Guozhen Zhu

Guozhen Zhu

Auto-generated profile, based on publicly available information

Guozhen Zhu

Origin Research, Rockville, Maryland, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 December 2023 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
GZGuozhen Zhu
Guozhen Zhu
YHYuqian Hu
Yuqian Hu
BWBeibei Wang
Beibei Wang
CWChenshu Wu
Chenshu Wu
XZXiaolu Zeng
Xiaolu Zeng
KLK. J. Ray Liu
K. J. Ray Liu
Indoor intelligent perception systems have gained significant attention in recent years. However, accurately detecting human presence can be challenging in the presence of nonhuman subjects, such as pets, robots, and electrical appliances, limiting the practicality of these systems for widespread use. In this article, we propose a novel system (“Wi-MoID”) that passively and unobtrusively distinguishes moving human and various nonhuman subjects using a single pair of commodity WiFi transceivers, without requiring any device on the subjects or restricting their movements. Wi-MoID leverages a novel statistical electromagnetic wave theory-based multipath model to detect moving subjects, extracts physically and statistically explainable features of their motion, and accurately differentiates human and various nonhuman movements through walls, even in complex environments. In addition, Wi-MoID is suitable for edge devices, requiring minimal computing resources and storage, and is environment independent, making it easy to deploy in new environments with minimum effort. We evaluate the performance of Wi-MoID in five distinct buildings with various moving subjects, including pets, vacuum robots, humans, and fans, and the results demonstrate that it achieves 97.34% accuracy and 1.75% false alarm rate for identification of human and nonhuman motion, and 95.98% accuracy in unseen environments without model tuning, demonstrating its robustness for ubiquitous use.

13 December 2022 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
GZGuozhen Zhu
Guozhen Zhu
CWChenshu Wu
Chenshu Wu
BWBeibei Wang
Beibei Wang
KLK. J. Ray Liu
K. J. Ray Liu
Indoor-location-based services rely on indoor maps, which are yet widely available despite numerous efforts from the industry. Existing solutions employ costly hardware (e.g., lidar) to achieve accurate mapping of indoor environments, or resort to crowdsourcing for floor plan generation at the cost of precision due to inaccurate inertial sensing. In this article, we leverage a new opportunity enabled by recent advances in RF-based inertial tracking that achieves centimeter accuracy. We present EZMAP, a high-accuracy, low-cost floor plan construction system that fuses RF and inertial sensing. EZMAP combines the fine-grained yet local information from RF tracking with the coarse grained but global contexts from inertial sensing (e.g., magnetic field strength), which together makes for an accurate map. Our system employs a robot for trajectory collection and requires only a single access point to be arbitrarily installed in the space, both of which are widely available nowadays. Furthermore, it can generate a map even only a small amount of data is available, allowing it to scale for different buildings, such as malls, office buildings, and homes with little cost. We validate the performance using a Dji RoboMaster S1 robot with commodity WiFi in three different buildings. The results show that our system can efficiently generate faithful maps for the targeted areas. With the ubiquity of the WiFi infrastructure and the rise of home robots, we believe our approach will pave the way for pervasive indoor maps services.

16 December 2024 in IEEE Journal of Selected Areas in Sensors
Verified
Journal Article
Open access
GZGuozhen Zhu
Guozhen Zhu
BWBeibei Wang
Beibei Wang
WGWeihang Gao
Weihang Gao
YHYuqian Hu
Yuqian Hu
CWChenshu Wu
Chenshu Wu
KLK. J. Ray Liu
K. J. Ray Liu
As WiFi has become a ubiquitous medium for communication, its role in sensing applications has expanded. However, the current WiFi sensing applications are limited by their assumption that any detected motion signifies human activity, overlooking the potential impact of non-human subjects. Existing attempts to recognize the interference from non-human motion impose stringent requirements regarding device positioning, data quality, environmental complexity, and non-human subject categories. In this study, we design a robust deep learning framework, SrcSense (“ S ou rc e Sense ”), to recognize the motion source with WiFi signals through the wall. SrcSense extracts environment-independent features from single-link WiFi. We investigate the performance of popular deep neural networks and explore the efficacy of transferring pre-trained models to WiFi sensing tasks. We implement SrcSense and evaluate the performance in five real-world complex environments with commodity WiFi devices. With a challenging dataset considering large pets, diverse human activities and multiple subjects coexisting cases, SrcSense achieves an average validation accuracy of 95.84% across five distinct environments and an average testing accuracy of 91.71% in unseen environments without further model training or parameter tuning. By accumulating 20 seconds of WiFi data, SrcSense can achieve an elevated recognition accuracy of 99.77% with ResNet-50. These results underline the robustness of our approach and its readiness for integration into ubiquitous intelligent IoT systems and applications.

