Recognition Problem Research Articles

Few-shot agricultural pest recognition based on multimodal masked autoencoder

Visual recognition methods based on deep convolutional neural networks have performed well in pest diagnosis and have gradually become a research hotspot. However, agricultural pest recognition faces challenges such as few-shot learning, category imbalance, similarity in appearance, and small pest targets. Existing deep learning-based pest recognition methods typically rely solely on unimodal image data, which results in a model whose recognition performance is heavily dependent on the size and quality of the annotated training dataset. However, the construction of large-scale, high-quality pest datasets requires significant economic and technical costs, limiting the practical generalization of existing methods for pest recognition. To address these challenges, this paper proposes a few-shot pest recognition model called MMAE (multimodal masked autoencoder). Firstly, the masked autoencoder of MMAE integrates self-supervised learning, which can be applied to few-shot datasets and improves recognition accuracy. Secondly, MMAE embeds textual modal information on top of image modal information, thus improving the performance of pest recognition by utilizing the correlation and complementarity between the two modalities. The experimental results show that MMAE is the most effective for pest identification compared with the existing excellent models, and the identification accuracy is as high as 98.12%, which is 1.61 percentage points higher than the current state-of-the-art MAE method. The work in this paper shows that the introduction of textual information can assist the visual coder in capturing agricultural pest characterization information at a higher level of granularity, providing a methodological reference for solving the problem of agricultural pest recognition under few-shot conditions.

ITIMCA: Image-Text Information and Cross-Attention for Multi-Modal Cassava Leaf Disease Classification Based on a Novel Multi-Modal Dataset in Natural Environments

With artificial intelligence and deep learning development, crop disease recognition methods leverage deep networks for automatic feature learning but rely on the volume of training data. Addressing the scarcity of data in agriculture, few-shot learning (FSL) and multi-modal learning have become focal points. However, existing methods are confined to a single modality or insufficiently exploit cross-modal features. To address this, we propose a multi-modal contrastive learning approach integrating images and text to tackle the problem of small-sample recognition. This method combines CLIP multi-modal pre-training with cross-attention, termed ITIMCA. Experimental validation demonstrates the effectiveness of our approach in cassava leaf disease recognition tasks under natural conditions. Experimental results show that the proposed model achieved an accuracy of 78.00%, a precision of 88.48%, a recall rate of 80.00%, and an F1-Score of 79.00% on the cassava leaf disease identification and classification dataset. These results suggest that the proposed network effectively identifies cassava leaf diseases.

An Industrial Micro Parts Recognition Technology Based on Improved Yolov8

Abstract Aiming at the recognition and classification problem of micro assembly parts in industrial production, the Yolov8 object detection algorithm was used as the base model to improve the C2f class in the backbone. And apply the improved object detection algorithm to the recognition field of detecting assembly parts. By collecting images of gears, nails, and screws from various angles on Roboflow, a training set and a validation set containing three types of gears, nails, and screws are formed. At the same time, in order to improve the robustness of the Yolov8 object detection algorithm, data processing methods such as adding noise and image rotation were adopted for the samples in the data. Due to the use of Yolov8 as the base model, a TXT text file containing label prediction box position information was formed after labelling the dataset on Roboflow. Based on Python (3.10.12) and cloud platform, improved Yolov8 object detection algorithm was trained and network validation was carried out. Use TXT files as input for the model to obtain and learn features of gears, nails, and screws. After 200 epochs, the mAP for detecting gears, nails, and screws increased by about 3% compared to the base model.

Graph-Structure-Based Multigranular Belief Fusion for Human Activity Recognition.

