Reducing the complexity of soft-decision (SD) decoding algorithm or improving the performance of hard-decision (HD) decoding algorithm becomes an emerging trend on forward error corrections to ensure reliable optical transmission with high performance and low cost. In this paper, a hybrid decoding algorithm is proposed for staircase codes (SCCs), which performs HD decoding with the help of channel soft information via multi-level bit-marking (MLBM). The HD and SD in the proposed MLBM decoding algorithm isweakly hybridthat the soft information is only used for one-shot bit marking and does not involve in the decoding directly, thus providing good performance-complexity tradeoff. The marked bits indicate four reliability levels that are used to prevent miscorrections by checking conflicts with highly reliable bits and to enhance the error-correcting capability of the HD decoder by flipping unreliable bits. Particularly, three priority levels are set for bit flipping by combining with the decoding statuses of the associated component codes. The decoding results will, in turn, help to update the marked bits among the four reliability levels. Numerical results show up to 1.22 dB gains with steeper waterfall region and lower error floor when compared to conventional HD decoding for SCCs, at the cost of approximately a two-fold increase in the memory storage.

Deep learning has made significant advancements in polarization imaging through scattering media. However, there remains a deficiency in effective analysis and control of the abundant information embedded in polarization images during training. Therefore, we propose a de-scattering framework with stepwise adjustment of polarization features (FSAPF) for high-performance imaging through scattering media. This framework implements a physically guided hierarchical learning, in which supervision processes are progressively refined from global structure to local polarization details. To directly embed polarization priors into feature representations, a polarization learning module (PLM) is introduced, which regulates feature interactions by enforcing physical consistency constraints, thereby enabling the FSAPF to learn robust representations. In addition, by directly embedding polarization priors into the dynamic loss mechanism, polarization features can be enhanced during training, which further enhances the FSAPF's generalized robustness in changing scenarios. We conduct a series of validation experiments to verify the validity and superiority of the FSAPF. The experimental results show that the FSAPF can perform significantly in target recovery tasks under different scattering environments. And comparative and ablation experiments can both achieve better results.

The escalating data traffic in smart cities, driven by numerous connected devices and data-intensive applications, necessitates advanced communication. Traditional wireless networks are hindered by bandwidth limitations, high latency, and interference. Free Space Optical (FSO) communication leveraging orbital angular momentum (OAM) offers a promising alternative by enabling high-capacity, interference-free data transmission through the atmosphere. This study introduces MultipropNet, a deep learning model based on Convolutional Neural Networks (CNN), designed to address the challenge of varying propagation distances in OAM-based FSO communication. The model supports multi-distance communication and facilitates duplex data transfer between emitters and receivers, overcoming issues caused by differing OAM beam waists. Furthermore, the concept of an Intermediate Node (Relay) is introduced to mitigate the effects of atmospheric turbulence (AT) in long-distance communication links. This approach significantly improves flexibility and resilience compared to traditional fixed-distance, unidirectional systems. Tested under severe AT conditions (Cn2= 1 × 10-13m-2/3andCn2= 7 × 10-13m-2/3), the model has achieved classification accuracies of 99.66% for four multiplexed OAM beams (resulting in 16 beams) and 96.24% under higher turbulence, alongside low bit error rates (BER) in image transmissions with a value of 0.0067 forCn2= 1 × 10-13m-2/3and 0.1430 forCn2= 7 × 10-13m-2/3. This advancement delves into the ultimate potential of OAM-based FSO systems, establishing a robust foundation for high-speed, reliable wireless communication infrastructures in smart cities.

