Pub Date : 2024-11-19DOI: 10.1016/j.rico.2024.100495
Vassilios Yfantis , Achim Wagner , Martin Ruskowski
This paper presents a benchmark study of dual decomposition-based distributed optimization algorithms applied to constraint-coupled model predictive control problems. These problems can be interpreted as multiple subsystems which are coupled through constraints on the availability of shared limited resources. In a dual decomposition-based framework the production and consumption of these resources can be coordinated by iteratively computing their prices and sharing them with the involved subsystems. Following a brief introduction to model predictive control different architectures and communication topologies for a distributed setting are presented. After decomposing the system-wide control problem into multiple subproblems by introducing dual variables, several distributed optimization algorithms, including the recently proposed quasi-Newton dual ascent algorithm, are discussed. Furthermore, an epigraph formulation of the bundle cuts as well as a line search strategy are proposed for the quasi-Newton dual ascent algorithm, which increase its numerical robustness and speed up its convergence compared to the previously used trust region. Finally, the quasi-Newton dual ascent algorithm is compared to the subgradient method, the bundle trust method and the alternating direction method of multipliers for a large number of benchmark problems. The used benchmark problems are publicly available on GitHub.
{"title":"Numerical benchmarking of dual decomposition-based optimization algorithms for distributed model predictive control","authors":"Vassilios Yfantis , Achim Wagner , Martin Ruskowski","doi":"10.1016/j.rico.2024.100495","DOIUrl":"10.1016/j.rico.2024.100495","url":null,"abstract":"<div><div>This paper presents a benchmark study of dual decomposition-based distributed optimization algorithms applied to constraint-coupled model predictive control problems. These problems can be interpreted as multiple subsystems which are coupled through constraints on the availability of shared limited resources. In a dual decomposition-based framework the production and consumption of these resources can be coordinated by iteratively computing their prices and sharing them with the involved subsystems. Following a brief introduction to model predictive control different architectures and communication topologies for a distributed setting are presented. After decomposing the system-wide control problem into multiple subproblems by introducing dual variables, several distributed optimization algorithms, including the recently proposed quasi-Newton dual ascent algorithm, are discussed. Furthermore, an epigraph formulation of the bundle cuts as well as a line search strategy are proposed for the quasi-Newton dual ascent algorithm, which increase its numerical robustness and speed up its convergence compared to the previously used trust region. Finally, the quasi-Newton dual ascent algorithm is compared to the subgradient method, the bundle trust method and the alternating direction method of multipliers for a large number of benchmark problems. The used benchmark problems are publicly available on GitHub.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100495"},"PeriodicalIF":0.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-19DOI: 10.1016/j.rico.2024.100496
K. Ramalakshmi , B. Sundara Vadivoo , Kottakkaran Sooppy Nisar , Suliman Alsaeed
This study examines the mathematical model of Hepatitis B Virus (HBV) dynamics, focusing on its various stages of infection, including acute and chronic phases, and transmission pathways. By utilizing mathematical modeling and fractional calculus techniques with the -Hilfer operator, we analyze the epidemic’s behavior. The research proposes control strategies, such as treatment and vaccination, aimed at reducing both acute and chronic infections. To achieve optimal control, we employ Pontryagin’s Maximum Principle. Through simulations, we demonstrate the effectiveness of our approach using the Non-Standard Two-Step Lagrange Interpolation Method (NS2LIM), supported by numerical findings and graphical representations. Additionally, we identify two control variables to minimize the populations of acute and chronic infections while enhancing recovery rates.
