Application of Broad Learning System for Image Classification Based on Deep Features

The classification of hyperspectral images (HSIs) is one of the most popular topics in the remote sensing community. Numerous feature extraction methods have been proposed to improve the classification accuracy of HSIs. Recently, deep features extracted by convolution neural network (CNN) have been introduced into the classification process of HSIs. Due to the nonlinear and invariant advantages of the features, CNN methods provide a powerful tool for representing geographic objects and classifying HSIs. However, traditional deep features only extracted at pixel-level and often neglect multiscale characteristics of geographic objects. In this study, a new deep feature extraction method is proposed, which takes advantage of multi-scale object analysis and the CNN model. Firstly, multiscale image objects are obtained by the multiscale segmentation algorithm and multiscale low-level features of objects are extracted. Secondly, the CNN is devoted to obtain deep features from low-level object features at each scale, respectively. Thirdly, the obtained deep features at all scales are stacked and fed to one fully connected layer to extract the multiscale deep learning features for classification. Finally, the logistic regression classifier is applied to hyperspectral image (HSI) classification based on object-oriented multiscale deep features. The proposed method was carried out on three widely used hyperspectral data sets: University of Pavia, Salinas, and Washington DC. The results reveal that the proposed method provides better results than other state-of-the-art methods.

Network intrusion detection systems are an important defense technology to guarantee information security and protect a network from attacks. In recent years, the broad learning system has attracted much attention and has been introduced into intrusion detection systems with some success. However, since the traditional broad learning system is a simple linear structure, when dealing with imbalanced datasets, it often ignores the feature learning of minority class samples, leading to a poorer recognition rate of minority class samples. Secondly, the high dimensionality and redundant features in intrusion detection datasets also seriously affect the training time and detection performance of the traditional broad learning system. To address the above problems, we propose a deep belief network broad equalization learning system. The model fully learns the large-scale high-dimensional dataset via a deep belief network and represents it as an optimal low-dimensional dataset, and then introduces the equalization loss v2 reweighing idea into the broad learning system and learns to classify the low-dimensional dataset via a broad equalization learning system. The model was experimentally tested using the CICIDS2017 dataset and fully validated using the CICIDS2018 dataset. Compared with other algorithms in the same field, the model shortens the training time and has a high detection rate and a low false alarm rate.

Determining potential applications for personalized college English instruction through deep feature extraction and scene feature mining is essential for enabling Deep Learning assisted AI systems to generate effective educational outcomes. Traditional instructional approaches often struggle within dynamic digital environments, as they overlook variations in students’ learning styles, engagement levels, and behavioral patterns. This research proposes a hybrid methodology that integrates Convolutional Neural Networks for deep audio feature extraction with Random Forest algorithms for contextual and scene feature mining. The objective is to construct a personalized learning environment capable of adapting dynamically in real time to individual learner behaviors and preferences. A hybrid deep learning model is introduced to predict teaching effectiveness using speech related features such as clarity, rhythm, and engagement level. Feature fusion is employed by combining audio based deep features with contextual scene features to classify teaching effectiveness into three categories: low, medium, and high. Experimental results demonstrate strong predictive performance, achieving an accuracy of 0.9900, precision of 0.9906, recall of 0.9907, and an F1 measure of 0.9905, with minimal performance fluctuations. This AI assisted instructional framework enables college English teachers to enhance teaching quality by receiving immediate, data driven feedback, ultimately fostering improved student centered learning experiences.

The goal of infrared and visible image fusion is to generate a fused image that possesses the prominent attributes of infrared image and the rich textures of visible image. Current deep learning-based methods typically involve three main steps: feature extraction, feature fusion, and reconstruction. Extracting multi-scale features during the feature extraction stage is beneficial for fully utilizing deep features. Shallow image features exhibit higher resolution and contain more textures, while deep image features have lower resolution but stronger semantic information after more pooling and convolution. Existing methods use the same network to process features of different scales, while ignoring their differences. Moreover, they lack carefully designed texture preservation modules, leading to insufficient preservation of texture in the fused images. To overcome these issues, we propose a novel end-to-end fusion network for infrared and visible images where we develop a scaling-down network and texture attention. Based on the characteristics of features at different scales, we design a scaling-down fusion network that use deeper and more complex network to process shallow features, while using more streamlined network to process deep features. In order to better preserve image textures, we design texture attention in a relatively gentle way that focus on feature channels have rich textures to achieve the goal. We conducted experiments on publicly available datasets, and the results demonstrate that our method surpasses eleven state-of-the-art methods in terms of fusion performance. This conclusion has been verified through both subjective evaluation and objective evaluation.

