Tuning Of Model Parameters Research Articles

Emissions and Flame Stability Assessment of Hydrogen Addition and Air Dilution in a Micro Gas Turbine Combustor Using 0D/1D Modeling by Chemical Reactor Network

Abstract Hydrogen emerges as a promising fuel for clean and sustain- able electricity production when utilized in micro gas turbines (mGTs). However, some challenges linked to hydrogen usage must be overcome as its high reactivity can lead to increased NOx emissions and flame instabilities. Literature suggests that combustion air humidification and/or exhaust gas recirculation (EGR) may be methods to reduce this reactivity. However, these measures are limited due to the small operating range of the mGT combustor. In this context, a 20 kWth mGT combustor is investigated un- der various inlet conditions to assess the effect of EGR towards increased flame stability and emission control when operating under hydrogen-enriched methane firing, using a Chemical Re- action Network (CRN) model. The CRN modeling is a fast and low computational complexity tool to model combustion perfor- mance and emissions by representing complex reactive flow fields through idealized reactor models, leading to reduced computa- tional costs. This study examines partial load conditions, fuel compositions, and the effect of combustion air dilution through EGR. The CRN model of the combustion process is designed based on combustion zones extracted from the main flow fields with similar thermo-chemical states from CFD, while emission predictions are experimentally validated for different operating points. Predicted NOx and CO emissions by the proposed CRN model show an acceptable agreement with the experimental data at high power loads. However, its accuracy diminishes for loads below 70% due to the variability in model tuning parameters across different loads, whereas the

Distributed Denial of Service Attack Detection and Prevention Using Pipit Fox-Attentional Deep Learning in Software-Defined Networking

The Software-Defined Network (SDN) remains the innovative model that assists in satisfying the new application requirements of future networks. However, destructive attacks, particularly Distributed Denial of Service (DDoS) attacks, are aimed primarily at the SDN control panel, presenting a significant risk to network security. The traditional approaches for DDoS attack detection exhibit several limitations including interpretability challenges, overfitting problems, and false predictions. To mitigate these drawbacks, the research proposed a Pipit Flying Fox Optimized Deep Neural Network (PPF-DNN) and Intelligent Pipit Forage Optimized-Attentional Convolutional Neural Network (IPFO-ACNN) model. The channel attention is employed to enable the network to focus selectively on relevant information, improving the model’s sensitivity to subtle anomalies associated with DDoS attacks. By dynamically adjusting the attention weights across channels, the mechanism enhances the capability of the model to discriminate the normal network traffic and malicious patterns, which results in improved precision and reduced false positives. This approach harnesses the power of CNN to automatically extract hierarchical features from network data, enhancing the efficacy of the ACNN model in attack detection. IPFO and PPF algorithms integrate the unique strengths of bio-inspired algorithms, creating a synergistic approach for efficient model parameter tuning. In the case of Training Percentage (TP) 80, the accuracy, sensitivity, and specificity of the IPFO-ACNN model are evaluated as 98.87%, 99.24% and 97.91%, respectively. Similarly, the PPF-DNN model’s performance is assessed as 98.49%, 92.50% and 98.55%, which presents a promising avenue for bolstering network security infrastructure, ensuring more robust DDoS detection and mitigation capabilities in an increasingly complex cyber threat landscape.

A Novel Active Learning Framework for Cross-Subject Human Activity Recognition from Surface Electromyography.

Wearable sensor-based human activity recognition (HAR) methods hold considerable promise for upper-level control in exoskeleton systems. However, such methods tend to overlook the critical role of data quality and still encounter challenges in cross-subject adaptation. To address this, we propose an active learning framework that integrates the relation network architecture with data sampling techniques. Initially, target data are used to fine tune two auxiliary classifiers of the pre-trained model, thereby establishing subject-specific classification boundaries. Subsequently, we assess the significance of the target data based on classifier discrepancy and partition the data into sample and template sets. Finally, the sampled data and a category clustering algorithm are employed to tune model parameters and optimize template data distribution, respectively. This approach facilitates the adaptation of the model to the target subject, enhancing both accuracy and generalizability. To evaluate the effectiveness of the proposed adaptation framework, we conducted evaluation experiments on a public dataset and a self-constructed electromyography (EMG) dataset. Experimental results demonstrate that our method outperforms the compared methods across all three statistical metrics. Furthermore, ablation experiments highlight the necessity of data screening. Our work underscores the practical feasibility of implementing user-independent HAR methods in exoskeleton control systems.

