Feature Weights Research Articles

Intelligent alert system for predicting invasive mechanical ventilation needs via noninvasive parameters: employing an integrated machine learning method with integration of multicenter databases.

The use of invasive mechanical ventilation (IMV) is crucial in rescuing patients with respiratory dysfunction. Accurately predicting the demand for IMV is vital for clinical decision-making. However, current techniques are invasive and challenging to implement in pre-hospital and emergency rescue settings. To address this issue, a real-time prediction method utilizing only non-invasive parameters was developed to forecast IMV demand in this study. The model introduced the concept of real-time warning and leveraged the advantages of machine learning and integrated methods, achieving an AUC value of 0.935 (95% CI 0.933-0.937). The AUC value for the multi-center validation using the AmsterdamUMCdb database was 0.727, surpassing the performance of traditional risk adjustment algorithms (OSI(oxygenation saturation index): 0.608, P/F(oxygenation index): 0.558). Feature weight analysis demonstrated that BMI, Gcsverbal, and age significantly contributed to the model's decision-making. These findings highlight the substantial potential of a machine learning real-time dynamic warning model that solely relies on non-invasive parameters to predict IMV demand. Such a model can provide technical support for predicting the need for IMV in pre-hospital and disaster scenarios.

Multi-task transfer learning for the prediction of entity modifiers in clinical text: application to opioid use disorder case detection

BackgroundThe semantics of entities extracted from a clinical text can be dramatically altered by modifiers, including entity negation, uncertainty, conditionality, severity, and subject. Existing models for determining modifiers of clinical entities involve regular expression or features weights that are trained independently for each modifier.MethodsWe develop and evaluate a multi-task transformer architecture design where modifiers are learned and predicted jointly using the publicly available SemEval 2015 Task 14 corpus and a new Opioid Use Disorder (OUD) data set that contains modifiers shared with SemEval as well as novel modifiers specific for OUD. We evaluate the effectiveness of our multi-task learning approach versus previously published systems and assess the feasibility of transfer learning for clinical entity modifiers when only a portion of clinical modifiers are shared.ResultsOur approach achieved state-of-the-art results on the ShARe corpus from SemEval 2015 Task 14, showing an increase of 1.1% on weighted accuracy, 1.7% on unweighted accuracy, and 10% on micro F1 scores.ConclusionsWe show that learned weights from our shared model can be effectively transferred to a new partially matched data set, validating the use of transfer learning for clinical text modifiers.

Stable multivariate lesion symptom mapping.

Multivariate lesion-symptom mapping (MLSM) considers lesion information across the entire brain to predict impairments. The strength of this approach is also its weakness-considering many brain features together synergistically can uncover complex brain-behavior relationships but exposes a high-dimensional feature space that a model is expected to learn. Successfully distinguishing between features in this landscape can be difficult for models, particularly in the presence of irrelevant or redundant features. Here, we propose stable multivariate lesion-symptom mapping (sMLSM), which integrates the identification of reliable features with stability selection into conventional MLSM and describe our open-source MATLAB implementation. Usage is showcased with our publicly available dataset of chronic stroke survivors (N=167) and further validated in our independent public acute stroke dataset (N = 1106). We demonstrate that sMLSM eliminates inconsistent features highlighted by MLSM, reduces variation in feature weights, enables the model to learn more complex patterns of brain damage, and improves model accuracy for predicting aphasia severity in a way that tends to be robust regarding the choice of parameters for identifying reliable features. Critically, sMLSM more consistently outperforms predictions based on lesion size alone. This advantage is evident starting at modest sample sizes (N>75). Spatial distribution of feature importance is different in sMLSM, which highlights the features identified by univariate lesion symptom mapping while also implicating select regions emphasized by MLSM. Beyond improved prediction accuracy, sMLSM can offer deeper insight into reliable biomarkers of impairment, informing our understanding of neurobiology.

