Yiwen Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiwen Liang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Wen Zhou
School of Computer Science, Hubei University of Technology, Wuhan, China
4 shared publications Chengyu Tan
School of Computer Science, Wuhan University, Wuhan 430072, P. R. China
3 shared publications- Chengyu Tan
School of Computer Science, Wuhan University, Wuhan, China
2 shared publications - Dongmei Wang
School of Computer Science, Wuhan University, Wuhan, China
2 shared publications - Hongbin Dong
School of Cyber Science and Engineering, Wuhan University, Wuhan, China
2 shared publications Aolin Liu
1 shared publication
Latest Publications
- 2 December 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (12) , 16151-16169
NDAMM: a numerical differentiation-based artificial macrophage model for anomaly detection
- 2 December 2022
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (12) , 16151-16169
NDAMM: a numerical differentiation-based artificial macrophage model for anomaly detection
- 24 June 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (18) , 19478-19500
Immune optimization inspired artificial natural killer cell earthquake prediction method
- 24 June 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (18) , 19478-19500
Immune optimization inspired artificial natural killer cell earthquake prediction method
- 16 February 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (9) , 11680-11701
Innate immune memory and its application to artificial immune systems
The study of innate immune-based algorithms is an important research domain in Artificial Immune System (AIS), such as Dendritic Cell Algorithm (DCA), Toll-Like Receptor algorithm (TLRA). The parameters in these algorithms usually require either manually pre-defined usually provided by the immunologists, or empirically derived from the training dataset, and result in poor self-adaptation and self-learning. The fundamental reason is that the original innate immune mechanisms lack adaptive biological theory. To solve this problem, a theory called ‘Trained Immunity™ or Innate Immune Memory (IIM)™ that thinks innate immunity can also build immunological memory to enhance the immune system™s learning and adaptive reactions to the second stimulus is introduced into AIS to improve the innate immune algorithms™ adaptability. In this study, we present an overview of IIM with particular emphasis on analogies in the AIS world, and a modified DCA with an effective automated tuning mechanism based on IIM (IIM-DCA) to optimize migration threshold of DCA. The migration threshold of Dendritic Cells (DCs) determines the lifespan of the antigen collected by DCs, and directly affect the detection speed and accuracy of DCA. Experiments on real datasets show that our proposed IIM-DCA which integrates Innate Immune Memory mechanism delivers more accurate results.
- 16 February 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (9) , 11680-11701
Innate immune memory and its application to artificial immune systems
The study of innate immune-based algorithms is an important research domain in Artificial Immune System (AIS), such as Dendritic Cell Algorithm (DCA), Toll-Like Receptor algorithm (TLRA). The parameters in these algorithms usually require either manually pre-defined usually provided by the immunologists, or empirically derived from the training dataset, and result in poor self-adaptation and self-learning. The fundamental reason is that the original innate immune mechanisms lack adaptive biological theory. To solve this problem, a theory called ‘Trained Immunity™ or Innate Immune Memory (IIM)™ that thinks innate immunity can also build immunological memory to enhance the immune system™s learning and adaptive reactions to the second stimulus is introduced into AIS to improve the innate immune algorithms™ adaptability. In this study, we present an overview of IIM with particular emphasis on analogies in the AIS world, and a modified DCA with an effective automated tuning mechanism based on IIM (IIM-DCA) to optimize migration threshold of DCA. The migration threshold of Dendritic Cells (DCs) determines the lifespan of the antigen collected by DCs, and directly affect the detection speed and accuracy of DCA. Experiments on real datasets show that our proposed IIM-DCA which integrates Innate Immune Memory mechanism delivers more accurate results.
- 4 November 2021
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (5) , 7016-7037
NKA: a pathogen dose-based natural killer cell algorithm and its application to classification
- 4 November 2021
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (5) , 7016-7037
NKA: a pathogen dose-based natural killer cell algorithm and its application to classification
- 12 October 2021
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 35 (13)
A Safe Zone SMOTE Oversampling Algorithm Used in Earthquake Prediction Based on Extreme Imbalanced Precursor Data
Earthquake prediction based on extreme imbalanced precursor data is a challenging task for standard algorithms. Since even if an area is in an earthquake-prone zone, the proportion of days with earthquakes per year is still a minority. The general method is to generate more artificial data for the minority class that is the earthquake occurrence data. But the most popular oversampling methods generate synthetic samples along line segments that join minority class instances, which is not suitable for earthquake precursor data. In this paper, we propose a Safe Zone Synthetic Minority Oversampling Technique (SZ-SMOTE) oversampling method as an enhancement of the SMOTE data generation mechanism. SZ-SMOTE generates synthetic samples with a concentration mechanism in the hyper-sphere area around each selected minority instances. The performance of SZ-SMOTE is compared against no oversampling, SMOTE and its popular modifications adaptive synthetic sampling (ADASYN) and borderline SMOTE (B-SMOTE) on six different classifiers. The experiment results show that the quality of earthquake prediction using SZ-SMOTE as oversampling algorithm significantly outperforms that of using the other oversampling algorithms.
- 12 October 2021
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 35 (13)
A Safe Zone SMOTE Oversampling Algorithm Used in Earthquake Prediction Based on Extreme Imbalanced Precursor Data
Earthquake prediction based on extreme imbalanced precursor data is a challenging task for standard algorithms. Since even if an area is in an earthquake-prone zone, the proportion of days with earthquakes per year is still a minority. The general method is to generate more artificial data for the minority class that is the earthquake occurrence data. But the most popular oversampling methods generate synthetic samples along line segments that join minority class instances, which is not suitable for earthquake precursor data. In this paper, we propose a Safe Zone Synthetic Minority Oversampling Technique (SZ-SMOTE) oversampling method as an enhancement of the SMOTE data generation mechanism. SZ-SMOTE generates synthetic samples with a concentration mechanism in the hyper-sphere area around each selected minority instances. The performance of SZ-SMOTE is compared against no oversampling, SMOTE and its popular modifications adaptive synthetic sampling (ADASYN) and borderline SMOTE (B-SMOTE) on six different classifiers. The experiment results show that the quality of earthquake prediction using SZ-SMOTE as oversampling algorithm significantly outperforms that of using the other oversampling algorithms.
