Aiming at the problem that the training time of federated learning(FL) deep neural network is very long or not feasible,this paper presents an efficient federated learning and training *** framework consists of two pa...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
Aiming at the problem that the training time of federated learning(FL) deep neural network is very long or not feasible,this paper presents an efficient federated learning and training *** framework consists of two parts:distillation and coupled gradient algorithm,which can reduce the computational cost,speed up the training process of federated learning and save computational *** experiments were carried out using an open data set(mnist),and the results show that the framework can guarantee the learning performance and control the training cost well.
The Internet of Things(IOT) technology collects real-time data from material management, equipment status, production process integration, process parameters and other accurate traceability analysis, obtains the infor...
详细信息
There has been increasing interest in and demand for relevant datasets for machine learning-based anomaly detection research in academia and industry. The industrial control system (ICS) has become larger and more com...
详细信息
ISBN:
(纸本)9781450396844
There has been increasing interest in and demand for relevant datasets for machine learning-based anomaly detection research in academia and industry. The industrial control system (ICS) has become larger and more complex, and it is difficult for humans to understand the configuration and operation of the system. Normal and attack scenario plans based on partial knowledge are inevitably biased, and insufficient data annotations limit the performance verification. It is practically difficult to manually identify all tags used for system monitoring and control and their causal relationships. Therefore, we propose a method to generate a data flow graph from processcontrol information such as input/output tags, controlprocesses, and various control parameter values extracted from the database of the control system. It will be the basis for systematic scenario composition and provide information for the analysis of cause and ripple effects when the state of a specific point (control device, sensor, actuator, etc.) is changed. We applied the proposed method to a HAI testbed and confirmed its feasibility by using it to develop a dataset.
This paper presents a novel approach for automated fluid resuscitation by modeling hemodynamics with a machine learning method and controlling it with a model predictive control (MPC) algorithm. The modeling framework...
详细信息
ISBN:
(数字)9798350351552
ISBN:
(纸本)9798350351569
This paper presents a novel approach for automated fluid resuscitation by modeling hemodynamics with a machine learning method and controlling it with a model predictive control (MPC) algorithm. The modeling framework, called the robust nonlinear state-space modeling (RNSSM), uses variational autoencoders to predict hemodynamic responses from limited and noisy critical care data during hemorrhage resuscitation. The MPC controller, designed for the RNSSM models, leverages its predictive capabilities for precise control of fluid dosages in resuscitation. Simulation results demonstrate the potential of this approach in improving the safety and efficacy of fluid resuscitation in critical care settings.
This paper presents a run-to-run (R2R) controller for mechanical serial sectioning (MSS). MSS is a destructive material analysisprocess which repeatedly removes a thin layer of material and images the exposed surface...
详细信息
ISBN:
(数字)9781665473385
ISBN:
(纸本)9781665473385
This paper presents a run-to-run (R2R) controller for mechanical serial sectioning (MSS). MSS is a destructive material analysisprocess which repeatedly removes a thin layer of material and images the exposed surface. The images are then used to gain insight into the material properties and often to construct a 3-dimensional reconstruction of the material sample. Currently, an experience human operator selects the parameters of the MSS to achieve the desired thickness. The proposed R2R controller will automate this process while improving the precision of the material removal. The proposed R2R controller solves an optimization problem designed to minimize the variance of the material removal subject to achieving the expected target removal. This optimization problem was embedded in an R2R framework to provide iterative feedback for disturbance rejection and convergence to the target removal amount. Since an analytic model of the MSS system is unavailable, we adopted a data-driven approach to synthesize our R2R controller from historical data. The proposed R2R controller is demonstrated through simulations. Future work will empirically demonstrate the proposed R2R through experiments with a real MSS system.
The paper is devoted to the process of constructing infographic models for visualizing the results of analysis in BI-systems. The subject of research is the regularities of the choice of data visualization tools for a...
详细信息
ISBN:
(数字)9798331532024
ISBN:
(纸本)9798331532031
The paper is devoted to the process of constructing infographic models for visualizing the results of analysis in BI-systems. The subject of research is the regularities of the choice of data visualization tools for an analytical query depending on the structure and properties of the data set using the Multiforms platform as an example. A formal description of the dataset data and metadata obtained as a result of executing a user request to a global analytical model on the Multiforms platform allows us to set a task of developing a new approach to the visualization of datasets that provides an informed choice of chart type, automatic determination of axes and displayed values. Based on the study of the visual components of the DevExteme library, it was possible to develop a general algorithm for native user support when choosing a diagram that best reflects the contents of the data. The considered examples illustrate the operation of the algorithm and make sure that the recommended ways of presenting data correspond to the structure of the dataset and display the content in the appropriate way.
