WPWoojin Park

Woojin Park

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Woojin Park has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Mobile-AI-Based Docent System: Navigation and Localization for Visually Impaired Gallery Visitors

    by Hyeyoung An, Woojin Park, Philip Liu, Soochang Park

    Smart guidance systems in museums and galleries are now essential for delivering quality user experiences. Visually impaired visitors face significant barriers when navigating galleries due to existing smart guidance systems’ dependence on visual cues like QR codes, manual numbering, or static beacon positioning. These traditional methods often fail to provide adaptive navigation and meaningful content delivery tailored to their needs. In this paper, we propose a novel Mobile-AI-based Smart Docent System that seamlessly integrates real-time navigation and depth of guide services to enrich gallery experiences for visually impaired users. Our system leverages camera-based on-device processing and adaptive BLE-based localization to ensure accurate path guidance and real-time obstacle avoidance. An on-device object detection model reduces delays from large visual data processing, while BLE beacons, fixed across the gallery, dynamically update location IDs for better accuracy. The system further refines positioning by analyzing movement history and direction to minimize navigation errors. By intelligently modulating audio content based on user movement—whether passing by, approaching for more details, or leaving mid-description—the system offers personalized, context-sensitive interpretations while eliminating unnecessary audio clutter. Experimental validation conducted in an authentic gallery environment yielded empirical evidence of user satisfaction, affirming the efficacy of our methodological approach in facilitating enhanced navigational experiences for visually impaired individuals. These findings substantiate the system’s capacity to enable more autonomous, secure, and enriched cultural engagement for visually impaired individuals within complex indoor environments.


  • Open Access

    Real-Time Sensing and On-Site Spotting Scheme of Multi-Type WLAN Spycams

    by Hyeyoung An, Woojin Park, Soochang Park

    This paper proposes a real-time sensing and on-site spotting scheme for multi-type wireless LAN based spy-cameras. The proposed scheme has the goal of overcoming the restrictions of previous studies on location-dependent training data per target location for spycam traffic classification and learning-based positioning, and the overhead requiring additional equipment to gather specific data for spycam location such as channel state information (CSI). In addition, some ways to send video data via spycams exploit data encryption, so it leads to erasing feature of video data which should be trained to the models for camera existence detection. In other words, there is a lack of comprehensive research that integrates the detection and localization of these surveillance video devices without reliance on data preparation per location and special devices. Recognizing the need to detect video devices used for such malicious purposes in real-time, this paper introduces a method that utilizes the Nilsimsa hashing algorithm and the Log-Distance Path Loss (LDPL) model for similarity checks to detect and localize various video devices transmitting wirelessly. We capture the wireless data transmitted and use the Nilsimsa hashing algorithm, which generates similar hash results for similar inputs, to detect video devices through similarity checks. Furthermore, we rely only on the recent signal strength indication (RSSI) values received to quickly estimate the location of the device that is not very accurate but detectable with eyes at the site, regardless of its type. Our approach shows determining the presence of a device within 3 seconds and estimating its approximate location with an average accuracy of approximately 0.08 m within a 1 m range and 0.45 m within a 3 m range, regardless of the device type.


  • Open Access

    AI-Aided Proximity Detection and Location-Dependent Authentication on Mobile-Based Digital Twin Networks: A Case Study of Door Materials

    by Woojin Park, Hyeyoung An, Yongbin Yim, Soochang Park

    Nowadays, mobile–mobile interaction is becoming a fundamental methodology for human–human networking services since mobile devices are the most common interfacing equipment for recent smart services such as food delivery, e-commerce, ride-hailing, etc. Unlike legacy ways of human interaction, on-site and in-person mutual recognition between a service provider and a client in mobile–mobile interaction is not trivial. This is because of not only the avoidance of face-to-face communication due to safety and health concerns but also the difficulty of matching up the online user using mobiles with the real person in the physical world. So, a novel mutual recognition scheme for mobile–mobile interaction is highly necessary. This paper comes up with a novel cyber-physical secure communication scheme relying on the digital twin paradigm. The proposed scheme designs the digital twin networking architecture on which real-world users form digital twins as their own online abstraction, and the digital twins authenticate each other for a smart service interaction. Thus, inter-twin communication (ITC) could support secure mutual recognition in mobile–mobile interaction. Such cyber-physical authentication (CPA) with the ITC is built on the dynamic BLE beaconing scheme with accurate proximity detection and dynamic identifier (ID) allocation. To achieve high accuracy in proximity detection, the proposed scheme is conducted using a wide variety of data pre-processing algorithms, machine learning technologies, and ensemble techniques. A location-dependent ID exploited in the CPA is dynamically generated by the physical user for their own digital twin per each mobile service.


  • Open Access

    USING Sensor: User-Smartphone Decoupling Detection as a Mobile-Based Virtual Sensor

    by Woojin Park, Hyeyoung An, Soochang Park

    In many disaster situations, the location of victims is the most important information for saving them. To provide such information, most studies simply use indoor positioning technologies of the victim’s mobile device. Nevertheless, their schemes have a large lack to point out the exact location of a victim because people sometimes drop off their mobile device or put it down some places, such as a desk and a table. In other words, it merely provides the location of mobile devices and not of victims. Hence, this paper proposes a novel virtual sensing mechanism, named the USING sensor (User-Smartphone-Decoupling Detection). The USING sensor relies on the user activity sensing and co-existence monitoring of users and smart mobile devices. It could track the continuous coupling state of the user-mobile device. However, continuous user activity detection is not trivial, since some actions, such as sitting, dropping, and so on, intermittently occur while some actions like walking are frequent and continuous. So, data acquisition methods from a mobile device for the detection of user actions should be designed and managed differently. In addition, for high sensing reliability, the USING sensor is based on machine learning (ML) analytics with multiple algorithms and the ensemble technique. Thus, it could achieve 95.0% of user activity recognition accuracy and 86.8% of sensing accuracy.

  • Open Access

    Wireless Spy Camera Spotter System With Real-Time Traffic Similarity Analysis and WiFi Signal Tracing

    by Hyeyoung An, Woojin Park, Soochang Park

    This paper introduces a novel method to detect WiFi-enabled spy cameras potentially invading user privacy via wireless streaming within a user’s vicinity. So far, there have been social initiatives to conduct spy camera inspections to address this issue, and academic societies have been working on various detection methods. However, such studies typically rely on additional specific efforts, such as using specialized equipment to gather channel state information (CSI) or collecting extensive long-term data per location for machine learning approaches. In addition, some ideas could not recognize features of spy camera data due to data encryption. Hence, this paper comes up with a novel scheme for detecting wireless spy cameras based only on off-the-shelf devices. To achieve these functionalities, the proposed scheme consists of three phases: 1) classification, 2) detection, and 3) localization. First, in the classification phase, the collected packet headers are analyzed to identify and classify the upstream streaming protocols. In addition, the proposed scheme fulfills the detection phase that exploits the Nilsimsa algorithm to analyze packet similarity, identifying potential spy cameras by detecting consistent high similarity patterns in the classified data traffic. Finally, the proposed approach provides the localization phase that captures and analyzes Received Signal Strength Indication (RSSI) values at the target location and spots the camera position. Unlike existing methods, the proposed scheme does not rely on extensive data collection per location and complex mechanisms to interpret encrypted data. Moreover, compared to machine learning (ML)-based positioning means, which require significant data sets and long-term computation time, the scheme achieves real-time detection with minimal computational demands.