Hierarchical Classification Model Research Articles

LightDPH: Lightweight Dual-Projection-Head Hierarchical Contrastive Learning for Skin Lesion Classification

Effective skin cancer detection is crucial for early intervention and improved treatment outcomes. Previous studies have primarily focused on enhancing the performance of skin lesion classification models. However, there is a growing need to consider the practical requirements of real-world scenarios, such as portable applications that require lightweight models embedded in devices. Therefore, this study aims to propose a novel method that can address the major-type misclassification problem with a lightweight model. This study proposes an innovative Lightweight Dual Projection-Head Hierarchical contrastive learning (LightDPH) method. We introduce a dual projection-head mechanism to a contrastive learning framework. This mechanism is utilized to train a model with our proposed multi-level contrastive loss (MultiCon Loss), which can effectively learn hierarchical information from samples. Meanwhile, we present a distance-based weight (DBW) function to adjust losses based on hierarchical levels. This unique combination of MultiCon Loss and DBW function in LightDPH tackles the problem of major-type misclassification with lightweight models and enhances the model’s sensitivity in skin lesion classification. The experimental results demonstrate that LightDPH significantly reduces the number of parameters by 52.6% and computational complexity by 29.9% in GFLOPs while maintaining high classification performance comparable to state-of-the-art methods. This study also presented a novel evaluation metric, model efficiency score (MES), to evaluate the cost-effectiveness of models with scaling and classification performance. The proposed LightDPH effectively mitigates major-type misclassification and works in a resource-efficient manner, making it highly suitable for clinical applications in resource-constrained environments. To the best of our knowledge, this is the first work that develops an effective lightweight hierarchical classification model for skin lesion detection.

Optimizing hierarchical classifiers with parameter tuning and confidence scoring

Hierarchical classifiers play a crucial role in addressing complex classification tasks by breaking them down into smaller, more manageable sub-tasks. This paper continues a series of works, focused on the technical Ukrainian texts hierarchical classification, specifically the classification of repair works and spare parts used in automobile maintenance and servicing. We tackle the challenges posed by multilingual data inputs – specifically Ukrainian, Russian, and their hybrid – and the lack of standard data cleaning models for the Ukrainian language. We developed a novel classification algorithm, which employs TF-IDF victimization with unigrams and bigrams, keyword selection, and cosine similarity for classification. This paper describes a method for training and evaluating a hierarchical classification model using parameter tuning for each node in a tree structure. The training process involves initializing weights for tokens in the class tree nodes and input strings, followed by iterative parameter tuning to optimize classification accuracy. Initial weights are assigned based on predefined rules, and the iterative process adjusts these weights to achieve optimal performance. The paper also addresses the challenge of interpreting multiple confidence scores from the classification process, proposing a machine learning approach using Scikit-learn's GradientBoostingClassifier to calculate a unified confidence score. This score helps assess the classification reliability, particularly for unlabeled data, by transforming input values, generating polynomial parameters, and using logarithmic transformations and scaling. The classifier is fine-tuned using hyper parameter optimization techniques, and the final model provides a robust confidence score for classification tasks, enabling the verification and classification results optimization across large datasets. Our experimental results demonstrate significant improvements in classification performance. Overall classification accuracy nearly doubled after training, reaching 92.38 %. This research not only advances the theoretical framework of hierarchical classifiers but also provides practical solutions for processing large-scale, unlabeled datasets in the automotive industry. The developed methodology can enhance various applications, including automated customer support systems, predictive maintenance, and decision-making processes for stakeholders like insurance companies and service centers. Future work will extend this approach to more complex tasks, such as extracting and classifying information from extensive text sources like telephone call transcriptions.

Hierarchical classification for improving parcel-scale crop mapping using time-series Sentinel-1 data

