Daguang Jiang

Beijing University of Chemical Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Ruirui Li

East China University of Science and Technology

Junkai Yi

Beijing Information Science & Technology University

Shenghui Shi

Beijing University of Chemical Technology

Mengmeng Zhang

Zhejiang Normal University

Siyan Zhan

Peking University

Gaohui Bian

Beijing University of Chemical Technology

Xiaoyong Lin

Beijing University of Chemical Technology

Jiarun Liu

University of Electronic Science and Technology of China

Jiafeng Fu

Chinese Research Academy of Environmental Sciences

Kexin Meng

Beijing University of Chemical Technology

Cooperative Institutions

Beijing University of Chemical Technology

Beijing Institute of Technology

Academy of Military Medical Sciences

Nanjing University of Aeronautics and Astronautics

Ministry of Education of the People's Republic of China

Peking University

Sichuan University

Shanghai Jiao Tong University

Chongqing University

Chinese Academy of Sciences

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Chinese Data Extraction and Named Entity Recognition

Ting-Wei Yang Daguang Jiang Shenghui Shi Siyan Zhan Lin Zhuo

Extracting effective information from a large amount of Chinese text data is an important task for data analysis in the era of big data. The key to extracting information is whether it can quickly identify named entities in Chinese text. This paper analyzes the structure of text data about news text and specialized medical text, propose IDCNN-BiLSTM-CRF (Iterated Dilated Convolutions-Bidirectional Long Short Memory Network-Condition Random Field) model. In this paper, medical text data is processed by analyzing the structure of the public news dataset. This paper analyzes the structure of public news datasets to process special medical text data, and uses public news datasets and special medical text datasets to compare and analyze the model proposed in this paper and the BiLSTM-CRF model to verify the recognition result.

Named Entity Recognition

Iterated function

10.1109/icbda49040.2020.9101204

Cite

Citations (8)

ReadCurrent: a VDCNN-based tool for fast and accurate nanopore selective sequencing

Briefings in Bioinformatics (2024)

K.J. Fan Mengfan Li Jiarong Zhang Zihan Xie Daguang Jiang

Abstract Nanopore selective sequencing allows the targeted sequencing of DNA of interest using computational approaches rather than experimental methods such as targeted multiplex polymerase chain reaction or hybridization capture. Compared to sequence-alignment strategies, deep learning (DL) models for classifying target and nontarget DNA provide large speed advantages. However, the relatively low accuracy of these DL-based tools hinders their application in nanopore selective sequencing. Here, we present a DL-based tool named ReadCurrent for nanopore selective sequencing, which takes electric currents as inputs. ReadCurrent employs a modified very deep convolutional neural network (VDCNN) architecture, enabling significantly lower computational costs for training and quicker inference compared to conventional VDCNN. We evaluated the performance of ReadCurrent across 10 nanopore sequencing datasets spanning human, yeasts, bacteria, and viruses. We observed that ReadCurrent achieved a mean accuracy of 98.57% for classification, outperforming four other DL-based selective sequencing methods. In experimental validation that selectively sequenced microbial DNA from human DNA, ReadCurrent achieved an enrichment ratio of 2.85, which was higher than the 2.7 ratio achieved by MinKNOW using the sequence-alignment strategy. In summary, ReadCurrent can rapidly classify target and nontarget DNA with high accuracy, providing an alternative in the toolbox for nanopore selective sequencing. ReadCurrent is available at https://github.com/Ming-Ni-Group/ReadCurrent.

