Proses diagnosa penyakit jantung diawali dengan pemotongan rekaman sinyal EKG yang terdiri dari 9-11 gelombang menjadi satu gelombang utuh EKG. Selanjutnya, dilakukan dekomposisi dan ekstraksi menggunakan transformasi wavelet untuk memperoleh 6 parameter. Parameter yang telah diperoleh akan digunakan sebagai input pada proses pembentukan model ANFIS. Data yang diperoleh dari hasil ekstraksi EKG dibagi menjadi 70% data latih dan 30% data uji. Output yang diperoleh dari model ANFIS adalah hasil diagnosa penyakit jantung, yaitu normal, left bundle branch block (LBBB), dan right bundle branch block (RBBB). Pembelajaran ANFIS terbagi menjadi 6 tahapan, yaitu pengelompokan (clustering) data dengan metode Fuzzy C-Means, menentukan derajat keanggotaan setiap data, menentukan neuron tetap, mencari bobot normalized firing strength, menentukan nilai parameter konsekuen, dan menentukan output jaringan.
It is important to highlight that there are two main tests conducted, the first at the training module, where the training data set is tested against the trained Neural Network and Neuro-Fuzzy, and the second at the testing module, where the testing data set is tested against the trained Neural Network and Neuro-Fuzzy. Certain para- meters were modified for both systems in order to optimize the systems’ performance and acknowledge their effects on the overall systems’ performance. Finally, the best combination of parameters are selected and used in the systems for future tests. A third test is conducted, where users could input values for a specific case and classify whether the heartdisease is present or absent as shown in Table 4.
A group of patients CT liver images was evaluated in Obayya et al (2016) ANFIS model that was used to classify liver tumor as benign or malignant. In their work, the CT liver images passed through various transformation stages such as; enhancement and improvement of image quality as the first stage, the use of extraction algorithms based on thresholding for extraction of liver as the input for the fourth stage where the ANFIS classifier trained the extracted features using back propagation gradient descent method and least square method. The two types of features i.e (texture feature and discrete wavelettransformation) were used separately to evaluate the performance of the model. DWT features recorded 96% accuracy while the texture feature obtained an accuracy of 90%. In the proposed AdaptiveNeuroFuzzyInferenceSystem (ANFIS) of Rajamani and Rathika (2015), the primary objective of the model was tailored toward detection of liver cancer in patients with the help of 2-D CT images as input parameters through ANFIS algorithm to generate final optimal result. The summary of other related works are presented in Table 1. Deductions from the reviewed literature are as followed ;
SRM working is based on switched reluctance principle. The reluctance value in SRM is varied from unaligned position to aligned position. In aligned position the air gap as well as reluctance values are low. Since the reluctance is directly proportional to length of air gap. In unaligned position the air gap as well as reluctance is more. Reluctance is nothing but opposition to creation of flux. Hence the rotor poles are attracted by stator poles thereby movement of the poles taking place from unaligned position to aligned position. This is done when excitation of rotor poles occurred. For proper working of SRM rotor position details are essential. Rotor position information is sensed by sensors. But the usage of sensors has certain limitations such as occupies more space, electrical and mechanical loose contacts, deposit of dust particles and costly. So the sensors are replaced by sensorless methods such as fuzzy logic, artificial neural networks and ANFIS. Moreover SRM has salient poles in the stator and rotor. This introduces the nonlinear nature of SRM. The nonlinear characteristics can be easily analyzed by soft computing techniques. The inputs of the soft computing techniques are current and flux linkage, which are derived from the terminals of SRM stator. Using these values rotor position has been estimated by soft computing techniques. The rotor position information is fed to a processor. Based on the rotor position information firing pulses are produced for triggering of power electronic devices of a converter. The converter output excites the phase winding of the SRM. The same process repeated for other phases. The voltage equation for SRM is given in eq. (1).
