Hierarchical Convolutional Neural Network Research Articles

Hierarchical Convolutional Neural Network with Knowledge Complementation for Long-Tailed Classification

Existing methods based on transfer learning leverage auxiliary information to help tail generalization and improve the performance of the tail classes. However, they cannot fully exploit the relationships between auxiliary information and tail classes and bring irrelevant knowledge to the tail classes. To solve this problem, we propose a hierarchical CNN with knowledge complementation, which regards hierarchical relationships as auxiliary information and transfers relevant knowledge to tail classes. First, we integrate semantics and clustering relationships as hierarchical knowledge into the CNN to guide feature learning. Then, we design a complementary strategy to jointly exploit the two types of knowledge, where semantic knowledge acts as a prior dependence and clustering knowledge reduces the negative information caused by excessive semantic dependence (i.e., semantic gaps). In this way, the CNN facilitates the utilization of the two complementary hierarchical relationships and transfers useful knowledge to tail data to improve long-tailed classification accuracy. Experimental results on public benchmarks show that the proposed model outperforms existing methods. In particular, our model improves accuracy by 3.46% compared with the second-best method on the long-tailed tieredImageNet dataset.

In vivo EPID-based daily treatment error identification for volumetric-modulated arc therapy in head and neck cancers with a hierarchical convolutional neural network: a feasibility study.

We proposed a deep learning approach to classify various error types in daily VMAT treatment of head and neck cancer patients based on EPID dosimetry, which could provide additional information to support clinical decisions for adaptive planning. 146 arcs from 42 head and neck patients were analyzed. Anatomical changes and setup errors were simulated in 17,820 EPID images of 99 arcs obtained from 30 patients using in-house software for model training, validation, and testing. Subsequently, 141 clinical EPID images from 47 arcs belonging to the remaining 12 patients were utilized for clinical testing. The hierarchical convolutional neural network (HCNN) model was trained to classify error types and magnitudes using EPID dose difference maps. Gamma analysis with 3%/2mm (dose difference/distance to agreement) criteria was also performed. The F1 score, a combination of precision and recall, was utilized to evaluate the performance of the HCNN model and gamma analysis. The adaptive fractioned doses were calculated to verify the HCNN classification results. For error type identification, the overall F1 score of the HCNN model was 0.99 and 0.91 for primary type and subtype identification, respectively. For error magnitude identification, the overall F1 score in the simulation dataset was 0.96 and 0.70 for the HCNN model and gamma analysis, respectively; while the overall F1 score in the clinical dataset was 0.79 and 0.20 for the HCNN model and gamma analysis, respectively. The HCNN model-based EPID dosimetry can identify changes in patient transmission doses and distinguish the treatment error category, which could potentially provide information for head and neck cancer treatment adaption.

Hierarchical Convolutional Attention Network for Depression Detection on Social Media and Its Impact During Pandemic.

People across the globe have felt and are still going through the impact of COVID-19. Some of them share their feelings and suffering online via different online social media networks such as Twitter. Due to strict restrictions to reduce the spread of the novel virus, many people are forced to stay at home, which significantly impacts people's mental health. It is mainly because the pandemic has directly affected the lives of the people who were not allowed to leave home due to strict government restrictions. Researchers must mine the related human-generated data and get insights from it to influence government policies and address people's needs. In this paper, we study social media data to understand how COVID-19 has impacted people's depression. We share a large-scale COVID-19 dataset that can be used to analyze depression. We also have modeled the tweets of depressed and non-depressed users before and after the start of the COVID-19 pandemic. To this end, we developed a new approach based on Hierarchical Convolutional Neural Network (HCN) that extracts fine-grained and relevant content on user historical posts. HCN considers the hierarchical structure of user tweets and contains an attention mechanism that can locate the crucial words and tweets in a user document while also considering the context. Our new approach is capable of detecting depressed users occurring within the COVID-19 time frame. Our results on benchmark datasets show that many non-depressed people became depressed during the COVID-19 pandemic.