Parcel-scale crop classification utilizing time-series satellite observations is of significant importance in precision agriculture. The prior knowledge that crop types can be organized in a hierarchical tree structure is beneficial for improving crop classification. Moreover, the crop hierarchy aligns with the coarse-to-fine cognitive process of geographic scenes. Based on the crop hierarchy, this study developed a general hierarchical classification framework for enhancing crop mapping using time-series Sentinel-1 data. Central to this method is a deep-learning-based hierarchical classification model that explores and makes use of crop hierarchical knowledge. First, preprocessed Sentinel-1 data were geometrically overlaid onto farmland parcel maps to derive parcel-scale time-series features. Second, we constructed a hierarchical crop type system for study areas based on the crop phenology of labeled crop-type samples. Third, we developed a deep-learning-based hierarchical classification model to identify crop types for each parcel, to generate final crop-type classification maps. The proposed approach was further discussed and verified through the implementation of parcel-scale time-series crop hierarchical classifications in a study area in France with farmland parcel maps and time-series Sentinel-1 data. The classification results, indicating significant improvements greater than 4.0% in overall accuracy and 5.0% in F1 score over comparative methods, demonstrated the effectiveness of the proposed method in learning multi-scale time-series features for hierarchical crop classification utilizing Sentinel-1 data sequences.

The synergy of morphokinetic parameters and sHLA-G in cleavage embryo enhancing implantation rates.

Objective: This study aimed to assess the relationship between implantation and soluble HLA-G (sHLA-G) expression in cleavage embryo culture medium (ECM) in conjunction with early developmental kinetics determined by time-lapse imaging (TLI). Methods: A retrospective, single-center study was conducted involving 238 embryos from 165 patients who underwent Frozen-thawed embryo transfer (FET) using autologous oocytes, with either single or double embryo transfer. TLI morphokinetic parameters (t2, t3, t4, t5, t6, t7, t8, cc2, s2, cc3, s3) of embryos were analyzed, and sHLA-G levels in D3 ECM were measured using an enzyme-linked immunosorbent assay (ELISA). A hierarchical classification model was developed to categorize embryos into five groups (A, B, C, D, E). The correlation between sHLA-G levels, TLI classification of embryos, and embryo implantation was investigated to establish a non-invasive method for evaluating implantation potential. Multivariate logistic regression analysis was performed to identify potential influencing factors, and receiver operating characteristic (ROC) curves were used to evaluate the predictive value for implantation. Results: Multivariate unconditional logistic regression analysis indicated that TLI parameters t5 and s3 and sHLA-G level in ECM were independent risk factors affecting embryo implantation. The implantation rate decreased from TLI classification A to E. The proposed classification model effectively assessed the implantation potential of embryos. The implantation rate was higher in the sHLA-G positive group compared to the sHLA-G negative group (p < 0.001). The expression of sHLA-G in D3 ECM, combined with the TLI classification model, accurately evaluated the implantation potential of embryos with an AUC of 0.876. Conclusion: The integration of cleavage kinetics and embryonic sHLA-G expression could reliably identify embryos with a high likelihood of successful implantation.

Enhancing precision in coastal dunes vegetation mapping: ultra-high resolution hierarchical classification at the individual plant level

ABSTRACT The classification of ultra-high-resolution (UHR) imagery, characterized by spatial resolutions exceeding 10 cm, presents opportunities and challenges distinct from lower-resolution counterparts. Particularly, challenges are pronounced in some scenarios, such as mapping plant species in coastal environments, where similar vegetation responses and small plant sizes pose additional difficulties. The present work addressed such issues by developing a UHR vegetation cover classification model at the single plant level using data from uncrewed aerial systems (UASs) equipped with a multispectral optical sensor. The model was tested across the San Rossore Regional Park (Italy), where three pilot areas were defined as training-test-validation sites. The proposed solution consists of a hierarchical two-level-of-detail machine learning model based on object-based image analysis (OBIA) and random forest. This model considers spectral features and indices, elevation, and texture and can classify twelve plant species and two service classes (debris and sand) within the study areas. Train and test were carried out utilizing UAS flight data collected during two specific phenological periods and precise field data derived from in-situ vegetation surveys, which provided 937 herbaceous and shrub samples. The model performance was evaluated based on the error matrix and 50-fold stratified cross-validation method, obtaining an overall accuracy (OA) of 0.76 and a standard deviation of 0.08. Such assessment underscored the crucial role of texture information, in addition to radiometric and elevation. Finally, the model was tested against an unseen dataset, proving its transferability (OA equal to 0.62). Although the discussion highlights some aspects to be further improved and claims for future research, the first version of this hierarchical classification model demonstrated its potential for mapping and monitoring coastal sand dune ecosystems, providing data for understanding and, eventually, modeling ecological and biogeomorphological dynamics.