ACVPred: Enhanced prediction of anti-coronavirus peptides by transfer learning combined with data augmentation

Anti-coronavirus peptides (ACVPs) have garnered significant attention in COVID-19 therapeutic research due to their precise targeting, low risk of drug resistance, flexible synthesis, and effectiveness against viral mutations. Although some in-silico methods have been developed to predict ACVPs, they suffer from challenges such as limited datasets and a lack of interpretability. Hence, this study introduces ACVPred, an algorithm for ACVP prediction, based on two few-shot learning strategies: transfer learning and data augmentation strategies. Our experiments demonstrate that data augmentation can significantly enhance model performance, while transfer learning can effectively prevent overfitting and strengthen generalizability. Compared to existing methods, ACVPred exhibits superior performance and robust generalization both in training and independent test datasets. Moreover, the interpretability study of the model reveals that its transformer-based core can effectively capture key motifs on ACVP sequences, demonstrating strong feature learning capabilities. Additionally, the findings suggest that the sequence feature weights and key motif positions tend to be distributed towards the N-terminal end of ACVP sequences, providing vital clues for the design of ACVPs. In summary, ACVPred is not only a practical and valuable tool for aiding in the design of ACVPs, but its algorithmic concept also serves as an important reference for research on other small sample prediction problems.

The cross-modality survival prediction method of glioblastoma based on dual-graph neural networks

Glioma, the highly lethal malignant brain tumor originating from abnormal proliferation of glial cells, exhibits a varied overall survival rate influenced by multiple factors. Accurate prediction rate of survival periods assist physicians in selecting the most suitable treatment plans to improve patient overall survival (OS) rates. The paper proposes a dual-graph neural network (GNN) with manually constructed feature relational graph for OS prediction and inference of different survival periods in glioblastoma based on cross-modality data. Specifically, five radiomic features from magnetic resonance imaging are extracted to construct two sets of feature relational graphs. The main GNN is utilized to extract comprehensive features, including age, brain MRI features, and radiomics features of gliomas. The branch GNN additionally extracts radiomics features specific to gliomas, constraining the feature weights of the main GNN through attention mechanisms. Pretraining an autoencoder to extract deep features from patient text information. The text features and image features are then reorganized based on features from different modalities through a transformer decoder. Finally, a multi-layer perceptron is utilized for regression and classification, thus enabling the classification and prediction of patient survival. The proposed method achieved an accuracy of 0.586 for classifying and predicting the survival of glioma patients in the short, medium, and long term on the BraTS20 dataset, outperforming state-of-the-art methods.

Multi‐scale feature aggregation network for single‐image dehazing

AbstractTransformer possesses a broader perceptual scope, while the Convolutional Neural Network (CNN) excels at capturing local information. In this paper, the authors propose the Multi‐Sclale Feature Aggregation Network (MSFA‐Net) for single‐image dehazing which is fused with the advantages of Transformer and CNN. Our MSFA‐Net is based on the encoder–decoder structure, and there are four main innovations. Firstly, the authors make some improvements to the original Swin Transformer to make it more effective for dehazing tasks, and the authors name it Spatial Information Aggregation Transformer (SIAT). The authors place the SIAT in both encoder and decoder of MSFA‐Net for feature extraction. The authors propose an upsampling module called Efficient Spatial Resolution Recovery (ESRR) which is placed in the decoder part. Compared to commonly used transposed convolutions, the authors’ ESRR module has fewer computational cost. Considering that the haze distribution is always uneven and the information from each channel is different, the authors introduce the Dynamic Multi‐Attention (DMA) module to provide pixel‐wise weights and channel‐wise weights for input features. The authors place the DMA module between the encoder and decoder parts. As the network depth increases, the spatial structural information from the high‐resolution layer tends to degrade. To deal with the problem, the authors propose the Multi‐Scale Feature Fusion (MSFF) module to recover missing spatial structural information. The authors place the MSFF module in both the encoder and decoder parts. Extensive experimental results show that the authors’ proposed dehazing network achieves state‐of‐the‐art dehazing performance with relatively low computational cost.

Efficient site selection for clinical trials using simulated annealing.

