Fuzzy Sugeno Research Articles

Development of a System for Determining Loan Eligibility in the Bukit Indah Cooperative, Batunya Village Using the Fuzzy Sugeno Method

This study aims to develop a loan eligibility determination system at the Bukit Indah Cooperative in Batunya Village using the fuzzy sugeno method. The Bukit Indah Cooperative is a savings and business cooperative run independently by the Batunya Village community and carries out efforts for the welfare of the Batunya Village community. Fuzzy Sugeno is one of the fuzzy logic methods used for modeling, control and decision making. Fuzzy Sugeno was developed by Takagi, Sugeno, and Kang in 1985, this method aims to provide more efficient results in the control and decision making system. The research method used in this study is the waterfall method. This study has succeeded in developing and producing a system used to help the Bukit Indah Cooperative in Batunya Village to determine the eligibility of providing loans to customers. In testing the feasibility of the system with 20 sample data, it was found that out of 20 sample data, there were 18 correct data in the system, data comparison was carried out by comparing the data from the evaluation of calculations by cooperative officers with the data produced by the system which produced an accuracy level of 90.00%. Based on these results, it was found that the system developed can be said to work well and is considered sufficient to test the accuracy of the fuzzy Sugeno method.

Impact of Smart Greenhouse Using IoT for Enhanced Quality of Plant Growth

Greenhouses play a crucial role in manipulating environmental conditions for optimal plant growth. While existing greenhouses enhance control over environmental factors, manual controls such as watering and humidity regulation often lead to suboptimal production and increased costs. This study proposes the development of a smart greenhouse with an automatic control system using fuzzy logic, specifically fuzzy Sugeno, to regulate watering and lighting based on soil moisture, temperature, and light intensity. The system's architecture involves sensor inputs, microcontroller processing, and the activation of actuators, such as UV lights and water pumps. Fuzzy logic is applied to interpret soil moisture and temperature inputs and determine optimal irrigation durations. The system's functionality is tested and validated through functional testing, Blynk application testing, and fuzzy Sugeno testing. Results indicate the successful implementation of the proposed smart greenhouse system. Functional testing demonstrates accurate sensor readings, including temperature and soil moisture. The Blynk application enables real-time monitoring and control of environmental conditions. Fuzzy Sugeno testing validates the irrigation control system, with an average error rate of 1.3%, affirming the system's alignment with desired specifications. Plant testing in different conditions showcases the effectiveness of the smart greenhouse in supporting plant growth and development.

Optimizing Plant Watering Efficiency via IoT: Fuzzy Sugeno Method with ESP8266 Microcontroller

This research explores automatic plant sprinklers utilizing fuzzy logic with the fuzzy Sugeno method to overcome optimal watering schedules. Developed with ESP8266 microcontroller hardware and Arduino IDE software, the WSN prototype focuses on spinach plants. Watering in the nursery was done twice a day for seedling growth, then reduced to once a day. Soil moisture levels were assessed using a soil analyzer, as well as temperature variations with the HTC-1 device. Python facilitates data analysis, generating fuzzy inference graphs on temperature sensors (10-40°C) and soil moisture values (1-1024 RH). This innovative approach, which integrates fuzzy logic and advanced hardware, offers a promising solution for effective plant care.

Predictive Analysis of the Amount of Batik Production Using the Fuzzy Sugeno Algorithm

To meet market demand, a company must be able to plan and determine the amount of appropriate and timely production to compete with other companies. To support this, we need a system that can determine the product's production amount so that the product can be sold according to expectations and the desired target. This study aims to determine the amount of production through a decision support system using the Fuzzy Sugeno algorithm in the form of logic used to produce a single decision or crisp. This research was conducted on batik production in a company. The problem in the batik production process is the amount of production that differs from the market demand. The factors that influence the process of determining the amount of production are the number of inventories and the number of requests used as variables in this study. The results of this study are in the form of a decision support system that can determine the amount of batik production based on the analysis of the number of requests and the amount of supply used to assist companies in making decisions with a truth value of 80%. Thus, the company can be assisted in determining the amount of production to meet market demand and increase profits and achievement targets by minimizing stockpiling.

