Large Number Of Training Samples Research Articles

ArcheType: A Novel Framework for Open-Source Column Type Annotation Using Large Language Models

Existing deep-learning approaches to semantic column type annotation (CTA) have important shortcomings: they rely on semantic types which are fixed at training time; require a large number of training samples per type; incur high run-time inference costs; and their performance can degrade when evaluated on novel datasets, even when types remain constant. Large language models have exhibited strong zero-shot classification performance on a wide range of tasks and in this paper we explore their use for CTA. We introduce ArcheType, a simple, practical method for context sampling, prompt serialization, model querying, and label remapping, which enables large language models to solve CTA problems in a fully zero-shot manner. We ablate each component of our method separately, and establish that improvements to context sampling and label remapping provide the most consistent gains. ArcheType establishes a new state-of-the-art performance on zero-shot CTA benchmarks (including three new domain-specific benchmarks which we release along with this paper), and when used in conjunction with classical CTA techniques, it outperforms a SOTA DoDuo model on the fine-tuned SOTAB benchmark.

An iterative and subsequent proximation method to map historical crop information with satellite images

Mapping agricultural information such as cropping area and type is of great significance for land use and food security and a common method to retrieve such information is satellite imagery classification. The current image classification techniques require a statistically large number of training samples to obtain representative spectral signatures, ideally collected during the satellite overpass time/date. Although this prerequisite sounds simple and easy in principle, it is extremely challenging and sometimes impossible when classifying historical satellite images, as one simply cannot go back in time to collect training datasets or ground truthing. In this paper, we introduce an iterative and subsequent proximation (ISP) method to circumvent this problem for historical image classifications for historical crop mapping. This method assumes that the same crops grown two years apart have similar spectral properties within the same growing season, with limited variation. This allows the use of the crop information classified in any given year (n) to be used as training samples for the next year (n + 1) or the previous year (n-1). Iteratively repeating n-1, n-2… process leads to the mapping of historical cropping information without a priori ground truthing data. To demonstrate the ISP feasibility, we first used the historical Landsat time-series data to map four major stable crops (rice, maize, soybean, and wheat) in Hailun County, Heilongjiang Province, China, and then further expanded the ISP application to the entire Heilongjiang Province to map cropping areas from 1982 to 2020, using the classification and regression trees (CART) algorithm. The results were validated for those years when actual cropping measurement data were available and further verified with statistical data for other years. The results indicated that the proposed ISP method was appropriate for the historical mapping of four major crops, with a mapping accuracy of approximately 80 % when validated with field data, and correlation coefficients of 0.86, 0.85, 0.91, and 0.94, respectively when compared with historical statistical cropping data. The crop mapping results showed distinct trends of northward expansion in each of the four crops in Heilongjiang Province, which agreed well with previous studies. In conclusion, the ISP method is quick, easy, and convenient for historical crop mapping, which is important in understanding the agricultural production history.

Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning

Efficient collaboration in the centralized training with decentralized execution (CTDE) paradigm remains a challenge in cooperative multi-agent systems. We identify divergent action tendencies among agents as a significant obstacle to CTDE's training efficiency, requiring a large number of training samples to achieve a unified consensus on agents' policies. This divergence stems from the lack of adequate team consensus-related guidance signals during credit assignment in CTDE. To address this, we propose Intrinsic Action Tendency Consistency, a novel approach for cooperative multi-agent reinforcement learning. It integrates intrinsic rewards, obtained through an action model, into a reward-additive CTDE (RA-CTDE) framework. We formulate an action model that enables surrounding agents to predict the central agent's action tendency. Leveraging these predictions, we compute a cooperative intrinsic reward that encourages agents to align their actions with their neighbors' predictions. We establish the equivalence between RA-CTDE and CTDE through theoretical analyses, demonstrating that CTDE's training process can be achieved using N individual targets. Building on this insight, we introduce a novel method to combine intrinsic rewards and RA-CTDE. Extensive experiments on challenging tasks in SMAC, MPE, and GRF benchmarks showcase the improved performance of our method.