1558 Background: Identifying sites with eligible patients for multi-site oncology clinical trials is challenging given increasingly complex inclusion/exclusion criteria, limited site resources, and the need to ensure diversity in trials. This is a complex systems problem with many factors that present nonlinear behaviors. Given manifold combinations of sites, research capabilities, and study characteristics, artificial intelligence solutions may help research sites and sponsors optimize site selection to achieve enrollment, speed, and diversity of goals. We report on one of the first deployments of a multi-AI model solution to optimize site selection for an ongoing clinical trial. Methods: The clinical trials were translated into a standardized digital form expressed as rules fully encompassing the inclusion and exclusion criteria. A patient cohort was created from the criteria using the ConcertAI oncology research database, including site affiliations. The sites had numerical features specific to the protocol indication, such as physician count and projected patient count. Each site was scored by its features with the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to create higher alignment to the best matched sites. Feature weights allowed TOPSIS to emphasize desirable attributes in an interpretable way. A simulated annealing algorithm, adept with nonlinear objectives, explored site combinations, yielding a high-scoring, constraint satisfying solution. Independent simulations measured convergence and provided a distribution of solutions. Shapley analysis clarified site contributions to score and constraints. The implementation was compiled and parallelized. Results: Utilizing a Multiple Myeloma clinical trial protocol with 7 criteria, we formed a cohort of 15,881 patients across 1,246 US clinical trial sites. Each site had 12 features. The weights optimized patient diversity while enrolling at least 10 patients per month across all sites to achieve the targeted study accrual timeline. The result was a set of 3 sites enrolling 12 patients per month with 51% diversity, in agreement with the optimal solution obtained through detailed, multi-week, manual analysis. As constraints increased, and exact verification became impractical, convergence was gauged by decreasing variance in independent solutions. Conclusions: Our study introduced a robust, efficient, and interpretable approach to clinical trial site selection. It addressed the challenges posed by increasingly complicated protocols, requirements for study participant diversity, and heterogeneous site features. The multi-AI model scalability underscored its practical utility in streamlining the site selection process for clinical research networks, academic centers, industry sponsored trials, cooperative group studies, and investigator-initiated studies.

AM-HNN based real-time voltage estimation method of distribution network using joint PMU and AMI data

A large amount of distributed energy access increases the risk of voltage fluctuation and off-limit voltage. Accurate voltage estimation is more and more important to ensure the safety of distribution networks. With the introduction of phasor measurement unit (PMU), multi-source measuring data with different time scales and measuring precision exist in distribution networks. How to fully integrate multi-source measurement data to achieve fast and accurate state estimation of distribution networks is an important prerequisite for efficient operation decision making. In this paper, a distribution network voltage state estimation method based on AM-HNN model is proposed. The attentional mechanism (AM) is introduced to mine the influence of PMU measurement data on voltage state estimation, and the feature weight is modified adaptively. The highway neural network (HNN) was used to fit the mapping relationship between the injected power of grid nodes and the voltage of key nodes. Taking the distribution network data of different scenes as an example, the superiority of the proposed optimal measurement model is verified by comparing with various voltage estimation methods.

An approach to bearing fault diagnosis based on ensemble learning and case-based reasoning

Abstract In response to the challenge of multiple fault types and complex diagnostic criteria in bearing fault diagnosis, a case reasoning method based on ensemble learning is proposed. The approach utilizes Case-Based Reasoning (CBR) to construct a case library for vibration-based features of rolling bearings and perform fault diagnosis. Moreover, addressing the issue of determining optimal feature weight ratios when retrieving similar cases in traditional case reasoning methods, a Random Forest algorithm combined with Bayesian Optimization is introduced. This integration allows for adaptive retrieval of similar cases, thereby enhancing the diagnostic capability for bearing faults. The effectiveness of this approach is validated through experimental analysis.