JointPRS: A Data-Adaptive Framework for Multi-Population Genetic Risk Prediction Incorporating Genetic Correlation.

Genetic prediction accuracy for non-European populations is hindered by the limited sample size of Genome-wide association studies (GWAS) data in these populations. Additionally, it is challenging to tune model parameters with a small tuning dataset for methods that require tuning data, which is often the case for non-European samples. To address these challenges, we propose JointPRS, a novel, data-adaptive framework that simultaneously models multiple populations using GWAS summary statistics. JointPRS incorporates genetic correlation structures into the prediction framework, enabling accurate performance even without individual-level tuning data. Additionally, it uniquely employs a data-adaptive approach, providing a robust solution when only a small tuning dataset is available. Through extensive simulations and real data applications to 22 quantitative traits and four binary traits in five continental populations (European (EUR); East Asian (EAS); African (AFR); South Asian (SAS); and Admixed American (AMR)) evaluated using the UK Biobank (UKBB) and All of Us (AoU), we demonstrate that JointPRS outperforms six other state-of-art methods across three different data scenarios (no tuning data, tuning and testing data from the same cohort, and tuning and testing data from different cohorts) for most traits in non-European populations, while maintaining model simplicity and computational efficiency.

Neutron star in covariant f(Q) gravity

Assuming static and spherically symmetric stars with perfect fluid matter, we used realistic equations of state to study neutron stars in covariant f(Q) gravity. The structure profiles and properties of neutron stars such as mass, radius and compactness are obtained through numerical methods using quadratic, exponential, and logarithmic f(Q) models. The results indicate that nonmetricity affects the interior profile deviations of the star, which in turn influence the properties of stars, as illustrated in the mass-radius relation diagram. This effect allows the star to accommodate either more or less matter compared to GR, resulting in a different total mass. For the quadratic model, we cannot generate larger masses, whereas the other two models can give consistent results for both smaller and larger masses of the observed stars. By tuning model parameters, we obtain ℳ-ℛ diagrams that are compatible with observational constraints from NICER and LIGO.

Comparing discrete choice and machine learning models in predicting destination choice

Destination choice modeling has long been dominated by theory-based discrete choice models. Simultaneously, machine learning has demonstrated improved predictive performance to other fields of discrete choice modeling. The objective of this research was to compare machine learning models and a multinomial logit model in predicting destination choice. The models were assessed on their predictive performance using metrics for both binary classification and probabilistic classification. The results indicate that machine learning models, especially a random forest model, could bring improvements in prediction accuracy. The more data was used in training the models, the better the machine learning models tended to perform compared to the multinomial logit model. With less data, the multinomial logit model performed comparatively well. The findings are relevant for the field of destination choice modeling, where evidence on the use of machine learning models is very limited. In addition, the unbalanced choice sets of destination choice models with multiple non-chosen alternatives increases the need for further research in model fit and parameter tuning.

Bayesian optimization based extreme gradient boosting and GPR time-frequency features for the recognition of moisture damage in asphalt pavement

Moisture damage is one of the major defects in asphalt pavement, and will evolve into potholes in a short time which will affect traffic safety. Ground Penetrating Radar (GPR) is an effective non-destructive testing (NDT) method for detecting moisture damage but its data explanation replies on human experience and subjects to labor intensive. To address this issue, an automatic detection method based on extreme gradient boosting (XGBoost) combined with Bayesian hyper-parameter optimization (BHPO) was proposed to detect moisture damage area from GPR traces. High frequency GPR antenna with 2.3 GHz was used to detect the moisture damage area from simulation, laboratory and field tests, and moisture damage dataset with 7960 traces was collected. Thirty time-frequency parameters were extracted from each GPR trace, normalized to unify the three data source, and then optimized into 12 sensitive parameters by feature importance method. These 12 parameters were used to build the recognition model with XGBoost, and the model tuning parameters were optimized by BHPO. To obtain optimization model, random forest (RF) and artificial neural network (ANN) were also trained with BHPO, and compared with XGBoost model. The results indicate that performance of XGBoost model with BHPO achieves the highest accuracy and lowest time cost both in moisture damage and normal trace classification, the accuracies for moisture damage are XGBoost (96.9%) > ANN (95.6%) > RF (95.4%), respectively, and normal are XGBoost (96.5%) > RF (96.1%) and ANN (96.0%), respectively. On this basis, field tests were conducted by core samples, which verified the correct result of XGBoost model. Our method provides a swift and accurate method to locate subsurface targets directly from GPR signals.

