Traditional Recognition Methods Research Articles

Dual-Feature Fusion Learning: An Acoustic Signal Recognition Method for Marine Mammals

Marine mammal acoustic signal recognition is a key technology for species conservation and ecological environment monitoring. Aiming at the complex and changing marine environment, and because the traditional recognition method based on a single feature input has the problems of poor environmental adaptability and low recognition accuracy, this paper proposes a dual-feature fusion learning method. First, dual-domain feature extraction is performed on marine mammal acoustic signals to overcome the limitations of single feature input methods by interacting feature information between the time-frequency domain and the Delay-Doppler domain. Second, this paper constructs a dual-feature fusion learning target recognition model, which improves the generalization ability and robustness of mammal acoustic signal recognition in complex marine environments. Finally, the feasibility and effectiveness of the dual-feature fusion learning target recognition model are verified in this study by using the acoustic datasets of three marine mammals, namely, the Fraser’s Dolphin, the Spinner Dolphin, and the Long-Finned Pilot Whale. The dual-feature fusion learning target recognition model improved the accuracy of the training set by 3% to 6% and 20% to 23%, and the accuracy of the test set by 1% to 3% and 25% to 38%, respectively, compared to the model that used the time-frequency domain features and the Delay-Doppler domain features alone for recognition.

A Review of Research on Handwritten Chinese Character Recognition with Multi-Feature Fusion

This paper analyzes the progress of handwritten Chinese character recognition technology, from two perspectives: traditional recognition methods and deep learning-based recognition methods. Firstly, the complexity of Chinese character recognition is pointed out, including its numerous categories, complex structure, and the problem of similar characters, especially the variability of handwritten Chinese characters. Subsequently, recognition methods based on feature optimization, model optimization, and fusion techniques are highlighted. The fusion studies between feature optimization and model improvement are further explored, and these studies further enhance the recognition effect through complementary advantages. Finally, the article summarizes the current challenges of Chinese character recognition technology, including accuracy improvement, model complexity, and real-time problems, and looks forward to future research directions.

Design and Implementation of Apple Leaf Disease Recognition System Based on ResNet50

Timely identification of apple leaf diseases is critical to preventing crop losses and safeguarding yields. Spotted leaf drop, brown spot, gray spot, mosaic and rust are all common types of apple leaf diseases, and their presence signals a potential risk that could lead to significant reductions in fruit and crop yields. The apple industry is thus at risk of economic losses. In order to solve this problem, this study applies ResNet50, a deep learning model for image recognition and classification of apple leaf diseases, and develops an intelligent recognition system for apple leaf diseases by combining PyQt technology. The purpose of this system is to overcome the shortcomings of traditional recognition methods. Through experimental validation, the ResNet50 model achieves a high accuracy rate of 93.19% in apple leaf disease recognition, demonstrating its efficiency and practicality in practical applications.

Multisource working condition recognition via nonlinear kernel learning and p-Laplacian manifold learning

Effectively utilizing information from multiple sources and fewer labeled operating condition samples from a sucker-rod pumping system for oil production can improve the recognition effects and engineering practicability. Nevertheless, this is a challenging energy environment scientific application research subject, and therefore, this study proposes an operating state recognition scheme that relies on multisource nonlinear kernel learning and p-Laplacian high-order manifold regularization logistic regress. Specifically, three measured features are selected and extracted, i.e., wellhead temperature signal, electrical power signal, and ground dynamometer cards, based on mechanism analysis, expert experience, and prior knowledge. Finally, we establish the operating condition recognition model to recognize by the multisource p-Laplacian regularization kernel logistic regress algorithm. The experimental data are derived from 60 wells of a common high-pressure and low-permeability thin oil reservoir block of an oil field in China. The corresponding trials highlight that our scheme outperforms traditional recognition methods by exploiting single-source and multiple-feature data. In the context of fewer labeled samples, the proposed method has a greater recognition effect, engineering practicability, and better model robustness than the existing schemes based on other high-order manifold learning, verifying our method's effectiveness.

