Computational Resources Research Articles

Diffuse radio sky models using large-scale shapelets

Sky models used in radio interferometric data-processing primarily consist of compact and discrete radio sources. When there is a need to model large-scale diffuse structure such as the Galaxy, specialized source models are sought after for the sake of simplicity and computational efficiency. We propose the use of shapelet basis functions for modeling the large-scale diffuse structure in various radio interferometric data-processing pipelines. The conventional source model construction using shapelet basis functions is restricted to using images of smaller size due to limitations in computational resources such as memory. We propose a novel shapelet decomposition method to lift this restriction, enabling the use of images of millions of pixels (as well as a wide spectral bandwidth) for building models of large-scale diffuse structure. Furthermore, the application of direction-dependent errors onto diffuse sky models is an expensive operation that is often performed as a convolution. We propose using some specific properties of shapelet basis functions to apply these direction-dependent errors as a product of the model coefficients, which avoids the need for convolution. We provide results based on simulations and real observations. In order to measure the efficacy of our proposed method in modeling large-scale diffuse structure, we considered the direction-dependent calibration of simulated as well as real LOFAR observations that have a significant number of diffuse large-scale structure. The results show that by including large-scale shapelet models of the diffuse sky, we are able to overcome a major problem of existing calibration techniques, which do not model this large-scale diffuse structure, that is, the suppression of this large-scale diffuse structure because the model is incomplete.

A lightweight deep-learning model for parasite egg detection in microscopy images.

Intestinal parasitic infections are still a serious public health problem in developing countries, and the diagnosis of parasitic infections requires the first step of parasite/egg detection of samples. Automated detection can eliminate the dependence on professionals, but the current detection algorithms require large computational resources, which increases the lower limit of automated detection. Therefore, we have designed a lightweight deep-learning model, YAC-Net, to achieve rapid and accurate detection of parasitic eggs and reduce the cost of automation. This paper uses the ICIP 2022 Challenge dataset for experiments, and the experiments are conducted using fivefold cross-validation. The YOLOv5n model is used as the baseline model, and then two improvements are made to the baseline model based on the specificity of the egg data. First, the neck of the YOLOv5n is modified to from a feature pyramid network (FPN) to an asymptotic feature pyramid network (AFPN) structure. Different from the FPN structure, which mainly integrates semantic feature information at adjacent levels, the hierarchical and asymptotic aggregation structure of AFPN can fully fuse the spatial contextual information of egg images, and its adaptive spatial feature fusion mode can help the model select beneficial feature and ignore redundant information, thereby reducing computational complexity and improving detection performance. Second, the C3 module of the backbone of the YOLOv5n is modified to a C2f module, which can enrich gradient information, improving the feature extraction capability of the backbone. Moreover, ablation studies are designed by us to verify the effectiveness of the AFPN and C2f modules in the process of model lightweighting. The experimental results show that compared with YOLOv5n, YAC-Net improves precision by 1.1%, recall by 2.8%, the F1 score by 0.0195, and mAP_0.5 by 0.0271 and reduces the parameters by one-fifth. Compared with some state-of-the-art detection methods, YAC-Net achieves the best performance in precision, F1 score, mAP_0.5, and parameters. The precision, recall, F1 score, mAP_0.5, and parameters of our method on the test set are 97.8%, 97.7%, 0.9773, 0.9913, and 1,924,302, respectively. Compared with the baseline model, YAC-Net optimizes the model structure and simplifies the parameters while ensuring the detection performance. It helps to reduce the equipment requirements for performing automated detection and can be used to realize the automatic detection of parasite eggs under microscope images.

