Performance Of Proposed Method Research Articles

A deep neural network model with spectral correlation function for electrocardiogram classification and diagnosis of atrial fibrillation

Atrial Fibrillation (AF) is a common type of irregular heartbeat, and early detection can significantly improve treatment outcomes and prognoses. Single-lead Electrocardiogram (ECG) devices are under extensive scrutiny for monitoring patients' heart health worldwide. Standardized ECG signal monitoring has demonstrated a significant reduction in mortality rates associated with severe cardiovascular diseases. However, the automatic detection method for AF requires significant improvement. This study presents a novel approach that utilizes the cyclostationary analysis of ECG signals, uncovering a spectral hidden periodicity between the QRS-T (the main wave components representing electrical activity in the heart) complexes of the ECG signal through the Spectral Correlation Function (SCF). To validate the proposed method's performance, the single ECG's SCF coefficients are applied to the Convolutional Recurrent Neural Network (CRNN), which consists of convolutional and long short-term memory (LSTM) layers, on the 2017 PhysioNet challenge dataset. The obtained results demonstrate that the proposed approach efficiently represents ECG signals through SCF coefficients, leading to the accurate detection of AF with an average accuracy of 92.76% and an average F1-score of 89.1%.

COMBINED FIRST AND SECOND-ORDER SLIDING MODE CONTROL OF INDUCTION MOTOR

This paper uses hybrid sliding mode control to solve an output feedback tracking problem for the induction motor (IM). The main idea of this approach lies in the design of a law that ensures a smooth transition between two sliding regimes based on the choice of two sliding surfaces, one being linked to the other. The control is a combination of first and second-order sliding modes. The proposed approach controls the speed and rotor flux amplitude of the induction motor and guarantees the stability of the decoupled speed and rotor flux by using a Lyapunov method. The hybrid sliding mode algorithm provides robustness despite external disturbances and parameter variations. The controller has been implemented on an experimental setup, and results are presented to confirm the proposed method's effectiveness, robustness, and good performance.

Convolutional sparse coding network for sparse seismic time-frequency representation

Seismic time-frequency (TF) transforms are essential tools in reservoir interpretation and signal processing, particularly for characterizing frequency variations in non-stationary seismic data. Recently, sparse TF transforms, which leverage sparse coding (SC), have gained significant attention in the geosciences due to their ability to achieve high TF resolution. However, the iterative approaches typically employed in sparse TF transforms are computationally intensive, making them impractical for real seismic data analysis. To address this issue, we propose an interpretable convolutional sparse coding (CSC) network to achieve high TF resolution. The proposed model is generated based on the traditional short-time Fourier transform (STFT) transform and a modified UNet, named ULISTANet. In this design, we replace the conventional convolutional layers of the UNet with learnable iterative shrinkage thresholding algorithm (LISTA) blocks, a specialized form of CSC. The LISTA block, which evolves from the traditional iterative shrinkage thresholding algorithm (ISTA), is optimized for extracting sparse features more effectively. Furthermore, we create a synthetic dataset featuring complex frequency-modulated signals to train ULISTANet. Finally, the proposed method's performance is subsequently validated using both synthetic and field data, demonstrating its potential for enhanced seismic data analysis.

Figure-ground segmentation based medical image denoising using deep convolutional neural networks

Medical image noise can have a substantial impact on both diagnosis accuracy and image quality. Noise can cause problems with tasks related to diagnosis, like defining object boundaries, which are essential for precise diagnosis. By applying denoising techniques, medical imaging professionals can significantly improve image quality, reduce errors, and enhance the accuracy of diagnoses and treatments. This article presents a method for reducing noises like Gaussian noise, salt and pepper noise, speckle noise, and ring artefacts in medical images, such as magnetic resonance imaging (MRI), computed tomography (CT), and chest X-ray images. This study explores the integration of adaptive CNNs with guided image filtering for enhanced image quality and deep learning-driven Figure-Ground segmentation. The proposed method's performance is extensively evaluated on chest X-ray and MRI/CT images under diverse noise scenarios, with comparisons to existing techniques using established statistical metrics. The results validate that the proposed approach attains superior performance, yielding the highest values across these metrics.

ROAD value-based detection for GAE enhanced interference mitigation in LDACS.