Modeling Digital Personality: A Fuzzy-Logic-Based Myers–Briggs Type Indicator for Fine-Grained Analytics of Digital Human

Digital human in cyberspace can help provide humanized services in specific applications, such as question & answer systems, recommender systems, chatter robots, and intelligent assistants. While most researches focus on behavior analytics, few of them integrate the personality that is also a closely related factor. As a classic indicator for personality representation, Myers–Briggs type indicator (MBTI) categorizes an individual into mutually exclusive types from four dichotomous axes (extraversion versus introversion, sensing versus intuition, thinking versus feeling, judging versus perceiving). Traditional recognition method using MBTI simply measures the user’s preference frequency in each axis through questionnaires, treating the dominant value as the identified result. Such a paradigm, however, represents all the people with only 16 types and cannot distinguish heterogeneous users clearly. This article proposes a novel personality recognition method using fuzzy logic. Different from previous classifications, our new method categorizes the individual in a continuous space and represents one’s personality in a more fine-grained level. We have designed comparative psychological tests for 77 people. The validation experiments on such tests indicate that the fuzzy-logic-based method is not only consistent with the classic MBTI tests (in the sense of defuzzification) but also provides the uncertainty for each personality type. Therefore, it can be viewed as a generalization of the classic MBTI tests and promotes the representation of individual’s heterogeneity for fine-grained analytics of digital human.

ERTNet: an interpretable transformer-based framework for EEG emotion recognition.

Emotion recognition using EEG signals enables clinicians to assess patients' emotional states with precision and immediacy. However, the complexity of EEG signal data poses challenges for traditional recognition methods. Deep learning techniques effectively capture the nuanced emotional cues within these signals by leveraging extensive data. Nonetheless, most deep learning techniques lack interpretability while maintaining accuracy. We developed an interpretable end-to-end EEG emotion recognition framework rooted in the hybrid CNN and transformer architecture. Specifically, temporal convolution isolates salient information from EEG signals while filtering out potential high-frequency noise. Spatial convolution discerns the topological connections between channels. Subsequently, the transformer module processes the feature maps to integrate high-level spatiotemporal features, enabling the identification of the prevailing emotional state. Experiments' results demonstrated that our model excels in diverse emotion classification, achieving an accuracy of 74.23% ± 2.59% on the dimensional model (DEAP) and 67.17% ± 1.70% on the discrete model (SEED-V). These results surpass the performances of both CNN and LSTM-based counterparts. Through interpretive analysis, we ascertained that the beta and gamma bands in the EEG signals exert the most significant impact on emotion recognition performance. Notably, our model can independently tailor a Gaussian-like convolution kernel, effectively filtering high-frequency noise from the input EEG data. Given its robust performance and interpretative capabilities, our proposed framework is a promising tool for EEG-driven emotion brain-computer interface.

Fault Feature Mining and Identification Method of 10kV XLPE Cable Combining SAE and RF

Background: Feature extraction methods such as statistical features and image features based on traditional partial discharge spectrograms require the support of expert experience and prior knowledge, making their engineering applications have significant limitations. Currently, electrical equipment fault diagnosis is moving towards intelligent and scientific directions, and how to apply deep learning methods for more accurate, intelligent, and autonomous diagnosis has become a hot issue in the current field. background: Feature extraction methods such as statistical features and image features based on traditional partial discharge spectrograms require the support of expert experience and prior knowledge, making their engineering applications have significant limitations. Methods: The construction and optimal selection of high-voltage cable partial discharge feature space is an important means to improve recognition accuracy. This paper proposes a new method that can independently and deeply mine partial discharge image features to quickly identify partial discharge types. Firstly, a self encoder is used to encode and decode partial discharge images, and a multi-level stack structure is used to achieve the goal of deep feature mining; then, the partial discharge data features decoded based on a stack self encoder are imported into a random forest network for type recognition; Finally, based on the random forest algorithm, the redundant feature space is optimized and compared with other traditional recognition methods. Results: The recognition accuracy of the proposed method is about 10% higher than that of traditional methods. Conclusion: The optimized feature parameters can maintain more than 90% recognition accuracy in both random forest algorithms, common support vector machines, and BP neural networks, proving the feasibility and effectiveness of the method in this paper. result: The recognition accuracy of the proposed method is about 10% higher than that of traditional methods.

Museum Achieving Future Sustainable Development: A Study on the Attraction of Historical Exhibits in Museum Nursing Direction

The aim of this study is to explore a method that combines Digital Twins (DTs) with Convolutional Neural Network (CNN) algorithms to analyze the attractiveness of historical and cultural exhibits in museums and humanistic care, in order to achieve intelligent and digital development of exhibitions under museum humanistic care. The concept of "Health Museum and Health Management" has received initial attention and rapid response from the nursing community in Europe and America. Its essence emphasizes the intervention of museum intelligence in medical and health care and the role of improving the medical and health system, creating the medical service function of museums. Firstly, using DTs technology to digitally model the historical and cultural exhibits of the museum, achieving the display and interaction of virtual exhibits. Then, the Mini_Xception network was proposed to improve the CNN algorithm and combined with the ResNet algorithm to construct a facial emotion recognition model. Finally, using this model, the attractiveness of museum historical and cultural DTs exhibits was accurately predicted by recognizing people's facial expressions. The comparative experimental results show that this recognition method can greatly improve recognition accuracy and scalability. Compared with traditional recognition methods, the recognition accuracy can be improved by 5.53%, and 2.71s can reduce the data transmission delay of the model. The scalability of enhanced recognition types can also meet real-time interaction requirements in a shorter amount of time. This study has important reference value for the digital and intelligent development of museums combined with nursing exhibitions.

