Small Sample Learning Research Articles

Augmented pre-training-based carbon emission accounting method using electricity data under small-sample condition

IntroductionAccurate and rapid carbon accounting method for the power industry is crucial to support China’s low-carbon transformation. Currently, carbon emission accounting methods are based on slowly updated fuel statistics or expensive monitoring equipment, resulting in high costs and delays in carbon emission estimation. Power data offers high real-time availability, accuracy, and resolution, and exhibits a strong correlation with carbon emissions. These characteristics provide a pathway for achieving rapid and precise annual carbon emission accountings. However, carbon emission data inherently exhibits small sample characteristics, making these methods less effective in small sample conditions and leading to lower accounting accuracy.MethodsTherefore, this paper proposes an augmented pre-training-based “electricity-to-carbon” method under small sample conditions.ResultsThis approach utilizes the correlation between electricity and carbon data as well as the autocorrelation characteristics of carbon emission data to construct a machine learning-based electricity-carbon fitting model for rapid and accurate carbon emission estimation. To address the challenges of small sample learning, this paper introduces an interpolation pre-training method to optimize the model’s hyperparameters and conserve samples for model training, thereby improving the model’s generalization and robustness.DiscussionCase studies on a real dataset verifies the effectiveness of the proposed method. The findings of this study can promote the development of carbon measurement technology and facilitate the low-carbon transition of developing countries.

Design and Research on Identification of Typical Tea Plant Diseases Using Small Sample Learning

Tea plants are susceptible to diseases during their growth. These diseases seriously affect the yield and quality of tea. The effective prevention and control of diseases requires accurate identification of diseases. With the development of artificial intelligence and computer vision, automatic recognition of plant diseases using image features has become feasible. As the support vector machine (SVM) is suitable for high dimension, high noise, and small sample learning, this paper uses the support vector machine learning method to realize the segmentation of disease spots of diseased tea plants. An improved Conditional Deep Convolutional Generation Adversarial Network with Gradient Penalty (C-DCGAN-GP) was used to expand the segmentation of tea plant spots. Finally, the Visual Geometry Group 16 (VGG16) deep learning classification network was trained by the expanded tea lesion images to realize tea disease recognition.

A Fault Diagnosis Method for Pumped Storage Unit Stator Based on Improved STFT-SVDD Hybrid Algorithm

Stator faults are one of the common issues in pumped storage generators, significantly impacting their performance and safety. To ensure the safe and stable operation of pumped storage generators, a stator fault diagnosis method based on an improved short-time Fourier transform (STFT)-support vector data description (SVDD) hybrid algorithm is proposed. This method establishes a fault model for inter-turn short circuits in the stator windings of pumped storage generators and analyzes the electrical and magnetic states associated with such faults. Based on the three-phase current signals observed during an inter-turn short circuit fault in the stator windings, the three-phase currents are first converted into two-phase currents using the principle of equal magnetic potential. Then, the STFT is applied to transform the time-domain signals of the stator’s two-phase currents into frequency-domain signals, and the resulting fault current spectrum is input into the improved SVDD network for processing. This ultimately outputs the diagnosis result for inter-turn short circuit faults in the stator windings of the pumped storage generator. Experimental results demonstrate that this method can effectively distinguish between normal and faulty states in pumped storage generators, enabling the diagnosis of inter-turn short circuit faults in stator windings with low cross-entropy loss. Through analysis, under small data sample conditions, the accuracy of the proposed method in this paper can be improved by up to 7.2%. In the presence of strong noise interference, the fault diagnosis accuracy of the proposed method remains above 90%, and compared to conventional methods, the fault diagnosis accuracy can be improved by up to 6.9%. This demonstrates that the proposed method possesses excellent noise robustness and small sample learning ability, making it effective in complex, dynamic, and noisy environments.

Current computational tools for protein lysine acylation site prediction.