Extensive data engineering to the rescue: building a multi-species katydid detector from unbalanced, atypical training datasets.

Passive acoustic monitoring (PAM) is a powerful tool for studying ecosystems. However, its effective application in tropical environments, particularly for insects, poses distinct challenges. Neotropical katydids produce complex species-specific calls, spanning mere milliseconds to seconds and spread across broad audible and ultrasonic frequencies. However, subtle differences in inter-pulse intervals or central frequencies are often the only discriminatory traits. These extremities, coupled with low source levels and susceptibility to masking by ambient noise, challenge species identification in PAM recordings. This study aimed to develop a deep learning-based solution to automate the recognition of 31 katydid species of interest in a biodiverse Panamanian forest with over 80 katydid species. Besides the innate challenges, our efforts were also encumbered by a limited and imbalanced initial training dataset comprising domain-mismatched recordings. To overcome these, we applied rigorous data engineering, improving input variance through controlled playback re-recordings and by employing physics-based data augmentation techniques, and tuning signal-processing, model and training parameters to produce a custom well-fit solution. Methods developed here are incorporated into Koogu, an open-source Python-based toolbox for developing deep learning-based bioacoustic analysis solutions. The parametric implementations offer a valuable resource, enhancing the capabilities of PAM for studying insects in tropical ecosystems. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Improving Identification of Tic Disorders in Children

ABSTRACT This study combines data from five studies in a quantitative modeling approach to improve identification of tics and tic disorders using two questionnaires (the Motor or Vocal Inventory of Tics and the Description of Tic Symptoms), administered to parents and children (N = 1,307). Combining final diagnoses (positive or negative for tic disorder) with data from recently developed questionnaires implemented to assist in the identification of tics and tic disorders in children, we investigate methods for predicting positive diagnosis while also identifying which items in the questionnaires are most predictive. Logistic regression and random forest models are compared using various summary statistics. We further discuss the differences in errors (false positives versus false negatives) in the specification of predictive model tuning parameters. Compared to logistic regression models, random forest models provided comparable and often superior predictive abilities and were also more useful in summarizing the contributions to predictions from individual questions. The combined analyses identified a subset of screener questions that were the best predictors of tic disorders; the identified questions differed based on parent or self-report. These results provide information to inform the future development of tools to screen for tics in a variety of healthcare and epidemiological settings.

Optimisation Study of Natural Language Processing Algorithms Based on Deep Learning

This paper presents a comprehensive optimization study of natural language processing (NLP) algorithms based on deep learning techniques. The research explores various strategies to enhance the performance and efficiency of NLP models, aiming to address the challenges posed by large-scale datasets and complex linguistic structures. Through a systematic review of existing literature and methodologies, this study synthesizes insights into key optimization approaches, including model architecture design, parameter tuning, and data preprocessing techniques. Moreover, it investigates the impact of different optimization strategies on NLP tasks such as sentiment analysis, named entity recognition, and machine translation. By elucidating the strengths and limitations of various optimization techniques, this paper offers valuable insights for researchers and practitioners in the field of deep learning-based NLP.

ILOSCAR: interactive Long-term Ocean-atmosphere-Sediment CArbon cycle Reservoir model v1.0

