arXiv subjects

Jinhong Wang

Publications and source records attributed to Jinhong Wang.

34 records · Page 2Linked to original sources

arXiv2023

Classification of Single Tree Decay Stages from Combined Airborne LiDAR Data and CIR Imagery

Understanding forest health is of great importance for the conservation of the integrity of forest ecosystems. In this regard, evaluating the amount and quality of dead wood is of utmost interest as they are favorable indicators of biodiversity. Apparently, remote sensing-based machine learning techniques have proven to be more efficient and sustainable with unprecedented accuracy in forest inventory. This study, for the first time, automatically categorizing individual coniferous trees (Norway spruce) into five decay stages (live, declining, dead, loose bark, and clean) from combined airborne laser scanning (ALS) point clouds and color infrared (CIR) images using three different Machine Learning methods - 3D point cloud-based deep learning (KPConv), Convolutional Neural Network (CNN), and Random Forest (RF). First, CIR colorized point clouds are created by fusing the ALS point clouds and color infrared images. Then, individual tree segmentation is conducted, after which the results are further projected onto four orthogonal planes. Finally, the classification is conducted on the two datasets (3D multispectral point clouds and 2D projected images) based on the three Machine Learning algorithms. All models achieved promising results, reaching overall accuracy (OA) of up to 88.8%, 88.4% and 85.9% for KPConv, CNN and RF, respectively. The experimental results reveal that color information, 3D coordinates, and intensity of point clouds have significant impact on the promising classification performance. The performance of our models, therefore, shows the significance of machine/deep learning for individual tree decay stages classification and landscape-wide assessment of the dead wood amount and quality by using modern airborne remote sensing techniques. The proposed method can contribute as an important and reliable tool for monitoring biodiversity in forest ecosystems.

cs.CV↗

arXiv2023

Ord2Seq: Regarding Ordinal Regression as Label Sequence Prediction

Ordinal regression refers to classifying object instances into ordinal categories. It has been widely studied in many scenarios, such as medical disease grading, movie rating, etc. Known methods focused only on learning inter-class ordinal relationships, but still incur limitations in distinguishing adjacent categories thus far. In this paper, we propose a simple sequence prediction framework for ordinal regression called Ord2Seq, which, for the first time, transforms each ordinal category label into a special label sequence and thus regards an ordinal regression task as a sequence prediction process. In this way, we decompose an ordinal regression task into a series of recursive binary classification steps, so as to subtly distinguish adjacent categories. Comprehensive experiments show the effectiveness of distinguishing adjacent categories for performance improvement and our new approach exceeds state-of-the-art performances in four different scenarios. Codes are available at https://github.com/wjh892521292/Ord2Seq.

cs.AI↗

arXiv2023

Robust Image Ordinal Regression with Controllable Image Generation

Image ordinal regression has been mainly studied along the line of exploiting the order of categories. However, the issues of class imbalance and category overlap that are very common in ordinal regression were largely overlooked. As a result, the performance on minority categories is often unsatisfactory. In this paper, we propose a novel framework called CIG based on controllable image generation to directly tackle these two issues. Our main idea is to generate extra training samples with specific labels near category boundaries, and the sample generation is biased toward the less-represented categories. To achieve controllable image generation, we seek to separate structural and categorical information of images based on structural similarity, categorical similarity, and reconstruction constraints. We evaluate the effectiveness of our new CIG approach in three different image ordinal regression scenarios. The results demonstrate that CIG can be flexibly integrated with off-the-shelf image encoders or ordinal regression models to achieve improvement, and further, the improvement is more significant for minority categories.

cs.CV↗

arXiv2022

CTT-Net: A Multi-view Cross-token Transformer for Cataract Postoperative Visual Acuity Prediction