The increasing volume of air traffic has placed significant stress on the current Air Traffic Management (ATM) systems, especially concerning the use of Very High Frequency (VHF) communication bands. As air traffic continues to grow, the limitations of the existing spectrum and infrastructure necessitate significant upgrades to ensure safety, efficiency, and capacity. The modernization of air traffic management systems has led to the development and introduction of the L-band Digital Aeronautical Communication System (LDACS), a new communication protocol. LDACS is designed to operate alongside existing L-band systems, ensuring compatibility with legacy users. The coexistence of LDACS with legacy systems poses significant interference challenges, as any disruption in data retrieval can critically impact flight safety. This paper proposes four potential interference mitigation techniques that LDACS can employ to detect and reduce the primary source of interference: Distance Measuring Equipment (DME). The authors introduce a prototype LDACS receiver that uses Rank-Ordered Absolute Differences (ROAD) statistics for effective interference sensing and employs GAE-enhanced pulse peak processors to mitigate Distance Measuring Equipment (DME) interference. Unlike the current GAE-enhanced pulse peak processors, the proposed methods use ROAD value-based detection for identifying DME interference. The performance of the proposed methods - ROAD GAE enhanced Pulse Peak Attenuator (RGPPA), ROAD GAE enhanced Pulse Peak Limiter (RGPPL), ROAD joint GAE enhanced Pulse Peak Attenuator (RJGPPA), and ROAD joint GAE enhanced Pulse Peak Limiter (RJGPPL) is analyzed across different threshold ROAD values to determine their efficacy in various signal conditions. Moreover, the performance of the proposed methods is compared to existing methods such as conventional pulse blanking and GAE-enhanced nonlinear devices, which use the amplitude of the received signal for the detection of interference. Furthermore, the proposed method's performance is compared to another method, ROAD PB, which uses ROAD statistics to detect DME interference and pulse blanking for DME mitigation. The comparative results show that the proposed methods outperformed conventional pulse blanking and ROADPB. Besides, these methods outperformed existing GAE-enhanced methods for their optimum threshold ROAD value.

Synergetic UPQC Application for Power Quality Enhancement in Microgrid Distribution System: SCSO Approach

Nowadays, Hybrid renewable energy systems (HRES) are increasingly being integrated into grid-connected load systems to lower losses and boost dependability. When the HRES system is connected to the grid system to satisfy needed load demand, power quality issues arise because of imbalanced load circumstances, non-linear load, and critical load. So this manuscript proposed a synergetic Unified Power Quality Conditioner (UPQC) application for power quality enhancement in microgrid distribution systems. The Sand Cat Swarm Optimization (SCSO) technique is based on the proposed sand cat swarm optimization method. The proposed strategy's primary goal is to regulate power flow, minimize harmonic distortion in both voltage and current waveforms, and maximize UPQC. By then, the proposed method's performance has been implemented into practice on the MATLAB platform and contrasted with several currently used techniques. The proposed technique displays the low Total Harmonic Distortion (THD) and operation time in all existing approaches like Moth Flame Optimization (MFO), Genetic Algorithm (GA), Salp Swarm Algorithm (SSA), Ant Lion Optimizer (ALO), Improved Bat Search Algorithm (IBSA), Lion Algorithm (LA), Artificial Bee Colony (ABC), Atom Search Optimization (ASO) and Crow Search Algorithm (CSA). The proposed method attains THD as before UPQC is 31%, after UPQC is 3%, load current is 1.42%, and load voltage is 2%. It also achieves a low operation time of 506ms and a low settling time of 0.15s compared to the existing methods. The significant improvement in power quality metrics demonstrates the effectiveness of the proposed SCSO technique.

