Performance Of Hybrid Model Research Articles

Highly Imbalanced Classification of Gout Using Data Resampling and Ensemble Method

Gout is one of the most painful diseases in the world. Accurate classification of gout is crucial for diagnosis and treatment which can potentially save lives. However, the current methods for classifying gout periods have demonstrated poor performance and have received little attention. This is due to a significant data imbalance problem that affects the learning attention for the majority and minority classes. To overcome this problem, a resampling method called ENaNSMOTE-Tomek link is proposed. It uses extended natural neighbors to generate samples that fall within the minority class and then applies the Tomek link technique to eliminate instances that contribute to noise. The model combines the ensemble ’bagging’ technique with the proposed resampling technique to improve the quality of generated samples. The performance of individual classifiers and hybrid models on an imbalanced gout dataset taken from the electronic medical records of a hospital is evaluated. The results of the classification demonstrate that the proposed strategy is more accurate than some imbalanced gout diagnosis techniques, with an accuracy of 80.87% and an AUC of 87.10%. This indicates that the proposed algorithm can alleviate the problems caused by imbalanced gout data and help experts better diagnose their patients.

Macroscopic modeling of mixed bi-modal urban networks: A hybrid model of accumulation- and trip-based principles

Network-level traffic flow models either assume steady-state urban flows (i.e. accumulation-based models) or track the movement of all vehicles (i.e. trip-based models). The steady-state assumption present in the accumulation-based models may pose a challenge in light of the multi-modal nature of urban flows. It might be indeed a rough assumption for the flow of some transportation modes like buses, cruising-for-parking vehicles, taxis, and on-demand vehicles. Trip-based models address this concern, however, they need significant parameter calibration effort and are not computationally efficient, which substantially reduces the practicality of these models in real-world applications. Nevertheless, despite the critical importance of developing multi-modal traffic flow models, few attempts have been made to investigate these models in network macroscopic fundamental diagram (NMFD)-related literature. This paper bridges this gap by developing a hybrid network-level traffic flow model for mixed bi-modal (i.e. car and bus) networks. The present hybrid model reproduces the dynamics of car flows via accumulation-based model principles while tracking the movement of buses using the trip-based model. This effort also includes the development of a new FIFO-based entrance function to ensure different modes experience the same delay under saturated traffic conditions. Different numerical experiments are conducted to study the hybrid model performance and to compare it with that of accumulation-based and trip-based models in both steady-state and transition periods under different traffic conditions. Our observations reveal that the hybrid model simulates the dynamics of cars and buses by closely following the behavior of its components under free-flow conditions. The model also outperforms the accumulation-based model under saturated traffic conditions while being considerably less demanding than the trip-based model. A further investigation of the model performance is performed for networks with different bus shares in both free-flow and saturated traffic conditions, confirming the results of the initial numerical experiments. The hybrid model’s computational efficiency is demonstrated. The potential real-world applications of the hybrid model in development of bi-modal network-level simulation models, NMFD-based control strategies along with bus space allocation policies, public transport operation problems, modeling of cruising-for-parking vehicles, taxis, and on-demand vehicles, and modeling and application of autonomous modular vehicles are discussed and future research directions are highlighted.

Optimal Feature Selection from High-dimensional Microarray Dataset Employing Hybrid IG-Jaya Model

Background: Feature selection (FS) is a crucial strategy for dimensionality reduction in data preprocessing since microarray data sets typically contain redundant and extraneous features that degrade the performance and complexity of classification models. Objective: The purpose of feature selection is to reduce the number of features from highdimensional cancer datasets and enhance classification accuracy. Methods: This research provides a wrapper-based hybrid model integrating information gain (IG) and Jaya algorithm (JA) for determining the optimum featured genes from high-dimensional microarray datasets. This paper's comprehensive study is divided into two segments: we employed the parameterless JA to identify the featured gene subsets in the first stage without filter methods. Various classifiers evaluate JA's performance, such as SVM, LDA, NB, and DT. In the second section, we introduce a hybrid IG-JA model. The IG is used as a filter to eliminate redundant and noisy features. The reduced feature subset is then given to the JA as a wrapper to improve the hybrid model's performance using the classifiers outlined above. Results: We used 13 benchmark microarray data sets from the public repository for experimental analysis. It is noteworthy to state that the hybrid IG-JA model performs better as compared to its counterparts. Conclusion: Tests and statistics show that the suggested model outperforms the standard feature selection method with JA and other existing models. Our proposed model is unable to provide the best accuracy compared to other existing approaches; however, it is quite steady and good. In the future, this work could be implemented with various filter methods and real-time data sets. A multi-filter approach with the Jaya algorithm will be used to check the efficiency of the proposed one. And it would be better to choose any other hybrid model (chaos-based) with Jaya to enhance the feature selection accuracy with a high dimensional dataset.

