In the previous work, a detector generation algorithm, named as the EvoSeedRNSA, is proposed. A genetic algorithm is adopted in the EvoSeedRNSA to evolve the random seeds to generate an approximately optimal detector ...
详细信息
In the previous work, a detector generation algorithm, named as the EvoSeedRNSA, is proposed. A genetic algorithm is adopted in the EvoSeedRNSA to evolve the random seeds to generate an approximately optimal detector set. This paper proposes an improved EvoSeedRNSA, named as the EvoSeedRNSAII, to generate a more efficient detector set. A multi-group random seed encoding scheme is designed to represent the individuals and different detector generation sequences are discussed. The experiments demonstrate that the EvoSeedRNSAII has a better performance than the EvoSeedRNSA. (C) 2014 Elsevier B.V. All rights reserved.
Concerned with the problem of lacking fault samples of complex equipments, it studies the principle and application of negative selection algorithm of artificial immune system. The detectors generation mechanism of re...
详细信息
Concerned with the problem of lacking fault samples of complex equipments, it studies the principle and application of negative selection algorithm of artificial immune system. The detectors generation mechanism of real-valued negative selection algorithm is introduced. Intuitively, to maximize the covering produced by a set of detectors, it is necessary to reduce their overlapping and not covering the self set. This paper presents an optimization strategy base on re-heating simulated annealing algorithm to modify the position of detectors, not changing their number. This method can improve the covering effect of non-self space. The triangle training data are used to demonstrate the properties of optimized VRNS. Detection rate is improved and false alarming rate is decreased. It is used for fault detection in analog circuit; result demonstrates that the proposed algorithm is better than artificial neural network in fault detection of this circuit.
Shadow regions are detected as objects at image segmentation, object detection and tracking applications. So, it affects negatively the accuracy and performance of algorithms. In this study, artificial immune system-b...
详细信息
ISBN:
(纸本)9781467373869
Shadow regions are detected as objects at image segmentation, object detection and tracking applications. So, it affects negatively the accuracy and performance of algorithms. In this study, artificial immune system-based negative selection algorithm (YBSG) is proposed in order to determine shadow region. This algorithm obtains fast and effective solution to detect nonlinear change shadow region on the video scenes. This algorithm obtains us to increase in 5%-20% shadow detecting performance and 5%-10% execution time with effective method proposed to detect the shadows of different video scenes in literature.
Inspired by the idea of Artificial Immune System, many researches of wireless sensor network (WSN) intrusion detection is based on the artificial intelligent system (AIS). However, a large number of generated detector...
详细信息
Inspired by the idea of Artificial Immune System, many researches of wireless sensor network (WSN) intrusion detection is based on the artificial intelligent system (AIS). However, a large number of generated detectors, black hole, overlap problem of NSA have impeded further used in WSN. In order to improve the anomaly detection performance for WSN, detector generation mechanism need to be improved. Therefore, in this paper, a Differential Evolution Constraint Multi-objective Optimization Problem based negative selection algorithm (DE-CMOP based NSA) is proposed to optimize the distribution and effectiveness of the detector. By combining the constraint handling and multi-objective optimization technique, the algorithm is able to generate the detector set with maximized coverage of non-self space and minimized overlap among detectors. By employing differential evolution, the algorithm can reduce the black hole effectively. The experiment results show that our proposed scheme provides improved NSA algorithm in-terms, the detectors generated by the DE-CMOP based NSA more uniform with less overlap and minimum black hole, thus effectively improves the intrusion detection performance. At the same time, the new algorithm reduces the number of detectors which reduces the complexity of detection phase. Thus, this makes it suitable for intrusion detection in WSN.
Concerned with the problem of lacking fault samples of complex equipments, it studies the principle and application of negative selection algorithm of artificial immune system. The detectors generation mechanism of re...
详细信息
Concerned with the problem of lacking fault samples of complex equipments, it studies the principle and application of negative selection algorithm of artificial immune system. The detectors generation mechanism of real-valued negative selection algorithm is introduced. Intuitively, to maximize the covering produced by a set of detectors, it is necessary to reduce their overlapping and not covering the self set. This paper presents an optimization strategy base on re-heating simulated annealing algorithm to modify the position of detectors, not changing their number. This method can improve the covering effect of non-self space. The triangle training data are used to demonstrate the properties of optimized VRNS. Detection rate is improved and false alarming rate is decreased. It is used for fault detection in analog circuit;result demonstrates that the proposed algorithm is better than artificial neural network in fault detection of this circuit.
This paper presents a new artificial immune algorithm with continuous-learning, which is inspired by the biological immune system, to realize the voltage diagnosis in electrical distribution systems. This conception a...
