A metaheuristics-equipped post-processing model for coronary angiograms.

In recent years, deep learning methods have made breakthroughs in the field of rotating equipment fault diagnosis, thanks to their powerful data analysis capabilities. However, the vibration signals usually incorporate fault features and background noise, and these features may be scattered over multiple frequency levels, which increases the complexity of extracting important information from them. To address this problem, this paper proposes a Masked and Cascaded Multi-Branch Attention Network (MCMBAN), which combines the Noise Mask Filter Block (NMFB) with the Multi-Branch Cascade Attention Block (MBCAB), and significantly improves the noise immunity of the fault diagnostic model and the efficiency of fault feature extraction. NMFB novelly combines a wide convolutional layer and a top k neighbor self-attention masking mechanism, so as to efficiently filter unnecessary high-frequency noise in the vibration signal. On the other hand, MBCAB strengthens the interaction between different layers by cascading the convolutional layers of different scales, thus improving the recognition of periodic fault signals and greatly enhancing the diagnosis accuracy of the model when processing complex signals. Finally, the time–frequency analysis technique is employed to explore the internal mechanisms of the model in depth, aiming to validate the effectiveness of NMFB and MBCAB in fault feature recognition and to improve the feature interpretability of the proposed modes in fault diagnosis applications. We validate the superior performance of the network model in dealing with high-noise backgrounds by testing it on a standard bearing dataset from Case Western Reserve University and a self-constructed composite bearing fault dataset, and the experimental results show that its performance exceeded six of the top current fault diagnosis techniques.

Abstract Deep learning models have been instrumental in extracting critical indicators for breast cancer diagnosis - the prevalent malignancy among women worldwide - from baseline magnetic resonance imaging. However, many existing models do not fully leverage the rich spatial information available in the 3D structure of medical imaging data, potentially overlooking important contextual details. This develops an explainable deep learning framework for classifying breast cancer that leverages the complete 3D and provides classification results alongside visual explanations of the decision-making process. The preprocessing pipeline is fed with 3D sequences containing ‘tumour’ and ‘non-tumour’ regions. It includes a 3D Adaptive Unsharp Mask (AUM) filter to reduce noise and augment image class, followed by normalisation and data augmentation. Classification is then achieved by training an augmented ResNet150 model. Three explainable artificial intelligence (XAI) techniques, including Shapley Additive Explanations, 3D Gradient-Weighted Class Activation Mapping, and Contextual Importance and Utility, are employed to provide improved interpretability. The model demonstrates state-of-the-art performance over the QIN-BREAST dataset, achieving testing accuracies of 98.861% for ‘tumours’ and 99.447% for ‘non-tumours’, as well as over the Duke Breast Cancer Dataset, where it achieves 99.104% for ‘tumours’ and 99.753% for ‘non-tumours’, while offering enhanced interpretability through XAI methods.

As remote work and online education continue to gain prominence, the importance of clear audio communication becomes crucial. Deep Learning-based Speech Enhancement has emerged as a promising solution for processing data in noisy environments. In this study, we conducted an in-depth analysis of two speech enhancement models, RNNoise and DeepFilterNet3, selected for their respective strengths. DeepFilterNet3 leverages time-frequency masking with a Complex Mask filter, while RNNoise employs Recurrent Neural Networks with lower complexity. The performance evaluation in training revealed that RNNoise demonstrated impressive denoising capabilities, achieving low loss values, while DeepFilterNet3 showed superior generalization. Specifically, "DeepFilterNet3 (Pre-Trained)" exhibited the best overall performance, excelling in intelligibility and speech quality. RNNoise also performed well in subjective quality measures. Furthermore, we assessed the real-time processing efficiency of both models. Both RNNoise variants processed speech signals almost in real-time, whereas DeepFilterNet3, though slightly slower, remained efficient. The findings demonstrate significant improvements in speech quality, with "DeepFilterNet3 (Pre-Trained)" emerging as the top-performing model. The implications of this study have the potential to enhance video conference experiences and contribute to the improvement of remote work and online education.

