8 results on '"Wang, Haipeng"'
Search Results
2. Fitness-Based Hierarchical Reinforcement Learning for Multi-human-robot Task Allocation in Complex Terrain Conditions.
- Author
-
Wang, Haipeng, Li, Shiqi, and Ji, Hechao
- Subjects
- *
MACHINE learning , *BIOLOGICAL fitness , *REINFORCEMENT learning - Abstract
A fitness-based hierarchical reinforcement learning method is proposed in this study for multi-human-robot task allocation in complex terrain conditions. Firstly, three fitness functions, including task fitness, distance fitness, and environmental fitness, are designed to quantify the adaptability of each subject to each task. Then, a two-layer hierarchical reinforcement learning algorithm is designed for task allocation. The values of the fitnesses are used as input for the task allocation algorithm. A series of task allocation experiments are conducted to verify the effectiveness of the proposed methods. Compared with the conventional reinforcement learning algorithm, the task allocation efficiency increases by no less than 57% by the proposed method under different numbers of subjects, and by about 65% under different numbers of tasks. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
3. A novel concatenate feature fusion RCNN architecture for sEMG-based hand gesture recognition.
- Author
-
Xu, Pufan, Li, Fei, and Wang, Haipeng
- Subjects
CONVOLUTIONAL neural networks ,RECURRENT neural networks ,GESTURE ,SIGNAL convolution ,MACHINE learning ,ROBOT control systems ,HUMAN-computer interaction - Abstract
Hand gesture recognition tasks based on surface electromyography (sEMG) are vital in human-computer interaction, speech detection, robot control, and rehabilitation applications. However, existing models, whether traditional machine learnings (ML) or other state-of-the-arts, are limited in the number of movements. Targeting a large number of gesture classes, more data features such as temporal information should be persisted as much as possible. In the field of sEMG-based recognitions, the recurrent convolutional neural network (RCNN) is an advanced method due to the sequential characteristic of sEMG signals. However, the invariance of the pooling layer damages important temporal information. In the all convolutional neural network (ACNN), because of the feature-mixing convolution operation, a same output can be received from completely different inputs. This paper proposes a concatenate feature fusion (CFF) strategy and a novel concatenate feature fusion recurrent convolutional neural network (CFF-RCNN). In CFF-RCNN, a max-pooling layer and a 2-stride convolutional layer are concatenated together to replace the conventional simple dimensionality reduction layer. The featurewise pooling operation serves as a signal amplitude detector without using any parameter. The feature-mixing convolution operation calculates the contextual information. Complete evaluations are made on both the accuracy and convergence speed of the CFF-RCNN. Experiments are conducted using three sEMG benchmark databases named DB1, DB2 and DB4 from the NinaPro database. With more than 50 gestures, the classification accuracies of the CFF-RCNN are 88.87% on DB1, 99.51% on DB2, and 99.29% on DB4. These accuracies are the highest compared with reported accuracies of machine learnings and other state-of-the-art methods. To achieve accuracies of 86%, 99% and 98% for the RCNN, the training time are 2353.686 s, 816.173 s and 731.771 s, respectively. However, for the CFF-RCNN to reach the same accuracies, it needs only 1727.415 s, 542.245 s and 576.734 s, corresponding to a reduction of 26.61%, 33.56% and 21.19% in training time. We concluded that the CFF-RCNN is an improved method when classifying a large number of hand gestures. The CFF strategy significantly improved model performance with higher accuracy and faster convergence as compared to traditional RCNN. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
4. Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks.