An RGB‐D object detection model with high‐generalization ability applied to tea harvesting robot for outdoor cross‐variety tea shoots detection

AbstractDetecting tea shoots is the first and most crucial step in achieving intelligent tea harvesting. However, when faced with thousands of tea varieties, establishing a high‐quality and comprehensive database comes with significant costs. Therefore, it has become an urgent challenge to improve the model's generalization ability and train it with minimal samples to develop a model capable of achieving optimal detection performance in various environments and tea varieties. This paper introduces a model named You Only See Tea (YOST) which utilizes depth maps to enhance model's generalization ability. It is applied to detect tea shoots in complex environments and to perform cross‐variety tea shoots detection. Our approach differs from common data augmentation strategies aimed at enhancing model generalization by diversifying the data set. Instead, we enhance the model's learning capability by strategically amplifying its attention towards core target features while simultaneously reducing attention towards noncore features. The proposed module YOST is developed upon the You Only Look Once version 7 (YOLOv7) model, utilizing two shared‐weight backbone networks to process both RGB and depth images. Then further integrate two modalities with feature layers at the same scale into our designed Ultra‐attention Fusion and Activation Module. By utilizing this approach, the model can proficiently detect targets by capturing core features, even when encountering complex environments or unfamiliar tea leaf varieties. The experimental results indicate that YOST displayed faster and more consistent convergence compared with YOLOv7 in training. Additionally, YOST demonstrated a 6.58% enhancement in AP50 for detecting tea shoots in complex environments. Moreover, when faced with a cross‐variety tea shoots detection task involving multiple unfamiliar varieties, YOST showcased impressive generalization abilities, achieving a significant maximum AP50 improvement of 33.31% compared with YOLOv7. These findings establish its superior performance. Our research departs from the heavy reliance on high‐generalization models on a large number of training samples, making it easier to train small‐scale, high‐generalization models. This approach significantly alleviates the pressure associated with data collection and model training.

A series fault arc detection method based on denoising autoencoder and deep residual network

Given the problem that the existing series arc fault identification methods use existing features such as the time-frequency domain of the current signal as the basis for identification, resulting in relatively limited arc detection solutions, and that the methods of directly extracting current signal features using deep learning algorithms have insufficient feature extraction, a new series arc fault detection method based on denoising autoencoder (DAE) and deep residual network (ResNet) is proposed. First, a large number of training samples are obtained through sliding window and data normalization methods, and then high-dimensional abstract feature data are obtained from the fault and normal samples collected in the experiment through denoising autoencoders, converted into grayscale images, and processed in pseudo-color. The single-channel grayscale images are mapped into three-channel color values, and finally, the three-channel values are input into the constructed deep residual network for deep learning training. In the 152 super high-level ResNet, the arc fault recognition rate can reach 99.7%. For loads that have not participated in ResNet network training, the recognition rate can also reach 97.6%.

An edge-aware graph autoencoder trained on scale-imbalanced data for traveling salesman problems

In recent years, there has been a notable surge in research on machine learning techniques for combinatorial optimization. It has been shown that learning-based methods outperform traditional heuristics and mathematical solvers on the Traveling Salesman Problem (TSP) in terms of both performance and computational efficiency. However, most learning-based TSP solvers are primarily designed for fixed-scale TSP instances, and also require a large number of training samples to achieve optimal performance. To fill this gap, this work proposes a data-driven graph representation learning method for solving TSPs with various numbers of cities. Specifically, we formulate the TSP as a link prediction task and propose an edge-aware graph autoencoder (EdgeGAE) model that can solve TSPs by learning from various-scale samples with an imbalanced distribution. A residual gated encoder is trained to learn latent edge embeddings, followed by an edge-centered decoder to output link predictions in an end-to-end manner. Furthermore, we introduce an active sampling strategy into the training process to improve the model’s generalization capability in large-scale scenarios. To investigate the model’s practical applicability, we generate a scale-imbalanced dataset comprising 50,000 TSP instances ranging from 50 to 500 cities. The experimental results demonstrate that the proposed edge-aware graph autoencoder model achieves a highly competitive performance among state-of-the-art graph learning-based approaches in solving TSPs with various scales, implying its remarkable potential in dealing with practical optimization challenges.