The belief functions (BFs) introduced by Shafer in the mid of 1970s are widely applied in information fusion to model epistemic uncertainty and to reason about uncertainty. Their success in applications is however limited because of their high-computational complexity in the fusion process, especially when the number of focal elements is large. To reduce the complexity of reasoning with BFs, we can envisage as a first method to reduce the number of focal elements involved in the fusion process to convert the original basic belief assignments (BBAs) into simpler ones, or as a second method to use a simple rule of combination with potentially a loss of the specificity and pertinence of the fusion result, or to apply both methods jointly. In this article, we focus on the first method and propose a new BBA granulation method inspired by the community clustering of nodes in graph networks. This article studies a novel efficient multigranular belief fusion (MGBF) method. Specifically, focal elements are regarded as nodes in the graph structure, and the distance between nodes will be used to discover the local community relationship of focal elements. Afterward, the nodes belonging to the decision-making community are specially selected, and then the derived multigranular sources of evidence can be efficiently combined. To evaluate the effectiveness of the proposed graph-based MGBF, we further apply this new approach to combine the outputs of convolutional neural networks + attention (CNN + Attention) in the human activity recognition (HAR) problem. The experimental results obtained with real datasets prove the potential interest and feasibility of our proposed strategy with respect to classical BF fusion methods.

Divide and Retain: A Dual-Phase Modeling for Long-Tailed Visual Recognition.

This work explores visual recognition models on real-world datasets exhibiting a long-tailed distribution. Most of previous works are based on a holistic perspective that the overall gradient for training model is directly obtained by considering all classes jointly. However, due to the extreme data imbalance in long-tailed datasets, joint consideration of different classes tends to induce the gradient distortion problem; i.e., the overall gradient tends to suffer from shifted direction toward data-rich classes and enlarged variances caused by data-poor classes. The gradient distortion problem impairs the training of our models. To avoid such drawbacks, we propose to disentangle the overall gradient and aim to consider the gradient on data-rich classes and that on data-poor classes separately. We tackle the long-tailed visual recognition problem via a dual-phase-based method. In the first phase, only data-rich classes are concerned to update model parameters, where only separated gradient on data-rich classes is used. In the second phase, the rest data-poor classes are involved to learn a complete classifier for all classes. More importantly, to ensure the smooth transition from phase I to phase II, we propose an exemplar bank and a memory-retentive loss. In general, the exemplar bank reserves a few representative examples from data-rich classes. It is used to maintain the information of data-rich classes when transiting. The memory-retentive loss constrains the change of model parameters from phase I to phase II based on the exemplar bank and data-poor classes. The extensive experimental results on four commonly used long-tailed benchmarks, including CIFAR100-LT, Places-LT, ImageNet-LT, and iNaturalist 2018, highlight the excellent performance of our proposed method.

ALGORITHM FOR IDENTIFYING ABNORMAL ACTIONS

The study is devoted to the problem of recognition of human activity recognition and the definition of normal and abnormal behavior (activity) depending on the action scene. Automated detection of abnormal activity using computer vision technologies and rapid response makes it possible to improve the work of rapid response services, thereby saving human lives or stopping offenses. The paper presents a comprehensive review of methods for recognizing human activity and detecting abnormal human activity based on deep learning. Various classifications of abnormal activity are investigated, and then deep learning methods and neural network architectures used to detect abnormal activity are discussed and analyzed. Based on the comparative analysis of various approaches, an algorithm for recognizing human activity has been proposed and a neural network has been developed that determines violent and nonviolent actions with an accuracy of 92,22% in 150 epochs.

IIS-FVIQA: Finger Vein Image Quality Assessment with intra-class and inter-class similarity

In recent years, Finger Vein Image Quality Assessment (FVIQA) has been recognized as an effective solution to the problem of erroneous recognition resulting from low image quality due to false and missing information in finger vein images, and has become an important part of finger vein recognition systems. Compared to traditional FVIQA methods that rely on domain knowledge, newer methods that reject low-quality images have been favored for their independence from human interference. However, these methods only consider intra-class similarity information and ignore valuable information from inter-class distribution, which is also an important factor in evaluating the performance of recognition systems. In this work, we propose a novel FVIQA approach, named IIS-FVIQA, which concurrently takes into account the intra-class similarity density and inter-class similarity distribution distance within recognition systems. Specifically, our method generates quality scores for finger vein images by combining the information entropy of intra-class similarity distribution and Wasserstein distance of inter-class distribution. Then, we train a regression network for quality prediction using training images and corresponding quality scores. When a new image enters the recognition system, the trained regression network directly predicts the quality score of the image, making it easier for the system to select the corresponding operation based on the quality score of the image. Extensive experiments conducted on benchmark datasets demonstrate that the IIS-FVIQA method proposed in this paper consistently achieves top performance across multiple public datasets. After filtering out 10% of low-quality images predicted by the quality regression network, the recognition system’s performance improves by 43.96% (SDUMLA), 32.23% (MMCBNU_6000), and 21.20% (FV-USM), respectively. Furthermore, the method exhibits strong generalizability across different recognition algorithms (e.g., LBP, MC, and Inception V3) and datasets (e.g., SDUMLA, MMCBNU_6000, and FV-USM).