- Author
-
Zhou, Yu, Wang, Haipeng, Xu, Feng, and Jin, Ya-Qiu
- Abstract
Deep convolutional neural networks have achieved great success in computer vision and many other areas. They automatically extract translational-invariant spatial features and integrate with neural network-based classifier. This letter investigates the suitability and potential of deep convolutional neural network in supervised classification of polarimetric synthetic aperture radar (POLSAR) images. The multilooked POLSAR data in the format of coherency or covariance matrix is first converted into a normalized 6-D real feature vector. The six-channel real image is then fed into a four-layer convolutional neural network tailored for POLSAR classification. With two cascaded convolutional layers, the designed deep neural network can automatically learn hierarchical polarimetric spatial features from the data. Two experiments are presented using the AIRSAR data of San Francisco, CA, and Flevoland, The Netherlands. Classification result of the San Francisco case shows that slant built-up areas, which are conventionally mixed with vegetated area in polarimetric feature space, can now be successfully distinguished after taking into account spatial features. Quantitative analysis with respect to ground truth information available for the Flevoland test site shows that the proposed method achieves an accuracy of 92.46% in classifying the considered 15 classes. Such results are comparable with the state of the art. [ABSTRACT FROM PUBLISHER]
- Published
- 2016
- Full Text
- View/download PDF
5. pepReap: A Peptide Identification Algorithm Using Support Vector Machines
- Author
-
Sun Ruixiang, Gao Wen, Fu Yan, He Simin, Zeng Rong, and Wang Haipeng
- Subjects
Structured support vector machine ,Computer Networks and Communications ,Computer science ,business.industry ,Machine learning ,computer.software_genre ,Relevance vector machine ,Support vector machine ,Identification (information) ,Hardware and Architecture ,Artificial intelligence ,business ,computer ,Software - Published
- 2005
6. Partial least squares regression residual extreme learning machine (PLSRR-ELM) calibration algorithm applied in fast determination of gasoline octane number with near-infrared spectroscopy.
- Author
-
Wang, Haipeng, Chu, Xiaoli, Chen, Pu, Li, Jingyan, Liu, Dan, and Xu, Yupeng
- Subjects
- *
PARTIAL least squares regression , *ANTIKNOCK gasoline , *GASOLINE , *MACHINE learning , *STANDARD deviations , *NEAR infrared spectroscopy , *GASOLINE blending - Abstract
[Display omitted] • PLS was used in conjunction with ELM for fast determination of blended gasoline octane number with NIR spectroscopy. • Allocation of relationship information (NIR spectrum and property) in between PLS and ELM can be adjusted adaptively. • The proposed method exhibited better prediction accuracy over PLS or ELM alone. • The proposed method can be well-suited for calibrating an analysis system with unknown degree of no-linearity. Based on near-infrared (NIR) spectroscopy, a new quantitative calibration algorithm, called "Partial Least Squares Regression Residual Extreme Learning Machine (PLSRR-ELM)", was proposed for fast determination of research octane number (RON) for blended gasoline. In this algorithm, partial least square (PLS) cooperates with non-linear extreme learning machine (ELM) to separate the relationship information suitable for each other from the raw relationship information (between NIR spectrum and corresponding property) with the unknown degree of non-linearity, with aim of calibrating them respectively. Since the advantages of both PLS and ELM are fully utilized, it is expected that PLSRR-ELM can address the relationship information more effectively and leads to improved calibration performance over PLS and ELM alone. The calibration performance of PLSRR-ELM was evaluated by a set of on-line gasoline blending sample data from a refinery. As a result, it showed an enhanced prediction performance, e.g. , about 13% or 11% decrease in the root mean squared error of test (RMSE-T) over PLS or ELM alone, respectively. In method comparison, the model performance of PLRR-ELM exceeds all other methods including PLS, Poly-PLS, KPLS, ELM, and ANN, demonstrating its superiority for fast prediction of gasoline RON. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
