Super-resolution reconstruction of underwater polarized images with a fused attention mechanism.

The polarization imaging technique leverages the disparity between target and background polarization information to mitigate the impact of backward scattered light, thereby enhancing image quality. However, the imaging model of this method exhibits limitations in extracting inter-image features, resulting in less-than-optimal outcomes in turbid underwater environments. In recent years, machine learning methodologies, particularly neural networks, have gained traction. These networks, renowned for their superior fitting capabilities, can effectively extract information from multiple images. The incorporation of an attention mechanism significantly augments the capacity of neural networks to extract inter-image correlation attributes, thereby mitigating the constraints of polarization imaging methods to a certain degree. To enhance the efficacy of polarization imaging in complex underwater environments, this paper introduces a super-resolution network with an integrated attention mechanism, termed as SRGAN-DP. This network is a fusion of an enhanced SRGAN network and the high-performance deep pyramidal split attention (DPSA) module, also proposed in this paper. SRGAN-DP is employed to perform high-resolution reconstruction of the underwater polarimetric image dataset, constructed specifically for this study. A comparative analysis with existing algorithms demonstrates that our proposed algorithm not only produces superior images but also exhibits robust performance in real-world environments.

Optical Diffractive Convolutional Neural Networks Implemented in an All-Optical Way.

Optical neural networks can effectively address hardware constraints and parallel computing efficiency issues inherent in electronic neural networks. However, the inability to implement convolutional neural networks at the all-optical level remains a hurdle. In this work, we propose an optical diffractive convolutional neural network (ODCNN) that is capable of performing image processing tasks in computer vision at the speed of light. We explore the application of the 4f system and the diffractive deep neural network (D2NN) in neural networks. ODCNN is then simulated by combining the 4f system as an optical convolutional layer and the diffractive networks. We also examine the potential impact of nonlinear optical materials on this network. Numerical simulation results show that the addition of convolutional layers and nonlinear functions improves the classification accuracy of the network. We believe that the proposed ODCNN model can be the basic architecture for building optical convolutional networks.

Polarized deep diffractive neural network for sorting, generation, multiplexing, and de-multiplexing of orbital angular momentum modes.

The multiplexing and de-multiplexing of orbital angular momentum (OAM) beams are critical issues in optical communication. Optical diffractive neural networks have been introduced to perform sorting, generation, multiplexing, and de-multiplexing of OAM beams. However, conventional diffractive neural networks cannot handle OAM modes with a varying spatial distribution of polarization directions. Herein, we propose a polarized optical deep diffractive neural network that is designed based on the concept of dielectric rectangular micro-structure meta-material. Our proposed polarized optical diffractive neural network is optimized to sort, generate, multiplex, and de-multiplex polarized OAM beams. The simulation results show that our network framework can successfully sort 14 kinds of orthogonally polarized vortex beams and de-multiplex the hybrid OAM beams into Gauss beams at two, three, and four spatial positions, respectively. Six polarized OAM beams with identical total intensity and eight cylinder vector beams with different topology charges have also been sorted effectively. Additionally, results reveal that the network can generate hybrid OAM beams with high quality and multiplex two polarized linear beams into eight kinds of cylinder vector beams.

American Barrier Option Pricing Formulas for Currency Model in Uncertain Environment.

Option pricing problem is one of the central issue in the theory of modern finance. Uncertain currency model has been put forward under the foundation of uncertainty theory as a tool to portray the foreign exchange rate in uncertain finance market. This paper uses uncertain differential equation involved by Liu process to dispose of the foreign exchange rate. Then an American barrier option of currency model in uncertain environment is investigated. Most important of all, the authors deduce the formulas to price four types of American barrier options for this currency model in uncertain environment by rigorous derivation.

Circulating miR-342-5p serves as a diagnostic biomarker in patients with carotid artery stenosis and predicts the occurrence of the cerebral ischemic event.

BACKGROUND: Carotid artery stenosis (CAS) is an important risk factor for cerebral ischemia events (CIE). Previous studies have shown that microRNAs (miRNAs) are involved in the occurrence and development of CAS. AIMS: The purpose of this study was to reveal the clinical diagnostic value of miR-342-5p for asymptomatic CAS (ACAS) and to evaluate its predictive value for the occurrence of CIE in patients. METHODS: A total of 92 ACAS patients and 86 healthy controls were enrolled as subjects. The expression level of serum miR-342-5p was detected by qRT-PCR. The receiver operating characteristic (ROC) curve was used to detect the diagnostic value of miR-342-5p in ACAS. Kaplan-Meier survival and Cox regression analysis assessed the predictive value of miR-342-5p for the occurrence of CIE in ACAS patients. RESULTS: The level of serum miR-342-5p in ACAS patients was significantly higher than that in healthy controls (P < 0.05). ROC curve showed the high diagnostic value of serum miR-342-5p, which could distinguish ACAS patients from healthy controls. Multivariate Cox regression analysis confirmed that miR-342-5p was an independent predictor (HR = 5.512, 95%CI = 1.370-22.176, P = 0.016). What is more, Kaplan-Meier analysis confirmed that patients with high miR-342-5p expression develop more CIE (log-rank, P = 0.020). CONCLUSIONS: miR-342-5p was significantly overexpressed in ACAS. And the upregulation of serum miR-342-5p is a valuable diagnostic biomarker and can predict the occurrence of CIE.

Inferring lncRNA Functional Similarity Based on Integrating Heterogeneous Network Data.

Although lncRNAs lack the potential to be translated into proteins directly, their complicated and diversiform functions make them as a window into decoding the mechanisms of human physiological activities. Accumulating experiment studies have identified associations between lncRNA dysfunction and many important complex diseases. However, known experimentally confirmed lncRNA functions are still very limited. It is urgent to build effective computational models for rapid predicting of unknown lncRNA functions on a large scale. To this end, valid similarity measure between known and unknown lncRNAs plays a vital role. In this paper, an original model was developed to calculate functional similarities between lncRNAs by integrating heterogeneous network data. In this model, a novel integrated network was constructed based on the data of four single lncRNA functional similarity networks (miRNA-based similarity network, disease-based similarity network, GTEx expression-based network and NONCODE expression-based network). Using the lncRNA pairs that share the target mRNAs as the benchmark, the results show that this integrated network is more effective than any single networks with an AUC of 0.736 in the cross validation, while the AUC of four single networks were 0.703, 0.733, 0.611, and 0.602. To implement our model, a web server named IHNLncSim was constructed for inferring lncRNA functional similarity based on integrating heterogeneous network data. Moreover, the modules of network visualization and disease-based lncRNA function enrichment analysis were added into IHNLncSim. It is anticipated that IHNLncSim could be an effective bioinformatics tool for the researches of lncRNA regulation function studies. IHNLncSim is freely available at http://www.lirmed.com/ihnlncsim.