The design of protective devices has been a great challenge for power system engineers to ensure the reliability and security of a power system. To achieve this, the protection equipment or components in power system need to be designed for accurate detection and classification of fault in the system. The various abnormalities that occur in electrical distribution networks are capacitor switching, high impedance faults, line faults and sudden load rejection and so on. Among these disturbances, the detection of high impedance faults on electrical power system networks have been one of the most challenging phenomenon faced by the today’s electric utility industry . Over-the- years, the typical protection schemes used to detect the fault in the system involves only the low impedance faults (i.e. the fault with infinitesimal low resistance) and it outperforms to locate the faults. On the flipside, the resistance of the fault path is very high when one of phases of the transmission line makes electrical contact with a semi-insulated object such as tree, pole, surface of the road, gravels, concrete, dry land etc., which is called high impedance fault (HIF). The most significance of HIF is the magnitude of fault current, ranges from 0 to 75 amperes and exhibits the arcing and flashing at the point of contact leading to serious threat of electrical shock or fire to the public. Hence, the detection is more important from the public and reliable operation point of view
This paper, adaptiveneuro-fuzzyinferencesystem for okra yield prediction, describes the use of neuro -fuzzyinferencesystem in the prediction of okra yield using environmental parameters such as mini- mum temperature, relative humidity, evaporation, sunshine hours, rainfall and maximum temperature as input into the neuro-fuzzyinferencesystem, and yield as output. The agro meteorological data used were obtained from the department of agro meteorological and water management, Federal University of Agriculture, Abeokuta and the yield data were obtained from the Department of Horticulture, Federal University of Agriculture, Abeokuta. MATLAB was used for the analysis of the data. From the results, the maximum predicted yield showed that at minimum temperature of 24.4 o C, relative humidity of
Another context profiling framework is proposed in  which utilized context variables including GPS readings, sur- rounding devices via both WIFI and Bluetooth. This frame- work firstly detects personal contexts of interest (CoIs) and then infer user trust level based on device familiarity and context familiarity. However, this framework is not able to adaptively update CoIs when a user’s routine regarding lo- cation changes significantly. Later as a follow-up study, an improved version based on  called ConXsense is proposed in  to protect against device misuse. The identification of CoIs is optimized by using stay points and stay regions to identify CoIs based on GPS and WIFI. ConXsense is designed not to authenticate the user, but to provide smart device locking system. With the similar aim, a context-aware scalable authentication scheme is proposed in  which is designed to reduce active authentication on the mobile device by inferring the safety level of the context.
ANFIS is a combination of fuzzy logic and neural network approaches and naturally carries the advantages of both. In the present work for prediction of future load, the historical load data from TATA POWER Company, Mumbai for complete one year 2013 is used to construct the ANFIS model. The training method that is utilized for the proposed forecasting model is a hybrid training algorithm; it uses back propagation to estimate values for the parameters. In order to speed up the process, the number of inputs was kept low in the proposed model. IV DESIGN OF ANFIS MODEL
Abstract: Estimating groundwater recharge using mathematical models such as water budget or soil water balance method has been proved to be very difficult due to the complex, uncertain multidimensional nature of the process, despite the simplicity of the concept. Artificial Intelligence (AI) techniques have been proposed to deal with this complexity and uncertainty in a similar way to human thinking and reasoning. This study proposed the use of the AdaptiveNeuro-FuzzyInferenceSystem (ANFIS) to model unconfined groundwater recharge using a set of data records from Kaharoa monitoring site in the North Island of New Zealand. Fifty-three data points, comprising a set of input parameters such as rainfall, temperature, sunshine hours, and radiation, for a period of approximately four and a half years, have been used to estimate ground water recharge. The results suggest that the ANFIS model is overall a reliable estimator for groundwater recharge, the correlation coefficient of the model reached 93% using independent data set. The method is easy, flexible and reliable; hence, it is recommended to be used for similar applications.
architecture consists of fuzzification layer, inferences process, defuzzification layer, and summation as final output layer. Typical architecture of ANFIS is shown by Figure 2. The process flows from layer 1 to layer 5. It is started by giving a number of sets of crisp values as input to be fuzzyfied in layer 1, passing through inference process in layer 2 and 3 where rules applied, calculating output for each corresponding rules in layer 4 and then in layer 5 all outputs from layer 4 are summed up to get one final output. The main objective of the ANFIS is to determine the optimum values of the equivalent fuzzyinferencesystem parameters by applying a learning algorithm using input- output data sets. The parameter optimization is done in such a way during training session that the error between the target and the actual output is minimized. Parameters are optimized by Backpropagation. The parameters to be optimized in ANFIS are the premise parameters which describe the shape of the membership functions, and the consequent parameters which describe the overall output of the system. The optimum parameters obtained are then used in testing session to calculate the prediction. A number of 730 data were utilized during training session and 365 data were used during testing session.
