Abstract ：

Background: Publicly accessible critical care-related databases contain enormous clinical data, but their utilization often requires advanced programming skills. The growing complexity of large databases and unstructured data presents challenges for clinicians who need programming or data analysis expertise to utilize these systems directly. Objective: This study aims to simplify critical care-related database deployment and extraction via large language models. Methods: The development of this platform was a 2-step process. First, we enabled automated database deployment using Docker container technology, with incorporated web-based analytics interfaces Metabase and Superset. Second, we developed the intensive care unit-generative pretrained transformer (ICU-GPT), a large language model fine-tuned on intensive care unit (ICU) data that integrated LangChain and Microsoft AutoGen. Results: The automated deployment platform was designed with user-friendliness in mind, enabling clinicians to deploy 1 or multiple databases in local, cloud, or remote environments without the need for manual setup. After successfully overcoming GPT's token limit and supporting multischema data, ICU-GPT could generate Structured Query Language (SQL) queries and extract insights from ICU datasets based on request input. A front-end user interface was developed for clinicians to achieve code-free SQL generation on the web-based client. Conclusions: By harnessing the power of our automated deployment platform and ICU-GPT model, clinicians are empowered to easily visualize, extract, and arrange critical care-related databases more efficiently and flexibly than manual methods. Our research could decrease the time and effort spent on complex bioinformatics methods and advance clinical research. JMIR Med Inform 2025;13:e63216; doi: 10.2196/63216

Keyword ：

critical care-related databases AI ICU intensive care unit LLM big data artificial intelligence large language model GPT database deployment database extraction

Cite：

Copy from the list or Export to your reference management。

Abstract ：

一种数据知识驱动的城市污水处理过程多目标优化控制方法,属于污水处理领域。 为了平衡能耗和出水水质,建立了数据驱动的多目标优化模型,包括能耗模型和出水水质模型,以获得能耗、出水水质和控制变量的非线性关系。 同时,提出了一种基于进化知识的多目标粒子群优化算法来优化硝态氮和溶解氧的设定点。 此外,比例积分微分 (PID) 控制器旨在跟踪设定点。 从而可以提高出水水质并降低能耗。

Cite：

Copy from the list or Export to your reference management。

Abstract ：

In this study, a new strategy for NO detection based on the aggregation-induced electrochemical luminescence (AIECL) of a ruthenium-based complex and the halogen bonding effect was developed. First, [Ru(phen)(2)(phen-Br-2)](2+) (phen : 1,10-phenanthroline, phen-Br-2 : 3,8-dibromo-1,10-phenanthroline) was synthesized and exhibited aggregation-induced emission (AIE) and AIECL properties in a poor solvent (H2O). [Ru(phen)(2)(phen-Br-2)](2+) exhibited greatly enhanced AIECL properties compared to its AIE intensity. When the volume fraction of water (f(w), v %) in the H2O-acetonitrile (MeCN) system was increased from 30 to 90 %, the photoluminescence and electrochemiluminescence (ECL) intensities were three- and 800-fold that of the pure MeCN system, respectively. Dynamic light scattering and scanning electron microscopy results indicated that [Ru(phen)(2)(phen-Br-2)](2+) aggregated into nanoparticles. AIECL is sensitive to NO because of its halogen bonding effect. The C-Br center dot center dot center dot N bond between [Ru(phen)(2)(phen-Br-2)](2+) and NO increased the distance of complex molecules, resulting in ECL quenching. A detection limit of 2 nM was obtained with 5 orders of magnitude linear range. The combination of the AIECL system and the halogen bond effect expands the theoretical research and applications in biomolecular detection, molecular sensors, and stages of medical diagnosis.

