Emotion recognition in conversation (ERC) faces two major challenges: biased predictions and poor calibration. Classifiers often disproportionately favor certain emotion categories, such as neutral, due to the structural complexity of classifiers, the subjective nature of emotions, and imbalances in training datasets. This bias results in poorly calibrated predictions where the model’s predicted probabilities do not align with the true likelihood of outcomes. To tackle these problems, we introduce the application of conformal prediction (CP) into ERC tasks. CP is a distribution-free method that generates set-valued predictions to ensure marginal coverage in classification, thus improving the calibration of models. However, inherent biases in emotion recognition models prevent baseline CP from achieving a uniform conditional coverage across all classes. We propose a novel CP variant, class spectrum conformation, which significantly reduces coverage bias in CP methods. The methodologies introduced in this study enhance the reliability of prediction calibration and mitigate bias in complex natural language processing tasks.

In order to enable widespread integration of solar energy into the power system, there is an increasing need to reduce the uncertainty associated with solar power output which requires major improvements in solar irradiance forecasting. While most recent works have addressed short-term (minutes or hours ahead) forecasting, through this work, we propose using deep sequence learning models for forecasting at longer lead times such as a week in advance, as this can play a significant role in future power system storage applications. Along with point forecasts, we also produce uncertainty estimates through probabilistic prediction and showcase the potential of our machine learning frameworks for a new and important application of longer lead time forecasting in this domain. Our study on the SURFRAD data over seven US cities compares various deep sequence models and the results are encouraging, demonstrating their superior performance against most benchmarks from the literature and a current machine learning-based probabilistic prediction baseline (previously applied to short-term solar forecasting).

This paper presents a novel control algorithm for electrically driven robot manipulators. The proposed control law is simple and model-free based on the voltage control strategy with the decentralized structure and only joint position feedback. It works for both repetitive and non-repetitive tasks. Recently, some control approaches based on the uncertainty estimation using the Fourier series have been presented. However, the proper value for the fundamental period duration has been left as an open problem. This paper addresses this issue and intuitively shows that in order to perform repetitive tasks; the least common multiple (LCM) of fundamental period durations of the desired trajectories of the joints is a proper value for the fundamental period duration of the Fourier series expansion. Selecting the LCM results in the least tracking error. Moreover, the truncation error is compensated by the proposed control law to make the tracking error as small as possible. Adaptation laws for determining the Fourier series coefficients are derived according to the stability analysis. The case study is an SCARA robot manipulator driven by permanent magnet DC motors. Simulation results and comparisons with a voltage-based controller using adaptive neuro-fuzzy systems show the effectiveness of the proposed control approach in tracking various periodic trajectories. Moreover, the experimental results on a real SCARA robot manipulator verify the successful practical implementation of the proposed controller.