-methyladenine (6mA) is an important epigenetic modification that plays a vital role in various cellular processes. Accurate identification of the 6mA sites is fundamental to elucidate the biological functions and mechanisms of modification. However, experimental methods for detecting 6mA sites are high-priced and time-consuming. In this study, we propose a novel computational method, called Ense-i6mA, to predict 6mA sites. Firstly, five encoding schemes, i.e., one-hot encoding, gcContent, Z-Curve, K-mer nucleotide frequency, and K-mer nucleotide frequency with gap, are employed to extract DNA sequence features. Secondly, eXtreme gradient boosting coupled with recursive feature elimination is applied to remove noisy features for avoiding over-fitting, reducing computing time and complexity. Then, the best subset of features is fed into base-classifiers composed of Extra Trees, eXtreme Gradient Boosting, Light Gradient Boosting Machine, and Support Vector Machine. Finally, to minimize generalization errors, the prediction probabilities of the base-classifiers are aggregated by averaging for inferring the final 6mA sites results. We conduct experiments on two species, i.e., Arabidopsis thaliana and Drosophila melanogaster, to compare the performance of Ense-i6mA against the recent 6mA sites prediction methods. The experimental results demonstrate that the proposed Ense-i6mA achieves area under the receiver operating characteristic curve values of 0.967 and 0.968, accuracies of 91.4% and 92.0%, and Mathew's correlation coefficient values of 0.829 and 0.842 on two benchmark datasets, respectively, and outperforms several existing state-of-the-art methods.

Automatic roads detection is an essential task for traffic safety and intelligent transportation systems. Recently the long-wave infrared (LWIR) polarization imaging-based road detection technique has obtained significant progresses. However, the joint analysis among multiple polarization characteristics, sparse inter-channel information (along the$z$-axis), and dense intra-channel information (inside the$x$-$y$plane), have not been considered effectively, hindering the effective detection of many road areas. Additionally, most of the existing methods often encounter a challenging trade-off between achieving high precision and maintaining a lightweight design. To tackle these issues, this paper presents a novel Lightweight Multi-Pathway Collaborative 2D/3D Convolutional Networks (LMPC2D3DCNet) with a small number of parameters for full-time road detection. Our LMPC2D3DCNet is the first attempt to incorporate 2D and 3D convolutional networks to balance extraction for sparse inter-channel polarization information and dense intra-channel polarization information, in which a new Cross 2D-3D Non-Local Attention (C2D3DNLA) network is proposed to derive respective latent features by exploiting both local and global polarization correlations. Meanwhile, it also follows the design of a multipath network structure that elegantly fuses plenty of low-frequency, high-frequency, and multiscale polarization information, thus obtaining more accurate modeling for road regions. Extensive experiments on one public infrared polarization dataset of road scenes demonstrate that our proposed LMPC2D3DCNet (The code will release soon on https://github.com/XueqiangF) achieves PRE of 96.96%,RECof 96.71%,OAof 99.45%, F1 of 96.72, BER of 1.80% andIoUof 93.85%, and outperforms significantly state-of-the-art methods.

The existing scattering medium has a serious impact on the optical remote sensing. It is a challenge and urgent problem to extract the original target’s information influenced by scattering systems. Here, we adopt the target’s polarization information as the original data and load it into the modified U-net-based deep-learning network (MU-DLN) to retrieve the original target’s information influenced by the scattering medium. The dense blocks in the MU-DLN can extract the features of the target information contained in the polarization images. Meanwhile, the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) have been used to evaluate the quality of target reconstruction. The experimental results show that our strategy can reconstruct the target’s information very well, and the model trained for a fixed optical thickness (OT) environment can also be used for remote sensing in the larger or smaller OT environment within a certain range. In addition, due to the polarization imaging characteristics, compared with traditional methods, our strategy can improve the quality of target reconstruction effectively. Our work provides a new direction for DL technique in remote sensing of targets’ information from the complex scattering systems.

This letter makes a first attempt to design a cooperative relay scheme to secure wireless communications by adopting a fast-forward full-duplex (F3D) node. Different from the conventional full-duplex relay, the F3D node could process and forward the received signal immediately. With such forwarding, the forwarded signal of F3D could enhance the signal to interference plus noise ratio of the receiver, whereas weaken that of the eavesdropper and thus build up a secure channel. Beyond the proposed scheme, we move forward to optimize the signal processing design of the F3D node with the target of maximizing the secrecy capacity. The formulated optimization problem is nonconvex and challenging to deal with. We then design an iterative algorithm based on generalized fractional programming to solve it. One key step in the iterative algorithm involves another nonconvex optimization and we decompose it into a two-level optimization. Simulation results validate the effectiveness of our designed secure cooperative relay scheme and show that adopting F3D node for physical-layer security has good performance in terms of achievable secrecy capacity compared with the scheme without F3D node.