Superior performance of hybrid model in ungauged basins for real-time hourly water level forecasting – A case study on the Lancang-Mekong mainstream

In the context of climate change and human influence, timely and reliable information about water level variations is crucial for downstream flood control, navigation, and water resource management, particularly for the Lancang-Mekong River, the largest transboundary river in Southeast Asia. However, accurate real-time water level forecasts remain challenging, especially in data-limited regions. This study focused on the Chiang Saen Station, the uppermost Mekong River hydrological station, comparing three methods to predict 48-hour water levels: the Variable Infiltration Capacity (VIC) and Hydrology-Hydraulic (HH) physics-based models, the Gated Recurrent Unit (GRU) model, and hybrid models (VIC-GRU and HH-GRU). Evaluations were conducted at the 1-h, 3-h, 6-h, 12-h, 24-h, and 48-h forecast lead times. Assessments at various lead times showed that hybrid models incorporating physics-based mechanisms significantly enhanced predictions. VIC-GRU demonstrated superior performance, with KGE values surpassing 0.94, NSE values exceeding 0.95, MAE below 0.17 m, and PBIAS within ± 1 % across all lead times. Compared to GRU, PBIAS decreased by 84 %, while MAE dropped by 76 % to 81 % relative to VIC and HH, respectively. Notably, seasonal variations affected hybrid model performance, especially in the dry season. Optimal parameter selections enhanced model accuracy by 48 % to 49 %. These results underscore the potential of combining physics-based and deep learning models for more accurate, high-temporal-resolution real-time water level forecasts in data-scarce regions. A comprehensive study of streamflow characteristics enhances the advantages of this integration. This research contributes valuable insights to water level prediction in data-scarce regions and informs flood risk reduction and management in the Lancang-Mekong mainstream.

Reserching performance of the Dubins machine hybrid model with single separation of control objects

The problem of the performance of a hybrid system, which the number of control objects changes during the operation is considered. One control object (carrier) begins to move. At some point in time, several moving objects are separated from it and sent to specified terminal states (targets). The carrier is represented by a hybrid model of the Dubins machine, allowing trajectories of unlimited curvature. The movement of separated objects is rectilinear with limited speeds and accelerations. The problem of minimizing the time to achieve all goals is solved.

Improving pixel-based regional landslide susceptibility mapping

Regional landslide susceptibility mapping (LSM) is essential for risk mitigation. While deep learning algorithms are increasingly used in LSM, their extensive parameters and scarce labels (limited landslide records) pose training challenges. In contrast, classical statistical algorithms, with typically fewer parameters, are less likely to overfit, easier to train, and offer greater interpretability. Additionally, integrating physics-based and data-driven approaches can potentially improve LSM. This paper makes several contributions to enhance the practicality, interpretability, and cross-regional generalization ability of regional LSM models: (1) Two new hybrid models, composed of data-driven and physics-based modules, are proposed and compared. Hybrid Model I combines the infinite slope stability analysis (ISSA) with logistic regression, a classical statistical algorithm. Hybrid Model II integrates ISSA with a convolutional neural network, a representative of deep learning techniques. The physics-based module constructs a new explanatory factor with higher nonlinearity and reduces prediction uncertainty caused by incomplete landslide inventory by pre-selecting non-landslide samples. The data-driven module captures the relation between explanatory factors and landslide inventory. (2) A step-wise deletion process is proposed to assess the importance of explanatory factors and identify the minimum necessary factors required to maintain satisfactory model performance. (3) Single-pixel and local-area samples are compared to understand the effect of pixel spatial neighborhood. (4) The impact of nonlinearity in data-driven algorithms on hybrid model performance is explored. Typical landslide-prone regions in the Three Gorges Reservoir, China, are used as the study area. The results show that, in the testing region, by using local-area samples to account for pixel spatial neighborhoods, Hybrid Model I achieves roughly a 4.2% increase in the AUC. Furthermore, models with 30 m resolution land-cover data surpass those using 1000 m resolution data, showing a 5.5% improvement in AUC. The optimal set of explanatory factors includes elevation, land-cover type, and safety factor. These findings reveal the key elements to enhance regional LSM, offering valuable insights for LSM practices.