Using posture recognition algorithms based on machine learning to identify senior health

Faced with the situation that the elderly people at home have dangerous behaviors, the study explores various aspects of motion target detection, real-time target tracking and behavioral pose recognition and classification, using behavioral poses in videos as samples. To tackle the challenges in detecting motion targets, a target detection method based on Gaussian mixture model (GMM) and four frame difference method is proposed; A tracking technique incorporating Kalman filter (KF) is investigated to trail the behavioral changes of the elderly in actual time. A seven-layer convolutional neural network (CNN) is constructed to face the problem of inaccurate behavioral pose recognition. Through relevant experimental analyses, the outcomes show that the increased GMM detection way has a complete profile and the accuracy is significantly improved. The KF target tracking technique can trail the object trajectory in actual time and steadily, with the smallest trailing error value of 0.19. The classification accuracy of the CNN pose recognition model is 95.87%, and the pose classification time is 27 seconds. Its performance is superior to the mean shift algorithm, particle filter algorithm, and Cam Shift algorithm in all aspects. When applied in practice, it can accurately identify whether the elderly’s behavior is abnormal and ensure their daily health.

Diagnosing sucker-rod pumping units by means of a neural network module implemented on the basis of an oilwell controller

Currently, sucker-rod pumping (SRP) units are widely used in oil wells, due to two important factors: costs and ease of use. To optimize production using sucker rod pumps, well Rod Pump Controllers (RPC) have been used for more than 20 years. Today the main method of controlling the sucker-rod pumping unit is the analysis of dynagraph card (determination of the state and mode of operation of the pump based on the dependence of the rod’s load on its position). The qualitative analysis of a dynagraph (DMG) comes down to diagnostics, which detects and identifies signs of possible malfunctions of the pump and the well as a whole. The task of determining malfunctions by a dynagraph is considered difficult for a computer analysis and involves the evaluation of a dynagraph card by a qualified technologist. This article discusses methods and algorithms for determining malfunctions from obtained RPC dynagraphs, implemented directly on base of the well controller. These methods can be divided into analytical and neural network methods. Analytical algorithms describe the DMG defect in the form of formulas or logical dependencies. Neural network methods approach the problem of defect recognition as recognizing a set of unrelated data. This helps to work with a system with a large number of parameters, such as a (SRP). The Naftamatika took into account the pros and cons of previous approaches and developed its own neural network model. The development consisted of selecting the type of network, the number of its layers, creating a spatial structure of neurons, creating conditions for training the network and selecting an adequate training sample. To train the controller, a program was used in which thousands of dynamograms with various defects and conditions were loaded. This network model is implemented in a Wellsim pump controller, which provides sufficient performance, the algorithm successfully detects insufficient filling, gas factor and other faults with an accuracy of 96 %.

Learning From Human Attention for Attribute-Assisted Visual Recognition.