Nanopore

Minion

Multiplex

10.1093/bib/bbae435

Cite

Citations (0)

LIRnet:Lightweight Hyperspectral Image Classification Based Information Redistribution

IEEE Transactions on Geoscience and Remote Sensing (2024)

Lujie Song Yunhao Gao Lan Lan Xiangyang Jiang Xiaofei Yin

Contextual image classification

Redistribution

10.1109/tgrs.2024.3475635

Cite

Citations (1)

SGDANet: Gland Instance Segmentation Based on Spatial and Geometric Dual-Path Attention Modules

2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI) (2022)

Haikun Zhang Daguang Jiang Ruirui Li

Gland instance segmentation is an essential step in quantitatively analyzing the malignancy degree of adenocarcinomas [1] by pathologists. Automated gland instance segmentation is in great demand. Despite the great progress of CNN-based methods, they are still prone to inaccurate segmentation when dealing with adjacent glandular cells with large morphological differences. To address this issue, this paper extends Mask R-CNN and proposes SGDANet. It proposes a novel and effective geometric module for better capturing geometric features of the cell membrane, cytoplasm and nucleus. It also designs a parallel spatial-geometric dual-path attention mechanism for better feature extraction. To make the dual-path attention work, SGDANet integrates the fine features with coarse features through a new fusion module to better preserve details. We conducted experiments on Glas and CRAG public datasets. SGDANet not only achieves higher F1 values than the state-ofthe-art gland segmentation methods but also outperforms those applied latest instance segmentation networks in the mAP metric.

Feature (linguistics)

10.1109/prai55851.2022.9904289

Cite

Citations (1)

Tucker Bilinear Attention Network for Multi-scale Remote Sensing Object Detection

arXiv (Cornell University) (2023)

Tao Chen Ruirui Li Jiafeng Fu Daguang Jiang

Object detection on VHR remote sensing images plays a vital role in applications such as urban planning, land resource management, and rescue missions. The large-scale variation of the remote-sensing targets is one of the main challenges in VHR remote-sensing object detection. Existing methods improve the detection accuracy of high-resolution remote sensing objects by improving the structure of feature pyramids and adopting different attention modules. However, for small targets, there still be seriously missed detections due to the loss of key detail features. There is still room for improvement in the way of multiscale feature fusion and balance. To address this issue, this paper proposes two novel modules: Guided Attention and Tucker Bilinear Attention, which are applied to the stages of early fusion and late fusion respectively. The former can effectively retain clean key detail features, and the latter can better balance features through semantic-level correlation mining. Based on two modules, we build a new multi-scale remote sensing object detection framework. No bells and whistles. The proposed method largely improves the average precisions of small objects and achieves the highest mean average precisions compared with 9 state-of-the-art methods on DOTA, DIOR, and NWPU VHR-10.Code and models are available at https://github.com/Shinichict/GTNet.

Feature (linguistics)

10.48550/arxiv.2303.05329

Cite

Citations (0)

Named Entity Recognition of Chinese Electronic Medical Records Based on Cascaded Conditional Random Field

Xiaoyu Chen Shenghui Shi Siyan Zhan Daguang Jiang Xiaoyong Lin

Medical information carried by electronic medical records has high clinical application value, and named entity recognition is the key task to extract valuable information from a large number of electronic medical records. In order to realize the intelligent identification of named entities in Chinese electronic medical record texts, this paper analyzes the characteristics that affect the recognition performance. The feature set is composed of language symbol features, part of speech features, context features, word boundary features and identifier feature. The feature template is designed and the Cascaded Conditional Random Field model is established. Based on the data selection strategy, we trained the Cascaded Conditional Random Field to identify the disease names, drug names and symptom names in Chinese electronic medical records. This method reduced the scale of training data, reduced the artificial markers and improved the recognition performance of disease names, drug names and symptom names, and the F value reached 68.18%, 90.91% and 87.13%, respectively.