As a main subtype of post-translational modification (PTM), protein lysine acylations (PLAs) play crucial roles in regulating diverse functions of proteins. With recent advancements in proteomics technology, the identification of PTM is becoming a data-rich field. A large amount of experimentally verified data is urgently required to be translated into valuable biological insights. With computational approaches, PLA can be accurately detected across the whole proteome, even for organisms with small-scale datasets. Herein, a comprehensive summary of 166 in silico PLA prediction methods is presented, including a single type of PLA site and multiple types of PLA sites. This recapitulation covers important aspects that are critical for the development of a robust predictor, including data collection and preparation, sample selection, feature representation, classification algorithm design, model evaluation, and method availability. Notably, we discuss the application of protein language models and transfer learning to solve the small-sample learning issue. We also highlight the prediction methods developed for functionally relevant PLA sites and species/substrate/cell-type-specific PLA sites. In conclusion, this systematic review could potentially facilitate the development of novel PLA predictors and offer useful insights to researchers from various disciplines.

Online multi-scenario impedance spectra generation for batteries based on small-sample learning

Online multi-scenario impedance spectra generation for batteries based on small-sample learning

Unlocking freeform structured surface denoising with small sample learning: Enhancing performance via physics-informed loss and detail-driven data augmentation

Denoising plays a vital role in freeform structured surface metrology. Traditional techniques, such as Gaussian and partial differential equation-based diffusion filters, often involve a time-consuming calibration process, particularly for complex surfaces. The main challenge lies in automating the denoising operation while accurately preserving features for varied surface textures. To address this challenge, an automatic approach PI-DnCNN based on small sample learning is presented in this paper. Denoising convolutional neural network (DnCNN) is employed as the basic architecture of this approach, due to its effectiveness in tackling mix-level Gaussian noise and adapting to small training datasets. Acknowledging the constraints of limited datasets, a novel physics-informed denoising loss function marrying filtering techniques is proposed to improve model performance. Additionally, a hybrid data augmentation strategy is developed to enhance the recognition of complex components. The paper also reports a set of experiments to demonstrate the presented approach in terms of performance over conventional techniques, enhancements with limited sample sizes, and applicability in general image denoising. The experiment results suggest that the presented approach consistently achieves higher average scores compared to traditional filters and emerges superior compared to the conventional DnCNN loss across different dataset sizes. In addition, the proposed loss also shows effectiveness in general image denoising, which suggests the robustness and universality of the approach.

Virtual Power Plant Transaction Management Using Small Sample Learning Through Cloud Computing Based Noise Reduction by Machine Learning

Virtual Power Plant Transaction Management Using Small Sample Learning Through Cloud Computing Based Noise Reduction by Machine Learning

Research on abnormal diagnosis model of electric power measurement based on small sample learning

Research on abnormal diagnosis model of electric power measurement based on small sample learning

Simultaneous Determination of Four Catechins in Black Tea via NIR Spectroscopy and Feature Wavelength Selection: A Novel Approach.

As a non-destructive, fast, and cost-effective technique, near-infrared (NIR) spectroscopy has been widely used to determine the content of bioactive components in tea. However, due to the similar chemical structures of various catechins in black tea, the NIR spectra of black tea severely overlap in certain bands, causing nonlinear relationships and reducing analytical accuracy. In addition, the number of NIR spectral wavelengths is much larger than that of the modeled samples, and the small-sample learning problem is rather typical. These issues make the use of NIRS to simultaneously determine black tea catechins challenging. To address the above problems, this study innovatively proposed a wavelength selection algorithm based on feature interval combination sensitivity segmentation (FIC-SS). This algorithm extracts wavelengths at both coarse-grained and fine-grained levels, achieving higher accuracy and stability in feature wavelength extraction. On this basis, the study built four simultaneous prediction models for catechins based on extreme learning machines (ELMs), utilizing their powerful nonlinear learning ability and simple model structure to achieve simultaneous and accurate prediction of catechins. The experimental results showed that for the full spectrum, the ELM model has better prediction performance than the partial least squares model for epicatechin (EC), epicatechin gallate (ECG), epigallocatechin (EGC), and epigallocatechin gallate (EGCG). For the feature wavelengths, our proposed FIC-SS-ELM model enjoys higher prediction performance than ELM models based on other wavelength selection algorithms; it can simultaneously and accurately predict the content of EC (Rp2 = 0.91, RMSEP = 0.019), ECG (Rp2 = 0.96, RMSEP = 0.11), EGC (Rp2 = 0.97, RMSEP = 0.15), and EGCG (Rp2 = 0.97, RMSEP = 0.35) in black tea. The results of this study provide a new method for the quantitative determination of the bioactive components of black tea.