With prior knowledge of seen objects, humans have a remarkable ability to recognize novel objects using shared and distinct local attributes. This is significant for the challenging tasks of zero-shot learning (ZSL) and fine-grained visual classification (FGVC), where the discriminative attributes of objects have played an important role. Inspired by human visual attention, neural networks have widely exploited the attention mechanism to learn the locally discriminative attributes for challenging tasks. Though greatly promoted the development of these fields, existing works mainly focus on learning the region embeddings of different attribute features and neglect the importance of discriminative attribute localization. It is also unclear whether the learned attention truly matches the real human attention. To tackle this problem, this paper proposes to employ real human gaze data for visual recognition networks to learn from human attention. Specifically, we design a unified Attribute Attention Network (A 2 Net) that learns from human attention for both ZSL and FGVC tasks. The overall model consists of an attribute attention branch and a baseline classification network. On top of the image feature maps provided by the baseline classification network, the attribute attention branch employs attribute prototypes to produce attribute attention maps and attribute features. The attribute attention maps are converted to gaze-like attentions to be aligned with real human gaze attention. To guarantee the effectiveness of attribute feature learning, we further align the extracted attribute features with attribute-defined class embeddings. To facilitate learning from human gaze attention for the visual recognition problems, we design a bird classification game to collect real human gaze data using the CUB dataset via an eye-tracker device. Experiments on ZSL and FGVC tasks without/with real human gaze data validate the benefits and accuracy of our proposed model. This work supports the promising benefits of collecting human gaze datasets and automatic gaze estimation algorithms learning from human attention for high-level computer vision tasks.

Few-Shot Learning Sensitive Recognition Method Based on Prototypical Network

Traditional machine learning-based entity extraction methods rely heavily on feature engineering by experts, and the generalization ability of the model is poor. Prototype networks, on the other hand, can effectively use a small amount of labeled data to train models while using category prototypes to enhance the generalization ability of the models. Therefore, this paper proposes a prototype network-based named entity recognition (NER) method, namely the FSPN-NER model, to solve the problem of difficult recognition of sensitive data in data-sparse text. The model utilizes the positional coding model (PCM) to pre-train the data and perform feature extraction, then computes the prototype vectors to achieve entity matching, and finally introduces a boundary detection module to enhance the performance of the prototype network in the named entity recognition task. The model in this paper is compared with LSTM, BiLSTM, CRF, Transformer and their combination models, and the experimental results on the test dataset show that the model outperforms the comparative models with an accuracy of 84.8%, a recall of 85.8% and an F1 value of 0.853.

Phasor-Based Myoelectric Synergy Features: A Fast Hand-Crafted Feature Extraction Scheme for Boosting Performance in Gait Phase Recognition.

Gait phase recognition systems based on surface electromyographic signals (EMGs) are crucial for developing advanced myoelectric control schemes that enhance the interaction between humans and lower limb assistive devices. However, machine learning models used in this context, such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), typically experience performance degradation when modeling the gait cycle with more than just stance and swing phases. This study introduces a generalized phasor-based feature extraction approach (PHASOR) that captures spatial myoelectric features to improve the performance of LDA and SVM in gait phase recognition. A publicly available dataset of 40 subjects was used to evaluate PHASOR against state-of-the-art feature sets in a five-phase gait recognition problem. Additionally, fully data-driven deep learning architectures, such as Rocket and Mini-Rocket, were included for comparison. The separability index (SI) and mean semi-principal axis (MSA) analyses showed mean SI and MSA metrics of 7.7 and 0.5, respectively, indicating the proposed approach's ability to effectively decode gait phases through EMG activity. The SVM classifier demonstrated the highest accuracy of 82% using a five-fold leave-one-trial-out testing approach, outperforming Rocket and Mini-Rocket. This study confirms that in gait phase recognition based on EMG signals, novel and efficient muscle synergy information feature extraction schemes, such as PHASOR, can compete with deep learning approaches that require greater processing time for feature extraction and classification.

An open-set recognition method for ship radiated noise signal based on graph convolutional neural network prototype learning

The underwater acoustic perception system often undertakes multi-class ship recognition tasks. As the underwater acoustic recognition environment becomes increasingly complex, underwater acoustic perception systems often face various interference, such as unknown ships radiated noise signals and decoy signals. This poses higher requirements on the robustness and recognition capabilities of underwater acoustic target recognition methods. In this paper, we transform the problem of underwater acoustic target recognition in this scenario into an open-set recognition problem. We design a deep learning model based on graph convolutional neural networks, propose a graph embedding method for time-domain ships radiated noise signals, and propose a fully parameterized prototype learning framework. We simulate decoy signals in real sea areas, and all the data used in the experiments are actual collected data. The fully parameterized prototype learning framework based on a data-driven approach can not only effectively resist interference from unknown ship-radiated noise signals and decoy signals, but also accurately identify multi-class target ship-radiated noise signals. Ultimately, our method achieves end-to-end open-set recognition of ship-radiated noise signals.

