Memory Network Model Research Articles

Aided diagnosis of cervical spondylotic myelopathy using deep learning methods based on electroencephalography

Cervical spondylotic myelopathy (CSM) is the most severe type of cervical spondylosis. It is challenging to achieve early diagnosis with current clinical diagnostic tools. In this paper, we propose an end-to-end deep learning approach for early diagnosis of CSM. Electroencephalography (EEG) experiments were conducted with patients having spinal cord cervical spondylosis and age-matched normal subjects. A Convolutional Neural Network with Long Short-Term Memory Networks (CNN-LSTM) model was employed for the classification of patients versus normal individuals. In contrast, a Convolutional Neural Network with Bidirectional Long Short-Term Memory Networks and attention mechanism (CNN-BiLSTM-attention) model was used to classify regular, mild, and severe patients. The models were trained using focal Loss instead of traditional cross-entropy Loss, and cross-validation was performed. Our method achieved a classification accuracy of 92.5 % for the two-class classification among 40 subjects and 72.2 % for the three-class classification among 36 subjects. Furthermore, we observed that the proposed model outperformed traditional EEG decoding models. This paper presents an effective computer-aided diagnosis method that eliminates the need for manual extraction of EEG features and holds potential for future auxiliary diagnosis of spinal cord-type cervical spondylosis.

An Intrusion Detection Method Based on Attention Mechanism to Improve CNN-BiLSTM Model

Abstract Security of computer information can be improved with the use of a network intrusion detection system. Since the network environment is becoming more complex, more and more new methods of attacking the network have emerged, making the original intrusion detection methods ineffective. Increased network activity also causes intrusion detection systems to identify errors more frequently. We suggest a new intrusion detection technique in this research that combines a Convolutional Neural Network (CNN) model with a Bi-directional Long Short-term Memory Network (BiLSTM) model for adding attention mechanisms. We distinguish our model from existing methods in three ways. First, we use the NCR-SMOTE algorithm to resample the dataset. Secondly, we use recursive feature elimination method based on extreme random tree to select features. Thirdly, we improve the profitability and accuracy of predictions by adding attention mechanism to CNN-BiLSTM. This experiment uses UNSW-UB15 dataset composed of real traffic, and the accuracy rate of multi-classification is 84.5$\%$; the accuracy rate of multi-classification in CSE-IC-IDS2018 dataset reached 98.3$\%$.

Deep learning-based sleep stage classification with cardiorespiratory and body movement activities in individuals with suspected sleep disorders

Deep learning methods have gained significant attention in sleep science. This study aimed to assess the performance of a deep learning-based sleep stage classification model constructed using fewer physiological parameters derived from cardiorespiratory and body movement data. Overnight polysomnography (PSG) data from 123 participants (age: 19–82 years) with suspected sleep disorders were analyzed. Multivariate time series data, including heart rate, respiratory rate, cardiorespiratory coupling, and body movement frequency, were input into a bidirectional long short-term memory (biLSTM) network model to train and predict five-class sleep stages. The trained model's performance was evaluated using balanced accuracy, Cohen's κ coefficient, and F1 scores on an epoch-per-epoch basis and compared with the ground truth using the leave-one-out cross-validation scheme. The model achieved an accuracy of 71.2 ± 5.8%, Cohen's κ of 0.425 ± 0.115, and an F1 score of 0.650 ± 0.083 across all sleep stages, and all metrics were negatively correlated with the apnea–hypopnea index, as well as age, but positively correlated with sleep efficiency. Moreover, the model performance varied for each sleep stage, with the highest F1 score observed for N2 and the lowest for N3. Regression and Bland–Altman analyses between sleep parameters of interest derived from deep learning and PSG showed substantial correlations (r = 0.33–0.60) with low bias. The findings demonstrate the efficacy of the biLSTM deep learning model in accurately classifying sleep stages and in estimating sleep parameters for sleep structure analysis using a reduced set of physiological parameters. The current model without using EEG information may expand the application of unobtrusive in-home monitoring to clinically assess the prevalence of sleep disorders outside of a sleep laboratory.