Each convolutional layer in any convolutional neural network produces a feature map containing the most important information, which a network needs to recognize respective images. To further improve these neural networks and better understand their capabilities, it is essential to discover, which features are actually extracted and how the images to be recognized are transformed by convolutions resulted from the learning process. This paper presents a comparative analysis of convolutions obtained via two complex-valued neural networks based on multi-valued neurons. The first network is a convolutional neural network based on multi-valued neurons (CNNMVN) which has a traditional convolutional neural network topology except of that it employs complex-valued convolutional kernels in its convolutional part and multi-valued neurons in its fully connected part. The second one is the multi-valued neural network based on multi-valued neurons (MLMVN) which is a fully connected multilayer neural network employed as a convolutional network in the frequency domain. Considering that both neural networks are complex-valued and the obtained filters operate in the complex domain, the conducted research indicates that the kernels of both networks produce filters similar to existing digital image processing filters. The analysis of CNNMVN kernels revealed that they implement unsharp masking filters and edge detection filters for identifying shapes in images, while the MLMVN kernels enhance specific frequency sub-bands. The latter means that the respective filters are mostly not similar to the ones known as unsharp masking or sharpening filters. Thus, the kernels of both convolutional networks contribute to improving image recognition performance in their own ways.

This paper presents a novel hardware architecture for Frequency Response Masking (FRM) Filter Bank based on Residue Number System (RNS) arithmetic for Digital Hearing Aids (DHA). FRM is a computationally efficient approach for filter bank design that separates different frequencies based on the Audiograms of a patient. However, filter banks are critical power-hungry elements that require high computational resources. Therefore, the proposed architecture aims to provide an efficient implementation of FRM filter banks, which can improve the value and affordability of DHAs. The proposed architecture employs FIR filters in direct form, linear phase, and poly phase using RNS arithmetic. This approach enables the performance of arithmetic operations in parallel and independently. The concepts are further extended for the efficient implementation of FRM filter bank. The results of the proposed architecture show that direct implementation reduces the delay when the number of taps increases in the FIR filter. However, to reduce computational resources and optimize the area requirement, a Folded RNS architecture is also proposed. The Folded RNS architecture offers hardware savings of 23–27% for a 40-tap FIR filter and 29–31% for a 60-tap FIR filter. Additionally, it improves speed by 13–15% for a 40-tap FIR filter and 16–19% for a 60-tap folded RNS FIR filter. The implementation of FRM filter bank using the folded FIR filter shows the same trend in hardware saving and speed improvement as in the case of FIR filters. These results demonstrate that the proposed hardware architecture has the potential to improve the efficiency and affordability of DHAs while enhancing the listening comfort, which can enhance the quality of life for patients with hearing impairments.

In various hazardous locations, gas mask filters are essential to protect from airborne pollutants and harmful gases. However, under certain conditions, such as the weather or climate in some locations can affect gas mask filtration. Based on a previous study, the existing geometry of the gas mask filter cartridge unit been analyse for its preferential flow within the gas mask domain, which resulted in a significant pressure drop and heat concentration in the filter, affecting the filtration. However, another study suggested designing the main sieve passageway of the filter to help in resolving the pressure drop and create much well distribution of flow within the cartridge. In this study, three geometries with re-design of the main sieve passageway of the filter were made and simulated to determine the preferential flow using the computational fluid dynamics (CFD) method. Two filter concentrations (300 ppm, and 1000 ppm) and constant humidity ratios of at 80 % were simulated. The presence of the dead zone was examined using the computational fluid dynamics (CFD) method, which was controlled by the Navier-Stokes equation and continuity based on several flow parameters. Based on the result occupied can be concluded, the second geometry had a much better velocity contour distribution around 40% than the other geometry, maintaining the overall minimum velocity area even though the formation of the dead zone area for the second geometry was 10% higher at the lower part of the filter than for the third geometry. The abilities of the second geometry to perform well even in the presence of higher concentrations brought to the honeycomb-based design as the main sieve passageway actually improve the velocity distribution and then minimizing formation of “dead zone”. Concluding justified that the proposed geometry met the prediction of improving the pressure drop and create quite well distribution of flow in the filter. prediction of improving the pressure drop and create quite much well distribution of flow in the filter.

Cataract occurs when the lens of the eyes, normally transparent, becomes cloudy. Clouded vision resulting from cataracts can posechallenges in activities such as reading, nighttime driving, and discerning facial expressions of acquaintances. Ensuring quality of vision now requires early detection of cataracts. This study aims to create a deep-learning classification system capable of distinguishing between healthy eyes and those affected by cataracts. To achieve this, modifications such as skip connections andchannel-wise attention have been integrated into the pre-trained MobileNetV2 model to formulate the proposed model. Furthermore, augmentation technique and unsharp masking filter are implemented in the pre-processing dataset to augment the image count and improve image quality. The findings indicate that the model achieved an accuracy rate of 98,80% for ODIR-2019 in 2 categories: cataract and normal.