Using a Convolutional Neural Network for Machine Written Character Recognition

Convolutional neural networks are special types of artificial neural networks that can solve various tasks in computer vision, such as image classification, object detection, and general recognition. The paper presents the basic building blocks of convolutional neural networks and their architecture, and compares their recognition accuracy with other character recognition techniques using the example of character recognition from vehicle registration plates. The purpose of the experiments was to determine the optimal configuration of the convolutional neural network and the influence of the size and design method of the training set on the recognition rate. The study shows that although convolutional neural networks have recently gained attention, traditional recognition methods are still relevant, and the choice of the right classifier and its configuration depends on the type of recognition task.

Improved U-Net for Growth Stage Recognition of In-Field Maize

Precise recognition of maize growth stages in the field is one of the critical steps in conducting precision irrigation and crop growth evaluation. However, due to the ever-changing environmental factors and maize growth characteristics, traditional recognition methods usually suffer from limitations in recognizing different growth stages. For the purpose of tackling these issues, this study proposed an improved U-net by first using a cascade convolution-based network as the encoder with a strategy for backbone network replacement to optimize feature extraction and reuse. Secondly, three attention mechanism modules have been introduced to upgrade the decoder part of the original U-net, which highlighted critical regions and extracted more discriminative features of maize. Subsequently, a dilation path of the improved U-net was constructed by integrating dilated convolution layers using a multi-scale feature fusion approach to preserve the detailed spatial information of in-field maize. Finally, the improved U-net has been applied to recognize different growth stages of maize in the field. The results clearly demonstrated the superior ability of the improved U-net to precisely segment and recognize maize growth stage from in-field images. Specifically, the semantic segmentation network achieved a mean intersection over union (mIoU) of 94.51% and a mean pixel accuracy (mPA) of 96.93% in recognizing the maize growth stage with only 39.08 MB of parameters. In conclusion, the good trade-offs made in terms of accuracy and parameter number demonstrated that this study could lay a good foundation for implementing accurate maize growth stage recognition and long-term automatic growth monitoring.

Studies Advanced in Mask Face Recognition based on Deep Learning

In the era of epidemic, wearing a mask when going out has become a more common phenomenon. And how to complete face recognition and guarantee certain accuracy without letting users take off their masks has been a challenge in recently years’ face recognition field. In this paper, the traditional masked face recognition method and the new MTCNN deep learning masked face recognition method are compared and analyzed, and other similar masked experiments are introduced as data references. It is synthetically found that the accuracy of MTCNN masked face recognition using CASIA-FaceV5 as dataset is more than 90%, which is far better than other traditional recognition methods, but its requirement for dataset image quality is high, and the training time is long and costly. We hope that the process analysis and result comparison of different methods in this paper can shed light on the future development of masked face recognition technology.

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.

A Deep Learning Method for Facies Recognition from Core Images and Its Application: A Case Study of Mackay River Oil Sands Reservoir

There is a large amount of drilling core data in the Mackay River oil sands block in Canada, and the accurate identification of facies from the cores is important and necessary for the understanding of the subsurface reservoir. The traditional recognition method of facies from cores is by human work and is very time consuming. Furthermore, the results are different according to different geologists because of the subjective judgment criterion. An efficient and objective method is important to solve the above problem. In this paper, the deep learning image-recognition algorithm is used to automatically and intelligently recognize the facies type from the core image. Through a series of high-reliability preprocessing operations, such as cropping, segmentation, rotation transformation, and noise removal of the original core image, that have been manually identified, the key feature information in the images is extracted based on the ResNet50 convolutional neural network. On the dataset of about 200 core images from 13 facies, an intelligent identification system of facies from core images is constructed, which realizes automatic facies identification from core images. Comparing this method with traditional convolutional neural networks and support vector machines (SVM), the results show that the recognition accuracy of this model is as high as 91.12%, which is higher than the other two models. It is also shown that for a relatively special dataset, such as core images, it is necessary to rely on their global features in order to classify them, and, with a large similarity between some of the categories, it is extremely difficult to classify them. The selection of a suitable neural network model can have a great impact on the accuracy of recognition results. Then, the recognized facies are input as hard data to construct the three-dimensional facies model, which reveals the complex heterogeneity and distribution of the subsurface reservoir for further exploration and development.