Integrating fuzzy metrics and negation operator in FCM algorithm via genetic algorithm for MRI image segmentation

In this study, we redefine FCM algorithm by integrating fuzzy set theory, fuzzy metrics, and Sugeno negation principles. This innovative approach overcomes the limitations inherent in conventional machine learning models, especially in situations characterized by uncertainty, noise, and ambiguity. Our model utilizes the membership degrees from fuzzy set theory, and transforms the concept of proximity defined by fuzzy metrics into a minimization problem. This transformation is achieved using a linguistic negation operator, which is crucial for optimizing FCM algorithm's objective function. A significant innovation in our research is the use of GA for optimizing parameters within the contexts of fuzzy metrics and Sugeno negation. The precise optimization capabilities of GA greatly enhance the sensitivity and adaptability of FCM algorithm, thereby improving overall performance. By leveraging the meticulous parameter adjustments provided by GA, our approach has shown superior results in practical applications, such as brain MRI image segmentation, surpassing traditional methods. Experimental results highlight the considerable enhancements our proposed FCM algorithms bring over existing methods across various performance metrics. In conclusion, this study makes a valuable addition to the field of fuzzy-based machine learning methodologies. It combines the optimization strength of GA with the flexible classification capabilities of fuzzy logic. The integration of Sugeno negation and fuzzy metrics not only improves the accuracy and precision of FCM algorithm but also provides significant benefits in handling complex and ambiguous datasets. This research signifies a major advance in machine learning and fuzzy logic, setting the stage for future applications and studies.

Prototype of pH and Water Temperature Control System in Discus Fish Farming Using IoT-based Sugeno Fuzzy

Challenges in cultivating discus fish often arise from abrupt pH and temperature fluctuations attributed to manual and sluggish intervention. An IoT-based prototype for automatic pH and water temperature regulation was developed to address this. The study aimed to evaluate the efficacy of the prototype in controlling pH levels and water temperature and to explore the application of IoT-based fuzzy logic in discus fish cultivation. Test data from the implemented tools and sensors revealed an error comparison value of 0.0132% and an accuracy level of 99.986% for pH measurement. In comparison, temperature sensing yielded an error value of 0% with 100% accuracy. The IoT-based fuzzy Sugeno system demonstrated regular and effective operation in regulating pH and water temperature in discus fish cultivation, showcasing superiority over manual handling systems in mitigating sudden environmental changes.

Rancang Bangun Alat Pemilah Biji Kopi Berdasarkan Kualitas Buah Menggunakan Sensor TCS3200

Coffee fruit is a trade commodity that has been known for centuries. Coffee fruit can be processed into a delicious drink, but when coffee farmers harvest at the same time, farmers combine immature and ripe coffee fruit in one container, this results in a decrease in the quality of the taste. significant. In this research, the fuzzy Sugeno method was used to determine the classification of ripe, semi-ripe and ripe coffee fruit. This tool uses an Arduino Uno Atmega328 microcontroller to control the TCS3200 color sensor as a reader for the color of the coffee fruit and uses a servo to sort the coffee fruit according to quality. In testing the automatic control system for separating coffee beans based on color using the TCS3200 Color Sensor, it was successful in directing the coffee beans to a predetermined container. Keywords— TCS3200 Sensor, Arduino ATmega328P,Coffee,Color,Quality,Fuzzy sugeno.

FUZZY APPLICATION (MAMDANI METHOD) IN DECISION-MAKING ON LED TV SELECTION

Science is now developing very quickly. Information technology has been used in various places. Using computers in business, government, and personal activities shows how important science and technology are in helping human activities. One method used to solve various problems is fuzzy logic. Several types of Fuzzy are classified as Fuzzy Inference Systems (FIS), namely Tsukamoto, Mamdani, and Sugeno. The application of vague logic in making decisions about choosing an LED TV is to make it easier to select electronic media. This research aims to help people who need clarification on the many LED TV choices currently available. So, we need a decision-making method to help people choose an LED TV that suits their needs and budget. One of the methods used in this research is the Mamdani method. There were 50 LED TV brands in this research, and the criteria used in selecting LED TVs were based on size, resolution, and price. An LED TV that meets the medium size, high resolution, and normal price criteria will be purchased. The LED TV data that meets the medium size, high resolution, and normal price criteria is the Samsung UA43AU7000KXXD brand LED TV. However, the actual decision remains based on the buyer's decision.

Creation of an intelligent irrigation system based on the fuzzy Sugeno model

This paper discusses the creation of an intelligent irrigation system based on the fuzzy Sugeno model. The goal of the work is to develop an effective system capable of automatically managing irrigation in agriculture, horticulture and other areas where optimal use of water resources is required. To achieve this goal, an analysis and selection of data processing methods was carried out, and the key parameters necessary for the implementation of an intelligent irrigation system were identified. The fuzzy Sugeno model was chosen as the base model, which allows taking into account the uncertainty and fuzziness of data when making decisions. The main objective of the work was to create software capable of making a decision on the need for irrigation and the optimal volume of water supply based on the collected data on soil moisture. Research has shown that the developed system is capable of effectively managing irrigation, optimizing the consumption of water resources and increasing crop yields. The results of the work can be applied in agriculture, horticulture and other areas where automated irrigation control based on soil moisture data is required.