The hydrologic behavior of rainfall-runoff process is very complicated phenomenon which is controlled by large number of climatic and physiographic factors that vary with both the time and space. The relationship between rainfall and resulting runoff is quite complex and is influenced by factors relating the topography and climate. In recent years, artificial neural network (ANN), fuzzy logic, genetic algorithm and chaos theory have been widely applied in the sphere of hydrology and water resource. ANN have been recently accepted as an efficient alternative tool for modeling of complex hydrologic systems and widely used for prediction. Some specific applications of ANN to hydrology include modeling rainfall-runoff process. Fuzzy logic method was first developed to explain the human thinking and decision system by . Several studies have been carried out usingfuzzy logic in hydrology and water resources planning . Adaptiveneuro- fuzzyinferencesystem (ANFIS) which is integration of neural networks and fuzzy logic has the potential to capture the benefits of both these fields in a single framework. ANFIS utilizes linguistic information from the fuzzy logic as well learning capability of an ANN. Adaptiveneurofuzzyinferencesystem (ANFIS) is a fuzzy mapping algorithm that is based on Tagaki-Sugeno-Kang (TSK) fuzzyinferencesystem  and . ANFIS used for many applications such as, database management, system
The dynamics of robot manipulators are highly nonlinear with strong couplings existing between joints and are frequently subjected to structured and unstructured uncertainties. Fuzzy Logic Controller can very well describe the desired system behavior with simple “if-then” relations owing the designer to derive “if-then” rules manually by trial and error. On the other hand, Neural Networks perform function approximation of a system but cannot interpret the solution obtained neither check if its solution is plausible. The two approaches are complementary. Combining them, Neural Networks will allow learning capability while Fuzzy-Logic will bring knowledge representation (Neuro-Fuzzy). This paper presents the control of six degrees of freedom robot arm (PUMA Robot) usingAdaptiveNeuroFuzzyInferenceSystem (ANFIS) based PD plus I controller. Numerical simulation using the dynamic model of six DOF robot arm shows the effectiveness of the approach in trajectory tracking problems. Comparative evaluation with respect to PID, Fuzzy PD+I controls are presented to validate the controller design. The results presented emphasize that a satisfactory tracking precision could be achieved using ANFIS controller than PID and Fuzzy PD+I controllers
et al., 2015). However, this technique suffers from poor interpretability, since it is difficult for humans to explain the practicality and logical meaning behind the learned weights of the model (Jothiprakash & Kote, 2011; Kajornrit et al., 2013). This problem can be solved by the AdaptiveNeuroFuzzyInferenceSystem (ANFIS). ANFIS is a hybrid intelligent system which combines the fuzzy processing of Fuzzy Logic (FL) and the learning capability of ANN. The next section presents several related studies on ANFIS and its application on modeling reservoir operations, followed by the methodology, results and discussion. The last section presents the paper’s conclusions.
Analyzes the performance of classification of cancer using ANFIS with RKLM and ANFIS. In this assessment, the estimation performance, together with the training error rate is considered as the primary comparison measures. From the result it is seen that the performance of ANFIS with RKLM gives the best in estimation. The work, reported in this paper, indicates that ANFIS structure is a good candidate for identification purposes. Additionally, the elegant performance of the RKLM approach with on-line operation and with ordinary feed forward neural network. The work is in progress in the direction of improving the estimation performance through the use of ANFIS with RKLM approaches in combination.
Thermistor is a very widely used sensor especially for temperature measurement because of its fast response to small temperature changes. The high sensitivity of the thermistor leads to a non-linear behaviour which can give rise to various difficulties such as on-chip integration, direct digital display, wireless capability and so on. So, there arises a requirement for an efficient linearizer to overcome this difficulty. The thermistor is connected to an op-amp signal conditioning circuit (OSCC) which has a stable temperature-voltage relationship over the temperature range 0 °C-100 °C, but suffers with considerable non-linearity of ±12%. In this paper, an adaptiveneuro-fuzzy interference system (ANFIS) is used to reduce the non-linearity of the thermistor OSCC. The linearity error is reduced to below ±2% using the proposed methodology and thus making the system suitable to be utilized efficiently for practical applications.