Application of one-dimensional hierarchical network assisted screening for cervical cancer based on Raman spectroscopy combined with attention mechanism

Cervical cancer is one of the most common malignant tumors among women, and its pathological change is a relatively slow process. If it can be detected in time and treated properly, it can effectively reduce the incidence rate and mortality rate of cervical cancer, so the early screening of cervical cancer is particularly critical and significant. In this paper, we used Raman spectroscopy technology to collect the tissue sample data of patients with cervicitis, Low-grade Squamous Intraepithelial Lesion, High-grade Squamous Intraepithelial Lesion, Well differentiated squamous cell carcinoma, Moderately differentiated squamous cell carcinoma, Poorly differentiated squamous cell carcinoma and cervical adenocarcinoma. A one-dimensional hierarchical convolutional neural network based on attention mechanism was constructed to classify and identify seven types of tissue samples. The attention mechanism Efficient Channel Attention Networks module and Squeeze-and-Excitation Networks module were combined with the established one-dimensional convolutional hierarchical network model, and the results showed that the combined model had better diagnostic performance. The average accuracy, F1, and AUC of the Principal Component Analysis-Squeeze and Excitation-hierarchical network model after 5-fold cross validations could reach 96.49%±2.12%, 0.9663±0.0253, and 0.9815±0.0224, respectively, which were 1.58%, 0.0140, and 0.008 higher than those of hierarchical network. The recall rate of the Principal Component Analysis-Efficient Channel Attention-hierarchical network model was as high as 96.78%±2.85%, which is 1.47% higher than hierarchical network. Compared with the classification results of traditional CNN and ResNet for seven types of cervical cancer staging, the accuracy of the Principal Component Analysis-Squeeze and Excitation-hierarchical network model is 3.33% and 11.05% higher, respectively. The experimental results indicate that the model established in this study is easy to operate and has high accuracy. It has good reference value for rapid screening of cervical cancer, laying a foundation for further research on Raman spectroscopy as a clinical diagnostic method for cervical cancer.

End-to-End Network Intrusion Detection Based on Contrastive Learning.

The network intrusion detection system (NIDS) plays a crucial role as a security measure in addressing the increasing number of network threats. The majority of current research relies on feature-ready datasets that heavily depend on feature engineering. Conversely, the increasing complexity of network traffic and the ongoing evolution of attack techniques lead to a diminishing distinction between benign and malicious network behaviors. In this paper, we propose a novel end-to-end intrusion detection framework based on a contrastive learning approach. We design a hierarchical Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) model to facilitate the automated extraction of spatiotemporal features from raw traffic data. The integration of contrastive learning amplifies the distinction between benign and malicious network traffic in the representation space. The proposed method exhibits enhanced detection capabilities for unknown attacks in comparison to the approaches trained using the cross-entropy loss function. Experiments are carried out on the public datasets CIC-IDS2017 and CSE-CIC-IDS2018, demonstrating that our method can attain a detection accuracy of 99.9% for known attacks, thus achieving state-of-the-art performance. For unknown attacks, a weighted recall rate of 95% can be achieved.

MultiScaleCrackNet: A parallel multiscale deep CNN architecture for concrete crack classification

Structural health monitoring plays a crucial role in assessing the condition of civil structures and ensuring their safety and maintenance. One important aspect of structural assessment is the detection and analysis of cracks, which can occur in various structures such as bridges, buildings, tunnels, dams, monuments, and roadways. Recent advancements in crack classification and segmentation techniques have utilized convolutional neural network (CNN) variations. In this paper, we propose an end-to-end learning approach utilizing a deep hierarchical CNN for crack region identification. The proposed architecture leverages high pass kernels in the early convolutional layers to accurately capture the crack patterns, complemented by learnable filters to facilitate adaptive learning. Furthermore, parallel channels within the network enable the learning of cracks at multiple scales, accommodating the varying severity and characteristics of cracks. The model is trained using data at different scales and levels, ensuring comprehensive learning from the lowest to the highest convolutional layers. To validate the effectiveness of our approach, we conducted experimental evaluations using end-to-end training on the Concrete Crack Images for Classification dataset, Asphalt Crack Dataset, and SDNET2018 dataset for crack classification. The results demonstrate the robustness and efficacy of the proposed methodology in accurately identifying crack regions across different datasets.

