检索结果-内蒙古大学图书馆

Neuro-dynamic Programming to Optimal Control of a Biotechnological Process

International Journal Bioautomation 2024年第4期28卷 205-220页

作者： Ilkova, Tatiana Petrov, Mitko Faculty of Engineering South-West University "Neofit Rilski" 66 Ivan Mihaylov Str. Blagoevgrad2700 Bulgaria Department Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences 105 Acad. George Bonchev Str. Sofia1113 Bulgaria

Dynamic programming (DP) is an elegant way to solve problems related to optimization and optimal control of processes. DP, however, has one major drawback, namely the "curse of dimensionality". To overcome this shortcoming, an approach called neuro-dynamic programming (NDP) has been developed. This approach solves the "curse of dimensionality" problem of DP. For this purpose, a neural network is used in NDP, which ignores the poor results of the utility criterion. In this way, the time for solving the specific task is significantly shortened. In this work, an NDP algorithm is presented for the optimal control of a fed-batch biotechnological process for the production of L-lysine by the strain Brevibacterium flavum 22LD. Application of the NDP algorithm ensures maximum productivity of the L-lysine. © 2024 by the authors.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Hybrid Sensor System for Robot Control with Nonlinear Autoregressive Network with Exogenous Inputs 20th

Hybrid Sensor System for Robot Control with Nonlinear Autore...

引用

20th International Workshop on Intuitionistic Fuzzy Sets and Generalized Nets, IWIFSGN 2022

作者： Sotirov, Sotir Ribagin, Simeon University "Prof. D-r Asen Zlatarov" Burgas Bulgaria Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Sofia Bulgaria

ISBN: (纸本)9783031450686

In this paper, nonlinear autoregressive exogenous input (NARX) neural network has been used for modeling a sensor based hybrid system for possible control of robotic devices. The signals for the model are obtained from the MyoWare surface muscle sensors and the so proposed hybrid sensor system represents a sensor-based control for various task execution and direct human-robot interaction. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

Accurate prediction of in vivo protein abundances by coupling constraint-based modelling and machine learning

引用

Metabolic Engineering 2023年 80卷 184-192页

作者： Moura Ferreira, Maurício Alexander de Wendering, Philipp Arend, Marius Batista da Silveira, Wendel Nikoloski, Zoran Department of Microbiology Federal University of Viçosa Minas Gerais Viçosa36570900 Brazil Bioinformatics Institute of Biochemistry and Biology University of Potsdam Potsdam14476 Germany Systems Biology and Mathematical Modelling Max Planck Institute of Molecular Plant Physiology Potsdam14476 Germany

Quantification of how different environmental cues affect protein allocation can provide important insights for understanding cell physiology. While absolute quantification of proteins can be obtained by resource-intensive mass-spectrometry-based technologies, prediction of protein abundances offers another way to obtain insights into protein allocation. Here we present CAMEL, a framework that couples constraint-based modelling with machine learning to predict protein abundance for any environmental condition. This is achieved by building machine learning models that leverage static features, derived from protein sequences, and condition-dependent features predicted from protein-constrained metabolic models. Our findings demonstrate that CAMEL results in excellent prediction of protein allocation in E. coli (average Pearson correlation of at least 0.9), and moderate performance in S. cerevisiae (average Pearson correlation of at least 0.5). Therefore, CAMEL outperformed contending approaches without using molecular read-outs from unseen conditions and provides a valuable tool for using protein allocation in biotechnological applications. © 2023 The Authors

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Chaotic Electromagnetic Field Optimization Algorithms

引用

International Journal Bioautomation 2024年第4期28卷 245-265页

作者： Roeva, Olympia Zoteva, Dafina Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Acad. G. Bonchev Str. bl. 105 Sofia1113 Bulgaria Department of Computer Informatics Faculty of Mathematics and Informatics Sofia University "St. Kliment Ohridski" 5 James Bourchier Blvd. Sofia1164 Bulgaria