详细信息
This paper presents a new artificial immune algorithm with continuous-learning, which is inspired by the biological immune system, to realize the voltage diagnosis in electrical distribution systems. This conception allows one to compose a diagnosis system that can continuously learn without reinitialization when new disturbances occur due to the evolution of the electrical system. Two artificial immune algorithms, which are the negative selection algorithm and the clonal selectionalgorithm, are used for the pattern recognition process and the learning process, respectively. The principal application of this new method aids the operation during failures, supervises the protection system, and can evolve with the power systems to continuously acquire new knowledge. This new methodology has a direct impact in the area of diagnosis in electrical systems, as well as, in the pattern recognition problem, because the main contribution and novelty of this method is the continuous learning capability, which enables the system to learn unknown patterns without having to restart the knowledge. This is the major advantage of this methodology. To evaluate the efficiency and performance of this new method, failure simulations were performed in a real distribution system with 134 buses using the EMTP software. The results show robustness and efficiency. (C) 2016 Elsevier Ltd. All rights reserved.
This paper presents a methodology for diagnosis of faults and power quality problems in primary distribution feeders. The input data are the currents of the feeder per phase, monitored only in the substation. An artif...
详细信息
This paper presents a methodology for diagnosis of faults and power quality problems in primary distribution feeders. The input data are the currents of the feeder per phase, monitored only in the substation. An artificial immune system was developed using the negative selection algorithm to detect and classify the faults and power quality problems. The main application of the software is to assist in the operation during a fault and supervise the power quality problem. A 103-bus non-transposed real feeder is used to evaluate the proposed algorithm. The results show that the algorithm is effective in its proposed and it has great potential for on-line applications.
Run-time malware detection strategies have already attracted extensive attention due to its effectiveness and robustness. With regards to Windows operating system, the API (Application Program Interface) is chosen to ...
详细信息
ISBN:
(纸本)9781509034840
Run-time malware detection strategies have already attracted extensive attention due to its effectiveness and robustness. With regards to Windows operating system, the API (Application Program Interface) is chosen to analyze program behavior. However, the API call sequences can be manipulated by a crafty attacker to circumvent detection. In order to handle this problem, we present a novel run-time malware detection strategy based on IRP (I/O Request Package) and develop a tool for capturing IRPs based on kernel driver technology. Some classic approaches are exploited to classify IRP sequences for malware detection, including Naive Bayes, Bayesian Networks, Support Vector Machine, C4.5 Decision Tree, Boosting, and negative selection algorithm. For fast run-time malware detection, we also present a novel artificial immune algorithm (NAIA) by means of short IRP sequences which exist only in malicious IRP sequences. Ultimately, for the whole dataset, boosted decision tree outperforms others with true positive rate 98.3%, and our NAIA outperforms other methods for the first 200 IRPs of each sequence.
The artificial immune algorithm is the hot topic in much research such as the intrusion detection system, the information retrieval system and the data mining system. The negative selection algorithm is the typical ar...
详细信息
The artificial immune algorithm is the hot topic in much research such as the intrusion detection system, the information retrieval system and the data mining system. The negative selection algorithm is the typical artificial immune algorithm. A common representation of binary strings for antibody (detector) and antigen have been associated with inefficiencies when generating detector and inspecting antigen. We use a single integer to represent the detector and provide the basis of improving negative selection algorithm efficiency. In the detector generation algorithm, extracting sub-strings in self that its length is larger than threshold and converting them to single integer in numerical interval, then the rest integers in numerical interval are selected as numerical detectors. It can reduce the time and space overhead of detector generation and provide the facility to analyze the positive and negative errors when antigen inspection. The numerical matching rule is given. The B-tree is used to create index of numerical detector. Extracting sub-strings in antigen that its length is larger than threshold and converting them to some integers. If there is the same value as those integers in the index of numerical detector, then the antigen matches one numerical detector. It can improve the efficiency of antigen inspection. Finally the prototype of the numerical negative selection algorithm and negative selection algorithm are realized to test the overhead of the detector generation and antigen inspection using the live data set. The results show that the numerical negative selection algorithm can reduce the time and space overhead and avoid fluctuation of the overhead.
The negative selection algorithm (NSA) is one of models in artificial immune systems. Traditional NSAs do not perform any differentiation for training self dataset and only use the mechanism of negativeselection. The...
详细信息
The negative selection algorithm (NSA) is one of models in artificial immune systems. Traditional NSAs do not perform any differentiation for training self dataset and only use the mechanism of negativeselection. They will generate excessive invalid detectors and have poor detection performance when the training selves contain noisy data. Inspired by immune suppression mechanism, an outlier robust NSA is proposed. The new algorithm will divide the training selves into internal selves, boundary selves and outlier selves. At the same time, the information hiding in different kind of selves is fully utilized. Furthermore, by combining negativeselection mechanism with positive selection mechanism, the new algorithm can cover the non-self region more effectively. The experiment results show that no matter the training self data is clean or not, the new algorithm can obtain better detection performance with fewer detectors.
暂无评论