本研究探讨了乙型肝炎病毒（HBV）动态的数学模型，重点是其各个感染阶段，包括急性期和慢性期，以及传播途径。通过利用数学建模和带有 Θ-Hilfer 算子的分数微积分技术，我们分析了流行病的行为。研究提出了治疗和疫苗接种等控制策略，旨在减少急性和慢性感染。为了实现最优控制，我们采用了庞特里亚金最大原则（Pontryagin's Maximum Principle）。通过模拟，我们利用非标准两步拉格朗日插值法（NS2LIM）证明了我们方法的有效性，并辅以数值结果和图形表示。此外，我们还确定了两个控制变量，以尽量减少急性和慢性感染人群，同时提高恢复率。
{"title":"The Θ-Hilfer fractional order model for the optimal control of the dynamics of Hepatitis B virus transmission","authors":"K. Ramalakshmi , B. Sundara Vadivoo , Kottakkaran Sooppy Nisar , Suliman Alsaeed","doi":"10.1016/j.rico.2024.100496","DOIUrl":"10.1016/j.rico.2024.100496","url":null,"abstract":"<div><div>This study examines the mathematical model of Hepatitis B Virus (HBV) dynamics, focusing on its various stages of infection, including acute and chronic phases, and transmission pathways. By utilizing mathematical modeling and fractional calculus techniques with the <span><math><mi>Θ</mi></math></span>-Hilfer operator, we analyze the epidemic’s behavior. The research proposes control strategies, such as treatment and vaccination, aimed at reducing both acute and chronic infections. To achieve optimal control, we employ Pontryagin’s Maximum Principle. Through simulations, we demonstrate the effectiveness of our approach using the Non-Standard Two-Step Lagrange Interpolation Method (NS2LIM), supported by numerical findings and graphical representations. Additionally, we identify two control variables to minimize the populations of acute and chronic infections while enhancing recovery rates.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100496"},"PeriodicalIF":0.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-19DOI: 10.1016/j.rico.2024.100491
Ravi Sekhar , Sharnil Pandya , Pritesh Shah , Hemant Ghayvat , Deepak Sharma , Matthias Renz , Deep Shah , Adeeth Jagdale , Devansh Hukmani , Santosh Saxena , Neeraj Kumar
Acoustics based smart condition monitoring is a viable alternative to mechanical vibrations or image-capture based predictive maintenance methods. In this study, a texture analysis based transfer learning methodology was applied to classify tool wear based on the noise generated during mild steel machining. The machining acoustics were converted to spectrogram images and transfer learning was applied for their classification into high/medium/low tool wear using four pre-trained deep learning models (SqueezeNet, ResNet50, InceptionV3, GoogLeNet). Moreover, three optimizers (RMSPROP, ADAM, SGDM) were applied to each of the deep learning models to enhance classification accuracies. Primary results indicate that the InceptionV3-RMSPROP obtained the highest testing accuracy of 87.50%, followed by the SqueezeNet-RMSPROP and ResNet50-SGDM at 75.00% and 62.50% respectively. However, SqueezeNet-RMSPROP was determined to be more desirable from a practical machining quality and safety perspective, owing to its greater recall value for the highest tool wear class. The proposed acoustics-texture extraction-transfer learning approach is especially suitable for cost effective tool wear condition monitoring involving limited datasets.
{"title":"Noise robust classification of carbide tool wear in machining mild steel using texture extraction based transfer learning approach for predictive maintenance","authors":"Ravi Sekhar , Sharnil Pandya , Pritesh Shah , Hemant Ghayvat , Deepak Sharma , Matthias Renz , Deep Shah , Adeeth Jagdale , Devansh Hukmani , Santosh Saxena , Neeraj Kumar","doi":"10.1016/j.rico.2024.100491","DOIUrl":"10.1016/j.rico.2024.100491","url":null,"abstract":"<div><div>Acoustics based smart condition monitoring is a viable alternative to mechanical vibrations or image-capture based predictive maintenance methods. In this study, a texture analysis based transfer learning methodology was applied to classify tool wear based on the noise generated during mild steel machining. The machining acoustics were converted to spectrogram images and transfer learning was applied for their classification into high/medium/low tool wear using four pre-trained deep learning models (SqueezeNet, ResNet50, InceptionV3, GoogLeNet). Moreover, three optimizers (RMSPROP, ADAM, SGDM) were applied to each of the deep learning models to enhance classification accuracies. Primary results indicate that the InceptionV3-RMSPROP obtained the highest testing accuracy of 87.50%, followed by the SqueezeNet-RMSPROP and ResNet50-SGDM at 75.00% and 62.50% respectively. However, SqueezeNet-RMSPROP was determined to be more desirable from a practical machining quality and safety perspective, owing to its greater recall value for the highest tool wear class. The proposed acoustics-texture extraction-transfer learning approach is especially suitable for cost effective tool wear condition monitoring involving limited datasets.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100491"},"PeriodicalIF":0.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-17DOI: 10.1016/j.rico.2024.100497
Yuanshan Liu, Yude Xia
A novel approach is proposed for designing control strategies for time-varying cyber–physical systems (CPSs) with unknown dynamics, eliminating the need for system identification. Combining with the dynamic-triggered strategies (DTSs), the closed-loop system is parameterized using matrices that are depended on data obtained from a collection of input-state trajectories gathered offline. Additionally, the problem of data-driven optimization control is elegantly resolved through the utilization of classical linear quadratic regulator (LQR) technology, showcasing a remarkable innovation by obviating the necessity for the specific mathematical model of CPSs proposed in this paper. A numerical illustration is provided to illustrate these findings.