A kind of multi-dot ensemble regression AI detector for lubricating oil additive content based on lambert-beer law

In this work, we propose a Multi-dot Ensemble Regression AI detector (MER) based on the Lambert-Beer law. We pre-trained a model using the infrared spectral data of target additives collected in advance to detect the target additives in unknown oil samples. The algorithm's feasibility was validated by assessing the content of additives in a series of simulated commercial oil samples that were not part of the training set. We established models for three common lubricating oil additives (anti-friction, anti-wear, and antioxidant agents), demonstrating their effectiveness in oil sample detection. Additionally, by comparing with other algorithms, we established the superiority of MER in small-sample learning scenarios.

Contrasting YOLOv7, SSD, and DETR on Insulator Identification under Small-sample Learning

Background:: Daily inspections of insulators are necessary because they are indispensable components for power transmission lines. Using deep learning to monitor insulators is a newly developed method. However, most deep learning-based detection methods rely on a large training sample set, which consumes computing resources and increases the workload of sample labeling. The selection of learning models to monitor insulators becomes problematic. Objective:: Through comparative analysis, a model suitable for small-sample insulator learning is found to provide a reference for the research and application of insulator detection. Methods:: This paper compares some of the latest deep learning models, YOLOv7, SSD, and DETR, for insulator detection based on small-sample learning. The small sample here means that the number of samples and their proportion to the total sample are relatively small. Two public insulator image sets, InsulatorDataSet with 600 insulator images and Transmission-line-pictures (TLP) with 1230 insulator images in the natural background are selected to test the performance of these models. Results:: Tests on two public insulator image sets, InsulatorDataSet and TLP, show that the recognition rates of YOLOv7, DETR, and SSD are arranged from high to low. The DETR and the YOLOv7 have stable performance, while the SSD lacks stable performance in terms of the learning time and recognition rate. Conclusion:: The in-domain and cross-domain scenario tests show that YOLOv7 is more suitable for insulator detection under small-sample conditions among the three models.

SLKIR: A framework for extracting key information from air traffic control instructions Using small sample learning

In air traffic control (ATC), Key Information Recognition (KIR) of ATC instructions plays a pivotal role in automation. The field's specialized nature has led to a scarcity of related research and a gap with the industry's cutting-edge developments. Addressing this, an innovative end-to-end deep learning framework, Small Sample Learning for Key Information Recognition (SLKIR), is introduced for enhancing KIR in ATC instructions. SLKIR incorporates a novel Multi-Head Local Lexical Association Attention (MHLA) mechanism, specifically designed to enhance accuracy in identifying boundary words of key information by capturing their latent representations. Furthermore, the framework includes a task focused on prompt, aiming to bolster the semantic comprehension of ATC instructions within the core network. To overcome the challenges posed by category imbalance in boundary word and prompt discrimination tasks, tailored loss function optimization strategies are implemented, effectively expediting the learning process and boosting recognition accuracy. The framework's efficacy and adaptability are demonstrated through experiments on two distinct ATC instruction datasets. Notably, SLKIR outperforms the leading baseline model, W2NER, achieving a 3.65% increase in F1 score on the commercial flight dataset and a 12.8% increase on the training flight dataset. This study is the first of its kind to apply small-sample learning in KIR for ATC and the source code of SLKIR will be available at: https://github.com/PANPANKK/ATC_KIR.

