A Method for Forecasting the Demand for Pharmaceutical Products in a Distributed Pharmacy Network Based on an Integrated Approach Using Fuzzy Logic and Neural Networks

Oglu, Alekperov Ramiz Balashirin; Kizi, Isgandarova Ilhama Tarlan

doi:10.1007/978-3-030-51156-2_116

Cited by 7 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prediction models using Machine Learning can be used as a solution in decision-making to increase the productivity of drug procurement [8]. Other studies also explain that mathematical interpretation algorithms in forecasting cases are used to deal with drug demand problems [9]. The prediction process developed based on a model from sales data can be used to predict drug demand [10].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

Yanto¹,

Arlis²,

Putra³

et al. 2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

The high demand for drugs in the last period has caused problems with drug shortages in several pharmacies. Almost all pharmacies experience the same problem, causing many people who do not to get their drug needs during the current pandemic. To overcome this, analyzing the process of predicting drug demand in the next period is necessary. The prediction process can be used as an initial solution in solving problems to see the number of drug demand numbers that will occur. This study aims to develop a predictive analysis model for drug demand using a deep learning approach and a classification model. Deep learning is an approach that does well in the case of prediction. The classification model also includes the right concept for solving the problem. The prediction and classification analysis methods include K-Means clustering, Multiple Linear Regression (MRL), Artificial Neural Network (ANN), and Decision Tree algorithms C.45. This method can provide better performance results in the prediction process to get precise and accurate output. Prediction results obtained from the learning process provide an accuracy rate of 99.99%. The output of the classification model also provides an overview of the knowledge base in the form of a decision tree. The level of classification model testing carried out gives the accuracy of the classification pattern of 97.05% so that the analytical model developed can predict future drug demand.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

Yanto¹,

Arlis²,

Putra³

et al. 2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…The design of fuzzy controllers is easier than developing a model-based controller, and it is customizable, due to one being able modify the structure, rule base, and display them as a human being would do to control a system. There are a vast number of applications of FL, such as simplified control of robots [ 10 ], control of car engines [ 11 ], cruise-control for automobiles [ 12 ], prediction systems for early recognition of earthquakes [ 13 ], anti-lock braking systems [ 14 ], renewable energy systems [ 15 ], aircraft engines [ 16 ], energy allocation [ 17 , 18 ], demand forecasting [ 19 ], predictive maintenance [ 20 ], and material handling [ 21 ], just to mention a few.…”

Section: Introductionmentioning

confidence: 99%

A PID-Type Fuzzy Logic Controller-Based Approach for Motion Control Applications

García-Martínez

Cruz-Miguel

Carrillo-Serrano

et al. 2020

Sensors

View full text Add to dashboard Cite

Motion control is widely used in industrial applications since machinery, robots, conveyor bands use smooth movements in order to reach a desired position decreasing the steady error and energy consumption. In this paper, a new Proportional-Integral-Derivative (PID) -type fuzzy logic controller (FLC) tuning strategy that is based on direct fuzzy relations is proposed in order to compute the PID constants. The motion control algorithm is composed by PID-type FLC and S-curve velocity profile, which is developed in C/C++ programming language; therefore, a license is not required to reproduce the code among embedded systems. The self-tuning controller is carried out online, it depends on error and change in error to adapt according to the system variations. The experimental results were obtained in a linear platform integrated by a direct current (DC) motor connected to an encoder to measure the position. The shaft of the motor is connected to an endless screw; a cart is placed on the screw to control its position. The rise time, overshoot, and settling time values measured in the experimentation are 0.124 s, 8.985% and 0.248 s, respectively. These results presented in part 6 demonstrate the performance of the controller, since the rise time and settling time are improved according to the state of the art. Besides, these parameters are compared with different control architectures reported in the literature. This comparison is made after applying a step input signal to the DC motor.

show abstract

“…In general, to analyze the effectiveness of marketing activities for firms, a comprehensive assessment is carried out in the following areas and criteria [2]:…”

mentioning

confidence: 99%

System of Methodical Approaches and Methods of Complex Marketing Researches in Food Enterprises

Isgandarova

2021

RS Global - IJITE

View full text Add to dashboard Cite

The methodology for assessing the quality of public service at catering firms should be based on a comparison of consumer expectations and perceptions in relation to the service process, that is, the quality coefficient is determined as the difference between perception and expectations. In this case, the quality factor can be determined both by the indicator of interest and by the enterprise as a whole. Consequently, the criteria for assessing the quality of public service at catering establishments must be formed taking into account its type and class. To obtain primary information from consumers, it is necessary to organize and conduct a sociological study. When choosing a method of sociological research, it is advisable to give preference to interviews, since this is a rather flexible method of collecting information, based on direct contact between the interviewer and the respondent. The main advantage of the interview, in comparison with the questionnaire, is the ability to control the perception and understanding of the questions by the respondent; if necessary, the interviewer can explain the questions asked, and also clarify the respondent's point of view with the help of additional questions.When conducting a sociological research by the interview method, the requirements for the formation of a questionnaire are significantly reduced. The list of questions asked to respondents should be expanded with personal questions, the purpose of which is to reflect: age, social status, average monthly income. These questions are necessary to represent the target group of consumers of public catering services.

show abstract

A Method for Forecasting the Demand for Pharmaceutical Products in a Distributed Pharmacy Network Based on an Integrated Approach Using Fuzzy Logic and Neural Networks

Cited by 7 publications

References 3 publications

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

Prediction of Drug Demand Based on Deep Learning Approach and Classification Model

A PID-Type Fuzzy Logic Controller-Based Approach for Motion Control Applications

System of Methodical Approaches and Methods of Complex Marketing Researches in Food Enterprises

Contact Info

Product

Resources

About