A quantitative identification method based on CWT and CNN for external and inner broken wires of steel wire ropes

The detection of broken wires in steel wire ropes is of great significance for the production safety. However, the existing identification techniques mainly focus on the external broken wires problem. Here, the artificial feature extraction is one of the most important method, while only the prior knowledge of the artificial feature extraction method is adequate, the identification precision can be satisfied. Therefore, it is still a challenge to realize intelligent diagnosis for the broken wires. Besides, the identification of internal broken wires problem is still not well solved. In this paper, a quantitative identification method based on continuous wavelet transform (CWT) and convolutional neural network (CNN) is proposed to solve the internal and external broken wires identification problem. The key technology of this research is that the fault information from the time-frequency images converted by the magnetic flux leakage (MFL) signals can be automatically extracted through a designed CNN. The main innovation is that the complex signal processing work can be eliminated and the internal and external broken wires can be accurately identified simultaneously by combining CWT and CNN. The experimental results of a steel wire rope test rig are compared with the traditional recognition method, which shows that the proposed method achieved significant improvement on detection accuracy and recognition performance.

Detection and Identification of Mesoscale Eddies in the South China Sea Based on an Artificial Neural Network Model—YOLOF and Remotely Sensed Data

Mesoscale eddies are typical mesoscale ocean phenomena that exist widely in all oceans and marginal seas around the world, playing important roles in ocean circulation and material transport. They also have important impacts on the safe navigation of ships and underwater acoustic communications. Traditional mesoscale eddy identification methods are subjective and usually depend on parameters that must be pre-defined or adjusted by experts, meaning that their accuracy cannot be guaranteed. With the rise of deep learning, the “you only look once” (YOLO) series target recognition models have been shown to present certain advantages in eddy detection and recognition. Based on sea level anomaly (SLA) data provided over the past 30 years by the Copernicus Marine Environment Monitoring Service (CMEMS), as well as deep transfer learning, we propose a method for oceanic mesoscale eddy detection and identification based on the “you only look once level feature” (YOLOF) model. Using the proposed model, the mesoscale eddies in the South China Sea from 1993 to 2021 were detected and identified. Compared with traditional recognition methods, the proposed model had a better recognition effect (with an accuracy of 91%) and avoided the bias associated with subjectively set thresholds; to a certain extent, the model also improved the detection of and the identification speed for mesoscale eddies. The method proposed in this paper not only promotes the development of deep learning in the field of oceanic mesoscale eddy detection and identification, but also provides an effective technical method for the study of mesoscale eddy detection using sea surface height data.

Multi-scale convolutional neural network for texture recognition

Texture is of great significance for humans and robots to recognize the surface features of objects. In the field of texture recognition, methods based on spatial information have been widely applied. However, in the case of fine texture recognition, the methods only using spatial features for texture recognition may ignore the features of small texture and result in poor recognition accuracy. In this paper, a Multi-Scale Convolutional Neural Network (MS-CNN) is proposed to recognize millimetric fine textures. MS-CNN has three paths to extract features of different time scales from different numbers of continuous pressure images. The three paths have the same backbone network structure, but the number of convolution cores of the convolution layer in the backbone network of adjacent paths is doubled. After the convolution layer, we add SE-Net to automatically obtain the importance of each feature channel through learning, and then improve the useful features to further improve the accuracy. Finally, the output of all paths is averaged, and the classification vector is calculated through the final full connection layer. To validate MS-CNN, data sets containing 9 kinds of millimetric fine textures are obtained by flexible tactile sensors. The pressure image is transformed into one-dimensional vectors and these vectors are arranged into a sample in time order as the input of MS-CNN. In addition, the attention mechanism module is applied to MS-CNN to train the weight of each convolution channel and increase the proportion of useful features in the network. Ablation experiments prove that our modification is effective and our method achieves an accuracy of 81.83% for 9 fine textures. Compared with traditional recognition methods, our method achieves better recognition performance.

