25 March 2021 in Neural Computing and Applications
1 February 2020 in Knowledge-Based Systems
25 August 2020 in IEEE Transactions on Smart Grid
The reliability of distribution systems is often challenged under unfavorable weather conditions, where weather-related failures occur with high probability. Predicting the number of weather-related failures in distribution systems can provide guiding information for operation and maintenance decisions, improving the risk management capability of utility companies. This paper proposes a novel Bayesian Neural Network (BNN) based model to predict weather-related failures caused by wind, rain and lightning. Superior prediction performance of the BNN based model is verified by contrast experiments with other advanced prediction models under four different evaluation metrics. BNN based prediction model presents remarkable robustness, especially in the prediction of high failure levels. In addition, compared to most previous used prediction models without any prediction confidence feedback, BNN based prediction model has the capability of uncertainty estimation. The confidence interval of prediction results can be obtained, which provides sufficient information for guiding risk management of utility companies. An effective operation and maintenance guiding scheme based on the analysis of prediction uncertainty is proposed, which fully excavates the interpretability of the proposed model and enrich the application value of the model.
18 May 2020 in IEEE Robotics and Automation Letters
Event-based cameras are a new type of vision sensor that can encode spatial-temporal context in a pixel-level event stream. Its appealing properties offer great potential for applications requiring low processing latency and low power consumption. As an effective representation of events, the surface of active event (SAE) has become a favorable choice for corner detection and object classification, among others. These tasks apply normalizations as an essential preprocessing step to extract time-invariant features from SAEs. However, previous normalization methods have some drawbacks, including low efficiency, requiring parameter tuning, etc. These drawbacks largely limit their performances in practical tasks. In this work, we propose a highly efficient normalization method, i.e., chain normalization, to break the limits in the previous state-of-the-art. We leverage the inherent properties of SAE in designing. First, we propose a novel SAE implementation to utilize the characteristics of SAE. Compared with previous works, our method can efficiently capture the spatial and temporal relationships of events and enable robust normalization. Second, we further increase the efficiency by using a novel stacking strategy. We compare our method to the state-of-the-art with extensive experiments, showing high classification accuracy and a significant improvement in runtime performance. We also release the source codes for future distribution and improvement in the community.
3 November 2022 in Ocean Engineering
15 May 2025 in Artificial Intelligence Review
Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem.