Bo Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bo Lu has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Chun Xie
State Key Laboratory of Quality Research in Chinese Medicine, Macau Institute for Applied Research in Medicine and Health, Macau University of Science and Technology, Macau 853, (S.A.R.), China
1 shared publication - Gang Ren
College of Computer Science and Technology Henan Institute of Technology Xinxiang China
1 shared publication - Guiyuan Yuan
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China
1 shared publication - He Huang
Academy of Medical Engineering and Translational Medicine, State Key Laboratory of Advanced Medical Materials and Devices, Haihe Laboratory of Brain-computer Interaction and Human-machine Integration, Tianjin Key Laboratory of Brain Science and Neural Engineering, Tianjin University, Tianjin, China
1 shared publication Hongyu Shi
College of Computer Science and Technology Henan Institute of Technology Xinxiang China
1 shared publication- Jianming Ye
Department of Oncology, The First Affiliated Hospital of Gannan Medical University, China
1 shared publication
Latest Publications
- 27 March 2025
- Published by Springer Nature
- p. 18-23
Development of a Low Cost 3D LiDAR Using 2D LiDAR and Servo Motor
- 27 March 2025
- Published by Springer Nature
- p. 18-23
Development of a Low Cost 3D LiDAR Using 2D LiDAR and Servo Motor
- 17 November 2022
- Published by Springer Nature
- p. 175-184
A Behavior Decision Method for Autonomous Vehicles in an Urban Scene
- 17 November 2022
- Published by Springer Nature
- p. 175-184
A Behavior Decision Method for Autonomous Vehicles in an Urban Scene
- Open Access
- 14 October 2021
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 14 (1) , 1-19
A Cooperative Coevolution Wingsuit Flying Search Algorithm with Spherical Evolution
The algorithm wingsuit flying search (WFS) mimics the procedure of landing the vehicle. The outstanding feature of WFS is parameterless and of rapid convergence. However, WFS also has its shortcomings, sometimes it will inevitably be trapped into local optima, thereby yield inferior solutions owing to its relatively weak exploration ability. Spherical evolution (SE) adopts a novel spherical search pattern that takes aim at splendid search ability. Cooperative coevolution is a useful parallel structure for reconciling algorithmic performance. Considering the complementary strengths of both algorithms, we herein propose a new hybrid algorithm that is comprised of SE and WFS using cooperative coevolution. During the search for optimal solutions in WFS, we replaced the original search matrix and introduced the spherical mechanism of SE, in parallel with coevolution to enhance the competitiveness of the population. The two distinct search dynamics were combined in a parallel and coevolutionary way, thereby getting a good search performance. The resultant hybrid algorithm, CCWFSSE, was tested on the CEC2017 benchmark set and 22 CEC 2011 real-world problems. The experimental data obtained can verify that CCWFSSE outperforms other algorithms in aspects of effectiveness and robustness.
- 14 October 2021
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 14 (1) , 1-19
Open AccessA Cooperative Coevolution Wingsuit Flying Search Algorithm with Spherical Evolution
The algorithm wingsuit flying search (WFS) mimics the procedure of landing the vehicle. The outstanding feature of WFS is parameterless and of rapid convergence. However, WFS also has its shortcomings, sometimes it will inevitably be trapped into local optima, thereby yield inferior solutions owing to its relatively weak exploration ability. Spherical evolution (SE) adopts a novel spherical search pattern that takes aim at splendid search ability. Cooperative coevolution is a useful parallel structure for reconciling algorithmic performance. Considering the complementary strengths of both algorithms, we herein propose a new hybrid algorithm that is comprised of SE and WFS using cooperative coevolution. During the search for optimal solutions in WFS, we replaced the original search matrix and introduced the spherical mechanism of SE, in parallel with coevolution to enhance the competitiveness of the population. The two distinct search dynamics were combined in a parallel and coevolutionary way, thereby getting a good search performance. The resultant hybrid algorithm, CCWFSSE, was tested on the CEC2017 benchmark set and 22 CEC 2011 real-world problems. The experimental data obtained can verify that CCWFSSE outperforms other algorithms in aspects of effectiveness and robustness.
