Fuzzy Inference System Algorithm Research Articles

Design of intelligent decision support system for supply chain sustainability assessment

The objective of this research is to develop an intelligent decision support system (IDSS) that can aid decision-makers in enhancing the performance and sustainability of the sugarcane agroindustry's supply chain. A case study focusing on a sugarcane agroindustry supply chain was proposed. The IDSS was developed using the waterfall approach, which follows the system development life cycle (SDLC) and employed an object-oriented programming technique. The outcome of this study is a prototype of the IDSS, consisting of a database, model base, and knowledge-based management system configuration. To evaluate the sustainability of the supply chain, a fuzzy inference system and an adaptive fuzzy inference system algorithm were utilized. Through verification and validation, it was determined that the IDSS prototype has the potential to be implemented in real-world scenarios, as long as certain assumptions related to the model are taken into consideration.

Internet of things implementation and analysis of fuzzy Tsukamoto in prototype irrigation of rice

<span lang="EN-US">This research raises the topic of modern technology in the field of rice fields. The problem in this research is determining the fuzzy inference system algorithm for electronic engineering. The prototype was built by Raspberry Pi and python-based to the internet of things. The objective of this research is to design a new model for the rice field monitoring/control system and display every condition based on the internet of things. So that the hypothesis of this research can answer the phenomena that occur in rice fields, including drought problems, maintained plant conditions. The test results showed that irrigation control automatically runs optimally by scheduling, automatic irrigation control of water pH degree value detection analyzed by fuzzy Tsukamoto method at Z=3.5 defuzzification value for low and high irrigation control, and Z value=1.83 for normal irrigation control. Furthermore, the scheduling of spraying liquid fertilizer obtained the results of duration for 60 min in accordance with the needs of fertilizer dose. Lastly, for monitoring data on the website successfully accessed anywhere from the use of hosting servers and domains. Finally, it can be concluded that fuzzy Tsukamoto's algorithm is appropriate to be applied to the modern rice field system.</span>

Automated Ultraviolet C Light Mobile Robot for Room Sterilization and Disinfection

The number of COVID-19 cases in Indonesia has increased significantly of late. Therefore, isolation rooms are needed in hospitals for patient treatment Room sterilization and disinfection are strictly required as it is mandatory to protect the medical personnel. Chemical and physical methods can be used for sterilization and disinfection. Of these, the ultraviolet C (UVC) light method is the best because it has no residual. Even though UVC light is hazardous for humans' skin and eyes, such hazard can be avoided by eliminating human operators during usage. Thus, we developed a mobile robot with a UVC light system installed at the top and bottom to emit UVC light We called this robot the Automated UVC Light Mobile Robot (AUMR). The AUMR can be operated automatically as it has a magnetic line sensor and employs a fuzzy inference system algorithm for its movement. The experiment showed that UVC light has good sterilization and disinfection performance in three room types: positive-pressure rooms, negative-pressure rooms, and standard public rooms.

Fountains Height Measurement Accuracy With Mamdani Fuzzy Inference System Algorithm

Fountains can be found in gardens or offices. The fountain has several patterns for each activation. The pattern height produced by the fountain greatly affects the beauty of a garden. The purpose of this research is to measure the height of the fountain accurately using the Mamdani Fuzzy Inference System (FIS) method. The input of this research is voltage and volume with the output in the form of the height of the fountain. The output produced in the research is a prototype. The results obtained in this study are in accordance with the tests carried out in the field with three tests with the results of defuzzification or confirmation. The height level of the fountains with a value of 34.6 for a voltage of 10 V and a volume of 20 is included in the MEDIUM category.

A Fuzzy Logic Based Piezoresistive/Piezoelectric Fusion Algorithm for Carbon Nanocomposite Wide Band Strain Sensor

Polymer nanocomposites (PNC) have a great potential for in-situ strain sensing applications in both static and dynamic loading scenarios. These PNCs, having a polymer matrix of polyvinylidene fluoride (PVDF) with a conductive filler of multi-walled carbon nanotubes (MWCNT), have both piezoelectric and piezoresistive characteristics. Generally, this composite would accurately measure either low frequency dynamic strain using piezoresistive characteristic or high frequency dynamic strains using piezoelectric characteristics of the MWCNT/PVDF film sensor. This limits the frequency bands of the strain sensor to either piezoresistive or piezoelectric ranges. In this study, a novel weighted fusion technique, called piezoresistive/piezoelectric fusion (PPF), is proposed to combine both piezoresistive and piezoelectric characteristics to capture wide frequency bands of strain measurements in real time. This fuzzy logic (FL) based method combines the salient features (i.e. piezoresistive and piezoelectric) of the nanocomposite sensor via reasonably accurate models to extend the frequency range over a wider band. The FL determines the weight of each signal based on the error between the estimate and actual measurements. These weights indicate the contribution of each signal to the final fused measurement. The fuzzy inference system (FIS) was developed using both optimization and data clustering techniques. In addition, type-2 FIS was utilized to overcome the model's uncertainty limitations. The developed PPF methods were verified with experimental data at different dynamic frequencies that were obtained from existing literature. The fused measurements of the MWCNT/PVDF were found to correlate very well with the actual strain and a high degree of accuracy was achieved by the subtractive clustering PPF's FISs algorithm.

