Jingyu Tong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jingyu Tong has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Lei Yang
The Hong Kong Polytechnic University
9 shared publications - Donghui Dai
Tongji University
7 shared publications - Zhenlin An
Department of Computing, The Hong Kong Polytechnic University, Hong Kong
7 shared publications - Zheng Gong
Tianjin University
6 shared publications - Sicong Liao
The Hong Kong Polytechnic University, Hong Kong, China
4 shared publications - Xiaopeng Zhao
Department of Computing, The Hong Kong Polytechnic University, Hong Kong
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 920-931
Learning Video-Derived Behavioral and Physiological Representations for Automated Deception Detection
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 920-931
Open AccessLearning Video-Derived Behavioral and Physiological Representations for Automated Deception Detection
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20296-20313
Bridging the Gap in Cross-Medium Networks With Mechanical Antennas
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (11) , 20296-20313
Bridging the Gap in Cross-Medium Networks With Mechanical Antennas
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 26824-26835
ARGUS: Cross-Antenna Channel Estimation and Intelligent Antenna Selection for Massive MIMO
Massive multiple-input–multiple-output (massive MIMO) has emerged as a cornerstone technology for 5G-advanced and future 6G networks; yet, its practical deployment remains limited by hardware cost and power consumption. Switch-based architectures, which share a small number of RF chains among many antenna elements, provide a scalable alternative, but create a new bottleneck: only a subset of antennas is observable at any given moment, leaving the channel state of the remaining elements unknown. Lacking this information prevents the system from exploiting advanced physical-layer functions, such as digital beamforming or multistream MIMO. In this article, we present ARGUS, a generative channel reconstruction framework that infers the channel state information (CSI) of unobserved antennas from partial observations. The key idea is that all antenna responses are governed by the same underlying wireless propagation environment, enabling the task to be formulated as a generative inference problem. We employ a variational autoencoder (VAE) to capture the latent spatial structure and reconstruct unobserved channels through sampling. Extensive experiments show that our reconstructed CSI incurs less than 2.5% achievable rate loss and real-world measurements demonstrate a more than 90% antenna-selection match rate, confirming the practicality of the proposed approach.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (12) , 26824-26835
ARGUS: Cross-Antenna Channel Estimation and Intelligent Antenna Selection for Massive MIMO
Massive multiple-input–multiple-output (massive MIMO) has emerged as a cornerstone technology for 5G-advanced and future 6G networks; yet, its practical deployment remains limited by hardware cost and power consumption. Switch-based architectures, which share a small number of RF chains among many antenna elements, provide a scalable alternative, but create a new bottleneck: only a subset of antennas is observable at any given moment, leaving the channel state of the remaining elements unknown. Lacking this information prevents the system from exploiting advanced physical-layer functions, such as digital beamforming or multistream MIMO. In this article, we present ARGUS, a generative channel reconstruction framework that infers the channel state information (CSI) of unobserved antennas from partial observations. The key idea is that all antenna responses are governed by the same underlying wireless propagation environment, enabling the task to be formulated as a generative inference problem. We employ a variational autoencoder (VAE) to capture the latent spatial structure and reconstruct unobserved channels through sampling. Extensive experiments show that our reconstructed CSI incurs less than 2.5% achievable rate loss and real-world measurements demonstrate a more than 90% antenna-selection match rate, confirming the practicality of the proposed approach.
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12797-12813
Toward Scalable Reconfigurable Intelligent Surfaces Using Commercial RFIDs
Reconfigurable Intelligent Surfaces (RISs) have emerged as cost-effective technologies for improving wireless signal transmission. Conventional RIS designs, however, face challenges such as bulkiness, high production costs, limited scalability, and complex installation due to their reliance on wired connections. In this work, we introduce MetaMosaic, a novel RIS platform that repurposes 920 MHz RFID tags into battery-free unit cells, enabling an affordable, scalable, and flexible one-bit phase-modulated RIS. The system is engineered for compatibility with 2.4 GHz Wi-Fi communications while being controlled at 920 MHz. Our design incorporates two central innovations: the transformation of commercial RFID tags into functional unit cells and the development of a tailored neural radiance field to guide efficient reconfiguration. To further enhance global search capability and support multi-hotspot alignment, we extend the system with a genetic algorithm (GA)-based optimization strategy. Compared with the vanilla MetaMosaic, the GA-based MetaMosaic achieves an additional 3.1 dB signal strength improvement and enables simultaneous enhancement for up to five target points. Extensive testing across ten diverse environments demonstrates that MetaMosaic consistently boosts signal strength, with a mean gain of 19 dB over non-RIS setups. This outperforms current leading RIS systems by a 3-fold improvement.
