ISSN / EISSN : 2169-3536 / 2169-3536
Published by: IEEE (10.1109)
Total articles ≅ 48,573
Latest articles in this journal
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096387
In this paper, we propose a coherent framework for multi-machine analysis, using a group clustering model, which can be utilized for predictive maintenance (PdM). The framework benefits from the repetitive structure posed by multiple machines and enables for assessment of health condition, degradation modeling and comparison of machines. It is based on a hierarchical probabilistic model, denoted Gaussian topic model (GTM), where cluster patterns are shared over machines and therefore it allows one to directly obtain proportions of patterns over the machines. This is then used as a basis for cross comparison between machines where identified similarities and differences can lead to important insights about their degradation behavior. The framework is based on aggregation of data over multiple streams by a predefined set of features extracted over a time window. Moreover, the framework contains a clustering schema which takes uncertainty of cluster assignments into account and where one can specify a desirable degree of reliability of the assignments. By using a multi-machine simulation example, we highlight how the framework can be utilized in order to obtain cluster patterns and inherent variations of such patterns over machines. Furthermore, a comparative study with the commonly used Gaussian mixture model (GMM) demonstrates that GTM is able to identify inherent patterns in the data while the GMM fails. Such result is a consequence of the group level being modeled by the GTM while being absent in the GMM. Hence, the GTM are trained with a view on the data that is not available to the GMM with the consequence that the GMM can miss important, possibly even key, cluster patterns. Therefore, we argue that more advanced cluster models, like the GTM, can be key for interpreting and understanding degradation behavior across machines and ultimately for obtaining more efficient and reliable PdM systems.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096527
Retrieving incidents from video stream plays an important role in many computer vision applications. However, most video surveillance system can neither recognize incidents nor support content-based retrieval before the video stream is saved into files. As an emerging type of sensing modality, Wi-Fi signal have the potential to become a signal synchronized with the video stream to perform the incidents detection and recognition. In this work, we simultaneously collect the video stream and the Wi-Fi signal in two surveillance scenarios, and develop a LSTM-based classification model that is able to recognize the incidents in surveillance scenarios. Specifically, we first deploy a video surveillance system in two scenarios to capture the video stream and the synchronized Wi-Fi signal that is very sensitive to environmental changes. Second, an incident detection method based on the entropy change of Wi-Fi signal is proposed to find out the start and end time of the incident in the CSI sequence, thus greatly reducing the computational complexity compared with shot detection in the video stream. Third, the deep network LSTM is adopted to develop an incident recognition model that would be used to classify each size-variable CSI segments into known categories corresponding to the types of incidents. Fourth, using Wi-Fi signal to locate and recognize incidents in the video stream, we build a quick content-based video retrieval system. Last, the experimental evaluation was performed on a group of real Wi-Fi signal samples. The statistical results shows that the proposed incident detection method is feasible and effective to find out the incidents in video files with an average error of 1.5 s. And the evaluation experiment results demonstrates that the proposed multi-classification model acquires an average value of 0.972, 0.973, 0.985, 0.972 and 0.962 for recall, precision, accuracy, F-1 score and Kappa coefficient, respectively.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096208
Internet of things is providing us numerous ways to improve our quality of experience by using smart cyber-physical infrastructure systems. Also, due to arrival of LED lighting systems, there is the possibility to improve user’s visual comfort at less cost. In our proposed model, by using a fuzzy inference system, used in cyber-physical infrastructure system, we save energy from the heating, ventilation and air conditioning system. This saved energy is used to improve the visual comfort of the user. Simulation results show that considering the visual comfort standard of 500 lux instead of 250 lux results in energy savings and ensures visual comfort. Together with the preservation of thermal comfort increases the overall users’ comfort. Since research confirms that users’ improved comfort results in up to 14% of increased productivity. Our model is unique in the sense that using fuzzy logic, indirectly improved the users’ productivity. By using our fuzzy logic controller on electric equipment, we can achieve improved users’ performance without paying any extra cost.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096548
Recent studies have shown that a super-resolution generative adversarial network (SRGAN) can significantly improve the quality of single-image super-resolution. However, existing SRGAN methods also have certain drawbacks, such as an insufficient feature utilization, a large number of parameters. To further enhance the visual quality, we thoroughly studied three key components of SRGAN, i.e., the network architecture, adversarial loss, and perceptual loss, and propose a DenseNet with Residual-in-Residual Bottleneck Block (RRBB), called a residual bottleneck dense network (RBDN), for single-image super-resolution. First, to improve the utilization of features between the various layers of the network, we adopted a dense cascading connection between layers. At the same time, to reduce the computational cost, we added a bottleneck structure to each layer, greatly reducing the number of network parameters and accelerating the convergence speed of the training process. Second, the proposed RRBB, as the basic network building unit, removes the batch normalization (BN) layer and employs the ELU function to reduce the opposite effects in the absence of BN. In addition, we applied an improved overall loss function during the model training process to stably train the model and further improve the realism of the reconstructed high-resolution image. To prove the superiority of our proposed model, we conducted a comprehensive and objective evaluation of the Peak Signal-to-Noise Ratio, structural similarity, learned perceptual image patch similarity, and other evaluation indicators obtained from the three test sets, i.e., Set5, Set14, and BSD100, from the recent state-of-the-art model. Finally, we conducted qualitative and quantitative analyses of the results obtained in terms of the evaluation indicators, the authenticity of the restored HR images, and textural details, which show the superiority of the RBDN model.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096595
