1 October 2019 in ISA Transactions
19 June 2020 in IEEE Access
Removing the haze in an image is a huge challenge due to the difficulty of accurate hazy image modeling. Although the atmospheric scattering model (ASM) is widely used to describe the formation of hazy images, it is hard to deal with the uneven haze image, once the ASM is restricted with the assumption that the atmosphere distributed homogeneously. This paper analyzes the haze imaging mechanism, then proposes an image-to-image architecture to handle the uneven image dehazing, in which a heterogeneous twin network (HT-Net) with two parallel sub-networks are constructed to establish the high dimensional nonlinear mapping model between the hazy and clean images. Consequently, the inhomogeneous haze is removed by the symmetric U-shape network with encoder-decoder structure, meanwhile, the other enhancement network extracts the high-frequency feature from the hazy image to compensate the edge and texture of the object. The effectiveness is validated by the experiments based on three real haze image datasets which depict the same visual content recorded in haze-free and hazy conditions, under the same illumination parameters. One professional uneven haze image dataset is found in the real environment and covers 190 types of scene and 21975 uneven images accordingly. This dataset includes thin, heavy, and uneven haze images. The other two benchmark datasets are I-HAZE and O-HAZE, respectively including 35 pairs of indoor real haze and haze-free (ground-truth) images and 45 different outdoor scenes. Extensive experimental results demonstrate that the proposed method in this paper can remove the haze and achieve superior performance over the other mentioned methods.
1 April 2020 in IEEE Access
Applying model-based learning for the optimal decision of the multi-agent system is not trivial due to the expensive price or even the impossibility of obtaining the ground truth for training the model of the complex environment. Such as learning the optimal action of hydraulic supports in the top-coal caving, the optimal action could not accessible as the ground truth of the corresponding state in the intricate processes. Regarding the latent ground truth as the hidden variable is an effective method in the hidden Markov model. This paper extends the hidden variable of ground truth to the multi-agent system and proposes the hidden Markov random field (HMRF) model with reinforcement learning for optimizing the action decision of the multi-agent. In the HMRF model, the input states and the output actions of the multi-agent are considered as an observable random field and a latent Markov random field, respectively. Based on the HMRF model, the optimal decision is inferred by the maximum posterior probability with the prior probability obtained by Q-learning. Meanwhile, the parameters of the HMRF model are estimated by the expectation maximum algorithm. In the experiment, the top-coal caving demonstrates the effectiveness of the proposed method that the recall of top-coal is improved prominently with a very small price of increasing the rock-rate. Furthermore, the proposed method is employed to deal with the predator-preys problem in the gym. The experiment result shows that the communication between agents by the HMRF increases the reward of the preys.
25 March 2021 in Information Technology And Control
Mathematical description of a complex signal is very important in engineering but nearly impossible in many occasions. The emergence of the Generative Adversarial Network (GAN) shows the possibility to train a single neural network to be a Specific Signal Generator (SSG), which is only controlled by a random vector with several elements. However, there is no explicit criterion for the GAN training process to stop, and in real applications the training always stops after a certain big iteration. In this paper, a serious issue was discussed during the process to use GAN as a SSG. And, an explicit criterion for the GAN as a SSG to stop the training process were proposed. Several experiments were carried out to illustrate the issues mentioned above and the effectiveness of the stopping criterion proposed in this paper.
5 December 2025 in IEEE Journal of Radio Frequency Identification
In many Radio Frequency Identification-based systems, Ultra-Wideband technology has emerged as a compelling alternative for improving positioning accuracy. Thanks to its high precision, low power consumption, and strong anti-interference capability, it shows broad application potential in complex environments. However, under non-line-of-sight conditions, the accuracy is considerably degraded due to signal obstruction and multipath interference. To address this challenge, an Ultra-Wideband signal classification method is proposed that leverages multi-level feature fusion and a cross-channel attention network. Initially, a feature selection mechanism utilizing recursive feature elimination with cross-validation is proposed to identify and retain the most salient Ultra-Wideband signal features, thereby mitigating the impact of irrelevant features and reducing computational complexity. Subsequently, to further enhance the model’s feature representation capability, a multi-level feature fusion module is introduced, which progressively integrates the outputs of each convolutional layer, consolidating features from multiple stages of the network. Concurrently, to further strengthen the proposed network’s ability to capture key features, a cross-channel attention mechanism is incorporated to adaptively assign weights based on feature importance. The results demonstrate that the proposed method achieved classification accuracies of 93.15%, 96.2%, and 98.49% on the three Ultra-Wideband datasets.