This paper investigates the performance of various Electromagnetic Field Optimization (EFO) algorithms. Chaos maps are proposed to improve the performance of EFO algorithms. Ten chaotic maps are incorporated in EFO – Chebyshev, Circle, Gauss, Iterative, Logistic, Piecewise, Sine, Singer, Sinusoidal and Tent. To compare the performance of the constructed EFO algorithms, a case study of the identification of the model parameters of a cultivation process model is studied. An experimental data set from E. coli BL21(DE3)pPhyt109 fed-batch cultivation process is used. Based on the results of 30 runs of each EFO, some statistical and InterCriteria analyzes are performed. As a result, the best performing EFO algorithms are iterative EFO and tent chaotic map EFO. These algorithms gave the best objective value (best and mean value) and had a good distribution of results. © 2024 by the authors.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Multistep modelling and Monitoring of Bioprocesses

引用

International Journal Bioautomation 2024年第4期28卷 185-196页

作者： Lyubenova, Velislava Ignatova, Maya Kristeva, Denitsa Roeva, Olympia Department of Mechatronic Bio Technological Systems Institute of Robotics Bulgarian Academy of Science Acad. G. Bonchev Str. Bl. 2 Sofia1113 Bulgaria Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Acad. G. Bonchev Str. Bl. 105 Sofia1113 Bulgaria

A new approach is proposed for modelling and monitoring bioprocesses dynamics characterized by different metabolic states. Bioprocesses cannot be described by a single model. For this reason, three phases characterised by the bioprocess are defined – periodic, exponential, and stationary. During each phase, the process passes through one or more physiological states. Each physiological state is described by a sub-model with a different structure and parameter values. The transition of the process from one physiological state to another is carried out by switching the sub-models based on a predefined key parameter. Monitoring is performed by a cascade of software sensors using the sub-models and real-time measurement of the concentrations of the main process variables. The proposed approach was tested by modelling and monitoring the Escherichia coli phytase production process. © 2024 by the authors.

关键词： Escherichia coli

来源：评论

学校读者我要写书评

暂无评论

Generalized Net Model of Rehabilitation Algorithm for Patients with Shoulder Impingement Syndrome 20th

Generalized Net Model of Rehabilitation Algorithm for Patien...

引用

20th International Workshop on Intuitionistic Fuzzy Sets and Generalized Nets, IWIFSGN 2022

作者： Ribagin, Simeon Angelova-Popova, Gergana Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Sofia Bulgaria Department of Health and Pharmaceutical Care Medical College University "Prof. D-r Asen Zlatarov" Burgas Bulgaria

ISBN: (纸本)9783031450686

Shoulder pain related to the impingement syndrome is a common disorder and despite the growing evidence of the importance of rehabilitation, in particular active exercise physiotherapy, little data is available to guide the treatment process. The purpose of the present paper is to present an example of Generalized Nets application in orthopedics and traumatology rehabilitation and the model describes a possible algorithm protocol for rehabilitation treatment of the patients with shoulder impingement syndrome. The proposed model can be implemented in the decision making support systems, telerehabilitation platforms, optimization of the physiotherapy protocols for shoulder impingement syndrome and better rehabilitation strategies. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Physical therapy

来源：评论

学校读者我要写书评

暂无评论

Generalized Net Model of Rehabilitation Algorithm for Patients with Proximal Humeral Fracture After Surgical Treatment 2nd

Generalized Net Model of Rehabilitation Algorithm for Patien...

引用

2nd International Symposium on bioinformatics and Biomedicine, BioInfoMed 2022

作者： Ribagin, Simeon Grozeva, Antoaneta Hristov, Stoyan Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Sofia Bulgaria Department of Health and Pharmaceutical Care Medical College University "Prof. D-r Asen Zlatarov" Burgas Bulgaria University Hospital Burgas Burgas Bulgaria

ISBN: (纸本)9783031310683

The purpose of the present paper is to present an example of Generalized Nets application in orthopedics and traumatology rehabilitation. The model describes a possible algorithm protocol for rehabilitation treatment of patients with fracture of the proximal humerus and the different transitions of the model are representing respectively the different parts of the rehabilitation process. The proposed model can be implemented in the decision making support systems, telerehabilitation platforms, optimization of the physiotherapy protocols for proximal humeral fractures rehabilitation based on current ‘good practices’ and better rehabilitation strategies. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

InterCriteria Analysis of Data Obtained from Patients with Hypercholesterolemia Treated with Linoprixol 2nd

InterCriteria Analysis of Data Obtained from Patients with H...