Enhanced Fault Diagnosis in IoT: Uniting Data Fusion with Deep Multi-Scale Fusion Neural Network

One of the biggest challenges is figuring out when industrial IoT devices break. Notwithstanding these difficulties, one of the many advantages of using real-time sensor data from the Industrial Internet of Things (IIoT) is the ability to monitor events and respond promptly. The IIoT's sensor numbers may be analysed, combined with data from other sources, and applied quickly to make decisions. This manuscript proposes Enhanced Fault Diagnosis in IoT, Uniting Data Fusion with Deep Multi-Scale Fusion Neural Network (FD-IoT-DMSFNN). Initially, input sensor data are taken from the CWRU Dataset. Then, sensor data is normalised using Multivariate Fast Iterative Filtering. Then, the normalised sensor data are extensively dispersed and diverse; hence, the data outlier detection is performed using the Deep isolation forest (DIF) approach. Therefore, this manuscript proposes a Mexican Axolotl Optimization (MAO) for tuning the weight parameter of DMSFNN, which exhibits an enhanced fault detection process. Python is used to implement the recommended strategy. The proposed method's performance yields a lower completion time of 6.5%, 1.8%, and 4.13%; higher prediction accuracy of 2.26%, 6.71%, and 8.32% compared with existing approaches such as towards deep domain adaptability training methods for industrial IoT edge device soft real-time fault diagnosis (FD-IoT-LSTM), Intelligent Fault Quantitative Identification for the Industrial Internet of Things (IIoT) utilising a particular deep dual reinforcement learning model with insufficient samples (FD-IoT-DRL) and IIoT- based fault identification model for industrial use (FD-IoT-ML-LSTM) respectively.

Convolutional Neural Network-Based Lane-Change Strategy via Motion Image Representation for Automated and Connected Vehicles.

The lane-change decision-making module of automated and connected vehicles (ACVs) is one of the most crucial and challenging issues to be addressed. Motivated by human beings' underlying driving paradigm and the convolutional neural network's (CNN) dramatic capability of extracting features and learning strategies, this article proposes a CNN-based lane-change decision-making method via the dynamic motion image representation. Human drivers take proper driving maneuvers after they subconsciously construct the dynamic traffic scene representation in their brains, so this study first proposes the dynamic motion image representation method to reveal informative traffic situations in the motion-sensitive area (MSA), which provides a full view of surrounding cars. Then, this article develops a CNN model to extract the underlying features and learn driving policies from labeled datasets of MSA motion images. Besides, a safety-constrained layer is added to avoid vehicle collisions. We build a simulation platform based on the simulation of urban mobility (SUMO) to collect traffic datasets and test our proposed method. In addition, real-world traffic datasets are also involved to further investigate the proposed method's performance. The rule-based strategy and reinforcement learning (RL)-based method are used to compare with our approach. All results demonstrate that the proposed method performs lane-change decision-making much better than prevailing methods, which suggests our scheme has huge potential to accelerate the deployment of ACVs and is worth further study.

Improved fault detection and classification in PV arrays using stockwell transform and data mining techniques

The growing integration of photovoltaic (PV) systems into the power grid necessitates reliable fault detection and classification mechanisms to ensure operational efficiency and safety. Fault detection in photovoltaic (PV) arrays is crucial for maintaining optimal system performance and ensuring the reliability of solar power generation. This paper proposes a novel approach for fault detection in PV arrays by employing the Stockwell transform in combination with various data mining techniques. The Stockwell transform is an advanced time-frequency analysis tool that allows for enhanced feature extraction from time-series data. By applying the Stockwell transform to the PV array's operational data, valuable frequency-domain information is extracted, enabling the identification of subtle fault signatures. To effectively detect and classify various faults, different data mining techniques, such as support vector machines, decision trees, random forests, and k-nearest neighbours, are applied to the transformed data. Each technique's effectiveness in identifying faults is evaluated and compared, enabling the selection of the most suitable algorithm for the specific application. Experimental results demonstrate the effectiveness of the proposed fault detection approach, exhibiting high accuracy, sensitivity, and specificity in identifying various types of faults in PV arrays. Extensive simulations and experimental validations were conducted on various fault conditions, including partial shading, open-circuit faults, and degradation. The results demonstrate the proposed method's superior performance, achieving an accuracy of 99.61 %, precision of 99.75 % and F1 score of 98.73 %. These metrics significantly surpass traditional fault detection techniques, highlighting the method's potential for real-world deployment. The approach not only enhances the reliability of PV systems but also contributes to reducing maintenance costs and improving system efficiency. The combination of the Stockwell transforms with data mining techniques proposed here provides a robust and efficient framework for early detection of faults, enabling timely maintenance and minimizing energy losses.