Surgery is the only viable treatment for cataract patients with visual acuity (VA) impairment. Clinically, to assess the necessity of cataract surgery, accurately predicting postoperative VA before surgery by analyzing multi-view optical coherence tomography (OCT) images is crucially needed. Unfortunately, due to complicated fundus conditions, determining postoperative VA remains difficult for medical experts. Deep learning methods for this problem were developed in recent years. Although effective, these methods still face several issues, such as not efficiently exploring potential relations between multi-view OCT images, neglecting the key role of clinical prior knowledge (e.g., preoperative VA value), and using only regression-based metrics which are lacking reference. In this paper, we propose a novel Cross-token Transformer Network (CTT-Net) for postoperative VA prediction by analyzing both the multi-view OCT images and preoperative VA. To effectively fuse multi-view features of OCT images, we develop cross-token attention that could restrict redundant/unnecessary attention flow. Further, we utilize the preoperative VA value to provide more information for postoperative VA prediction and facilitate fusion between views. Moreover, we design an auxiliary classification loss to improve model performance and assess VA recovery more sufficiently, avoiding the limitation by only using the regression metrics. To evaluate CTT-Net, we build a multi-view OCT image dataset collected from our collaborative hospital. A set of extensive experiments validate the effectiveness of our model compared to existing methods in various metrics. Code is available at: https://github.com/wjh892521292/Cataract OCT.

eess.IV↗

arXiv2022

D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentation

Computer-aided medical image segmentation has been applied widely in diagnosis and treatment to obtain clinically useful information of shapes and volumes of target organs and tissues. In the past several years, convolutional neural network (CNN) based methods (e.g., U-Net) have dominated this area, but still suffered from inadequate long-range information capturing. Hence, recent work presented computer vision Transformer variants for medical image segmentation tasks and obtained promising performances. Such Transformers model long-range dependency by computing pair-wise patch relations. However, they incur prohibitive computational costs, especially on 3D medical images (e.g., CT and MRI). In this paper, we propose a new method called Dilated Transformer, which conducts self-attention for pair-wise patch relations captured alternately in local and global scopes. Inspired by dilated convolution kernels, we conduct the global self-attention in a dilated manner, enlarging receptive fields without increasing the patches involved and thus reducing computational costs. Based on this design of Dilated Transformer, we construct a U-shaped encoder-decoder hierarchical architecture called D-Former for 3D medical image segmentation. Experiments on the Synapse and ACDC datasets show that our D-Former model, trained from scratch, outperforms various competitive CNN-based or Transformer-based segmentation models at a low computational cost without time-consuming per-training process.

cs.CV↗

arXiv2021

Calibration of Human Driving Behavior and Preference Using Naturalistic Traffic Data

Understanding human driving behaviors quantitatively is critical even in the era when connected and autonomous vehicles and smart infrastructure are becoming ever more prevalent. This is particularly so as that mixed traffic settings, where autonomous vehicles and human driven vehicles co-exist, are expected to persist for quite some time. Towards this end it is necessary that we have a comprehensive modeling framework for decision-making within which human driving preferences can be inferred statistically from observed driving behaviors in realistic and naturalistic traffic settings. Leveraging a recently proposed computational framework for smart vehicles in a smart world using multi-agent based simulation and optimization, we first recapitulate how the forward problem of driving decision-making is modeled as a state space model. We then show how the model can be inverted to estimate driver preferences from naturalistic traffic data using the standard Kalman filter technique. We explicitly illustrate our approach using the vehicle trajectory data from Sugiyama experiment that was originally meant to demonstrate how stop-and-go shockwave can arise spontaneously without bottlenecks. Not only the estimated state filter can fit the observed data well for each individual vehicle, the inferred utility functions can also re-produce quantitatively similar pattern of the observed collective behaviors. One distinct advantage of our approach is the drastically reduced computational burden. This is possible because our forward model treats driving decision process, which is intrinsically dynamic with multi-agent interactions, as a sequence of independent static optimization problems contingent on the state with a finite look ahead anticipation. Consequently we can practically sidestep solving an interacting dynamic inversion problem that would have been much more computationally demanding.