引用

2nd International Symposium on bioinformatics and Biomedicine, BioInfoMed 2022

作者： Vassilev, Valentin Hlebarov, Hristo Ribagin, Simeon Atanassov, Krassimir University Hospital Burgas Burgas Bulgaria Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Sofia Bulgaria Department of Health and Pharmaceutical Care Medical College University "Prof. D-r Asen Zlatarov" Burgas Bulgaria

ISBN: (纸本)9783031310683

Hypercholesterolemia is one of the main factors contributing to number of diseases, leading to permanent disability and/or worldwide. Nowadays the standard treatment of high cholesterol levels is carried out by drugs known as statins. Despite their main effect they also have a number of ADRs. The purpose of the present paper is to analyze the effects of the alternative treatment of patients with hypercholesterolemia with *** the InterCriteria Analysis method. The method of InterCriteria Analysis was applied to study the dependencies between the total cholesterol, LDL and triglycerides levels obtained in a clinical trial conducted in the Vascular Surgery Clinic of University Hospital Burgas. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Crow Search Algorithm-Based Optimization of Feedforward/Feedback Controller for Fed-Batch Cultivation Process Control

Crow Search Algorithm-Based Optimization of Feedforward/Feed...

引用

Mediterranean Conference on Embedded Computing (MECO)

作者： Olympia Roeva Tsonyo Slavov Jordan Kralev Asparuh Markovski Department of Bioinformatics and Mathematical Modelling Institute of Biophysics and Biomedical Engineering Bulgarian Academy of Sciences Sofia Bulgaria Department of Systems and Control Technical University of Sofia Sofia Bulgaria

ISBN: (数字)9798331513412

ISBN: (纸本)9798331513429

In this paper, for the first time, the Crow Search Algorithm is applied to tune a nonlinear feedforward/feedback controller for fed-batch cultivation process control. The designed controller consists of a nonlinear feedforward part, a linear two-degree-of-freedom PID controller as a feedback part and an extended Kalman filter that estimates unmeasurable process variables. Based on the ten different nonlinear cultivation process models, ten controllers are tuned by optimisation. Their performance is investigated by cross-simulation experiments (each controller is simulated with each process model). In simulation, for more realistic results, the measurement delay of Flow Injection Analysis system, process and measurement noises are taken into account. The obtained results show the robustness of the developed control systems.

关键词： Biological system modeling Noise Metaheuristics Process control Control systems Robustness Biomass Noise measurement Tuning Substrates

来源：评论

学校读者我要写书评

暂无评论

InterCriteria Analysis of the Global Competitiveness Report for the Financial System EU Countries 11

InterCriteria Analysis of the Global Competitiveness Report ...

引用

11th IEEE International Conference on Intelligent Systems, IS 2022

作者： Danailova-Veleva, Slaviiana Doukovska, Lyubka Vassilev, Peter Bulgarian Academy of Sciences Institute of Information and Communication Technologies Intelligent Systems Department Sofia Bulgaria Bulgarian Academy of Sciences Institute of Biophysics and Biomedical Engineering Bioinformatics and Mathematical Modelling Department Sofia Bulgaria

ISBN: (纸本)9781665456562

In recent years, innovative techniques for data analysis and decision-making, resulting from the processing of a large database, have been increasingly used. This trend is part of the management process, for example in the field of finance, where through the application of elements of artificial intelligence, data is processed, processes are analyzed, risk is assessed and intelligent solutions are *** this paper, data from The Global competitiveness report of the World Economic Forum is processed in order to analyze the financial systems of EU Countries. The emphasis is on the data from Pillar 9 - Financial System. It consists of the indicators - Debt and Stability. These in turn include several *** analysis was carried out by applying the Intercriteria Analysis. © 2022 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：