Keyword ：

halogen bonding nitric oxide molecular recognition ruthenium aggregation-induced electrochemiluminescence

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Multiple-swarm approach is a quite successful evolutionary computation framework for multi-objective particle swarm optimization algorithm (MOPSO) to solve multi-objective optimization problems (MOPs). However, the main challenge of using this framework lies in the lack of leader selection, resulting in the optimal solutions being distributed loosely, as well as far away from the true Pareto-optimal front. To overcome this problem, a multi-swarm MOPSO with an adaptive multiple selection strategy (MOPSO-AMS) is investigated in this paper. This proposed MOPSO-AMS is able to guide each swarm with a suitable lea-der to improve the evolutionary performance. The novelties and advantages of MOPSO-AMS include the following three aspects. First, a hierarchical evolutionary state detection mechanism, based on the distribution and dominance information of non-dominated solu-tions, is designed to obtain the evolutionary state of current iteration. Then, the require-ments of evolutionary process can be detected. Second, an adaptive multiple selection strategy, using the evolutionary state information and spatial features of candidate solu-tions, is developed to select leaders of sub-swarms in multiple evolutionary states. Then, suitable leaders can be selected to keep the balance between convergence and diversity. Third, an adaptive parameter adjustment mechanism, based on the dominance relationship of each particle, is introduced to further improve the evolutionary performance of MOPSO-AMS. Finally, numerical simulations and a practical application are used to validate the analytical results and demonstrate the significant improvement of MOPSO-AMS.(c) 2022 Elsevier Inc. All rights reserved.

Keyword ：

Multi-objective optimization problem Multi-objective particle swarm optimization Adaptive multiple selection strategy Evolutionary state detection

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The selection of global best (Gbest) exerts a high influence on the searching performance of multi-objective particle swarm optimization algorithm (MOPSO). The candidates of MOPSO in external archive are always estimated to select Gbest. However, in most estimation methods, the candidates are considered as the Gbest in a fixed way, which is difficult to adapt to varying evolutionary requirements for balance between convergence and diversity of MOPSO. To deal with this problem, an adaptive candidate estimation-assisted MOPSO (ACE-MOPSO) is proposed in this paper. First, the evolutionary state information, including both the global dominance information and global distribution information of non-dominated solutions, is introduced to describe the evolutionary states to extract the evolutionary requirements. Second, an adaptive candidate estimation method, based on two evaluation distances, is developed to select the excellent leader for balancing convergence and diversity during the dynamic evolutionary process. Third, a leader mutation strategy, using the elite local search (ELS), is devised to select Gbest to improve the searching ability of ACE-MOPSO. Fourth, the convergence analysis is given to prove the theoretical validity of ACE-MOPSO. Finally, this proposed algorithm is compared with popular algorithms on twenty-four benchmark functions. The results demonstrate that ACE-MOPSO has advanced performance in both convergence and diversity.

Keyword ：

multi-objective particle swarm optimization convergence and diversity convergence analysis evolutionary state information adaptive candidate estimation

Cite：

Copy from the list or Export to your reference management。

Abstract ：

With the increasing complexity and scale of activated sludge process (ASP), it is quite challenging to coordinate the performance indices with different time scales. To address this problem, a cooperative optimal controller (COC) is proposed to improve the operation performance in this paper. First, a cooperative optimal scheme is developed for designing the control system, where the different time-scale performance indices are formulated by two levels. Second, a data-driven surrogate-assisted optimization (DDSAO) algorithm is provided to optimize the cooperative objectives, where a surrogate model is established for evaluating the feasibility of optimal solutions based on the minimum squared error. Third, an adaptive predictive control strategy is investigated to derive the control laws for improving the tracking control performance. Finally, the proposed COC is tested on benchmark simulation model No. 1 (BSM1). The results demonstrate that the proposed COC is able to coordinate the multiple time-scale performance indices and achieve the competitive optimal control performance.