Sistem inferensi fuzzy Mamdani untuk menentukan tingkat kualitas air pada kolam bioflok dalam budidaya ikan lele

The government has launched a program to increase the production of catfish by using biofloc ponds. The biofloc ponds can maintain the quality of water biologically to maximize the growth of fish. However, the level of water quality monitoring is generally only divided into good or bad categories so that it cannot represent the condition of fish growth. Therefore, this study aims to get the level of water quality (0–100 %) using the Mamdani fuzzy inference system (FIS) algorithm based on pH, temperature, and dissolved oxygen (DO). The level of water quality was correlated based on catfish growth conditions. The results showed that the range of values of the water quality level for each condition of catfish growth was 100 % for normal-living fish, 83–99 % for stunted fish growth, and < 83% for threatened fish. The FIS algorithm had 89.92 % of accuracy.

Implementation of fuzzy inference system algorithm in brooding system simulator with the concept of IoT and wireless nodes

This paper aims to implement the Fuzzy Inference System algorithm as a controller in an IoT-based observation system in a brooding system simulator. The system consists of sensor and actuator nodes that are connected to the internet using a microcontroller. The two nodes are connected wirelessly. Sensor nodes as devices that collect input data variables that are temperature and humidity. The value of the sensor readings is sent to Antares cloud storage by a microcontroller which functions as data storage so that it can be accessed by the user as well as an input controller. The Mamdani Fuzzy Inference System algorithm is implemented on the actuator node. The actuator node takes fuzzy input values from Antares and then outputs in the form of a PWM crisp value that aims to regulate blower speed and heating level. The experiments performed were comparing the calculation of the algorithm using MATLAB and the brooding system simulator. The results showed identical outputs with practical results with an average error of 0.11% for the PWM value of the blower and 0.22% for the PWM value of the heater. The scheme is expected to be an alternative solution for implementing the control algorithm on an IoT-based system.

Designing Decision Support System for Scholarship Prediction Using Adaptive Neuro Fuzzy Inference System Algorithm

The increasing enthusiasm of students applying for scholarships caused the selection committee to experience difficulties in the decision-making process, the large and complex amount of data caused the committee to need a system that could assist in the decision making process. One method in the system that can help in decision making is artificial neural networks. This method is capable of reasoning like the human brain’s brain network to solve a problem into a form of neurons or equations as a basis for determining a solution or prediction. Researchers have done the method of artificial neural network using the Backpropagation method with an accuracy of 0.9090 and MAE 0.0001017 on the epoch to 329. Based on these results the researchers want to make improvements using a new method, namely adaptive neuro fuzzy inference system (ANFIS) and yields an accuracy value of 92.04% and Mean Absolute Error (MAE) of 0.0001001 on the epoch to 318. The test results were obtained using 3000 data through the K-3 Fold Validation test and 0.2 learning rate configuration and 0.2 momentum.

Applying Grid partitioning based Fuzzy inference system as novel algorithm to predict Asphaltene precipitation

ABSTRACTAsphaltene precipitation is one of challenging problems in petroleum and chemical engineering so the importance of investigation of Asphaltene precipitation is clear. The asphaltene deposition effects on wellbore plugging, wettability alteration and facility damages. In order to solve these problems, a novel investigation based on Grid partitioning based Fuzzy inference system algorithm to predict precipitated asphaltene in terms of dilution ratio, temperature and carbon number of precipitant was developed. The predicting algorithm performance was evaluated statistically and graphically. The coefficients of determination (R2) for training and testing phases 0.9973 and 0.9900 respectively which confirm the great accuracy and high potential of predicting algorithm for estimation of precipitated asphaltene so this algorithm can be used as high accurate and simple software for prediction of asphaltene behavior in crude oil.

A Residual Gradient Fuzzy Reinforcement Learning Algorithm for Differential Games

In this work, we propose a new fuzzy reinforcement learning algorithm for differential games that have continuous state and action spaces. The proposed algorithm uses function approximation systems whose parameters are updated differently from the updating mechanisms used in the algorithms proposed in the literature. Unlike the algorithms presented in the literature which use the direct algorithms to update the parameters of their function approximation systems, the proposed algorithm uses the residual gradient value iteration algorithm to tune the input and output parameters of its function approximation systems. It has been shown in the literature that the direct algorithms may not converge to an answer in some cases, while the residual gradient algorithms are always guaranteed to converge to a local minimum. The proposed algorithm is called the residual gradient fuzzy actor–critic learning (RGFACL) algorithm. The proposed algorithm is used to learn three different pursuit–evasion differential games. Simulation results show that the performance of the proposed RGFACL algorithm outperforms the performance of the fuzzy actor–critic learning and the Q-learning fuzzy inference system algorithms in terms of convergence and speed of learning.