A multi-view ensemble model based on semi-supervised feature learning for small sample classification of PolSAR images

ABSTRACT Classification with a few samples of training set has been a long-standing issue in the field of polarimetric synthetic aperture radar (PolSAR) image analysis and processing. In fact, one of the most important challenges of the PolSAR image classification task is the number of labelled samples. In essence, training network by utilizing just few numbers of training samples cannot be led to the reliable result since the neural network is so sensitive to the number of training samples. In addition, in the real PolSAR image classification task, the huge number of training samples is not accessible. On the other hand, classification performance using just small number of labelled samples is not an accurate result. So, in this paper, aiming at the small number of training samples of the PolSAR image classification task, a novel ensemble self-supervised feature-learning (ESSFL) model is designed. The designed ESSFL can automatically extract PolSAR features conducive to PolSAR image classification with a small number of training samples. In addition, it can significantly decrease the dependence of neural network algorithms on large labelled samples of training set. First, to utilize the spatial–polarimetric features of PolSAR data perfectly, the EfficientNet-B0 is presented and utilized as the main section of the deep learning (DL) model to extract DL features of PolSAR data. Then, using an optimization function that constrains the cross-correlation matrix of various distortions of each sample to the identity matrix, the designed deep learning model can obtain the effective features of homogeneous samples gathering together and heterogeneous samples separating from each other in a self-supervised manner. Moreover, two ensemble learning (EL) models, feature-level and view-level ensemble, are proposed to increase the feature extraction capability and classification result by jointly using spatial features at different scales and polarimetric information at different bands. Finally, the stack of the obtained features and the main polarimetric information of PolSAR data can be input into classifier for the classification of PolSAR data. In this paper we use two different classifiers, the first one is the Random Forest (RF) classifier and the second one is the Support Vector Machine (SVM) classifier. The advantages of SVM include that it can be used to avoid the difficulties of using linear functions in the high-dimensional feature space, and the optimization problem is transformed into dual convex quadratic programs that are so usable for an actual image classification task. In addition, among all the available classification methods, random forests provide one of the highest accuracies. The random forest technique can also handle big data with numerous variables running into thousands. In fact, it can automatically balance data sets when a class is more infrequent than other classes in the data that is so important for a real PolSAR image classification task. Experimental results on three well-known PolSAR data sets illustrate that the designed ESSFL can extract more discriminant features using the designed deep learning model. In the end, the experiments prove that the designed ESSFL has a significant classification performance compared with different deep learning models in the case of small number of training samples, and also it can achieve a better result in the case of large number of training samples by comparison with the most of the deep learning models.

Few-shot detection of surface roughness of workpieces processed by different machining techniques

The traditional deep learning method for detecting workpiece surface roughness relies heavily on a large number of training samples. Also, when detecting the surface roughness of workpieces processed by different machining techniques, it requires a large number of samples of that workpiece to rebuild the model. To address these problems, this paper proposes a few-sample visual detection method for the surface roughness of workpieces processed by different techniques. This method first trains a base model using a relatively large amount of samples from one machining technique, then fine-tunes the model using small amounts of samples from workpieces of different techniques. By introducing contrastive proposal encoding into Faster R-CNN, the model’s ability to learn surface features from small amounts of workpiece samples is enhanced, thus improving the detection accuracy of surface roughness of workpieces processed by different techniques. Experiments show that this method reduces the model’s dependence on training samples and the cost of data preparation. It also demonstrates higher accuracy in surface roughness detection tasks of workpieces processed by different techniques, providing a new approach and insights for few-sample surface roughness detection.