Computationally inexpensive carbon cycle models serve as critical and efficient tools for illuminating the complex dynamics of the carbon cycle and its interplay with the climate system, offering insights into how our planet has responded to climate perturbations throughout its history. During geologic hyperthermal events, carbon cycle models are employed to trace the trajectory of carbon emissions and establish a connection between the emission trajectory and changes in the Earth's surface environment. To date, the prevalent method to estimate the carbon emission rate relies on coupling the carbon cycle modeling and proxy reconstructions. Most previous studies employ a forward methodology, i.e., they force the model with an array of predefined carbon injection scenarios and select the one that produces the best fit to one or more specific proxy-derived records (e.g., atmospheric pCO2, sea surface pH, and calcite compensation depth) as the optimal solution. However, this forward method has two potential disadvantages. First, it can be computationally expensive, particularly when tens of thousands of scenarios need to be conducted to find the best solution. Second, it might not yield the best injection trajectory if none of the predefined carbon emission curves represents the realistic emission curve. Hence, an inverse model that can reconstruct the carbon emission trajectory directly from the record/records is urgently needed. In this study, building upon the Long-term Ocean-atmosphere-Sediment CArbon cycle Reservoir (LOSCAR) Model (Zeebe, 2012), we develop an interactive carbon cycle model (named iLOSCAR) using the open-source Python language and include two options, a forward model and an inverse model. The forward model replicates the original LOSCAR model, while the inverse model calculates the emission trajectory constrained by the proxy records in a single run. Both models are accessible via a web-based interface, which allows users to interactively tune model parameters and conduct experiments. In this paper, we present the details of iLOSCAR, including model structure and derivation of key equations. We then validate iLOSCAR's performance through an identical twin test and model intercomparison. We also apply it to a climatic perturbation event to diagnose features of the emission pattern that were overlooked in previous studies. Finally, we discuss the possible directions for model's future development.

Modeling methyl-sensitive transcription factor motifs with an expanded epigenetic alphabet

BackgroundTranscription factors bind DNA in specific sequence contexts. In addition to distinguishing one nucleobase from another, some transcription factors can distinguish between unmodified and modified bases. Current models of transcription factor binding tend not to take DNA modifications into account, while the recent few that do often have limitations. This makes a comprehensive and accurate profiling of transcription factor affinities difficult.ResultsHere, we develop methods to identify transcription factor binding sites in modified DNA. Our models expand the standard A/C/G/T DNA alphabet to include cytosine modifications. We develop Cytomod to create modified genomic sequences and we also enhance the MEME Suite, adding the capacity to handle custom alphabets. We adapt the well-established position weight matrix (PWM) model of transcription factor binding affinity to this expanded DNA alphabet. Using these methods, we identify modification-sensitive transcription factor binding motifs. We confirm established binding preferences, such as the preference of ZFP57 and C/EBPβ for methylated motifs and the preference of c-Myc for unmethylated E-box motifs.ConclusionsUsing known binding preferences to tune model parameters, we discover novel modified motifs for a wide array of transcription factors. Finally, we validate our binding preference predictions for OCT4 using cleavage under targets and release using nuclease (CUT&RUN) experiments across conventional, methylation-, and hydroxymethylation-enriched sequences. Our approach readily extends to other DNA modifications. As more genome-wide single-base resolution modification data becomes available, we expect that our method will yield insights into altered transcription factor binding affinities across many different modifications.

Cocoa Diseases Classification using Deep Learning Algorithm

This work addresses the critical issue of cocoa plant diseases, which pose a significant threat to global agriculture and the livelihood of millions of farmers. Convolutional Neural Networks (CNN) has been utilized for classifying cocoa diseases, focusing on combating the significant agricultural and economic impacts of black pod rot and pod borer. Utilizing a dataset of 4390 images, five CNN architectures—Custom CNN, VGG-16, EfficientNetB0, ResNet50, and LeNet-5—were assessed for their ability to accurately identify disease presence. The Custom CNN model was found to be the most effective, achieving an accuracy of 91.79%, precision of 91.79%, recall of 91.79%, F1 score of 82.08%, sensitivity of 96.69%, and specificity of 98.40%, indicating its strong capability in correctly classifying both healthy and diseased plants. The work methodically approached data preprocessing, model parameter tuning, and a structured machine learning evaluation process. While EfficientNetB0 and ResNet50 also displayed commendable performances, VGG-16 and LeNet-5 lagged, suggesting the need for further model refinement. This work underscores the importance of the F1 score in evaluating model performance, especially given the class imbalance within the dataset. The findings suggest future exploration into other pre-trained models and data augmentation strategies to further enhance classification accuracy. The goal of this work is the implementation of a realtime system to minimize cocoa production losses due to disease.

