Error Correcting Output Codes Research Articles

Diagnosing skin cancer using social spider optimization (SSO) and error correcting output codes (ECOC) with weighted hamming distance

Skin cancer is a common disease resulting from genetic defects, and early detection is critical to improve treatment outcomes. Diagnostic programs that use computer aid especially those that use supervised learning are very useful in early diagnosis of skin cancer. This research therefore presents a new approach that integrates optimization methods with supervised learning to improve skin cancer diagnosis using machine vision approach. The presented method is initiated by data pre-processing that involves the removal of unnecessary data. Then, to segment the images, a combination of K-means clustering and social spider optimization technique is employed. The region of interest is then extracted from the segmented image and from this region a convolutional neural network extracts the significant features. To enhance the classification performance as compared with the standard classifiers, this research introduces a new concept of error correcting output codes coupled with a weighted Hamming distance in the group of gamma classifiers. The ability of the proposed approach in segmentation of skin lesions and classifying them was tested using samples from the ISIC-2017 and ISIC-2016 databases. The introduced method obtained state-of-the-art accuracy on both datasets (ISIC-2016: 97.10%, ISIC-2017: 95.17%). In particularly, the accuracy of the introduced approach for both these databases is at least 1.17% higher than the compared methods. This proves the high performance of the suggested method based on the usage of the convolutional neural networks for feature extraction and gamma classifiers with error correcting output codes for classification in skin cancer detection.

Automatic sucker rod pump fault diagnostics by transfer learning using googlenet integrated machine learning classifiers

Oil and gas extraction is vital for meeting the energy needs of a growing global population. Artificial lift (AL) systems play a crucial role in oilfields, especially when reservoir pressure is low. Among these systems, sucker rod pumps (SRPs) are extensively employed for onshore hydrocarbon recovery operations. However, SRPs are susceptible to mechanical failures and operational challenges arising from evolving reservoir conditions. This study proposes an approach for fault diagnosis in SRPs using real-time data from sensors and machine learning (ML) algorithms to detect anomalies and patterns associated with potential problems. The proposed method involves deep learning (DL) for automated feature extraction from dynamometer cards and error-correcting output codes (ECOC) model-based supervised machine learners for efficiently assessing the operational state of the SRP. By forecasting potential failures, preemptive measures can be taken to minimize downtime and reduce maintenance costs. The application of ML in the analysis of SRP provides a potential tool for diagnosing and predicting failures, improving productivity efficiency, and reducing downtime. Also, the accuracy of Convolutional Neural Networks (CNN) models was compared with that of CNN-ECOC model-based learners in this study, and the results demonstrated that integrating algorithms such as Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN) with the network caused significant improvements in the accuracy; however, Decision Tree (DT) and Naive Bayes (NB) did not perform well in the pattern classification task. Specifically, the GoogLeNet model achieved improved accuracy of 96.40 % and 99.40 % when SVM and k-NN were integrated, respectively. Conversely, with DT and NB, the accuracies dropped to 66.30 % and 75.10 %, respectively.

Gear fault diagnosis based on bidimensional time-frequency information theoretic features and error-correcting output codes: A multi-class support vector machine

Gear fault diagnosis based on bidimensional time-frequency information theoretic features and error-correcting output codes: A multi-class support vector machine

Fault diagnosis of power transformers based on t-SNE and ECOC-TEWSO-SVM

Support Vector Machines (SVMs) have achieved significant success in the field of power transformer fault diagnosis. However, challenges such as determining SVM hyperparameters and their suitability for binary classification still exist. This paper proposes a novel method for power transformer fault diagnosis, called ECOC-WSO-SVM, which utilizes a White Shark Optimizer (WSO) and error correcting output codes to optimize SVMs. First, t-distributed Stochastic Neighbor Embedding (t-SNE) is employed to reduce the dimensionality of Dissolved Gas Analysis (DGA) features constructed using the correlation ratio method, from 26 dimensions. In addition, to effectively solve the hyperparameters of SVMs, a multi-strategy fusion method is proposed to improve the WSO, incorporating tent chaos initialization, elite opposite learning, and selection strategies, forming TEWSO, and its superior optimization performance is validated using IEEE CEC2021 test functions. Furthermore, to address the limitations of SVMs as a binary classifier, an error correcting output code fusion SVM is introduced, thus constructing a multi-class SVM model. Finally, the diagnostic performance of the ECOC-TEWSO-SVM model is validated using real-world data. Results demonstrate that the proposed model exhibits the best diagnostic performance compared to traditional models and those in the literature, thereby proving the significance and effectiveness of the proposed model.