A Novel Computational Imaging Algorithm for Electrical Capacitance Tomography

High-precision images enable electrical capacitance tomography (ECT) to obtain more reliable measurement results, meaning that the reconstruction algorithm is particularly important. Some excellent numerical algorithms have successfully solved the inverse problem for ECT imaging, but their imaging quality is relatively low. To solve this problem, this paper proposes a new reconstruction algorithm based on regularized extreme learning machines (RELMs). The implementation of the algorithm is mainly divided into two steps: (1) according to a large number of training samples, the RELM model can be obtained by the iterative split Bregman (ISB) algorithm, which can describe the mapping relationship between the capacitance correlation coefficient and the imaging target well, and (2) the capacitance correlation coefficient is calculated, which is then used as input to the RELM model to predict the final imaging. Both simulation and experimental results show that the RELM algorithm achieves greater improvement in imaging quality and robustness, and provides new development ideas for the ECT.

Optimization of transfer learning based on source sample selection in Euclidean space for P300-based brain-computer interfaces.

Event-related potentials (ERPs), such as P300, are widely utilized for non-invasive monitoring of brain activity in brain-computer interfaces (BCIs) via electroencephalogram (EEG). However, the non-stationary nature of EEG signals and different data distributions among subjects create significant challenges for implementing real-time P300-based BCIs. This requires time-consuming calibration and a large number of training samples. To address these challenges, this study proposes a transfer learning-based approach that uses a convolutional neural network for high-level feature extraction, followed by Euclidean space data alignment to ensure similar distributions of extracted features. Furthermore, a source selection technique based on the Euclidean distance metric was applied to measure the distance between each source feature sample and a reference point from the target domain. The samples with the lowest distance were then chosen to increase the similarity between source and target datasets. Finally, the transferred features are applied to a discriminative restricted Boltzmann machine classifier for P300 detection. The proposed method was evaluated on the state-of-the-art BCI Competition III dataset II and rapid serial visual presentation dataset. The results demonstrate that the proposed technique achieves an average accuracy of 97% for both online and offline after 15 repetitions, which is comparable to the state-of-the-art methods. Notably, the proposed approach requires <½ of the training samples needed by previous studies. Therefore, this technique offers an efficient solution for developing ERP-based BCIs with robust performance against reduced a number of training data.

Essential Number of Principal Components and Nearly Training-Free Model for Spectral Analysis.

Learning-enabled spectroscopic analysis, promising for automated real-time analysis of chemicals, is facing several challenges. Firstly, a typical machine learning model requires a large number of training samples that physical systems can not provide. Secondly, it requires the testing samples to be in range with the training samples, which often is not the case in the real world. Further, a spectroscopy device is limited by its memory size, computing power, and battery capacity. That requires highly efficient learning models for on-site analysis. In this paper, by analyzing multi-gas mixtures and multi-molecule suspensions, we first show that orders of magnitude reduction of data dimension can be achieved as the number of principal components that need to be retained is the same as the independent constituents in the mixture. From this principle, we designed highly compact models in which the essential principal components can be directly extracted from the interrelations between the individual chemical properties and principal components; and only a few training samples are required. Our model can predict the constituent concentrations that have not been seen in the training dataset and provide estimations of measurement noises. This approach can be extended as an effectively standardized method for principle component extraction.

Active Learning for Deep Visual Tracking.

Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these samples directly affect the representational capability of the trained model. However, this approach is restrictive in practice, because manually labeling such a large number of training samples is time-consuming and prohibitively expensive. In this article, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNN model. Under the guidance of active learning, the tracker based on the trained deep CNN model can achieve competitive tracking performance while reducing the labeling cost. More specifically, to ensure the diversity of selected samples, we propose an active learning method based on multiframe collaboration to select those training samples that should be and need to be annotated. Meanwhile, considering the representativeness of these selected samples, we adopt a nearest-neighbor discrimination method based on the average nearest-neighbor distance to screen isolated samples and low-quality samples. Therefore, the training samples' subset selected based on our method requires only a given budget to maintain the diversity and representativeness of the entire sample set. Furthermore, we adopt a Tversky loss to improve the bounding box estimation of our tracker, which can ensure that the tracker achieves more accurate target states. Extensive experimental results confirm that our active-learning-based tracker (ALT) achieves competitive tracking accuracy and speed compared with state-of-the-art trackers on the seven most challenging evaluation benchmarks. Project website: https://sites.google.com/view/altrack/.