Multi-task hierarchical convolutional network for visual-semantic cross-modal retrieval

Bridging visual and textual representations plays a central role in delving into multimedia data understanding. The main challenge arises from that images and texts exist in heterogeneous spaces, leading to the difficulty to preserve the semantic consistency between both modalities. To narrow the modality gap, most recent methods resort to extra object detectors or parsers to obtain the hierarchical representations. In this work, we address this problem by introducing our Multi-Task Hierarchical Convolutional Neural Network (MT-HCN). It is characterized by mining the hierarchical semantic information without the aid of any extra supervisions. Firstly, from the perspective of representing architecture, we leverage the intrinsic hierarchical structure of Convolutional Neural Networks (CNNs) to decompose the representations of both modalities into two semantically complementary levels, i.e., exterior representations and concept representations. The former focuses on discovering the fine-grained low-level associations between both modalities, meanwhile the latter underlines capturing more high-level abstract semantics. Specifically, we present a Self-Supervised Clustering (SSC) loss to preserve more fine-grained semantic clues in exterior representations. It is constituted on the basis of viewing multiple image/text pairs with similar exterior as a category. In addition, a novel harmonious bidirectional triplet ranking (HBTR) loss is proposed, which mitigate the adverse effects brought about by the biased and noisy negative samples. Besides hardest negatives, it also imposes the constraints on the distance between the positive pairs and the centroid of negative pairs. Extensive experimental results on two popular cross-modal retrieval benchmarks demonstrate our proposed MT-HCN can achieve the competitive results compared with the state-of-the-art methods.

AI-based automated detection and stability analysis of traumatic vertebral body fractures on computed tomography

PurposeWe developed and tested a neural network for automated detection and stability analysis of vertebral body fractures on computed tomography (CT). Materials and Methods257 patients who underwent CT were included in this Institutional Review Board (IRB) approved study. 463 fractured and 1883 non-fractured vertebral bodies were included, with 190 fractures unstable. Two readers identified vertebral body fractures and assessed their stability. A combination of a Hierarchical Convolutional Neural Network (hNet) and a fracture Classification Network (fNet) was used to build a neural network for the automated detection and stability analysis of vertebral body fractures on CT. Two final test settings were chosen: one with vertebral body levels C1/2 included and one where they were excluded. ResultsThe mean age of the patients was 68 ± 14 years. 140 patients were female. The network showed a slightly higher diagnostic performance when excluding C1/2. Accordingly, the network was able to distinguish fractured and non-fractured vertebral bodies with a sensitivity of 75.8 % and a specificity of 80.3 %. Additionally, the network determined the stability of the vertebral bodies with a sensitivity of 88.4 % and a specificity of 80.3 %. The AUC was 87 % and 91 % for fracture detection and stability analysis, respectively. The sensitivity of our network in indicating the presence of at least one fracture / one unstable fracture within the whole spine achieved values of 78.7 % and 97.2 %, respectively, when excluding C1/2. ConclusionThe developed neural network can automatically detect vertebral body fractures and evaluate their stability concurrently with a high diagnostic performance.

Electrical synapses for a pooling layer of the convolutional neural network in retinas.