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (8) , 12797-12813
Toward Scalable Reconfigurable Intelligent Surfaces Using Commercial RFIDs
Reconfigurable Intelligent Surfaces (RISs) have emerged as cost-effective technologies for improving wireless signal transmission. Conventional RIS designs, however, face challenges such as bulkiness, high production costs, limited scalability, and complex installation due to their reliance on wired connections. In this work, we introduce MetaMosaic, a novel RIS platform that repurposes 920 MHz RFID tags into battery-free unit cells, enabling an affordable, scalable, and flexible one-bit phase-modulated RIS. The system is engineered for compatibility with 2.4 GHz Wi-Fi communications while being controlled at 920 MHz. Our design incorporates two central innovations: the transformation of commercial RFID tags into functional unit cells and the development of a tailored neural radiance field to guide efficient reconfiguration. To further enhance global search capability and support multi-hotspot alignment, we extend the system with a genetic algorithm (GA)-based optimization strategy. Compared with the vanilla MetaMosaic, the GA-based MetaMosaic achieves an additional 3.1 dB signal strength improvement and enables simultaneous enhancement for up to five target points. Extensive testing across ten diverse environments demonstrates that MetaMosaic consistently boosts signal strength, with a mean gain of 19 dB over non-RIS setups. This outperforms current leading RIS systems by a 3-fold improvement.
- Open Access
- 9 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (2) , 1-23
Everytime Everywhere All at Once: Enhancing Temporal-Spatial Traceability of Optical Codes through Voltmarks
Due to the absence of spatial-temporal traceability, static optical codes present considerable security risks and are thus confined to limited applications (for instance, transactions using static QR codes for mobile payments are capped at 500 RMB or about 76 USD daily in China). While dynamic codes that update periodically can mitigate these issues, they necessitate additional hardware, such as screens and computing devices. To overcome these limitations, we introduce Voltmark, a novel approach that enhances the spatial-temporal traceability of static optical codes to the level of dynamic ones through the use of voltmarks---natural watermarks generated by AC flickering during image capture indoors. Voltmarks carry unique temporal and spatial characteristics of the AC and bulbs, allowing for the verification of the time and location where code photographs were taken. This functionality effectively thwarts various security threats and fraudulent activities. Extensive evaluation demonstrates that Voltmark maintains an average accuracy of 93.3% in spatial tracing and delivers a time resolution of 42ms (equivalent to scanning at 24 fps). These outcomes solidly establish Voltmark as a reliable technique for boosting the security of optical codes.
- 9 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (2) , 1-23
Open AccessEverytime Everywhere All at Once: Enhancing Temporal-Spatial Traceability of Optical Codes through Voltmarks
Due to the absence of spatial-temporal traceability, static optical codes present considerable security risks and are thus confined to limited applications (for instance, transactions using static QR codes for mobile payments are capped at 500 RMB or about 76 USD daily in China). While dynamic codes that update periodically can mitigate these issues, they necessitate additional hardware, such as screens and computing devices. To overcome these limitations, we introduce Voltmark, a novel approach that enhances the spatial-temporal traceability of static optical codes to the level of dynamic ones through the use of voltmarks---natural watermarks generated by AC flickering during image capture indoors. Voltmarks carry unique temporal and spatial characteristics of the AC and bulbs, allowing for the verification of the time and location where code photographs were taken. This functionality effectively thwarts various security threats and fraudulent activities. Extensive evaluation demonstrates that Voltmark maintains an average accuracy of 93.3% in spatial tracing and delivers a time resolution of 42ms (equivalent to scanning at 24 fps). These outcomes solidly establish Voltmark as a reliable technique for boosting the security of optical codes.
