- Infrastructure Maintenance and Monitoring
- BIM and Construction Integration
- Geophysical Methods and Applications
- Topic Modeling
- Underground infrastructure and sustainability
- 3D Surveying and Cultural Heritage
- Asphalt Pavement Performance Evaluation
- Design Education and Practice
- Speech and dialogue systems
- Analog and Mixed-Signal Circuit Design
- Energy Harvesting in Wireless Networks
- Image Processing and 3D Reconstruction
- Machine Learning in Healthcare
- Vehicle License Plate Recognition
- Natural Language Processing Techniques
- Generative Adversarial Networks and Image Synthesis
- Indoor and Outdoor Localization Technologies
- Underwater Acoustics Research
- Color perception and design
- Digital Transformation in Industry
- Environmental Impact and Sustainability
- Video Surveillance and Tracking Methods
- Hand Gesture Recognition Systems
- Aesthetic Perception and Analysis
- Health, Environment, Cognitive Aging
Southwest University
2024
University of Macau
2024
University of Pennsylvania
2023-2024
Southern Illinois University Edwardsville
2020-2023
Penn Center for AIDS Research
2023
Universidad del Noreste
2023
California University of Pennsylvania
2023
Xi'an Jiaotong University
2020-2022
Northeastern University
2020-2022
University Town of Shenzhen
2020
Manufacturing has adopted technologies such as automation, robotics, industrial Internet of Things (IoT), and big data analytics to improve productivity, efficiency, capabilities in the production environment. Modern manufacturing workers not only need be adept at traditional but also ought trained advanced data-rich computer-automated technologies. This study analyzes science (DSA) skills gap today's workforce identify critical technical domain knowledge required for intelligent...
Abstract In recent years, driven by Industry 4.0 wave, academic research has focused on the science, engineering, and enabling technologies for intelligent cyber manufacturing. Using a network science data mining-based Keyword Co-occurrence Network (KCN) methodology, this work analyzes trends in topics manufacturing literature over past two decades to inform researchers, educators, industry leaders of knowledge It studies evolution methods Internet Things (IoT), cloud computing, The KCN...
A pothole is a severe pavement distress that can compromise rideability and safety be the cause of expensive damage claims. The detection evaluation potholes are predominantly manual time-consuming. Although sensing technologies such as global positioning systems (GPS), stereovision systems, ground penetrating radar (GPR) now combined to collect condition data for assessment, raw returned by these sensors often processed individually separately. This isolated approach processing hinders...
Enhancing workplace safety continues to be a major task in the construction industry. Approximately 75% of struck-by fatalities are caused by inappropriate spatial-temporal relationships between workers and heavy equipment. Construction can improved if location movement equipment tracked real time. However, detecting tracking with kinematic joints changing poses, such as excavators, is still challenge for vision-based sensing methods. This study proposes detect track excavators using stereo...
The designers' tendency to adhere a specific mental set and heavy emotional investment in their initial ideas often limit ability innovate during the design ideation process. shrinking time-to-market growing diversity of users' needs further exacerbate this gap. Recent advances deep generative models have created new possibilities overcome cognitive obstacles designers through automated generation or editing concepts. This article explores capabilities adversarial networks (GAN) for...
The information of exact locations underground utilities is an essential piece evidence for preventing utility strikes in excavation work. Ground penetrating radar (GPR), which has emerged as a promising, nondestructive solution this purpose, capable capturing reflections that are then recorded GPR scans. To determine the location, dimension, size, and spatial configuration pipes, radargrams must be further interpreted to extract shapes (e.g., hyperbolas lines) identify feature components...
Importance Predictive models using machine learning techniques have potential to improve early detection and management of Alzheimer disease (AD). However, these potentially biases may perpetuate or exacerbate existing disparities. Objective To characterize the algorithmic fairness longitudinal prediction for AD progression. Design, Setting, Participants This prognostic study investigated logistic regression, support vector machines, recurrent neural networks predicting progression mild...
The radio frequency identification (RFID) technology has proven its potential in locating and tracking construction resources, a critical task project control. However, the main challenge is how to achieve desired levels of accuracy. This paper presents an enhanced boundary condition method that incorporates tag-reader angle reader geometric configuration factors control accuracy system integrates RFID real time kinematic (RTK) global positioning (GPS). Controlled laboratory experiments were...
In their pursuit of ensuring the quality and long-term performance pavements, state highway agencies (SHAs) have established specifications for materials testing construction inspection processes as critical components assurance programs. SHAs face a grand challenge, however, in ever-growing gap between demand available resources. Many strategies been proposed over time to meet this challenge by optimizing resource allocation process. A promising approach is allocate limited resources most...