Multi-source domain transfer learning with small sample learning for thermal runaway diagnosis of lithium-ion battery

Data-driven thermal runaway diagnosis based on small amounts of thermal runaway data often struggles to produce satisfactory accuracy. However, in actual application scenarios, obtaining real thermal runaway data has a high cost. To this end, we propose a diagnostic method for multi-source domain transfer learning with few-shot learning (MDTL-FSL), which combines the ideas of small sample learning and adversarial learning. Use multiple different but related thermal runaway case data to obtain common diagnostic knowledge to achieve thermal runaway diagnosis. First of all, in order to avoid negative migration of the algorithm model caused by large differences in data distribution between multi-source domains, a data distribution difference measurement method under segmented pressure differences is proposed. This measurement method is simple and effective from multi-source domains. Select the source domain with a small difference in data distribution from the target domain. Secondly, the adversarial learning idea is integrated into multi-source domain transfer learning to learn temporal invariant features. Then, due to the small number of samples in each source domain in the multi-source domain under the thermal runaway scenario, a source domain reorganization mechanism was designed to find the decision boundary based on meta-learning ideas to achieve small-sample learning in the multi-source domain. Finally, we used cells produced by different battery manufacturers to trigger thermal runaway. By comparison and verification with other data-driven algorithms, the results show that the MDTL-FSL model proposed in this article has higher accuracy. At the same time, we use batteries of different types and capacities to trigger thermal runaway under different working conditions. The MDTL-FSL algorithm can issue early warnings before thermal runaway occurs, thereby effectively ensuring the safe operation of the energy storage system.

MAML–SGD: a reliable airline rescheduling algorithm for small-sample learning based on MAML and SGD

MAML–SGD: a reliable airline rescheduling algorithm for small-sample learning based on MAML and SGD

An imbalanced small sample slab defect recognition method based on image generation

The surface quality of slabs has a profound impact on the subsequent performance and quality of steel. Accurate detection and classification of surface defects are crucial for improving steel quality. However, online visual inspection in the steel industry faces challenges such as sparse data, unclear features, sample imbalances, and impeding the application of deep learning in slab defect detection. To address these challenges, this paper introduces a novel approach utilizing the Slab Defect Generation (SDG) network to generate additional images by training on imbalanced small samples of slab defects, thereby constructing a comprehensive defect database. This methodology significantly enhances the efficiency and accuracy of deep learning in slab defect detection. Furthermore, an improved loss function is proposed specifically for the You Only Look Once version 5 (YOLOv5) model to augment the training of challenging samples. Experimental validation confirms the superiority of our method in terms of both image generation quality and defect-recognition compared to State-Of-The-Art (SOTA) models. The accuracy achieved by our approach is 98.6 %, outperforming the second-ranking model with an accuracy of 90.1 %.Index Terms—Data Enhancement, Deep Learning, Defect Recognition, Machine Vision, Neural Networks, Small sample learning.

An enhanced automated machine learning model for optimizing cycle-to-cycle variation in hydrogen-enriched methanol engines

Renewable methanol and hydrogen have emerged as great potential alternative fuels for internal combustion engines in recent research. Hydrogen exhibits the ability to mitigate cycle-to-cycle variations in methanol engines thanks to its rapid combustion rate. Furthermore, the integration of machine learning with genetic algorithms provides a solution to achieve efficient and clean combustion in hydrogen-enriched methanol engines. Nevertheless, this approach is constrained due to the limited predictive accuracy in small-sample learning. This study aims at introducing an enhanced model based on the automated machine learning framework, and provide a comparative analysis of the enhanced model and computational fluid dynamics simulations in terms of multi-objective optimization performance and computational time. Additionally, this study further considered the effect of engine cycle-to-cycle variations on performance, ultimately attaining optimal operating parameters for stable combustion. The results indicate that datasets actively created by genetic algorithms are more effective than those generated through Latin hypercube sampling. The introduction of a classification model for the identification of misfires has enhanced the efficiency of dataset utilization. Through feature construction, the automated machine learning model demonstrates improvements in R-square and mean-squared error for all parameters on the test dataset. Furthermore, by employing a larger overall population size, the automated machine learning model has not only achieved a higher-quality Pareto fronts compared to the computational fluid dynamics method but has also significantly reduced computation time, particularly upon introducing additional engine cycle-to-cycle variations constraints.

