arXiv subjects

Peng Hao

Publications and source records attributed to Peng Hao.

31 records · Page 2Linked to original sources

arXiv2023

Integrated Simulation Platform for Quantifying the Traffic-Induced Environmental and Health Impacts

Air quality and human exposure to mobile source pollutants have become major concerns in urban transportation. Existing studies mainly focus on mitigating traffic congestion and reducing carbon footprints, with limited understanding of traffic-related health impacts from the environmental justice perspective. To address this gap, we present an innovative integrated simulation platform that models traffic-related air quality and human exposure at the microscopic level. The platform consists of five modules: SUMO for traffic modeling, MOVES for emissions modeling, a 3D grid-based dispersion model, a Matlab-based concentration visualizer, and a human exposure model. Our case study on multi-modal mobility on-demand services demonstrates that a distributed pickup strategy can reduce human cancer risk associated with PM2.5 by 33.4% compared to centralized pickup. Our platform offers quantitative results of traffic-related air quality and health impacts, useful for evaluating environmental issues and improving transportation systems management and operations strategies.

physics.soc-ph↗

arXiv2022

Attend and select: A segment selective transformer for microblog hashtag generation

Hashtag generation aims to generate short and informal topical tags from a microblog post, in which tokens or phrases form the hashtags. These tokens or phrases may originate from primary fragmental textual pieces (e.g., segments) in the original text and are separated into different segments. However, conventional sequence-to-sequence generation methods are hard to filter out secondary information from different textual granularity and are not good at selecting crucial tokens. Thus, they are suboptimal in generating more condensed hashtags. In this work, we propose a modified Transformer-based generation model with adding a segments-selection procedure for the original encoding and decoding phases. The segments-selection phase is based on a novel Segments Selection Mechanism (SSM) to model different textual granularity on global text, local segments, and tokens, contributing to generating condensed hashtags. Specifically, it first attends to primary semantic segments and then transforms discontinuous segments from the source text into a sequence of hashtags by selecting crucial tokens. Extensive evaluations on the two datasets reveal our approach's superiority with significant improvements to the extraction and generation baselines. The code and datasets are available at https://github.com/OpenSUM/HashtagGen.

cs.CL↗

arXiv2022

Spatiotemporal Transformer Attention Network for 3D Voxel Level Joint Segmentation and Motion Prediction in Point Cloud

Environment perception including detection, classification, tracking, and motion prediction are key enablers for automated driving systems and intelligent transportation applications. Fueled by the advances in sensing technologies and machine learning techniques, LiDAR-based sensing systems have become a promising solution. The current challenges of this solution are how to effectively combine different perception tasks into a single backbone and how to efficiently learn the spatiotemporal features directly from point cloud sequences. In this research, we propose a novel spatiotemporal attention network based on a transformer self-attention mechanism for joint semantic segmentation and motion prediction within a point cloud at the voxel level. The network is trained to simultaneously outputs the voxel level class and predicted motion by learning directly from a sequence of point cloud datasets. The proposed backbone includes both a temporal attention module (TAM) and a spatial attention module (SAM) to learn and extract the complex spatiotemporal features. This approach has been evaluated with the nuScenes dataset, and promising performance has been achieved.

cs.CV↗

arXiv2022

Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections

Taking advantage of both vehicle-to-everything (V2X) communication and automated driving technology, connected and automated vehicles are quickly becoming one of the transformative solutions to many transportation problems. However, in a mixed traffic environment at signalized intersections, it is still a challenging task to improve overall throughput and energy efficiency considering the complexity and uncertainty in the traffic system. In this study, we proposed a hybrid reinforcement learning (HRL) framework which combines the rule-based strategy and the deep reinforcement learning (deep RL) to support connected eco-driving at signalized intersections in mixed traffic. Vision-perceptive methods are integrated with vehicle-to-infrastructure (V2I) communications to achieve higher mobility and energy efficiency in mixed connected traffic. The HRL framework has three components: a rule-based driving manager that operates the collaboration between the rule-based policies and the RL policy; a multi-stream neural network that extracts the hidden features of vision and V2I information; and a deep RL-based policy network that generate both longitudinal and lateral eco-driving actions. In order to evaluate our approach, we developed a Unity-based simulator and designed a mixed-traffic intersection scenario. Moreover, several baselines were implemented to compare with our new design, and numerical experiments were conducted to test the performance of the HRL model. The experiments show that our HRL method can reduce energy consumption by 12.70% and save 11.75% travel time when compared with a state-of-the-art model-based Eco-Driving approach.

