We propose a novel interval-based transformer approach called DKformer to forecast quarterly carbon futures prices by treating interval-valued data as inseparable random sets. Our DKformer model leverages the attention mechanism to capture long-term dependencies and complex dynamics in the carbon market. The model integrates the European economic policy uncertainty (EEPU) index and the climate policy uncertainty (CPU) index, utilizing only lags of price values and EPU indices as explanatory variables to effectively capture the impact of policy shifts on carbon futures prices. Empirical tests demonstrate the strong performance of the model in predicting market turning points and responding to various policy change scenarios, including the implementation of the EU ETS Phase 4, the RePowerEU Plan, and the carbon border adjustment mechanism (CBAM). Furthermore, our findings indicate the outstanding performance of our method remains robust to various forecasting period, forecasting horizons, and sets of explanatory variables.

Humans use context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human communication, we study how to extract fine-grained data regarding why an example is preferred that is useful for learning an accurate reward model. We propose to enrich preference queries to ask both (1) which features of a given example are preferable in addition to (2) comparisons between objects. We derive an approach for learning from these feature-level preferences, both for cases where users specify which features are reward-relevant, and when users do not. We evaluate our approach on linear bandit settings in both visual and language-based domains. Results support the efficiency of our approach in quickly converging to accurate rewards with less comparisons vs. example-only labels. Finally, we validate the real-world applicability with a behavioral experiment on a mushroom foraging task. Our findings suggest that incorporating pragmatic feature preferences is a promising approach for more efficient user-aligned reward learning.

Sparse LU factorization is considered to be one of the most time-consuming components in circuit simulation, particularly when dealing with circuits of considerable size in the advanced process era. Sparse LU factorization can be expedited by utilizing the supernode structure, which partitions the matrix into dense sub-matrices, thereby improving computational performance by utilizing level-3 Basic Linear Algebra Subprograms (BLAS) General Matrix Multiplication (GEMM) operations. The sparse and irregular structure of circuit matrices often impedes the formation of supernodes or results in the formation of supernodes with many zero elements, which in turn poses challenges for exploiting GEMM operations. In this paper, by fully utilizing the density in sub-matrices and combining GEMM with the Dense-Sparse Matrix Multiplication (SpMM), we propose a density-aware adaptive matrix multiplication equipped with machine learning techniques to optimize performance of the most-time consuming matrix multiplication operator so as to accelerate the sparse LU factorization. Numerical experiment results show that among the 6 circuit matrices tested, the average performance of matrix multiplication in our algorithm can be improved by 5.35x (up to 9.35x) compared to the performance of using GEMM directly in Schur-complement updates. Compared with state-of-the-art solver SuperLU_DIST, our method shows a substantial performance improvement.

Zero-watermarking is a key technique for achieving lossless and flexible copyright protection of depth image-based rendering (DIBR) videos. Existing approaches extract features of both 2D frames and depth maps via a single mechanism to protect them simultaneously. However, it is difficult for these schemes to fully satisfy the copyright protection requirements of the two components, including the remarkable discriminative capability of 3D videos and robustness against various attacks. Hence, in this paper, we propose a novel multiple-feature-based zero-watermarking scheme to protect the copyright of DIBR 3D videos. To the best of our knowledge, this is the first scheme that integrates multiple features to improve both the discriminative capability and robustness against various attacks. Specifically, dual-tree complex wavelet transform and discrete cosine transform features enhance the robustness against DIBR conversion and noise addition, respectively, while ring-partition statistical residual features ensure robustness against geometric attacks and provide sufficient discriminative capacity. In addition, we use a logistic-logistic chaotic system to encrypt these multiple features for enhanced security and design an attention-based fusion approach to offer an optimal copyright protection solution. Extensive experimental results demonstrate that our proposed scheme has stronger robustness and discriminative capacity compared to state-of-the-art zero-watermarking methods.

This paper proposes a satellite laser communication system based on M-QAM OFDM and analyzes the system performance. The relationship between the link bit error rate and the transmission power under different conditions of atmospheric turbulence intensity and QAM modulation order is simulated. The results show that as the turbulence intensity increases, the QAM modulation order M increases, and the performance of OFDM optical links continues to deteriorate. This provides a reference for parameter optimization and performance evaluation of OFDM optical links in satellite laser communications.

A sensor data acquisition system is an essential part of an industrial automation control system. However, the variety of sensor producer causes the difficulty of protocol's unity. The mechanism which requires the acquisition boards to be powered off when the number or types or manufacturer of sensors is changed is unreasonable. Meanwhile, traditional sensor reading cycle depends more on the embedded program skills. In this paper, to solve these problems, a new method is proposed to design a reconfigurable data acquisition system for industrial sensors, in which field-programmable gate array (FPGA) is adopted as the core controller. We use both dynamic system reconfiguration and static system reconfiguration in our design. Performance of the proposed system is verified in practical application of an automated production system of poly carboxylic acid water reducing agent.