Blockchain‐Enabled Decentralized Healthcare Data Exchange: Leveraging Novel Encryption Scheme, Smart Contracts, and Ring Signatures for Enhanced Data Security and Patient Privacy

ABSTRACTThe healthcare industry has undergone a digital transformation in recent years, with the adoption of electronic health records (EHRs) becoming increasingly prevalent. While this digitization offers various advantages, concerns regarding the security and privacy of sensitive medical data have also intensified. Data breaches and cyber‐attacks targeting healthcare organizations have underscored the need for robust solutions to protect patient data. Blockchain technology has emerged as a promising solution due to its decentralized and immutable nature, which ensures secure and transparent data recording. This paper proposes a novel approach that combines blockchain with advanced encryption scheme and privacy protection technique to establish a secure and privacy protected medical data sharing environment. The proposed system consists of three phases such as initialization phase, data processing phase, and authentication phase. The hybrid Feistal‐Shannon homomorphic encryption algorithm (HFSHE) is proposed to encrypt the medical data to ensure data confidentiality, integrity, and availability. Ring signature is integrated to the system to provide additional anonymity and protect the identities of the participants involved in data transactions. In addition, the smart contract developed performs authentication checks on users, generates a time seal, and verifies the ring signature. Through this enhancement, the system becomes more resilient to both external and internal threats, enhancing overall security as well as privacy. A comprehensive security analysis is conducted to compare the proposed method's performance against existing techniques. The results demonstrate the effectiveness of the proposed approach in safeguarding sensitive medical information within the blockchain ecosystem.

Brain Tumor Classification Using Vanilla Convolutional Neural Networks

Brain tumours are a common and dangerous type of malignant tumour that, if not detected early enough, can cut short a patient's life. The segmentation and classification of brain tumours using solely traditional medical image processing is a difficult and time-consuming task. Various imaging modalities, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and ultrasound image, are frequently utilized to assess brain, lung, liver, breast, prostate and other tumours. MRI images are specifically utilised in these analyses to detect brain tumours. As a result, developing approaches for detecting, recognizing, and classifying the conditions based on image analysis becomes essential. A comprehensive and automatic classification system is important to saving human lives. The geographical and anatomical heterogeneity of brain tumours makes automatic categorization challenging. This study proposes an automated method for detecting brain tumours using Convolutional Neural Networks (CNNs) classification, with the primary goal of developing a deep learning model that is capable of accurately identifying and classifying images as either having a brain tumour or not. In this paper, we provide a classification model for brain tumours based on a Deep Convolutional Neural Network with a vanilla neural network technique. The proposed method's performance on a publicly available dataset of 3000 Brain MRI Images yielded superior results, with accuracy and F1 score of 98.00 percent and 98.00 percent, respectively. This study shows that the proposed vanilla-CNN model can be used to make it easier for brain tumours to be automatically classified

Radio Signal Modulation Recognition Method Based on Hybrid Feature and Ensemble Learning: For Radar and Jamming Signals.

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method's performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning.

Optimal placement of light sensor for improving energy efficiency and visual comfort in smart buildings

The energy consumed by artificial lighting accounts for a significant part of the energy consumption in buildings. Thus, energy consumption can be significantly decreased using optimization techniques, such as the optimum placement of the lighting sensors. In this paper, an optimal placement method of the light sensors is presented to minimize the lighting system's equipment costs and energy consumption and also meet visual comfort under the requirements of the European standard EN12464–1 regarding illuminance-based criteria. In the beginning, based on the illumination measurement grid's mathematical model, the potential location of the sensors is determined. As an average of the dimming levels of the LED lights, the objective function has been introduced. Then, the illuminance and uniformity levels are defined as constraints for the optimization problem. The Battle Royale Optimization (BRO) algorithm is used to solve the optimization problem. Ultimately, based on the results of the BRO algorithm and the calculation of the illuminance deviation, the optimal location of the light sensors is determined. The proposed method is tested in an office room. A fuzzy logic controller is developed to regulate the lighting control system's dimming levels to evaluate the proposed method's performance with other approaches. The comparison results have shown that the proposed method is superior as regards the number of sensors and the optimal sensor position, significant savings in energy consumption of up to 30.8%, and satisfactory visual comfort per the requirements of the European standard EN12464–1.