Applying machine learning techniques in the form of ensemble and hybrid models to appraise hardness properties of high-performance concrete

Accurately estimating concrete mechanical parameters using artificial intelligence-based methods can save time and energy. Existing nonlinear relationships between concrete components have entered uncertainty in the estimation of hardness properties of the slump and compressive strength as one of the most important parameters in concrete design. Employing regular approaches to use AI models individually in estimating dependent variables has been adopted in many studies. Therefore, the current study has aimed to develop predictive models in two categories of ensemble and hybrid frameworks to predict the hardness properties of high-performance concrete (HPC). In this regard, models based on Support Vector Regression, Decision Tree, and AdaBoost Machine learning were coupled with a metaheuristic optimization algorithm Chaos game optimizer (CGO). Linking three predictive models as well as tuning their internal settings via optimization algorithm could generate various types of hybrid and ensemble models. By assessing the results of the proposed models for compressive strength, the performance of ADA-CGO hybrid models was calculated higher than the ensemble model of SVR-ADA-DT, with 1.22% and 166% percent difference in terms of R2 and RMSE, respectively. Also, for predicting Slump, other hybrid models appeared with weaker performance than the ensemble model, with an average difference of 40.66% in terms of the MAE index. Generally, using advanced types of individual models, including ensemble and hybrid, indicated boosted performance accompanied by low-cost modeling processes.

A hybrid neural network approach for classifying diabetic retinopathy subtypes.

Diabetic retinopathy is a prevalent complication among diabetic patients that, if not predicted and treated promptly, can lead to blindness. This paper proposes a method for accurately and swiftly predicting the degree of diabetic retinopathy using a hybrid neural network model. Timely prediction of diabetic retinopathy is crucial in preventing blindness associated with this condition. This study aims to enhance the prediction accuracy of diabetic retinopathy by utilizing the hybrid neural network model EfficientNet and Swin Transformer. The specific methodology includes: (1) combining local and global features to accurately capture lesion characteristics by leveraging the strengths of both Swin Transformer and EfficientNet models; (2) improving prediction accuracy through a comprehensive analysis of the model's training details and applying data augmentation techniques such as Gaussian blur to enhance the hybrid model's performance; (3) validating the effectiveness and utility of the proposed hybrid model for diabetic retinopathy detection through extensive experimental evaluations and comparisons with other deep learning models. The hybrid model was trained and tested on the large-scale real-world diabetic retinopathy detection dataset APTOS 2019 Blindness Detection. The experimental results show that the hybrid model in this paper achieves the best results in all metrics, including sensitivity of 0.95, specificity of 0.98, accuracy of 0.97, and AUC of 0.97. The performance of the model is significantly improved compared to the mainstream methods currently employed. In addition, the model provides interpretable neural network details through class activation maps, which enables the visualization of diabetic retinopathy. This feature helps physicians to make more accurate diagnosis and treatment decisions. The model proposed in this paper shows higher accuracy in detecting and diagnosing diabetic retinopathy, which is crucial for the treatment and rehabilitation of diabetic patients. The hybrid neural network model based on EfficientNet and Swin Transformer significantly contributes to the prediction of diabetic retinopathy. By combining local and global features, the model achieves improved prediction accuracy. The validity and utility of the model are verified through experimental evaluations. This research provides robust support for the early diagnosis and treatment of diabetic patients.

Modeling transpiration using solar-induced chlorophyll fluorescence and photochemical reflectance index synergistically in a closed-canopy winter wheat ecosystem