Temporal-Incremental Learning for Android Malware Detection

Malware classification is a specific and refined task within the broader malware detection problem. Effective classification aids in understanding attack techniques and developing robust defenses, ensuring application security and timely mitigation of software vulnerabilities. The dynamic nature of malware demands adaptive classification techniques that can handle the continuous emergence of new families. Traditionally, this is done by retraining models on all historical samples, which requires significant resources in terms of time and storage. An alternative approach is Class-Incremental Learning (CIL), which focuses on progressively learning new classes (malware families) while preserving knowledge from previous training steps. However, CIL assumes that each class appears only once in training and is not revisited, an assumption that does not hold for malware families, which often persist across multiple time intervals. This leads to shifts in the data distribution for the same family over time, a challenge that is not addressed by traditional CIL methods. We formulate this problem as Temporal-Incremental Malware Learning (TIML), which adapts to these shifts and effectively classifies new variants. To support this, we organize the MalNet dataset, consisting of over a million entries of Android malware data collected over a decade, in chronological order. We first adapt state-of-the-art CIL approaches to meet TIML's requirements, serving as baseline methods. Then, we propose a novel multimodal TIML approach that leverages multiple malware modalities for improved performance. Extensive evaluations show that our TIML approaches outperform traditional CIL methods and demonstrate the feasibility of periodically updating malware classifiers at a low cost. This process is efficient and requires minimal storage and computational resources, with only a slight dip in performance compared to full retraining with historical data.

A review of multimodal deep learning methods for genomic-enabled prediction in plant breeding.

Deep learning methods have been applied when working to enhance the prediction accuracy of traditional statistical methods in the field of plant breeding. Although deep learning seems to be a promising approach for genomic prediction, it has proven to have some limitations, since its conventional methods fail to leverage all available information. Multimodal deep learning methods aim to improve the predictive power of their unimodal counterparts by introducing several modalities (sources) of input information. In this review, we introduce some theoretical basic concepts of multimodal deep learning and provide a list of the most widely used neural network architectures in deep learning, as well as the available strategies to fuse data from different modalities. We mention some of the available computational resources for the practical implementation of multimodal deep learning problems. We finally performed a review of applications of multimodal deep learning to genomic selection in plant breeding and other related fields. We present a meta-picture of the practical performance of multimodal deep learning methods to highlight how these tools can help address complex problems in the field of plant breeding. We discussed some relevant considerations that researchers should keep in mind when applying multimodal deep learning methods. Multimodal deep learning holds significant potential for various fields, including genomic selection. While multimodal deep learning displays enhanced prediction capabilities over unimodal deep learning and other machine learning methods, it demands more computational resources. Multimodal deep learning effectively captures intermodal interactions, especially when integrating data from different sources. To apply multimodal deep learning in genomic selection, suitable architectures and fusion strategies must be chosen. It is relevant to keep in mind that multimodal deep learning, like unimodal deep learning, is a powerful tool but should be carefully applied. Given its predictive edge over traditional methods, multimodal deep learning is valuable in addressing challenges in plant breeding and food security amid a growing global population.

Attack Reconstruction and Attack-Resilient Consensus Control for Fuzzy Markovian Jump Multi-Agent Systems

Driven by the rapid development of modern industrial applications, multi-agent systems (MASs), integrating computational and physical resources, have become increasingly important in recent years. However, the performance of MASs can be easily compromised by malicious false data injection attacks (FDIAs) due to the inherent vulnerability of the cyber layer. This work focuses on an event-triggered framework for secure reconstruction and consensus control in MASs subject to both sensor and actuator attacks. First, we introduce a class of Takagi–Sugeno fuzzy multi-agent systems that relax the traditional Lipschitz condition and incorporate realistic system dynamics by considering parameter variations governed by Markovian jump principles. Second, an adaptive fuzzy estimator is developed for the simultaneous reconstruction of states and attacks in MASs. The derived estimates are utilized to design an attack-resilient consensus control strategy that compensates for the effects of FDIAs on the closed-loop consensus error dynamics. Meanwhile, the sufficient conditions for the convergence of both estimation and consensus errors are presented and rigorously proved. Finally, evaluation results on an experimental platform through multiple truck-trailer systems are provided to demonstrate the effectiveness and performance of the proposed approach.

