| 1. |
- Adiban, Mohammad, et al.
(författare)
-
A step-by-step training method for multi generator GANs with application to anomaly detection and cybersecurity
- 2023
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 537, s. 296-308
-
Tidskriftsartikel (refereegranskat)abstract
- Cyber attacks and anomaly detection are problems where the data is often highly unbalanced towards normal observations. Furthermore, the anomalies observed in real applications may be significantly different from the ones contained in the training data. It is, therefore, desirable to study methods that are able to detect anomalies only based on the distribution of the normal data. To address this problem, we propose a novel objective function for generative adversarial networks (GANs), referred to as STEPGAN. STEP-GAN simulates the distribution of possible anomalies by learning a modified version of the distribution of the task-specific normal data. It leverages multiple generators in a step-by-step interaction with a discriminator in order to capture different modes in the data distribution. The discriminator is optimized to distinguish not only between normal data and anomalies but also between the different generators, thus encouraging each generator to model a different mode in the distribution. This reduces the well-known mode collapse problem in GAN models considerably. We tested our method in the areas of power systems and network traffic control systems (NTCSs) using two publicly available highly imbalanced datasets, ICS (Industrial Control System) security dataset and UNSW-NB15, respectively. In both application domains, STEP-GAN outperforms the state-of-the-art systems as well as the two baseline systems we implemented as a comparison. In order to assess the generality of our model, additional experiments were carried out on seven real-world numerical datasets for anomaly detection in a variety of domains. In all datasets, the number of normal samples is significantly more than that of abnormal samples. Experimental results show that STEP-GAN outperforms several semi-supervised methods while being competitive with supervised methods.
|
|
| 2. |
- Baptista, Marcia Lourenco, et al.
(författare)
-
A self-organizing map and a normalizing multi-layer perceptron approach to baselining in prognostics under dynamic regimes
- 2021
-
Ingår i: Neurocomputing. - : Elsevier. - 0925-2312 .- 1872-8286. ; 456, s. 268-287
-
Tidskriftsartikel (refereegranskat)abstract
- When the influence of changing operational and environmental conditions is not factored out, it can be dificult to observe a clear deterioration path. This can significantly affect the task of prognostics and other analytic operations. To address this issue, it is necessary to baseline the data, typically by first finding the operating regimes and then normalizing the data within each regime. In this paper, we propose the use of machine learning techniques to perform baselining. A self-organizing map identifies the regimes, and a multi-layer perceptron normalizes the data based on the detected regimes. Tests are performed on the C-MAPSS data. The approach is capable of producing similar results to classical methods without the need to specify in advance the number of regimes and the explicit computation of the statistical properties of a hold-out dataset. Importantly, the techniques can be integrated into a deep learning system to perform prognostics in a single pass.
|
|
| 3. |
- Farouq, Shiraz, 1980-, et al.
(författare)
-
Mondrian conformal anomaly detection for fault sequence identification in heterogeneous fleets
- 2021
-
Ingår i: Neurocomputing. - Amsterdam : Elsevier. - 0925-2312 .- 1872-8286. ; 462, s. 591-606
-
Tidskriftsartikel (refereegranskat)abstract
- We considered the case of monitoring a large fleet where heterogeneity in the operational behavior among its constituent units (i.e., systems or machines) is non-negligible, and no labeled data is available. Each unit in the fleet, referred to as a target, is tracked by its sub-fleet. A conformal sub-fleet (CSF) is a set of units that act as a proxy for the normal operational behavior of a target unit by relying on the Mondrian conformal anomaly detection framework. Two approaches, the k-nearest neighbors and conformal clustering, were investigated for constructing such a sub-fleet by formulating a stability criterion. Moreover, it is important to discover the sub-sequence of events that describes an anomalous behavior in a target unit. Hence, we proposed to extract such sub-sequences for further investigation without pre-specifying their length. We refer to it as a conformal anomaly sequence (CAS). Furthermore, different nonconformity measures were evaluated for their efficiency, i.e., their ability to detect anomalous behavior in a target unit, based on the length of the observed CAS and the S-criterion value. The CSF approach was evaluated in the context of monitoring district heating substations. Anomalous behavior sub-sequences were corroborated with the domain expert leading to the conclusion that the proposed approach has the potential to be useful for both diagnostic and knowledge extraction purposes, especially in domains where labeled data is not available or hard to obtain. © 2021
|
|
| 4. |
- González-Redondo, Álvaro, et al.