The joint use of solar-induced chlorophyll fluorescence (SIF) and the photochemical reflectance index (PRI) has been shown to improve gross primary productivity (GPP) estimation across various plant functional types. However, the utility of PRI in combination with SIF for transpiration (T) estimation has not yet been explored. Additionally, current SIF-driven transpiration models including linear models, semi-mechanical models (combination of canopy conductance, gC, derived from a SIF and vapor pressure deficit, VPD, driven linear model with the Penman-Monteith model), and hybrid models (combination of gC derived from a SIF and VPD driven machine learning model with the Penman-Monteith model) have rarely been mutually assessed. Based on concurrent remotely sensed SIF and PRI, and eddy covariance flux measurements during one growing season for a winter wheat ecosystem in northern China, we investigated the mediating effect of PRI on SIF-driven T estimation under different VPD conditions and compared the performance of linear, semi-mechanical, and hybrid models in estimating T. Our results showed that the mediating effect of PRI on T described in the SIF-driven linear, semi-mechanistic, and hybrid models was significant under high VPD conditions rather than under low VPD conditions. Specifically, based on T partitioned using an underlying water use efficiency method as a benchmark, the root mean square error (RMSE) value of the PRI-mediated linear, semi-mechanistic, and hybrid models was 28.01 W/m2, 22.25 W/m2, and 28.71 W/m2 lower, respectively, than those of the corresponding models without PRI when VPD was >1.5 kPa. Based on T partitioned using a transpiration estimation algorithm as a benchmark, these three models also exhibited a significant reduction in RMSE under high VPD conditions after considering PRI. The main rationale behind the PRI improvement is that PRI can track photosynthetic dynamics under high VPD conditions. Based on the simulation results of the Soil-Canopy-Observation of Photosynthesis and Energy fluxes (SCOPE) model, PRI can serve as an indicator for non-photochemical quenching (NPQ) within this ecosystem. Consequently, PRI can enhance the capability of SIF to characterize the energy dissipation of photosynthetically active radiation and help SIF to yield more accurate information on GPP and gc under high VPD conditions. Finally, the order of model performance in estimating T was generally hybrid model > semi-mechanistic model > linear model. Our findings show the effectiveness of PRI for improving SIF-driven transpiration estimation under high VPD conditions and provide a new hybrid model for estimating T from SIF.

Comparing Machine Learning Techniques for Detecting Chronic Kidney Disease in Early Stage

In medical care, side effect trial and error processes are utilized for the discovery of hidden reasons for ailments and the determination of conditions. In our exploration, we used a crossbreed strategy to refine our optimal model, improving the Pearson relationship for highlight choice purposes. The underlying stage included the choice of ideal models through a careful survey of the current writing. Hence, our proposed half-and-half model incorporated a blend of these models. The base classifiers utilized included XGBoost, Arbitrary Woods, Strategic Relapse, AdaBoost, and the Crossover model classifiers, while the Meta classifier was the Irregular Timberland classifier. The essential target of this examination was to evaluate the best AI grouping techniques and decide the best classifier concerning accuracy. This approach resolved the issue of overfitting and accomplished the most elevated level of exactness. The essential focal point of the assessment was precision, and we introduced a far-reaching examination of the significant writing in even configuration. To carry out our methodology, we used four top-performing AI models and fostered another model named "half and half," utilizing the UCI Persistent Kidney Disappointment dataset for prescient purposes. In our experiment, we found out that the AI model XGBoost classifier gains almost 94% accuracy, a random forest gains 93% accuracy, Logistic Regression about 90% accuracy, AdaBoost gains 91% accuracy, and our proposed new model named hybrid gains the highest 95% accuracy, and performance of Hybrid model is best on this equivalent dataset. Various noticeable AI models have been utilized to foresee the event of persistent kidney disappointment (CKF). These models incorporate Naïve Bayes, Random Forest, Decision Tree, Support Vector Machine, K-nearest neighbor, LDA (Linear Discriminant Analysis), GB (Gradient Boosting), and neural networks. In our examination, we explicitly used XGBoost, AdaBoost, Logistic Regression, Random Forest, and Hybrid models with the equivalent dataset of highlights to analyze their accuracy scores.

Hybrid model of CT-fractional flow reserve, pericoronary fat attenuation index and radiomics for predicting the progression of WMH: a dual-center pilot study.