A hybrid model for deep learning short-term power load forecasting based on feature extraction statistics techniques

Accurate and reliable load forecasting can ensure the safety and economy of power system operation. To improve the accuracy of short-term power load forecasting, this paper adopts feature extraction combined with a variety of machine learning methods,(Empirical wavelet decomposition (EWT), Convolutional neural network (CNN) model, Recurrent neural network (RNN) model, Long short-term memory network (LSTM) model, Bayesian optimization (BOA) algorithm). A new hybrid forecasting model, the EWT-CNN-S-RNN + LSTM model is proposed to predict power consumption. In this method, the fixed mode of EWT decomposition is used to extract statistical features, and the LSTM/RNN model is selected according to the statistical features. This method uses the Bayesian optimization (BOA) algorithm to optimize the parameters to solve the model gradient explosion problem. Based on the electricity consumption data of 2007 (Australian Energy Market Operator) and a total of 336 power load data, a good load forecasting result is obtained, which can provide indirect support for power regulation and sustainable development of electricity.

Online Intention Recognition With Incomplete Information Based on a Weighted Contrastive Predictive Coding Model in Wargame.

The incomplete and imperfect essence of the battlefield situation results in a challenge to the efficiency, stability, and reliability of traditional intention recognition methods. For this problem, we propose a deep learning architecture that consists of a contrastive predictive coding (CPC) model, a variable-length long short-term memory network (LSTM) model, and an attention weight allocator for online intention recognition with incomplete information in wargame (W-CPCLSTM). First, based on the typical characteristics of intelligence data, a CPC model is designed to capture more global structures from limited battlefield information. Then, a variable-length LSTM model is employed to classify the learned representations into predefined intention categories. Next, a weighted approach to the training attention of CPC and LSTM is introduced to allow for the stability of the model. Finally, performance evaluation and application analysis of the proposed model for the online intention recognition task were carried out based on four different degrees of detection information and a perfect situation of ideal conditions in a wargame. Besides, we explored the effect of different lengths of intelligence data on recognition performance and gave application examples of the proposed model to a wargame platform. The simulation results demonstrate that our method not only contributes to the growth of recognition stability, but it also improves recognition accuracy by 7%-11%, 3%-7%, 3%-13%, and 3%-7%, the recognition speed by 6-32x, 4-18x, 13-*x, and 1-6x compared with the traditional LSTM, classical FCN, OctConv, and OctFCN models, respectively, which characterizes it as a promising reference tool for command decision-making.

Detecting surface discharge faults in switchgear by using hybrid model

<span>Switchgear plays a crucial role in power systems, providing protection and control over electrical equipment. However, tracking (surface discharge) can lead to insulation degradation and switchgear failure, necessitating reliable and effective identification of tracking defects. In this paper, we propose a hybrid one-dimension convolutional neural network long short-term memory networks (1D-CNN-LSTM) model as a solution to this problem. Data from both time domain analysis (TDA) and frequency domain analysis (FDA) are utilized for model evaluation. The model achieved error-free accuracy of 100% in both TDA and FDA during the training, validation, and testing phases. The model's performance is further assessed using performance measures and the visualization of accuracy and loss curves. The results show that the hybrid 1D-CNN-LSTM model works well to accurately find and classify surface discharge tracking defects in switchgear. The model offers precise and dependable fault identification, which has the potential to significantly enhance switchgear functionality. By enabling proactive maintenance and timely intervention, the proposed model contributes to the overall reliability and performance of switchgear in power systems. The findings of this research provide valuable insights for the design and implementation of advanced fault detection systems in switchgear applications.</span>

Exploring effective methods for automated essay scoring of non-native speakers

Automated essay scoring (AES) has become a valuable tool in educational settings, providing efficient and objective evaluations of student essays. However, the majority of AES systems have primarily focused on native English speakers, leaving a critical gap in the evaluation of non-native speakers’ writing skills. This research addresses this gap by exploring the effectiveness of automated essay-scoring methods specifically designed for non-native speakers. The study acknowledges the unique challenges posed by variations in language proficiency, cultural differences, and linguistic complexities when assessing non-native speakers’ writing abilities. This work focuses on the automated student assessment prize and Khon Kaen University academic English language test dataset and presents an approach that leverages variants of the long short-term memory network model to learn features and compare results with the Kappa coefficient. The findings demonstrate that the proposed framework and approach, which involve joint learning of different essay representations, yield significant benefits and achieve results comparable to state-of-the-art deep learning models. These results suggest that the novel text representation proposed in this paper holds promise as a new and effective choice for assessing the writing tasks of non-native speakers. The result of this study can apply to advance educational assessment practices and promote equitable opportunities for language learners worldwide by enhancing the evaluation process for non-native speakers