Identification and Discrimination of Petrol Sources by Nuclear Magnetic Resonance Spectroscopy and Machine Learning in Fire Debris Analysis

Petrol is considered the most common fire accelerant. However, the identification and classification of petrol sources through the years has proven to be a challenging field in the investigation of fire debris analysis. This research explored the possibility of identifying petrol sources by high-field NMR methods accompanied by ML (machine learning). The automated identification and classification of petrol brands were achieved for first time based on the ML classification model developed in this research. A hierarchical classification model was constructed using local classifiers to categorize neat or weathered petrol into its sources.

A clustering machine learning approach for improving concrete compressive strength prediction

AbstractThis study investigates the application of clustering techniques to enhance the accuracy of hierarchical classification and regression (HCR) models for predicting concrete compressive strength (CCS). Following the hypothesis that integrating clustering at the initial levels of model hierarchy reduces classification errors and prevents their propagation to subsequent levels, HCR models were developed utilizing both the unweighted pair group method with arithmetic mean (UPGMA) and hard clustering (HC) methods. Findings demonstrate that models using UPGMA significantly outperform those based on HC. Furthermore, it was demonstrated that further hierarchical clustering allows for multilayered HCR models that improve predictive performance by further leveraging parent–child relationships within data clusters. Overall, this study demonstrates that the proposed methodology can be introduced in the model development pipeline to enhance the prediction accuracy of CCS models.

On the importance of integrating convolution features for Indian medicinal plant species classification using hierarchical machine learning approach

This work proposes a novel hierarchical classification framework designed to categorize hundred Indian medicinal plant species. The innovation lies in introducing a comprehensive feature representation by integrating convolutional features with geometric, texture, shape, and multispectral features for classification tasks. In this study, a two-level hierarchical plant classification model is proposed to address the challenges of inter-class similarity and intra-class variations. The first level classifies 100 medicinal plant species into 11 groups based on visual similarities among the plants. At level two, the specific plant species containing in each group are predicted using Random Forest classifier. The evaluation is performed at two levels to analyze the effectiveness of the proposed model. The performance analysis compares the effectiveness of individual feature types against the composite feature model. Performance is also evaluated based on specific groups that demonstrate high similarity between classes and intra-class variations among the plant species separately. Furthermore, the generality of the model is tested using two self-created datasets-RTL80 and RTP40, requiring more than 300 man-hours to collect. Experimental results demonstrate a promising accuracy of 94.54% on GSL100 leaf dataset and 75.46% on RTL80 and RTP40 real-time datasets reflecting the superiority of the proposed hierarchical model over state-of-the-art methods.

Abnormal line loss identification and category classification of distribution networks based on semi-supervised learning and hierarchical classification

Line loss refers to the electrical energy that is dissipated as heat during the transmission and distribution of electricity through power lines. However, unusual causes, such as grid topology mismatch and communication failure, can cause abnormal line loss. Efficient abnormal line loss detection contributes not only to minimizing energy wastage and reducing carbon emissions but also to maintaining the stability and reliability of the entire distribution network. In actual situations, the cause of abnormal line loss is not labeled due to the expensive labor cost. This paper proposes a hierarchical abnormal line loss identification and category classification model, considering the unlabeled and unbalanced sample problem. First, an abnormal line loss identification model-based random forest is established to detect whether the line loss is abnormal. Then, an abnormal line loss category classification model is developed with semi-supervised learning for line loss abnormal category classification, considering the unlabeled samples. The real dataset in China is utilized to validate the performance of the proposed model. Its reliability implies the potential to be applied to real-world scenarios to improve the management level and safety of the power grid.

DeepMedFeature: An Accurate Feature Extraction and Drug-Drug Interaction Model for Clinical Text in Medical Informatics

Drug-drug interactions (DDIs) are an important biological phenomenon which can result in medical errors from medical practitioners. Drug interactions can change the molecular structure of interacting agents which may prove to be fatal in the worst case. Finding drug interactions early in diagnosis can be pivotal in side-effect prevention. The growth of big data provides a rich source of information for clinical studies to investigate DDIs. We propose a hierarchical classification model which is double-pass in nature. The first pass predicts the occurrence of an interaction and then the second pass further predicts the type of interaction such as effect, advice, mechanism, and int. We applied different deep learning algorithms with Convolutional Bi-LSTM (ConvBLSTM) proving to be the best. The results show that pre-trained vector embeddings prove to be the most appropriate features. The F1-score of the ConvBLSTM algorithm turned out to be 96.39% and 98.37% in Russian and English language respectively which is greater than the state-of-the-art systems. According to the results, it can be concluded that adding a convolution layer before the bi-directional pass improves model performance in the automatic classification and extraction of drug interactions, using pre-trained vector embeddings such as Fasttext and Bio-Bert.

