Accurate wind power forecasting (WPF) is crucial for integrating renewable energy into power grids and optimizing energy management systems. However, existing forecasting methods often struggle to capture the complex temporal dynamics and nonlinear relationships inherent in wind power data. This paper introduces ASPEN-WIND (Adaptive Spectral and Self-supervised Predictive Network - Wind Integrated Neural Dynamics), a novel deep learning (DL) model for enhanced WPF. ASPEN-WIND combines an adaptive spectral block (ASB), an interactive convolution block (ICB), long short-term memory (LSTM) networks, and self-supervised learning. The ASB employs Fourier analysis to capture multi-scale temporal patterns and adaptively filter noise, while the ICB extracts complex spatial-temporal features. LSTM networks model long-term dependencies, and self-supervised pre-training improves the model’s ability to learn from limited labeled data. We evaluated ASPEN-WIND on multiple real-world wind farm datasets, demonstrating its superior performance compared to traditional and recent DL-based forecasting methods across various time horizons. The results, averaged over multiple runs (e.g., 10 runs with different random seeds), show significant improvements in forecasting accuracy, with average reductions in mean absolute error (MAE) and root mean square error (RMSE) of 5–8% and 8–12%, respectively.

Imbalanced datasets are a significant challenge in real-world scenarios. They lead to models that underperform on underrepresented classes, which is a critical issue in infrastructure inspection. This article introduces the enhanced feature pyramid network (E-FPN), a deep learning model for the semantic segmentation of culverts and sewer pipes within imbalanced datasets. The E-FPN incorporates architectural innovations like sparsely connected blocks and depth-wise separable convolutions to improve feature extraction and handle object variations. To address dataset imbalance, the model employs strategies like class decomposition and data augmentation. Experimental results on the culvert-sewer defects dataset and two benchmark datasets show that the E-FPN outperforms state-of-the-art methods, achieving an average intersection over union (IoU) improvement of 16.2%, 27.2%, and 28.82%, respectively. Additionally, class decomposition and data augmentation together boost the model’s performance by approximately 6.9% IoU. The proposed E-FPN presents a promising solution for enhancing object segmentation in challenging, multiclass real-world datasets, with potential applications extending beyond culvert-sewer defect detection.

Enabling effective learning using only a few presented examples is a crucial but difficult computer vision objective. Few-shot learning have been proposed to address the challenges, and more recently variational inference-based approaches are incorporated to enhance few-shot classification performances. However, the current dominant strategy utilized the Kullback-Leibler (KL) divergences to find the log marginal likelihood of the target class distribution, while neglecting the possibility of other probabilistic comparative measures, as well as the possibility of incorporating attention in the feature extraction stages, which can increase the effectiveness of the few-shot model. To this end, we proposed the HELlinger-Attention Variational Feature Aggregation network (HELA-VFA), which utilized the Hellinger distance along with attention in the encoder to fulfill the aforementioned gaps. We show that our approach enables the derivation of an alternate form of the lower bound commonly presented in prior works, thus making the variational optimization feasible and be trained on the same footing in a given setting. Extensive experiments performed on four benchmarked few-shot classification datasets demonstrated the feasibility and superiority of our approach relative to the State-Of-The-Arts (SOTAs) approaches.

Incorporating deep learning (DL) classification models into unmanned aerial vehicles (UAVs) can significantly augment search-and-rescue operations and disaster management efforts. In such critical situations, the UAV’s ability to promptly comprehend the crisis and optimally utilize its limited power and processing resources to narrow down search areas is crucial. Therefore, developing an efficient and lightweight method for scene classification is of utmost importance. However, current approaches tend to prioritize accuracy on benchmark datasets at the expense of computational efficiency. To address this shortcoming, we introduce the Wider ATTENTION EfficientNet (WATT-EffNet), a novel method that achieves higher accuracy with a more lightweight architecture compared to the baseline EfficientNet. The WATT-EffNet leverages width-wise incremental feature modules and attention mechanisms over width-wise features to ensure the network structure remains lightweight. We evaluate our method on a UAV-based aerial disaster image classification dataset and demonstrate that it outperforms the baseline by up to 15 times in terms of classification accuracy and 38.3% in terms of computing efficiency as measured by Floating Point Operations per second (FLOPs). Additionally, we conduct an ablation study to investigate the effect of varying the width of WATT-EffNet on accuracy and computational efficiency.