Inspection is critical to ensuring the quality of infrastructure construction. In recent years, state highway agencies (SHAs) have been facing challenge a shortage experienced inspectors due retirements, workforce downsizing, and resignations take jobs in private sector. There need retain manage accumulated construction inspection knowledge (what, when, how inspect) integrate this into business process. This paper presents an ontological approach managing development risk-based digital...
Abstract Design concept evaluation is a key process in the new product development with significant impact on product's success and total cost over its life cycle. This paper motivated by two limitations of state-of-the-art evaluation: (1) The amount diversity user feedback insights utilized existing methods such as quality function deployment are limited. (2) Subjective require manual effort which turn may limit number concepts considered for evaluation. A Deep Multimodal Evaluation (DMDE)...
Abstract Generative adversarial networks (GANs) have shown remarkable success in various generative design tasks, from topology optimization to material design, and shape parametrization. However, most approaches based on GANs lack evaluation mechanisms ensure the generation of diverse samples. In addition, no GAN-based model incorporates user sentiments loss function generate samples with high desirability aggregate perspectives users. Motivated by these knowledge gaps, this paper builds...
Abstract Generative adversarial networks (GANs) have recently been proposed as a potentially disruptive approach to generative design due their remarkable ability generate visually appealing and realistic samples. Yet, we show that the current generator-discriminator architecture inherently limits of GANs concept generation (DCG) tool. Specifically, conduct DCG study on large-scale dataset based GAN advance understanding performance these models in generating novel diverse Our findings,...
Transportation asset management (TAM) demands a data-driven decision-making process to proactively maintain, preserve, and extend the long-term service life of transportation assets. State highway agencies (SHAs) typically wait inventory their assets according locations, dimensions, material types properties after they are constructed open traffic. However, construction phase is best time collect data because access easier safer, more importantly, needed for operation maintenance (O&M)...
Deep Learning Approach for Volume Estimation inEarthmoving Operation been developed to estimate earth volume by classifying the images into different levels.Next, we applied transfer learning a pre-trained deep convolutional neural network in order improve classification performance.For evaluation of approach, models have trained and tested using miniature trucks loaded with amounts earth, ranging between 0 1000 ml up six classes at 200 intervals.The experimental results showed that achieved...
Abstract Generative Adversarial Networks (GANs) have shown stupendous power in generating realistic images to an extend that human eyes are not capable of recognizing them as synthesized. State-of-the-art GAN models and high-quality images, which promise unprecedented opportunities for design concepts. Yet, the preliminary experiments reported this paper shed light on a fundamental limitation GANs generative design: lack novelty diversity generated samples. This article conducts study...
In this paper, we consider multi-user multiple-input multiple-output (MU-MIMO) system with a full-duplex (FD) base station (BS) and number of FD users. The BS is equipped large-scale antenna arrays, while each user two antennas (one for transmitting the other one receiving). linear signal processing technique based on maximum-ratio combining/maximum-ratio transmission (MRC/MRT) adopted at BS. asymptotic expressions signal-to-interference-plus-noise ratio (SINR) uplink downlink are derived...
This brief presents an all-digital low dropout regulator (DLDO) with high regulating resolution and fast transient tracking by combining novel interval-searching algorithm recover acceleration techniques. By bringing forth enhanced (ISA) 9-bit register precision, the output can be stabilized within 8 cycles when load changes. A (RA) technique is proposed to improve response stability. The DLDO fabricated standard 180-nm CMOS process. needs 390 pF capacitance provide as much 170 mA current....
Object detection and tracking is a challenging problem in the dynamic construction environment, especially for objects with kinematic joints changing poses, e.g. excavators. This paper presents key nodes model dynamically detecting locating movable sites using color-depth cameras. The designed by first analyzing constraints from mechanic specifications of interested site then building representative segmented contour templates under supervision. Feature matching realized comparing real...
Rice is a globally important food crop, and it crucial to accurately conveniently obtain information on rice fields, understand their spatial patterns, grasp dynamic changes address security challenges. In this study, Chongqing’s Yongchuan District was selected as the research area. By utilizing UAVs (Unmanned Aerial Vehicles) collect multi-spectral remote sensing data during three seasons, phenological characteristics of fields were analyzed using NDVI (Normalized Difference Vegetation...
Abstract Missing data is a significant challenge in medical research. In longitudinal studies of Alzheimer’s disease (AD) where structural magnetic resonance imaging (MRI) collected from individuals at multiple time points, participants may miss study visit or drop out. Additionally, technical issues such as participant motion the scanner result unusable designated visits. Such missing hinder development high-quality imaging-based biomarkers. To address problem MRI AD, we introduced novel 3D...