A Geographic Object-Based Image Approach Based on the Sentinel-2 Multispectral Instrument for Lake Aquatic Vegetation Mapping: A Complementary Tool to In Situ Monitoring

Aquatic vegetation is an essential component of lake ecosystems, used as a biological indicator for in situ monitoring within the Water Framework Directive. We developed a hierarchical object-based image classification model with multi-seasonal Sentinel-2 imagery and suitable spectral indices in order to map the aquatic vegetation in a Mediterranean oligotrophic/mesotrophic deep lake; we then applied the model to another lake with similar abiotic and biotic characteristics. Field data from a survey of aquatic macrophytes, undertaken on the same dates as EO data, were used within the accuracy assessment. The aquatic vegetation was discerned into three classes: emergent, floating, and submerged aquatic vegetation. Geographic object-based image analysis (GEOBIA) proved to be effective in discriminating the three classes in both study areas. Results showed high effectiveness of the classification model in terms of overall accuracy, particularly for the emergent and floating classes. In the case of submerged aquatic vegetation, challenges in their classification prompted us to establish specific criteria for their accurate detection. Overall results showed that GEOBIA based on spectral indices was suitable for mapping aquatic vegetation in oligotrophic/mesotrophic deep lakes. EO data can contribute to large-scale coverage and high-frequency monitoring requirements, being a complementary tool to in situ monitoring.

Classification and Value Assessment of Sports Intangible Cultural Heritage Resources Combined with Digital Technology

Abstract This paper is dedicated to designing and constructing a knowledge ontology framework for sports intangible cultural heritage (ICH) resources, aiming to support their preservation and inheritance by integrating and mining sports ICH resources. The study includes the collection of multiple data of sports ICH from various data sources, and constructing ICH knowledge ontology using CIDOC CRM metadata reference model and seven-step method. To enrich the content of the ontology, the TextRank algorithm is used to extract textual critical information and design a domain-specific NER model for sports NRL. In addition, the study adopts the VSM vector space model for text representation and uses an improved hierarchical classification model for text categorization to improve classification accuracy. The study also explores the similarity calculation of concepts in the sports NRM ontology and proposes a semantic similarity calculation formula based on the ontology concepts. Respondents’ willingness to pay was investigated through the conditional value method (CVM) to assess the value of sports NRM tourism resources. Finally, the influencing factors of respondents’ willingness to pay were analyzed using statistical analysis and Logistic regression model, and it was found that they were mainly influenced by the degree of understanding of sports non-heritage resources and the level of education. The results of this study not only provide theoretical and methodological support for the effective integration and excavation of sports non-heritage resources and a new perspective for their protection, inheritance and sustainable development.

A Bloom Cognitive Hierarchical Classification Model for Chinese Exercises Based on Improved Chinese-RoBERTa-wwm and BiLSTM

A Bloom Cognitive Hierarchical Classification Model for Chinese Exercises Based on Improved Chinese-RoBERTa-wwm and BiLSTM

Bayesian workflow for the investigation of hierarchical classification models from tau-PET and structural MRI data across the Alzheimer's disease spectrum.