IAPCP: An Effective Cross‐Project Defect Prediction Model via Intra‐Domain Alignment and Programming‐Based Distribution Adaptation

Cross‐project defect prediction (CPDP) aims to identify defect‐prone software instances in one project (target) using historical data collected from other software projects (source), which can help maintainers allocate limited testing resources reasonably. Unfortunately, the feature distribution discrepancy between the source and target projects makes it challenging to transfer the matching feature representation and severely hinders CPDP performance. Besides, existing CPDP models require an intensively expensive and time‐consuming process to tune a lot of parameters. To address the above limitations, we propose an effective CPDP model named IAPCP based on distribution adaptation in this study, which consists of two stages: correlation alignment and intra‐domain programming. Correlation alignment first calculates the covariance matrices of the source and target projects and then erases some features of the source project (i.e., whitening operation) and employs the features of the target project (i.e., target covariance) to fill the source project, thereby well aligning the source and target feature distributions and reducing the distribution discrepancy across projects. Intra‐domain programming can directly learn a nonparametric linear transfer defect predictor with strong discriminative capacity by solving a probabilistic annotation matrix (PAM) based on the adjusted features of the source project. The model does not require model selection and parameter tuning. Extensive experiments on a total of 82 cross‐project pairs from 16 software projects demonstrate that IAPCP can achieve competitive CPDP effectiveness and efficiency compared with multiple state‐of‐the‐art baseline models.

CatBoost algorithms to predict the load-bearing capacity of centrally compressed short CFST columns of circular cross-section

The article investigates the use of regression models, GradientBoostingRegressor and RandomForestRegressor, to predict the load-bearing capacity of centrally compressed short concrete filled steel tubular columns. The work is based on experimental data covering a wide range of column geometric characteristics and material strength characteristics. An important part of the analysis was to deter-mine the influence of various parameters on the model predictions. The importance of features, assessment of the quality of models (MSE, MAE, MAPE) were considered , and visualization of actual and predicted values was carried out to compare the results. The results showed that both models success-fully cope with the task of predicting the load-bearing capacity of structures under given conditions. Analysis of the importance of features revealed the most significant parameters affecting the load-bearing capacity of columns. Visualization of forecasts and analysis of residuals confirmed the adequacy of the models. Additionally, a process of tuning model parameters using cross-validation was carried out to optimize their performance. The results of the study can be used in engineering applications such as the design of reinforced concrete structures to predict load-bearing capacity.

Exploring Time Series Models for Wind Speed Forecasting: A Comparative Analysis

The sustainability and efficiency of the wind energy industry rely significantly on the accuracy and reliability of wind speed forecasting, a crucial concern for optimal planning and operation of wind power generation. In this study, we comprehensively evaluate the performance of eight wind speed prediction models, spanning statistical, traditional machine learning, and deep learning methods, to provide insights into the field of wind energy forecasting. These models include statistical models such as ARIMA (AutoRegressive Integrated Moving Average) and GM (Grey Model), traditional machine learning models like LR (Linear Regression), RF (random forest), and SVR (Support Vector Regression), as well as deep learning models comprising ANN (Artificial Neural Network), LSTM (Long Short-Term Memory), and CNN (Convolutional Neural Network). Utilizing five common model evaluation metrics, we derive valuable conclusions regarding their effectiveness. Our findings highlight the exceptional performance of deep learning models, particularly the Convolutional Neural Network (CNN) model, in wind speed prediction. The CNN model stands out for its remarkable accuracy and stability, achieving the lowest mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and the higher coefficient of determination (R2). This underscores the CNN model’s outstanding capability to capture complex wind speed patterns, thereby enhancing the sustainability and reliability of the renewable energy industry. Furthermore, we emphasized the impact of model parameter tuning and external factors, highlighting their potential to further improve wind speed prediction accuracy. These findings hold significant implications for the future development of the wind energy industry.

Less complexity-aware intelligent 1-dimensional CNN with weighted deep features for artifacts removal in EEG signals

Electroencephalogram (EEG) signals contains a major role in examining the behavior of brain activity. Moreover, these signals are contaminated with artifacts, which may affect the EEG signal analysis. The EEG performs as the low spatial resolution in the unimodal analysis. Owing to the highly time-consumption procedure, the removal of artifact techniques cannot be applied in practical applications. In existing works, automatic artifact removal techniques are ineffective for eliminating the artifacts in the EEG signals. Thus, the core of this concept is to design a low complexity aware, intelligent artifacts removal model using deep learning. This paper attempts to introduce a 1-Dimensional-Convolutional Neural Network with a Weighted Deep Feature (1D-CNN-WDF), which acts as a filter to remove the unnecessary noise in EEG signals. The WDF extraction in 1D-CNN-WDF is developed by combining the Coyote Optimization Algorithm (COA), and Bird Swarm Algorithm (BSA) named Hybrid Bird-COA (HB-COA). The same hybrid algorithm is used for the tuning of model parameters in 1D-CNN-WDF. The analysis results confirm that the recommended method is more enriched than recently introduced methods when considering the improved Signal to Noise Ratio (SNR), less Mean Squared Error (MSE), and reduced computational complexity, which shows that the suggested method is attained the superior reconstruction quality.