To develop and validate a hybrid model incorporating CT-fractional flow reserve (CT-FFR), pericoronary fat attenuation index (pFAI), and radiomics signatures for predicting progression of white matter hyperintensity (WMH). A total of 226 patients who received coronary computer tomography angiography (CCTA) and brain magnetic resonance imaging from two hospitals were divided into a training set (n = 116), an internal validation set (n = 30), and an external validation set (n = 80). Patients who experienced progression of WMH were identified from subsequent MRI results. We calculated CT-FFR and pFAI from CCTA images using semi-automated software, and segmented the pericoronary adipose tissue (PCAT) and myocardial ROI. A total of 1,073 features were extracted from each ROI, and were then refined by Elastic Net Regression. Firstly, different machine learning algorithms (Logistic Regression [LR], Support Vector Machine [SVM], Random Forest [RF], k-nearest neighbor [KNN] and eXtreme Gradient Gradient Boosting Machine [XGBoost]) were used to evaluate the effectiveness of radiomics signatures for predicting WMH progression. Then, the optimal machine learning algorithm was used to compare the predictive performance of individual and hybrid models based on independent risk factors of WMH progression. Receiver operating characteristic (ROC) curve analysis, calibration and decision curve analysis were used to evaluate predictive performance and clinical value of the different models. CT-FFR, pFAI, and radiomics signatures were independent predictors of WMH progression. Based on the machine learning algorithms, the PCAT signatures led to slightly better predictions than the myocardial signatures and showed the highest AUC value in the XGBoost algorithm for predicting WMH progression (AUC: 0.731 [95% CI: 0.603-0.838] vs.0.711 [95% CI: 0.584-0.822]). In addition, pFAI provided better predictions than CT-FFR (AUC: 0.762 [95% CI: 0.651-0.863] vs. 0.682 [95% CI: 0.547-0.799]). A hybrid model that combined CT-FFR, pFAI, and two radiomics signatures provided the best predictions of WMH progression [AUC: 0.893 (95%CI: 0.815-0.956)]. pFAI was more effective than CT-FFR, and PCAT signatures were more effective than myocardial signatures in predicting WMH progression. A hybrid model that combines pFAI, CT-FFR, and two radiomics signatures has potential use for identifying WMH progression.

Application of forecasting strategies and techniques to natural gas consumption: A comprehensive review and comparative study

Accurate forecasting of natural gas consumption (NGC) plays an important role in energy supply, energy trading, economic effects and environmental sustainability. NGC forecasts can be used to adjust production and supply plans to improve gas efficiency and reduce carbon emissions and supply chain waste. This paper reviews the research progress on NGC in the past decade, analyzes the typical characteristics of different forecasting strategies, and highlights 163 studies in terms of the technical aspects of feature processing methods, data decomposition methods, forecasting models and optimization algorithms. It also systematically elaborates the application of statistical models, machine learning models, grey models, logistic regression and their combinations in predictive models. Bibliometric methods are also utilized to dissect research hotspots and summarize cutting-edge trends in the field. It is worth mentioning that in the terms of hybrid model structures, the application and performance of various model structures are described and evaluated. In this paper, the future development is discussed from spatiotemporal characteristics, studying reasonable data decomposition layers and fusion models, considering potential data privacy issues, and developing artificial intelligence-supporting models and interpretable frameworks. This paper is expected to provide a multi-technology reference for natural gas forecasting and help researchers to select and develop more accurate forecasting techniques and strategies.

Evaluating data-driven and hybrid modeling of terrestrial actual evapotranspiration based on an automatic machine learning approach

The performances of physics-based, data-driven, and hybrid models for estimating terrestrial actual evapotranspiration (ETa) is currently under debate, which requires thorough evaluations of those models particularly with recent developments in automatic machine learning (AML) techniques. In this study, six AML-based models were first constructed using the H2O-AML platform, from which an optimal (AML-OP) model was selected for estimating daily ETa at ecosystem scales. In addition, hybrid models were developed by combining the six AML models with surface conductance (Gs) inverted from the Penman-Monteith equation and an optimal (PM-OP) model was also selected. With 15 predictor variables as model inputs that were compiled from various data sources, the performances of those models for estimating daily ETa were evaluated using observed data from the FLUXNET2015 dataset. The results revealed that no models showed consistently low noise levels across different ecosystem types, making it necessary to use AML techniques for selecting ecosystem-specific models. Interestingly, the AML-OP models (root mean square error (RMSE) and symmetric mean absolute percentage error (SMAPE) were 0.16–0.31 mm d-1 and 9 %–36 % respectively) showed slightly better predictive results than the PM-OP models (RMSE and SMAPE were 0.23–0.36 mm d-1 and 15 %–68 % respectively), likely owing to model parameter uncertainties and tight constraints of physical models on application condition. Secondly, as ETa nonlinearly responds to environmental variables, model predictability under extreme weather (drought and heatwave) conditions was examined. The results showed that the prediction of the AML-OP and PM-OP models expectedly worsened (RMSE and SMAPE increased by 0.06–0.77 mm d-1 and −19 % to 79 %, respectively); however, the AML-OP model still outperformed the PM-OP model in most ecosystems, further underscoring the need to understand ETa regulation mechanisms under varying climatic conditions. Finally, the PM-OP models developed here provided better daily ETa estimates compared to other recently proposed hybrid models (RMSE reduced by 0.98–1.80 mm d-1). Both models can be better applied to wetlands that have been less frequently evaluated previously (RMSE reduction of 0.22 mm d-1 and 0.18 mm d-1 for the AML-OP and PM-OP models).