Residential electricity prediction based on GA-LSTM modeling

With residential electricity demand increasing year after year due to population growth and infrastructure expansion, accurate electricity load forecasting is critical to the operation of power systems. Although certain traditional machine learning models have achieved better results in several fields, their prediction accuracy for energy sources such as electricity is still unsatisfactory. The nonlinear and non-smooth consumption patterns of residential electricity make accurate prediction of electricity loads even more challenging. In this paper, we propose an attention-based competitive stochastic search method for training Long Short-Term Memory (LSTM) networks to predict electricity energy consumption. On the one hand, an attention layer is added to the traditional LSTM to assign feature weights; on the other hand, a genetic algorithm is introduced for stochastic search to prevent convergence to a local optimum during the training process. The experimental results show that the proposed model combines genetic algorithm and LSTM, and the prediction accuracy of the proposed model is higher than other existing prediction models in terms of root mean square error (RMSE), mean absolute error (MAE), r-square(R2), and mean absolute percentage error (MAPE), which are 0.6056, 0.3726, 0.8517, and 0.1856, respectively. In addition, the model also achieves excellent results in short-term prediction, which is better than the traditional LSTM, and the accuracy is significantly improved. It is proved that this method is effective and feasible in the prediction of power energy consumption.

MSTSENet: Multiscale Spectral–Spatial Transformer with Squeeze and Excitation network for hyperspectral image classification

Hyperspectral image (HSI) classification pertains to the task of assigning a single label to each pixel by analyzing its spectral–spatial characteristics. Convolutional Neural Networks (CNNs) have garnered significant attention on account of their remarkable performance in feature representation. However, these approaches possess a restricted capacity to acquire highly similar spectral features. Recently, Attention-based approaches have been devised as a means to surmount the limitations inherent in CNNs. In this paper, we address a novel architecture for spectral–spatial feature extraction and HSI classification. The framework efficiently amalgamates the robustness and efficacy of three modern backbone networks, i.e., Multiscale CNN, Squeeze and Excitation (SE), and Transformer named MSTSENet. Initially, the multiscale convolution module integrates three branches of 3D convolution layers, each employing distinct kernel sizes, facilitating multiscale and multi-resolution feature extraction. Subsequently, the SE module enhances the inter-channel relationship by adaptively recalibrating the feature weight. The strategic fusion of the SE module with multiscale CNN strengthens deep feature extraction while introducing a minimal increment in overall parameters. Lastly, the Transformer module orchestrates information aggregation across different spectral–spatial regions, accurately modeling long-range contextual dependencies and capturing dominant feature representations. To evaluate the model performance, comprehensive experiments have been carried out on widely used benchmark HSI datasets. The overall accuracy of 98.74%, 99.83%, and 99.98% is achieved over the Indian Pines, Pavia University, and Salinas Valley datasets, respectively. The code of this work will be accessible at https://github.com/irfan01000/MSTSENet.

Densely integrated multi-branch attentive net for image dehazing

Single image dehazing is a fundamental but challenging task in image processing. Various deep learning-based methods have achieved great dehazing performance. However, there are still hazy residues, even color distortion and texture loss when removing haze from complex outdoor images in dense hazy scenes. A densely integrated multi-branch attentive net for image dehazing is proposed in the paper to address the above problems. The network includes a multi-scale feature extraction module and a dense-feature fusion module. The multi-scale feature extraction module adopts a multi-branch structure composed of residual channel attention blocks, which can expand the receptive field and filter the extracted features of diverse scales by weighting for fusion. It raises network learning accuracy. The dense-feature fusion module contains a multi-level feature fusion module for front and back layers, a color information renovation module, and a feature enhancement module. It achieves dynamically adjusting the channel weights of features at diverse scales, learning rich context information and suppressing redundant information, and compensating for the lack of color and texture information. The dense-feature fusion module bolsters the generalization capability of the network. The proposed method achieves superior objective and subjective evaluation results via quantitative and qualitative experiments on synthetic hazy images and natural hazy images, with better generalization ability and dehazing effect than the current SOTA dehazing algorithms, and effectively ameliorates the color distortion and incomplete dehazing.

A hybrid feature weighted attention based deep learning approach for an intrusion detection system using the random forest algorithm.