Underwater Object Detection Algorithm Based on an Improved YOLOv8

Due to the complexity and diversity of underwater environments, traditional object detection algorithms face challenges in maintaining robustness and detection accuracy when applied underwater. This paper proposes an underwater object detection algorithm based on an improved YOLOv8 model. First, the introduction of CIB building blocks into the backbone network, along with the optimization of the C2f structure and the incorporation of large-kernel depthwise convolutions, effectively enhances the model’s receptive field. This improvement increases the capability of detecting multi-scale objects in complex underwater environments without adding a computational burden. Next, the incorporation of a Partial Self-Attention (PSA) module at the end of the backbone network enhances model efficiency and optimizes the utilization of computational resources while maintaining high performance. Finally, the integration of the Neck component from the Gold-YOLO model improves the neck structure of the YOLOv8 model, facilitating the fusion and distribution of information across different levels, thereby achieving more efficient information integration and interaction. Experimental results show that YOLOv8-CPG significantly outperforms the traditional YOLOv8 in underwater environments. Precision and Recall show improvements of 2.76% and 2.06%. Additionally, mAP50 and mAP50-95 metrics have increased by 1.05% and 3.55%, respectively. Our approach provides an efficient solution to the difficulties encountered in underwater object detection.

Edge Computing for AI-Based Brain MRI Applications: A Critical Evaluation of Real-Time Classification and Segmentation

Medical imaging plays a pivotal role in diagnostic medicine with technologies like Magnetic Resonance Imagining (MRI), Computed Tomography (CT), Positron Emission Tomography (PET), and ultrasound scans being widely used to assist radiologists and medical experts in reaching concrete diagnosis. Given the recent massive uplift in the storage and processing capabilities of computers, and the publicly available big data, Artificial Intelligence (AI) has also started contributing to improving diagnostic radiology. Edge computing devices and handheld gadgets can serve as useful tools to process medical data in remote areas with limited network and computational resources. In this research, the capabilities of multiple platforms are evaluated for the real-time deployment of diagnostic tools. MRI classification and segmentation applications developed in previous studies are used for testing the performance using different hardware and software configurations. Cost–benefit analysis is carried out using a workstation with a NVIDIA Graphics Processing Unit (GPU), Jetson Xavier NX, Raspberry Pi 4B, and Android phone, using MATLAB, Python, and Android Studio. The mean computational times for the classification app on the PC, Jetson Xavier NX, and Raspberry Pi are 1.2074, 3.7627, and 3.4747 s, respectively. On the low-cost Android phone, this time is observed to be 0.1068 s using the Dynamic Range Quantized TFLite version of the baseline model, with slight degradation in accuracy. For the segmentation app, the times are 1.8241, 5.2641, 6.2162, and 3.2023 s, respectively, when using JPEG inputs. The Jetson Xavier NX and Android phone stand out as the best platforms due to their compact size, fast inference times, and affordability.

A Data Driven Black Box Approach for the Inverse Quantification of Set-Theoretical Uncertainty

Abstract Inverse uncertainty quantification commonly uses the well established Bayesian framework. Recently, alternative interval methodologies have been introduced. However, in their current state of the art implementation, both techniques suffer from a large and usually unpredictable computational effort. Thus, both techniques are not applicable in a real-time context. To achieve a low-cost, real-time solution to this inverse problem, we introduce a deep-learning framework consisting of unsupervised auto-encoders and a shallow neural network. This framework is trained by means of a numerically generated dataset that captures typical relations between the model parameters and selected measured system responses. The performance and efficacy of the technique is illustrated using two distinct case studies. The first case involves the DLR AIRMOD, a benchmark case that has served as reference case for the inverse uncertainty quantification problem. The results demonstrate that the achieved accuracy is on par with the existing interval method found in literature, while requiring only a fraction of its computational resources. The second case study examines a resistance pressure welding process, which is known to require extremely fast monitoring and control due to the high process throughput. Based on the proposed method, and with only a limited selection of simulated responses of the process, it is possible to identify the interval uncertainty of the crucial parameters of the process. The computational cost in this case makes it possible for an inverse uncertainty quantification in a real-time setting.