eess.SY↗

arXiv2020

End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning

This paper presented a deep reinforcement learning method named Double Deep Q-networks to design an end-to-end vision-based adaptive cruise control (ACC) system. A simulation environment of a highway scene was set up in Unity, which is a game engine that provided both physical models of vehicles and feature data for training and testing. Well-designed reward functions associated with the following distance and throttle/brake force were implemented in the reinforcement learning model for both internal combustion engine (ICE) vehicles and electric vehicles (EV) to perform adaptive cruise control. The gap statistics and total energy consumption are evaluated for different vehicle types to explore the relationship between reward functions and powertrain characteristics. Compared with the traditional radar-based ACC systems or human-in-the-loop simulation, the proposed vision-based ACC system can generate either a better gap regulated trajectory or a smoother speed trajectory depending on the preset reward function. The proposed system can be well adaptive to different speed trajectories of the preceding vehicle and operated in real-time.

cs.CV↗

arXiv2019

Vision-Based Lane-Changing Behavior Detection Using Deep Residual Neural Network

Accurate lane localization and lane change detection are crucial in advanced driver assistance systems and autonomous driving systems for safer and more efficient trajectory planning. Conventional localization devices such as Global Positioning System only provide road-level resolution for car navigation, which is incompetent to assist in lane-level decision making. The state of art technique for lane localization is to use Light Detection and Ranging sensors to correct the global localization error and achieve centimeter-level accuracy, but the real-time implementation and popularization for LiDAR is still limited by its computational burden and current cost. As a cost-effective alternative, vision-based lane change detection has been highly regarded for affordable autonomous vehicles to support lane-level localization. A deep learning-based computer vision system is developed to detect the lane change behavior using the images captured by a front-view camera mounted on the vehicle and data from the inertial measurement unit for highway driving. Testing results on real-world driving data have shown that the proposed method is robust with real-time working ability and could achieve around 87% lane change detection accuracy. Compared to the average human reaction to visual stimuli, the proposed computer vision system works 9 times faster, which makes it capable of helping make life-saving decisions in time.

cs.CV↗

arXiv2019

Integrating PHY Security Into NDN-IoT Networks By Exploiting MEC: Authentication Efficiency, Robustness, and Accuracy Enhancement

Recent literature has demonstrated the improved data discovery and delivery efficiency gained through applying named data networking (NDN) to a variety of information-centric Internet of things (IoT) applications. However, from a data security perspective, the development of NDN-IoT raises several new authentication challenges. In particular, NDN-IoT authentication may require per-packet-level signatures, thus imposing intolerably high computational and time costs on the resource-poor IoT end devices. This paper proposes an effective solution by seamlessly integrating the lightweight and unforgeable physical-layer identity (PHY-ID) into the existing NDN signature scheme for the mobile edge computing (MEC)-enabled NDN-IoT networks. The PHY-ID generation exploits the inherent signal-level device-specific radio-frequency imperfections of IoT devices, including the in-phase/quadrature-phase imbalance, and thereby avoids adding any implementation complexity to the constrained IoT devices. We derive the offline maximum entropy-based quantization rule and propose an online two-step authentication scheme to improve the accuracy of the authentication decision making. Consequently, a cooperative MEC device can securely execute the costly signing task on behalf of the authenticated IoT device in an optimal manner. The evaluation results demonstrate 1) elevated authentication time efficiency, 2) robustness to several impersonation attacks including the replay attack and the computation-based spoofing attack, and 3) increased differentiation rate and correct authentication probability by applying our integration design in MEC-enabled NDN-IoT networks.

eess.SP↗

arXiv2019

Early Findings from Field Trials of Heavy-Duty Truck Connected Eco-Driving System

In recent years, the development of connected and automated vehicle (CAV) technology has inspired numerous advanced applications targeted at improving existing transportation systems. As one of the widely studied applications of CAV technology, connected eco-driving takes advantage of Signal Phase and Timing (SPaT) information from traffic signals to enable CAVs to approach and depart from signalized intersections in an energy-efficient manner. However the majority of the connected eco-driving studies have been numerical or microscopic traffic simulations. Only few studies have implemented the application on real vehicles, and even fewer have been focused on heavy-duty trucks. In this study, we developed a connected eco-driving system and equipped it on a heavy-duty diesel truck using cellular-based wireless communications. Field trials were conducted in the City ofCarson, California, along two corridors with six connected signalized intersections capable of communicating their SPaT information. Early results showed the benefits of the system in smoothing the speed profiles of the equipped truck when approaching the connected signalized intersections.

eess.SY↗

arXiv2019

Raman sideband cooling of $^{25}$Mg$^+$ -$^{27}$Al$^+$ ions pair and observation of quantum logic spectra