We have an example of a synergetic effect between neuroscience and connectome via artificial intelligence. The invention of Neocognitron, a machine learning algorithm, was inspired by the visual cortical circuitry for complex cells to be made by combinations of simple cells, which uses a hierarchical convolutional neural network (CNN). The CNN machine learning algorithm is powerful in classifying neuron borderlines on electron micrograph images for automatized connectomic analysis. CNN is also useful as a functional framework to analyze the neurocircuitry of the visual system. The visual system encodes visual patterns in the retina and decodes them in the corresponding cortical areas. The knowledge of evolutionarily chosen mechanisms in retinas may help the innovation of new algorithms. Since over a half-century ago, a classical style of serial section transmission electron microscopy has vastly contributed to cell biology. It is still useful to comprehensively analyze the small area of retinal neurocircuitry that is rich in natural intelligence of pattern recognition. I discuss the perspective of our study on the primary rod signal pathway in mouse and macaque retinas with special reference to electrical synapses. Photon detection under the scotopic condition needs absolute sensitivity but no intricate pattern recognition. This extreme case is regarded as the most simplified pattern recognition of the input with no autocorrelation. A comparative study of mouse and macaque retinas, where exists the 7-fold difference in linear size, may give us the underlying principle with quantitative verification of their adaptational designs of neurocircuitry.

Decoding Optical Responses of Contact-Printed Arrays of Thermotropic Liquid Crystals Using Machine Learning: Detection and Reporting of Aqueous Amphiphiles with Enhanced Sensitivity and Selectivity.

Surfactants and other amphiphilic molecules are used extensively in household products, industrial processes, and biological applications and are also common environmental contaminants; as such, methods that can detect, sense, or quantify them are of great practical relevance. Aqueous emulsions of thermotropic liquid crystals (LCs) can exhibit distinctive optical responses in the presence of surfactants and have thus emerged as sensitive, rapid, and inexpensive sensors or reporters of environmental amphiphiles. However, many existing LC-in-water emulsions require the use of complicated or expensive instrumentation for quantitative characterization owing to variations in optical responses among individual LC droplets. In many cases, the responses of LC droplets are also analyzed by human inspection, which can miss subtle color or topological changes encoded in LC birefringence patterns. Here, we report an LC-based surfactant sensing platform that takes a step toward addressing several of these issues and can reliably predict concentrations and types of surfactants in aqueous solutions. Our approach uses surface-immobilized, microcontact-printed arrays of micrometer-scale droplets of thermotropic LCs and hierarchical convolutional neural networks (CNNs) to automatically extract and decode rich information about topological defects and color patterns available in optical micrographs of LC droplets to classify and quantify adsorbed surfactants. In addition, we report computational capabilities to determine relevant optical features extracted by the CNN from LC micrographs, which can provide insights into surfactant adsorption phenomena at LC-water interfaces. Overall, the combination of microcontact-printed LC arrays and machine learning provides a convenient and robust platform that could prove useful for developing high-throughput sensors for on-site testing of environmentally or biologically relevant amphiphiles.

WFNet: A hierarchical convolutional neural network for wildfire spread prediction

Pattern analysis in wildfire spread behaviors is crucial for rescue actions and disaster reduction. Deep learning methods have the potential to model the wildfire spread despite problems such as continuous time prediction and multimodal environmental encoding. Therefore, we present a novel hierarchical convolutional neural network (CNN) denoted as WFNet to model the spread pattern of wildfires. The core of WFNet is defining the spread spatiotemporal distribution field (SSDF) to describe the process of wildfire spread, enabling global optimization and end-to-end prediction. Then, a hierarchical State-Condition mechanism is implemented to progressively and efficiently encode high-order features pertaining to multimodal elements. The experimental results demonstrate that WFNet has a competitive performance to existing models in computation time and model accuracy. More interestingly, WFNet shows excellent robustness when input fire state is in an uncertain moment, enabling investigators to quickly backward the ignition from the fire perimeter.