– Today most organizations have discovered that advanced trainings can be considered as the key asset for modern organizations. This study presents a forecasting model that predicts intangible assets on the basis of innovation performance in organizational training using widely applied innovation criteria. The research focused on criteria, such as organization culture, ability to respond to organizational technology changes, relationship with other organizations in the training process and the use of high technology in education. The adaptiveneuro-fuzzyinference systems (ANFIS) approach has been used to verify the proposed model. It is possible to predict innovation performance and it can also adjust allocated resources to organizational training system for its innovation objectives with this method. Originality/value – A great deal of work has been published over the past decade on the application of neural networks in diverse fields. This paper presents a model that measure and forecasts the intangible assets by the development of an Adaptive Neural Network with FuzzyInferencesystem (ANFIS), using data that concern human capital, organizational support and innovativeness. The results indicate that fuzzy neural networks could be an efficient system that is easy to apply in order to accurately measure and forecast the intangible assets by measuring innovation capabilities of an organization or firm.
The aim of the research by Doubravsky and Doskocil is to present an approach of how to identify the profitability of a client in the insurance business under the condition of input data uncertainty. The solution to the decision-making problem is based on the decision to extend or renew an insurance contract for the next period (specifically two years). The solution to this problem is based on the decision- making task, which is graphically illustrated by a decision tree. This decision problem is solved for a fictitious client, but the necessary data sets are based on real data sets. The case study is represented by a tree with three lotteries, three decisions and seven terminals. The results arising from the paper serve mainly the needs of insurance companies. The main contribution of this paper is using a decision tree to provide managers with the tool to support decision-making in evaluating whether an insurance policy of a given client may be extended or not in the next period, and information about expected profitability for the next period and its confidence interval (Doubravsky & Doskocil, 2016; Doskocil & Doubravsky, 2015).
This paper presents a SNR-PSO PID controller for searching the optimal controller parameters of AVR. In this section, a PID controller using the SNRPSO algorithm was developed to improve the step transient response of an AVR system. Signal-to-Noise Ratio (SNR) algorithm are used in this paper to evaluate existence possibility of optimal value in PID parameters. This algorithm does not require a wide solution space, and the large number of searching and iterations were susceptible to related control parameters. On the other hand, this method has an effective appliance and better result for uncertainties conditions and different operation points. Signal-to-Noise Ratio algorithm has a responsible result in the nonlinear systems optimization. Signal-to-Noise Ratio (SNR) is a measure of the variation within a trial when noise factors present. It looks like a response which consolidates repetitions and reflects noise levels into one data point. SNR consolidates several repetitions into one value that reflects the amount of variation present. There SNR are defined depending on the type of characteristic desired, higher is better (HB), lower is better (LB) and nominal is best (NB). The equations for calculating S/N ratios for HB, LB or NB characteristics are given as follows :
As to further reduce the cost of the wind power genera- tion, a kind of sensorless wind speed estimator is pro- posed based on the ANFIS. Combining the wind speed estimation and the special data-acquisition mechanism in the SCADA system, a kind of optimum setting strategy is established. According to the simulation, the results show the effectiveness of the approaches. Especially, the ap- proaches can not only be the optimum setting strategy but also be the scheduling setting strategy. For the mod- ern wind power generation, the scheduling order form the grid side needs to be considered. Based on the optimum setting strategy, the way to give the setting values cor- responding to the scheduling order can also be estab- lished which will be studied in future.
Hybrid Power Systems (HPSs) is a promising solution for the shortages of electricity in several situations. However, HPSs are still facing several problems. These problems are the cost of electrical kilowatt-hour and repetitive breaking in the utility grid with existence varying loads. Besides the problem of non-optimal utilization of available renewable energy resources and the problems associated with the operation of large generators along small loads, which are the high cost of generation and the minimize in lifetime of the generator. This paper presents study and analyze the load profile and power system generation for a selected case. A fuzzy control systembased on ANFIS has been proposed to optimize the performance of the HPS. The proposed system has ten ANFIS models, which linked to the outputs of the proposed control system. All models have been trained to achieve the minimum root mean square error (RMSE). The proposed system has been built and simulated using MATLAB.