Prediction of Anatomical Presentation during Radiotherapy of Nasopharyngeal Carcinoma Using GAN-LSTM for Plan Adaption Decision

During treatment, patients frequently undergo anatomical changes that might result in dose degradation. Adaptive radiation therapy (ART) is now available to overcome this problem. However, this method is time-consuming, and the lack of criteria to trigger replanning prevents its widespread use. To overcome these obstacles, anatomical presentation models are necessary. In this study, we developed a novel deep-learning method to make a series of predictions for the remaining treatment course. Total 230 nasopharyngeal carcinoma patients who received radiotherapy in 33 fractions were enrolled. The data included cone-beam computed tomography (CBCT) and planning CT images. CBCT image quality was improved to CT level using an in-house software. A generative adversarial network-long short-term memory network model was proposed, with the generation abilities of the former network and forecasting abilities of the latter. To predict the anatomical presentation for 3-6 weeks, we trained four models. The planning CT and CBCT acquired earlier were used as the input. Physicians segmented the gross target volume (GTVnx) and parotid glands on prediction and real CBCT (ground truth). Contours, dosimetry parameters, and plan adaptation decision were used to evaluate the models. The table shows the overall performance of the test set (18 cases). The anatomical changes were predicted over the treatment course with a dice similarity coefficient (DSC) of 0.96, 0.90 and 0.92 and mean distance to agreement (MDA, in mm) of 0.37, 0.70, and 0.60 for GTVnx, left parotid, and right parotid, respectively. Bland-Altman analysis revealed that dosimetry parameters did not show significant difference between prediction and ground truth. The prescription coverage (%) of GTVnx, V30 of the left parotid, and V30 of the right parotid had mean absolute biases of 0.09, 1.09, and 0.27, respectively. At week 6, there were two cases that required plan adaptation, and the model effectively triggered replanning one week in advance. We developed a framework that predicts the anatomical changes occurring in future fractions. Establishing such a framework provides a proactive approach to ART and saves clinical time by anticipating and preparing for treatment strategies in advance.

Construction of a Hierarchical Organization in Semantic Memory: A Model Based on Neural Masses and Gamma-Band Synchronization

Semantic memory is characterized by a hierarchical organization of concepts based on shared properties. However, this aspect is insufficiently dealt with in recent neurocomputational models. Moreover, in many cognitive problems that exploit semantic memory, gamma-band synchronization can be relevant in favoring information processing and feature binding. In this work, we propose an attractor network model of semantic memory. Each computational unit, coding for a different feature, is described with a neural mass circuit oscillating in the gamma range. The model is trained with an original nonsymmetric Hebb rule based on a presynaptic gating mechanism. After training, the network creates a taxonomy of categories, distinguishes between subordinate and superordinate concepts, and discriminates between salient and marginal features. Examples are provided concerning a fourteen-animal taxonomy, including several subcategories. A sensitivity analysis reveals the robustness of the network but also points out conditions leading to confusion among categories, similar to the one observed in dreaming and some neurological disorders. Finally, the analysis emphasizes the role of fast GABAergic interneurons and inhibitory-excitatory balance to allow the correct synchronization of features. The model represents an original attempt to deal with a hierarchical organization of objects in semantic memory and correlated patterns, still exploiting gamma-band synchronization to favor neural processing. The same ideas, introduced in a more sophisticated multilayer network, can deepen our knowledge of semantic memory organization in the brain. Finally, they can open new perspectives in quantitatively analyzing neurological disorders connected with distorted semantics.