Alzheimer's disease (AD) diagnosis in its early stages remains difficult with current diagnostic approaches. Though tau neurofibrillary tangles (NFTs) generally follow the stereotypical pattern described by the Braak staging scheme, the network degeneration hypothesis (NDH) has suggested that NFTs spread selectively along functional networks of the brain. To evaluate this, we implemented a Bayesian workflow to develop hierarchical multinomial logistic regression models with increasing levels of complexity of the brain from tau-PET and structural MRI data to investigate whether it is beneficial to incorporate network-level information into an ROI-based predictive model for the presence/absence of AD. This study included data from the Translational Biomarkers in Aging and Dementia (TRIAD) longitudinal cohort from McGill University's Research Centre for Studies in Aging (MCSA). Baseline and 1 year follow-up structural MRI and [18F]MK-6240 tau-PET scans were acquired for 72 cognitive normal (CN), 23 mild cognitive impairment (MCI), and 18 Alzheimer's disease dementia subjects. We constructed the four following hierarchical Bayesian models in order of increasing complexity: (Model 1) a complete-pooling model with observations, (Model 2) a partial-pooling model with observations clustered within ROIs, (Model 3) a partial-pooling model with observations clustered within functional networks, and (Model 4) a partial-pooling model with observations clustered within ROIs that are also clustered within functional brain networks. We then investigated which of the models had better predictive performance given tau-PET or structural MRI data as an input, in the form of a relative annualized rate of change. The Bayesian leave-one-out cross-validation (LOO-CV) estimate of the expected log pointwise predictive density (ELPD) results indicated that models 3 and 4 were substantially better than other models for both tau-PET and structural MRI inputs. For tau-PET data, model 3 was slightly better than 4 with an absolute difference in ELPD of 3.10 ± 1.30. For structural MRI data, model 4 was considerably better than other models with an absolute difference in ELPD of 29.83 ± 7.55 relative to model 3, the second-best model. Our results suggest that representing the data generating process in terms of a hierarchical model that encompasses both ROI-level and network-level heterogeneity leads to better predictive ability for both tau-PET and structural MRI inputs over all other model iterations.

Prediction of fractional flow reserve with enhanced ant lion optimized support vector machine

The evaluation of coronary morphology provides important guidance for the treatment of coronary heart disease (CHD). A chaotic Gaussian mutation antlion optimizer algorithm (CGALO) is proposed in the paper, and it is combined with SVM to construct a classification prediction model for Fractional flow reserve (FFR). To overcome the limitations of the original antlion optimizer (ALO) algorithm, the chaotic Gaussian mutation strategy is introduced, which leads to an improvement in its convergence speed and accuracy. To evaluate the proposed algorithm's performance, comparative experiments were conducted on 23 benchmark functions alongside 12 other cutting-edge optimization algorithms. The experimental outcomes demonstrate that the proposed algorithm achieves superior convergence accuracy and speed compared to the alternative comparison algorithms. Additionally, it is combined with SVM and FS to construct a hierarchical FFR classification model, which is utilized to make effective predictions for 84 patients at the affiliated hospital of medical school, Ningbo university. The experimental results demonstrate that the proposed model achieves an average accuracy of 92%. Moreover, it concludes that smoking history, number of lesion vessels, lesion location, diffuse lesions and ST segment changes, and other factors are the most critical indicators for FFR. Therefore, the model that has been established is a new FFR intelligent classification prediction technology that can effectively assist doctors in making corresponding decisions and evaluation plans.

ENHANCING NON-NATIVE ACCENT RECOGNITION THROUGH A COMBINATION OF SPEAKER EMBEDDINGS, PROSODIC AND VOCAL SPEECH FEATURES

The transcription accuracy of automatic speech recognition (ASR) system may suffer when recognizing accented speech. The resulting bias in ASR system towards a specific accent due to under representation of that accent in the training dataset. Accent recognition of existing speech samples can help with the preparation of the training datasets, which is an important step toward closing the accent gap and eliminating biases in ASR system. For that we built a system to recognize accent from spoken speech data. In this study, we have explored some prosodic and vocal speech features as well as speaker embeddings for accent recognition on our custom English speech data that covers speakers from around the world with varying accents. We demonstrate that our selected speech features are more effective in recognizing nonnative accents. Additionally, we experimented with a hierarchical classification model for multi-level accent classification. To establish an accent hierarchy, we employed a bottom-up approach, combining regional accents and categorizing them as either native or non-native at the top level. Furthermore, we conducted a comparative study between flat classification and hierarchical classification using the accent hierarchy structure.

Traffic Sign Detection and Recognition Using Multi-Frame Embedding of Video-Log Images

The detection and recognition of traffic signs is an essential component of intelligent vehicle perception systems, which use on-board cameras to sense traffic sign information. Unfortunately, issues such as long-tailed distribution, occlusion, and deformation greatly decrease the detector’s performance. In this research, YOLOv5 is used as a single classification detector for traffic sign localization. Afterwards, we propose a hierarchical classification model (HCM) for the specific classification, which significantly reduces the degree of imbalance between classes without changing the sample size. To cope with the shortcomings of a single image, a training-free multi-frame information integration module (MIM) was constructed, which can extract the detection sequence of traffic signs based on the embedding generated by the HCM. The extracted temporal detection information is used for the redefinition of categories and confidence. At last, this research performed detection and recognition of the full class on two publicly available datasets, TT100K and ONCE. Experimental results show that the HCM-improved YOLOv5 has a mAP of 79.0 in full classes, which exceeds that of state-of-the-art methods, and achieves an inference speed of 22.7 FPS. In addition, MIM further improves model performance by integrating multi-frame information while only slightly increasing computational resource consumption.