The Timing of Gaze Direction Perception: ERP Decoding and Task Modulation

Distinguishing the direction of another person's eye gaze is extremely important in everyday social interaction, as it provides critical information about people's attention and, therefore, intentions. The temporal dynamics of gaze processing have been investigated using event-related potentials (ERPs) recorded with electroencephalography (EEG). However, the moment at which our brain distinguishes the gaze direction (GD), irrespectively of other facial cues, remains unclear. To solve this question, the present study aimed to investigate the time course of gaze direction processing, using an ERP decoding approach, based on the combination of a support vector machine and error-correcting output codes. We recorded EEG in young healthy subjects, 32 of them performing GD detection and 34 conducting face orientation tasks. Both tasks presented 3D realistic faces with five different head and gaze orientations each: 30°, 15° to the left or right, and 0°. While the classical ERP analyses did not show clear GD effects, ERP decoding analyses revealed that discrimination of GD, irrespective of head orientation, started at 140 ms in the GD task and at 120 ms in the face orientation task. GD decoding accuracy was higher in the GD task than in the face orientation task and was the highest for the direct gaze in both tasks. These findings suggest that the decoding of brain patterns is modified by task relevance, which changes the latency and the accuracy of GD decoding.

Application research of image classification algorithm based on deep learning in household garbage sorting

The classification of garbage types is an important issue in today's world, and its proper implementation can contribute to environmental conservation and improved efficiency of recycling processes. Unfortunately, the classification of garbage types is currently predominantly performed through human supervision, which leads to high errors and environmental risks. It is crucial to automate this procedure utilizing machine vision methods as a result. This research proposes a revolutionary deep learning-based strategy for classifying domestic waste. The suggested method uses deep learning methods to extract information from images. The Capuchin Search Algorithm (CapSA) is used to improve the hyperparameters of the convolutional neural network (CNN) used as the feature extraction model. Furthermore, for categorizing the retrieved features from the CNN model, a hybrid learning model based on Error-Correcting Output Codes (ECOC) and Artificial Neural Networks (ANN) is used. The classification accuracy may be successfully increased by using this hybrid model, and the benefit becomes more pronounced as the number of target categories rises. The TrashNet and HGCD databases were used to assess the suggested method's effectiveness, and its results in waste type detection were contrasted with those of earlier techniques. Based on the study findings, the suggested approach can identify trash types with an accuracy of 98.81 % and 99.01 % on the TrashNet and HGCD databases, respectively. This is at least a 1.46 % improvement over earlier approaches. The study's conclusions validate that the suggested strategy may be used in real-world scenarios and show how successful the approaches used in it are.

Sports activity (SA) recognition based on error correcting output codes (ECOC) and convolutional neural network (CNN)

The increasing use of motion sensors is causing major changes in the process of monitoring people's activities. One of the main applications of these sensors is the detection of sports activities, for example, they can be used to monitor the condition of athletes or analyze the quality of sports training. Although the existing sensor-based activity recognition systems can recognize basic activities such as: walking, running, or sitting; they don't perform well in recognizing different types of sports activities. This article introduces a new model based on machine learning (ML) techniques to more accurately distinguish between sports and everyday activities. In the proposed method, the necessary data to detect the type of activity is collected through his two sensors: an accelerometer and a gyroscope attached to a person's foot. For this purpose, the input signals are first preprocessed and then short-time Fourier transform (STFT) is used to describe the characteristics of each signal. In the next step, each STFT matrix is used as input to a convolutional neural network (CNN). This CNN describes various motion characteristics of the sensor in the form of vectors. Finally, a classification model based on error correction output code (ECOC) is used to classify the extracted features and detect the type of SA. The performance of the proposed AS recognition method is evaluated using the DSADS database and the results are compared with previous methods. Based on the results, the proposed method can recognize sports activities with an accuracy of 99.71. Furthermore, the performance of the proposed method based on precision and recall criteria are 99.72 and 99.71, respectively, which are better than the compared methods.