{"title":"Optimization control of time-varying cyber–physical systems via dynamic-triggered strategies","authors":"Yuanshan Liu, Yude Xia","doi":"10.1016/j.rico.2024.100497","DOIUrl":"10.1016/j.rico.2024.100497","url":null,"abstract":"<div><div>A novel approach is proposed for designing control strategies for time-varying cyber–physical systems (CPSs) with unknown dynamics, eliminating the need for system identification. Combining with the dynamic-triggered strategies (DTSs), the closed-loop system is parameterized using matrices that are depended on data obtained from a collection of input-state trajectories gathered offline. Additionally, the problem of data-driven optimization control is elegantly resolved through the utilization of classical linear quadratic regulator (LQR) technology, showcasing a remarkable innovation by obviating the necessity for the specific mathematical model of CPSs proposed in this paper. A numerical illustration is provided to illustrate these findings.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100497"},"PeriodicalIF":0.0,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.rico.2024.100490
Pulak Kundu, Uzzwal Kumar Mallick
Because of its high nutritional value and easy availability, guava fruit has become more popular as a crop in tropical regions in recent decades. Unfortunately, its cultivation faces multifaceted challenges, with increasing the guava borer due to global warming posing a significant threat to crop yield, while the cost of pesticides adds to the economic burden on farmers. To overcome this difficulty, an integrated cultivation method has been devised to simultaneously cultivate guava and tuberose flowers for the purpose of biological pest management, while also earning money through the sale of the flowers to support the integrated agricultural plan. The present mathematical modeling study has focused on the optimal control problem using the strategy of spraying pesticides and flower harvesting, to achieve the highest possible profit. Characterization of the proposed optimal control was then carried out using Pontryagin’s maximum principle, where the objective of our farming would be higher when optimal management of our strategies would be provided compared to other scenarios. To find the most efficient and least expensive approach, cost-effectiveness analysis has been performed. According to the findings, an optimal strategy for harvesting flowers is the most economical and efficient way to increase the amount of earnings from this integrated farming. However, the results of this study can help the farmers in developing beneficial strategies to gain maximum profit by reducing the cost.