Hospitals currently face numerous challenges in managing their pharmacy operations efficiently. While Business process Reengineering (BPR) has been proposed as a solution, its implementation in healthcare is more comp...
详细信息
Hospitals currently face numerous challenges in managing their pharmacy operations efficiently. While Business process Reengineering (BPR) has been proposed as a solution, its implementation in healthcare is more complex than in other industries. Healthcare professionals often struggle to identify problems and resist change. Simulation modeling is a technique that can visually present issues and facilitate user acceptance of changes. This paper systematically explores the application of discrete event simulation (DES) modeling in hospital pharmacy management. The specific problem of inefficient inventory control policies was analyzed and simulated using primary and secondary data from a tertiary care hospital case study in Thailand, focusing on a fast-moving drug called "Tear Natural Free (TNF)”. The simulation revealed the current inefficient performance, highlighting various phenomena such as demand characteristics, inventory levels, and stock-outs in each pharmacy room. The simulation outputs were utilized to identify alternative scenarios for further analysis of the effects of changing the business process. The most suitable forecasting technique and inventory replenishment policy for this type of item were determined to be Croston’s method and continuous review order-point, order-up-to-level (s, S) or min-max policy, respectively. Simulation modeling can serve as a valuable tool in identifying problems and improving business processes in hospital pharmacy management.
As technology advances and cyber crime rates rise, companies are facing threats such as hacker attacks, cyber fraud, and theft of property, making the practical work, its process, and the verification of digital foren...
详细信息
As the maturity and complexity of wind energy systems increase, the operation of wind turbines in wind farms needs to be adjustable in order to provide flexibility to the grid operators and optimize operations through...
详细信息
As the maturity and complexity of wind energy systems increase, the operation of wind turbines in wind farms needs to be adjustable in order to provide flexibility to the grid operators and optimize operations through wind farm control. An important aspect of this is monitoring and managing the structural reliability of the wind turbines in terms of fatigue loading. Additionally, in order to perform optimization, uncertainty analyses, condition monitoring, and other tasks, fast and accurate models of the turbine response are required. To address these challenges, we present the controller tuning and surrogate modeling for a wind turbine that is able to vary its power level in both down-regulation and power-boosting modes, as well as reducing loads with an individual blade control loop. Two methods to derive the setpoints for down-regulation are discussed and implemented. The response of the turbine, in terms of loads, power, and other metrics, for relevant operating conditions and for all control modes is captured by a data-driven surrogate model based on aeroelastic simulations following two regression approaches: a spline-based interpolation and a Gaussian process regression model. The uncertainty of the surrogate models is quantified, showing a good agreement with the simulation with a mean absolute error lower than 4% for all quantities considered. Based on the surrogate model, the aeroelastic response of the entire wind turbine for the different control modes and their combination is analyzed to shed light on the implications of the control strategies on the fatigue loading of the various components.
Metal additive manufacturing (AM) has recently attracted attention due to its potential for batch/mass production of metal parts. This process, however, currently suffers from problems including low productivity, inco...
详细信息
ISBN:
(纸本)9780791886236
Metal additive manufacturing (AM) has recently attracted attention due to its potential for batch/mass production of metal parts. This process, however, currently suffers from problems including low productivity, inconsistency in the properties of the printed parts, and defects such as lack of fusion, keyholing, and un-melted powders. Finite Element (FE) modeling cannot accurately model the metal AM process and has a high computational cost. Empirical models based on experiments are time- consuming and expensive. This paper improves a previously developed framework that takes advantages of both empirical and FE models. The validity and accuracy of the metamodel developed in the previous framework depend on the initial assumption of parameter uncertainties. This causes a problem when the assumed uncertainties are far from the actual values. The proposed framework introduces an iterative calibration process to overcome this limitation. In addition, the u_pooling metric used as the calibration metric in the previous framework is found not as good as the second- order statistical momentbased metric (SMM), after comparing several calibration metrics. The proposed framework is then applied to a fourvariable porosity modeling problem. The obtained model is more accurate than using other approaches with only 10 available experimental data points for calibration and validation.
暂无评论