Short-Term Power Demand Forecasting Using Blockchain-Based Neural Networks Models

With the rapid development of blockchain technology, blockchain-based neural network short-term power demand forecasting has become a research hot spot in the power industry. This paper aims to combine neural network algorithms with blockchain technology to establish a trustworthy and efficient short-term demand forecasting model. By leveraging the distributed ledger and immutability features of blockchain, we ensure the security and reliability of power demand data. Meanwhile, short-term power demand forecasting research using neural networks has the potential to increase the stability of the power system and offer opportunities for improved operations. In this paper, the root mean-square-error model evaluation indicator was used to compare the back propagation (BP) neural network algorithm and the traditional forecasting algorithm. The evaluation was performed on the randomly selected five household power datasets. The results show that, by comparing the long short-term memory network (LSTM) model with the BP neural network model, it was determined that the average prediction impact increases by about 25.7% under stable power demand. The short-term power prediction model of the BP neural network has the average error values more than two times lower than the traditional prediction model. It was shown that the use of the BP neural network algorithm and blockchain could increase the accuracy of short-term power demand forecasting, allowing the neural network-based algorithm to be implemented and taken into account in the research on short-term power demand forecasting.

A Data-Driven Approach for Fatigue Detection during Running Using Pedobarographic Measurements.

Detecting fatigue at the early stages of a run could aid training programs in making adjustments, thereby reducing the heightened risk of injuries from overuse. The study aimed to investigate the effects of running fatigue on plantar force distribution in the dominant and nondominant feet of amateur runners. Thirty amateur runners were recruited for this study. Bilateral time-series plantar forces were employed to facilitate automatic fatigue gait recognition using convolutional neural network (CNN) and CNN-based long short-term memory network (ConvLSTM) models. Plantar force data collection was conducted both before and after a running-induced fatigue protocol using a FootScan force plate. The Keras library in Python 3.8.8 was used to train and tune deep learning models. The results demonstrated that more mid-forefoot and heel force occurs during bilateral plantar and less midfoot fore force occurs in the dominant limb after fatigue (p < 0.001). The time of peak forces was significantly shortened at the midfoot and sum region of the nondominant foot, while it was delayed at the hallux region of the dominant foot (p < 0.001). In addition, the ConvLSTM model showed higher performance (Accuracy = 0.867, Sensitivity = 0.874, and Specificity = 0.859) in detecting fatigue gait than CNN (Accuracy = 0.800, Sensitivity = 0.874, and Specificity = 0.718). The findings of this study could offer empirical data for evaluating risk factors linked to overuse injuries in a single limb, as well as facilitate early detection of fatigued gait.

Establishing a Berry Sensory Evaluation Model Based on Machine Learning.

In recent years, people's quality of life has increased, and the requirements for fruits have also become higher; blueberries are particularly popular because of their rich nutrients. In the blueberry industry chain, sensory evaluation is an important link in determining the quality of blueberries. Therefore, to make a more objective scientific evaluation of blueberry quality and reduce the influence of human factors, on the basis of traditional sensory evaluation methods, machine learning is introduced to establish a support vector regression prediction model optimized by the particle swarm algorithm. Ten physical and chemical flavor indices of blueberries (such as catalase, flavonoids, and soluble solids) were used as input data, and sensory evaluation scores were used as output data. Three different predictive models were applied and compared: a particle swarm optimization support vector machine, a convolutional neural network, and a long short-term memory network model. To ensure reliability, the experiments with each of the three models were repeated 20 times, and the mean of each index was calculated. The experimental results showed that the root mean square error and mean absolute error of the particle swarm optimization support vector machine were 0.45 and 0.40, respectively; these values were lower than those of the convolutional neural network (0.96 and 0.78, respectively) and the long short-term memory network (1.22 and 0.97, respectively). Hence, these results highlighted the superiority of the proposed model when sample data are limited.

The dilemma and the way out of the construction of the law profession in the context of new liberal arts based on an intelligent legal learning system

Abstract Due to society’s practical demands, the legal profession’s growth within the context of the new liberal arts is necessary to improve teaching mechanisms and the comprehensive development of interdisciplinarity. In this paper, from the two major dilemmas of the specificity of legal instruments and the correlation between sentencing tasks, to examine the relationship between sentencing prediction, charge prediction, and law suggestion of legal instruments, respectively, the Bi-LSTM-attention model, end-to-end memory network model, and CNN-GRU network model are employed, to build an intelligent legal learning system. The outcomes demonstrate that, compared to the conventional machine learning algorithm, the intelligent legal learning system based on deep learning can increase prediction performance by 5.2% to 6%, global accuracy can reach 93.3%, and accuracy of legal documents processing by 7.9%. The deep learning-based intelligent legal learning system suggested in this study can assist law students in completing legal paperwork duties and increase their learning effectiveness.

