Hongyang Zhao

Bio: Hongyang Zhao is an academic researcher from College of William & Mary. The author has contributed to research in topics: Gesture recognition & Gesture. The author has an hindex of 10, co-authored 19 publications receiving 363 citations. Previous affiliations of Hongyang Zhao include Zhejiang University.

SignFi: Sign Language Recognition Using WiFi

Abstract: We propose SignFi to recognize sign language gestures using WiFi. SignFi uses Channel State Information (CSI) measured by WiFi packets as the input and a Convolutional Neural Network (CNN) as the classification algorithm. Existing WiFi-based sign gesture recognition technologies are tested on no more than 25 gestures that only involve hand and/or finger gestures. SignFi is able to recognize 276 sign gestures, which involve the head, arm, hand, and finger gestures, with high accuracy. SignFi collects CSI measurements to capture wireless signal characteristics of sign gestures. Raw CSI measurements are pre-processed to remove noises and recover CSI changes over sub-carriers and sampling time. Pre-processed CSI measurements are fed to a 9-layer CNN for sign gesture classification. We collect CSI traces and evaluate SignFi in the lab and home environments. There are 8,280 gesture instances, 5,520 from the lab and 2,760 from the home, for 276 sign gestures in total. For 5-fold cross validation using CSI traces of one user, the average recognition accuracy of SignFi is 98.01%, 98.91%, and 94.81% for the lab, home, and lab+home environment, respectively. We also run tests using CSI traces from 5 different users in the lab environment. The average recognition accuracy of SignFi is 86.66% for 7,500 instances of 150 sign gestures performed by 5 different users.

Incentive-Driven and Freshness-Aware Content Dissemination in Selfish Opportunistic Mobile Networks

Abstract: Recently, the content-based publish/subscribe (pub/sub) paradigm has been gaining popularity in opportunistic mobile networks (OppNets) for its flexibility and adaptability. Since nodes in OppNets are controlled by humans, they often behave selfishly. Therefore, stimulating nodes in selfish OppNets to collect, store, and share contents efficiently is one of the key challenges. Meanwhile, guaranteeing the freshness of contents is also a big problem for content dissemination in OppNets. In this paper, in order to solve these problems, we propose an incentive-driven and freshness-aware pub/sub Content Dissemination scheme, called ConDis , for selfish OppNets. In ConDis , the Tit-For-Tat (TFT) scheme is employed to deal with selfish behaviors of nodes in OppNets. Moreover, a novel content exchange protocol is proposed when nodes are in contact. Specifically, during each contact, the exchange order is determined by the content utility, which represents the usefulness of a content for a certain node, and the objective of nodes is to maximize the utility of the content inventory stored in their buffer. Extensive realistic trace-driven simulation results show that ConDis is superior to other existing schemes in terms of total freshness value, total delivered contents, and total transmission cost.

On Exploiting Contact Patterns for Data Forwarding in Duty-Cycle Opportunistic Mobile Networks

Abstract: In this paper, we focus on investigating the impact of duty-cycle operation on data forwarding in duty-cycle opportunistic mobile networks (OppNets) and on designing an efficient data-forwarding strategy for duty-cycle OppNets. Some recent studies utilize node contact patterns to aid in the design of a data-forwarding strategy in OppNets. However, when duty-cycle operation is applied in OppNets, several node contacts will be missed when nodes are in the sleep state for energy saving, and it becomes challenging to design an efficient data-forwarding strategy based on exploitation of node contact patterns. To address this challenge, we first propose a model to investigate the contact process in duty-cycle OppNets and to estimate the probability of contact discovery. We also experimentally validate the correctness of our proposed model. Second, based on this model, we propose a novel approach to improve the performance of data forwarding in duty-cycle OppNets. The proposed forwarding strategy takes into account both the contact frequency and contact duration and manages to forward data copies along the opportunistic forwarding paths, which maximize the data delivery probability. Finally, extensive real-trace-driven simulations are conducted to compare the proposed data-forwarding strategy with other recently reported data-forwarding strategies in terms of delivery ratio and cost. The simulation results show that our proposed data-forwarding strategy is close to the Epidemic Routing strategy in terms of delivery ratio but with significantly reduced delivery cost. Additionally, our proposed strategy outperforms the Bubble Rap and Prophet strategies in terms of delivery ratio with reasonable delivery cost.

Join driving: A smart phone-based driving behavior evaluation system

Abstract: In this paper, we develop a smart phone-based driving behavior evaluation system, named Join Driving, which helps drivers notice how aggressive their driving behaviors are and be aware of the riding comfort level of passengers. The proposed evaluation system is made of two parts: driving events detection and evaluation part and riding comfort level evaluation part. In driving events detection and evaluation part, the proposed system, Join Driving, first presents a model to detect drivers' driving events, based on the data collected from the acceleration, orientation and GPS sensors in smart phones. Then, based on the detected drivers' driving events, Join Driving implements a novel scoring mechanism to quantitatively evaluate how aggressive these driving events are. In riding comfort level evaluation part, the proposed system gives the specific scores to rate passengers' riding comfort level based on ISO 2631. Finally, several practical experiments are conducted to evaluate the effectiveness of the proposed scoring system.

