Article
Ergonomics
Jan Schnee, Juergen Stegmaier, Pu Li
Summary: The study proposes an online approach based on IMU signals to classify bicycle crashes, functioning as a trigger for an automatic emergency system. Utilizing decision trees and probabilistic models, different kinematic events and crash scenarios are classified. The model's accuracy is verified through a series of driving tests, showing high sensitivity and specificity.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Computer Science, Theory & Methods
Zhongcheng Lei, Hong Zhou, Wenshan Hu, Guo-Ping Liu
Summary: This paper explores a novel system constructed based on front-end and back-end separation, which allows concurrent interactive experiments for multiple users, enabling massive access to virtual experimentation and avoiding the need for advance booking or queuing.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Information Systems
Devaprakash Muniraj, Mazen Farhood
Summary: This article presents a scalable approach for identifying system inputs and trajectories that lead to undesirable scenarios in a cyber-physical system. The approach falls under the broad class of falsification methods, which aim to find initial conditions and input signals violating a system property expressed as a formal specification. The existing falsification methods are not suitable for systems with input dependencies on the system's state history. The proposed approach utilizes a graph-search-based motion planning algorithm and a surrogate model to improve scalability and computational efficiency in finding falsifying trajectories.
IEEE SYSTEMS JOURNAL
(2023)
Article
Business
Zaoli Yang, Weijian Zhang, Fei Yuan, Nazrul Islam
Summary: This research introduces a novel method that analyzes knowledge and social sentiment within online communities to discover topical coverage of emerging technology and track technological trends. By studying data from Zhihu, an online Q&A community, they built a network to identify technology trends based on question-and-answer and social sentiment data.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Computer Science, Interdisciplinary Applications
Yuzhi Fang, Li Liu
Summary: This paper introduces a novel scalable supervised online hashing method to solve the problems of learning compact binary codes for new data streams and updating hash functions. By establishing a similarity matrix and using an alternate optimization algorithm, the method effectively addresses data imbalance and achieves superior performance in terms of accuracy and scalability for online retrieval tasks.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2021)
Article
Multidisciplinary Sciences
Valeria P. Catalani, Honor Townshend, Mariya Prilutskaya, Robert Chilcott, Antonio Metastasio, Hani Banayoti, Tim McSweeney, Ornella Corazza
Summary: The study aimed to identify the availability of unlicenced COVID-19 products on Dark Web Markets (DWMs). A retrospective search was conducted across 118 DWMs from March 2020 to October 2021, resulting in the identification of 42 listings of unlicenced COVID-19 cures and vaccination certificates. The study also revealed correlations between vendors selling COVID-19 products and other illicit goods.
Article
Automation & Control Systems
Mahya Adibi, Jacob van der Woude
Summary: In this article, a reinforcement learning-based scheme for secondary frequency control of lossy inverter-based microgrids is proposed. The scheme does not require a priori information and can achieve frequency synchronization in complex environments.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Computer Science, Information Systems
Sawsan Almahmoud, Bassam Hammo, Bashar Al-Shboul, Nadim Obeid
Summary: This paper proposes a hybrid approach using two-level fingerprints to detect illegitimate non-human traffic, and experimental results show that it can effectively detect fake clicks.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Zequn Niu, Jingfeng Xue, Dacheng Qu, Yong Wang, Jun Zheng, Hongfei Zhu
Summary: This paper proposes an approach based on adaptive online analysis to accurately determine the families of malware in Industrial Internet of Things (IIoT) by analyzing encrypted, drift, and imbalanced traffic streams. The experiments show that the proposed method achieves a high classification accuracy.