Gear fault diagnosis based on complex network theory and error-correcting output codes: Multi class support vector machine

Gearbox failures have a detrimental effect on the machine performance that affects the production capacity and economic benefits of a manufacturing industry in an adverse manner. Early detection of faults in gears helps to prevent sudden machine failures. Previously, many signal processing and artificial intelligence techniques have been successfully applied to diagnose gear faults by analyzing the machine vibrations. These techniques have repeatedly emphasized on the need to extract quality features from gear vibration signals and using artificial intelligence techniques that can identify multiple types of faults simultaneously. As such, in this article, new features called as visibility graph features based on complex network theory have been proposed to extract fault information from vibration signals. In addition, a new artificial intelligence framework for multifault classification known as error-correcting output codes-multiclass support vector machine is proposed to detect gear faults. To the best of authors’ knowledge, these features along with the error-correcting output codes-artificial intelligence framework have been rarely utilized for fault diagnosis purpose. The proposed approach has been applied on experimental gear vibration data to validate its effectiveness. First, the vibration signals are transformed to graphs, and various graph properties are computed to serve as fault features. Then, the fault features are supplied to train the error-correcting output codes-multiclass support vector machine model and learn the fault patterns. Finally, the gear fault classification accuracies are determined for various gear test conditions and compared with those of existing methods. It is observed that the proposed approach provides an average improvement of 4.22%, 9.93% and 11.8% over the time-domain features, time–frequency domain features and voting-based multiclass support vector machine classifier, respectively, for different operating conditions. Furthermore, the suggested technique augments the classification accuracies by 10%, 7.5% and 6.7%, respectively, as compared with the deep-learning models, namely standard stacked sparse autoencoder, deep neural network and convolution neural network.

Hilbert domain characterizations of wavelet packets for automated heart sound abnormality detection

Heart valve disease (HVD) is a common disease that affects millions of people worldwide. Early detection and treatment are essential for improving the prognosis of patients with HVD. Phonocardiogram (PCG) signals are a non-invasive and inexpensive way to assess the mechanical activity of the heart. In this study, a novel method for HVD detection using Hilbert domain mapping of wavelet packet of PCG signals is proposed. Two standard PCG databases are used to evaluate the proposed method. Packet instantaneous frequency deviation (PIFD) and packet instantaneous energy deviation (PIED) features are extracted from the PCG signals and used for classification. A support vector machine (SVM) and K-nearest neighbour (KNN) based error-correcting output code (ECOC) approach is used to handle multiclass classification and minimize classification error. The proposed method achieves an unweighted average recall (UAR) of 99.8% on database 1 and 99.32% on database 2, which outperforms other baseline methods. The results suggest that the proposed method is a promising approach for HVD detection using PCG signals.

An ensemble-based machine learning solution for imbalanced multiclass dataset during lithology log generation

The lithology log, an integral component of the master log, graphically portrays the encountered lithological sequence during drilling operations. In addition to offering real-time cross-sectional insights, lithology logs greatly aid in correlating and evaluating multiple sections efficiently. This paper introduces a novel workflow reliant on an enhanced weighted average ensemble approach for producing high-resolution lithology logs. The research contends with a challenging multiclass imbalanced lithofacies distribution emerging from substantial heterogeneities within subsurface geological structures. Typically, methods to handle imbalanced data, e.g., cost-sensitive learning (CSL), are tailored for issues encountered in binary classification. Error correcting output code (ECOC) originates from decomposition strategies, effectively breaking down multiclass problems into numerous binary subproblems. The database comprises conventional well logs and lithology logs obtained from five proximate wells within a Middle Eastern oilfield. Utilizing well-known machine learning (ML) algorithms, such as support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and extreme gradient boosting (XGBoost), as baseline classifiers, this study aims to enhance the accurate prediction of underground lithofacies. Upon recognizing a blind well, the data from the remaining four wells are utilized to train the ML algorithms. After integrating ECOC and CSL techniques with the baseline classifiers, they undergo evaluation. In the initial assessment, both RF and SVM demonstrated superior performance, prompting the development of an enhanced weighted average ensemble based on them. The comprehensive numerical and visual analysis corroborates the outstanding performance of the developed ensemble. The average Kappa statistic of 84.50%, signifying almost-perfect agreement, and mean F-measures of 91.04% emphasize the robustness of the designed ensemble-based workflow during the evaluation of blind well data.