Research on Entity and Relationship Extraction with Small Training Samples for Cotton Pests and Diseases

The extraction of entities and relationships is a crucial task in the field of natural language processing (NLP). However, existing models for this task often rely heavily on a substantial amount of labeled data, which not only consumes time and labor but also hinders the development of downstream tasks. Therefore, with a focus on enhancing the model’s ability to learn from small samples, this paper proposes an entity and relationship extraction method based on the Universal Information Extraction (UIE) model. The core of the approach is the design of a specialized prompt template and schema on cotton pests and diseases as one of the main inputs to the UIE, which, under its guided fine-tuning, enables the model to subdivide the entity and relationship in the corpus. As a result, the UIE-base model achieves an accuracy of 86.5% with only 40 labeled training samples, which really solves the problem of the existing models that require a large amount of manually labeled training data for knowledge extraction. To verify the generalization ability of the model in this paper, experiments are designed to compare the model with four classical models, such as the Bert-BiLSTM-CRF. The experimental results show that the F1 value on the self-built cotton data set is 1.4% higher than that of the Bert-BiLSTM-CRF model, and the F1 value on the public data set is 2.5% higher than that of the Bert-BiLSTM-CRF model. Furthermore, experiments are designed to verify that the UIE-base model has the best small-sample learning performance when the number of samples is 40. This paper provides an effective method for small-sample knowledge extraction.

Electrolytic capacitor surface defect detection based on deep convolution neural network

The existing methods for detecting surface defects in electrolytic capacitors are typically based on conventional machine vision, with limited feature extraction capabilities, poor versatility, slow detection speed, and the inability to achieve accurate and real-time defect detection. In this study, a real-time object detection algorithm based on an improved single shot multibox detector (SSD) is proposed to achieve omnidirectional surface defect detection of electrolytic capacitors. First, an electrolytic capacitor surface image acquisition device was established to capture omnidirectional surface images of the capacitors, and an electrolytic capacitor surface defect dataset was created. Next, the visual geometry group (VGG)-16 network structure was replaced with the MobileNetv2 network structure, effectively reducing the model’s parameter count and improving inference speed. Moreover, the Multibox Loss function was replaced with the Focal Loss function to increase the model’s attention to difficult-to-classify samples and improve model accuracy. Additionally, a transfer learning network model was designed to apply the model to electrolytic capacitors of different colors using small sample learning. Finally, the performance of the improved network model was tested on a dataset of electrolytic capacitor surface defects. The experimental results demonstrate that the parameters quantity of improved model is 3.50 M, the mAP value reaches 92.67 %, which is improved by 2.54 %, and the Macro-F1 value reaches 92.15 %, which is 11.32 % higher than that before improvement. Thus, the proposed improved SSD model provides a theoretical basis and technical prerequisites for automated and intelligent surface defect detection in electrolytic capacitors.

State of Health Prediction of Lithium-Ion Batteries Using Combined Machine Learning Model Based on Nonlinear Constraint Optimization

Accurate State of Health (SOH) estimation of battery systems is critical to vehicle operation safety. However, it’s difficult to guarantee the performance of a single model due to the unstable quality of raw data obtained from lithium-ion battery aging and the complexity of operating conditions in actual vehicle operation. Therefore, this paper combines a long short-term memory (LSTM) network with strong temporality, and support vector regression (SVR) with nonlinear mapping and small sample learning. A novel LSTM-SVR combined model with strong input features, less computational burden and multiple advantage combinations is proposed for accurate and robust SOH estimation. The nonlinear constraint optimization is used to assign weights to individual models in terms of minimizing the sum of squared errors of the combined models, which can combine strengths while compensating for weaknesses. Furthermore, voltage, current and temperature change curves during the battery charging were analyzed, and indirect health features (IHFs) with a strong correlation with capacity decline were extracted as model inputs using correlation analysis and principal component analysis (PCA). The NASA dataset was used for validation, and the results show that the LSTM-SVR combined model has good SOH estimation performance, with MAE and RMSE all less than 0.75% and 0.97%.

Research on intelligent constellation map monitoring for fiber optic communication based on small sample learning network

Research on intelligent constellation map monitoring for fiber optic communication based on small sample learning network