- Open Access
- 14 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 261-270
In-Sensor Machine Learning: Radio Frequency Neural Networks for Wireless Sensing
Growing interest in wireless sensing, a cornerstone of the Artificial Intelligence of Things (AIoT), stems from its ability to gauge target states through nearby wireless signals. However, the escalating count of AIoT nodes escalates redundant data flow and exacerbates energy usage in AI cloud infrastructures. This amplifies the urgency for machine learning techniques that function in proximity to, or directly within, sensors. In light of this, we present the Radio-Frequency Neural Network (RFNN), a novel architecture that uses cost-effective transmissive intelligent surfaces to mimic the functions of a traditional neural network near (or in) sensors, transforming sensory nodes into intelligent terminals primed for machine learning. We first devised a unique training algorithm to mitigate the issues arising from unmodelable error-backward propagation; secondly, we incorporated contrastive learning to address the issue of blind labels stemming from environmental uncertainties. Our RFNN prototype, resonating at a 5 GHz WiFi bandwidth, has been honed across nine varied sensing tasks. The rigorous evaluation shows that it achieves a mean accuracy of 91.5% while consuming only 67.2 μJ of energy. This positions RFNN as a match in inferencing prowess to its electronic neural network counterparts but with significantly diminished energy demands.
- 14 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 261-270
Open AccessIn-Sensor Machine Learning: Radio Frequency Neural Networks for Wireless Sensing
Growing interest in wireless sensing, a cornerstone of the Artificial Intelligence of Things (AIoT), stems from its ability to gauge target states through nearby wireless signals. However, the escalating count of AIoT nodes escalates redundant data flow and exacerbates energy usage in AI cloud infrastructures. This amplifies the urgency for machine learning techniques that function in proximity to, or directly within, sensors. In light of this, we present the Radio-Frequency Neural Network (RFNN), a novel architecture that uses cost-effective transmissive intelligent surfaces to mimic the functions of a traditional neural network near (or in) sensors, transforming sensory nodes into intelligent terminals primed for machine learning. We first devised a unique training algorithm to mitigate the issues arising from unmodelable error-backward propagation; secondly, we incorporated contrastive learning to address the issue of blind labels stemming from environmental uncertainties. Our RFNN prototype, resonating at a 5 GHz WiFi bandwidth, has been honed across nine varied sensing tasks. The rigorous evaluation shows that it achieves a mean accuracy of 91.5% while consuming only 67.2 μJ of energy. This positions RFNN as a match in inferencing prowess to its electronic neural network counterparts but with significantly diminished energy demands.