Deep Error-Correcting Output Codes

Ensemble learning, online learning and deep learning are very effective and versatile in a wide spectrum of problem domains, such as feature extraction, multi-class classification and retrieval. In this paper, combining the ideas of ensemble learning, online learning and deep learning, we propose a novel deep learning method called deep error-correcting output codes (DeepECOCs). DeepECOCs are composed of multiple layers of the ECOC module, which combines several incremental support vector machines (incremental SVMs) as base classifiers. In this novel deep architecture, each ECOC module can be considered as two successive layers of the network, while the incremental SVMs can be viewed as weighted links between two successive layers. In the pre-training procedure, supervisory information, i.e., class labels, can be used during the network initialization. The incremental SVMs lead this procedure to be very efficient, especially for large-scale applications. We have conducted extensive experiments to compare DeepECOCs with traditional ECOC, feature learning and deep learning algorithms. The results demonstrate that DeepECOCs perform, not only better than existing ECOC and feature learning algorithms, but also related to deep learning ones in most cases.

Speech emotion analysis using convolutional neural network (CNN) and gamma classifier-based error correcting output codes (ECOC)

Speech emotion analysis is one of the most basic requirements for the evolution of Artificial Intelligence (AI) in the field of human–machine interaction. Accurate emotion recognition in speech can be effective in applications such as online support, lie detection systems and customer feedback analysis. However, the existing techniques for this field have not yet met sufficient development. This paper presents a new method to improve the performance of emotion analysis in speech. The proposed method includes the following steps: pre-processing, feature description, feature extraction, and classification. The initial description of speech features in the proposed method is done by using the combination of spectro-temporal modulation (STM) and entropy features. Also, a Convolutional Neural Network (CNN) is utilized to reduce the dimensions of these features and extract the features of each signal. Finally, the combination of gamma classifier (GC) and Error-Correcting Output Codes (ECOC) is applied to classify features and extract emotions in speech. The performance of the proposed method has been evaluated using two datasets, Berlin and ShEMO. The results show that the proposed method can recognize speech emotions in the Berlin and ShEMO datasets with an average accuracy of 93.33 and 85.73%, respectively, which is at least 6.67% better than compared methods.

Asbestos detection in construction and demolition waste by different classification methods applied to short-wave infrared hyperspectral images

In this study, different multivariate classification methods were applied to hyperspectral images acquired, in the short-wave infrared range (SWIR: 1000–2500 nm), to define and evaluate quality control actions applied to construction and demolition waste (C&DW) flow streams, with particular reference to the detection of hazardous material as asbestos. Three asbestos fibers classes (i.e., amosite, chrysotile and crocidolite) inside asbestos-containing materials (ACM) were investigated. Samples were divided into two groups: calibration and validation datasets. The acquired hyperspectral images were first explored by Principal Component Analysis (PCA). The following multivariate classification methods were selected in order to verify and compare their efficiency and robustness: Hierarchical Partial Least Squares-Discriminant Analysis (Hi-PLSDA), Principal Component Analysis k-Nearest Neighbors (PCA-kNN) and Error Correcting Output Coding with Support Vector Machines (ECOC-SVM). The classification results obtained for the three models were evaluated by prediction maps and the values of performance parameters (Sensitivity and Specificity). Micro-X-ray fluorescence (micro-XRF) maps confirmed the correctness of classification results. The results demonstrate how SWIR-HSI technology, coupled with multivariate analysis modelling, is a promising approach to develop both “off-line” and “online” fast, reliable and robust quality control strategies, finalized to perform a quick assessment of ACM presence.

TMM: A comprehensive CAD system for hepatic fibrosis 5-grade METAVIR staging based on liver MRI.