7. Parallel incremental efficient attribute reduction algorithm based on attribute tree.
- Author
-
Ding, Weiping, Qin, Tingzhen, Shen, Xinjie, Ju, Hengrong, Wang, Haipeng, Huang, Jiashuang, and Li, Ming
- Subjects
- *
PLYOMETRICS , *ROUGH sets , *ALGORITHMS , *MULTICASTING (Computer networks) , *VIDEO coding , *TREES , *MACHINE learning , *ELECTRONIC data processing - Abstract
• We introduce the mechanism of a binary tree and propose a parallel incremental acceleration strategy based on the attribute tree. • The branch threshold coefficient is added into the calculation process to guide the algorithm to jump out of the loop, avoid redundant calculations, and reduce the number of attribute evaluations. • When multiple incremental objects are added to the decision system, the incremental mechanism can be used to update the reduction. • We combine IARAT and Spark parallel technology to parallelize data processing to accelerate the calculation process. Attribute reduction is an important application of rough sets. Efficiently reducing massive dynamic data sets quickly has always been a major goal of researchers. Traditional incremental methods focus on reduction by updated approximations. However, these methods must evaluate all attributes and repeatedly calculate their importance. When these algorithms are applied to large datasets with high time complexity, reducing large decision systems becomes inefficient. We propose an incremental acceleration strategy based on attribute trees to solve this problem. The key step is to cluster all attributes into multiple trees for incremental attribute evaluation. Specifically, we first select the appropriate attribute tree for attribute evaluation according to the attribute tree correlation measure to reduce the time complexity. Next, the branch coefficient is added to the stop criterion, increasing with the branch depth and guiding a jump out of the loop after reaching the maximum threshold. This avoids redundant calculation and improves efficiency. Furthermore, we propose an algorithm for incremental attribute reduction based on attribute trees using these improvements. Finally, a Spark parallel mechanism is added to parallelize data processing to implement the parallel incremental efficient attribute reduction based on the attribute tree. Experimental results on the Shuttle dataset show that the time consumption of our algorithm is more than 40% lower than that of the classical IARC algorithm while maintaining its good classification performance. In addition, the time is shortened by more than 87% from the benchmark after adding the Spark parallelizing mechanism. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
8. Information bottleneck-based interpretable multitask network for breast cancer classification and segmentation.
- Author
-
Wang, Junxia, Zheng, Yuanjie, Ma, Jun, Li, Xinmeng, Wang, Chongjing, Gee, James, Wang, Haipeng, and Huang, Wenhui
- Subjects
- *
DEEP learning , *BREAST , *TUMOR classification , *BREAST cancer , *MACHINE learning , *BREAST ultrasound , *BREAST imaging - Abstract
Breast cancer is one of the most common causes of death among women worldwide. Early signs of breast cancer can be an abnormality depicted on breast images (e.g., mammography or breast ultrasonography). However, reliable interpretation of breast images requires intensive labor and physicians with extensive experience. Deep learning is evolving breast imaging diagnosis by introducing a second opinion to physicians. However, most deep learning-based breast cancer analysis algorithms lack interpretability because of their black box nature, which means that domain experts cannot understand why the algorithms predict a label. In addition, most deep learning algorithms are formulated as a single-task-based model that ignores correlations between different tasks (e.g., tumor classification and segmentation). In this paper, we propose an interpretable multitask information bottleneck network (MIB-Net) to accomplish simultaneous breast tumor classification and segmentation. MIB-Net maximizes the mutual information between the latent representations and class labels while minimizing information shared by the latent representations and inputs. In contrast from existing models, our MIB-Net generates a contribution score map that offers an interpretable aid for physicians to understand the model's decision-making process. In addition, MIB-Net implements multitask learning and further proposes a dual prior knowledge guidance strategy to enhance deep task correlation. Our evaluations are carried out on three breast image datasets in different modalities. Our results show that the proposed framework is not only able to help physicians better understand the model's decisions but also improve breast tumor classification and segmentation accuracy over representative state-of-the-art models. Our code is available at https://github.com/jxw0810/MIB-Net. • A multi-task learning framework is designed to joint breast cancer classification and tumor segmentation. • An interpretable network based on information bottleneck is proposed for the classification task. • A dual prior knowledge guidance strategy is suggested to improve the task correlation. • Classification and segmentation promote each other during the training process. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.