Keyword ：

Activated sludge process (ASP) cooperative optimal controller (COC) coordinate Energy consumption Process control Optimal control Adaptation models Heuristic algorithms Cybernetics data-driven surrogate-assisted optimization (DDSAO) Optimization

Cite：

Copy from the list or Export to your reference management。

Abstract ：

城市污水处理过程优化控制是降低能耗的有效手段,然而,如何提高出水水质的同时降低能耗依然是当前城市污水处理过程面临的挑战.围绕上述挑战,文中提出了一种数据和知识驱动的多目标优化控制(Data-knowledge driven mul-tiobjective optimal control,DK-MOC)方法.首先,建立了出水水质、能耗以及系统运行状态的表达关系,获得了运行过程优化目标模型.其次,提出了一种基于知识迁徙学习的动态多目标粒子群优化算法,实现了控制变量优化设定值的自适应求解.最后,将提出的DK-MOC应用于城市污水处理过程基准仿真模型1(Benchmark simulation model No.1,BSM1).结果 表明该方法能够实时获取控制变量的优化设定值,提高了出水水质,并且有效降低了运行能耗.

Keyword ：

动态多目标粒子群优化 城市污水处理过程 多目标优化控制 知识迁徙学习 数据和知识驱动方法

Cite：

Copy from the list or Export to your reference management。

Abstract ：

一种数据-知识驱动的城市污水处理过程多目标优化控制方法，属于污水处理领域。 为了平衡能耗和出水水质，建立了数据驱动的多目标优化模型，包括能耗模型和出水水质模型，得到能耗，出水水质和控制变量的非线性关系。 同时，提出了一种基于进化知识的多目标粒子群优化算法，对硝酸盐氮和溶解氧设定点进行优化。 此外，比例积分微分(PID)控制器被设计成跟踪设定点。 从而改善出水水质，降低能耗。

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The optimal control is an effective method to reduce energy consumption for municipal wastewater treatment process. However, it is still a challenge to improve the effluent qualities and reduce energy consumption simultaneously for the municipal wastewater treatment process. To solve this problem, a data-knowledge driven multiobjective optimal control (DK-MOC) method is proposed in this paper. First, the expression relationship among effluent qualities, energy consumption and system operation state is established to obtain the operational optimal objective model. Second, a dynamic multiobjective particle swarm optimization algorithm, based on knowledge transfer learning method, is proposed to obtain the optimal set-points of control variables adaptively. Finally, the proposed DK-MOC method is applied to the benchmark simulation model No. 1 (BSM1) of the municipal wastewater treatment process. The results demonstrate that this proposed method can obtain the optimal set-points of control variables online, which not only improve the effluent qualities, but also reduce the operation energy consumption effectively. Copyright © 2021 Acta Automatica Sinica. All rights reserved.

Keyword ：

Effluent treatment Effluents Reclamation Learning systems Particle swarm optimization (PSO) Energy utilization Swarm intelligence Wastewater treatment Water quality Process control Multiobjective optimization Knowledge management

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Aggregation-induced electrochemiluminescence (AIECL) of the dichlorobis(1,10-phenanthroline)ruthenium(II) (Ru(phen)(2)Cl-2)/tri-n-propylamine (TPrA) system was systematically investigated in H2O-MeCN media. Up to a 120-fold increase in the ECL intensity was observed when the H2O fraction (v%) was changed from 30% to 70%, whereas only an approximately 5.7-fold increase in the corresponding aggregation-induced fluorescence emission was demonstrated. The gradual formation of clusters of Ru(phen)(2)Cl-2 nanoaggregates along with the increase in the H2O fraction to MeCN, which was verified by dynamic light scattering (DLS), scanning electron microscopy (SEM), and transmission electron microscopy (TEM), was believed to be responsible for the remarkable ECL enhancement. Significantly, the above-mentioned AIECL behavior was found to be very sensitive which provided an effective and novel strategy for distinguishing RNA from DNA and for differentiating different miRNAs. The present study could have a substantial impact in various research areas, such as molecular sensors, bioimaging probes, organellespecific imaging, and tumor diagnosis.

Cite：

Copy from the list or Export to your reference management。