cs.MA↗

arXiv2020

Design of a Time-to-Digital Converter ASIC and a mini-DAQ system for the Phase-2 Upgrade of the ATLAS Monitored Drift Tube detector

We present the second prototype of a time-to-digital (TDC) ASIC for the upgrade of the ATLAS Monitored Drift Tube (MDT) detector for High-Luminosity LHC operations. Compared to the first prototype, triple modular redundancy has been implemented for the configuration and flow control logic. The total power consumption is increased by less than 10 mW while achieving the same time resolution and channel uniformity. A mini-DAQ system has been built to verify the front-end electronics chain with the new prototype together with other ASICs and boards in triggered mode. Cosmic ray tests with a small-diameter MDT chamber indicate that the configuration and data transmission of the readout electronics perform well. It is expected that this prototype design will be used in the final production.

physics.ins-det↗

arXiv2019

Design and performance of a TDC ASIC for the upgrade of the ATLAS Monitored Drift Tube detector

We present the prototype of a time-to-digital (TDC) ASIC for the upgrade of the ATLAS Monitored Drift Tube (MDT) detector for high-luminosity LHC operation. This ASIC is based on a previously submitted demonstrator ASIC designed for timing performance evaluation, and includes all features necessary for the various operation modes, as well as the migration to the TSMC 130 nm CMOS technology. We present the TDC design with the emphasis on added features and performance optimization. Tests of the timing performance demonstrate that this ASIC meets the design specifications. The TDC has a bin size of about 780 ps, and a timing bin variations within 40 ps for all 24 channels with leading and trailing edge digitization, while the power consumption has been limited to 250 mW, corresponding to a consumption of about 5.2 mW per edge measurement.

physics.ins-det↗

arXiv2019

Mass Production of a Trigger Data Serializer ASIC for the Upgrade of the Muon Spectrometer at the ATLAS Experiment

The Trigger Data Serializer (TDS) is a custom ASIC designed for the upgrade of the innermost station of the endcap ATLAS Muon Spectrometer. It is a mixed-signal chip with two working modes that can handle up to 128 detector channels. A total of 6,000 TDS ASICs have been produced for detector operation. This paper discusses a custom automatic test platform we developed to provide quality control of the TDS ASICs. We introduce the design, test procedures, and results obtained from this TDS testing platform.

physics.ins-det↗

arXiv2019

A Multi-Layer SEU Mitigation Strategy to Improve FPGA Design Robustness for the ATLAS Muon Spectrometer Upgrade

We present a multi-layer single-event upset mitigation strategy implemented in a low-cost Xilinx Artix-7 FPGA. The implementation is targeted for a trigger data router for the ATLAS muon spectrometer upgrade. The mitigation strategy employs three layers of protection to improve overall FPGA design robustness: use of triple-modular redundancy for FPGA fabric logic and embedded soft-error mitigation in the first layer; further enhancement with multi-boot FPGA reconfiguration across multiple copies of configuration memory in the second layer; and FPGA power cycling and configuration memory re-initialization in the third layer. The effectiveness of this scheme has been evaluated at two different neutron facilities, LANSCE and NCSR Demokritos, with 800 MeV and 25 MeV beam energies, respectively. Testing was performed with a similar configuration to that planned for final operation. We discuss the testing strategy and summarize the test results to estimate the expected data loss over 10 years of operation in the ATLAS experiment.

physics.ins-det↗

arXiv2017

Development of a time-to-digital converter ASIC for the upgrade of the ATLAS Monitored Drift Tube detector

The upgrade of the ATLAS muon spectrometer for high-luminosity LHC requires new trigger and readout electronics for the various elements of the detector. We present the design of a time-to-digital converter (TDC) ASIC prototype for the ATLAS Monitored Drift Tube (MDT) detector. The chip was fabricated in a GlobalFoundries 130 nm CMOS technology. Studies indicate that its timing and power consumption characteristics meet the design specifications, with a timing bin variation of 40 ps for all 48 channels with a power consumption of about 6.5 mW per channel.