Ground penetrating radar is a high-resolution, efficient, non-destructive geophysical detection method. It is widely used in various application scenarios such as tunnel geological prediction and road maintenance. Ground penetrating radar data contains a variety of valid signals as well as noise. The diffracted waves of ground penetrating radar contain high-resolution small target imaging information. A critical challenge in GPR applications is how to extract diffracted waves from the wave fields. We provide a strategy to achieve this goal by applying the masking filters. Considering the complexity of the ground penetrating radar wave field and the weak energy of the diffracted waves, the median filter is first employed to suppress the linear reflections and then the f-k filter and filter are implemented to further increase the proportion of diffractions in the wave fields. Three numerical experiments are employed to test the diffraction-separation method.

Recent advances in satellite technology have brought enormous potential to ecosystem mapping, which is one of the fundamental components of environmental studies. In this paper, a Random Forest classifier is applied for the strict assessment of the efficiency of ecosystem mapping through a detailed comparative analysis between combined Sentinel-1 and Sentinel-2 data and stand-alone Sentinel-2 imagery over three priority ecosystems, including wetlands, riverine areas, and mangroves in Bangladesh. The collocated images, based on the integration of Sentinel-1 data with Sentinel-2 data, would do better than Sentinel-2 imagery alone over various ecosystems. Particularly, in this study, attention focused on the Hakaluki Haor area for the wetlands, the Padma-Jamuna River confluence for the riverine ecosystem, and the Sundarban forest for mangroves. By leveraging Synthetic Aperture Radar (SAR) data in C-band dual-polarization from Sentinel-1 and four spectral bands (blue, green, red, and near-infrared) from Sentinel-2, the study analyzes imagery from December 2022 to February 2023. A 5% cloud masking filter is applied to optical data to enhance accuracy. In this methodology, 70% of the total signature values are used for training the classification model and the remaining 30% for testing. It can be noticed from the results that with the use of fused data, remarkably high accuracy in classification has been improved, such as overall accuracies of 94.17% for mangroves, 87.30% for riverine, and 85.96% for wetland ecosystems. In contrast, the use of singular Sentinel-2 imagery yields lower accuracies of 91.56%, 85.21%, and 82.51% for the respective ecosystems. The integration of radar data is shown to provide critical information, especially in environments with dense vegetation or cloud cover, where optical data alone may be insufficient. The findings of this study underline the limitations of relying on Sentinel-2 imagery to capture complex details of diverse ecosystems and highlight the need to include Sentinel-1 data for a more holistic analysis. This fusion allows improved accuracy to be achieved, which not only brings in more depth of ecological knowledge but also underpins more effective conservation strategies.

The trend of decreasing young workers in the agricultural sector needs to be anticipated by developing intelligent machines known as agricultural robots. This research aims to apply a stereo vision system to control the movement of the robot's grip towards the 3D position of the red chili fruit. The stereo vision system installed on the robot waist (joint-2) is used to capture plant images and process them using HSV masking filters and triangulation principal to obtain the 3D center point position of the fruit. The robot joint movement is calculated using geometric based inverse kinematics. The research results show that the average accuracy of the stereo vision system is 93.9 %. The average grip positioning accuracy is 95.6 % to the actual chili fruit position and 98.5 % to the stereo vision calculation value. The average stability of the stereo vision values is 99.5 %, while the average positioning stability of the robot's grip is 99.6 %. Time consumption for image processing is 0.053 s while time consumption for robot grip movement is 9 s. Therefore, the stereo vision system can be used to control robot's grip movement with a good accuracy. Keywords: Red chili fruit, Robot arm, Stereo vision, Three-dimensional position.

ABSTRACT Air is an important component that affects human survival, but air quality in Indonesia has greatly decreased due to air pollution. This study used chitosan / ZnO / cellulose acetate composite membranes made from citronella waste as mask filters with ZnO variations of 1%, 2%, and 3%. Composite membranes are made by the phase inversion method and characterized by FTIR, tensile, SEM, and antibacterial tests. Optimum conditions based on the formation of pores measuring 0.17 μm are found in chitosan/ZnO/Cellulose Acetate composite membranes with a variation of 3% ZnO. In addition, this variation also has good mechanical properties, with an elongation value of 2.1177% and an elastic modulus of 6.5560 N/m². Based on antibacterial tests, the composite membrane of the 3% ZnO variation also showed the ability to increase antibacterial activity with moderate antibacterial inhibitory strength. Keywords: Composite, Filter Mask, Cellulose Acetate, Chitosan, ZnO

