Publications

Various image compression methods have been proposed to realize the easiness and relative inexpensiveness for obtaining and storing digital information, and the possibility to manipulate such information is almost unlimited [1][6][8]. As the number of image compression methods grows steadily, selecting appropriate methods is no longer a simple task. Now we face a stage in which we choose an appropriate method considering its applications (e.g. image database [5] and digital watermark [2] etc). An example of such image compression methods has been proposed by Hirota and Pedrycz, called Image Compression method based on Fuzzy relational equation [4]. In this paper, a fast image reconstruction method for ICF is proposed.

In Neurospora crassa, expression from an unpaired gene is suppressed by a mechanism known as meiotic silencing by unpaired DNA (MSUD). MSUD utilizes common RNA interference (RNAi) factors to silence target mRNAs. Here, we report that Neurospora CAR-1 and CGH-1, homologs of two Caenorhabditis elegans RNA granule components, are involved in MSUD. These fungal proteins are found in the perinuclear region and P-bodies, much like their worm counterparts. They interact with components of the meiotic silencing complex (MSC), including the SMS-2 Argonaute. This is the first time MSUD has been linked to RNA granule proteins.

Reinforcement Learning (RL) has emerged as a highly effective technique for addressing various scientific and applied problems. Despite its success, certain complex tasks remain challenging to be addressed solely with a single model and algorithm. In response, ensemble reinforcement learning (ERL), a promising approach that combines the benefits of both RL and ensemble learning (EL), has gained widespread popularity. ERL leverages multiple models or training algorithms to comprehensively explore the problem space and possesses strong generalization capabilities. In this study, we present a comprehensive survey on ERL to provide readers with an overview of recent advances and challenges in the field. Firstly, we provide an introduction to the background and motivation for ERL. Secondly, we conduct a detailed analysis of strategies such as model selection and combination that have been successfully implemented in ERL. Subsequently, we explore the application of ERL, summarize the datasets, and analyze the algorithms employed. Finally, we outline several open questions and discuss future research directions of ERL. By offering guidance for future scientific research and engineering applications, this survey significantly contributes to the advancement of ERL.