Followed Journals
Journal you Follow: 0
 
Sign Up to follow journals, search in your chosen journals and, optionally, receive Email Alerts when new issues of your Followed Journals are published.
Already have an account? Sign In to see the journals you follow.
Similar Journals
Journal Cover
IEEE Transactions on Emerging Topics in Computational Intelligence
Number of Followers: 5  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Online) 2471-285X
Published by IEEE Homepage  [229 journals]
  • IEEE Transactions on Emerging Topics in Computational Intelligence
    • Abstract: Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • IEEE Computational Intelligence Society
    • Abstract: Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Information for Authors
    • Abstract: These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Guest Editorial Special Issue on Adversarial Learning in Computational
           Intelligence
    • Pages: 414 - 416
      Abstract: The seven papers in this special section focus on adversarial learning in computational intelligence. The papers aim to capture the most recent advances of adversarial learning from both theoretical and empirical perspectives. Moreover, it attempts to present its novel applications to other domains beyond image generation. Adversarial learning has attracted tremendous attention in the community of machine learning over the past few years. It normally integrates two components that contest with each other in a two-player zero-sum game. Since its birth in 2014, adversarial learning has been widely applied to not only the generation of realistic images, but also many other research topics, such as data augmentation, domain adaptation, and adversarial attack, often leading to appealing performance. However, we have just witnessed the early rise of this technique, and still confront many challenges, for example, the mode collapse problem, and the interpretability of its results and failures. Computational Intelligence (CI) technologies are expected to provide efficient solutions to deal with the raised challenges. Moreover, most of the previous adversarial-learning studies are largely limited in addressing static images or feature vectors. It still remains largely an open question of how adversarial learning performs for other complex and temporally variational signals or modalities, such as speech and text.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Improving Adversarial Neural Machine Translation for Morphologically Rich
           Language
    • Pages: 417 - 426
      Abstract: Generative adversarial networks (GAN) have great successes on natural language processing (NLP) and neural machine translation (NMT). However, the existing discriminator in GAN for NMT only combines two words as one query to train the translation models, which restrict the discriminator to be more meaningful and fail to apply rich monolingual information. Recent studies only consider one single reference translation during model training, this limit the GAN model to learn sufficient information about the representation of source sentence. These situations are even worse when languages are morphologically rich. In this article, an extended version of GAN model for neural machine translation is proposed to optimize the performance of morphologically rich language translation. In particular, we use the morphological word embedding instead of word embedding as input in GAN model to enrich the representation of words and overcome the data sparsity problem during model training. Moreover, multiple references are integrated into discriminator to make the model consider more context information and adapt to the diversity of different languages. Experimental results on German$leftrightarrow$English, French$leftrightarrow$English, Czech$leftrightarrow$English, Finnish$leftrightarrow$English, Turkish$leftrightarrow$English, Chinese$leftrightarrow$English, Finnish$leftrightarrow$Turkish and Turkish$leftrightarrow$Czech translation tasks demonstrate that our method achieves significant improvements over baseline systems.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Hardening Random Forest Cyber Detectors Against Adversarial Attacks
    • Pages: 427 - 439
      Abstract: Machine learning algorithms are effective in several applications, but they are not as much successful when applied to intrusion detection in cyber security. Due to the high sensitivity to their training data, cyber detectors based on machine learning are vulnerable to targeted adversarial attacks that involve the perturbation of initial samples. Existing defenses assume unrealistic scenarios; their results are underwhelming in non-adversarial settings; or they can be applied only to machine learning algorithms that perform poorly for cyber security. We present an original methodology for countering adversarial perturbations targeting intrusion detection systems based on random forests. As a practical application, we integrate the proposed defense method in a cyber detector analyzing network traffic. The experimental results on millions of labelled network flows show that the new detector has a twofold value: it outperforms state-of-the-art detectors that are subject to adversarial attacks; it exhibits robust results both in adversarial and non-adversarial scenarios.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Static2Dynamic: Video Inference From a Deep Glimpse
    • Pages: 440 - 449
      Abstract: In this article, we address a novel and challenging task of video inference, which aims to infer video sequences from given non-consecutive video frames. Taking such frames as the anchor inputs, our focus is to recover possible video sequence outputs based on the observed anchor frames at the associated time. With the proposed Stochastic and Recurrent Conditional GAN (SR-cGAN), we are able to preserve visual content across video frames with additional ability to handle possible temporal ambiguity. In the experiments, we show that our SR-cGAN not only produces preferable video inference results, it can also be applied to relevant tasks of video generation, video interpolation, video inpainting, and video prediction.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • A System-Driven Taxonomy of Attacks and Defenses in Adversarial Machine
           Learning
    • Pages: 450 - 467
      Abstract: Machine Learning (ML) algorithms, specifically supervised learning, are widely used in modern real-world applications, which utilize Computational Intelligence (CI) as their core technology, such as autonomous vehicles, assistive robots, and biometric systems. Attacks that cause misclassifications or mispredictions can lead to erroneous decisions resulting in unreliable operations. Designing robust ML with the ability to provide reliable results in the presence of such attacks has become a top priority in the field of adversarial machine learning. An essential characteristic for rapid development of robust ML is an arms race between attack and defense strategists. However, an important prerequisite for the arms race is access to a well-defined system model so that experiments can be repeated by independent researchers. This article proposes a fine-grained system-driven taxonomy to specify ML applications and adversarial system models in an unambiguous manner such that independent researchers can replicate experiments and escalate the arms race to develop more evolved and robust ML applications. The article provides taxonomies for: 1) the dataset, 2) the ML architecture, 3) the adversary's knowledge, capability, and goal, 4) adversary's strategy, and 5) the defense response. In addition, the relationships among these models and taxonomies are analyzed by proposing an adversarial machine learning cycle. The provided models and taxonomies are merged to form a comprehensive system-driven taxonomy, which represents the arms race between the ML applications and adversaries in recent years. The taxonomies encode best practices in the field and help evaluate and compare the contributions of research works and reveals gaps in the field.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Unsupervised Representation Disentanglement Using Cross Domain Features
           and Adversarial Learning in Variational Autoencoder Based Voice Conversion
           
    • Pages: 468 - 479
      Abstract: An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic features of different properties, to improve the performance of VAE-VC. We believed that the success came from more disentangled latent representations. In this article, we extend the CDVAE-VC framework by incorporating the concept of adversarial learning, in order to further increase the degree of disentanglement, thereby improving the quality and similarity of converted speech. More specifically, we first investigate the effectiveness of incorporating the generative adversarial networks (GANs) with CDVAE-VC. Then, we consider the concept of domain adversarial training and add an explicit constraint to the latent representation, realized by a speaker classifier, to explicitly eliminate the speaker information that resides in the latent code. Experimental results confirm that the degree of disentanglement of the learned latent representation can be enhanced by both GANs and the speaker classifier. Meanwhile, subjective evaluation results in terms of quality and similarity scores demonstrate the effectiveness of our proposed methods.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Learning Class-Aligned and Generalized Domain-Invariant Representations
           for Speech Emotion Recognition
    • Pages: 480 - 489
      Abstract: Although recent research on speech emotion recognition has demonstrated that learning domain-invariant features provide an elegant solution to domain mismatch, the features learned by the existing methods lack generalization capabilities to capture latent information from datasets. We propose two novel domain adaptation methods, the generalized domain adversarial neural network (GDANN) and the class-aligned GDANN (CGDANN), to learn generalized domain-invariant representations for emotion recognition. GDANN and CGDANN, which are derived from multitask learning (MTL), consist of three tasks. The main task is to recognize the emotional category to which the input belongs. The remaining two tasks are auxiliary tasks. One is to use a variational autoencoder to model the input distribution, which encourages the model to learn the distribution of latent representations. The other is to learn the common representations of different domains, for which distinguishing via the domain classifier is difficult. The gradient of the domain classifier guides the shared representations of the source and target domains to approximate each other using a gradient reversal layer. To evaluate the effectiveness of the proposed methods, we conduct several experiments with the IEMOCAP and MSP-IMPROV datasets. The results illustrate that good performance is achieved compared with that of state-of-the-art methods. Notably, CGDANN utilizes a small quantity of labeled target domain samples to align the distribution representation and obtains the best performance among the comparison methods. We further visualize the representations learned by the proposed methods and discover that the representations of the source and target domains converge with a low variance.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Attacking VQA Systems via Adversarial Background Noise
    • Pages: 490 - 499
      Abstract: Adversarial examples have been successfully generated for various image classification models. Recently, several methods have been proposed to generate adversarial examples for more sophisticated tasks such as image captioning and visual question answering (VQA). In this paper, we propose a targeted adversarial attack for VQA where the noise is added only to the background pixels of the image keeping the rest of the image unchanged. The experiments are done on two state-of-the-art VQA systems: End-to-End Neural Module Network (N2NMN) and Memory, Attention and Composition Network (MAC network) and three datasets: SHAPES, CLEVR, and VQA v2.0. We combine validation and test sets of SHAPES, and select 1000 image-question pairs from CLEVR validation set. For VQA v2.0, we select 500 image-question pairs from the validation set for experimentation. We study the proposed attack under two different settings: same-category and different-category; referring to whether or not the target adversarial answer lies in the same category as the original answer. For CLEVR, the proposed attack achieves 100% success rate for both the models under same-category setting and success rate of 22.3% for N2NMN and 73.9% for MAC network under different-category setting. For SHAPES, the proposed attack achieves success rate of 68.9% for N2NMN. The proposed attack also achieves high success rate for same-category setting in VQA v2.0. Furthermore, we give strong rationale behind the robustness of N2NMN to different-category attack.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Loss Functions of Generative Adversarial Networks (GANs): Opportunities
           and Challenges
    • Pages: 500 - 522
      Abstract: Recently, the Generative Adversarial Networks (GANs) are fast becoming a key promising research direction in computational intelligence. To improve the modeling ability of GANs, loss functions are used to measure the differences between samples generated by the model and real samples, and make the model learn towards the goal. In this paper, we perform a survey for the loss functions used in GANs, and analyze the pros and cons of these loss functions. Firstly, the basic theory of GANs, and its training mechanism are introduced. Then, the loss functions used in GANs are summarized, including not only the objective functions of GANs, but also the application-oriented GANs’ loss functions. Thirdly, the experiments and analyses of representative loss functions are discussed. Finally, several suggestions on how to choose appropriate loss functions in a specific task are given.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • A Comprehensive Review of Shepherding as a Bio-Inspired Swarm-Robotics
           Guidance Approach
    • Pages: 523 - 537
      Abstract: The simultaneous control of multiple coordinated robotic agents represents an elaborate problem. If solved, however, the interaction between the agents can lead to solutions to sophisticated problems. The concept of swarming, inspired by nature, can be described as the emergence of complex system-level behaviors from the interactions of relatively elementary agents. Due to the effectiveness of solutions found in nature, bio-inspired swarming-based control techniques are receiving a lot of attention in robotics. One method, known as swarm shepherding, is founded on the sheep herding behavior exhibited by sheepdogs, where a swarm of relatively simple agents are governed by a shepherd (or shepherds) which is responsible for high-level guidance and planning. Many studies have been conducted on shepherding as a control technique, ranging from the replication of sheep herding via simulation, to the control of uninhabited vehicles and robots for a variety of applications. A comprehensive review of the literature on swarm shepherding is presented in order to reveal the advantages and potential of the approach to be applied to a plethora of robotic systems in the future.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • A Survey of Evolutionary Computation for Web Service Composition: A
           Technical Perspective
    • Pages: 538 - 554
      Abstract: Service oriented computing has emerged as a popular software development paradigm. In the era of Cloud computing, Big data, the Internet of Things (IoT) and Smart Cities, Web service composition has been extensively researched. Web service composition aims to find the best way of combining services, which accomplish simple tasks, into a more sophisticated composite application. Evolutionary computation lends itself to tackling the problem of Web service composition, since it allows for the optimisation of the overall Quality of Service attributes of the composite solution. In order to gain a better understanding of the different evolutionary computation-based approaches applied to this problem, a number of literature surveys have been written in this area. However, these surveys do not focus on the technical aspects of using evolutionary computation to this end, instead focusing on the general application of methods. Thus, the focus of this survey is on analysing existing works from a technical perspective, paying particular attention to the following key decisions when choosing an evolutionary computation-based approach for Web service composition: a) the representation of candidates, b) the fitness evaluation strategy, c) the handling of correctness constraints, d) the choice of evolutionary algorithms and operators. Based on these analyses, current trends, limitations, and future research paths are identified.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • A Survey of Computational Intelligence Techniques for Air-Conditioners
           Energy Management
    • Pages: 555 - 570
      Abstract: Effective design of air-conditioner (AC) management system has the potential to reduce the cost of electricity consumption and help users to participate in demand response (DR) program as interruptible loads. However, optimizing the operation of AC is complex and, as a potential solution, computational intelligence (CI) techniques based model predictive algorithms are being explored in the literature. This article aims to provide an overview of the CI techniques that are established in addressing relevant and timely open problems of AC management for residential buildings. To do so, first, we provide a brief background on different DR mechanisms and AC management systems. Second, a review of recent advances in CI-based model prediction and optimal control techniques of AC systems for DR management is presented. The discussion reveals that the interest in CI techniques with adaptive learning algorithms is increasing due to their ability to adjust in varying conditions. Then, we provide a brief description of a testbed, which is used for testing various newly developed CI-based AC management techniques in a residential setting. Finally, key issues related to the coordination of a large number of AC systems, modeling accuracy, and computational tractability are highlighted along with their challenges and future research directions.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
  • Mimicking Short-Term Memory in Shape-Reconstruction Task Using an
           EEG-Induced Type-2 Fuzzy Deep Brain Learning Network
    • Pages: 571 - 588
      Abstract: The paper attempts to model short-term memory (STM) for shape-reconstruction tasks by employing a 4-stage deep brain leaning network (DBLN), where the first two stages are built with Hebbian learning and the last two stages with Type-2 Fuzzy logic. The model is trained stage-wise independently with visual stimulus of the object-geometry as the input of the first stage, EEG acquired from different cortical regions as input and output of respective intermediate stages, and recalled object-geometry as the output of the last stage. Two error feedback loops are employed to train the proposed DBLN. The inner loop adapts the weights of the STM based on a measure of error in model-predicted response with respect to the object-shape recalled by the subject. The outer loop adapts the weights of the iconic (visual) memory based on a measure of error of the model predicted response with respect to the desired object-shape. In the test phase, the DBLN model reproduces the recalled object shape from the given input object geometry. The motivation of the paper is to test the consistency in STM encoding (in terms of similarity in network weights) for repeated visual stimulation with the same geometric object. Experiments undertaken on healthy subjects, yield high similarity in network weights, whereas patients with pre-frontal lobe Amnesia yield significant discrepancy in the trained weights for any two trials with the same training object. This justifies the importance of the proposed DBLN model in automated diagnosis of patients with learning difficulty. The novelty of the paper lies in the overall design of the DBLN model with special emphasis to the last two stages of the network, built with vertical slice based type-2 fuzzy logic, to handle uncertainty in function approximation (with noisy EEG data). The proposed technique outperforms the state-of-the-art functional mapping algorithms with respect to the (pre-defined outer loop) error metric, computational complexity and runt-me.
      PubDate: Aug. 2020
      Issue No: Vol. 4, No. 4 (2020)
       
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
 


Your IP address: 54.236.59.154
 
Home (Search)
API
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-