(författare)
-
Reinforcement learning in a spiking neural model of striatum plasticity
- 2023
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 548
-
Tidskriftsartikel (refereegranskat)abstract
- The basal ganglia (BG), and more specifically the striatum, have long been proposed to play an essential role in action-selection based on a reinforcement learning (RL) paradigm. However, some recent findings, such as striatal spike-timing-dependent plasticity (STDP) or striatal lateral connectivity, require further research and modelling as their respective roles are still not well understood. Theoretical models of spiking neurons with homeostatic mechanisms, lateral connectivity, and reward-modulated STDP have demonstrated a remarkable capability to learn sensorial patterns that statistically correlate with a rewarding signal. In this article, we implement a functional and biologically inspired network model of the striatum, where learning is based on a previously proposed learning rule called spike-timing-dependent eligibility (STDE), which captures important experimental features in the striatum. The proposed computational model can recognize complex input patterns and consistently choose rewarded actions to respond to such sensorial inputs. Moreover, we assess the role different neuronal and network features, such as homeostatic mechanisms and lateral inhibitory connections, play in action-selection with the proposed model. The homeostatic mechanisms make learning more robust (in terms of suitable parameters) and facilitate recovery after rewarding policy swapping, while lateral inhibitory connections are important when multiple input patterns are associated with the same rewarded action. Finally, according to our simulations, the optimal delay between the action and the dopaminergic feedback is obtained around 300 ms, as demonstrated in previous studies of RL and in biological studies.
|
|
| 5. |
- Li, J., et al.
(författare)
-
Neural fuzzy approximation enhanced autonomous tracking control of the wheel-legged robot under uncertain physical interaction
- 2020
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 410, s. 342-353
-
Tidskriftsartikel (refereegranskat)abstract
- The accuracy of trajectory tracking and stable operation with heavy load are the main challenges of parallel mechanism for wheel-legged robots, especially in complex road conditions. To guarantee the tracking performance in an uncertain environment, the disturbances, including the internal-robot friction and external-robot and environment interaction forces, should be considered in the robot's dynamical system. In this article, a neural fuzzy-based model predictive tracking scheme (NFMPC) for reliable tracking control is proposed to the developed four wheel-legged robot, and the fuzzy neural network approximation is applied to estimate the unknown physical interaction and external dynamics of the robot system. Meanwhile, the advanced parallel mechanism of the four wheel-legged robot (BIT-NAZA) is introduced. Finally, co-simulation and experiment results using the BIT-NAZA robot derived from the proposed hybrid control strategy indicate that the methodology can achieve satisfactory tracking performance in terms of accuracy and stability. This research can provide theoretical and engineering guidance for lateral stability of intelligent robots under unknown disturbances and uncertain nonlinearities, and facilitate the control performance of the wheel-legged robot in a practical system.
|
|
| 6. |
- Linnusson, Henrik, et al.
(författare)
-
Efficient conformal predictor ensembles
- 2020
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 397, s. 266-278
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, we study a generalization of a recently developed strategy for generating conformal predictor ensembles: out-of-bag calibration. The ensemble strategy is evaluated, both theoretically and empirically, against a commonly used alternative ensemble strategy, bootstrap conformal prediction, as well as common non-ensemble strategies. A thorough analysis is provided of out-of-bag calibration, with respect to theoretical validity, empirical validity (error rate), efficiency (prediction region size) and p-value stability (the degree of variance observed over multiple predictions for the same object). Empirical results show that out-of-bag calibration displays favorable characteristics with regard to these criteria, and we propose that out-of-bag calibration be adopted as a standard method for constructing conformal predictor ensembles.
|
|
| 7. |
- Pérez, Javier, et al.
(författare)
-
On-line learning applied to spiking neural network for antilock braking systems
- 2023
-
Ingår i: Neurocomputing. - : Elsevier. - 0925-2312 .- 1872-8286. ; 559
-
Tidskriftsartikel (refereegranskat)abstract
- Computationally replicating the behaviour of the cerebral cortex to perform the control tasks of daily life in a human being is a challenge today. First, it is necessary to know the structure and connections between the el- ements of the neural network that perform movement control. Next, a mathematical neural model that adequately resembles biological neurons has to be developed. Finally, a suitable learning model that allows adapting neural network response to changing conditions in the environment is also required. Spiking Neural Networks (SNN) are currently the closest approximation to biological neural networks. SNNs make use of temporal spike trains to deal with inputs and outputs, thus allowing a faster and more complex computation. In this paper, a controller based on an SNN is proposed to perform the control of an anti-lock braking system (ABS) in vehicles. To this end, two neural networks are used to regulate the braking force. The first one is devoted to estimating the optimal slip while the second one is in charge of setting the optimal braking pressure. The latter resembles biological reflex arcs to ensure stability during operation. This neural structure is used to control the fast regulation cycles that occur during ABS operation. Furthermore, an algorithm has been developed to train the network while driving. On-line learning is proposed to update the response of the controller. Hence, to cope with real conditions, a control algorithm based on neural networks that learn by making use of neural plasticity, similar to what occurs in biological systems, has been implemented. Neural connections are modulated using Spike-Timing-Dependent Plasticity (STDP) by means of a supervised learning structure using the slip error as input. Road-type detection has been included in the same neural structure. To validate and to evaluate the performance of the proposed algorithm, simulations as well as experiments in a real vehicle were carried out. The algorithm proved to be able to adapt to changes in adhesion conditions rapidly. This way, the capability of spiking neural networks to perform the full control logic of the ABS has been verified.
|
|
| 8. |
- Ran, Hang, et al.