Erasing-inpainting-based data augmentation using denoising diffusion probabilistic models with limited samples for generalized surface defect inspection

Surface defect inspection aims to identify defective regions in product surface images to ensure product quality. Existing deep learning methods have developed rapidly on surface defect inspection. However, their excellent performances rely on a large number of training samples, which are hard to acquire in practical industrial scenarios due to the continuous improvements of the production line. To solve this issue, we propose an erasing-inpainting-based data augmentation method using a denoising diffusion probabilistic model (DDPM) with limited samples for generalized surface defect inspection. Our method is based on the idea that a defect image is difficult to recover to its previous state after undergoing a large-scale erasure operation, thus diverse defect images can be generated using different settings in the inpainting model. Specifically, we first train a DDPM model using limited defective images. Then, we erase large-scale parts of an input image to obtain a degraded image and restore the erased areas using the trained DDPM. Finally, the repaired images are further used for updating the DDPM. The main advantage of our method is to generate diverse images by only being trained using limited training samples. On the one hand, our method fundamentally avoids the dimension inconsistency between the sampled noise and the generated image by sampling from a two-dimensional noise map with the same resolution as the output image based on DDPM. On the other hand, the proposed erasing-inpainting operation promotes the recombination of the real features from the training set and the learned features from the trained DDPM to fully use the limited defective samples and the easily obtainable defect-free samples. Extensive experiments demonstrated the effectiveness and advantagesof our model on data augmentation for generalized surface defect inspection.

Rapid mapping of volcanic eruption building damage: A model based on prior knowledge and few-shot fine-tuning

Large-scale volcanic eruptions always inflict severe damage upon facilities and cause significant environmental pollution. Building damage caused by lava flow and volcanic ash coverage can reflect the infrastructure devastation and victim scope within the affected region. The application of machine learning methods for building damage automated identification from remote sensing imagery typically relies on a large number of training samples. However, labeled data scarcity is a common issue in the field of disasters, particularly in volcanic eruptions. To address this, we propose a two-stage building damage quick mapping workflow, which combines a building localization model trained on prior knowledge and a damage classification model fine-tuned on few-shot volcanic eruption-related samples. The classification model utilizes a CNN-based Siamese network for bi-temporal image feature extraction and comparison, with the backbone initialized with pre-trained weights from ImageNet. We conducted building damage classification tasks for single-disaster scenarios and cross-disaster domain scenarios in the eruptions of Mount Semeru, Tonga, and ST. Vincent; the visual damage level of each building was used as ground truth. The results demonstrate that our model can identify building damage efficiently and accurately in different volcanic eruption scenarios, with an over 93% F1-score on the 2-way 20-shot tasks. Furthermore, though building samples from different volcanic eruption regions present cross-domain challenges, our model can adapt to different feature domains by being supplemented with a few samples of another volcanic eruption disaster. Additionally, in the case of Mount Semeru Eruption, we gain insights into the potential of building damage statistics in post-eruption environmental assessments. To further enhance the model robustness on mixed-domain samples and multi-level damage classification tasks, issues including sample bias of certain disaster sources should be addressed.