Deep network based approaches to mitigate seasonal effects in SAR images for deforestation monitoring

Abstract. Most deforestation monitoring programs are based on optical images, which are severely affected by clouds, especially in tropical regions. As an alternative, Synthetic Aperture Radar (SAR) data are minimally affected by atmospheric conditions. However, one of the challenges inherent in such approaches is the effect of seasonal rainforest variations over the SAR images. Recently proposed stabilization algorithms mitigate this effect with significant accuracy gains, however, at the cost of higher computational resources, needed to accommodate long temporal SAR image sequences. This work addresses this issue and presents two alternative solutions that attain similar or better accuracy at a much lower computational requirements. One solution is based on a ResUnet, while the second combines an LSTM and a UNet. Both approaches were tested using raw and stabilized pairs as well as raw sequences. Experiments have indicated that both approaches can mitigate the seasonality effect using a much shorter SAR image sequences than modern stabilization methods require. The results with the multitemporal input outperformed those with the preprocessed bitemporal set by 4.3% in Recall, 1.7% in Precision, and 2.7% in F1-Score, also delivering the best deforestation probability maps.

Exploring the effects of RNNs and deep learning frameworks on real‐time, lightweight, adaptive time series anomaly detection

SummaryReal‐time, lightweight, adaptive time series anomaly detection is increasingly critical in cybersecurity, industrial control, finance, healthcare, and many other domains due to its capability to promptly process time series and detect anomalies without requiring extensive computation resources. While numerous anomaly detection approaches have emerged recently, they generally employ a single type of recurrent neural network (RNN) and are implemented using a single type of deep learning framework. The impacts of using various RNN types across different deep learning frameworks on the performance of these approaches remain unclear due to a lack of comprehensive evaluations. In this article, we aim to investigate the impact of different RNN variants and deep learning frameworks on real‐time, lightweight, and adaptive time series anomaly detection. We reviewed several state‐of‐the‐art anomaly detection approaches and implemented a representative approach using several RNN variants supported by three popular deep learning frameworks. A thorough evaluation was conducted to analyze the detection accuracy, time efficiency, and resource consumption of each implementation using four real‐world, open‐source time series datasets. The results show that RNN variants and deep learning frameworks have a significant impact. Therefore, it is crucial to carefully select appropriate RNN variants and deep learning frameworks for the implementation.

ESTIMATION OF FORMANT INFORMATION USING AUTOCORRELATION FUNCTION OF VOICE SIGNAL

Context. The current scientific problem of extracting biometric characteristics of a user of a voice authentication system, which can significantly increase its reliability, is considered. There has been performed estimation of formant information from the voice signal, which is a part of the user template in the voice authentication system and is widely used in the processing of speech signals in other applications, including in the presence of interfering noise components. The work is distinguished by the investigation of a polyharmonic signal. Objective. The purpose of the work is to develop procedures for generating formant information based on the results of calculating the autocorrelation function of the analyzed fragment of the voice signal and their subsequent spectral analysis. Method. The procedures for generating formant information in the process of digital processing of voice signal are proposed. Initially, the autocorrelation function of the analyzed fragment of the voice signal is calculated. Based on the results of the autocorrelation function estimation, the amplitude-frequency spectrum is calculated, from which the formant information is extracted, for example, by means of threshold processing. When the signal-to-noise ratio of the analyzed voice signal fragment is low, it is advisable to iteratively calculate the autocorrelation function. The latter allows increasing the signal-to-noise ratio and the efficiency of formant information extraction. However, each subsequent iteration of the autocorrelation function calculation is associated with an increase in the required computational resource. The latter is conditioned by the doubling of the amount of processed data at each iteration. Results. The developed procedures for generating formant information were investigated both in the processing of model and experimental voice signals. The model signals had a low signal-to-noise ratio. The proposed procedures allow to determine more precisely the width of the spectrum of extracted formant frequencies, significantly increase the number of extracted formants, including cases at low signal-to-noise ratio. Conclusions. The conducted model experiments have confirmed the performance and reliability of the proposed procedures for extracting formant information both in the processing of model and experimental voice signals. The results of the research allow to recommend their use in practice for solving problems of voice authentication, speaker differentiation, speech and gender recognition, intelligence, counterintelligence, forensics and forensic examination, medicine (diseases of the speech tract and hearing). Prospects for further research may include the creation of procedures for evaluating formant information based on phase data of the processed voice signal.