Land Cover Classification of Remote Sensing Images Based on Hierarchical Convolutional Recurrent Neural Network

Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have gained improved results in remote sensing image data classification. Multispectral image classification can benefit from the rich spectral information extracted by these models for land cover classification. This paper proposes a classification model called a hierarchical convolutional recurrent neural network (HCRNN) to combine the CNN and RNN modules for pixel-level classification of multispectral remote sensing images. In the HCRNN model, the original 13-band information from Sentinel-2 is transformed into a 1D multispectral sequence using a fully connected layer. It is then reshaped into a 3D multispectral feature matrix. The 2D-CNN features are extracted and used as inputs to the corresponding hierarchical RNN. The feature information at each level is adapted to the same convolution size. This network structure fully leverages the advantages of CNNs and RNNs to extract temporal and spatial features from the spectral data, leading to high-precision pixel-level multispectral remote sensing image classification. The experimental results demonstrate that the overall accuracy of the HCRNN model on the Sentinel-2 dataset reaches 97.62%, which improves the performance by 1.78% compared to the RNN model. Furthermore, this study focused on the changes in forest cover in the study area of Laibin City, Guangxi Zhuang Autonomous Region, which was 7997.1016 km2, 8990.4149 km2, and 8103.0020 km2 in 2017, 2019, and 2021, respectively, with an overall trend of a small increase in the area covered.

Predicting bridge longitudinal displacement from monitored operational loads with hierarchical CNN for condition assessment

Over the past few years, longitudinal displacement has gained popularity as a means of evaluating the condition of long-span cable-supported bridge components, such as bearings. However, accurately predicting bearing displacement under varying load conditions is challenging due to the exposure of bridges to environmental and traffic loads. To address this issue, a hierarchical convolutional neural network (HCNN) model was developed in this paper for predicting bearing displacement using comprehensive loads as predictors. Structural health monitoring (SHM) systems of a cable-stayed bridge are utilized to provide one-month datasets for training and testing of the proposed method. Temperature, wind, and vehicle loads are adopted as input variables, and bearing displacement is the output. Results demonstrated the effectiveness of the proposed approach in predicting bearing displacement with an accuracy of over 95.6%, surpassing other models like traditional CNN, encoder-decoder, and U-Net in both accuracy and efficiency. Additionally, the contributions of different loads in predicting displacement are investigated, demonstrating the importance of traffic loads. Cumulative displacement can consequently be calculated for condition assessment of components such as bearings and expansion joints. A comparison with another cable-stayed bridge showed that the expansion joints in the current bridge were in satisfactory condition. Overall, the proposed approach can facilitate predictive maintenance in long-span bridges, helping to prevent premature failures.

Stool Image Analysis for Digital Health Monitoring By Smart Toilets

Gastrointestinal (GI) conditions are widespread and significantly impact the quality of life and healthcare. Stool appearance is a valuable GI diagnostic indicator, and with the advent of the Internet of Things (IoT), daily monitoring of excreta from a toilet is emerging as a promising digital health tool. This article describes a stool image analysis approach that classifies two physiologically relevant stool characteristics: 1) form and 2) color for an IoT-based smart toilet. We constructed a stool image data set with 3275 images, spanning all seven types of the Bristol stool-form scale (BSFS), a widely used metric for stool consistency and a variety of colors. We used ground-truth data obtained through the annotation of our data set by two gastroenterologists and developed a stool-color card to standardize the labeling of stool colors. We addressed two limitations associated with the application of computer-vision techniques to a smart-toilet system: 1) uneven separability between different stool-form categories and 2) class imbalance in the data set. We present results on hierarchical convolutional neural network (CNN) architectures for training a stool-form classifier and on perceptual color quantization coupled with machine-learning techniques to optimize the color-feature space for the classification of stool color. We utilized an edge–cloud approach to pursue an optimal balance between accuracy and latency and for the classification of stool form, we achieved a balanced accuracy of 84.4% and 84.2% reduction in latency compared to a cloud-model only. For color classification, the logistic-regression (LR) classifier provided 80.8% balanced accuracy and 47.3% reduction in communication latency.

