scholarly journals Analisis Perbandingan Kalkulasi Manual Fuzzy Logic Metode Mamdani Dan Tsukamoto Pada Penentuan Tipe Diabetes Melitus

2020 ◽  
Vol 2 (3) ◽  
pp. 12-23
Author(s):  
Rico Adrial
Keyword(s):  
Fuzzy Logic ◽  
Diabetes Melitus

Terdapat beberapa metode pada Fuzzy Logic diantaranya Mamdani dan Tsukamoto. Kedua metode ini memiliki hubungan yang menarik dimana output yang dihasilkan ditampilkan dalam bentuk grafik akan tetapi dengan kalkulasi yang berbeda. Artikel ini akan menjabarkan bagaimana perbandingan antar kedua metode tersebut dalam kasus penentuan tipe diabetes melitus. Diabetes itu sendiri terdiri atas dua tipe, dimana perbedaan antara kedua tipe tersebut sering terabaikan. Penggunaan fuzzy logic menggunakan metode Mamdani lebih optimal dalam kasus penentuan tipe diabetes dibandingkan dengan metode Tsukamoto. Hasil kalkulasi manual menunjukan bahwa metode Mamdani lebih mendekati keadaan yang sebenarnya. Berdasarkan kalkulasi yang telah dilakukan perbedaan hasil keluaran yang signifikan ini disebabkan oleh beberapa hal, yaitu Output yang ada pada Tsukamoto hanya berkisar pada nilai 45 sampai dengan 55. Hal ini membuat jika sedikit saja kalkulasi salah maka hasil yang diperoleh akan berdampak besar. Sedangkan hal ini tidak akan berlaku pada metode Mamdani.

scholarly journals Purwarupa Sistem Pakar dengan Mamdani Product untuk Menentukan Menu Harian Penderita DM

2013 ◽  
Vol 7 (1) ◽  
pp. 45
Author(s):  
Nur Hasanah ◽  
Retantyo Wardoyo
Keyword(s):  
Fuzzy Logic ◽  
Expert System ◽  
Inference Engine ◽  
Rule Based ◽  
Knowledge Based ◽  
Menu Planning ◽  
Model Complex ◽  
Uncertainty Method ◽  
Management Expert ◽  
Diabetes Melitus

AbstrakPada 2025 diperkirakan 12,4 juta orang yang mengidap Diabetes Melitus (DM) di Indonesia. Perencanaan makan merupakan salah satu pilar dalam pengelolaan DM. Sistem pakar dapat berfungsi sebagai konsultan yang memberi saran kepada pengguna sekaligus sebagai asisten bagi pakar. Logika fuzzy fleksibel, memiliki kemampuan dalam proses penalaran secara bahasa dan memodelkan fungsi-fungsi matematika yang kompleks. Penelitian ini bertujuan menerapkan metode ketidakpastian logika fuzzy pada purwarupa sistem pakar untuk menentukan menu harian. Manfaat penelitian ini adalah untuk mengetahui keakuratan mesin inferensi Mamdani Product.            Pendekatan basis pengetahuan yang digunakan pada sistem pakar ini adalah dengan Rule-Based Reasoning. Proses inferensi pada sistem pakar menggunakan logika fuzzy dengan mesin inferensi Mamdani Product. Fuzzifier yang digunakan adalah Singleton sedangkan defuzzifier yang digunakan adalah Rata-Rata Terpusat. Penggunaan kombinasi Singleton fuzzifier, mesin inferensi Product dan defuzzifier Rata-Rata Terpusat yang digunakan pada sistem pakar dapat diterapkan untuk domain permasalahan yang dibahas. Meskipun demikian, terdapat kemungkinan Singleton fuzzifier tidak dapat memicu beberapa atau semua aturan. Jika semua aturan tidak dapat dipicu maka tidak dapat disimpulkan kebutuhan kalori hariannya. Kata kunci— sistem pakar, logika fuzzy, mamdani product, diabetes, menu  AbstractIt is predicted that 12.4 million people will suffer from Diabetes Mellitus (DM) in Indonesia in 2025. Menu planning is one of the important aspects in DM management. Expert system can be used as a consultant that gives suggestion to users as well as an assistant for experts. Fuzzy logic is flexible, has the ability in linguistic reasoning and can model complex mathemathical functions. This research aims to implement fuzzy logic uncertainty method into expert sistem prototype to determine diabetic daily menu. The advantage is to find out the accuracy of Mamdani Product inference engine. The knowledge-based approach in this expert system uses Rule-Based Reasoning. The inference process employs fuzzy logic making use of Mamdani Product inference engine. The fuzzifier used is Singleton while defuzzifier is Center Average.            The combination of Singleton fuzzifier, Mamdani Product inference engine and Center Average defuzzifier that is used can be applied in the domain of the problem under discussion. In spite of the case, there is possibility that Singleton fuzzifier can’t trigger some or all of the rules. If all of the rules can’t be triggered then the diabetic daily menu can’t be concluded. Keyword— expert system, fuzzy logic, mamdani product, diabetes, menu

