Recent advancements in large language models (LLMs) have demonstrated their potential to significantly impact finance trading, particularly through sentiment analysis. The cryptocurrency market, known for its volatility and unpredictability, often renders price-based trading approaches inadequate. This necessitates the adoption of more sophisticated techniques such as market sentiment analysis, which can benefit from the insights provided by LLMs. This study introduces an innovative method that integrates sentiment analysis derived from five distinct LLMs with deep reinforcement learning to devise a cryptocurrency trading strategy. Recognizing that LLM outputs cannot be guaranteed to be infallibly accurate, which contributing to the LLM hallucinations, this paper details the implementation of a stringent outlier detection and removal process. By adopting a “Trust-The-Majority” strategy, the research aims to ensure that trading decisions are informed by reliable sentiment data. In addition, sentiment scores are traditionally timestamped to the publication of news or social media posts. To more accurately reflect the actual impact of such information on market sentiment, this study applies the Ebbinghaus Forgetting Curve to model the waning influence of information over time. This allows for a more nuanced understanding of how news affects market dynamics. The enhanced sentiment scores, in conjunction with traditional market data such as OHLCV (Open, High, Low, Close, Volume), are utilized by a deep reinforcement learning model to make trading decisions. Experimental results demonstrate that the proposed multi-LLM sentiment-driven framework improves trading performance in the fast-paced cryptocurrency market. The methodology outlined in this paper offers a solid foundation for incorporating real-time market sentiment analysis into financial applications.

This article investigates the distributed estimation problem of an unknown high-dimensional sparse state vector for a stochastic dynamic system. The communication topology randomly switches, and the switching law is governed by a time-homogeneous Markovian chain. By means of the compressed sensing (CS) theory and a diffusion strategy, we propose a compressed distributed Kalman filter (CDKF). That is, each sensor first compresses the original high-dimensional regression data. Then, the covariance intersection fusion rule is utilized to obtain a distributed Kalman filter (DKF) estimate in the compressed low-dimensional space. Afterward, the original high-dimensional sparse state vector can be well recovered by a reconstruction technique. In terms of stability analysis, one of the main difficulties lies in analyzing the product of nonindependent and nonstationary random matrices in the context of time-varying communication topologies. Relying on the stochastic stability theory, the Markov chain theory, and the CS theory, we establish the upper bound for the estimation error under the compressed cooperative excitation condition, which is much weaker than the traditional uncompressed collective observability conditions used in the existing literature. Finally, we provide a simulation example to illustrate the performance of the proposed algorithm.

Accurate oral disease segmentation is a challenging task, for three major reasons: 1) The same type of oral disease has a diversity of size, color and texture; 2) The boundary between oral lesions and their surrounding mucosa is not sharp; 3) There is a lack of public large-scale oral disease segmentation datasets. To address these issues, we first report an oral disease segmentation network termed Oralformer, which enables to tackle multiple oral diseases. Specifically, we use a parallel design to combine local-window self-attention (LWSA) with channel-wise convolution (CWC), modeling cross-window connections to enlarge the receptive fields while maintaining linear complexity. Meanwhile, we connect these two branches with bi-directional interactions to form a basic parallel Transformer block namely LC-block. We insert the LC-block as the main building block in a U-shape encoder-decoder architecture to form Oralformer. Second, we introduce an uncertainty-driven self-adaptive loss function which can reinforce the network's attention on the lesion's edge regions that are easily confused, thus improving the segmentation accuracy of these regions. Third, we construct a large-scale oral disease segmentation (ODS) dataset containing 2602 image pairs. It covers three common oral diseases (including dental plaque, calculus and caries) and all age groups, which we hope will advance the field. Extensive experiments on six challenging datasets show that our Oralformer achieves state-of-the-art segmentation accuracy, and presents advantages in terms of generalizability and real-time segmentation efficiency (35fps). The code and ODS dataset will be publicly available at https://github.com/LintaoPeng/Oralformer.

Automated program repair (APR) has been gaining ground with substantial effort devoted to the area, opening up many challenges and opportunities. One such challenge is that the state-of-the-art repair techniques often resort to incomplete specifications, e.g., test cases that witness buggy behavior, to generate repairs. In practice, bug-exposing test cases are often available when: (1) developers, at the same time of (or after) submitting bug fixes, create the tests to assure the correctness of the fixes, or (2) regression errors occur. The former case – a scenario commonly used for creating popular bug datasets – however, may not be suitable to assess how APR performs in the wild. Since developers already know where and how to fix the bugs, tests created in this case may encapsulate knowledge gained only after bugs are fixed. Thus, more effort is needed to create datasets for more realistically evaluating APR.We address this challenge by creating a dataset focusing on bugs identified via continuous integration (CI) failures – a special case of regression errors – wherein bugs happen when the program after being changed is re-executed on the existing test suite. We argue that CI failures, wherein bug-exposing tests are created before bug fixes and thus assume no prior knowledge of developers on the bugs to be involved, are more realistic for evaluating APR. Toward this end, we curated 102 CI failures from 40 popular real-world software on GitHub. We demonstrate various features and the usefulness of the dataset via an evaluation of five well-known APR techniques, namely GenProg, Kali, Cardumen, RsRepair and Arja. We subsequently discuss several findings and implications for future APR studies. Overall, experiment results show that our dataset is complementary to existing datasets such as Defect4J in realistic evaluations of APR.

This paper studies the impact of stochastic load variations on distributed optimal load tracking and allocation (OLTA) problems in cyber-physical DC microgrids (MGs) for transportation electrification. Without load variations, the distributed optimization strategies developed in our earlier work can achieve convergence to global optimal solutions in a multi-objective optimization that balances fair load allocation and power loss reduction. Under persistent stochastic load variations, this paper develops distributed optimal strategies to track time-varying loads under noisy observations and establishes their convergence properties and error bounds. The limiting behavior of the errors characterizes the fundamental impact of the step size on irreducible errors due to conflict between attenuating observation noises and tracking load changes. Optimality conditions and algorithms for selecting the optimal step size are introduced to guide step size selection in practical applications. Simulation studies on real-world systems demonstrate the effectiveness of the proposed algorithms and validate the theoretical results.

In many large-scale machine learning applications, data are accumulated over time, and thus, an appropriate model should be able to update in an online style. In particular, it would be ideal to have a storage independent from the data volume, and scan each data item only once. Meanwhile, the data distribution usually changes during the accumulation procedure, making distribution-free one-pass learning a challenging task. In this paper, we propose a simple yet effective approach for this task, without requiring prior knowledge about the change, where every data item can be discarded once scanned. We also present a variant for high-dimensional situations, by exploiting compressed sensing to reduce computational and storage complexity. Theoretical analysis shows that our proposal converges under mild assumptions, and the performance is validated on both synthetic and real-world datasets.