- Open Access
- 20 June 2021
- Published by Wiley in Internet Technology Letters
- Vol. 7 (1)
A DDoS attack detection and defense mechanism based on the self‐organizing mapping in SDN
Since the emergence of Software Defined Network (SDN), it has been widely concerned by the academia and the industry. However, Distributed Denial of Attack (DDoS) can pose a threat to the SDN. Many papers use machine learning algorithms to detect DDoS attacks in SDN, trying to find a balance between detection accuracy and processing time. The purpose of this paper is to propose a DDoS attack detection and defense mechanism based on the Self‐Organizing Mapping (SOM) under SDN environment. The experimental results show that this mechanism can not only maintain the proper precision, but also reduce the processing time. In addition, it can also restore port communication.
- 20 June 2021
- Published by Wiley in Internet Technology Letters
- Vol. 7 (1)
Open AccessA DDoS attack detection and defense mechanism based on the self‐organizing mapping in SDN
Since the emergence of Software Defined Network (SDN), it has been widely concerned by the academia and the industry. However, Distributed Denial of Attack (DDoS) can pose a threat to the SDN. Many papers use machine learning algorithms to detect DDoS attacks in SDN, trying to find a balance between detection accuracy and processing time. The purpose of this paper is to propose a DDoS attack detection and defense mechanism based on the Self‐Organizing Mapping (SOM) under SDN environment. The experimental results show that this mechanism can not only maintain the proper precision, but also reduce the processing time. In addition, it can also restore port communication.
- Open Access
- 22 April 2021
- Published by Wiley in Scientific Programming
- Vol. 2021, 1-11
Tumor Grade and Overall Survival Prediction of Gliomas Using Radiomics
Glioma is one of the most common and deadly malignant brain tumors originating from glial cells. For personalized treatment, an accurate preoperative prognosis for glioma patients is highly desired. Recently, various machine learning-based approaches have been developed to predict the prognosis based on preoperative magnetic resonance imaging (MRI) radiomics, which extract quantitative features from radiographic images. However, major challenges remain for methodologic developments to optimize feature extraction and provide rapid information flow in clinical settings. This study investigates two machine learning-based prognosis prediction tasks using radiomic features extracted from preoperative multimodal MRI brain data: (i) prediction of tumor grade (higher-grade vs. lower-grade gliomas) from preoperative MRI scans and (ii) prediction of patient overall survival (OS) in higher-grade gliomas ( 12 months) from preoperative MRI scans. Specifically, these two tasks utilize the conventional machine learning-based models built with various classifiers. Moreover, feature selection methods are applied to increase model performance and decrease computational costs. In the experiments, models are evaluated in terms of their predictive performance and stability using a bootstrap approach. Experimental results show that classifier choice and feature selection technique plays a significant role in model performance and stability for both tasks; a variability analysis indicates that classification method choice is the most dominant source of performance variation for both tasks.
- 22 April 2021
- Published by Wiley in Scientific Programming
- Vol. 2021, 1-11
Open AccessTumor Grade and Overall Survival Prediction of Gliomas Using Radiomics
Glioma is one of the most common and deadly malignant brain tumors originating from glial cells. For personalized treatment, an accurate preoperative prognosis for glioma patients is highly desired. Recently, various machine learning-based approaches have been developed to predict the prognosis based on preoperative magnetic resonance imaging (MRI) radiomics, which extract quantitative features from radiographic images. However, major challenges remain for methodologic developments to optimize feature extraction and provide rapid information flow in clinical settings. This study investigates two machine learning-based prognosis prediction tasks using radiomic features extracted from preoperative multimodal MRI brain data: (i) prediction of tumor grade (higher-grade vs. lower-grade gliomas) from preoperative MRI scans and (ii) prediction of patient overall survival (OS) in higher-grade gliomas ( 12 months) from preoperative MRI scans. Specifically, these two tasks utilize the conventional machine learning-based models built with various classifiers. Moreover, feature selection methods are applied to increase model performance and decrease computational costs. In the experiments, models are evaluated in terms of their predictive performance and stability using a bootstrap approach. Experimental results show that classifier choice and feature selection technique plays a significant role in model performance and stability for both tasks; a variability analysis indicates that classification method choice is the most dominant source of performance variation for both tasks.