Multi-label learning with emerging new labels is a practical problem that occurs in data streams and has become an important new research issue in the area of machine learning. However, existing models for dealing with this problem require high learning computational times, and there still exists a lack of research. Based on these issues, this paper presents an incremental kernel extreme learning machine for multi-label learning with emerging new labels, consisting of two parts: a novelty detector; and a multi-label classifier. The detector with free-user-setting threshold parameters was developed to identify instances with new labels. A new incremental multi-label classifier and its improved version were developed to predict a label set for each instance, which can add output units incrementally and update themselves in unlabeled instances. Comprehensive evaluations of the proposed method were carried out on the problems of multi-label classification with emerging new labels compared to comparative algorithms, which revealed the promising performance of the proposed method.

This paper presents the Bias-Boosted Extreme Learning Machine guided Brain Emotional Learning (B2ELM-BEL) model, a significant advancement in chaotic time series prediction that effectively incorporates knowledge transfer learning. Integrating traditional Brain Emotional Learning (BEL) with the novel Biased-ELM method, the B2ELM-BEL introduces a bias term into the output weights of Extreme Learning Machines (ELM). This addition enhances the model’s predictive accuracy, proving particularly beneficial in configurations with a minimal number of hidden nodes. Our evaluation of the B2ELM-BEL model across various datasets, including complex chaotic time-series benchmarks and real-world scenarios, demonstrates its superior performance over several BEL models. It achieves lower mean RMSE, MAE, and SMAPE values, and exhibits enhanced generalizability and efficiency. The findings indicate that while the single hidden node variant of B2ELM-BEL is apt for simpler tasks, the multi-node version is more adept at handling challenging environments. This highlights the necessity of tailoring the model to the complexity of the specific dataset being analyzed.

In recent years, agricultural product price forecasting has played a crucial role in supply chain management and market decision-making. However, due to the influence of multiple factors such as supply-demand dynamics, seasonality, and weather conditions, agricultural product prices exhibit highly nonlinear and dynamic characteristics, making traditional methods often insufficient for accurate price change prediction. To address these challenges, this paper proposes a novel time series prediction model based on Temporal Convolutional Network (TCN), Multi-Layer Perceptron (MLP), and attention mechanism (referred to as "TCN-MLP-Attention"), using daily average price data from the U.S. avocado market from 2015 to 2023. The model aims to provide more accurate price trend forecasts for various stages of the supply chain. In the model architecture design, the TCN module utilizes causal convolution structure and dilated convolution to handle long-term temporal dependencies; the MLP module performs feature transformation and nonlinear mapping through a two-layer network; and the attention mechanism identifies important features at key time steps. This multi-module collaborative architecture effectively processes multi-scale features of time series data while providing model interpretability. Through comparative analysis of various optimization algorithms’ convergence performance and prediction accuracy, this study found that the AdamW optimizer, with its effective weight decay mechanism and adaptive learning rate, demonstrated superior performance in training stability and generalization capability, with MSE and R² metrics outperforming traditional optimizers. Therefore, the AdamW optimizer with an adaptive learning rate adjustment strategy was adopted for model training. Experimental results show that the proposed TCN-MLP-Attention model exhibits better prediction performance compared to the baseline Transformer model: MSE decreased by approximately 1.24%, and R² increased by about 0.17%, indicating stronger generalization ability in capturing time series features. Although MAE was slightly higher, the overall error control remained within an acceptable range, validating the model’s stability and effectiveness. The importance of the attention mechanism was further verified through ablation experiments, with the complete model’s R² value improving by 87.04% and MSE decreasing by 87.18% compared to using TCN alone, confirming the effectiveness of the multi-module collaborative design. The model’s generalization capability is further validated through noise robustness tests and cross-product validation experiments. Even with medium-level noise (=0.05), the model maintains 77% of its R² value, and when applied to strawberry price prediction using the dataset published by the United States Department of Agriculture Economic Research Service (USDA ERS)—a product with significantly different market characteristics—it achieves an R² value of 0.7499 without any retraining, demonstrating strong adaptability to different data distributions. This research not only demonstrates the superiority of this hybrid architecture in handling complex time series prediction tasks, especially showing strong adaptability during market fluctuation periods, but also provides new research directions for deep learning applications in agricultural price prediction.