR-type sensor. The device provides a 3D point cloud representation of the surrounding environment as captured by the sensor. Based on the acquired 3D point cloud, we propose a real-time object recognition method. The technical challenge is how to process the 3D point data in real-time while pursuing the best trade-off between the processing overhead and recognition accuracy. To answer the question, we leverage the Fisher Vector to extract spatio-temporal features of different objects enabling efficient classification of these objects using the Support Vector Machine approach. The experimental results show that the proposed method achieves mean Average Precision of 0.961. The processing speed on the device was 59.3 frames/second, indicating that object detection can be done in real-time on the device.

Indoor localization is a key component of pervasive and mobile computing. Due to the widespread use of WiFi technology, WiFi fingerprinting is one of the most widely utilized approaches for indoor localization. Despite advancements in WiFi-based positioning approaches, existing solutions necessitate a dense deployment of access points, time-consuming manual fingerprinting, and/or special hardware.

Location services are one of the most used applications today on mobile devices. The vast majority of localization systems propose solutions for locating the user in a 2D single floor environment. However, accurate estimation of the user's floor level, in tall multistory buildings, is a crucial basis for many applications, especially for emergency services.

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.

The demand for a ubiquitous and accurate indoor localization service is continuously growing. Cellular-based systems are a good candidate to provide such ubiquitous service due to their wide availability worldwide. One of the main barriers for accuracy is the large number of models of cell phones, which results in variations of the measured received signal strength (RSS), even at the same location and time. In this paper, we propose OmniCells, a deep learning-based system that leverages cellular measurements from one or more training devices to provide a consistent performance across unseen tracking phones. Specifically, OmniCells uses a novel approach to multi-task learning based on autoencoders that allows it to learn a rich and device-invariant RSS representation without any assumptions about the source or target devices. OmniCells also incorporates different modules to boost the system’s accuracy with RSS relative difference-based features and to improve the deep model’s generalization and robustness. Evaluation of OmniCells in two realistic testbeds using different Android phones with different form factors and cellular radio hardware shows that OmniCells can achieve a consistent median localization accuracy when tested on different phones. This is better than the state-of-the-art indoor cellular-based systems by at least 101%.

The demand for a ubiquitous and accurate indoor localization service is continuously growing. Despite the pervasive nature of cellular-based solutions, their localization quality depends on the number of cell towers provided by the phone. According to the standard, any cell phone can receive signal strength information from up to seven cell towers. However, the majority of cell phones usually return only the associated cell tower information, significantly limiting the amount of information available to the location determination algorithm. In this paper, we present SoloCell: a novel deep learning-based indoor localization system that utilizes the signal strength history from only the associated cell tower to achieve a fine-grained localization. SoloCell incorporates different modules that lessen the data collection effort and improve the deep model's robustness against noise. Evaluation using different Android phones shows that SoloCell can track the user with a median localization error of 0.95m This accuracy demonstrates the superiority of SoloCell compared to the state-of-the-art systems by at least 210%.

The demand for a ubiquitous and accurate indoor localization service is continuously growing. Despite the pervasive nature of cellular-based solutions, their localization quality depends on the number of cell towers provided by the phone, which is typically limited. Specifically, according to the standard, any cell phone can receive signal strength information from up to seven cell towers. However, the majority of cell phones usually return only the associated cell tower information, significantly limiting the amount of information available to the location determination algorithm, degrading its performance.

Robust and accurate indoor localization has been the goal of several research efforts over the past decade. Due to the ubiquitous availability of WiFi indoors, many indoor localization systems have been proposed relying on WiFi fingerprinting. However, due to the inherent noise and instability of the wireless signals, the localization accuracy usually degrades and is not robust to dynamic changes in the environment.We present WiDeep, a deep learning-based indoor localization system that achieves a fine-grained and robust accuracy in the presence of noise. Specifically, WiDeep combines a stacked denoising autoencoders deep learning model and a probabilistic framework to handle the noise in the received WiFi signal and capture the complex relationship between the WiFi APs signals heard by the mobile phone and its location. WiDeep also introduces a number of modules to address practical challenges such as avoiding over-training and handling heterogeneous devices.We evaluate WiDeep in two testbeds of different sizes and densities of access points. The results show that it can achieve a mean localization accuracy of 2.64m and 1.21m for the larger and the smaller testbeds, respectively. This accuracy outperforms the state-of-the-art techniques in all test scenarios and is robust to heterogeneous devices.

Recently, deep learning-based positioning systems have gained attention due to their higher performance relative to traditional methods. However, obtaining the expected performance of deep learning-based systems requires large amounts of data to train model. Obtaining this data is usually a tedious process which hinders the utilization of such deep learning approaches. In this paper, we introduce a number of techniques for addressing the data collection problem for deep learning-based cellular localization systems. The basic idea is to generate synthetic data that reflects the typical pattern of the wireless data as observed from a small collected dataset. Evaluation of the proposed data augmentation techniques using different Android phones in a cellular localization case study shows that we can enhance the performance of the localization systems in both indoor and outdoor scenarios by 157% and 50.5%, respectively. This highlights the promise of the proposed techniques for enabling deep learning-based localization systems.