An efficient hybrid technique for energy management system with renewable energy system and energy storage system in smart grid

This manuscript proposes a hybrid technique for an energy management system (EMS) with a renewable energy system and energy storage system using the smart micro grid. This work's novelty liesin the integration of Flying Foxes Optimization (FFO) algorithm and Deep Attention Dilated Residual Convolutional Neural Network (DADRCNN). Unlike existing methods, the FFO-DADRCNN method effectively leverages both optimization and predictive modelling capabilities to enhance grid stability, efficiency, and load prediction accuracy. The main goals of the proposed approach are to increase grid stability and efficiency, decrease micro grid system costs, and increase load prediction accuracy. The micro grid system incorporates PV, an energy storage system, wind turbine and load demand. To regulate the micro grid system and estimate load utilizing the DADRCNN most effectively, the proposed FFO technique is used. The proposed method's performance is evaluated using the MATLAB platform and compared with existing approaches, including Giza Pyramids Construction, Heap-based optimizer, and Nomadic People Optimizer. The proposed technique shows better outcomes when compared to other methods. Compared to other methods currently available, our proposed approach boasts an impressive 98 % efficiency rate and comes at a low operating cost of $1840.

Causal inference using multivariate generalized linear mixed-effects models.

Dynamic prediction of causal effects under different treatment regimens is an essential problem in precision medicine. It is challenging because the actual mechanisms of treatment assignment and effects are unknown in observational studies. We propose a multivariate generalized linear mixed-effects model and a Bayesian g-computation algorithm to calculate the posterior distribution of subgroup-specific intervention benefits of dynamic treatment regimes. Unmeasured time-invariant factors are included as subject-specific random effects in the assumed joint distribution of outcomes, time-varying confounders, and treatment assignments. We identify a sequential ignorability assumption conditional on treatment assignment heterogeneity, that is, analogous to balancing the latent treatment preference due to unmeasured time-invariant factors. We present a simulation study to assess the proposed method's performance. The method is applied to observational clinical data to investigate the efficacy of continuously using mycophenolate in different subgroups of scleroderma patients.

Effective Cancer Diagnosis through High-Dimensional Microarray Data Analysis by Integrating DCT and UFS

Cancer remains a global health challenge, with various types such as lung, breast, and colon cancer posing significant threats. Timely and accurate diagnosis is crucial for effective treatment and improved survival rates. Genetic research offers promising avenues in the fight against cancer, as identifying gene mutations and expression levels enables the development of targeted therapies and a deeper understanding of disease subtypes and progression. This study explores an innovative hybrid approach to enhance cancer diagnosis and classification. By combining Discrete Cosine Transformation (DCT) and Univariate Feature Selection (UFS) methods, the feature selection process is optimized for the dataset. The extracted features are then rigorously tested using established classifiers to assess their effectiveness in cancer classification. The proposed method's performance was evaluated using eight distinct datasets, and metrics such as MF1, K-score, and sensitivity were calculated and compared with various methods in the literature. Empirical evidence demonstrates that the proposed method outperforms others on 5 out of 8 datasets in terms of both accuracy and computational efficiency. The introduced method represents a reliable tool for cancer diagnosis and classification.

Integrated optimization of well placement and perforation layer selection using a modified dung beetle algorithm

In the oilfield development process, a proper well pattern plays a crucial role in improving oil recovery and economic benefits. However, traditional well pattern optimization mainly focuses on two-dimensional plane well placement, overlooking the spatial alignment of perforated layers and well placements. This oversight presents significant challenges, especially in meeting the demands for fine development of high water-cut oilfields. Therefore, this paper introduces an innovative approach to well pattern optimization, termed integrated well pattern optimization (WPO–I), which couples well placements with perforation positions. By maximizing net present value, a novel mathematical model for well pattern optimization is established, considering the location of infill wells, the status and type of existing wells, and the perforation position of working wells as co-optimization variables. Besides, an improved discrete dung beetle optimization (IDDBO) algorithm is developed, utilizing multi-layer integer coding and an opposition-based learning strategy. To evaluate the proposed method's performance, the Egg model is used to compare it with five optimization algorithms. Furthermore, this study assesses the development effects of conventional plane well placement optimization (WPO–P) compared to WPO-I. The results highlight the distinct advantages of the IDDBO algorithm in solving discrete nonlinear programming problems. Particularly, the WPO-I method enables spatial matching of the well pattern with reservoir heterogeneity and remaining oil distribution, effectively utilizing spatial residual oil. This method provides a new development optimization strategy in mature oilfields, especially for fine adjustment of well patterns during the secondary recovery stage of water flooding.