WiFi Sensing with Channel State Information: A Survey

Abstract: With the high demand for wireless data traffic, WiFi networks have experienced very rapid growth, because they provide high throughput and are easy to deploy. Recently, Channel State Information (CSI) measured by WiFi networks is widely used for different sensing purposes. To get a better understanding of existing WiFi sensing technologies and future WiFi sensing trends, this survey gives a comprehensive review of the signal processing techniques, algorithms, applications, and performance results of WiFi sensing with CSI. Different WiFi sensing algorithms and signal processing techniques have their own advantages and limitations and are suitable for different WiFi sensing applications. The survey groups CSI-based WiFi sensing applications into three categories, detection, recognition, and estimation, depending on whether the outputs are binary/multi-class classifications or numerical values. With the development and deployment of new WiFi technologies, there will be more WiFi sensing opportunities wherein the targets may go beyond from humans to environments, animals, and objects. The survey highlights three challenges for WiFi sensing: robustness and generalization, privacy and security, and coexistence of WiFi sensing and networking. Finally, the survey presents three future WiFi sensing trends, i.e., integrating cross-layer network information, multi-device cooperation, and fusion of different sensors, for enhancing existing WiFi sensing capabilities and enabling new WiFi sensing opportunities.

Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi

Abstract: Wi-Fi based sensing systems, although sound as being deployed almost everywhere there is Wi-Fi, are still practically difficult to be used without explicit adaptation efforts to new data domains. Various pioneering approaches have been proposed to resolve this contradiction by either translating features between domains or generating domain-independent features at a higher learning level. Still, extra training efforts are necessary in either data collection or model re-training when new data domains appear, limiting their practical usability. To advance cross-domain sensing and achieve fully zero-effort sensing, a domain-independent feature at the lower signal level acts as a key enabler. In this paper, we propose Widar3.0, a Wi-Fi based zero-effort cross-domain gesture recognition system. The key insight of Widar3.0 is to derive and estimate velocity profiles of gestures at the lower signal level, which represent unique kinetic characteristics of gestures and are irrespective of domains. On this basis, we develop a one-fits-all model that requires only one-time training but can adapt to different data domains. We implement this design and conduct comprehensive experiments. The evaluation results show that without re-training and across various domain factors (i.e. environments, locations and orientations of persons), Widar3.0 achieves 92.7% in-domain recognition accuracy and 82.6%-92.4% cross-domain recognition accuracy, outperforming the state-of-the-art solutions. To the best of our knowledge, Widar3.0 is the first zero-effort cross-domain gesture recognition work via Wi-Fi, a fundamental step towards ubiquitous sensing.

A Survey on Vehicular Social Networks

Abstract: This paper surveys recent literature on vehicular social networks that are a particular class of vehicular ad hoc networks, characterized by social aspects and features. Starting from this pillar, we investigate perspectives on next-generation vehicles under the assumption of social networking for vehicular applications (i.e., safety and entertainment applications). This paper plays a role as a starting point about socially inspired vehicles and mainly related applications, as well as communication techniques. Vehicular communications can be considered the “first social network for automobiles” since each driver can share data with other neighbors. For instance, heavy traffic is a common occurrence in some areas on the roads (e.g., at intersections, taxi loading/unloading areas, and so on); as a consequence, roads become a popular social place for vehicles to connect to each other. Human factors are then involved in vehicular ad hoc networks, not only due to the safety-related applications but also for entertainment purposes. Social characteristics and human behavior largely impact on vehicular ad hoc networks, and this arises to the vehicular social networks, which are formed when vehicles (individuals) “socialize” and share common interests. In this paper, we provide a survey on main features of vehicular social networks, from novel emerging technologies to social aspects used for mobile applications, as well as main issues and challenges. Vehicular social networks are described as decentralized opportunistic communication networks formed among vehicles. They exploit mobility aspects, and basics of traditional social networks , in order to create novel approaches of message exchange through the detection of dynamic social structures. An overview of the main state-of-the-art on safety and entertainment applications relying on social networking solutions is also provided.

A Review of Intelligent Driving Style Analysis Systems and Related Artificial Intelligence Algorithms.

Abstract: In this paper the various driving style analysis solutions are investigated. An in-depth investigation is performed to identify the relevant machine learning and artificial intelligence algorithms utilised in current driver behaviour and driving style analysis systems. This review therefore serves as a trove of information, and will inform the specialist and the student regarding the current state of the art in driver style analysis systems, the application of these systems and the underlying artificial intelligence algorithms applied to these applications. The aim of the investigation is to evaluate the possibilities for unique driver identification utilizing the approaches identified in other driver behaviour studies. It was found that Fuzzy Logic inference systems, Hidden Markov Models and Support Vector Machines consist of promising capabilities to address unique driver identification algorithms if model complexity can be reduced.

Wireless Sensing for Human Activity: A Survey

Abstract: With the advancement of wireless technologies and sensing methodologies, many studies have shown the success of re-using wireless signals (e.g., WiFi) to sense human activities and thereby realize a set of emerging applications, ranging from intrusion detection, daily activity recognition, gesture recognition to vital signs monitoring and user identification involving even finer-grained motion sensing. These applications arguably can brace various domains for smart home and office environments, including safety protection, well-being monitoring/management, smart healthcare and smart-appliance interaction. The movements of the human body impact the wireless signal propagation (e.g., reflection, diffraction and scattering), which provide great opportunities to capture human motions by analyzing the received wireless signals. Researchers take the advantage of the existing wireless links among mobile/smart devices (e.g., laptops, smartphones, smart thermostats, smart refrigerators and virtual assistance systems) by either extracting the ready-to-use signal measurements or adopting frequency modulated signals to detect the frequency shift. Due to the low-cost and non-intrusive sensing nature, wireless-based human activity sensing has drawn considerable attention and become a prominent research field over the past decade. In this paper, we survey the existing wireless sensing systems in terms of their basic principles, techniques and system structures. Particularly, we describe how the wireless signals could be utilized to facilitate an array of applications including intrusion detection, room occupancy monitoring, daily activity recognition, gesture recognition, vital signs monitoring, user identification and indoor localization. The future research directions and limitations of using wireless signals for human activity sensing are also discussed.