Hysteresis in Categorization: Fuzzy Logic Makes Fuzzy Boundaries

2012 ◽  
Author(s):  
Thomas M. Crawford ◽  
Justin Fine ◽  
Donald Homa
Keyword(s):  
Fuzzy Logic

Psychological factors associated with diabetes melitus

2009 ◽  
Author(s):  
P. Heras ◽  
A. Hatzopoulos ◽  
K. Kritikos ◽  
P. Kazakopoulos ◽  
M. Mantzioros
Keyword(s):  
Psychological Factors ◽  
Factors Associated ◽  
Diabetes Melitus

Continuous Estimation of CO2 Production during Exercise

1997 ◽  
Vol 36 (04/05) ◽  
pp. 368-371
Author(s):  
R. Soma ◽  
Y. Yamamoto
Keyword(s):  
Fuzzy Logic ◽  
Steady State ◽  
Infusion Rate ◽  
Feedback System ◽  
Whole Body ◽  
Co2 Production ◽  
Cycle Exercise ◽  
Continuous Estimation ◽  
Breath Measurement ◽  
13Co2 Enrichment

Abstract.A new method was developed for continuous isotopic estimation of human whole body CO2 rate of appearance (Ra) during non-steady state exercise. The technique consisted of a breath-by-breath measurement of 13CO2 enrichment (E) and a real-time fuzzy logic feedback system which controlled NaH13CO3 infusion rate to achieve an isotopic steady state. Ra was estimated from the isotope infusion rate and body 13CO2 enrichment which was equal to E at the isotopic steady state. During a non-steady state incremental cycle exercise (5 w/min or 10 w/min), NaH13CO3 infusion rate was successfully increased by the action of feedback controller so as to keep E constant.

Modified fuzzy-based greedy routing protocol for VANETs

2020 ◽  
Vol 39 (6) ◽  
pp. 8357-8364
Author(s):  
Thompson Stephan ◽  
Ananthnarayan Rajappa ◽  
K.S. Sendhil Kumar ◽  
Shivang Gupta ◽  
Achyut Shankar ◽  
...  
Keyword(s):  
Fuzzy Logic ◽  
Routing Protocol ◽  
Intelligent Transportation Systems ◽  
Vehicular Ad Hoc Networks ◽  
Ad Hoc ◽  
Research Area ◽  
Transportation Systems ◽  
Delivery Ratio ◽  
Greedy Routing ◽  
Hoc Networks

Vehicular Ad Hoc Networks (VANETs) is the most growing research area in wireless communication and has been gaining significant attention over recent years due to its role in designing intelligent transportation systems. Wireless multi-hop forwarding in VANETs is challenging since the data has to be relayed as soon as possible through the intermediate vehicles from the source to destination. This paper proposes a modified fuzzy-based greedy routing protocol (MFGR) which is an enhanced version of fuzzy logic-based greedy routing protocol (FLGR). Our proposed protocol applies fuzzy logic for the selection of the next greedy forwarder to forward the data reliably towards the destination. Five parameters, namely distance, direction, speed, position, and trust have been used to evaluate the node’s stability using fuzzy logic. The simulation results demonstrate that the proposed MFGR scheme can achieve the best performance in terms of the highest packet delivery ratio (PDR) and minimizes the average number of hops among all protocols.

Design and Simulation of Smart Control System for Internet Traffic Distribution on Servers by Using Fuzzy Logic System

2018 ◽  
Vol 2 (1) ◽  
Author(s):  
Raid Daoud ◽  
Yaareb Al-Khashab
Keyword(s):  
Fuzzy Logic ◽  
Control System ◽  
Input Parameter ◽  
Traffic Density ◽  
The Internet ◽  
Linguistic Variables ◽  
Internet Service ◽  
Traffic Distribution ◽  
Smart Control ◽  
High Level

The internet service is provided by a given number of servers located in the main node of internet service provider (ISP). In some cases; the overload problem was occurred because a demand on a given website goes to very high level. In this paper, a fuzzy logic control (FLC) has proposed to distribute the load into the internet servers by a smart and flexible manner. Three effected parameters are tacked into account as input for FLC: link capacity which has three linguistic variables with Gaussian membership function (MF): (small, medium and big), traffic density with linguistic variables (low, normal and high) and channel latency with linguistic variables (empty, half and full); with one output which is the share server status (single, simple and share). The proposed work has been simulated by using MATLAB 2016a, by building a structure in the Fuzzy toolbox. The results were fixed by two manners: the graphical curves and the numerical tables, the surface response was smoothly changed and translates the well-fixed control system. The numerical results of the control system satisfy the idea of the smart rout for the incoming traffics from the users to internet servers. So, the response of the proposed system for the share of server ratio is 0.122, when the input parameter in the smallest levels; and the ratio is 0.879 when the input parameters are in highest level. The smart work and flexible use for the FLC is the main success solution for most of today systems control.

