Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the short-range dependencies within brain networks while neglecting the long-range dependencies, limiting an integrated understanding of brain-wide communication. To address this limitation, we propose Adaptive Long-range aware TransformER (ALTER), a brain graph transformer to capture long-range dependencies between brain ROIs utilizing biased random walk. Specifically, we present a novel long-range aware strategy to explicitly capture long-range dependencies between brain ROIs. By guiding the walker towards the next hop with higher correlation value, our strategy simulates the real-world brain-wide communication. Furthermore, by employing the transformer framework, ALERT adaptively integrates both short- and long-range dependencies between brain ROIs, enabling an integrated understanding of multi-level communication across the entire brain. Extensive experiments on ABIDE and ADNI datasets demonstrate that ALTER consistently outperforms generalized state-of-the-art graph learning methods (including SAN, Graphormer, GraphTrans, and LRGNN) and other graph learning based brain network analysis methods (including FBNETGEN, BrainNetGNN, BrainGNN, and BrainNETTF) in neurological disease diagnosis.

Deep reinforcement learning (DRL) has demonstrated promising performance to learn effective heuristics to solve complex combinatorial optimisation problems via policy networks. However, traditional reinforcement learning (RL) suffers from insufficient exploration, which often results in pre-convergence to poor policies and many challenges the performance of DRL. To prevent this, we propose an Entropy Regularised Reinforcement Learning (ERRL) method that supports exploration by providing more stochastic policies, improving optimisation. The ERRL method incorporates an entropy term, defined over the policy network's outputs, into the loss function of the policy network. Hence, policy exploration can be explicitly advocated subjected to a balance to maximise the reward. As a result, the risk of pre-convergence to inferior policies can be reduced. We implement the ERRL method based on two existing DRL algorithms. We have compared the performances of our implementations with the two DRL algorithms along with several state-of-the-art heuristic-based non-RL approaches for three categories of routing problems, i.e., travelling salesman problem (TSP), capacitated vehicle routing problem (CVRP) and multiple routing with fixed fleet problems (MRPFF). Experimental results show that the proposed method can find better and faster solutions in most test cases than the state-of-the-art algorithms.

Speckle noise is the main cause of image degradation in optical coherence tomography, which makes denoising an essential process to obtain quality images. This study proposes a wavelet‐based denoising technique in which detail coefficients are assigned weights using similarity measures of Pearson's correlation coefficient and structural similarity index (SSIM). Stationary wavelet transform is used for SSIM which is an image quality measure is used as optimisation criterion to denoise images in this study. Procedure of weight computation is discussed in detail. Average of these detailed components is used to denoise the images. Comparison of proposed technique with the existing techniques has been carried out at length. Extensive qualitative and quantitative analysis reveal that the proposed technique is efficient and performs better in terms of noise reduction while maintaining the structural contents of the image.

In this paper, a super-resolution technique is proposed that uses a combination of bicubic interpolation and wavelet transform. Bicubic interpolation produces a high resolution image but is prone to blurring artifact. So the blurring artifact is reduced in the wavelet domain. The input low-resolution is up-sampled using bicubic interpolation. The edges of the resultant high-resolution image are enhanced using stationary wavelet transform (SWT). SWT is applied to the image to produce sub-bands of the image and then these sub-bands are modified by multiplying with a boost value. Then these sub-bands are combined using inverse stationary wavelet transform (ISWT) to produce the final high-resolution image. The quantitative and qualitative analysis illustrate that the proposed technique is provides superior results as compared to other existing techniques.