Current Issue : July - September Volume : 2017 Issue Number : 3 Articles : 5 Articles
A novel artificial immune system algorithm with social learning mechanisms (AIS-SL) is proposed in this paper. In AIS-SL,\ncandidate antibodies aremarked with an elitist swarm(ES) or a common swarm(CS). Correspondingly, these antibodies are named\nES antibodies or CS antibodies. In the mutation operator, ES antibodies experience self-learning, while CS antibodies execute two\ndifferent social learning mechanisms, that is, stochastic social learning (SSL) and heuristic social learning (HSL), to accelerate the\nconvergence process. Moreover, a dynamic searching radius update strategy is designed to improve the solution accuracy. In the\nnumerical simulations, five benchmark functions and a practical industrial application of proportional-integral-differential (PID)\ncontroller tuning is selected to evaluate the performance of the proposed AIS-SL. The simulation results indicate that AIS-SL has\nbetter solution accuracy and convergence speed than the canonical opt-aiNet, IA-AIS, and AAIS-2S....
It is a fact that more and more users are adopting\nthe online digital payment systems via mobile devices for\neveryday use. This attracts powerful gangs of cybercriminals,\nwhich use sophisticated and highly intelligent types of malware\nto broaden their attacks. Malicious software is designed\nto run quietly and to remain unsolved for a long time. It manages\nto take full control of the device and to communicate (via\nthe Tor network) with its Command&Control; servers of fastflux\nbotnets� networks to which it belongs. This is done to\nachieve the malicious objectives of the botmasters. This paper\nproposes the development of the computational intelligence\nanti-malware framework (CIantiMF) which is innovative,\nultra-fast and has low requirements. It runs under the android\noperating system (OS) and its reasoning is based on advanced\ncomputational intelligence approaches. The selection of the\nandroid OS was based on its popularity and on the number\nof critical applications available for it. The CIantiMF uses\ntwo advanced technology extensions for the ART java virtual\nmachine which is the default in the recent versions of android.\nThe first is the smart anti-malware extension, which can recognize\nwhether the java classes of an android application\nare benign or malicious using an optimized multi-layer perceptron.\nThe optimization is done by the employment of the\nbiogeography-based optimizer algorithm. The second is the\nTor online traffic identification extension, which is capable\nof achieving malware localization, Tor traffic identification and botnets prohibition, with the use of the online sequential\nextreme learning machine algorithm....
In the emerging field of acoustic novelty detection, most research efforts are devoted to probabilistic approaches such as mixture\nmodels or state-space models. Only recent studies introduced (pseudo-)generative models for acoustic novelty detection with\nrecurrent neural networks in the form of an autoencoder. In these approaches, auditory spectral features of the next short term\nframe are predicted from the previous frames by means of Long-Short Term Memory recurrent denoising autoencoders. The\nreconstruction error between the input and the output of the autoencoder is used as activation signal to detect novel events. There is\nno evidence of studies focused on comparing previous efforts to automatically recognize novel events fromaudio signals and giving\na broad and in depth evaluation of recurrent neural network-based autoencoders. The present contribution aims to consistently\nevaluate our recent novel approaches to fill this white spot in the literature and provide insight by extensive evaluations carried out\non three databases:A3Novelty, PASCALCHiME, and PROMETHEUS.Besides providing an extensive analysis of novel and state-ofthe-\nart methods, the article shows how RNN-based autoencoders outperformstatistical approaches up to an absolute improvement\nof 16.4% average ...
As a typical deep-learning model, Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from\nimages using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN\nmodels employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there\nare some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining\nBiomimetic Pattern Recognition (BPR) with CNNs is proposed for image classification. BPR performs class recognition by a union\nof geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern\nrecognition.The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-\n10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which\nare much higher in comparison with the other four methods in most cases...
To deal with the problems of illumination changes or pose variations and serious partial occlusion, patch based multiple instance\nlearning (P-MIL) algorithm is proposed. The algorithm divides an object into many blocks. Then, the online MIL algorithm is\napplied on each block for obtaining strong classifier. The algorithm takes account of both the average classification score and\nclassification scores of all the blocks for detecting the object. In particular, compared with thewhole object based MIL algorithm, the\nP-MIL algorithm detects the object according to the unoccluded patches when partial occlusion occurs. After detecting the object,\nthe learning rates for updatingweak classifiers� parameters are adaptively tuned.The classifier updating strategy avoids overupdating\nand underupdating the parameters. Finally, the proposed method is compared with other state-of-the-art algorithms on several\nclassical videos.Theexperiment results illustrate that the proposed method performs well especially in case of illumination changes\nor pose variations and partial occlusion. Moreover, the algorithm realizes real-time object tracking....
Loading....