Research on Distributed Autonomous Timekeeping Algorithm for Low-Earth-Orbit Constellation

The time of a satellite navigation system is primarily generated by the main control station of the ground system. Consequently, when ground stations fail, there is a risk to the continuous provision of time services to the equipment and users. Furthermore, the anticipated launch of additional satellites will further strain the satellite–ground link. Next-generation satellite navigation systems will rely on time deviation measurements from inter-satellite links to independently establish and maintain a space-based time reference, enhancing the system’s reliability and robustness. The increasing number of low-Earth-orbit satellite navigation constellations provides ample resources for establishing a space-based time reference. However, this also introduces challenges, including extensive time scale computations, increased link noise, and low clock resource utilization. To address these issues, this paper proposes a Distributed Kalman Plus Weight (D-KPW) algorithm, which combines the benefits of Kalman filtering and the weighted average algorithm, balancing the performance with computational resources. Furthermore, an adaptive clock control algorithm, D-KPW (Control), is developed to account for both the short-term and long-term frequency stability of the time reference. The experimental results demonstrate that the frequency stability of the time reference established by the D-KPW (Control) algorithm reaches 7.40×10−15 and 2.30×10−15 for sampling intervals of 1000 s and 1,000,000 s, respectively, outperforming traditional algorithms such as ALGOS. The 20-day prediction error of the time reference is 1.55 ns. Compared to traditional algorithms such as AT1, ALGOS, Kalman, and D-KPW, the accuracy improves by 65%, 65%, 66%, and 67%, respectively.

Ultra-Short-Term Wind Power Forecasting in Complex Terrain: A Physics-Based Approach

This paper proposes a method based on Computational Fluid Dynamics (CFD) and the detection of Wind Energy Extraction Latency for a given wind turbine (WT) designed for ultra-short-term (UST) wind energy forecasting over complex terrain. The core of the suggested modeling approach is the Wind Spatial Extrapolation model (WiSpEx). Measured vertical wind profile data are used as the inlet for stationary CFD simulations to reconstruct the wind flow over a wind farm (WF). This wind field reconstruction helps operators obtain the wind speed and available wind energy at the hub height of the installed WTs, enabling the estimation of their energy production. WT power output is calculated by accounting for the average time it takes for the turbine to adjust its power output in response to changes in wind speed. The proposed method is evaluated with data from two WTs (E40-500, NM 750/48). The wind speed dataset used for this study contains ramp events and wind speeds that range in magnitude from 3 m/s to 18 m/s. The results show that the proposed method can achieve a Symmetric Mean Absolute Percentage Error (SMAPE) of 8.44% for E40-500 and 9.26% for NM 750/48, even with significant simplifications, while the SMAPE of the persistence model is above 15.03% for E40-500 and 16.12% for NM 750/48. Each forecast requires less than two minutes of computational time on a low-cost commercial platform. This performance is comparable to state-of-the-art methods and significantly faster than time-dependent simulations. Such simulations necessitate excessive computational resources, making them impractical for online forecasting.

Deep Autoencoder for Real-Time Single-Channel EEG Cleaning and Its Smartphone Implementation Using TensorFlow Lite With Hardware/Software Acceleration.