Rapid learning of bearing signal pattern using CfCs promoted by a self-attention mechanism

Deep learning is helpful for improving the fault recognition ability of bearings, but this kind of model relies on a large number of training samples and computing resources. In this paper, an algorithm termed a closed-form continuous-depth neural network (CfC) assisted by an information compression-interaction (ICI) module and spatial conjunction attention (SCA) module (CfC-ISCA) is proposed. The ICI module extracts the main features of input signals, the SCA module is designed for positioning target features and capturing more useful features, and the CfC module is used to further fuse features and achieve rapid learning of samples. This algorithm can learn bearing fault signal patterns rapidly and has excellent fault identification ability under small sample conditions. Some public datasets are used to validate the model performance. The test results show that the proposed CfC-ISCA algorithm has comprehensive advantages in fault signal recognition, consumption of computing resources and fast learning compared to comparative methods.

Causal Factor Disentanglement for Few-Shot Domain Adaptation in Video Prediction.

An important challenge in machine learning is performing with accuracy when few training samples are available from the target distribution. If a large number of training samples from a related distribution are available, transfer learning can be used to improve the performance. This paper investigates how to do transfer learning more effectively if the source and target distributions are related through a Sparse Mechanism Shift for the application of next-frame prediction. We create Sparse Mechanism Shift-TempoRal Intervened Sequences (SMS-TRIS), a benchmark to evaluate transfer learning for next-frame prediction derived from the TRIS datasets. We then propose to exploit the Sparse Mechanism Shift property of the distribution shift by disentangling the model parameters with regard to the true causal mechanisms underlying the data. We use the Causal Identifiability from TempoRal Intervened Sequences (CITRIS) model to achieve this disentanglement via causal representation learning. We show that encouraging disentanglement with the CITRIS extensions can improve performance, but their effectiveness varies depending on the dataset and backbone used. We find that it is effective only when encouraging disentanglement actually succeeds in increasing disentanglement. We also show that an alternative method designed for domain adaptation does not help, indicating the challenging nature of the SMS-TRIS benchmark.

Blockchain-based biometric identity management

In recent years, face biometrics recognition systems are a wide space of a computer usage which is mostly employed for security purpose. The main purpose of the face biometrics recognition system is to authenticate a user from a given database. Due to the widespread expansion of the surveillance cameras and facial recognition technology, a robust face recognition system required. The recognition system needs to store a large number of training samples in any storage unit, that time hackers can access and control that data. So, Protecting and managing sensitive data is essential object. This requires a technique that preserve the privacy of individuals, maintain data integrity, and prevent information leakage. The storage of biometric templates on centralized servers has been associated with potential privacy risks. To address this issue, we have developed and implemented a proof-of-concept facial biometric identification system that uses a private Blockchain platform and smart contract technology. So, the proposed approach is presented a secure and tamper-proof from data breaches as well as hacks with data availability, by using the Blockchain platform to store face images. This paper aims to utilize Blockchain technology to identify individuals based on their biometric traits, specifically facial recognition system makes it tamper-proof (immutable) ensuring security. The system consists of enrolment and authentication phases. Blockchain technology uses peer-to-peer communication, cryptography, consensus processes, and smart contracts to ensure the security. The proposed approach was tested on two popular datasets: CelebFaces Attributes (CelebA) and large-scale face UTKFace datasets. The experimental results indicate that the system yields highly performance outcomes, as evidenced by the Equal Error Rate (EER) values of 0.05% and 0.07% obtained for the CelebA and UTKFace datasets, respectively. The system was compared to three baseline methods and scored the lowest Equal Error Rate.

Generating Virtual Training Labels for Crop Classification from Fused Sentinel-1 and Sentinel-2 Time Series

Convolutional neural networks (CNNs) have shown results superior to most traditional image understanding approaches in many fields, incl. crop classification from satellite time series images. However, CNNs require a large number of training samples to properly train the network. The process of collecting and labeling such samples using traditional methods can be both, time-consuming and costly. To address this issue and improve classification accuracy, generating virtual training labels (VTL) from existing ones is a promising solution. To this end, this study proposes a novel method for generating VTL based on sub-dividing the training samples of each crop using self-organizing maps (SOM), and then assigning labels to a set of unlabeled pixels based on the distance to these sub-classes. We apply the new method to crop classification from Sentinel images. A three-dimensional (3D) CNN is utilized for extracting features from the fusion of optical and radar time series. The results of the evaluation show that the proposed method is effective in generating VTL, as demonstrated by the achieved overall accuracy (OA) of 95.3% and kappa coefficient (KC) of 94.5%, compared to 91.3% and 89.9% for a solution without VTL. The results suggest that the proposed method has the potential to enhance the classification accuracy of crops using VTL.