Due to the recent advances in the Internet and communication technologies, network systems and data have evolved rapidly. The emergence of new attacks jeopardizes network security and make it really challenging to detect intrusions. Multiple network attacks by an intruder are unavoidable. Our research targets the critical issue of class imbalance in intrusion detection, a reflection of the real-world scenario where legitimate network activities significantly out number malicious ones. This imbalance can adversely affect the learning process of predictive models, often resulting in high false-negative rates, a major concern in Intrusion Detection Systems (IDS). By focusing on datasets with this imbalance, we aim to develop and refine advanced algorithms and techniques, such as anomaly detection, cost-sensitive learning, and oversampling methods, to effectively handle such disparities. The primary goal is to create models that are highly sensitive to intrusions while minimizing false alarms, an essential aspect of effective IDS. This approach is not only practical for real-world applications but also enhances the theoretical understanding of managing class imbalance in machine learning. Our research, by addressing these significant challenges, is positioned to make substantial contributions to cybersecurity, providing valuable insights and applicable solutions in the fight against digital threats and ensuring robustness and relevance in IDS development. An intrusion detection system (IDS) checks network traffic for security, availability, and being non-shared. Despite the efforts of many researchers, contemporary IDSs still need to further improve detection accuracy, reduce false alarms, and detect new intrusions. The mean convolutional layer (MCL), feature-weighted attention (FWA) learning, a bidirectional long short-term memory (BILSTM) network, and the random forest algorithm are all parts of our unique hybrid model called MCL-FWA-BILSTM. The CNN-MCL layer for feature extraction receives data after preprocessing. After convolution, pooling, and flattening phases, feature vectors are obtained. The BI-LSTM and self-attention feature weights are used in the suggested method to mitigate the effects of class imbalance. The attention layer and the BI-LSTM features are concatenated to create mapped features before feeding them to the random forest algorithm for classification. Our methodology and model performance were validated using NSL-KDD and UNSW-NB-15, two widely available IDS datasets. The suggested model's accuracies on binary and multi-class classification tasks using the NSL-KDD dataset are 99.67% and 99.88%, respectively. The model's binary and multi-class classification accuracies on the UNSW-NB15 dataset are 99.56% and 99.45%, respectively. Further, we compared the suggested approach with other previous machine learning and deep learning models and found it to outperform them in detection rate, FPR, and F-score. For both binary and multiclass classifications, the proposed method reduces false positives while increasing the number of true positives. The model proficiently identifies diverse network intrusions on computer networks and accomplishes its intended purpose. The suggested model will be helpful in a variety of network security research fields and applications.

Identification of Airline Turbulence Using WOA-CatBoost Algorithm in Airborne Quick Access Record (QAR) Data

Turbulence is a significant operational aviation safety hazard during all phases of flight. There is an urgent need for a method of airline turbulence identification in aviation systems to avoid turbulence hazards to aircraft during flight. Integrating flight data and machine learning significantly enhances the efficacy of turbulence identification. Nevertheless, present studies encounter issues including unstable model performance, challenges in data feature extraction, and parameter optimization. Hence, it is imperative to propose a superior approach to enhance the accuracy of turbulence identification along airline. The paper presents a combined swarm intelligence and machine learning model based on data mining for identifying airline turbulence. Based on the theory of swarm-intelligence-based optimization algorithm, the optimal parameters of Categorical Boosting (CatBoost) are obtained by introducing the whale optimization algorithm (WOA), and the corresponding WOA-CatBoost fusion model is established. Then, the Recursive Feature Elimination algorithm (RFE) is used to eliminate the data with lower feature weights, extract the effective features of the data, and the combination with the WOA brings robust optimization effects, whereby the accuracy of CatBoost increased by 11%. The WOA-CatBoost model can perform accurate turbulence identification from QAR data, comparable to that with established EDR approaches and outperforms traditional machine learning models. This discovery highlights the effectiveness of combining swarm intelligence and machine learning algorithms in turbulence monitoring systems to improve aviation safety.