Precise staging of hepatic fibrosis with MRI is necessary as it can assist precision medicine. Computer aided diagnosis (CAD) system with distinguishing radiomics features and radiologists domain knowledge is expected to obtain 5-grade meta-analysis of histological data in viral hepatitis (METAVIR)staging. This study aims to obtain the precise staging of hepatic fibrosis based on MRI as it predicts the risk of future liver-related morbidity and the need for treatment, monitoring and surveillance. Based on METAVIR score, fibrosis can be divided into five stages. Most previous researches focus on binary classification, such as cirrhosis versus non-cirrhosis, early versus advanced fibrosis, and substantial fibrosis or not. In this paper, a comprehensive CAD system TMM is proposed to precisely class hepatic fibrosis into five stages for precision medicine instead of the common binaryclassification. We propose a novel hepatic fibrosis staging CAD system TMM which includes three modules, Two-level Image Statistical Radiomics Feature (TISRF), Monotonic Error Correcting Output Codes (MECOC) and Monotone Multiclassification with Deep Forest (MMDF). TISRF extracts radiomics features for distinguishing different hepatic fibrosis stages. MECOC is proposed to encode monotonic multiclass by making full use of the progressive severity of hepatic fibrosis and increase the fault tolerance and error correction ability. MMDF combines multiple Deep Forest network to ensure the final five-class classification, which can achieve more precise classification than the common binary classification. The performance of the proposed hepatic fibrosis CAD system is tested on the hepatic data collected from our rabbits models offibrosis. A total of 140 regions of interest (ROI) are selected from MRI T1W of liver fibrosis models in 35 rabbits with F0(n=16), F1(n=28), F2(n=29), F3(n=44) and F4(n=23). The performance is evaluated by five-fold cross-validation. TMM can achieve the highest total accuracy of 72.14% for five fibrosis stages compared with other popular classifications. To make a comprehensive comparison, a binary classification experiment have been carried out. T1WI can obtain precise staging of hepatic fibrosis with the help of comprehensive CAD including radiomics features extraction inspired by radiologists, monotonic multiclass according to the severity of hepatic fibrosis, and deep learningclassification.

Methodological approach for the automatic discrimination of pictorial materials using fused hyperspectral imaging data from the visible to mid-infrared range coupled with machine learning methods

Hyperspectral imaging represents a powerful tool for the study of artwork’s materials since it permits to obtain simultaneously information about the spectral behavior of the materials and their spatial distribution. By combining hyperspectral images performed on several spectral intervals (visible, near infrared and mid-infrared ranges) through chemometric methods it is possible to clearly identify most of the materials used in painting (i.e., pigments, dyes, varnishes, and binders). Moreover, in the last decade, the development of machine learning algorithms coupled with comprehensive and continuously updated databases opens new perspective on the automatic recognition of pictorial materials.In this work, we propose a novel procedure to support the automatic discrimination of pictorial materials consisting in a mid-level data fusion on imaging datasets coming from two commercial hyperspectral cameras, in the 400–1000 nm and 1000–2500 nm spectral ranges, respectively, and a MAcroscopic Fourier Transform InfRared scanning in reflection mode (MA-rFTIR), in the 7000 to 350 cm-1 (1428 nm − 28 μm) spectral range. The automatic recognition of 102 pictorial mock-ups from the fused data is performed by testing the performance of ECOC-SVM (error-correcting output coding and support vector machine) model obtaining a good predictive result with only few pixels that are confused with other classes. The methodology described in this paper demonstrates that an accurate paint layer multiclass recognition is feasible, and the use of chemometric approaches solves some challenges involving the study of materials.

An adaptive error-correcting output codes algorithm based on gene expression programming and similarity measurement matrix

The multi-class classification task is one of the most common tasks in machine learning. As a typical solution based on a partitioning strategy, Error-Correcting Output Codes (ECOC) can transform a multi-class classification problem into multiple binary classification problems. The key of ECOC is to construct an effective codematrix to represent a set of class decomposition schemes, which transforms a multiclass problem into a group of binary class problems. Consequently, the design of a fast and effective ECOC codematrix generation method is of great research significance and value for solving multi-class classification problems. In ECOC algorithms, the design of codematrix is treated as a combination problem between different code columns, in which the evolutionary algorithm shows a great advantage. Based on this consideration, the Gene Expression Programming (GEP) is applied to search for the codematrix with high performance because its expressive tree structure makes it well represent codematrcies for subsequent optimization operations. This paper proposes an adaptive ECOC algorithm based on Gene Expression Programming (GEP) and similarity measurement matrix, named GEP-ECOC. In our GEP, each individual represents a set of columns to form a random ECOC codematrix, which is optimized in the evolutionary process. Meanwhile, the crossover and mutation operations are modified to include a legality checking process to ensure that the generated codematrix satisfies the ECOC constraints. The GEP-based ECOC codematrix generation algorithm can quickly produce a codematrix with better performance, which ensures the efficiency of the algorithm to a certain extent. In addition, an adaptive algorithm based on a similarity measurement matrix is proposed to add new columns to the current codematrix, aiming to better handle hard classes. Our algorithm is compared with other algorithms on various data sets, and the experimental results confirm that our GEP-ECOC can balance the efficiency and performance of the algorithm and achieve higher performance.