Fuzzy based modeling and optimization of EDMed response of Zircaloy-2

In this work, fuzzy model was developed that predicts response parameters and surface properties of an electrical discharge machined Zircaloy-2. Taguchi L18 mixed design was used to perform the experiments using different process parameters (polarity, pulse-on-time, pulse-off-time, tool electrode material, and peak current). Material removal rate (MRR) and tool wear rate (TWR) were chosen as machining response parameters, whereas number of particles (NoP) and the percentage particle area (PPA) for surface properties of EDMed surface. Digital image processing tool was used to evaluate the surface properties. Fuzzy-Sugeno (FS)-model was developed to predict MRR, TWR, NoP, and PPA. Model accuracy was found to be 94% for MRR and TWR, and 92% for NoP and PPA. Maximum MRR 1.53 × 10−3 mm3/min found when machining was performed using graphite tool with negative polarity. Fuzzy Sugeno-GRA method was successfully implemented to predict optimal response corresponding to high value of GRG.

Decision-making for solar panel selection using Sugeno-Weber triangular norm-based on q-rung orthopair fuzzy information

Solar power is an alternative energy derived from the sun. Solar power is more environmentally friendly and sustainable than burning fossil fuels which releases harmful greenhouse gas emissions. Therefore, this study aims to evaluate a reliable solar panel based on certain characteristics by incorporating the theory of the decision-making process. To serve this goal, this study discusses a well-known aggregation model of the q-rung orthopair fuzzy set, which is a broader and flexible environment of fuzzy sets and intuitionistic fuzzy sets used to handle unpredictable information of human opinions. The key components of this article are to demonstrate some realistic operations of Sugeno–Weber triangular norms considering q-rung orthopair fuzzy information. These operations provide authentic estimated information during the decision-making process. We developed a class of new aggregation operators using the q-rung orthopair fuzzy information system, including q-rung orthopair fuzzy Sugeno–Weber power weighted average and q-rung orthopair fuzzy Sugeno–Weber power weighted geometric operators. Some realistic characteristics and special cases are also demonstrated to show the compatibility of the proposed methodologies. An innovative approach to the multi-attribute decision-making problem is utilized to resolve different real-life applications considering various criteria or attributes. To show the intensity and applicability of the proposed approaches, we explored a numerical example for efficient solar panel selection based on the proposed methodologies. Furthermore, we presented a comprehensive comparison technique to compare the findings of the existing methods with the proposed aggregation approaches. Finally, the proposed research work is summarized, and the future prospects are discussed.

Prediksi Tingkat Produksi Bawang Goreng menggunakan Metode K-Means dan Fuzzy Inference System

Shallots are a strategic commodity because they are needed for household consumption as well as the food industry. Shallots are usually used as a cooking spice, or as a topping for food dishes called fried onions. Shallots are easily damaged, one way to prevent damage is to process shallots into fried onions. Sales of fried onions fluctuate every month due to consumer demand, therefore in this research a grouping of production levels and predictions of fried onion production was carried out. The methods used in this research are K-Means and Fuzzy Sugeno. From the results of research using the K-Means method, there are 3 clusters of fried onion production levels, namely high, medium and small production levels. High production levels were found in months 4, 5, 9, and 10; moderate production levels in months 1, 2, 3, 6, 7, 8 and 11; while a small production level was found in the 12th month. Based on system testing using the fuzzy Sugeno method, data was generated that could be processed and produce 9 rules to serve as a reference in predicting fried onion production for the following years. Apart from that, based on the results of the Mean Absolute Percent Error calculation, the capability of the model created is good and accurate because it has a value of 14.2%. Fried onion production levels in the 4th and 12th months have more accurate predictions compared to other months

The Application of Artificial Intelligence (AI)-Based Ultrasound for the Diagnosis of Fatty Liver Disease: A Systematic Review.