We perform quantum logic spectroscopy (QLS) on $^{27}$Al$^+$ ion $^1$S$_0$ - $^3$P$_1$ transition, which is an important step toward the QLS based $^{27}$Al$^+$ ion optical clock. As a precondition of QLS, both the stretch (STR) mode and the common (COM) mode of the $^{27}$Al$^+$ and $^{25}$Mg$^+$ ions pair are cooled to the vibrational ground state by Raman sideband cooling. The mean phonon number is measured to be 0.10(1) for the STR mode and 0.01(1) for the COM mode, respectively. The heating rate is evaluated to be 13(3) phonons/s for the STR mode and 5.5(1) phonons/s for the COM mode.

physics.atom-ph↗

arXiv2018

Cluster-Wise Cooperative Eco-Approach and Departure Application for Connected and Automated Vehicles along Signalized Arterials

In recent years, various versions of the Eco-Approach and Departure (EAD) application have been developed and evaluated. This application utilizes Signal Phase and Timing (SPaT) information to allow connected and automated vehicles (CAVs) to approach and depart from a signalized intersection in an energy-efficient manner. To date, most existing work have studied the EAD application from an ego-vehicle perspective (Ego-EAD) using Vehicle-to-Infrastructure (V2I) communication, while relatively limited research takes into account cooperation among vehicles at intersections via Vehicle-to-Vehicle (V2V) communication. In this research, we developed a cluster-wise cooperative EAD (Coop-EAD) application for CAVs to further reduce energy consumption compared to existing Ego-EAD applications. Instead of considering CAVs traveling through signalized intersections one at a time, our approach strategically coordinates CAVs' maneuvers to form clusters using various operating modes: initial vehicle clustering, intra-cluster sequence optimization, and cluster formation control. The novel Coop-EAD algorithm is applied to the cluster leader, and CAVs in the cluster follow the cluster leader to conduct EAD maneuvers. A preliminary simulation study with a given scenario shows that, compared to an Ego-EAD application, the proposed Coop-EAD application achieves 11% reduction on energy consumption, up to 19.9% reduction on pollutant emissions, and 50% increase on traffic throughput, respectively.

eess.SY↗

arXiv2014

Extending cascading gravity model to lower dimensions

The cascading gravity model was proposed to eliminate instabilities of the original DGP model by embedding our 4D universe into a 5D brane, which is itself embedded in a 6D bulk. Thus gravity cascades from 6D down to 4D as we decrease the length scales. We show that it is possible to extend this setup to lower dimensions as well, i.e. there is a self-consistent embedding of a 3D brane into a 4D brane, which is itself embedded in a 5D bulk and so on. This extension fits well into the "vanishing dimensions" framework in which dimensions open up as we increase the length scales.

gr-qc↗

arXiv2011

Time Evolution of Temperature and Entropy of a Gravitationally Collapsing Cylinder

We investigate the time evolution of the temperature and entropy of a gravitationally collapsing cylinder, represented by an infinitely thin domain wall, as seen by an asymptotic observer. Previous work has shown that the entropy of a spherically symmetric collapsing domain approaches a constant, and we follow this procedure using a (3+1) BTZ metric to see if a different topology will yield different results. We do this by coupling a scalar field to the background of the domain wall and analyzing the spectrum of radiation as a function of time. We find that the spectrum is quasi-thermal, with the degree of thermality increasing as the domain wall approaches the horizon. The thermal distribution allows for the determination of the temperature as a function of time, and we find that the late time temperature is very close to the Hawking temperature and that it also exhibits the proper scaling with the mass. From the temperature we find the entropy. Since the collapsing domain wall is what forms a black hole, we can compare the results to those of the standard entropy-area relation. We find that the entropy does in fact approach a constant that is close to the Hawking entropy. However, the time dependence of the entropy shows that the entropy decreases with time, indicating that a (3+1) BTZ domain wall will not collapse spontaneously.

gr-qc↗

arXiv2010

Classical and Quantum Equations of Motion for a BTZ Black String in AdS Space

We investigate gravitational collapse of a $(3+1)$-dimensional BTZ black string in AdS space in the context of both classical and quantum mechanics. This is done by first deriving the conserved mass per unit length of the cylindrically symmetric domain wall, which is taken as the classical Hamiltonian of the black string. In the quantum mechanical context, we take primary interest in the behavior of the collapse near the horizon and near the origin (classical singularity) from the point of view of an infalling observer. In the absence of radiation, quantum effects near the horizon do not change the classical conclusions for an infalling observer, meaning that the horizon is not an obstacle for him/her. The most interesting quantum mechanical effect comes in when investigating near the origin. First, quantum effects are able to remove the classical singularity at the origin, since the wave function is non-singular at the origin. Second, the Schrödinger equation describing the behavior near the origin displays non-local effects, which depend on the energy density of the domain wall. This is manifest in that derivatives of the wavefunction at one point are related to the value of the wavefunction at some other distant point.

gr-qc↗