Stream label distribution learning processing via broad learning system

Automated ASD detection using hybrid deep lightweight features extracted from EEG signals

340P Prediction of relapse in colon cancer patients by machine learning models combining radiomics and deep features extracted from baseline computed tomography

Emerging evidence suggests that the use of artificial intelligence can assist in the timely detection and optimization of therapeutic approach in patients with prostate cancer. The conventional perspective on radiomics encompassing segmentation and the extraction of radiomic features considers it as an independent and sequential process. However, it is not necessary to adhere to this viewpoint. In this study, we show that besides generating masks from which radiomic features can be extracted, prostate segmentation and reconstruction models provide valuable information in their feature space, which can improve the quality of radiomic signatures models for disease aggressiveness classification. We perform 2,244 experiments with deep learning features extracted from 13 different models trained using different anatomic zones and characterize how modeling decisions, such as deep feature aggregation and dimensionality reduction, affect performance. While models using deep features from full gland and radiomic features consistently lead to improved disease aggressiveness prediction performance, others are detrimental. Our results suggest that the use of deep features can be beneficial, but an appropriate and comprehensive assessment is necessary to ensure that their inclusion does not harm predictive performance. The study findings reveal that incorporating deep features derived from autoencoder models trained to reconstruct the full prostate gland (both zonal models show worse performance than radiomics only models), combined with radiomic features, often lead to a statistically significant increase in model performance for disease aggressiveness classification. Additionally, the results also demonstrate that the choice of feature selection is key to achieving good performance, with principal component analysis (PCA) and PCA + relief being the best approaches and that there is no clear difference between the three proposed latent representation extraction techniques.

A comparative study of statistical, radiomics, and deep learning feature extraction techniques for medical image classification in optical and radiological modalities.

High accuracy of text classification can be achieved through simultaneous learning of multiple information, such as sequence information and word importance. In this article, a kind of flat neural networks called the broad learning system (BLS) is employed to derive two novel learning methods for text classification, including recurrent BLS (R-BLS) and long short-term memory (LSTM)-like architecture: gated BLS (G-BLS). The proposed two methods possess three advantages: 1) higher accuracy due to the simultaneous learning of multiple information, even compared to deep LSTM that extracts deeper but single information only; 2) significantly faster training time due to the noniterative learning in BLS, compared to LSTM; and 3) easy integration with other discriminant information for further improvement. The proposed methods have been evaluated over 13 real-world datasets from various types of text classification. From the experimental results, the proposed methods achieve higher accuracies than LSTM while taking significantly less training time on most evaluated datasets, especially when the LSTM is in deep architecture. Compared to R-BLS, G-BLS has an extra forget gate to control the flow of information (similar to LSTM) to further improve the accuracy on text classification so that G-BLS is more effective while R-BLS is more efficient.

e20611 Background: Predicting immunotherapy response in advanced non-small cell lung cancer (NSCLC) through non-invasive means could be a groundbreaking advancement. Deep features extracted from medical images by deep Convolutional Neural Networks (CNNs) along with radiomics have demonstrated promising results in different oncologic diseases. However, the method for extracting these deep features influences the predictive capabilities of the model. Methods: A retrospective analysis of a multicenter study was conducted in advanced NSCLC patients with high PD-L1 expression with the aim of developing an imaging features-based model for the prediction of best overall response (BOR) to a checkpoint inhibitor immunotherapy. All visible lung lesions, beyond RECIST 1.1, were manually segmented in baseline CT scans. Radiomics features were extracted at lesion-level, and various preprocessing methods and CNN architectures were tested for deep features extraction. Radiomics and deep features were harmonized using ComBat methodology. A distinctive feature signature was created for each patient by calculating the mean across all lesions. Using this data, machine learning models were trained to predict treatment response, specifically distinguishing between complete response (CR) and partial response (PR) from stable disease (SD) and progressive disease (PD). The study compared the performance of different deep features extraction methods and assessed shapley additive explanations (SHAP) values of radiomics for interpretability. Results: In the cohort of 116 patients (mean age: 67, 93% ever-smokers, 73% male), 1024 to 5475 quantitative imaging features per lesion were extracted. Among these patients, 67 patients were CR+PR, and 49 were SD+PD. The top-performing predictive model, trained with radiomics and deep features from a deep convolutional autoencoder, achieved an average AUC of 85%. SHAP values showed that impactful radiomics features were correlated with intensity changes in adjacent pixels describing the tumor heterogeneity, along with shape features potentially associated with malignancy. Ultimately, combining both features demonstrated statistical significance, leading to a performance improvement of ~2-5% compared to models exclusively using deep features. Conclusions: Diverse techniques for extracting deep features were evaluated, revealing autoencoder training as the most effective strategy for predicting immunotherapy response. Consequently, the findings suggest that employing deep learning to extract imaging features from baseline CT scans, combined with radiomics, represents a promising non-invasive approach for the predicting immunotherapy outcomes in advanced NSCLC patients.