Dual-Path Neural Network based on Deep Features and Transfer Learning for Bearing Fault Diagnosis

The safe operation of mechanical equipment is a basic requirement in the industrial manufacturing process. As an important component of mechanical equipment, rolling bearings are prone to unforeseen failures due to long-term operation under complex conditions. The occurrence of failures, no matter how big or small, will cause economic losses. Therefore, reliable diagnosis of rolling bearings is crucial. Aiming at the problem of insufficient feature recognition of convolutional neural networks under strong noise background, a deep feature extraction network integrating multiscale convolutional neural network (MSCNN) and bidirectional gated recurrent unit (BiGRU) is proposed. MSCNN and BiGRU are used to extract multiscale features and temporal features from noisy vibration signals respectively, and different weights are assigned to the fused features through the attention mechanism module to achieve important feature selection. Furthermore, in order to solve the problem of different feature distributions between the source domain and the target domain under variable working conditions, transfer learning is introduced in the proposed deep feature extraction network. The difference in feature distribution between the source domain and the target domain is measured by a multi-level distance formula, and the measurement result is added to the loss function. The back propagation of the loss is used to achieve the alignment of feature distribution between the source domain and the target domain. Finally, the model uses the SoftMax function as a classifier for rolling bearing fault diagnosis. Experimental comparison and analysis show that the proposed model has good migration ability and achieves a higher fault identification accuracy.

Recognition and quantification of apparent damage to concrete structure based on computer vision

To solve the problems of poor recognition of apparent concrete damage and the difficulty of efficient quantitative characterization of the damage parameters, this study proposes a damage detection method that integrates the target localization algorithm and the quantitative characterization algorithm of the damage based on computer vision. This paper proposes a YOLO v5-RS network combining Res2Net and SimAM to solve the problem of indistinctive apparent damage feature. The damage is segmented by image processing, and the crack and crush damage quantification method are proposed. The results show that compared with YOLO v5, the mAP and F1 of YOLO V5-RS are improved by 8.4% and 0.07, respectively, which indicates that the recognition of apparent structural damage has high robustness. To verify the recognition method’s generalization ability and the characterization method’s accuracy, four cases of different scale are introduced in this paper.

The interface between authoritarian innovations and labour: Implications for the Indian workforce

On assuming office in 2014, India's BJP-led government initiated an ambitious plan to facilitate the ease of doing business, aiming to make India an attractive investment destination. Interview data from 20 trade union leaders and an expert and published data from ILO, government and trade union documents and newspaper archives reveal that, to advance this neoliberal agenda, the government did not use direct and obvious repressive tactics as was the case during the 1976 Emergency, but rather, a combination of discourse, manipulation of democratic institutions like the Parliament and a strategy for disengaging and disempowering the unions that oppose reforms. The new Labour Codes provide a facade for tackling the perennial problem of union recognition and collective bargaining that has plagued Indian industrial relations, but in their implementation, these Codes are likely to weaken unions and erode working conditions. The government's practices attempt to obscure precariousness and silence civil society organisations by imposing unprecedented restrictions on them and disengaging with them. Today, more than ever before, employment in India tends towards informality. Rather than strengthening unions, the government has created fissures in the labour movement by using the unions affiliated with it to manufacture a democratic debate on various pertinent issues, like the Labour Codes.

Non-cooperative target recognition and relative motion estimation with inertial measurement unit assistance

This study investigated the problems of non-cooperative target recognition and relative motion estimation during spacecraft rendezvous maneuvers. A structure integrating an Inertial Measurement Unit (IMU) and a visual camera was presented. The angular velocity output of the IMU was used to calculate the motion trajectories of star points in multiple image frames, which can highlight the motion of non-cooperative targets with respect to the image background to improve the probability of target recognition. To solve the problem of target misidentification caused by new star points entering the field of view, a target-tracking link based on IMU prediction was introduced to track the position of the target in the image. Furthermore, a measurement model was constructed using the line-of-sight vector generated from target recognition, and the relative motion state was estimated using a Huber-based non-linear filter. Semi-physical and numerical simulations were performed to evaluate the effectiveness and efficiency of the proposed method.