{"title":"Optimal control analysis of a mathematical model for guava nutrients in an integrated farming with cost-effectiveness","authors":"Pulak Kundu, Uzzwal Kumar Mallick","doi":"10.1016/j.rico.2024.100490","DOIUrl":"10.1016/j.rico.2024.100490","url":null,"abstract":"<div><div>Because of its high nutritional value and easy availability, guava fruit has become more popular as a crop in tropical regions in recent decades. Unfortunately, its cultivation faces multifaceted challenges, with increasing the guava borer due to global warming posing a significant threat to crop yield, while the cost of pesticides adds to the economic burden on farmers. To overcome this difficulty, an integrated cultivation method has been devised to simultaneously cultivate guava and tuberose flowers for the purpose of biological pest management, while also earning money through the sale of the flowers to support the integrated agricultural plan. The present mathematical modeling study has focused on the optimal control problem using the strategy of spraying pesticides and flower harvesting, to achieve the highest possible profit. Characterization of the proposed optimal control was then carried out using Pontryagin’s maximum principle, where the objective of our farming would be higher when optimal management of our strategies would be provided compared to other scenarios. To find the most efficient and least expensive approach, cost-effectiveness analysis has been performed. According to the findings, an optimal strategy for harvesting flowers is the most economical and efficient way to increase the amount of earnings from this integrated farming. However, the results of this study can help the farmers in developing beneficial strategies to gain maximum profit by reducing the cost.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100490"},"PeriodicalIF":0.0,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1016/j.rico.2024.100488
Redouane Chaibi , Rachid EL Bachtiri , Karima El Hammoumi , Mohamed Yagoubi
To improve the efficiency and performance of a photovoltaic system (PV) an observer-based fuzzy controller design methodology is provided in the study. The desired controller is achieved by employing a combination of linear matrix inequalities (LMIs). The system consists of a photovoltaic generator (PVG) connected to a boost converter. A battery is linked to the boost converter to stock additional energy for further use. A fuzzy controller based on a T–S fuzzy type observer that guarantees a predefined performance is suggested to achieve maximum power point tracking (MPPT) even under changing weather conditions. An optimal trajectory should be tracked to ensure maximum power operation. For this aim, a specific reference fuzzy model is proposed to create the aimed trajectories. Using this method, the system dynamics are precisely reproduced over a large range of operations. The whole T–S fuzzy methodology, suggested in this paper, aims to ensure the most efficient energy recovery to recharge a battery under partially shaded conditions, resulting in high system efficiency. The proposed method is simulated with MATLAB /SIMULINK and the simulation results, with realistic reference trajectories, are driven while taking into account climate variations. The analysis of these simulations, along with a comparison with two other commonly used approaches, led to the conclusion that the suggested strategy succeeded in reducing the tracking time, as well as eliminating the oscillation that often occurs around maximum power point (MPP).
{"title":"Observer-based fuzzy T–S control with an estimation error guarantee for MPPT of a photovoltaic battery charger in partial shade conditions","authors":"Redouane Chaibi , Rachid EL Bachtiri , Karima El Hammoumi , Mohamed Yagoubi","doi":"10.1016/j.rico.2024.100488","DOIUrl":"10.1016/j.rico.2024.100488","url":null,"abstract":"<div><div>To improve the efficiency and performance of a photovoltaic system (PV) an observer-based fuzzy controller design methodology is provided in the study. The desired controller is achieved by employing a combination of linear matrix inequalities (LMIs). The system consists of a photovoltaic generator (PVG) connected to a boost converter. A battery is linked to the boost converter to stock additional energy for further use. A fuzzy controller based on a T–S fuzzy type observer that guarantees a predefined <span><math><msub><mrow><mi>L</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span> performance is suggested to achieve maximum power point tracking (MPPT) even under changing weather conditions. An optimal trajectory should be tracked to ensure maximum power operation. For this aim, a specific reference fuzzy model is proposed to create the aimed trajectories. Using this method, the system dynamics are precisely reproduced over a large range of operations. The whole T–S fuzzy methodology, suggested in this paper, aims to ensure the most efficient energy recovery to recharge a battery under partially shaded conditions, resulting in high system efficiency. The proposed method is simulated with MATLAB<!--> <!-->/SIMULINK <!--> <!-->and the simulation results, with realistic reference trajectories, are driven while taking into account climate variations. The analysis of these simulations, along with a comparison with two other commonly used approaches, led to the conclusion that the suggested strategy succeeded in reducing the tracking time, as well as eliminating the oscillation that often occurs around maximum power point (MPP).</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100488"},"PeriodicalIF":0.0,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-10DOI: 10.1016/j.rico.2024.100492
B. Janani , K. Ambika , S. Jegan
We embarked on a comprehensive exploration of a single server queueing design, with a specific focus on handling soft failures. Soft failures refer to instances where customers do not need to be removed but rather need to wait for the server to be reactivated. These occurrences can happen at any time during the server's operation. When a soft failure occurs, the process automatically initiates a repair action, which we will refer to as the self-healing time. This self-healing time is relatively short, as the server possesses a remarkable restoration capability. Once the repair is complete, the server resumes its service provision and resumes normal operations. Moreover, during periods of prolonged idleness, the server can enter a dormant state, akin to a vacation mode. This dormant state is triggered when the server awaits the accumulation of N or more users. Once the threshold is reached, the server transitions into a busy state and resumes its normal operations. This study represents the pioneering integration of soft failures with the N policy, marking the first of its kind in this field. Additionally, we provide explicit expressions for the transient probabilities of the model, employing generating function methodology and Laplace transform techniques. Furthermore, we include performance measures and a numerical component to underscore the significance of the model's parameters.