Traditional oversampling methods are well explored for binary and multi-class imbalanced datasets. In most cases, the data space is adapted for oversampling the imbalanced classes. It leads to various issues like poor modelling of the structure of the data, resulting in data overlapping between minority and majority classes that lead to poor classification performance of minority class(es). To overcome these limitations, we propose a novel data oversampling architecture called Structure Preserving Variational Learning (SPVL). This technique captures an uncorrelated distribution among classes in the latent space using an encoder-decoder framework. Hence, minority samples are generated in the latent space, preserving the structure of the data distribution. The improved latent space distribution (oversampled training data) is evaluated by training an MLP classifier and testing with unseen test dataset. The proposed SPVL method is applied to various benchmark datasets with i) binary and multi-class imbalance data, ii) high-dimensional data and, iii) large or small-scale data. Extensive experimental results demonstrated that the proposed SPVL technique outperforms the state-of-the-art counterparts.

In real world scenarios, out-of-distribution (OOD) datasets may have a large distributional shift from training datasets. This phenomena generally occurs when a trained classifier is deployed on varying dynamic environments, which causes a significant drop in performance. To tackle this issue, we are proposing an end-to-end deep multi-task network in this work. Observing a strong relationship between rotation prediction (self-supervised) accuracy and semantic classification accuracy on OOD tasks, we introduce an additional auxiliary classification head in our multi-task network along with semantic classification and rotation prediction head. To observe the influence of this addition classifier in improving the rotation prediction head, our proposed learning method is framed into bi-level optimisation problem where the upper-level is trained to update the parameters for semantic classification and rotation prediction head. In the lower-level optimisation, only the auxiliary classification head is updated through semantic classification head by fixing the parameters of the semantic classification head. The proposed method has been validated through three unseen OOD datasets where it exhibits a clear improvement in semantic classification accuracy than other two baseline methods. Our code is available on GitHub https://github.com/harshita-555/OSSL

Many real-world classification problems have imbalanced frequency of class labels; a well-known issue known as the "class imbalance" problem. Classic classification algorithms tend to be biased towards the majority class, leaving the classifier vulnerable to misclassification of the minority class. While the literature is rich with methods to fix this problem, as the dimensionality of the problem increases, many of these methods do not scale-up and the cost of running them become prohibitive. In this paper, we present an end-to-end deep generative classifier. We propose a domain-constraint autoencoder to preserve the latent-space as prior for a generator, which is then used to play an adversarial game with two other deep networks, a discriminator and a classifier. Extensive experiments are carried out on three different multi-class imbalanced problems and a comparison with state-of-the-art methods. Experimental results confirmed the superiority of our method over popular algorithms in handling high-dimensional imbalanced classification problems. Our code is available on https://github.com/TanmDL/SLPPL-GAN

Autonomous learning algorithms operate in an online fashion in dealing with data stream mining, where minimum computational complexity is a desirable feature. For such applications, parsimonious learning machines (PALMs) are suitable candidates due to their structural simplicity. However, these parsimonious algorithms depend upon predefined thresholds to adjust their structures in terms of adding or deleting rules. Besides, another adjustable parameter of PALM is the fuzziness in membership grades. The best set of such hyper parameters is determined by experts' knowledge or by optimization techniques such as greedy algorithms. To mitigate such experts' dependency or usage of computationally expensive greedy algorithms, in this work, a meta heuristic-based optimization technique, called the multimethod-based optimization technique (MOT), is utilized to develop an advanced PALM. The performance has been compared with some popular optimization techniques, namely, the greedy search, local search, genetic algorithm (GA), and particle swarm optimization (PSO). The proposed parsimonious learning algorithm with MOT outperforms the others in most cases. It validates the multioperator-based optimization technique's advantages over the single operator-based variants in selecting the best feasible hyperparameters for the autonomous learning algorithm by maintaining a compact architecture.