Applying matrix regularization to identification of traffic-induced equivalent loads and multi-vehicle weight on beam-like bridge

Identification of traffic-induced forces is an important topic in the field of bridge structural health monitoring (B-SHM). It can provide reliable data to support the great demand for monitoring and evaluating the working conditions of bridges. Bridges may serve under consistent moving vehicles and this requires that the methods of moving force identification (MFI) should be applicable under circumstances such as multiple-vehicle loading and long-term monitoring. Centering on cases containing multiple vehicles, this study proposed a matrix regularization-based method for the identification of traffic-induced equivalent loads and multi-vehicle weights. Herein, multiple moving forces in the spatial domain are converted into a certain number of equivalent loads which virtually act at fixed locations on the bridge as a kind of coordinate transformation. The MFI problem then can be transformed into tasks of identifying some concentrated forces. To solve the problem of equivalent load identification, the structural input-output relationship is firstly reorganized in a matrix-matrix-matrix form with the help of segmentation via time windows and consideration of unknown structural initial conditions. Then the matrix regularization with a sparse penalty term is introduced to formulate an identified equation so that, it can ensure the strong noise robustness of the identified results. Finally, the total weight of multiple vehicles can be empirically estimated from the sum of the identified equivalent loads. Numerical simulations and model experiments are performed to verify the proposed method's performance. The effects of vehicle speeds, measuring noise, number of modal orders, number of vehicles, and vehicle spacings are investigated. The illustrated results show that the proposed method turns out to be effective and precise in identifying the traffic-induced equivalent loads and the weight of multiple vehicles.

Denoising Autoencoder-Based Defensive Distillation as an Adversarial Robustness Algorithm Against Data Poisoning Attacks

Deep neural networks (DNNs) have demonstrated promising performances in handling complex real-world scenarios, surpassing human intelligence. Despite their exciting performances, DNNs are not robust against adversarial attacks. They are specifically vulnerable to data poisoning attacks where attackers meddle with the initial training data, despite the multiple defensive methods available, such as defensive distillation. However, defensive distillation has shown promising results in robustifying image classification deep learning (DL) models against adversarial attacks at the inference level, but they remain vulnerable to data poisoning attacks. This work incorporates a data denoising and reconstruction framework with a defensive distillation methodology to defend against such attacks. We leverage a denoising autoencoder (DAE) to develop a data reconstruction and filtering pipeline with a well-designed reconstruction threshold. We added carefully created adversarial examples to the initial training data to assess the proposed method's performance. Our experimental findings demonstrate that the proposed methodology significantly reduced the vulnerability of the defensive distillation framework to a data poison attack.

Performance evaluation of attention-deep hashing based medical image retrieval in brain MRI datasets

BackgroundBrain MRI images pose significant challenges due to their complexity and voluminous data, which often hinder the accuracy of traditional image retrieval methods. In response, this research delves into a novel medical image retrieval approach grounded in attention mechanisms and deep hashing techniques. MethodologyThe study enhances the network's edge perception capability by incorporating a dual mixed attention module (CBAM-MA dual attention) into the convolutional neural network architecture. This addition optimally captures edge saliency and distributional features by introducing an extra attention layer atop CBAM. Furthermore, a novel triple loss function is introduced, amalgamating Euclidean and cosine distances. This fusion exploits the strengths of both distance metrics to comprehensively consider sample geometric attributes, thereby generating more robust and expressive feature representations crucial for preserving categorical details. ResultsExperimental evaluations showcase significant performance advancements in MRI image retrieval tasks using the proposed method. The average hit rate stands at 0.7783, average precision at 0.752246, and average inverse rank at 0.956721. These metrics collectively underscore the method's efficacy in enhancing the quality and expediting the diagnosis of brain diseases. ConclusionThe research underscores the critical role of attention and deep hashing techniques in augmenting the accuracy and efficiency of medical image retrieval, particularly in the context of brain MRI images. The proposed method's notable performance improvements pave the way for enhanced diagnostic capabilities, signaling a significant step forward in improving healthcare outcomes related to brain diseases.