Higher Order Polynomial Transformer for Fine-Grained Freezing of Gait Detection.

Freezing of Gait (FoG) is a common symptom of Parkinson's disease (PD), manifesting as a brief, episodic absence, or marked reduction in walking, despite a patient's intention to move. Clinical assessment of FoG events from manual observations by experts is both time-consuming and highly subjective. Therefore, machine learning-based FoG identification methods would be desirable. In this article, we address this task as a fine-grained human action recognition problem based on vision inputs. A novel deep learning architecture, namely, higher order polynomial transformer (HP-Transformer), is proposed to incorporate pose and appearance feature sequences to formulate fine-grained FoG patterns. In particular, a higher order self-attention mechanism is proposed based on higher order polynomials. To this end, linear, bilinear, and trilinear transformers are formulated in pursuit of discriminative fine-grained representations. These representations are treated as multiple streams and further fused by a cross-order fusion strategy for FoG detection. Comprehensive experiments on a large in-house dataset collected during clinical assessments demonstrate the effectiveness of the proposed method, and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.92 is achieved for detecting FoG.

HybAVPnet: A Novel Hybrid Network Architecture for Antiviral Peptides Prediction.

Viruses pose a great threat to human production and life, thus the research and development of antiviral drugs is urgently needed. Antiviral peptides play an important role in drug design and development. Compared with the time-consuming and laborious wet chemical experiment methods, it is critical to use computational methods to predict antiviral peptides accurately and rapidly. However, due to limited data, accurate prediction of antiviral peptides is still challenging and extracting effective feature representations from sequences is crucial for creating accurate models. This study introduces a novel two-step approach, named HybAVPnet, to predict antiviral peptides with a hybrid network architecture based on neural networks and traditional machine learning methods. We adopted a stacking-like structure to capture both the long-term dependencies and local evolution information to achieve a comprehensive and diverse prediction using the predicted labels and probabilities. Using an ensemble technique with the different kinds of features can reduce the variance without increasing the bias. The experimental result shows HybAVPnet can achieve better and more robust performance compared with the state-of-the-art methods, which makes it useful for the research and development of antiviral drugs. Meanwhile, it can also be extended to other peptide recognition problems because of its generalization ability.

Optimal segmentation of non-linear and non-stationary time series based on fractal dimension and Poincare section and its application in solving EEG-signal

Non-linearity and non-stationarity characteristics in physiological and biological time series limit the reliability of conventional analysis. The main challenge in pattern recognition problems is determining the Optimal-Window-Duration (OWD) for segmenting these time series. Our study presents an innovative algorithm, based on Individual-Optimal-Segmentation (IOS), which integrates chaos theory using fractal dimension, and Poincare section into the estimation of the OWD for segmenting time series with non-linear and non-stationary characteristics. In the logistic map case study, the IOS algorithm proved to be effective in detecting cycles in a range of numerical examples, from period-2 to chaotic behavior. So that its performance was superior to previous approaches, especially when it comes to detecting chaotic behaviors. Furthermore, the combination of the IOS algorithm with the Welch signal processing method shows promise in identifying abnormal Power-Spectral-Density (PSD) curves related to Beta and Gamma rhythms in depression diagnosis scenarios. The generated depression diagnosis system attained an accuracy (%) of 99.07±0.35 (with 2-channel) using the Monte Carlo simulation method. These findings suggest a potentially valuable tool for addressing segmentation challenges in time series analysis, particularly in contexts involving complex, dynamic data. While, it is suggested that future research investigate the computational efficiency and robustness of the IOS algorithm when handling large-scale or real-time data and increase its application in various fields in data science and signal processing. Furthermore, expanding the application range of the IOS algorithm for other pattern recognition problems with physiological or biological data can strengthen the generalizability and practical application of the algorithm.