In recent years, there has been a growing concern for robust supervisory control policies that can handle both deadlock and blockage propagation in automated manufacturing systems in the event of resource failures. This work proposes a novel robust supervisory control policy for automated manufacturing systems with multiple unreliable resources without using central buffers. The policy permits legal states as many as possible and ensures that parts not requiring unreliable resources can be automatically processed without human intervention if one or multiple unreliable resources fail. It is based on the modified neighborhood policy, namely single route neighborhood, which handles the allocation of failure-prone resources in a system. To guarantee deadlock-free operations in the remaining parts of the system, monitors are designed for emptiable strictly minimal siphons. Through examples, the applicability of the proposed policy is demonstrated.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096419
A simple synthesis method for ultra-thin double-sided cross-dipoles-based Frequency Selective Surfaces (FSS) is presented in this paper. The presented technique is used to design a flexible band-stop FSS for Electromagnetic Interference (EMI) shielding applications operating at 10 GHz. An Equivalent Circuit (EC) combined with a closed-form expression is used to synthesize and validate the response of the proposed element. Further, a parametric study of the proposed FSS aiming to optimize the bandwidth has been presented. The proposed FSS holds similar responses for TE and TM mode of polarization at normal incidence. Further, the conformal behavior of the proposed FSS in comparison with planar FSS is presented and evaluated. The proposed FSS is validated with the full-wave EM solver for simulation, and a prototype is fabricated. The measured results of a proposed FSS are presented and compared to the simulations with good agreement.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096184
This paper presents a novel nonlinear estimator called the fuzzy finite memory (FFM) state estimator for electro-hydraulic active suspension systems, based on fuzzy techniques and finite impulse response. The Takagi-Sugeno fuzzy model is introduced to effectively describe highly nonlinear suspension systems with electro-hydraulic actuator dynamics. Compared with the conventional state estimator, which has an infinite memory structure and requires whole data from the initial to current time, the proposed fuzzy state estimator with a finite memory structure guarantees robustness against external disturbances and modeling uncertainty. The simulation results verify that the developed fuzzy finite memory state estimator is more robust under external disturbances and modeling uncertainties than the existing infinite impulse response nonlinear estimator.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096547
In high frequency applications of silicon carbide (SiC) MOSFET, it is easy to be affected by parasitic parameters where crosstalk phenomenon in bridge arm will occur. This paper proposes a novel multi-level gate driver which can suppress the crosstalk phenomenon of the SiC MOSFETs in bridge arm. An auxiliary MOSFET branch between the gate and source of SiC MOSFET is adopted to generate negative and zero gate voltage when SiC MOSFET is turned off. The negative gate voltage may reduce the positive gate crosstalk voltage, and zero gate voltage may reduce negative gate crosstalk voltage. Both the simulations and experiments are carried out to verify the feasibility and high performance of the proposed multi-level gate driver. Compared to the conventional gate driver, the proposed multi-level gate driver reduces the positive crosstalk voltage to -2.2V, and the negative crosstalk voltage to -4.4V, respectively.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096569
Computational ghost imaging is a novel technique, which has a wide range of applications in many fields. As a key part of computational ghost imaging, the measurement matrix plays an important role in imaging quality and system practicability. To improve the imaging quality of computational ghost imaging and overcome the poor stability and non-negativity of the measurement matrix, we propose a new construction method for the deterministic measurement matrix based on the difference set modulo subgroup. This method uses an efficient simulated annealing algorithm to search for the difference set modulo subgroup. Then a 0-1 binary measurement matrix can be constructed according to the obtained difference set. We can show that the measurement matrix constructed by this method has low coherence and can satisfy the restricted isometry property. The simulation and experimental results showed that the reconstruction quality of the proposed measurement matrix was equivalent to the Sparse random matrix and better than the Toeplitz and Circulant matrices, which indicates the feasibility of the newly proposed measurement matrix.
IEEE Access, pp 1-1; doi:10.1109/access.2021.3096194
Multi-label classification aims to deal with the problem that an object may be associated with one or more labels, which is a more difficult task due to the complex nature of multi-label data. The crucial problem of multi-label classification is the more robust and higher-level feature representation learning, which can reduce non-helpful feature attributes from the input space prior to training. In recent years, deep learning methods based on autoencoders have achieved excellent performance in multi-label classification for the advantages of powerful representations learning ability and fast convergence speed. However, most existing autoencoder-based methods only rely on the single autoencoder model, which pose challenges for multi-label feature representations learning and fail to measure similarities between data spaces. To address this problem, in this paper, we propose a novel representation learning method with dual autoencoder for multi-label classification. Compared to the existing autoencoder-based methods, our proposed method can capture different characteristics and more abstract features from data by the serially connection of two different types of autoencoders. More specifically, firstly, the algorithm of Reconstruction Independent Component Analysis (RICA) in sparse autoencoder is trained on patches on all training and test dataset for robust global feature representations learning. Secondly, with the output of RICA, stacked autoencoder with manifold regularization (SAMR) is introduced to ameliorate the quality of multi-label features learning. Comprehensive experiments on several real-world data sets demonstrate the effectiveness of our proposed approach compared with several competing state-of-the-art methods.