Real-time forecasting of the financial time-series data is challenging for many machine learning (ML) algorithms. First, many ML models operate offline, where they need a batch of data, which may not be available during training. Besides, due to a fixed architecture of the majority of the offline-based ML models, they suffer to deal with the uncertain nature of financial time-series data. In contrast, online learning mode evolving-structured ML models could be promising for financial time-series forecasting. For real-time deployment of such models, low memory demand is a must. Besides, the model’s explainability plays a crucial role in forecasting financial time-series. Considering all the requirements, a rule-based autonomous neuro-fuzzy learning algorithm called the parsimonious learning machine (PALM) is proposed here to forecast time-varying stock indices. To provide efficient automation of the proposed algorithm by maintaining the model explainability in terms of limited number linguistic IF-THEN rules, two popular multiobjective evolutionary algorithms (MEAs), such as a real-coded genetic algorithm (GA) and a self-adaptive differential evolution (DE) algorithm are utilized here. In addition, fuzzy type-2 variants of PALMs’ are considered here due to better uncertainty handling capacity than their type-1 counterparts. To evaluate the proposed algorithm’s performance, the closing stock price of fifteen (15) different stock market indices are predicted here. From the results, it is observed that the MEA-based PALMs are performing better than the state-of-the-art benchmark online ML models and providing a rule-based explainable model to the end-user.

Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer an end-to-end solution. To overcome this, we propose a three-player adversarial game-based end-to-end method, where a domain-constraints mixture of generators, a discriminator, and a multi-class classifier are used. Rather than adversarial minority oversampling, we propose an adversarial oversampling (AO) and a data-space oversampling (DO) approach. In AO, the generator updates by fooling both the classifier and discriminator, however, in DO, it updates by favoring the classifier and fooling the discriminator. While updating the classifier, it considers both the real and synthetically generated samples in AO. But, in DO, it favors the real samples and fools the subset class-specific generated samples. To mitigate the biases of a classifier towards the majority class, minority samples are over-sampled at a fractional rate. Such implementation is shown to provide more robust classification boundaries. The effectiveness of our proposed method has been validated with high-dimensional, highly imbalanced and large-scale multi-class tabular datasets. The results as measured by average class specific accuracy (ACSA) clearly indicate that the proposed method provides better classification accuracy (improvement in the range of 0.7% to 49.27%) as compared to the baseline classifier

In recent times, with the incremental demand for fully autonomous systems, research interests are observed in learning machine-based intelligent, self-organizing, and evolving controllers. In this paper, a new evolving and self-organizing controller, namely generic-controller (G-controller), is proposed. The G-controller works in a fully online mode with minor expert domain knowledge. It is developed by incorporating the sliding mode control (SMC) theory with an advanced incremental learning machine, namely generic evolving neuro-fuzzy inference system. The controller starts operating from scratch with an empty set of fuzzy rule, and therefore, no offline training is required. To cope with the changing dynamic characteristics of the plant, the controller can add or prune the rules on demand. Control law and adaptation laws for the consequent parameters are derived from the SMC algorithm to establish a stable closed-loop system, where the stability of the G-controller is guaranteed by using the Lyapunov function. The uniform asymptotic convergence of tracking error to zero is witnessed through the implication of an auxiliary robustifying control term. In addition, the implementation of the multivariate Gaussian function helps the controller to handle the nonaxis parallel data from the plant and consequently, enhances the robustness against uncertainties and environmental perturbations. Finally, the controller's performance has been evaluated by observing the tracking performance in controlling simulated plants of unmanned aerial vehicle, namely bio-inspired flapping wing micro air vehicle and hexacopter for a variety of trajectories.