INFORMATION SCIENCES
(2022)
Article
Ergonomics
Jimoku Hinda Salum, Angela E. Kitali, Thobias Sando, Priyanka Alluri
Summary: The research examined the safety benefits of Florida's Road Rangers freeway service patrol program in reducing the likelihood of secondary crashes compared to other responding agencies. Factors like an increase in equivalent hourly traffic volume, incident impact duration, and the percentage of lanes closed were found to significantly increase the likelihood of a secondary crash. The model showed that a 16-minute decrease in incident impact duration could reduce the probability of secondary crashes by 21% in the Road Rangers program.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Computer Science, Artificial Intelligence
David Haldimann, Marco Guerriero, Yannick Maret, Nunzio Bonavita, Gregorio Ciarlo, Marta Sabbadin
Summary: The detection and identification of sensor faults are crucial for the efficient operation of modern industrial processing systems. This article introduces a novel approach using a disentangled recurrent neural network and a probabilistic model to accurately identify faulty sensors in sensor fault detection and isolation.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Bo Yang, Yanyong Guo, Weihua Zhang, Ying Yao, Yiping Wu
Summary: This study explores the relationship between traffic flow states and crash type/severity using association rules mining approach. The results show that different traffic flow states are associated with different crash types, and unsafe driving behaviors can increase the proportion of crashes. These findings have the potential to reduce the probability of secondary crashes.
IET INTELLIGENT TRANSPORT SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Shushman Choudhury, Jayesh K. Gupta, Peter Morales, Mykel J. Kochenderfer
Summary: We present a scalable tree search planning algorithm for large multi-agent sequential decision problems that require dynamic collaboration. Our algorithm allows for trading computation for approximation quality and dynamically coordinating actions.
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
(2022)
Article
Computer Science, Information Systems
Yamina Moualkia, Mourad Amad, Abderrahmane Baadache
Summary: This paper proposes a decentralized architecture for online social networks based on a peer-to-peer infrastructure. Through the design of hierarchical architecture, the performance is improved and the issues of data privacy and anonymity are addressed.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Health Care Sciences & Services
Mingda Li, Jinhe Shi, Yi Chen
Summary: This study aims to identify influential posts in online health communities that impact decision-making. By utilizing a deep learning model and text relevance measurement methods, the researchers successfully identified these influence relationships and demonstrated the effectiveness of their approach. The findings indicate that these discussions have a significant impact on user decision-making processes and encourage active engagement in health communities.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2022)
Article
Environmental Studies
Hongtai Yang, Guocong Zhai, Linchuan Yang, Kun Xie
Summary: A survey conducted in Chengdu, China found that most ride-sourcing users would shift to public transit when ride-sourcing services are suspended, significantly reducing vehicle emissions. Factors such as age, gender, household income, number of cars per person, trip purpose, and transit accessibility have a significant influence on alternative mode choice.
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT
(2022)
Article
Engineering, Electrical & Electronic
Songhua Hu, Hangfei Lin, Xiaohong Chen, Kun Xie, Xiaonian Shan
Summary: This study analyzes over five million transactions data from the largest EV sharing company in Shanghai, aiming to understand users' decision-making, usage frequencies, and vehicle preferences. The findings reveal a positive relationship between the number of coupons and monthly usage frequency, higher usage frequencies in areas with poor transit access, significant impact of state of charge on users' vehicle preferences, and users' preferences for newer vehicles with more seats, lower rental prices, and longer battery ranges.
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
(2022)
Article
Engineering, Civil
Xuesong Wang, Dongjie Tang, Saijun Pei, Penghui Li, Rongjie Yu, Kun Xie
Summary: Safety performance functions (SPFs) are important in roadway safety management. However, due to the lack of local data, transferring and calibrating SPFs is necessary. This study explored the transferability of SPFs from Shanghai to Guangzhou and found that calibration is required. Various calibration methods were compared, and the best method was recommended.
JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS
(2022)
Article
Economics
Guocong Zhai, Kun Xie, Di Yang, Hong Yang
Summary: This study proposes a novel causal inference approach that integrates propensity score matching and spatial difference-in-differences to estimate the safety effectiveness of citywide speed limit reduction in NYC. The results suggest a significant decrease in fatal crashes and a significant spatial spillover effect, but no significant change in injury and property-damage-only crashes.
TRANSPORTATION RESEARCH PART A-POLICY AND PRACTICE
(2022)
Article
Geography
Hongtai Yang, Jinghai Huo, Renbin Pan, Kun Xie, Wenjia Zhang, Xinggang Luo
Summary: This study examines the market share of traditional taxis and ridesourcing services using panel fractional regression model based on the taxi trip data of New York City in 2017. The results indicate that the market share of ridesourcing services is higher in remote areas, areas with low population density, low density of transportation facilities, low household income, and high proportion of young residents.