Aircraft parameter estimation using a stacked long short-term memory network and Levenberg-Marquardt method

To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data, this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory (LSTM) network model and the Levenberg-Marquardt (LM) method. The stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input–output data of the aircraft system without requiring explicit postulation of the dynamics. The LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic parameters. The proposed method is applied by using the real flight data, generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle (UAV). The investigation reveals that for the two different flight data, the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters (i.e., the initial weights, initial biases, number of hidden cells, time-steps, learning rate, and number of training iterations). Besides, the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.

Privacy-Preserving Electricity Theft Detection Based on Blockchain

In most electricity theft detection schemes, consumers’ power consumption data is directly input into the detection center. Although it is valid in detecting the theft of consumers, the privacy of all consumers is at risk unless the detection center is assumed to be trusted. In fact, it is impractical. Moreover, existing schemes may result in some security problems, such as the collusion attack due to the presence of a trusted third party, and malicious data tampering caused by the system operator (SO) being attacked. Aiming at the problems above, we propose a blockchain-based privacy-preserving electricity theft detection scheme without a third party. Specifically, the proposed scheme uses an improved functional encryption scheme to enable electricity theft detection and load monitoring while preserving consumers’ privacy; distributed storage of consumers’ data with blockchain to resolve security problems such as data tampering, etc. Meanwhile, we build a long short-term memory network (LSTM) model to perform higher accuracy for electricity theft detection. The proposed scheme is evaluated in a real environment, and the results show that it is more accurate in electricity theft detection within acceptable communication and computational overhead. Our system analysis demonstrates that the proposed scheme can resist various security attacks and preserve consumers’ privacy.

Data-driven methods for situation awareness and operational adjustment of sustainable energy integration into power systems

In the context of increasing complexity in power system operations due to the integration of renewable energy sources, two main challenges arise: accurate short-term wind power forecasting and power flow convergence control. Accurate wind power forecasting plays a crucial role in power system scheduling, while controlling power flow convergence is essential for system stability. This study proposes a concise short-term wind power generation prediction model that combines a feature selection-based convolutional neural network-bidirectional long short-term memory network (CNN-BiLSTM) model. By effectively screening multidimensional feature datasets, the model optimizes the selection of highly correlated feature parameters and assigns weights to input data based on feature correlation. The CNN-BiLSTM combination model is then employed to establish a predictive model for wind power generation based on multiple features. Additionally, this study introduces an automatic adjustment model for power flow convergence using the D3QN (Double Dueling Q Network) reinforcement learning algorithm. This addresses the challenge of power imbalance leading to flow non-convergence, enabling effective control of power flow convergence and adaptive adjustment of operating modes. Experiments conducted using the KDD Cup 2022 wind power prediction dataset validate the wind power prediction method. The results demonstrate that the CNN-BiLSTM model effectively utilizes time-series data, surpassing other neural networks in prediction accuracy. Simulation results based on the PYPOWER case39 standard case reveal that the reinforcement learning model’s reward value increases with training rounds and stabilizes at 40. Remarkably, more than 72% of abnormal flow samples achieve rapid convergence within 10 steps, affirming the proposed method's efficacy and computational efficiency. The findings of this study contribute to enhancing the accurate awareness of new energy integration into power systems and provide a novel adaptive control method for power flow.

Exploring English-Chinese Translation Skills Based on Big Data Technology

Abstract This paper first explores and evaluates English-Chinese translation skills through deep learning in machine learning based on big data technology, focusing on applying convolutional neural networks and long and short-term memory network models in English-Chinese translation. Then it is to construct a deep learning evaluation model based on the dataset with text-level labels of English-Chinese translation. The structure of the deep learning evaluation model consists of three categories: data representation of text, feature extraction of text, and text classifier. Finally, the research object is determined from the purpose of the study, and the data analysis is performed on the experimental and control groups using the deep learning model to characterize the fluency by the continuous convergence of the data. The results showed that the continuous convergence of the experimental group remained in the range of 76.95% to 82.6%, and its average value was 79.76%. The continuous convergence of the control group remained in the range of 60.15% to 71.92%, with a mean value of 67.02%. The average convergence value of the experimental group was 12.74% higher than that of the control group, and the experimental group outperformed the control group. This study should learn and cultivate English-Chinese translation skills while improving the efficiency and accuracy of English-Chinese translation, which is a guiding reference value for the progress of translation talents.