RFID Backscatter Based Sport Motion Sensing Using ECOC-Based SVM.

With the advent of the 5G era, radio frequency identification (RFID) has been widely applied in various fields as one of the key technologies for the Internet of Things (IoT) to realize the Internet of Everything (IoE). In recent years, RFID-based motion sensing has emerged as an important research area with great potential for development. In this paper, an RFID backscatter sport motion sensing scheme is proposed, which effectively solves the multi-classification problem by using the received signal strength (RSS) of the backscattered RFID and the error correcting output coding (ECOC)-based support vector machine (SVM). We conduct extensive experiments to validate the effectiveness of the proposed scheme, in which the signal intensities of different types of action poses are collected and the SVM is used as the classification algorithm to achieve high classification accuracies.

Identification of Solid and Liquid Materials Using Acoustic Signals and Frequency-Graph Features.

Material identification is playing an increasingly important role in various sectors such as industry, petrochemical, mining, and in our daily lives. In recent years, material identification has been utilized for security checks, waste sorting, etc. However, current methods for identifying materials require direct contact with the target and specialized equipment that can be costly, bulky, and not easily portable. Past proposals for addressing this limitation relied on non-contact material identification methods, such as Wi-Fi-based and radar-based material identification methods, which can identify materials with high accuracy without physical contact; however, they are not easily integrated into portable devices. This paper introduces a novel non-contact material identification based on acoustic signals. Different from previous work, our design leverages the built-in microphone and speaker of smartphones as the transceiver to identify target materials. The fundamental idea of our design is that acoustic signals, when propagated through different materials, reach the receiver via multiple paths, producing distinct multipath profiles. These profiles can serve as fingerprints for material identification. We captured and extracted them using acoustic signals, calculated channel impulse response (CIR) measurements, and then extracted image features from the time-frequency domain feature graphs, including histogram of oriented gradient (HOG) and gray-level co-occurrence matrix (GLCM) image features. Furthermore, we adopted the error-correcting output code (ECOC) learning method combined with the majority voting method to identify target materials. We built a prototype for this paper using three mobile phones based on the Android platform. The results from three different solid and liquid materials in varied multipath environments reveal that our design can achieve average identification accuracies of 90% and 97%.

A self-adaptive soft-recoding strategy for performance improvement of error-correcting output codes

The technique of error-correcting output codes (ECOC) has been proven to be of high discriminative ability in many classification applications. However, most algorithms on the ECOC were designed based on the binary or ternary codes (referred to as the hard codes), which might fail to precisely correct errors in dealing with tough tasks. In this study, a Soft-Recoding strategy based on a self-adaptive algorithm is proposed, which replaces the traditional hard codes with the real-value elements to better fit the output distribution of the base learners. This is achieved by minimizing the ratio of two distances: the distance of the output vector to the ground-truth class, and the average distance of the output vector to the remaining classes. Extensive experiments using five different hard ECOC algorithms and the corresponding softened versions on twenty datasets with diversified numbers of features and classes confirm the effectiveness of our Soft-Recoding strategy in promoting the performance of the original ECOC algorithms. Our source code and additional results are available at: github.com/MLDMXM2017/SA-soft-recoding.

Wafer map defect pattern detection method based on improved attention mechanism

Wafer map defect pattern recognition is an indispensable part in the semiconductor manufacturing process. Wafer map defect pattern recognition and classification can locate the cause of failures in the manufacturing process. In this study, we propose a deep convolutional neural network architecture incorporating improved convolutional block attention module (I-CBAM) for pattern recognition and classification of single-type wafer map defects. The proposed method consists of three steps: First, a multi-branch attention module is designed, which focuses more on the main information of defect clusters, extracts richer feature information, and improves feature extraction capabilities. Secondly, I-CBAM is integrated into the ResneXt50 backbone network to extract wafer map defect features. Finally, the extracted features are fed to a support vector machine combined with an error-correcting output code to classify the wafer map defect pattern. The experimental results on the real-world datasets WM-811K show that the accuracy rate of the I-CBAM-ResneXt50 can reach 96.96%. Compared with the existing algorithms, the proposed model can achieve better recognition and classification results.