我们开始对单服务器队列设计进行全面探索，重点是处理软故障。软故障指的是客户不需要被移走，而是需要等待服务器重新激活的情况。这种情况可能在服务器运行期间的任何时候发生。软故障发生时，进程会自动启动修复操作，我们将其称为自愈时间。自愈时间相对较短，因为服务器具有出色的修复能力。一旦修复完成，服务器就会重新开始提供服务，恢复正常运行。此外，在长时间闲置期间，服务器可以进入休眠状态，类似于度假模式。当服务器等待累积 N 个或更多用户时，就会触发休眠状态。一旦达到阈值，服务器就会转入繁忙状态，恢复正常运行。这项研究开创性地将软故障与 N 策略整合在一起，在该领域尚属首次。此外，我们还利用生成函数方法和拉普拉斯变换技术，为模型的瞬态概率提供了明确的表达式。此外，我们还包括性能测量和数值部分，以强调模型参数的重要性。
{"title":"Implementing self-healing N-policy queueing models and their impact on IoT design applications","authors":"B. Janani , K. Ambika , S. Jegan","doi":"10.1016/j.rico.2024.100492","DOIUrl":"10.1016/j.rico.2024.100492","url":null,"abstract":"<div><div>We embarked on a comprehensive exploration of a single server queueing design, with a specific focus on handling soft failures. Soft failures refer to instances where customers do not need to be removed but rather need to wait for the server to be reactivated. These occurrences can happen at any time during the server's operation. When a soft failure occurs, the process automatically initiates a repair action, which we will refer to as the self-healing time. This self-healing time is relatively short, as the server possesses a remarkable restoration capability. Once the repair is complete, the server resumes its service provision and resumes normal operations. Moreover, during periods of prolonged idleness, the server can enter a dormant state, akin to a vacation mode. This dormant state is triggered when the server awaits the accumulation of N or more users. Once the threshold is reached, the server transitions into a busy state and resumes its normal operations. This study represents the pioneering integration of soft failures with the N policy, marking the first of its kind in this field. Additionally, we provide explicit expressions for the transient probabilities of the model, employing generating function methodology and Laplace transform techniques. Furthermore, we include performance measures and a numerical component to underscore the significance of the model's parameters.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100492"},"PeriodicalIF":0.0,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Several intuitionistic fuzzy logic approaches have been used for the diagnosis of COVID-19 patients. We have developed a fuzzy rule base system for the detection of COVID-19 patients. In this study, we have considered six major parameters based symmetric/asymmetric, linear/non-linear hexagonal intuitionistic fuzzy numbers (HIFN) for the input-output factors of the problem. In real-life diagnosis problems, such as assessing COVID-19 symptoms, applying symmetric and asymmetric, linear and non-linear hexagonal intuitionistic fuzzy numbers allows for a more accurate representation of patient conditions. Centre of area method is used for the defuzzied value of the hexagonal intuitionistic fuzzy parameters. HIFN are used because they provide a detailed representation of uncertainty, incorporating both membership and non-membership degrees through six parameters. This flexibility allows for nuanced modelling of real-world scenarios, such as medical diagnoses, where data often includes ambiguity. Then the HIFN approach is used for obtaining the compromising and superlative solution in the diagnostic process of COVID-19 patients. To figure out the adaptability of the proposed HIFN based technique, a comparative study is also introduced. The originality, limitations, future aspects and advantages of using this HIFN based technique is also discussed in this article.