Fuzzy Inference System Algorithm of Plant Classification for Tea Leaf Recognition

Background/Objectives: Biologists found that the morphological, physiological, bio-chemical and molecular methods of plant identification are found to be laborious and require great amount of technical knowledge. This research paper concentrates on the identification of varieties of tea using leaf images. It aims to identify the species in an easy and an accurate manner. Methods/Statistical analysis: The phases involved in this work are image pre processing, feature extraction and classification. Three classification algorithms such as Fuzzy Inference system, Radial basis function network and K-nearest neighbour were used and optimized to achieve a better accuracy and execution time. Results/Findings: The classification algorithm K-nearest neighbor, Radial basis function neural network and Fuzzy Inference System are trained with 40 samples and tested using 20 samples. Conclusions: Fuzzy Inference System has a better accuracy and a lesser execution time, when compared to the other classification algorithm.Keywords: Classification algorithm, Fuzzy Inference System (FIS), Leaf Recognition, Pre-processing

Design and Implementation of ANFIS Algorithm Using VHDL for Vechicular System

-In this paper an (Adaptive Neuro Fuzzy(NF) Inference System algorithm)ANFISA proposed and try to implemented using FPGA(FIELD PROGRAMMABLE GATE ARRAY)for the behavior of the system will be nonlinear. In the application of designing the algorithm for vehicular controlling of nonlinear active suspension system. The algorithm for neural was Back propagation(BPN) and for fuzzy takagisugeno-kang active suspension systems is very important for guaranteeing the passengers feel the comfortable riding and also road handled quality for a vehicle. It is shown that the ANFIS can modelize a nonlinear system very accurately by means of data taken from mathematical model. Firstly the MATLAB SIMULINK toolboxes were use for to simulate the proposed controllers in the pre view paper and to display the responses of the controlled model under different types of disturbance. But in this paper the implementation of the (ANFIS)adaptive neuro fuzzy inference system algorithm using FPGA boards has been try to investigated in this work. The Xilinx ISE software is employed to synthesis the VHDL codes used to program the FPGA.

Improved prediction of mental workload versus HSE and ergonomics factors by an adaptive intelligent algorithm

This study proposes an adaptive intelligent algorithm for forecasting and improving mental workload among operators with respect to HSEE in large gas Treatment Company. The algorithm is composed of reliability, verification, validation and forecasting mechanisms through robust mathematical and statistical methods, Artificial Neural Network (ANN) and Adaptive Network Based Fuzzy Inference System Algorithm (ANFIS). To achieve the objectives of this study, standard questionnaires with respect to HSEE are completed by operators. The average results for each category of HSEE are used as inputs and mental workload is used as output in the algorithm. The efficiency of ANN is examined against ANFIS by use of Mean Absolute Percentage Error (MAPE). The results concluded that ANN provides better solutions than ANFIS. Therefore, ANN is used to forecast and rank operators performance with respect to HSEE and mental workload. Normal probability technique is used to identify outlier operators. Moreover, operators with inadequate mental workload with respect to HSEE are identified. This would help managers to foresee if operators are satisfied with their mental workload in the context of HSEE. Finally, sensitivity analysis of the intelligent algorithm is shown by error analysis in contrast with conventional regression approaches. This is the first study that introduces an adaptive algorithm for efficient forecasting of mental workload with respect to HSEE program in complex systems.

Reply to: A Discussion on “Hindcasting of wave parameters using different soft computing methods” [Appl. Ocean Res. (2008), doi:10.1016/j.apor.2008.03.002

Tarkan ERDIK provides some comments on our paper. He has some misapprehensions on our paper. The following discussions follow the order of his comments. 1. Response to the first comment Dr ERDIK is asked to reread Section 3 and 4 of the paper [1]. Several types of Fuzzy Inference System have been proposed in the literature. One of these types is the so called Takagi and Sugeno FIS [2], which has been used in the paper. In the original paper,the subtractive clusteringmethodwas introduced in the last paragraph of the Section 3 as a method to estimate the optimum number of IF–THEN rules and to determine the membership functions, not as a Fuzzy Inference System (FIS) algorithm. The discusser has claimed we introduced the ‘‘grid partitioning’’ as a FIS algorithm which is not correct. 2. Response to the second comment In the process of training an ANN for a dataset that you own no prior knowledge about, you ought to generate the initial weights and thresholds randomly, but with a bit of logic. All the synaptic weights and thresholds are picked from a uniform distribution with a mean of zero, and a variance such that the standard deviations of the induced local fields of the neurons lie at the transition between the linear and the saturated parts of