An Attention-Based Full-Scale Fusion Network for Segmenting Roof Mask from Satellite Images

Accurately segmenting building roofs from satellite images is crucial for evaluating the photovoltaic power generation potential of urban roofs and is a worthwhile research topic. In this study, we propose an attention-based full-scale fusion (AFSF) network to segment a roof mask from the given satellite images. By developing an attention-based residual ublock, the channel relationship of the feature maps can be modeled. By integrating attention mechanisms in multi-scale feature fusion, the model can learn different weights for features of different scales. We also design a ladder-like network to utilize weakly labeled data, thereby achieving pixel-level semantic segmentation tasks assisted by image-level classification tasks. In addition, we contribute a new roof segmentation dataset, which is based on satellite images and uses the roof as the segmentation target rather than the entire building to further promote the algorithm research of estimating roof area using satellite images. The experimental results on the new roof segmentation dataset, WHU dataset, and IAIL dataset demonstrate the effectiveness of the proposed network.

AM-MSFF: A Pest Recognition Network Based on Attention Mechanism and Multi-Scale Feature Fusion.

Traditional methods for pest recognition have certain limitations in addressing the challenges posed by diverse pest species, varying sizes, diverse morphologies, and complex field backgrounds, resulting in a lower recognition accuracy. To overcome these limitations, this paper proposes a novel pest recognition method based on attention mechanism and multi-scale feature fusion (AM-MSFF). By combining the advantages of attention mechanism and multi-scale feature fusion, this method significantly improves the accuracy of pest recognition. Firstly, we introduce the relation-aware global attention (RGA) module to adaptively adjust the feature weights of each position, thereby focusing more on the regions relevant to pests and reducing the background interference. Then, we propose the multi-scale feature fusion (MSFF) module to fuse feature maps from different scales, which better captures the subtle differences and the overall shape features in pest images. Moreover, we introduce generalized-mean pooling (GeMP) to more accurately extract feature information from pest images and better distinguish different pest categories. In terms of the loss function, this study proposes an improved focal loss (FL), known as balanced focal loss (BFL), as a replacement for cross-entropy loss. This improvement aims to address the common issue of class imbalance in pest datasets, thereby enhancing the recognition accuracy of pest identification models. To evaluate the performance of the AM-MSFF model, we conduct experiments on two publicly available pest datasets (IP102 and D0). Extensive experiments demonstrate that our proposed AM-MSFF outperforms most state-of-the-art methods. On the IP102 dataset, the accuracy reaches 72.64%, while on the D0 dataset, it reaches 99.05%.

ERSegDiff: a diffusion-based model for edge reshaping in medical image segmentation

Medical image segmentation is a crucial field of computer vision. Obtaining correct pathological areas can help clinicians analyze patient conditions more precisely. We have observed that both CNN-based and attention-based neural networks often produce rough segmentation results around the edges of the regions of interest. This significantly impacts the accuracy of obtaining the pathological areas. Without altering the original data and model architecture, further refining the initial segmentation outcomes can effectively address this issue and lead to more satisfactory results. Recently, diffusion models have demonstrated outstanding results in image generation, showcasing their powerful ability to model distributions. We believe that this ability can greatly enhance the accuracy of the reshaping results. This research proposes ERSegDiff, a neural network based on the diffusion model for reshaping segmentation borders. The diffusion model is trained to fit the distribution of the target edge area and is then used to modify the segmentation edge to produce more accurate segmentation results. By incorporating prior knowledge into the diffusion model, we can help it more accurately simulate the edge probability distribution of the samples. Moreover, we introduce the edge concern module, which leverages attention mechanisms to produce feature weights and further refine the segmentation outcomes. To validate our approach, we employed the COVID-19 and ISIC-2018 datasets for lung segmentation and skin cancer segmentation tasks, respectively. Compared with the baseline model, ERSegDiff improved the dice score by 3%–4% and 2%–4%, respectively, and achieved state-of-the-art scores compared to several mainstream neural networks, such as swinUNETR.