(författare)
-
3D human pose and shape estimation via de-occlusion multi-task learning
- 2023
-
Ingår i: Neurocomputing. - Amsterdam : Elsevier. - 0925-2312 .- 1872-8286. ; 548
-
Tidskriftsartikel (refereegranskat)abstract
- Three-dimensional human pose and shape estimation is to compute a full human 3D mesh given a single image. The contamination of features caused by occlusion usually degrades its performance significantly. Recent progress in this field typically addressed the occlusion problem implicitly. By contrast, in this paper, we address it explicitly using a simple yet effective de-occlusion multi-task learning network. Our key insight is that feature for mesh parameter regression should be noiseless. Thus, in the feature space, our method disentangles the occludee that represents the noiseless human feature from the occluder. Specifically, a spatial regularization and an attention mechanism are imposed in the backbone of our network to disentangle the features into different channels. Furthermore, two segmentation tasks are proposed to supervise the de-occlusion process. The final mesh model is regressed by the disentangled occlusion-aware features. Experiments on both occlusion and non-occlusion datasets are conducted, and the results prove that our method is superior to the state-of-the-art methods on two occlusion datasets, while achieving competitive performance on a non-occlusion dataset. We also demonstrate that the proposed de-occlusion strategy is the main factor to improve the robustness against occlusion. The code is available at https://github.com/qihangran/De-occlusion_MTL_HMR. © 2023
|
|
| 9. |
- Ristea, Nicolae-Catalin, et al.
(författare)
-
CyTran: A cycle-consistent transformer with multi-level consistency for non-contrast to contrast CT translation
- 2023
-
Ingår i: Neurocomputing. - : ELSEVIER. - 0925-2312 .- 1872-8286. ; 538
-
Tidskriftsartikel (refereegranskat)abstract
- We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to noncontrast CT scans and the other way around. Solving this task has two important applications: (i) to automatically generate contrast CT scans for patients for whom injecting contrast substance is not an option, and (ii) to enhance the alignment between contrast and non-contrast CT by reducing the differences induced by the contrast substance before registration.Our approach is based on cycle-consistent generative adversarial convolutional transformers, for short, CyTran. Our neural model can be trained on unpaired images, due to the integration of a multi-level cycleconsistency loss. Aside from the standard cycle-consistency loss applied at the image level, we propose to apply additional cycle-consistency losses between intermediate feature representations, which enforces the model to be cycle-consistent at multiple representations levels, leading to superior results. To deal with high-resolution images, we design a hybrid architecture based on convolutional and multi-head attention layers. In addition, we introduce a novel data set, Coltea-Lung-CT-100W, containing 100 3D triphasic lung CT scans (with a total of 37,290 images) collected from 100 female patients (there is one examination per patient). Each scan contains three phases (non-contrast, early portal venous, and late arterial), allowing us to perform experiments to compare our novel approach with state-of-the-art methods for image style transfer.Our empirical results show that CyTran outperforms all competing methods. Moreover, we show that CyTran can be employed as a preliminary step to improve a state-of-the-art medical image alignment method. We release our novel model and data set as open source at: https://github.com/ristea/cycletransformer.Our qualitative and subjective human evaluations reveal that CyTran is the only approach that does not introduce visual artifacts during the translation process. We believe this is a key advantage in our application domain, where medical images need to precisely represent the scanned body parts. (c) 2023 Elsevier B.V. All rights reserved.
|
|
| 10. |
- Shao, Wen-ZE, et al.
(författare)
-
Gradient-based discriminative modeling for blind image deblurring
- 2020
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 413, s. 305-327
-
Tidskriftsartikel (refereegranskat)abstract
- Blind image deconvolution is a fundamental task in image processing, computational imaging, and computer vision. It has earned intensive attention in the past decade since the seminal work of Fergus et al. [1] for camera shake removal. In spite of the recent great progress in this field, this paper aims to formulate the blind problem with a simpler modeling perspective. What is more important, the newly proposed approach is expected to achieve comparable or even better performance towards the real blurred images. Specifically, the core critical idea is the proposal of a pure gradient-based discriminative prior for accurate and robust blur kernel estimation. Numerous experimental results on both the benchmark datasets and real-world blurred images in various imaging scenarios, e.g., natural, manmade, low-illumination, text, or people, demonstrate well the effectiveness and robustness of the proposed approach.
|
|