Forecasting household energy consumption based on lifestyle data using hybrid machine learning

Household lifestyle play a significant role in appliance consumption. The overall effects are that, it can be a determining factor in the healthy functioning of the household appliance or its abnormal functioning. The rapid growth in residential consumption has raised serious concerns toward limited energy resource and high electricity pricing. The propose 134% electricity tariffs adjustment by Electricity Company of Ghana (ECG) at the heat of economic hardships caused by Covid-19 has raised serious public agitation in Ghana (west Africa) . The unpredictable lifestyle of residential consumers in an attempt to attain a comfortable lifestyle and the rippling effects of population growth burdens energy demand at the residential sector. This study attempts to identify the lifestyle factors that have great influence on household energy consumption and predict future consumption of the household with mitigating factors to cushion the effects on high consumption. The study is based on lifestyle data using hybrid machine learning. The hybrid model achieved high accuracy (96%) as compared to previous models. The hybrid model performance was evaluated using mean absolute percentage error (MAPE), root mean square error (RMSE) and correlation coefficient (R) metrics.

The Design of an Intelligent Lightweight Stock Trading System Using Deep Learning Models: Employing Technical Analysis Methods

Individual investors often struggle to predict stock prices due to the limitations imposed by the computational capacities of personal laptop Graphics Processing Units (GPUs) when running intensive deep learning models. This study proposes solving these GPU constraints by integrating deep learning models with technical analysis methods. This integration significantly reduces analysis time and equips individual investors with the ability to identify stocks that may yield potential gains or losses in an efficient manner. Thus, a comprehensive buy and sell algorithm, compatible with average laptop GPU performance, is introduced in this study. This algorithm offers a lightweight analysis method that emphasizes factors identified by technical analysis methods, thereby providing a more accessible and efficient approach for individual investors. To evaluate the efficacy of this approach, we assessed the performance of eight deep learning models: long short-term memory (LSTM), a convolutional neural network (CNN), bidirectional LSTM (BiLSTM), CNN Attention, a bidirectional gated recurrent unit (BiGRU) CNN BiLSTM Attention, BiLSTM Attention CNN, CNN BiLSTM Attention, and CNN Attention BiLSTM. These models were used to predict stock prices for Samsung Electronics and Celltrion Healthcare. The CNN Attention BiLSTM model displayed superior performance among these models, with the lowest validation mean absolute error value. In addition, an experiment was conducted using WandB Sweep to determine the optimal hyperparameters for four individual hybrid models. These optimal parameters were then implemented in each model to validate their back-testing rate of return. The CNN Attention BiLSTM hybrid model emerged as the highest-performing model, achieving an approximate rate of return of 5 percent. Overall, this study offers valuable insights into the performance of various deep learning and hybrid models in predicting stock prices. These findings can assist individual investors in selecting appropriate models that align with their investment strategies, thereby increasing their likelihood of success in the stock market.

Application of empirical mode decomposition, particle swarm optimization, and support vector machine methods to predict stream flows.

Modeling stream flows is vital for water resource planning and flood and drought management. In this study, the performance of hybrid models constructed by combining least square support vector machines (LSSVM), empirical model decomposition (EMD), and particle swarm optimization (PSO) methods in modeling monthly streamflow was evaluated. For establishing the models, 42years of monthly average streamflow data was used in two hydrometer stations located in the Konya Closed Basin, covering 1964 to 2005. Lagged streamflow values ​​were selected as inputs according to partial autocorrelation values ​​in establishing the models. The dataset was divided into 70% training and 30% testing. Model performances were evaluated according to mean square error, root mean square error, correlation coefficients, scatter plot, and Taylor and Violin diagrams. As a result of the analysis, it was determined that the PSO-LSSVM and EMD-LSSVM models were slightly more successful than the single LSSVM model, and the best model was obtained with the EMD-PSO-LSSVM. In addition, in estimating monthly stream flows, 1-, 9-, 10-, 11-, and 12-month lagged streamflow values were the input combination that gave the best results in semi-arid climatic regions. This result demonstrated that EMD improved the performance of both LSSVM and PSO-LSSVM models by 1% to 5% based on correlation coefficient (R) values.