H-CNN combined with tissue Raman spectroscopy for cervical cancer detection

Cervical cancer is one of the most common cancers with a long latent period and slow onset process. Early and accurate identification of the stage of cervical cancer can significantly improve the cure rate and patient survival time. In this study, we collected 699 Raman spectral data of tissue sections from 233 different patients. We analyzed and compared the characteristics and differences of the mean Raman spectra of the seven tissues and pointed out the main differences in the biochemical composition of the seven tissues. In this study, 1D hierarchical convolutional neural network (H-CNN) is proposed by integrating the prior knowledge of hierarchical classification relations with the research of deep learning in Raman spectroscopy. H-CNN is based on CNN and is added with three network branches. Hierarchical classification is performed from coarse to fine for tissue samples of cervicitis, Low-grade Squamous Cell Carcinoma, High-grade Squamous Cell Carcinoma, Well Differentiated Squamous Cell Carcinoma, Moderately Differentiated Squamous Cell Carcinoma, Poorly Differentiated Squamous Cell Carcinoma and cervical adenocarcinoma. To evaluate the recognition performance of H-CNN, we compared it with traditional methods such as Bayesian classifier (NB), decision tree classifier (DT), support vector machine classifier (SVM) and CNN. The experimental results show that H-CNN can accurately identify different classes of tissue sections and has apparent advantages in several aspects such as recognition accuracy, stability and sensitivity compared with the other four traditional recognition methods. The classification Macro-Accuracy of H-CNN can reach 94.91%, Macro-Recall can reach 95.31%, Macro-F1 can reach 95.23%, and Macro-AUC can reach 97.35%. The hierarchical classification method proposed in this study can diagnose patients more accurately. This could lay the foundation for further research on Raman spectroscopy as a clinical diagnostic method for cervical cancer.

Wavelet Packet Decomposition-Based Multiscale CNN for Fault Diagnosis of Wind Turbine Gearbox.

This article presents an intelligent fault diagnosis method for wind turbine (WT) gearbox by using wavelet packet decomposition (WPD) and deep learning. Specifically, the vibration signals from the gearbox are decomposed using WPD and the decomposed signal components are fed into a hierarchical convolutional neural network (CNN) to extract multiscale features adaptively and classify faults effectively. The presented method combines the multiscale characteristic of WPD with the strong classification capacity of CNNs, and it does not need complex manual feature extraction steps as usually adopted in existing results. The presented CNN with multiple characteristic scales based on WPD (WPD-MSCNN) has three advantages: 1) the added WPD layer can legitimately process the nonstationary vibration data to obtain components at multiple characteristic scales adaptively, it takes full advantage of WPD and, thus, enables the CNN to extract multiscale features; 2) the WPD layer directly sends multiscale components to the hierarchical CNN to extract rich fault information effectively, and it avoids the loss of useful information due to hand-crafted feature extraction; and 3) even if the scale changes, the lengths of components remain the same, which shows that the proposed method is robust to scale uncertainties in the vibration signals. Experiments with vibration data from a production wind farm provided by a company using condition monitoring system (CMS) show that the presented WPD-MSCNN method is superior to traditional CNN and multiscale CNN (MSCNN) for fault diagnosis.

Joint Classification of Hyperspectral and LiDAR Data Using a Hierarchical CNN and Transformer

The joint use of multisource remote-sensing (RS) data for Earth observation missions has drawn much attention. Although the fusion of several data sources can improve the accuracy of land-cover identification, many technical obstacles, such as disparate data structures, irrelevant physical characteristics, and a lack of training data, exist. In this article, a novel dual-branch method, consisting of a hierarchical convolutional neural network (CNN) and a transformer network, is proposed for fusing multisource heterogeneous information and improving joint classification performance. First, by combining the CNN with a transformer, the proposed dual-branch network can significantly capture and learn spectral–spatial features from hyperspectral image (HSI) data and elevation features from light detection and ranging (LiDAR) data. Then, to fuse these two sets of data features, a cross-token attention (CTA) fusion encoder is designed in a specialty. The well-designed deep hierarchical architecture takes full advantage of the powerful spatial context information extraction ability of the CNN and the strong long-range dependency modeling ability of the transformer network based on the self-attention (SA) mechanism. Four standard datasets are used in experiments to verify the effectiveness of the approach. The experimental results reveal that the proposed framework can perform noticeably better than state-of-the-art methods. The source code of the proposed method will be available publicly at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zgr6010/Fusion_HCT.git</uri> .