To remove signal contamination in electroencephalogram (EEG) traces coming from ocular, motion, and muscular artifacts which degrade signal quality. To do this in real-time, with low computational overhead, on a mobile platform in a channel count independent manner to enable portable Brain-Computer Interface (BCI) applications. We propose a Deep AutoEncoder (DAE) neural network for single-channel EEG artifact removal, and implement it on a smartphone via TensorFlow Lite. Delegate based acceleration is employed to allow real-time, low computational resource operation. Artifact removal performance is quantified by comparing corrupted and ground-truth clean EEG data from public datasets for a range of artifact types. The on-phone computational resources required are also measured when processing pre-saved data. DAE cleaned EEG shows high correlations with ground-truth clean EEG, with average Correlation Coefficients of 0.96, 0.85, 0.70 and 0.79 for clean EEG reconstruction, and EOG, motion, and EMG artifact removal respectively. On-smartphone tests show the model processes a 4 s EEG window within 5 ms, substantially outperforming a comparison FastICA artifact removal algorithm. The proposed DAE model shows effectiveness in single-channel EEG artifact removal. This is the first demonstration of a low-computational resource deep learning model for mobile EEG in smartphones with hardware/software acceleration. This work enables portable BCIs which require low latency real-time artifact removal, and potentially operation with a small number of EEG channels for wearability. It makes use of the artificial intelligence accelerators found in modern smartphones to improve computational performance compared to previous artifact removal approaches.

VPRF: Visual Perceptual Radiance Fields for Foveated Image Synthesis.

Neural radiance fields (NeRF) has achieved revolutionary breakthrough in the novel view synthesis task for complex 3D scenes. However, this new paradigm struggles to meet the requirements for real-time rendering and high perceptual quality in virtual reality. In this paper, we propose VPRF, a novel visual perceptual based radiance fields representation method, which for the first time integrates the visual acuity and contrast sensitivity models of human visual system (HVS) into the radiance field rendering framework. Initially, we encode both the appearance and visual sensitivity information of the scene into our radiance field representation. Then, we propose a visual perceptual sampling strategy, allocating computational resources according to the HVS sensitivity of different regions. Finally, we propose a sampling weight-constrained training scheme to ensure the effectiveness of our sampling strategy and improve the representation of the radiance field based on the scene content. Experimental results demonstrate that our method renders more efficiently, with higher PSNR and SSIM in the foveal and salient regions compared to the state-of-the-art FoV-NeRF. The results of the user study confirm that our rendering results exhibit high-fidelity visual perception.

Computational screening of phytochemicals present in some Nigerian medicinal plants against sickle cell disease

Four hundred Phytochemical (bio-active) compounds having predictive activity for treating Sickle Cell Anemia were screened, using PASS online computational resource. Twenty-six compounds out of the four hundred compounds which showed high probability for treating sickle were further screened for pharmacokinetics profiles (ADMET properties) using SwissAdmet, AdmetSAR 2 and Pro-tox II online resources. Only thirteen compounds that displayed good ADMET properties from the twenty-six were further used for DFT calculations and molecular docking against carbonmonoxy sickle hemoglobin (PDB ID: 5E6E). Molecular docking analysis reinforced by DFT calculations showed that two compounds, phenanthrene-5,6-dione (A9) and 2-(3,4-dihydroxyphenyl)-5,7-dihydroxychromen-4-one (A13, Luteolin) had the best binding affinity of − 8.3 and − 8.9 kcal/mol, respectively, compared to voxelotor (GBT-440), a drug use in treating sickle cell disease. Molecular dynamic simulations showed that 2-(3,4-dihydroxyphenyl)-5,7-dihydroxychromen-4-one (A13, Luteolin) is highly stable with the protein than voxelotor.