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 722-723
POSTER: A One-size-fits-all Solution for Cross-Technology Communication via Transformer
Cross-Technology Communication (CTC) is an emerging technology that enables physical-layer direct communication from a WiFi sender to other Internet of Things (IoT) receivers via waveform emulation. Previous research has primarily relied on the reverse engineering to identify the suitable WiFi payloads capable of emulating waveforms similar to desired IoT packets (e.g., ZigBee). However, this approach has several limitations, including irreversibility, scalability challenges, symbol misalignment, and an over-reliance on empirical methods. In this work, we present XiTuXi, a one-size-fits-all solution to automatically achieve the CTC by taking advantage of the neural machine translation (NMT). Inspired by the task comparability between CTC and homophony-based cross-linguistic communication, we employ a well-known NMT model called Transformer to learn the rationale behind translating bit sequences for CTC without human intervention. Specifically, we introduce forward engineering as a solution to tackle the challenge of acquiring training datasets. By utilizing XiTuXi, we effortlessly achieved CTC across 30 protocol combinations (including 802.11b, g, n, ax, ah → Zig-Bee, Bluetooth, LoRa, and Sigfox), ultimately freeing experts from the tedious tasks they faced previously.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 722-723
Open AccessPOSTER: A One-size-fits-all Solution for Cross-Technology Communication via Transformer
Cross-Technology Communication (CTC) is an emerging technology that enables physical-layer direct communication from a WiFi sender to other Internet of Things (IoT) receivers via waveform emulation. Previous research has primarily relied on the reverse engineering to identify the suitable WiFi payloads capable of emulating waveforms similar to desired IoT packets (e.g., ZigBee). However, this approach has several limitations, including irreversibility, scalability challenges, symbol misalignment, and an over-reliance on empirical methods. In this work, we present XiTuXi, a one-size-fits-all solution to automatically achieve the CTC by taking advantage of the neural machine translation (NMT). Inspired by the task comparability between CTC and homophony-based cross-linguistic communication, we employ a well-known NMT model called Transformer to learn the rationale behind translating bit sequences for CTC without human intervention. Specifically, we introduce forward engineering as a solution to tackle the challenge of acquiring training datasets. By utilizing XiTuXi, we effortlessly achieved CTC across 30 protocol combinations (including 802.11b, g, n, ax, ah → Zig-Bee, Bluetooth, LoRa, and Sigfox), ultimately freeing experts from the tedious tasks they faced previously.
- Open Access
- 29 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 648-662
Enabling Cross-Medium Wireless Networks with Miniature Mechanical Antennas
Within the burgeoning 6G wireless network landscape, there is an intensified push toward achieving all-encompassing accessibility through integrated solutions spanning a multitude of domains. Notwithstanding recent advancements, the conventional relay-centric communication paradigms grapple with scalability and optimal performance issues. In this paper, we introduce MeAnt ---a versatile IoT platform uniquely architected to foster seamless cross-medium communication by leveraging the compact design of piezoelectric-based mechanical antennas (Piezo-MAs). By capitalizing on the propagation attributes of medium-frequency radios emitted from Piezo-MAs, MeAnt promises communication across diverse environments such as air, water, soil, concrete, and even biological tissue, all while maintaining a compact antenna footprint. Moreover, in light of challenges such as potential interference from AM broadcasts and the intrinsic unidirectional nature of Piezo-MAs, we have developed a finely crafted full-stack communication protocol. Comprehensive tests underscore the system's proficiency, demonstrating a penetration depth of up to 10 m in cross-medium environments and realizing a throughput of 8.7 kbps.
- 29 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 648-662
Open AccessEnabling Cross-Medium Wireless Networks with Miniature Mechanical Antennas
Within the burgeoning 6G wireless network landscape, there is an intensified push toward achieving all-encompassing accessibility through integrated solutions spanning a multitude of domains. Notwithstanding recent advancements, the conventional relay-centric communication paradigms grapple with scalability and optimal performance issues. In this paper, we introduce MeAnt ---a versatile IoT platform uniquely architected to foster seamless cross-medium communication by leveraging the compact design of piezoelectric-based mechanical antennas (Piezo-MAs). By capitalizing on the propagation attributes of medium-frequency radios emitted from Piezo-MAs, MeAnt promises communication across diverse environments such as air, water, soil, concrete, and even biological tissue, all while maintaining a compact antenna footprint. Moreover, in light of challenges such as potential interference from AM broadcasts and the intrinsic unidirectional nature of Piezo-MAs, we have developed a finely crafted full-stack communication protocol. Comprehensive tests underscore the system's proficiency, demonstrating a penetration depth of up to 10 m in cross-medium environments and realizing a throughput of 8.7 kbps.