Machine learning-based predictive control using on-line model linearization: Application to an experimental electrochemical reactor

The electrochemical reaction-based process, a new type of chemical process that can generate valuable products using renewable electricity, is a sustainable alternative to the traditional chemical manufacturing processes. One promising research area of electrochemical reaction processing is to reduce carbon dioxide (CO2) into carbon-based products, which can contribute to closing the carbon cycle if CO2 is directly captured from the atmosphere. In this work, we demonstrate a model predictive control (MPC) scheme that uses a neural network (NN) model as the process model to implement real-time multi-input-multi-output (MIMO) control in an electrochemical reactor for CO2 reduction. Specifically, a long short-term memory network (LSTM) model is developed using historical experimental data of the electrochemical reactor to capture the nonlinear input-output relationship as an alternative to the complex, first principles-based model. Furthermore, the Koopman operator method is used to linearize the LSTM model to reduce the nonlinear optimization step in the MPC to a well-understood and easy-to-solve quadratic programming (QP) problem. The performance of the LSTM model, Koopman-based optimization, and MPC using the linearization of the LSTM model are evaluated with various simulations as well as open-loop and closed-loop experiments. As the results, the proposed MPC scheme can drive the two output states, that are concentrations of the products (C2H4 and CO), to their desired setpoints by computing optimal input variables (surface potential and electrode rotation speed) in real-time in closed-loop experiments. Furthermore, a transfer learning-based method is utilized to update the NN model to handle process variability.

An LSTM based cross-site scripting attack detection scheme for Cloud Computing environments

Cloud Computing plays a pivotal role in facilitating the Internet of Things (IoT) and its diverse applications. Users frequently access and store data on remote servers in Cloud Computing environments through web browsers. Consequently, attackers may exploit vulnerabilities in web browsing to embed malicious code into web pages, enabling them to launch attacks on remote servers in Cloud Computing environments. Due to its complexity, prevalence, and significant impact, XSS has consistently been recognized as one of the top ten web security vulnerabilities by OWASP. The existing XSS detection technology requires optimization: manual feature extraction is time-consuming and heavily reliant on domain knowledge, while the current confusion technology and complex code logic contribute to a decline in the identification of XSS attacks. This paper proposes a character-level bidirectional long-term and short-term memory network model based on a multi-attention mechanism. The bidirectional long-term and short-term memory network ensures the association of current features with preceding and subsequent text, while the multi-attention mechanism extracts additional features from different feature subspaces to enhance the understanding of text semantics. Experimental results demonstrate the effectiveness of the proposed model for XSS detection, with an F1 score of 98.71%.

Long Short-Term Memory and Attention Models for Simulating Urban Densification

This paper introduces a novel cellular automata model that combines Long Short-Term Memory, Attention, and Neural Network models to capture spatio-temporal Land Use Change (LUC) behaviors while addressing the challenge of imbalanced datasets. The proposed method is developed and validated using data from Belgium, defined as three (100x100) m raster-based built-up maps for 2000, 2010, and 2020. The model is trained and validated using data from 2000 to 2010, and its effectiveness is tested using data from 2010 to 2020. The key contribution of our approach lies in its ability to tackle long-term temporal dependency and class imbalance problems in LUC science. Our proposed method significantly enhances the performance of spatio-temporal LUC simulation. Additionally, we adopt a data splitting strategy that takes into account the different transitions between classes, improving the accuracy of the model predictions of minority class. The obtained results demonstrate the efficiency of the proposed model in capturing complex spatio-temporal dynamics and reducing the impact of imbalanced datasets surpassing existing methods. The implications of our study extend beyond LUC modeling, as the proposed approach can be applied to a wide range of applications where machine learning is used to model complex environmental and geographical phenomena.