Fatty liver disease, also known as hepatic steatosis, poses a significant global health concern due to the excessive accumulation of fat within the liver. If left untreated, this condition can give rise to severe complications. Recent advances in artificial intelligence (AI, specifically AI-based ultrasound imaging) offer promising tools for diagnosing this condition. This review endeavors to explore the current state of research concerning AI's role in diagnosing fatty liver disease, with a particular emphasis on imaging methods. To this end, a comprehensive search was conducted across electronic databases, including Google Scholar and Embase, to identify relevant studies published between January 2010 and May 2023, with keywords such as "fatty liver disease" and "artificial intelligence (AI)." The article selection process adhered to the PRISMA framework, ultimately resulting in the inclusion of 13 studies. These studies leveraged AI-assisted ultrasound due to its accessibility and cost-effectiveness, and they hailed from diverse countries, including India, China, Singapore, the United States, Egypt, Iran, Poland, Malaysia, and Korea. These studies employed a variety of AI classifiers, such as support vector machines, convolutional neural networks, multilayer perceptron, fuzzy Sugeno, and probabilistic neural networks, all of which demonstrated a remarkable level of precision. Notably, one study even achieved a diagnostic accuracy rate of 100%, underscoring AI's potential in diagnosing fatty liver disease. Nevertheless, the review acknowledged certain limitations within the included studies, with the majority featuring relatively small sample sizes, often encompassing fewer than 100 patients. Additionally, the variability in AI algorithms and imaging techniques added complexity to the comparative analysis. In conclusion, this review emphasizes the potential of AI in enhancing the diagnosis and management of fatty liver disease through advanced imaging techniques. Future research endeavors should prioritize the execution of large-scale studies that employ standardized AI algorithms and imaging techniques to validate AI's utility in diagnosing this prevalent health condition.

COMPARISON OF SUGENO AND MAMDANI FUZZY SYSTEM PERFORMANCE IN PREDICTING THE AMOUNT OF VIRGIN COCONUT OIL (VCO) PRODUCTION

In the future, a tight industrial competition.The professional manage companies become crucial to successful so competitive on the global market.One of the key figure in production is the ability to plan and optimize goods production process. To face fluctuations of consumer demand without adding existing facilities, The company can use fuzzy mammal and sugeno methods to determine the amount of production of voc (virgin organic coconut) based on supply and demand data in the wotay coconut (main business area). process involving 18 fuzzy rules using AND and OR operators on each fuzzy set and IF-THEN rules for each input variable demand (little, medium, a lot), inventory (little, medium, a lot), output (little, medium , Lots). The thing that strengthens the conclusion that fuzzy sugeno is better than fuzzy mamdani with this data is that the MAPE for fuzzy sugeno has a value of 36.11% with a truth level of 63.89%, while for fuzzy mamdani the MAPE value is 38.77%, with a truth level 61.23 %. With the MAPE value obtained from Fuzzy Mamdani and Sugeno, the forecast for VOC production at KBU is predicted. Wootay Coconut is worth using with fuzzy sugeno.

Modeling of Fuzzy Systems Based on the Competitive Neural Network

This paper presents a method to dynamically model Type-1 fuzzy inference systems using a Competitive Neural Network. The aim is to exploit the potential of Competitive Neural Networks and fuzzy logic systems to generate an intelligent hybrid model with the ability to group and classify any dataset. The approach uses the Competitive Neural Network to cluster the dataset and the fuzzy model to perform the classification. It is important to note that the fuzzy inference system is generated automatically from the classes and centroids obtained with the Competitive Neural Network, namely, all the parameters of the membership functions are adapted according to the values of the input data. In the approach, two fuzzy inference systems, Sugeno and Mamdani, are proposed. Additionally, variations of these models are presented using three types of membership functions, including Trapezoidal, Triangular, and Gaussian functions. The proposed models are applied to three classification datasets: Wine, Iris, and Wisconsin Breast Cancer (WDBC). The simulations and results present higher classification accuracy when implementing the Sugeno fuzzy inference system compared to the Mamdani system, and in both models (Mamdani and Sugeno), better results are obtained when the Gaussian membership function is used.

Optimizing the Diet of Diabetes Mellitus Sufferers Through Food Mapping Using the Fuzzy Sugeno Method

This research focuses on developing optimal strategies for diet management for Diabetes Mellitus (DM) sufferers by utilizing the Fuzzy Sugeno method in food mapping. Diabetes Mellitus is a chronic metabolic disease that requires a careful management approach to diet to control blood sugar levels. In this study, we designed a system that uses Sugeno's fuzzy principles to categorize foods based on glycemic parameters, nutritional content, and individual patient characteristics. This method allows the formation of fuzzy rules that cover the variability and complexity in the preferences and health needs of each patient. The developed model was tested using DM patient data involving detailed information about diet, medical history and blood sugar response. Experimental results show that this approach can provide more personalized diet recommendations that suit individual health conditions. The application of the Fuzzy Sugeno method in food mapping for DM patients is expected to increase patient compliance with the recommended diet, reduce blood sugar levels, and overall, improve quality of life. Additionally, this approach also provides a foundation for the development of adaptive dietary management systems, which can continuously adapt to changing patient health needs over time.