physics.ins-det↗

arXiv2017

A Programmable Time Alignment Scheme for Detector Signals from the Upgraded muon Spectrometer at the ATLAS Experiment

We present a programmable time alignment scheme used in an ASIC for the ATLAS forward muon trigger development. The scheme utilizes regenerated clocks with programmable phases to compensate for the timing offsets introduced by different detector trace lengths. Each ASIC used in the design has 104 input channels with delay compensation circuitry providing steps of ~ 3 ns and a full range of 25 ns for each channel. Detailed implementation of the scheme including majority logic to suppress single-event effects is presented. The scheme is flexible and fully synthesizable. The approach is adaptable to other applications with similar phase shifting requirements. In addition, the design is resource efficient and is suitable for cost-effective digital implementation with a large number of channels.

physics.ins-det↗

arXiv2017

Design of a Trigger Data Serializer ASIC for the Upgrade of the ATLAS Forward Muon Spectrometer

The small-strip Thin Gap Chamber (sTGC) will be used for both triggering and precision tracking purposes in the upgrade of the ATLAS forward muon spectrometer. Both sTGC pad and strip detectors are readout by a Trigger Data Serializer (TDS) ASIC in the trigger path. This ASIC has two operation modes to prepare trigger data from pad and strip detectors respectively. The pad mode (pad-TDS) collects the firing status for up to 104 pads from one detector layer and transmits the data at 4.8 Gbps to the pad trigger extractor every 25 ns. The pad trigger extractor collects pad-TDS data from eight detector layers and defines a region of interest along the path of a muon candidate. In the strip mode (strip-TDS), the deposited charges from up to 128 strips are buffered, time-stamped, and a trigger matching procedure is performed to read out strips underneath the region of interest. The strip-TDS output is also transmitted at 4.8 Gbps to the following FPGA processing circuits. Details about the ASIC design and test results are presented in this paper.

physics.ins-det↗

arXiv2015

FPGA Implementation of a Fixed Latency Scheme in a Signal Packet Router for the Upgrade of ATLAS Forward Muon Trigger Electronics

We propose a new fixed latency scheme for Xilinx gigabit transceivers that will be used in the upgrade of the ATLAS forward muon spectrometer at the Large Hadron Collider. The fixed latency scheme is implemented in a 4.8 Gbps link between a frontend data serializer ASIC and a packet router. To achieve fixed latency, we use IO delay and dedicated carry in resources in a Xilinx FPGA, while minimally relying on the embedded features of the FPGA transceivers. The scheme is protocol independent and can be adapted to FPGA from other vendors with similar resources. This paper presents a detailed implementation of the fixed latency scheme, as well as simulations of the real environment in the ATLAS forward muon region.

physics.ins-det↗

arXiv2015

Characterization of a Serializer ASIC chip for the upgrade of the ATLAS muon detector

We report on the design of a serializer ASIC to be used in the ATLAS forward muon detector for trigger data transmission. We discuss the performance of a prototype chip covering power dissipation, latency and stable operating line rate. Tests show that the serializer is capable of running at least at 5.76 Gbps with a bit error ratio below 1x10^{-15}, and a power consumption of 200 mW running at 4.8 Gbps. The latency between the start of loading 30 bits into the serializer to the transmission of the first bit from the serializer is measured to be about 6 ns.

physics.ins-det↗

arXiv2015

Waveform Timing Performance of a 5 GS/s Fast Pulse Sampling Module with DRS4

We first clarify timing issues of non-uniform sampling intervals regarding a 5 GS/s fast pulse sampling module with DRS4. Calibration strategy is proposed, and as a result, the waveform timing performance is improved to be below 10 ps RMS. We then further evaluate waveform timing performance of the module by comparing with a 10 GS/s oscilloscope in a setup with plastic scintillators and fast PMTs. Different waveform timing algorithms are employed for analysis, and the module shows comparable timing performance with that of the oscilloscope.

physics.ins-det↗