- Open Access
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 70-82
XiTuXi: Sealing the Gaps in Cross-Technology Communication by Neural Machine Translation
Cross-Technology Communication (CTC) is an emerging technology that enables physical-layer direct communication from a WiFi sender to other Internet of Things (IoT) receivers via waveform emulation. The previous works use the reverse engineering to find the appropriate WiFi payload that can emulate the waveform similar to the desired IoT packet in the format of the IoT protocol (e.g., ZigBee). Unfortunately, the reverse engineering approach suffers from many limitations, such as being non-reversible and unscalable, misaligning symbols, and over-relying on empiricism. In this work, we present XiTuXi, a one-size-fits-all solution to automatically achieve the CTC by taking advantage of the neural machine translation (NMT), inspired by the task comparability between CTC and homophony-based cross-linguistic communication. We employ a well-known NMT model called Transformer to learn the bit-sequence to bit-sequence translation rationale behind the CTC without human intervention. Particularly, we introduce the forward engineering to address the dilemma of acquiring training datasets. By using XiTuXi, we achieved the CTC with 30 protocol combinations (ie., 802.11b, g, n, ax, ah Å ZigBee, Bluetooth, LoRa, and Sigfox) effortlessly, which ultimately liberates the experts from previous tedious tasks.
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 70-82
Open AccessXiTuXi: Sealing the Gaps in Cross-Technology Communication by Neural Machine Translation
Cross-Technology Communication (CTC) is an emerging technology that enables physical-layer direct communication from a WiFi sender to other Internet of Things (IoT) receivers via waveform emulation. The previous works use the reverse engineering to find the appropriate WiFi payload that can emulate the waveform similar to the desired IoT packet in the format of the IoT protocol (e.g., ZigBee). Unfortunately, the reverse engineering approach suffers from many limitations, such as being non-reversible and unscalable, misaligning symbols, and over-relying on empiricism. In this work, we present XiTuXi, a one-size-fits-all solution to automatically achieve the CTC by taking advantage of the neural machine translation (NMT), inspired by the task comparability between CTC and homophony-based cross-linguistic communication. We employ a well-known NMT model called Transformer to learn the bit-sequence to bit-sequence translation rationale behind the CTC without human intervention. Particularly, we introduce the forward engineering to address the dilemma of acquiring training datasets. By using XiTuXi, we achieved the CTC with 30 protocol combinations (ie., 802.11b, g, n, ax, ah Å ZigBee, Bluetooth, LoRa, and Sigfox) effortlessly, which ultimately liberates the experts from previous tedious tasks.
- Open Access
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Radio Frequency Neural Networks for Wireless Sensing
Wireless sensing has attracted considerable attention because it can sense the state of the targets by analyzing the surrounding wireless signals, which has become the key role of the artificial intelligence of things (AIoT). As the number of sensory nodes increases, large amounts of redundant data are exchanged between sensory terminals and the AI cloud. To process such large amounts of data efficiently and decrease power consumption, a machine-learning approach that operates close to or inside sensors must be developed. To this end, we present the radio-frequency neural network (RFNN), a physical neural network taking advantage of a group of transmissive intelligent surfaces (i.e., metasurfaces) to mimic the computations of a fully-connected neural network. The design is spurred by the capability of RFNNs to perform expensive multiplication and additions at the speed of light, with ultra-low power consumption. We prototype RFNN at 5 GHz for WiFi sensing regarding nine wireless sensing tasks. Extensive evaluations demonstrate the comparably equivalent inference ability as the conventional electronic neural networks while consuming less energy.
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessRadio Frequency Neural Networks for Wireless Sensing
Wireless sensing has attracted considerable attention because it can sense the state of the targets by analyzing the surrounding wireless signals, which has become the key role of the artificial intelligence of things (AIoT). As the number of sensory nodes increases, large amounts of redundant data are exchanged between sensory terminals and the AI cloud. To process such large amounts of data efficiently and decrease power consumption, a machine-learning approach that operates close to or inside sensors must be developed. To this end, we present the radio-frequency neural network (RFNN), a physical neural network taking advantage of a group of transmissive intelligent surfaces (i.e., metasurfaces) to mimic the computations of a fully-connected neural network. The design is spurred by the capability of RFNNs to perform expensive multiplication and additions at the speed of light, with ultra-low power consumption. We prototype RFNN at 5 GHz for WiFi sensing regarding nine wireless sensing tasks. Extensive evaluations demonstrate the comparably equivalent inference ability as the conventional electronic neural networks while consuming less energy.