Prioritization of crowdsourcing models for last-mile delivery using fuzzy Sugeno–Weber framework

Modern technologies provide new opportunities for the industry but raise the expectations of the customers as well. This is valid also for the postal, courier, and logistics industries. The biggest challenge for the companies in the field is to improve the efficiency of the final phase in the transfer of shipments – last-mile delivery. A contemporary solution relates to collaboration between delivery companies and citizens who are willing to perform the delivery tasks as an additional activity to their established job or routine. Such a concept is known as crowdsourcing. There are several approaches within crowdsourcing, for example, transportation by car, utilizing public transport, etc. To make an appropriate choice, multiple criteria should be considered. This paper aims to propose an original methodology for solving the explained multi-criteria decision-making problem. The proposed framework is based on the application of the Sugeno–Weber nonlinear functions in a fuzzy environment. The application of the fuzzy Sugeno–Weber weighted assessment methodology showed that the proposed methodology has adaptability, a high degree of generalization, and stability of results. This enables the applicability of the methodology to various tasks from a broad spectrum of areas, which represents an additional value. A real-life case study is provided to solve the prioritization of crowdsourcing models in suburban municipalities of Belgrade, Serbia. The available alternatives and the most important criteria for the crowdsourced delivery model are identified. All criteria are divided into four groups, which define the dimensions of sustainability, including the technical aspect. The results of the conducted research indicate a high level of convenience in using one’s car or daily bus lines for crowdsourced delivery to optimize the entire process of shipment transfer in the observed territory.

Model predictive PESQ-ANFIS/FUZZY C-MEANS for image-based speech signal evaluation

This paper presents a new method to evaluate the quality of speech signals through images generated from a psychoacoustic model to estimate PESQ (ITU-T P862) values using a first-order Fuzzy Sugeno approach implemented in the Adaptive Neuro-Fuzzy Inference System - ANFIS. The factors feeding the network were obtained using an image-processing technique from the perceptual model coefficients. All simulations were performed using a database containing clean and corrupted signals by eight types of noises found in everyday situations. The proposal uses the PESQ values of the signals to train the network. The analyses proved that the predictive performance will depend on the choice of a psychoacoustic model, the factor extraction technique, the combination of these factors, the fuzzification algorithm, and the type of membership function in the ANFIS input space. The data sets for training and testing for each signal directory were randomly created and executed fifty times. The proposal achieves the best prediction values for PESQ when the averages of the measurements reach MAPE ≤0.09, RMSE ≤0.20, and R2≥95. In general, the approach provided satisfactory results compared to Multilayer Perceptron networks with their different learning algorithms, compared to another psychoacoustic model, to ITU-T P.563 and other non-intrusive methods that evaluate the quality of voice signals, and it was efficient regardless of the number of signals and the database used.

Direct Torque Control (DTC) Design With Fuzzy Sugeno-Proportional Derivative for 3-Phase Induction Motor Speed Control

In general, in the industrial world, induction motors are more widely used than direct current motors, due to the characteristics of induction motors that are sturdy, reliable, easy to maintain, and relatively inexpensive. The phenomenon of changing rotational speed when the load changes results in regulation of the speed of the induction motor, which risks slow response time, there is overshoot which should still be minimized, and there are disturbances caused by external environmental factors, so that a controller is needed that is able to work effectively to optimize performance. 3 phase induction motor. The purpose of this study is to design a sugeno-PD fuzzy DTC controller, where the DTC provides a fast and strong response mounted on an AC motor. Fuzzy Sugeno provides a short calculation time and its reasoning includes wide enough data and PD to speed up the response time results. So that the proposed method produces an induction motor rotating speed according to the given setpoint of 100 rad/s with a settling time of 0.45 seconds, a rise time of 0.2 seconds and no steady state error. From the state of the plan output response before being given the controller there is a steady state error of 5 rad/s, a maximum overshoot of 5.4111%, a settling time of 0.1554 seconds and a rise time of 0.1554 seconds

Monitoring Suhu Pada Tanaman Seledri Berbasis Internet of Things Dengan Metode Fuzzy Sugeno

In the process of plant growth is influenced by many factors one of which is the weather climate. Many crop failures occur due to unstable weather. One of them is the celery plant because it is susceptible to weather. Therefore an automatic temperature monitoring system is designed that can be monitored from a smartphone using a fuzzy Sugeno method. Starting from reading the DHT11 sensor which is then processed by ESP32 which then sends the data to the smartphone via the Inventor App, then ESP32 gives commands to the output which then works based on the conditions that occur from the results of sensor readings with PWM fuzzy sugeno. The parameter being monitored is the temperature of the celery plant. The reading results will be displayed on App Inventor as an Internet of Things (IoT) support system