In conventional non-intrusive speech intelligibility estimation, reverberation is extracted from the time-frequency representation of the input by explicit filter bank processing or spectral masking. However, these filter banks and masking processes are not always optimal. We replaced these processes with convolutional neural networks using rectangular kernels restricted to the frequency direction and masking such as a self-attention mechanism. We believe that this will enable feature extraction that is optimal for intelligibility estimation and will enable its estimation with high accuracy that generalizes well to input under various conditions. We further applied this front-end CNN to a previously proposed prediction model using speech enhancement. As a result, the estimation accuracy was improved compared to conventional front-ends using fixed filter banks, and this prediction showed a correlation coefficient with the subjective evaluation of 0.84 compared to 0.80 with the fixed filter bank.

SUMMARYSeismic interrogation of the upper mantle from the base of the crust to the top of the mantle transition zone has revealed discontinuities that are variable in space, depth, lateral extent, amplitude and lack a unified explanation for their origin. Improved constraints on the detectability and properties of mantle discontinuities can be obtained with P-to-S receiver function (Ps-RF) where energy scatters from P to S as seismic waves propagate across discontinuities of interest. However, due to the interference of crustal multiples, uppermost mantle discontinuities are more commonly imaged with lower resolution S-to-P receiver function (Sp-RF). In this study, a new method called CRISP-RF (Clean Receiver-function Imaging using SParse Radon Filters) is proposed, which incorporates ideas from compressive sensing and model-based image reconstruction. The central idea involves applying a sparse Radon transform to effectively decompose the Ps-RF into its underlying wavefield contributions, that is direct conversions, multiples, and noise, based on the phase moveout and coherence. A masking filter is then designed and applied to create a multiple-free and denoised Ps-RF. We demonstrate, using synthetic experiment, that our implementation of the Radon transform using a sparsity-promoting regularization outperforms the conventional least-squares methods and can effectively isolate direct Ps conversions. We further apply the CRISP-RF workflow on real data, including single station data on cratons, common-conversion-point stack at continental margins and seismic data from ocean islands. The application of CRISP-RF to global data sets will advance our understanding of the enigmatic origins of the upper mantle discontinuities like the ubiquitous mid-lithospheric discontinuity and the elusive X-discontinuity.

Self-driving vehicles require the ability to perceive and understand their surroundings, just like human drivers. It entails navigating efficiently on roads, obeying traffic signs and signals, and avoiding collisions with other vehicles and pedestrians. To address the challenges associated with object detection in self-driving cars, an effort was made to demonstrate lane detection using the OpenCV library. To achieve this goal, the well-established probabilistic Hough transform technique is used for line detection. Before applying Hough transforms, several pre-processing techniques are used, including converting the image to grayscale, camera calibration, and implementing a masking filter. In addition, edge detection is performed using the edge detection method. The study also indicates a preference for the use of HSL (Hue, Saturation, and Lightness) and HSV (Hue, Saturation, Value) color spaces. When HSL is applied, white lines appear purer and brighter, resulting in superior performance compared to using HSV specifically to detect white. This algorithm proved particularly effective in detecting straight lanes, which achieved an accuracy ratio of 96.06%. By incorporating these methodologies, the lane detection algorithm implemented with the OpenCV library addresses the challenges of self-driving vehicles, providing them with improved perception capabilities similar to human drivers.

Breast cancer survival rates can be increased by providing early treatment to patients; thereby, microcalcification detection is critical because microcalcifications are an early sign of breast cancer. The visibility of microcalcifications can be improved by using Digital Breast Tomosynthesis (DBT) images, which have been shown to improve the overlapping issue in mammograms. However, since DBT screening techniques generate blurry artefacts and noise, this study proposes a DBT image enhancement procedure. As a result, this study indicated an enhancement method based on Non-Linear Unsharp Masking filters (NLUM). A filter, such as the Median Filter in conventional NLUM, is required to complete the non-linear element in the algorithm. Other researchers have previously proposed and demonstrated the Fuzzy Weighted Median Filter (FWMF) to improve medical images; thus, these filters can be adapted to the NLUM and replaced with the conventional filter. Following that, the enhancement process's performance will be evaluated using Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR). When compared to the Median Filter, the results show that the FWMF is the best filter to use in NLUM and successfully enhances DBT images with MSE and PSNR averages of 0.0171 and 67.0574, respectively.