1 August 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
WWWei-Hsiang Wang
Wei-Hsiang Wang
BWBeibei Wang
Beibei Wang
YHYuqian Hu
Yuqian Hu
GZGuozhen Zhu
Guozhen Zhu
KLK. J. Ray Liu
K. J. Ray Liu
Device-free indoor object detection and localization are essential for the success of smart homes. Traditional vision/acoustic/radar-based approaches face operational constraints that limit their effectiveness and scalability. WiFi-based approaches have recently been a promising candidate due to their ubiquity, cost-effectiveness, and privacy-preserving nature. However, most of them show inadequate performance in typical residential settings due to the limited WiFi bandwidth and the resulting low spatial resolution. In this article, we introduce a novel system using commodity WiFi that can accurately determine the specific room where the person is, i.e., room-level localization. The system employs a novel multipath selection technique to concentrate on a limited set of multipaths predominated by the proximate motions to the device. Based on the technique, a spatial feature leveraging multiple antennas to enhance the spatial resolution is proposed for more refined detection coverage. Combining the spatial feature with time- and frequency-domain features, the system is shown to achieve an overall test accuracy of 87.63%, a true positive rate of 89.47%, and a positive predictive value of 88.51%, outperforming state-of-the-art methods by >20% and showing its potential for real-world applications.

4 December 2024
Verified
Conference Paper
Open access
YHYuqian Hu
Yuqian Hu
GZGuozhen Zhu
Guozhen Zhu
WWWei-Hsiang Wang
Wei-Hsiang Wang
BWBeibei Wang
Beibei Wang
KLK. J. Ray Liu
K. J. Ray Liu
Channel State Information (CSI) is foundational for enabling advanced Wi-Fi sensing applications, yet its efficacy is significantly influenced by environmental factors, hardware variations, and noise. This paper introduces a structured framework designed to rigorously evaluate the quality of CSI, thereby enhancing the performance and reliability of Wi-Fi-based sensing systems. Our evaluation system features a multilayered pipeline, where the first layer assesses fundamental CSI characteristics, including packet loss and amplitude consistency over time, to verify data integrity, and the second layer evaluates the compatibility of CSI with specific applications, such as motion detection. Validation of our framework across various chipset samples demonstrates its utility in improving the accuracy and reliability of CSI-derived sensing and potential in refining data quality for data-driven approaches.

3 June 2024
Verified
Conference Paper
Open access
GZGuozhen Zhu
Guozhen Zhu
YHYuqian Hu
Yuqian Hu
BWBeibei Wang
Beibei Wang
CWChenshu Wu
Chenshu Wu
WGWeihang Gao
Weihang Gao
KLK. J. Ray Liu
K. J. Ray Liu
Addressing the pivotal challenge of discerning human and nonhuman activities in smart environments, in this demo, we present a system utilizing commercial WiFi transceivers for precise human and non-human motion differentiation through the walls. This system effectively filters non-human interference in smart home systems by extracting physically and statistically explainable features from ubiquitous WiFi signals. It passively recognizes moving subjects in real time without constraining their movement, even in complex environments. Tailored for edge computing, it ensures minimal resource consumption and generalizes well across various settings. Our long-term field tests confirm a high accuracy rate of 97.34% and a low false alarm rate of 1.75%, underscoring its robustness and readiness for practical deployment. Please find the companion video with the URL: https://youtu.be/6xkJZ_VvL9Q.