Sistem Kontrol Optimal Fuzzy-Particle Swarm Optimization

2018 ◽  
Vol 9 (1) ◽  
pp. 1-5
Author(s):  
Fachrudin Hunaini ◽  
Imam Robandi ◽  
Nyoman Sutantra
Keyword(s):  
Fuzzy Logic ◽  
Particle Swarm Optimization ◽  
Control System ◽  
Membership Function ◽  
Fuzzy Logic Control ◽  
Particle Swarm ◽  
Optimization Method ◽  
Swarm Optimization ◽  
Motion Error ◽  
Logic Control

Fuzzy Logic Control (FLC) is a reliable control system for controlling nonlinear systems, but to obtain optimal fuzzy logic control results, optimal Membership Function parameters are needed. Therefore in this paper Particle Swarm Optimization (PSO) is used as a fast and accurate optimization method to determine Membership Function parameters. The optimal control system simulation is carried out on the automatic steering system of the vehicle model and the results obtained are the vehicle's lateral motion error can be minimized so that the movement of the vehicle can always be maintained on the expected trajectory

Kajian Interaksi Obat Metformin pada Pasien Diabetes Mellitus

2019 ◽  
Vol 8 (2) ◽  
pp. 55-58
Author(s):  
Havizur Rahman ◽  
Teresia Anggi Octavia
Keyword(s):  
Diabetes Mellitus ◽  
Drug Interaction ◽  
Data Collection ◽  
Drug Interactions ◽  
Degenerative Disease ◽  
Moderate Severity ◽  
Purposive Sampling ◽  
Chronic Degenerative Disease ◽  
Over Time ◽  
Diabetes Melitus

Diabetes melitus merupakan penyakit degeneratif kronis yang apabila tidak ditangani dengan tepat, lama kelamaan bisa timbul berbagai komplikasi, ini cenderung menyebabkan pasien mendapatkan banyak obat dalam satu resep yang dapat menimbulkan interaksi antar obat. Tujuan dari penelitian ini adalah mengetahui persentase terjadinya interaksi obat metformin secara teori serta mengkaji efek yang mungkin timbul dan solusinya. Teknik pengambilan data dengan purpossive sampling, yaitu resep pasien rujuk balik yang menderita diabetes mellitus yang menggunakan metformin. Data yang diperoleh ditemukan bahwa obat yang berinteraksi dengan metformin dengan tingkat keparahan minor ialah sebesar 60%. Kemudian untuk tingkat keparahan moderat ialah sebesar 20%. Sedangkan untuk tingkat keparahan mayor tidak ditemukan. Dari tabel diatas juga dapat diketahui bahwa terdapat 4 obat yang saling berinteraksi dengan metformin, sedangkan untuk obat yang tidak saling berinteraksi dengan metformin terdapat 9 obat. Jumlah obat yang berinteraksi secara teori sebesar 6,85% dan yang tidak berinteraksi 93,15%. Terdapat interaksi obat metformin dengan beberapa obat yaitu furosemid, lisinopril, acarbose dan ramipril.   Kata kunci: interaksi obat, metformin, diabetes mellitus   STUDY OF METFORMIN INTERACTION IN MELLITUS DIABETES PATIENTS   ABSTRACT Mellitus is a chronic degenerative disease which if not handled properly, over time can arise various complications, this tends to cause patients to get many drugs in one recipe that can cause interactions between drugs. The purpose of this study is to determine percentage of metformin drug interactions in theory and examine the effects that may arise and solutions. Data collection techniques using purposive sampling, which is a recipe for reconciliation patients who suffer from diabetes mellitus using metformin. The data obtained it was found that drugs that interact with metformin with minor severity were 60%. Then for moderate severity is 20%. Whereas the major severity was not found. From the table above it can also be seen that there are 4 drugs that interact with metformin, while for drugs that do not interact with metformin there are 9 drugs. The number of drugs that interacted theoretically was 6.85% and 93.15% did not interact. An interaction of the drug metformin with several drugs namely furosemide, lisinopril, acarbose and ramipril.   Keywords: drug interaction, metformin, diabetes mellitus

Sign in / Sign up

Export Citation Format

Share Document