This paper discusses the value added by using a single vector sensor over a conventional pressure-only hydrophone for geoacoustic inversions. Inversion methods based on genetic algorithms are used to estimate the seabed properties. Synthetic signals of impulsive arrivals first are modeled using KRAKEN and RAM propagation models, each being modified to predict components of the vector field. While KRAKEN is utilized to directly compute dispersion curves, RAM provides full-field results that require the application of time warping to separate the modal arrivals. Combinations of dispersion curves utilizing all vector sensor channels are compared to curves estimated with the pressure-only channel. Within the time warping analysis, both binary masking and band-pass filter masking methods are applied to compare stability of results. The environment modeled for the synthetic analysis and inversion method utilize sound speed profiles measured during the Monterey Bay 2019 at-sea experiment and assume a sediment layer of constant thickness overlying a deeper sub-bottom type. White noise is added to the synthetic data at different signal-to-noise ratios to evaluate the impact of signal excess on the results. A hybrid optimization approach is used to improve the results of the genetic algorithm method. The analysis with synthetic data is consistent with the analysis of broadband, impulsive data collected from the experiment, indicating that the additional information from the vertical velocity channel further improves the geoacoustic parameter estimates.

Face masks are increasingly important in the battle against infectious diseases and air pollution. Nanofibrous membranes (NFMs) are promising filter layers for removing particulate matter (PM) without restricting air permeability. In this study, tannic-acid-enriched poly(vinyl alcohol) (PVA-TA) NFMs were fabricated by electrospinning PVA solutions containing large amounts of tannic acid (TA), a multifunctional polyphenol compound. We were able to prepare uniform electrospinning solution without coacervate formation by inhibiting the robust hydrogen bonding between PVA and TA. Notably, the NFM maintained its fibrous structure even under moist conditions after heat treatment without the use of a cross-linking agent. Further, the mechanical strength and thermal stability of the PVA NFM were improved by the introduction of TA. The functional PVA NFM with a high TA content showed excellent UV-shielding (UV-A: 95.7%, UV-B: 100%) and antibacterial activity against Escherichia coli (inhibition zone: 8.7 ± 1.2 mm) and Staphylococcus aureus (inhibition zone: 13.7 ± 0.6 mm). Moreover, the particle filtration efficiency of the PVA-TA NFM for PM0.6 particles was 97.7% at 32 L min-1 and 99.5% at 85 L min-1, indicating excellent filtration performance and a low pressure drop. Therefore, the TA-enriched PVA NFM is a promising mask filter layer material with excellent UV-blocking and antibacterial properties and has the potential for various practical applications.

Abstract During the COVID‐19 pandemic, face masks have become an important protective measure for reducing the spread of potentially infectious aerosol particles emitted while speaking, coughing, or simply breathing. In this work, a voxel‐based numerical model obtained from micro‐computed tomography (microCT) scans of a medical mask was validated by comparing fractional filtration efficiency and net pressure loss to values measured at an in‐house mask test bench after discharging the mask in isopropanol. Varying mean fiber diameter, solid volume fraction, and thickness of the filter medium, parametric studies based on a digital twin of the mask sample were carried out. It is demonstrated that face masks can be designed where filtration efficiency, pressure drop, and material consumption is improved compared to the base case.

ABSTRACT Cognitive radio is a potential solution to meet the upcoming spectrum scarcity issue. Spectrum sensing techniques can be employed in a cognitive radio. Even the smallest inactive section of the spectrum can be effectively used with high-resolution spectrum hole detection. This study proposes a method for detecting spectrum holes that performs coarse sensing as a first stage for finding occupied channels simultaneously. A fine sensing technique is proposed as a second stage using which we can efficiently find spectrum holes in the occupied band. A two-stage Frequency Response Masking (FRM) filter sandwiched between two Pascal structure based sampling rate converters results in arbitrary variation of bandwidth. By using this arbitrary variation in bandwidth, it is possible to identify spectrum holes with high resolution while fine sensing the spectrum. High-resolution spectrum hole detection can be accomplished using the proposed technique without adding to the hardware design’s complexity. When the proposed method’s hardware complexity is compared to the state of the art, it is observed to be substantially reduced. The prototype filter used for spectrum hole detection is synthesised using Xilinx Vivado and Cadence Genus tool for the area and power analysis.