Named Entity Recognition

Identification

Feature (linguistics)

10.1109/icbda.2019.8713244

Cite

Citations (9)

Swin Transformers Make Strong Contextual Encoders for VHR Image Road Extraction

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium (2022)

Tao Chen Daguang Jiang Ruirui Li

Significant progress has been made in automatic road extra-ction or segmentation based on deep learning, but there are still margins to improve in terms of the completeness and connectivity of the results. This is mainly due to the challenges of large intra-class variances, ambiguous inter-class distinctions, and occlusions from shadows, trees, and buildings. Therefore, being able to perceive global context and model geometric information is essential to further improve the accuracy of road segmentation. In this paper, we design a novel dual-branch encoding block CoSwin which exploits the capability of global context modeling of Swin Transformer and that of local feature extraction of ResNet. Furthermore, we also propose a context-guided filter block named CFilter, which can filter out context-independent noisy features for better reconstructing of the details. We use CoSwin and CFilter in a U-shaped network architecture. Experiments on Massachusetts and CHN6-CUG datasets show that the proposed method outperforms other state-of-the-art methods on the metrics of F1, IoU, and OA. Further analysis reveals that the improvement in accuracy comes from better integrity and connectivity of segmented roads.

Context model

10.1109/igarss46834.2022.9883628

Cite

Citations (60)

Semi-supervised 2D Human Pose Estimation via Adaptive Keypoint Masking

arXiv (Cornell University) (2024)

Kexin Meng Ruirui Li Daguang Jiang

Human pose estimation is a fundamental and challenging task in computer vision. Larger-scale and more accurate keypoint annotations, while helpful for improving the accuracy of supervised pose estimation, are often expensive and difficult to obtain. Semi-supervised pose estimation tries to leverage a large amount of unlabeled data to improve model performance, which can alleviate the problem of insufficient labeled samples. The latest semi-supervised learning usually adopts a strong and weak data augmented teacher-student learning framework to deal with the challenge of "Human postural diversity and its long-tailed distribution". Appropriate data augmentation method is one of the key factors affecting the accuracy and generalization of semi-supervised models. Aiming at the problem that the difference of sample learning is not considered in the fixed keypoint masking augmentation method, this paper proposes an adaptive keypoint masking method, which can fully mine the information in the samples and obtain better estimation performance. In order to further improve the generalization and robustness of the model, this paper proposes a dual-branch data augmentation scheme, which can perform Mixup on samples and features on the basis of adaptive keypoint masking. The effectiveness of the proposed method is verified on COCO and MPII, outperforming the state-of-the-art semi-supervised pose estimation by 5.2% and 0.3%, respectively.

10.48550/arxiv.2404.14835

Cite

Citations (0)

A New Method of Target Focused Sound A New Method of Target Focused Sound

Daguang Jiang Junkai Yi Gaohui Bian

In this paper, a new method of using advance beamforming algorithm is proposed to control target focused found. The advance beamforming algorithm that adjusts the timing of sound waves emitted from each speaker in an array. As a result, sound waves cancel each other out in some parts of space, and amplify each other in others, effectively creating a focused beam of sound that acts as target focused sound. Even as you walk around your office, the advance beamforming algorithm would allow speakers to work like virtual headphones.

Headphones

Directional sound

Source

Cite

Citations (0)

Agreement or Disagreement in Noise-tolerant Mutual Learning?

2022 26th International Conference on Pattern Recognition (ICPR) (2022)

Jiarun Liu Daguang Jiang Yukun Yang Ruirui Li

Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information between dual-network. However, the dual network always tends to convergent which would weaken the dual-network mechanism to resist the noisy labels. In this paper, we proposed a noise-tolerant framework named MLC in an end-to-end manner. It adjusts the dual-network with divergent regularization to ensure the effectiveness of the mechanism. In addition, we correct the label distribution according to the agreement between dual-networks. The proposed method can utilize the noisy data to improve the accuracy, generalization, and robustness of the network. We test the proposed method on the simulate noisy dataset MNIST, CIFAR-10, and the real-world noisy dataset Clothing1M. The experimental result shows that our method outperforms the previous state-of-the-art method. Besides, our method is network-free thus it is applicable to many tasks. Our code can be found at https://github.com/JiarunLiu/MLC.

MNIST database

Robustness

Regularization

Noisy data

Code (set theory)

10.1109/icpr56361.2022.9956595

Cite

Citations (2)