- Open Access
- 7 July 2021
- Published by Association for Computing Machinery (ACM)
- p. 115-116
Pathogen dose based natural killer cell algorithm for classification
Negative selection algorithm(NSA), which is the most representative classification algorithm among immune heuristic algorithms, has been successfully applied to solve many classification problems. However, there are two obvious problems with NSA. First, NSA establishes specific antibodies for each antigen based on the mechanism of specific antigen matching antibody, which leads to too many and redundant detectors. Second, the detection stage needs to calculate the matching degree of the antigen with all the detectors, and the detection efficiency is low. This paper proposes a new non-specific natural killer cell algorithm (NKA) based on pathogen dose. NKA draws on the mechanism of NK cells constructing phenotype detectors based on pathogen dose. First, NKA defines dose and phenotype detector, and optimizes it based on the memory evolution mechanism of phenotype; then establishes k-d tree for the optimized phenotype, and pathogens only need to match the dose with the nearest phenotype detector. Experimental results show that the method proposed in this paper, NKA, can not only achieve a better performance through fewer detectors, but also has a higher efficiency in the training and detection phase, compared with three NSA-based algorithms.
- 7 July 2021
- Published by Association for Computing Machinery (ACM)
- p. 115-116
Open AccessPathogen dose based natural killer cell algorithm for classification
Negative selection algorithm(NSA), which is the most representative classification algorithm among immune heuristic algorithms, has been successfully applied to solve many classification problems. However, there are two obvious problems with NSA. First, NSA establishes specific antibodies for each antigen based on the mechanism of specific antigen matching antibody, which leads to too many and redundant detectors. Second, the detection stage needs to calculate the matching degree of the antigen with all the detectors, and the detection efficiency is low. This paper proposes a new non-specific natural killer cell algorithm (NKA) based on pathogen dose. NKA draws on the mechanism of NK cells constructing phenotype detectors based on pathogen dose. First, NKA defines dose and phenotype detector, and optimizes it based on the memory evolution mechanism of phenotype; then establishes k-d tree for the optimized phenotype, and pathogens only need to match the dose with the nearest phenotype detector. Experimental results show that the method proposed in this paper, NKA, can not only achieve a better performance through fewer detectors, but also has a higher efficiency in the training and detection phase, compared with three NSA-based algorithms.
- 22 May 2021
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (2) , 1461-1476
An immune optimization based deterministic dendritic cell algorithm
- 22 May 2021
- Published by Springer Nature in Applied Intelligence
- Vol. 52 (2) , 1461-1476
An immune optimization based deterministic dendritic cell algorithm
- 22 February 2020
- Published by Springer Nature in Earth Science Informatics
- Vol. 13 (2) , 447-457
The deterministic dendritic cell algorithm with Haskell in earthquake magnitude prediction
- 22 February 2020
- Published by Springer Nature in Earth Science Informatics
- Vol. 13 (2) , 447-457
The deterministic dendritic cell algorithm with Haskell in earthquake magnitude prediction
- 27 April 2012
- Published by International Academy Publishing (IAP) in Journal of Software
- Vol. 7 (4)
The Effect of Real-valued Negative Selection Algorithm on Web Server Aging Detection
Several researchers have reported the fact that web server systems executing continuously for a long time show a degradation of their performance, and/or an in- creased occurrence rate of hang/crash failures. This phe- nomenon has been called ’web server aging’. To avoid this problem, it becomes an important issue to detect web server aging in web server maintenance. Existing technologies depending on aging samples succeed in detecting known web server aging, but fail to detect novel aging because of the nondeterministic nature of the web server aging. Given that normal samples are much easier to acquire from running web server than aging samples, this paper proposed an immune-inspired real-valued negative selection algorithm to detect previously unseen web server aging, it only needs normal samples to train detectors that have the ability to classify a novel sample as web server aging or not. The basis of the detection is aging causes performance deviation from the normal state. Preliminary experimental results showed that the method could improve the performance of the detection of novel web server aging without responding to normal status
- 27 April 2012
- Published by International Academy Publishing (IAP) in Journal of Software
- Vol. 7 (4)
The Effect of Real-valued Negative Selection Algorithm on Web Server Aging Detection
Several researchers have reported the fact that web server systems executing continuously for a long time show a degradation of their performance, and/or an in- creased occurrence rate of hang/crash failures. This phe- nomenon has been called ’web server aging’. To avoid this problem, it becomes an important issue to detect web server aging in web server maintenance. Existing technologies depending on aging samples succeed in detecting known web server aging, but fail to detect novel aging because of the nondeterministic nature of the web server aging. Given that normal samples are much easier to acquire from running web server than aging samples, this paper proposed an immune-inspired real-valued negative selection algorithm to detect previously unseen web server aging, it only needs normal samples to train detectors that have the ability to classify a novel sample as web server aging or not. The basis of the detection is aging causes performance deviation from the normal state. Preliminary experimental results showed that the method could improve the performance of the detection of novel web server aging without responding to normal status
- 18 August 2010
- Published by Springer Nature
- p. 79-84
Actor Petri net Model: toward Suitable and Flexible Level Representation of Scientific Workflows
- 18 August 2010
- Published by Springer Nature
- p. 79-84
Actor Petri net Model: toward Suitable and Flexible Level Representation of Scientific Workflows