Contextual Embeddings based on Fine-tuned Urdu-BERT for Urdu threatening content and target identification

Identification of threatening text on social media platforms is a challenging task. Contrary to the high-resource languages, the Urdu language has very limited such approaches and the benchmark approach has an issue of inappropriate data annotation. Therefore, we present robust threatening content and target identification as a hierarchical classification model for Urdu tweets. This study investigates the potential of the Urdu-BERT (Bidirectional Encoder Representations from Transformer) language model to learn universal contextualized representations aiming to showcase its usefulness for binary classification tasks of threatening content and target identification. We propose to exploit a pre-trained Urdu-BERT as a transfer learning model after fine-tuning its parameters on a newly designed Urdu corpus from the Twitter platform. The proposed dataset contains 2,400 tweets manually annotated as threatening or non-threatening at the first level and threatening tweets are further categorized into individual or group at the second level. The performance of fine-tuned Urdu-BERT is compared with the benchmark study and other feature models. Experimental results show that the fine-tuned Urdu-BERT model achieves state-of-the-art performance by obtaining 87.5% accuracy and 87.8% F1-score for threatening content identification and 82.5% accuracy and 83.2% F1-score for target identification task. Furthermore, the proposed model outperforms the benchmark study.

A Testlet Diagnostic Classification Model with Attribute Hierarchies.

In this article, a testlet hierarchical diagnostic classification model (TH-DCM) was introduced to take both attribute hierarchies and item bundles into account. The expectation-maximization algorithm with an analytic dimension reduction technique was used for parameter estimation. A simulation study was conducted to assess the parameter recovery of the proposed model under varied conditions, and to compare TH-DCM with testlet higher-order CDM (THO-DCM; Hansen, M. (2013). Hierarchical item response models for cognitive diagnosis (Unpublished doctoral dissertation). UCLA; Zhan, P., Li, X., Wang, W.-C., Bian, Y., & Wang, L. (2015). The multidimensional testlet-effect cognitive diagnostic models. Acta Psychologica Sinica, 47(5), 689. https://doi.org/10.3724/SP.J.1041.2015.00689). Results showed that (1) ignoring large testlet effects worsened parameter recovery, (2) DCMs assuming equal testlet effects within each testlet performed as well as the testlet model assuming unequal testlet effects under most conditions, (3) misspecifications in joint attribute distribution had an differential impact on parameter recovery, and (4) THO-DCM seems to be a robust alternative to TH-DCM under some hierarchical structures. A set of real data was also analyzed for illustration.

BADM-Net: Hierarchical Classification Network for Identifying Anomalous Trends in Bridge Monitoring Data Patterns

SHM systems have been widely implemented in long-span bridges, and seas of field measurement data have been accumulated. Due to the imperfect sensors, data transmission and acquisition, various anomalies inevitably exist in the SHM data, which may lead to unreliable structural condition assessment. Thus, an effective approach for detecting data anomalies is highly desirable. Due to the imbalanced data, some anomalous patterns are undertrained in popular end-to-end deep neural network models, resulting in a reduction in detection precision. In this paper, a hierarchical classification model with deep neural network tree is proposed for imbalanced data. The DNN tree contains three levels: (1) CNN to divide seven types of data into four categories (134, 2, 5, 67), denoted as C4; (2) two DNNs to classify to two classes separately (1, 34, 6, 7), denoted as D2D2; (3) DNNs to classify to two classes (3, 4). So, the DNN tree is presented as C4_D2D2_D2. The DNN tree is an open framework and can be defined based on the data characteristics. In the data processing, three data sets are built for training, namely single-channel data set, dual-channel data set and statistical data set. To validate our work, we considered the effects of balanced and imbalanced training sets and training ratios. The results show that our model can detect the multi-pattern anomalies of SHM data efficiently with 95.5% high accuracy. Besides, the proportion of abnormal data classified to normal data has been reduced, especially 3-minor. This model successfully solves the problem in a simple and easy to understand way, which has certain reference significance for the bridge structure anomaly judgment in the future.