{"title":"A review of fuzzy logic analysis in COVID-19 pandemic and a new technique through extended hexagonal intuitionistic fuzzy number in analysis of COVID-19","authors":"Laxmi Rathour , Vinay Singh , M.K. Sharma , Nitesh Dhiman , Vishnu Narayan Mishra","doi":"10.1016/j.rico.2024.100498","DOIUrl":"10.1016/j.rico.2024.100498","url":null,"abstract":"<div><div>Several intuitionistic fuzzy logic approaches have been used for the diagnosis of COVID-19 patients. We have developed a fuzzy rule base system for the detection of COVID-19 patients. In this study, we have considered six major parameters based symmetric/asymmetric, linear/non-linear hexagonal intuitionistic fuzzy numbers (HIFN) for the input-output factors of the problem. In real-life diagnosis problems, such as assessing COVID-19 symptoms, applying symmetric and asymmetric, linear and non-linear hexagonal intuitionistic fuzzy numbers allows for a more accurate representation of patient conditions. Centre of area method is used for the defuzzied value of the hexagonal intuitionistic fuzzy parameters. HIFN are used because they provide a detailed representation of uncertainty, incorporating both membership and non-membership degrees through six parameters. This flexibility allows for nuanced modelling of real-world scenarios, such as medical diagnoses, where data often includes ambiguity. Then the HIFN approach is used for obtaining the compromising and superlative solution in the diagnostic process of COVID-19 patients. To figure out the adaptability of the proposed HIFN based technique, a comparative study is also introduced. The originality, limitations, future aspects and advantages of using this HIFN based technique is also discussed in this article.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100498"},"PeriodicalIF":0.0,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-08DOI: 10.1016/j.rico.2024.100489
Abdelouafi Boukhris, Antari Jilali, Abderrahmane Sadiq
In the domain of efficient management of resources and ensuring nutritional consistency, accuracy in predicting crop yields becomes crucial. The advancement of artificial intelligence techniques, synchronized with satellite imagery, has emerged as a potent approach for forecasting crop yields in modern times. We used two types of data: spatial data and temporal data. Spatial data are gathered from satellite imagery and processed using ArcGIS to extract data about crops based on several indices like NDVI and NWDI. Temporal data are gathered from agricultural sensors such as temperature sensors, rainfall sensor, precipitation sensor and soil moisture sensor. In our case we used Sentinel 2 satellite to extract vegetation indices. We have used IoT systems, especially Raspberry Pi B+ to collect and process data coming from sensors. All data collected are then stored into a NoSQL server to be analysed and processed. Several machine learning and deep learning algorithms have been used for the processing of crop recommendation system, such as logistic regression, KNN, decision tree, support vector machine, LSTM, and Bi-LSTM through the collected dataset. We used GRU deep learning model for the best performance, the RMSE and R2 for this model was 0.00036 and 0.99 respectively.
The main contribution of our paper is the development of a new system that can predict several crop yields, such as wheat, maize, etc., using IoT, satellite imagery for spatial data and the use of sensors for temporal data. We are the first paper that has combined spatial data and temporal data to predict crop yield based on deep learning algorithms, unlike other works that uses only remote sensing data or temporal data. We created an E-monitoring crop yield prediction system that helps farmers track all information about crops and show the result of prediction in a mobile application. This system helps farmers with more efficient decision making to enhance crop production. The main production regions of wheat in Morocco are in the rainfed areas of the plains and plateaus of Chaouia, Abda, Haouz, Tadla, Gharb and Saïs. We studied three main regions well known for wheat production which are Rabat-Salé, Fez-Meknes, Casablanca-Settat.
