HL

Hao Liu

info

Please Note

5 records found

Transit-prioritized max-pressure control in sparse connected vehicle environments

Journal article (2027) - Chaopeng Tan, Hao Liu, Dingshan Sun, Marco Rinaldi, Hans van Lint
Max-pressure (MP) control stands out among real-time network traffic signal control methods due to its simplicity, decentralized nature, and theoretical stability. However, existing MP control methods have limited consideration of public transportation and do not address the network stability problem of transit-prioritized MP in partially connected vehicle (CV) environments. In this study, we propose Transit-MP, which realizes transit-prioritized MP control in partially CV environments by considering real-time vehicle occupancy and the impact of transit dwell at stations. Theoretically, we demonstrate that Transit-MP, while using different traffic state measures for upstream and downstream links for pressure calculation, still achieves road network stability even in partially CV environments. Note that for MP controllers in sparse CV environments, some movements may have missing CV observations, leading to link spillovers, which create the queue starvation phenomenon: a movement no longer receives the green phase despite the queue spillover. Therefore, we further propose a modified Transit-MP (mTransit-MP) that uses historical traffic data as a fallback under zero-CV-observation conditions to address this issue. We rigorously prove that the proposed mTransit-MP can effectively avoid the queue starvation phenomenon. Experimental results on a real-world corridor in Amsterdam with 15 transit lines and 31 stations show that our method significantly reduces the real-time vehicle and spillover count, and improves delays for both private vehicles and transit vehicles compared to a state-of-the-art MP controller for transit signal priority. In sparse CV environments, our mTransit-MP is effective in mitigating link spillovers while enhancing the overall performance of multi-modal traffic. ...

Max-pressure control in heterogeneously distributed and partially connected vehicle environments

Journal article (2026) - Chaopeng Tan, Dingshan Sun, Hao Liu, Marco Rinaldi, Hans van Lint
Max-pressure (MP) control has emerged as a prominent real-time network traffic signal control strategy due to its simplicity, decentralized structure, and theoretical guarantees of network queue stability. Meanwhile, advances in connected vehicle (CV) technology have sparked extensive research into CV-based traffic signal control. Despite these developments, few studies have investigated MP control in heterogeneously distributed and partially CV environments while ensuring network queue stability. To address these research gaps, we propose a CV-based MP control (CV-MP) method that leverages real-time CV travel time information to compute the pressure, thereby incorporating both the spatial distribution and temporal delays of vehicles, unlike existing approaches that utilized only spatial distribution or temporal delays. In particular, we establish sufficient conditions for road network queue stability that are compatible with most existing MP control methods. Moreover, we pioneered the proof of network queue stability even if the vehicles are only partially connected and heterogeneously distributed, and gave a necessary condition of CV observation for maintaining the stability. Evaluation results on an Amsterdam corridor show that CV-MP significantly reduces vehicle delays compared to both actuated control and conventional MP control across various CV penetration rates. Moreover, in scenarios with dynamic traffic demand, CV-MP achieves lower spillover peaks even with low and heterogeneous CV penetration rates, further highlighting its effectiveness and robustness. ...

EODL: Energy-Aware On-Device Training on Microcontrollers

Conference paper (2026) - Hao Liu, Shashwath Suresh, Marco Zuniga
Deep learning models can be trained on microcontrollers (MCUs) for privacy-sensitive applications, but such training is severely constrained by tiny SRAM capacity and limited battery energy. Existing on-device learning methods optimise memory usage by selectively freezing layers so that training fits within SRAM budgets, yet none explicitly account for training energy. A strategy that is feasible in memory may therefore still consume significantly more energy than necessary, shortening battery life on energyconstrained devices. We present eODL, an energy-aware on-device learning framework. eODL exploits two observations: (1) counts of multiplyaccumulate operations (MACs) predict training energy with high fidelity (R2 = 0.993), so energy can be estimated; and (2) energyaware layer-update selection can be solved efficiently with tabular dynamic programming. Using these, eODL selects which layers to update under a hard SRAM budget while balancing energy against accuracy. We implement eODL end to end on STM32 MCUs and evaluate it on MCUNetV2 fine-tuned on the Flowers-102 dataset. Under a 50 kB training-memory budget, eODL matches state-of-the-art accuracy while reducing measured on-device energy by 22.6% per epoch. ...

Fingerprinting USB Powered Peripherals via Power Side-channel

Conference paper (2023) - Riccardo Spolaor, Hao Liu, Federico Turrin, Mauro Conti, Xiuzhen Cheng
The literature and the news regularly report cases of exploiting Universal Serial Bus (USB) devices as attack tools for malware injections and private data exfiltration. To protect against such attacks, security researchers proposed different solutions to verify the identity of a USB device via side-channel information (e.g., timing or electromagnetic emission). However, such solutions often make strong assumptions on the measurement (e.g., electromagnetic interference-free area around the device), on a device’s state (e.g., only at the boot or during specific actions), or are limited to one particular type of USB device (e.g., flash drive or input devices).In this paper, we present PowerID, a novel method to fingerprint USB peripherals based on their power consumption. PowerID analyzes the power traces from a peripheral to infer its identity and properties. We evaluate the effectiveness of our method on an extensive power trace dataset collected from 82 USB peripherals, including 35 models and 8 types. Our experimental results show that PowerID accurately recognizes a peripheral type, model, activity, and identity. ...
Conference paper (2021) - Hao Liu, Hanting Ye, Jie Yang, Qing Wang
Motivated by the trend of realizing full screens on devices such as smartphones, in this work we propose through-screen sensing with visible light for the application of fingertip air-writing. The system can recognize handwritten digits with under-screen photodiodes as the receiver. The key idea is to recognize the weak light reflected by the finger when the finger writes the digits on top of a screen. The proposed air-writing system has immunity to scene changes because it has a fixed screen light source. However, the screen is a double-edged sword as both a signal source and a noise source. We propose a data preprocessing method to reduce the interference of the screen as a noise source. We design an embedded deep learning model, a customized model ConvRNN, to model the spatial and temporal patterns in the dynamic and weak reflected signal for air-writing digits recognition. The evaluation results show that our through-screen fingertip air-writing system with visible light can achieve accuracy up to 91%. Results further show that the size of the customized ConvRNN model can be reduced by 94% with less than a 10% drop in performance. ...