In this work, a simple evolving neuro-fuzzy system with less learning parameters is utilized to develop an intelligent controller namely Reduced Parsimonious Controller (RedPAC). The proposed RedPAC is a simplified version of one of the recently developed intelligent controller called Parsimonious Controller (PAC). In RedPAC, the network parameters are reduced into two steps. Firstly, unlike the conventional fuzzy logic or neuro-fuzzy-based intelligent controller, it has no premise parameters. Secondly, in contrast with PAC, the number of consequent parameters have further reduced to one parameter per rule in RedPAC. The sliding mode control (SMC) technique is utilized to adapt consequent parameters of RedPAC, where the SMC-based auxiliary robustifying control term has guaranteed the uniform asymptotic convergence of tracking error to zero. The proposed controller's performance has been evaluated by implementing it to control a quadcopter unmanned aerial vehicle (UAV) simulator namely Dronekit. In addition, trajectory tracking performance of the quadcopter is compared with three different benchmark controllers namely a linear PID, a nonlinear SMC, and an intelligent controller called PAC. RedPAC outperforms PID and SMC techniques. The results of tracking trajectories are also comparable to PAC; however, RedPAC needs comparatively less learning parameters to obtain a similar or better tracking accuracy.

Data stream has been the underlying challenge in the age of big data because it calls for real-time data processing with the absence of a retraining process and/or an iterative learning approach. In the realm of the fuzzy system community, data stream is handled by algorithmic development of self-adaptive neuro-fuzzy systems (SANFS) characterized by the single-pass learning mode and the open structure property that enables effective handling of fast and rapidly changing natures of data streams. The underlying bottleneck of SANFSs lies in its design principle, which involves a high number of free parameters (rule premise and rule consequent) to be adapted in the training process. This figure can even double in the case of the type-2 fuzzy system. In this paper, a novel SANFS, namely parsimonious learning machine (PALM), is proposed. PALM features utilization of a new type of fuzzy rule based on the concept of hyperplane clustering, which significantly reduces the number of network parameters because it has no rule premise parameters. PALM is proposed in both type-1 and type-2 fuzzy systems where all of which characterize a fully dynamic rule-based system. That is, it is capable of automatically generating, merging, and tuning the hyperplane-based fuzzy rule in the single-pass manner. Moreover, an extension of PALM, namely recurrent PALM, is proposed and adopts the concept of teacher-forcing mechanism in the deep learning literature. The efficacy of PALM has been evaluated through numerical study with six real-world and synthetic data streams from public database and our own real-world project of autonomous vehicles. The proposed model showcases significant improvements in terms of computational complexity and number of required parameters against several renowned SANFSs, while attaining comparable and often better predictive accuracy.

Nowadays, the application of fully autonomous system like rotary wing unamnned air vehicles (UAVs) are increasing sharply. Due to the complex nonlinear dynamics a huge research interest is witnessed in developing learning machine based intelligent, self-organizing evolving controller for these vehicles notably to address the system's dynamic characteristics. In this work, such an evolving controller namely Generic-controller (Gcontroller) is proposed to control the altitude of a rotary wing UAV namely hexacopter. This controller can work with very minor expert domain knowledge. The evolving architecture of this controller is based on an advanced incremental learning algorithm namely Generic Evolving Neuro-Fuzzy Inference System (GENEFIS). The controller does not require any offline training, since it starts operating from scratch with an empty set of fuzzy rules, and then add or delete rules on demand. The adaptation laws for the consequent paramters are derived from the sliding model control (SMC) theory. The Lyapunov theory is used to guarantee the stability of the proposed controller. In addition, an auxiliary robustifying control term is implemented to obtain an uniform asymptotic convergence of tracking error to zero. Finally, the G-controller's performance evaluation is observed through the altitude tracking of an UAV namely hexacopter for various trajectories.