{"title":"Satellite imagery, big data, IoT and deep learning techniques for wheat yield prediction in Morocco","authors":"Abdelouafi Boukhris, Antari Jilali, Abderrahmane Sadiq","doi":"10.1016/j.rico.2024.100489","DOIUrl":"10.1016/j.rico.2024.100489","url":null,"abstract":"<div><div>In the domain of efficient management of resources and ensuring nutritional consistency, accuracy in predicting crop yields becomes crucial. The advancement of artificial intelligence techniques, synchronized with satellite imagery, has emerged as a potent approach for forecasting crop yields in modern times. We used two types of data: spatial data and temporal data. Spatial data are gathered from satellite imagery and processed using ArcGIS to extract data about crops based on several indices like NDVI and NWDI. Temporal data are gathered from agricultural sensors such as temperature sensors, rainfall sensor, precipitation sensor and soil moisture sensor. In our case we used Sentinel 2 satellite to extract vegetation indices. We have used IoT systems, especially Raspberry Pi <em>B</em>+ to collect and process data coming from sensors. All data collected are then stored into a NoSQL server to be analysed and processed. Several machine learning and deep learning algorithms have been used for the processing of crop recommendation system, such as logistic regression, KNN, decision tree, support vector machine, LSTM, and Bi-LSTM through the collected dataset. We used GRU deep learning model for the best performance, the RMSE and R<sup>2</sup> for this model was 0.00036 and 0.99 respectively.</div><div>The main contribution of our paper is the development of a new system that can predict several crop yields, such as wheat, maize, etc., using IoT, satellite imagery for spatial data and the use of sensors for temporal data. We are the first paper that has combined spatial data and temporal data to predict crop yield based on deep learning algorithms, unlike other works that uses only remote sensing data or temporal data. We created an E-monitoring crop yield prediction system that helps farmers track all information about crops and show the result of prediction in a mobile application. This system helps farmers with more efficient decision making to enhance crop production. The main production regions of wheat in Morocco are in the rainfed areas of the plains and plateaus of Chaouia, Abda, Haouz, Tadla, Gharb and Saïs. We studied three main regions well known for wheat production which are Rabat-Salé, Fez-Meknes, Casablanca-Settat.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100489"},"PeriodicalIF":0.0,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-26DOI: 10.1016/j.rico.2024.100487
Marzia Ahmed , Mohd Herwan Sulaiman , Md. Maruf Hassan , Md. Atikur Rahaman , Masuk Abdullah
Mathematical models of Barnacle Mating Optimization (BMO) are based on observations of real-world barnacle mating behaviors such as sperm casting and self-fertilization. Nevertheless, BMO considers penis length to produce new offspring through pseudo-copulated mating behavior, with no constraints like strong wave motion, food availability, or wind direction considered. Exploration and exploitation are two crucial optimization stages as we implement the constrained BMO. They are informed by models of navigational sperm casting properties, food availability, food attractiveness, wind direction, and intertidal zone wave movement experienced by barnacles during mating. We will later integrate opposition-based learning (OBL) with constrained BMO (C-BMO) to improve its exploratory behavior while retaining a quick convergence rate. Rather than opposing all barnacle dimensions, we just opposed those that went over the border. In addition to increasing efficiency by cutting down on wasted time spent exploring, this also increases the likelihood of stumbling onto optimal solutions. After that, it is put through its paces in a real-world case study, where it proves to be superior to the most cutting-edge algorithms available.
{"title":"Selective opposition based constrained barnacle mating optimization: Theory and applications","authors":"Marzia Ahmed , Mohd Herwan Sulaiman , Md. Maruf Hassan , Md. Atikur Rahaman , Masuk Abdullah","doi":"10.1016/j.rico.2024.100487","DOIUrl":"10.1016/j.rico.2024.100487","url":null,"abstract":"<div><div>Mathematical models of Barnacle Mating Optimization (BMO) are based on observations of real-world barnacle mating behaviors such as sperm casting and self-fertilization. Nevertheless, BMO considers penis length to produce new offspring through pseudo-copulated mating behavior, with no constraints like strong wave motion, food availability, or wind direction considered. Exploration and exploitation are two crucial optimization stages as we implement the constrained BMO. They are informed by models of navigational sperm casting properties, food availability, food attractiveness, wind direction, and intertidal zone wave movement experienced by barnacles during mating. We will later integrate opposition-based learning (OBL) with constrained BMO (C-BMO) to improve its exploratory behavior while retaining a quick convergence rate. Rather than opposing all barnacle dimensions, we just opposed those that went over the border. In addition to increasing efficiency by cutting down on wasted time spent exploring, this also increases the likelihood of stumbling onto optimal solutions. After that, it is put through its paces in a real-world case study, where it proves to be superior to the most cutting-edge algorithms available.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"17 ","pages":"Article 100487"},"PeriodicalIF":0.0,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号