Generating tailored high frequency features in core collapse supernova gravitational wave signals applicable in LIGO interferometric studies

In this article, we introduce a methodology based on an analytical model of a damped harmonic oscillator subject to random forcing to generate transient gravitational wave signals. Such a model incorporates a simulated linear high-frequency component that mirrors the growing characteristic frequency over time observed in numerical simulations of core-collapse supernova gravitational wave signals. Unlike traditional numerical simulations, the method proposed in this study requires minimal computational resources, which makes it particularly advantageous for tasks such as data analysis, detection, and reconstruction of gravitational wave transients. To verify the physical accuracy of the generated signals, they are compared against the amplitude spectral of current LIGO interferometers and a 3D numerical simulation of a core-collapse supernova gravitational wave signal from the Andresen et al. 2017 model s15.nr. The results indicate that this approach is effective in generating scalable signals that align with LIGO interferometric data, offering potential utility in various gravitational wave transient investigations.

Disentangled feature fusion network for lightweight image super-resolution

Recently, the quality of generated images in image super-resolution (SR) has significantly improved due to the widespread application of convolutional neural networks. Existing super-resolution methods often overlook the importance of network width and instead prioritize designing deeper network structures to improve performance. Deeper networks, however, demand greater computational resources and are more challenging to train, making them less suitable for devices with limited performance. To address this issue, we propose a novel method called the disentangled feature fusion network (DFFN). Specifically, we construct dual feature extraction streams (DFES) using the strategies of feature disentanglement and parameter sharing, which increase the network's width without increasing the number of parameters. To facilitate the interaction of information between the dual feature extraction streams, we design a feature interaction module (FIM) that separately enhances high and low-frequency features. Furthermore, a feature fusion module (FFM) is presented to efficiently fuse different levels of high and low-frequency feature information. The proposed DFFN integrates DFES, FIM, and FFM, which not only widens the network without increasing parameters but also minimizes the loss of crucial feature information. Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms other state-of-the-art lightweight super-resolution methods, achieving a superior balance between parameter quantity, reconstruction performance, and model complexity. The code is available at https://github.com/zhoujy-aust/DFFN.

A Review on Multiple-Ocular Disease Detection Methodology using ML and DL Techniques

The rapid advancement in machine learning (ML) and deep learning (DL) techniques has significantly impacted the detection and diagnosis of ocular diseases, which are critical for preserving vision and overall eye health. This review aims to explore the various ML and DL methodologies applied to the detection of multiple ocular diseases, highlighting their effectiveness, limitations, and areas for improvement. The motivation behind this review stems from the increasing prevalence of ocular diseases and the need for efficient, accurate diagnostic tools. Despite the promising results of existing techniques, limitations such as data variability, the need for extensive training data, and computational resource requirements persist. The objective is to synthesize current methodologies and propose enhancements, particularly through the integration of attention mechanisms in convolutional neural networks (CNNs). This review identifies gaps in current research and suggests directions for future work to enhance diagnostic accuracy and clinical applicability.

Comparative analysis of performance, efficiency, and resource usage between COMSOL Multiphysics and the MPh library of Python in the simulation of physical phenomena

MPh is a library of Python that makes possible to link the Python computer language with COMSOL Multiphysics. The use of the MPh library opens the possibility to save the computer resources employed when simulating physical phenomena and solving mathematical models and equations. In the Python command interpreter is possible to change or adjust some settings and parameters from the models created in COMSOL, and to execute the COMSOL kernel to solve those models. In this study, we compare the performance of COMSOL Multiphysics and the MPh library of Python when computing the magnetic field generated by a distribution of currents and ferromagnetic material. The metrics employed to do the comparison and the methodology to measure them are described, as well as the computer equipment where the programs ran. The results show that the execution time of the computations are similar in both software, but in the rest of the metrics, the execution in Python surpassed the execution in COMSOL. We showed that the MPh library of Python demands less CPU and RAM usage when solving the mathematical models and the files containing the solutions use less storage memory. As a conclusion, we propose the use of the MPh library of Python to improve the performance of the computer in charge of carrying out the calculations.