Discriminative label correlation based robust structure learning for multi-label feature selection

Feature selection is a key technique to tackle the curse of dimensionality in multi-label learning. Lots of embedded multi-label feature selection methods have been developed. However, they face challenges in identifying and excluding redundant features. To address these issues, this paper proposes a multi-label feature selection method that combines robust structural learning and discriminative label regularization. The proposed method starts from the feature space rather than data space, motivated by the principle that redundant features have high similarity or strong correlation. To exclude redundant features, a regularization on the feature selection matrix is designed by combining ℓ2,1-norm penalty with inner products of feature weight vectors. This regularization can help to learn a robust structure in the feature selection matrix. Meanwhile, both of the similarity and dissimilarity of labels of instances are involved in exploring discriminative label correlations. Extensive experiments verified the effectiveness of the proposed model for feature selection.

EFNN-Nul0- a trustworthy knowledge extraction about stress identification through evolving fuzzy neural networks

This paper presents a novel hybrid architecture, denoted as EFNN-Nul0 (evolving neuro-fuzzy system based on null-unineurons), meticulously crafted for stress identification within the realm of pattern classification. The model seamlessly integrates neural networks, fuzzy systems, and n-uninorms to cultivate knowledge within an adaptive, real-time learning context. Neuro-fuzzy rules, encapsulating interdependencies among input features through IF-THEN type relationships, are formulated utilizing null-unineurons derived from n-uninorms. This construction enables the articulation of both AND- and OR-connections, thereby augmenting the interpretability of the generated rules. The evolution of neurons is facilitated by an extended adaptation of the autonomous data partition method (ADPA). To dynamically interpret the evolution of rules, the paper introduces (i) a mechanism that tracks changes in rules over data stream samples, providing insights into the process dynamics as a structural active learning component, and (ii) a concept for incrementally updating feature weights. These weights encapsulate the varying impact levels of features on stress identification, enabling the reduction of rule length by effectively masking out less significant features. The outcomes of the rules are represented by certainty vectors, recursively updated through an indicator-based recursive weighted least squares (I-RWLS) approach. Neuron activation levels play a pivotal role in determining the weights, ensuring stable local learning. The effectiveness of the proposed model is substantiated through a comprehensive comparison with existing hybrid and evolving approaches in the literature, focusing on binary and multi-class pattern classification. Aspects that identify special characteristics of neuro-fuzzy models related to interpretability will also be demonstrated in this work. The results demonstrate the model's superior performance, characterized by consistently higher accuracy trend lines over time. Furthermore, the model's interpretability is underscored by the coherent neuro-fuzzy rules, contributing to its remarkable accuracy (the EFNN-Nul0 achieved approximately 99% accuracy in stress identification), establishing its efficacy in addressing stress identification within classification problems.

An intelligent assessment method of criminal psychological attribution based on unbalance data

Criminal cases often exhibit imbalance and cannot be extended by data augmentation when classified into attribution types. To solve the problem of unbalance data in offenders’ attribution classification, this paper proposes a criminal psychological attribution assessment model by an improved Balanced TF-Distinguishing IDF method (B-TF-dIDF) and constructed a hybrid network with attention method to fuse numerical and text features for improving the accuracy. First, as a statistical method, B-TF-dIDF is presented to reduce the impact of class-imbalance for extraction of numerical features, in which a balanced element is added to reduce the effects of incorrect type keywords on classification, and a distinguishing element is added to discriminate the types of keywords. Then, an improved hybrid network model composed of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) is constructed to balance the influence of different lengths of text samples for extracting the semantic features of criminal texts. For evaluating different feature weights by their importance, Spatial Attention is used to improve CNN in the feature maps. Moreover, the self-attention is also performed to re-evaluate the mixed features. Finally, the softmax classifier provides a scientific basis for developing a hierarchical treatment mechanism further. Additionally, we build a criminal data set with labels from real cases for testing. The experiment proved that the proposed model is better than other related methods in various evaluation indicators, including the micro and macro scopes. Moreover, the F1 of minority samples has increased by 6%–8%, indicating that the proposed method can reduce the impact of class-imbalance.