Article
Environmental Studies
Qingyu Ma, Yanan Xin, Hong Yang, Kun Xie
Summary: The rise of shared electric scooter systems has provided urban areas with a new solution for micro-mobility. This study explores the integration of shared e-scooters with public transportation systems and compares their usage to shared bikes and taxis for connecting trips from/to metro stations. The results show that the preferences for shared e-scooters vary depending on land use and time period, and differ from shared bikes and taxis.
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT
(2022)
Article
Engineering, Civil
Pengyao Ye, Yifeng Deng, Hong Yang, Wenbo Fan
Summary: This study examines the route choice behavior of bus passengers in terms of transfer penalty estimation. It compares the stop-level origin-destination (O-D) pairs of direct paths and transfer paths using trip information inferred from automatic vehicle location (AVL) and automated fare collection (AFC) data. The results show that the normalized travel frequency is an important variable in explaining passenger route choices, with passengers who travel more frequently opting for transfer paths.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Defu Cui, Yuzhong Shen, Hong Yang, Zhitong Huang, Kyle Rush, Peter Huang, Pavle Bujanovic
Summary: This paper aims to develop a co-simulation framework for testing autonomous driving and cooperative driving automation. The framework integrates multiple open-source platforms and has been proven to be extensible and provide more realistic scenarios.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Giridhar Kattepogu, Mecit Cetin, Behrouz Salahshour, Hong Yang, Kun Xie
Summary: Measuring demand directly with vehicle sensors is not possible when demand exceeds capacity. This study proposes two methods based on probe vehicle speeds and capacity data to estimate demand volume. The methods are tested and validated using simulation and field data, showing less than 4% error.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Qingyu Ma, Hong Yang, Zizheng Yan
Summary: With the growing demand for short-distance trips in urban areas, safety issues related to shared electric scooters have become a major concern. This study quantitatively assesses the impact of different wheel sizes on riders' experiences using mobile sensing data. The results indicate that larger-wheel e-scooters effectively reduce vibrations during rides, suggesting their potential for improving riding experience and safety.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Mohammad Bagheri, Bekir Bartin, Kaan Ozbay
Summary: This study aimed to evaluate the impact of various operational and design alternatives at roundabouts and traffic circles using microscopic simulation tools. Accurately modeling drivers' gap acceptance behavior is crucial for the effectiveness of traffic operations at these intersections. An artificial neural network (ANN)-based gap acceptance model was implemented in SUMO, and compared with the default model calibrated using field data. The results showed that the ANN-based model provided accurate outputs and realistic vehicle crossings at uncontrolled intersections.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Ergonomics
Hongyu Guo, Kun Xie, Mehdi Keyvan-Ekbatani
Summary: This study develops a lane-change related evasive behavior model using large-scale connected vehicle data. A new surrogate safety measure called 2D-TTC is proposed to identify safety-critical situations during lane changes. The deep deterministic policy gradient algorithm is used to simulate evasive behaviors in these situations, and the results show the superiority of the model.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Engineering, Industrial
Chuan Xu, Kaan Ozbay, Hongling Liu, Kun Xie, Di Yang
Summary: This study utilized five years of extensive Weigh-in-Motion data from 88 stations in New Jersey to examine the impact of truck traffic characteristics on the proportions of severe crashes on road segments. The results showed that the mean vehicle weight was significantly and positively related to the proportion of severe crashes on road segments. For road segments with nonzero proportions of severe crashes, a 1 kip increase in mean vehicle weight led to a 3.3% increase in total crash proportion, a 3.4% increase in single-vehicle crash proportion, and a 2.2% increase in multiple-vehicle crash proportion.
Article
Engineering, Industrial
Di Yang, Kaan Ozbay, Kun Xie, Hong Yang
Summary: Before-after analysis methods in traffic safety often use long aggregation time periods to aggregate traffic crashes and assume that the treatment effect is temporally stable. However, certain treatments, such as the COVID-19 pandemic, may lead to fast-evolving changes to road safety. This study proposes a survival analysis with random parameter (SARP) approach that can accommodate the temporal instability in treatment effect at various temporal levels. The proposed SARP method is validated and tested through a statistical simulation study and an empirical case study on the safety impact of COVID-19 lockdown in Manhattan, New York.