Glioblastoma is a highly aggressive brain tumor with limited survival that poses challenges in predicting patient outcomes. The Karnofsky Performance Status (KPS) score is a valuable tool for assessing patient functionality and contributes to the stratification of patients with poor prognoses. This study aimed to develop a 6-month postoperative KPS prediction model by combining clinical data with deep learning-based image features from pre- and postoperative MRI scans, offering enhanced personalized care for glioblastoma patients. Using 1,476 MRI datasets from the Brain Tumor Segmentation Challenge 2020 public database, we pretrained two variational autoencoders (VAEs). Imaging features from the latent spaces of the VAEs were used for KPS prediction. Neural network-based KPS prediction models were developed to predict scores below 70 at 6 months postoperatively. In this retrospective single-center analysis, we incorporated clinical parameters and pre- and postoperative MRI images from 150 newly diagnosed IDH wild-type glioblastoma, divided into training (100 patients) and test (50 patients) sets. In training set, the performance of these models was evaluated using the area under the curve (AUC), calculated through fivefold cross-validation repeated 10 times. The final evaluation of the developed models assessed in the test set. Among the 150 patients, 61 had 6-month postoperative KPS scores below 70 and 89 scored 70 or higher. We developed three models: a clinical-based model, an MRI-based model, and a multimodal model that incorporated both clinical parameters and MRI features. In the training set, the mean AUC was 0.785±0.051 for the multimodal model, which was significantly higher than the AUCs of the clinical-based model (0.716±0.059, P = 0.038) using only clinical parameters and the MRI-based model (0.651±0.028, P<0.001) using only MRI features. In the test set, the multimodal model achieved an AUC of 0.810, outperforming the clinical-based (0.670) and MRI-based (0.650) models. The integration of MRI features extracted from VAEs with clinical parameters in the multimodal model substantially enhanced KPS prediction performance. This approach has the potential to improve prognostic prediction, paving the way for more personalized and effective treatments for patients with glioblastoma.

Wind speed forecasting is important for high‐efficiency utilisation of wind energy and management of grid‐connected power systems. Due to the noise, instability and irregularity of atmosphere system, the current models based on raw historical data have encountered many problems. In this study, a deep novel feature extraction approach is developed based on stacked denoising autoencoders and batch normalisation. Then the deep features extracted from raw historical data are fed to long short‐term memory (LSTM) neural networks for prediction. Meanwhile, density‐based spatial clustering of applications with noise is employed to process the numerical weather prediction data. By picking out the abnormal samples, the representative training samples are selected to improve the efficiency of the model. For illustration and verification purposes, the proposed model is used to predict the wind speed of Wind Atlas for South Africa (WASA). Empirical results show that deep feature extraction can improve the forecasting accuracy of LSTM 49% than feature selection, indicating that proper feature extraction is crucial to wind speed forecasting. And the proposed model outperforms other benchmark methods at least 17%. Hence, the proposed model is promising for wind speed forecasting.

An Adaptive Multi-Feature Fusion Network for Predicting Overall Survival of Patients with Head and Neck Cancer

Knee osteoarthritis (KOA) grading from x‐ray images is important for supporting effective treatment planning. Yet it remains difficult due to the disease's complex presentation. Subtle anatomical changes add to the challenge. The subjectivity of manual evaluation further complicates the process. Such challenges highlight the importance of automated, objective, and reproducible computer‐aided systems capable of leveraging complementary sources of information. In line with this, a joint fusion framework was developed to integrate optimized traditional image features with deep learning representations obtained from multiple pre‐trained convolutional neural network models. Traditional features, including morphological, statistical, texture‐based, and other clinically relevant descriptors, provide interpretable insights into bone structure and tissue characteristics. In parallel, deep features capture intricate spatial patterns and semantic details beyond the reach of manual modeling. For improved discrimination and efficiency, analysis of variance and linear discriminant analysis were used for selecting traditional features, while principal component analysis was applied to deep features to retain 85% variance. The two feature sets were combined using a Joint Fusion Type II approach, and class imbalance was mitigated through synthetic minority oversampling. A neural network was trained to capture interdependencies between these features. Experimental results on a benchmark KOA dataset indicated that fusion with VGG16 deep features achieved 85.39% accuracy, outperforming individual feature‐based approaches. The framework maintained relatively high accuracy across all five KOA grades, including borderline cases, indicating its potential for consistent and clinically relevant KOA grading.