Model-free autonomous control of four-wheel steering using artificial flow guidance

Four-wheel steering (4WS) is an effective technique to improve handling performance and lateral stability of road vehicles. Conventionally, controllers utilise the driver's actions and vehicle dynamics to coordinate front and rear-axle steering. This paper proposes a novel approach for 4WS controller design, based on the concept of Artificial Flow Guidance (AFG), which relies on a spatially distributed motion reference through a two-dimensional vector field. This field provides high-level guidance while lower-level steering controllers to control axle centres motions relative to the flow. These flow vectors, computed in real-time via simple geometric construction, can be pre-computed globally to evaluate the guidance algorithm's efficacy. When controlling only the front axle, this same approach can function as an autonomous driving system. Relying solely on a spatial reference field and control targets' velocities enables the controller to work in a simple and robust fashion, without using a reference vehicle dynamics model or lengthy parameter tuning. The proposed approach's effectiveness is validated through co-simulation with MATLAB/Simulink and the CarMaker simulation platform. AFG control performance is found to be at least comparable to that of more complex 4WS controllers using methods such as MPC; in the cases considered, AFG provides superior path-tracking performance.

A conceptual metaheuristic-based framework for improving runoff time series simulation in glacierized catchments

Glacio-hydrological modeling is a key task for assessing the influence of snow and glaciers on water resources, essential for water resources management. The present study aims to enhance a conceptual hydrological model (namely Glacial Snow Melt (GSM)) by data-driven and swarm computing for enhancing the accuracy of rainfall runoff prediction. The proposed framework combines the conceptual hydrological model (i.e. GSM) with the time series predictor model (SVR) and optimization-driven parameter tuning of the firefly algorithm (SVR-FFA). This integration uniquely captures the complex interplay between meteorological variables, glacier processes, and hydrological responses. Applying the hybrid framework proved better results than the standalone GSM and ordinary SVR in simulating runoff time series. The performance of the proposed conceptual integrated metaheuristic-based framework (W-SG-SVR-FFA) demonstrated several enhancements over the standalone GSM model. During the calibration (validation) period, the evaluation metric coefficient of determination (R2) was 0.77 (0.77) for the standalone GSM model and 0.98 (0.91) for the W-SG-SVR-FFA model. The Kling-Gupta Efficiency (KGE) values were 0.81 (0.77) and 0.97 (0.87), respectively. Applying the method in glacierized catchments underscores its importance in areas undergoing swift climate change and glacial melting. This approach enables readers to witness the intricate equilibrium between the model's complexity and the accuracy of simulation outcomes.

Semi-Supervised Specific Emitter Identification via Dual Consistency Regularization

Deep Learning (DL)-based Specific Emitter Identification (SEI) is a potential physical layer authentication technique for Industrial Internet-of-Things (IIoT) Security, which detects the individual emitter according to its unique signal features resulting from transmitter hardware impairments. The success of DL-based SEI often depends on sufficient training samples and the integrity of samples’ labels. The extensive deployment of wireless devices generates a huge amount of signals, but signals labeling is quite difficult and expensive with the high demand for expertise. In this paper, we present a SEI method based on Dual Consistency Regularization (DCR), which enables feature extraction and identification using a few labeled samples and a large number of unlabeled samples. With the help of pseudo-labeling, we leverage consistency between the predicted class distribution of weakly-augmented unlabeled training samples and that of strongly-augmented training unlabeled samples, and consistency between semantic feature distribution of labeled samples and that of pseudo-labeled samples, which takes the unlabeled samples into account to model parameter tuning for a more accurate emitter identification. Extensive numerical results demonstrate that compared with well-known semi-supervised learning-based SEI methods, our method obtains 99.77% identification accuracy on a Wi-Fi dataset and 90.10% identification accuracy on an Automatic Dependent Surveillance-Broadcast (ADS-B) dataset when only 10% of training samples are labeled, and improves the identification accuracy on the Wi-Fi dataset and the ADS-B dataset by more than 19.07% and 5.30%, respectively. Our codes are available at https://github.com/lovelymimola/DCR-Based-SemiSEI.