Xinming Huang

Prof. Xinming Huang

Worcester Polytechnic Institute, Worcester, Massachusetts, USA
orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 August 2018 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
LBLin Bai
Lin Bai
YZYiming Zhao
Yiming Zhao
XHXinming Huang
Xinming Huang
Convolutional neural networks (CNNs) have been widely deployed in the fields of computer vision and pattern recognition because of their high accuracy. However, large convolution operations are computing intensive and often require a powerful computing platform such as a graphics processing unit. This makes it difficult to apply CNNs to portable devices. The state-of-the-art CNNs, such as MobileNetV2 and Xception, adopt depthwise separable convolution to replace the standard convolution for embedded platforms, which significantly reduces operations and parameters with only limited loss in accuracy. This highly structured model is very suitable for field-programmable gate array (FPGA) implementation. In this brief, a scalable high performance depthwise separable convolution optimized CNN accelerator is proposed. The accelerator can be fit into an FPGA of different sizes, provided the balancing between hardware resources and processing speed. As an example, MobileNetV2 is implemented on Arria 10 SoC FPGA, and the results show this accelerator can classify each picture from ImageNet in 3.75 ms, which is about 266.6 frames per second. The FPGA design achieves 20× speedup if compared to CPU.

26 July 2018 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
HSHongming Shen
Hongming Shen
CXChen Xu
Chen Xu
YYYongjie Yang
Yongjie Yang
LSLing Sun
Ling Sun
ZCZhitian Cai
Zhitian Cai
XHXinming Huang
Xinming Huang
Respiration rate (RR) and heartbeat rate (HR) are important physiological parameters for a person. Impulse radio ultra-wideband (IR-UWB) is a promising technology for non-contact sensing and monitoring. This brief presents a new method based on autocorrelation to measure the RR and HR using IR-UWB radar. The correlation coefficient waveform contains the vital sign signals, overcoming the effect of noise and clutter. Applying fast Fourier transform, the respiration frequency can be acquired easily. A clever method also based on autocorrelation is proposed to locate the subject. The receive signal matrix is divided into a set of bins in the direction of fast time. By removing one block from the matrix each time and re-applying the autocorrelation, the removed block resulting the smallest correlations is corresponding to the location of a subject. Moreover, variational mode decomposition algorithm is adopted to successfully separate the respiration and heartbeat signals. Experiments are carried out using a PulsOn410 UWB radar. The results show that the proposed low-complexity algorithm has high accuracy.

18 December 2018 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
YLYecheng Lyu
Yecheng Lyu
LBLin Bai
Lin Bai
XHXinming Huang
Xinming Huang

20 March 2019 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
ZCZhilu Chen
Zhilu Chen
XHXinming Huang
Xinming Huang

11 June 2025 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
AGAntony García González
Antony García González
YSYessica Saez
Yessica Saez
IHItamar Harris
Itamar Harris
XHXinming Huang
Xinming Huang
ECEdwin Collado
Edwin Collado
Air quality monitoring is a critical component of environmental management, especially in developing countries where pollution levels are a growing concern. This review systematically analyzes recent advances in Internet-of-Things (IoT)-based air quality monitoring systems and highlights the impact of artificial intelligence (AI) technologies. A comprehensive selection process was used to identify 220 relevant studies using databases such as Google Scholar, Scopus, and ResearchRabbit. Following a selection process based on specific eligibility criteria, a total of 147 studies were chosen for a detailed analysis. These studies present notable advances in the application of artificial intelligence to improve data accuracy, predictive capabilities, and real-time analysis in air quality monitoring systems. A key contribution of this review is the proposal of a classification framework for AI techniques in air quality monitoring, organized into five main application areas: data imputation, sensor calibration, anomaly detection, air quality index (AQI) estimation, and short-term forecasting. The review takes an in-depth look at the different uses of these technologies in both urban and industrial settings, presenting successful case studies that showcase their effectiveness in addressing pressing air quality issues. Additionally, the paper identifies research gaps in the literature, particularly related to data quality, system scalability, and integration challenges in AI-driven IoT systems. The insights provided aim to guide researchers and practitioners in selecting appropriate AI techniques and system architectures, inform the design of more reliable and scalable air quality monitoring frameworks, and support future efforts to mitigate air pollution through data-driven decision-making.

13 December 2021 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
MLMing Li
Ming Li
JLJared Liu
Jared Liu
CZCe Zheng
Ce Zheng
XHXinming Huang
Xinming Huang
Ziming ZhangZiming Zhang
Ziming Zhang
Image-based vehicle re-identification (ReID) has witnessed much progress in recent years thanks to the advances of deep neural networks. However, most of existing works struggled to extract robust and discriminative features from a single image at each feedforward to represent one vehicle instance. We argue that images taken from distinct viewpoints, e.g., front and back, have significantly different appearances and patterns for recognition. In order to ‘`memorize’' each vehicle, existing models often have to capture consistent ``ID codes" from totally different view images, which causes learning difficulties. Additionally, we claim that correspondences among views, i.e., various vehicle parts observed from the identical image and the same part observed from different viewpoints, contribute to instance-level feature learning as well. Motivated by these observations, we propose to extract comprehensive instance-specific representations of the same vehicle from multiple views through modelling part-wise correlations. To this end, we present an efficient transformer-based framework to exploit both inner- and inter-view correlations for vehicle ReID. In specific, we first adopt a deep encoder to condense a series of patch embeddings from each view image. Then our efficient transformer, consisting of a distillation token and a noise token in addition to a regular class token, is constructed to enforce all patch embeddings to interact with each other regardless of whether they are taken from identical or different views. For inference, one testing image together with its augmented counterparts (pseudo views) are regarded as multi-view inputs and fed into our framework to capture its representations. We conduct extensive experiments on widely used vehicle ReID benchmarks, and our approach achieves the state-of-the-art performance, showing the effectiveness of our method.