Multimodal Hierarchical CNN Feature Fusion for Stress Detection

Stress is one of the most severe concerns in modern life. High-level stress can create various diseases or loss of focus and productivity at work. Being under stress prevents people from recognizing their stress levels, so early stress detection is essential. Recently, multimodal fusion has enhanced the performance of stress detection models using Deep Learning (DL) techniques. The low, mid, and high-level features of a Convolutional Neural Network (CNN) are discriminative. A comprehensive feature representation can be obtained by fusing all three levels of CNN’s features. This study mainly focuses on detecting stress by exploiting these advantages using a multimodal hierarchical CNN feature fusion. The two multimodal physiological signals used in this study are Electrodermal activity (EDA) and Electrocardiogram (ECG). We develop a hierarchical feature set by concatenating multi-level CNN features for each modality. Multimodal fusion on both hierarchical feature sets is performed using the Multimodal Transfer Module (MMTM). The experiments are carried out with raw frequency domain data and the features from the frequency bands to study the effectiveness of both. The model’s performance is compared to the different combinations of hierarchical features from low, mid, and high levels. To verify the generalizability, the proposed approach has been evaluated on four benchmark datasets - ASCERTAIN, CLAS, MAUS, and WAUC. The proposed method showed its effectiveness by outperforming existing models by 1-2%, respectively, on frequency band features. It is observed that the hierarchical feature set from all three levels performed better than all other combinations by 2-4%. As a result, this strategy can be a useful addition to stress detection.

Unsupervised domain adaptation using fuzzy rules and stochastic hierarchical convolutional neural networks

Unsupervised domain adaptation (UDA) describes a set of techniques for using previously acquired knowledge from labeled original data to support task completion in comparable but unlabeled target data. Existing UDA methods often use two classifiers to detect misaligned local areas between the original and prey vocations, resulting in poor implementation. To address this issue, we propose a fuzzy rules and stochastic classifier-based domain adaptation framework called SH-CNN+SMTEOA. Initially, the cross-domain mixed sampling approach is used to test the original and prey data. After that, the Principal Component Analysis is used to extract the characteristics, and fuzzy criteria are used to choose the suitable characteristics. Finally, we introduce the Stochastic Hierarchical Convolutional Neural Network for classification and the Selective Multi-Threshold Entropy Optimization Algorithm for judging a target instance’s dependability based on its predictive multi-threshold values. Investigations on UDA benchmark datasets reveal that the proposed method outperforms other methods in classification.

Automated Bone Age Assessment: A New Three-Stage Assessment Method from Coarse to Fine.

Bone age assessment (BAA) based on X-ray imaging of the left hand and wrist can accurately reflect the degree of the body's physiological development and physical condition. However, the traditional manual evaluation method relies too much on inefficient specialist labor. In this paper, to propose automatic BAA, we introduce a hierarchical convolutional neural network to detect the regions of interest (ROI) and classify the bone grade. Firstly, we establish a dataset of children's BAA containing 2518 left hand X-rays. Then, we use the fine-grained classification to obtain the grade of the region of interest via object detection. Specifically, fine-grained classifiers are based on context-aware attention pooling (CAP). Finally, we perform the model assessment of bone age using the third version of the Tanner-Whitehouse (TW3) methodology. The end-to-end BAA system provides bone age values, the detection results of 13 ROIs, and the bone maturity of the ROIs, which are convenient for doctors to obtain information for operation. Experimental results on the public dataset and clinical dataset show that the performance of the proposed method is competitive. The accuracy of bone grading is 86.93%, and the mean absolute error (MAE) of bone age is 7.68 months on the clinical dataset. On public dataset, the MAE is 6.53 months. The proposed method achieves good performance in bone age assessment and is superior to existing fine-grained image classification methods.