Mangrove species discrimination using Modified Spectral Angle Mapper algorithm on hyperspectral imagery: A study at Marine National Park (MNP) Jamnagar, Gulf of Kutch, Gujarat and Lothian Island, Sundarbans, West Bengal

Mangroves are coastal evergreen, salt-tolerant forest ecosystems that play a vital role in biodiversity conservation. Effective mapping and monitoring of mangrove ecosystems are essential for informed management and scientific decision-making. However, the dense and often inaccessible nature of mangrove forests makes traditional field surveys and ground truth collection challenging. Hyperspectral remote sensing offers a valuable solution by enabling species-level discrimination in mangroves through the extraction of vegetation structure and composition from imagery using diverse classification approaches.This study focuses on the discrimination of mangrove species in the mangrove forest areas of Marine National Park (MNP), Jamnagar, Gulf of Kutch, Lothian Island, Sundarbans, West Bengal. The proposed approach utilizes the Modified Spectral Angle Mapper (Modified SAM) algorithm with AVIRIS-NG hyperspectral data. This algorithm addresses the limitations of the traditional Spectral Angle Mapper (SAM) algorithm, which fails to account for the spatial structure and information of mangrove species. Additionally, the proposed algorithm reduces the reliance on a large number of training samples and complex classifiers, which are insufficient for extracting mangrove characteristics due to computational inefficiencies and limited generalization capabilities. By incorporating both spatial and spectral information, the Modified SAM algorithm enhances performance and classification accuracy, even in mixed mangrove pixel regions. This is achieved through the utilization of various distance and similarity measures, including angle change resulting from shape alterations in mangrove spectra, angle change due to the magnitude of mangrove spectra changes, and distance change between two mangrove spectra. These measures facilitate the identification of subtle differences between mangrove spectra.The results demonstrate a significant improvement in classification accuracy compared to the traditional SAM algorithm, particularly in mixed mangrove pixel regions. The achieved overall accuracy (OA) is 93.48% for the Lothian Islands, Sundarbans, West Bengal, and 94.32% for the Marine National Park (MNP), Jamnagar, Gulf of Kutch. The proposed Modified SAM algorithm, in conjunction with AVIRIS-NG hyperspectral data, offers an effective approach for reliable and efficient classification and discrimination of mangrove species. The algorithm’s enhanced performance and classification accuracy have significant implications for mapping, monitoring, and managing mangrove ecosystems, supporting conservation efforts, and facilitating informed decision-making for sustainable mangrove ecosystems.

A New Fourier Q Operator Network Based Reinforcement Learning Method for Continuous Action Space Decision-making in Manufacturing

The problems of continuous action space decision-making are widespread in industrial manufacturing. However, when dealing with these problems, existing reinforcement learning (RL) methods relies on a large number of training samples, which is always unacceptable given the limited availability or expensive nature of data, such as low-volume manufacturing. This paper proposes a new Fourier Q operator network (FQON) based RL method. The input of FQON is the expected state function and its output the Q-value function, and both functions take the action in RL as independent variables. The infinite-dimensional mapping between the function domains is established by a set of parameters that can be used with different discretization, which fixes the mapping complexity regardless of the action space resolution. By taking the advantages of the fast calculation using on Fourier kernel operator, the mapping complexity is highly reduced, and it enables that FQON can realize the decision-making in continuous action space using a small amount of training samples. Taking machining deformation control of an aero-engine casing as a case study, experimental results showed that FQON based RL method can control the deformation well with limited training samples.