Lightweight individual cow identification based on Ghost combined with attention mechanism

Individual cow identification is a prerequisite for intelligent dairy farming management, and is important for achieving accurate and informative dairy farming. Computer vision-based approaches are widely considered because of their non-contact and practical advantages. In this study, a method based on the combination of Ghost and attention mechanism is proposed to improve ReNet50 to achieve non-contact individual recognition of cows. In the model, coarse-grained features of cows are extracted using a large sensory field of cavity convolution, while reducing the number of model parameters to some extent. ResNet50 consists of two Bottlenecks with different structures, and a plug-and-play Ghost module is inserted between the two Bottlenecks to reduce the number of parameters and computation of the model using common linear operations without reducing the feature map. In addition, the convolutional block attention module (CBAM) is introduced after each stage of the model to help the model to give different weights to each part of the input and extract the more critical and important information. In our experiments, a total of 13 cows' side view images were collected to train the model, and the final recognition accuracy of the model was 98.58%, which was 4.8 percentage points better than the recognition accuracy of the original ResNet50, the number of model parameters was reduced by 24.85 times, and the model size was only 3.61 MB. In addition, to verify the validity of the model, it is compared with other networks and the results show that our model has good robustness. This research overcomes the shortcomings of traditional recognition methods that require human extraction of features, and provides theoretical references for further animal recognition.

JR-TFViT: A Lightweight Efficient Radar Jamming Recognition Network Based on Global Representation of the Time–Frequency Domain

Efficient jamming recognition capability is a prerequisite for radar anti-jamming and can enhance the survivability of radar in electronic warfare. Traditional recognition methods based on manually designed feature parameters have found it difficult to cope with the increasingly complex electromagnetic environment, and research combining deep learning to achieve jamming recognition is gradually increasing. However, existing research on radar jamming recognition based on deep learning can ignore the global representation in the jamming time–frequency domain data, while not paying enough attention to the problem of lightweighting the recognition network itself. Therefore, this paper proposes a lightweight jamming recognition network (JR-TFViT) that can fuse the global representation of jamming time–frequency domain data while combining the advantages of the Vision Transformer and a convolutional neural network (CNN). The global representation and local information in the jamming time–frequency data are fused with the assistance of the multi-head self-attention (MSA) mechanism in the transformer to improve the feature extraction capabilities of the recognition network. The model’s parameters are further decreased by modifying the standard convolutional operation mechanism and substituting the convolutional operation needed by the network with Ghost convolution, which has less parameters. The experimental results show that the JR-TFViT requires fewer model parameters while maintaining higher recognition performance than mainstream convolutional neural networks and lightweight CNNs. For 12 types of radar jamming, the JR-TFViT achieves 99.5% recognition accuracy at JNR = −6 dB with only 3.66 M model parameters. In addition, 98.9% recognition accuracy is maintained when the JR-TFViT parameter number is further compressed to 0.67 M.

Bimodal Learning Engagement Recognition from Videos in the Classroom.

Engagement plays an essential role in the learning process. Recognition of learning engagement in the classroom helps us understand the student’s learning state and optimize the teaching and study processes. Traditional recognition methods such as self-report and teacher observation are time-consuming and obtrusive to satisfy the needs of large-scale classrooms. With the development of big data analysis and artificial intelligence, applying intelligent methods such as deep learning to recognize learning engagement has become the research hotspot in education. In this paper, based on non-invasive classroom videos, first, a multi-cues classroom learning engagement database was constructed. Then, we introduced the power IoU loss function to You Only Look Once version 5 (YOLOv5) to detect the students and obtained a precision of 95.4%. Finally, we designed a bimodal learning engagement recognition method based on ResNet50 and CoAtNet. Our proposed bimodal learning engagement method obtained an accuracy of 93.94% using the KNN classifier. The experimental results confirmed that the proposed method outperforms most state-of-the-art techniques.

Knowledge-Driven Recognition Methodology of Partial Discharge Patterns in GIS

Recognition of partial discharge (PD) patterns in gas insulated switchgear (GIS), as a basis of fault diagnosis, provides essential information for the condition assessment of GIS. However, traditional recognition methods are limited to handcrafted feature extraction or are extremely sensitive to the quantity and quality of datasets. Therefore, this article proposes a knowledge-driven algorithm, composed of the feature space and the knowledge space, to automatically extract PD features and improve the performance on noised, insufficient, and imbalanced datasets. First, the deep residual network (ResNet) in feature space extracts features from raw signals. Second, in knowledge space, the graph convolutional network (GCN) extracts additional information from the knowledge graph, which compensates for the missing information of original datasets. Finally, the algorithm recognizes patterns by ranking similarities between feature vectors and knowledge vectors. Verified by the comparison experiment, the proposed algorithm outperforms traditional methods with the accuracy of 99.58% on the experimental dataset and 95.67% on the online-detected dataset. Moreover, the accuracy of the proposed algorithm achieves 88.79% and 70.37% on noised and insufficient datasets, respectively, while the F-measure is higher than those of the comparison methods by 12.95% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 18.69% on imbalanced datasets.