MSQAT: A multi-dimension non-intrusive speech quality assessment transformer utilizing self-supervised representations

Convolutional neural networks (CNNs) have been widely utilized as the main building block for many non-intrusive speech quality assessment (NISQA) methods. A new trend is to add a self-attention mechanism based on CNN to better capture long-term global content. However, it is not clear whether the pure attention-based network is sufficient to obtain good performance in NISQA. To this end, a framework named Multi-dimension non-intrusiveSpeech Quality Assessment Transformer (MSQAT) is proposed. To strengthen the interactions of various speech regions between local and global, we proposed the Audio Spectrogram Transformer Block (ASTB), Transposed Attention Block (TAB) and the Residual Swin Transformer Block (RSTB). These three modules employ attention mechanisms across spatial and channel dimensions, respectively. Additionally, speech quality varies not only in different frames, but also in different frequencies. Thus, a two-branch structure is designed to better evaluate the quality of speech by considering the weighting of each patch's score. Experimental results demonstrate that the proposed MSQAT has state-of-the-art performance on three standard datasets (NISQA Corpus, Tencent Corpus, and PSTN Corpus) and indicate that the pure attention model can achieve or surpass the performance of other CNN-attention hybrid models.

Improving the Performance of Hybrid Models Using Machine Learning and Optimization Techniques

Improving the Performance of Hybrid Models Using Machine Learning and Optimization Techniques

Gender Classification from Fingerprint Using Hybrid CNN-SVM

Gender classification is used in numerous applications such as biometrics, criminology, surveillance, HCI, and business profiling. Although biometric factors like gait, face, hand shape, and iris have been used to classify people into genders, the majority of research has focused on facial traits due to their more recognisable qualities. This research employs fingerprints to classify gender, with the intention of being relevant for future studies. Several methods for gender classification utilising fingerprints have been presented in the literature, including ANN, KNN, Naive Bayes, the Gaussian mixture model, and deep learning-based classifiers. Although these classifiers have shown good classification accuracy, gender classification remains an unexplored field of study that necessitates the development of new approaches to enhance recognition accuracy, computation, and running time. In this paper, a CNN-SVM hybrid framework for gender classification from fingerprints is proposed, where preprocessing, feature extraction, and classification are the three main components. The main goal of this study is to use CNN to extract fingerprint information. These features are then sent to an SVM classifier to determine gender. The hybrid model's performance measures are examined and compared to those of the conventional CNN model. Using a CNN-SVM hybrid model, the accuracy of gender classification based on fingerprints was 99.25%.

Denoising odontocete echolocation clicks using a hybrid model with convolutional neural network and long short-term memory network.

Ocean noise negatively influences the recording of odontocete echolocation clicks. In this study, a hybrid model based on the convolutional neural network (CNN) and long short-term memory (LSTM) network-called a hybrid CNN-LSTM model-was proposed to denoise echolocation clicks. To learn the model parameters, the echolocation clicks were partially corrupted by adding ocean noise, and the model was trained to recover the original echolocation clicks. It can be difficult to collect large numbers of echolocation clicks free of ambient sea noise for training networks. Data augmentation and transfer learning were employed to address this problem. Based on Gabor functions, simulated echolocation clicks were generated to pre-train the network models, and the parameters of the networks were then fine-tuned using odontocete echolocation clicks. Finally, the performance of the proposed model was evaluated using synthetic data. The experimental results demonstrated the effectiveness of the proposed model for denoising two typical echolocation clicks-namely, narrowband high-frequency and broadband echolocation clicks. The denoising performance of hybrid models with the different number of convolution and LSTM layers was evaluated. Consequently, hybrid models with one convolutional layer and multiple LSTM layers are recommended, which can be adopted for denoising both types of echolocation clicks.