In order to detect targets upon sea surface or near it, marine radars should be capable of distinguishing signals of target reflections from the sea clutter. Our proposed method in this paper relates to detection of dissimilar marine targets in an inhomogeneous environment with clutter and non-stationary noises, and is based on adaptive thresholding determination methods. The variance and the mean values of the noise level have been estimated in this paper, based on non-stationary, statistical methods and thresholding has been carried out using the suggested two-pole recursive filter. Making the rate of false alarm constant, the concerned threshold resolves the hypothesis of existence or absence of the target signal. Performance of the mentioned algorithm has been compared with the well-known conventional method as CA-CFAR in terms of decreasing the losses and increasing calculation speed. The algorithm provided for detection of signal has been implemented as a part of signal-processing algorithms of some practical marine radar. The results obtained from the algorithm performance in a real environment indicate appropriate workability of this method in heterogeneous environment and non-stationary interference.

Purpose: To compare the results of the new strategy Swedish Interactive Thresholding Algorithm (SITA) Faster to the results of SITA Standard in patients with glaucoma. Methods: This was a cross-sectional study of 49 patients with glaucoma and previous experience with standard automated perimetry. Two consecutive tests were performed in random order, one with SITA Standard and another one with SITA Faster, in the studied eye of each patient. Comparisons were made for test time, mean deviation (MD), visual field index (VFI), and number of depressed points in pattern deviation map and total deviation map for every level of significance. Results: The average test time was 56% shorter with SITA Faster (P < 0. 001). The intraclass correlation coefficient (ICC) for MD and VFI showed excellent agreement between both strategies, ICC = 0. 98 (95% confidence interval [CI]: 0. 96, 0. 99) and ICC = 0. 97 (95% CI: 0. 95, 0. 99), respectively. For the number of depressed points in total deviation map and pattern deviation map, ICC demonstrated good agreement with values between 0. 8 and 0. 95. Conclusions: Our study shows that SITA Faster is a shorter test with strong agreement with SITA Standard parameters. These results suggest that SITA Faster could replace SITA Standard for glaucoma diagnosis.

Out-of-domain intent detection in natural language understanding systems faces significant challenges from suboptimal threshold selection and signal degradation through inappropriate normalization techniques. This paper presents an adaptive ensemble thresholding framework that substantially extends our previous conference work by addressing fundamental limitations in existing variational autoencoder-based detection methods. Our approach combines reconstruction loss from variational autoencoders with classifier confidence scores to create a unified detection signal that captures both semantic deviation and prediction uncertainty. The framework incorporates a novel smart scaling strategy that preserves natural separation ratios between in-domain and out-of-domain samples, preventing the signal destruction caused by standard normalization approaches. Through systematic parameter optimization using grid search techniques, the method adaptively determines optimal ensemble weights and threshold selection strategies tailored to specific dataset characteristics. We evaluate our framework across multiple datasets with varying semantic complexity and domain structures, demonstrating consistent performance improvements over baseline variational autoencoder approaches and recent state-of-the-art methods. Compared to our previous VAE-based approach, the framework demonstrates an average performance gain of 3.15 percentage points across all evaluation metrics. Our analysis reveals that ensemble scaling strategy significantly impacts detection performance, with proper signal preservation being more critical than sophisticated threshold selection methods. This work provides a principled approach to adaptive ensemble learning for out-of-domain detection, offering a robust solution that generalizes effectively across diverse datasets and linguistic contexts including low-resource languages like Persian.

This paper addresses the problem of speech enhancement in wavelet domain. After decomposition of noisy signal into wavelet sub-bands, an adaptive thresholding process is applied on wavelet coefficients. In the proposed technique, small threshold value and hard thrsholding function are used in sub-bands with high speech energy; vice versa, in sub-bands with low speech energy, large threshold value and soft thresholding function are employed. For other sub-bands (between above two extreme cases for speech energy), we use an adaptive thresholding function that is actually between soft- and hard-thresholding functions. The threshold value and thresholding function are determined by a parameter related to the ratio of speech and noise powers in each sub-band. Our extensive experiments show the superiority of proposed method in removing the background noise and reduction of speech distortion. It was also shown that both wavelet tree structure and wavelet type affect on the performance of speech de-noising system.

This work presents a new multilevel thresholding algorithm for image segmentation, addressing the limitations of metaheuristic algorithms. Multilevel thresholding provides a fast and effective approach. A major challenge for metaheuristic algorithms like Whale Optimization Algorithm (WOA) is stagnation, leading to suboptimal solutions and premature convergence. This research introduces the Darwinian Whale Optimization Algorithm (DWOA), which incorporates the principles of natural selection to address this issue. DWOA enhances diversity and improves the quality of individuals within the population while maintaining the convergence speed of WOA.The proposed DWOA employs an encouragement-punishment strategy to guide search agents effectively through the search space. This strategy is implemented by dividing the population into groups, where each group collaborates to locate optimal threshold values. The effectiveness of DWOA is evaluated on 12 test images using the energy curve method, a well-established approach for performance assessment. Additionally, Kapur entropy is employed to further assess DWOA's capability. To conduct a thorough analysis, seven additional search algorithms have been developed and assessed alongside the DWOA. The segmented results indicate that the proposed mthod has the best performance on 32 out of 36 cases in terms of Kapur fitness. Results prove that DWOA consistently outperforms the standard WOA and other heuristic search methods, establishing itself as a powerful tool for image segmentation tasks.

is not possible. To use these simulations in medical science, they need to be able to predict the behavior of actual processes with actual patient-specific geometries. Many uncertainties enter in the process of developing these simulations, starting with creating the geometry. The actual patient-specific geometry is often complex and hard to process. Usually, simplifications to the geometry are introduced in exchange for faster results. However, when simplified, these simulations can no longer be considered patient-specific as they do not represent the actual patient they come from. The ultimate goal is to keep the geometries truly patient-specific without any simplification. However, even without simplifications, the patient-specific geometries are based on medical imaging modalities and consequent use of numerical algorithms to create and process the 3D surface. Multiple users are asked to process medical images of a complex geometry. Their resulting geometries are used to assess how the user’ s choices determine the resulting dimensions of the 3D model. It is shown that the resulting geometry heavily depends on user’ s choices.