Search

The goal of this research is to attain the epilepsy risk levels from Extracted features from EEG signals. This paper analyses a two-levelmethod of classification. At level one fuzzy method were endorsed to reach a multiple sub optimal solutions. Then the SVM and MRE classifiers were used to reach the singleton results. The Classifiers were compared by means of quality values. The SVM classifier accomplisher higher Quality Value of 23.02 when compared with other classifiers.

Surface roughness is an indicator of the quality of workpieces produced by machining processes. Whereas, the indicator of the productivity of the machining process is the metal removal rate. Surface roughness and metal removal rate have different characteristics. Setting the combination of turning parameters results is essential to get optimal responses. This research has been carried out of determining the parameters of the turning process to produce an optimal response with the use of environmentally friendly coolant. The turning process parameters that are varied are the cutting fluids, spindle rotation, feeding motion, and cutting depth while the tool used is the CNMG insert tool. The optimization method used is Taguchi, combined with grey and fuzzy logic. The results showed that to obtain the optimum arithmetic surface roughness, average total surface roughness and metal removal rate, the cutting fluids is set at level 1, which is soluble cold water + air pressure, level 3 spindle rotation with a value of 1200 rpm, level 3 feeding with an amount of 0.161 mm rev−1, and cutting depth level 3 of 0.5 mm.

Maintenance activities conduct to manage and preserve assets integrity. Risk assessment is used to develop interval inspection hence, maintenance strategy can arrange perfectly. On the other hand, prescriptive inspection is still used as the main consideration to determine the inspection schedule. The consequence is an ineffective inspection activity. Past expert judgement was a major consideration in resulting prescriptive schedule which probably has not been reassessed and updated at present. A quantitative assessment can cover the probability and consequence of failure through a detailed assessment. The assessment takes time to be developed which complex systems and formulas are adjusted to the actual condition. Somehow, this task might be conducted by an external party who has expert knowledge. Therefore, within this schedule vacancy, any deterioration might occur in the system. A qualitative assessment can be done to estimate risk. Local engineers, who have basic knowledge of corrosion and other damage factors, can do the qualitative assessment. The result shall update the previous prescriptive methods. In processing qualitative assessment, fuzzy methods are chosen due to their ability to cover linguistic tasks and numerical value. In this paper, fuzzy logic was used to determine the probability of failure of equipment. The result was compared to API 581 RBI assessment. At the latter, risk value from both methods was evaluated to determine the inspection interval. Both types of equipment have close results from inspection interval calculation. Mostly, the inspection interval from the fuzzy method was earlier than RBI methods. From this calculation, the fuzzy results can be used as an estimation for the local engineer’s consideration to determine any inspection based on qualitative assessment. If the result compared with an 8-years prescriptive inspection interval, inspection interval from qualitative assessment earlier conducted. It means asset integrity could be maintained more precisely. The equipment is pressure vessels in the utility area to support the boiler system from an Indonesian oil and gas company.

All Water is the most important source in the human body, healthy water can help the metabolic processes in the body perfectly. Water used by humans must be in accordance with those set by the government (Permenkes RI number 492 of 2010, regarding the requirements and supervision of water quality). Clean water according to regulations issued by the government through the Indonesian Ministry of Health is having a PH value of 6.5 - 8.5, TDS (Total Dissolved Solid) a maximum of 500 mg / L, and a maximum turbidity level is 5 NTU (Nephelometric Turbidity Unit). In the process of managing dirty water into clean water, it must be done carefully so that the germs in the water are completely gone and the people who use them are free from all diseases. From the problems above, a clean water management system has been created. This system can read the value of water suitable for use or not. Water condition readings using PH sensor, TDS (Total Dissolved solid) sensor and turbidity sensor (TSD 10). Data values from the sensor (input) are processed using fuzzy method as a logic to start the pump if the water value does not match the set point specified and display the sensor value on the LCD (Liquid Cristal Display). The results of the whole system were obtained an average error for the sr-HC04 sensor 1%, turbidity 2.12%, the TDS sensor 2.40% and the pH sensor 0.48%.

In this study using two methods, namely Sugeno Fuzzy Logic and Levenberg-Marquartd methods. The data to be used is data from used Toyota Avanza cars for Medan and surrounding areas. The use of the fuzzy method in this study is based on its superiority in solving vague problems so that it is considered to be suitable for the condition of a used car in which each unit has different conditions. The results of the use of Sugeno fuzzy data obtained will be used as input into the levenberg-marquardt (LM) network which has a fairly good ability to perform calculations, especially to predict an output with a more efficient time. LM produces an output with a small Minimun Square Error (MSE) value of 3.64 in testing with 9 hidden layers. On the other hand, to analyze the resulting error, a comparison is made between networks that have 9 hidden layers, 27 hidden layers and 81 hidden layers with the smallest MSE results obtained on a network with 9 hidden layers.

Aluminium hybrid composites and its machining receives a great attention due to their superior properties like good strength to weight ratio, good castability, machinability, and low cost, suitable for various applications in automotive and aerospace industries. CNC turning is considered as an ideal method for machining of aluminium hybrid composites. Nevertheless, the parameters of turning of aluminium hybrid composites need to be optimized for better and precise machining. Also, the presence of solid lubricants such as Carbon nanotube, Graphite, hexagonal Boron Nitride etc. promotes the machinability of aluminium hybrid composites. In this study, CNC turning on AA6061 matrix based hybrid composites reinforced with Boron carbide (5-15 vol.%) and Carbon nanotube (15 vol.%) was performed. Cutting Speed (rpm):60-180, feed (mm/rev): 0.10-0.20, depth of cut (mm): 0.50-1.00 and percentage of B4C (vol.%) 5-15 were the controlling parameters and responses namely tangential force (N), cutting power (W) and tool wear (mm3/min) were considered for the optimization. Experimental design was made as per Taguchi’s L27 orthogonal array and Grey-fuzzy analytical tool was applied for the optimization. The optimal setting for turning operation on this hybrid composite using Grey-fuzzy analysis were 120 rpm, 0.20 mm/rev, 0.5 mm and 15 vo.% for cutting speed, feed, depth of cut and reinforcement respectively.

A blind person must be protected from direct contact with unknown high-temperature objects in the surrounding environment. A system is needed to be able to detect the location and temperature of objects without direct contact. Ultrasonic sensors are used as object distance detectors and infrared temperature sensors are used as object temperature detectors without any direct contact. This system is processed with ATMega328 and information is conveyed to the user via buzzer sound signals and DC motor vibrations. The system as a whole is planted in a glove designed specifically to facilitate the user in using the tool.

Flat Electroencephalography (fEEG) is a method for mapping high dimensional signal, namely Electroencephalography (EEG) into a low dimensional space. The image of fEEG which is in grayscale form is obtained from digital fEEG by using fuzzy approach. The main aim of this paper is to reduce the spread of the vague boundary and improve the visibility of the clusters of epileptic foci in terms of contrast enhancement via Image Size Dependent Normalization (ISDN) and fuzzy technique. Contrast performance comparison between both methods are carried out for an epileptic patient at varied time, t. It shows that fuzzy method gives better contrast compared to ISDN.

The integration of Geographic Information Systems (GIS) and Multi-Criteria Decision Analysis (GIS-MCDA) are widely used in many fields. Nowadays, GIS-MCDA is combined with a fuzzy method, especially fuzzy logic, as the solutions for many problems, including site selection problem. Site selection is a process to find the most appropriate site with desired conditions by considering a number of criteria. This paper attempts to review various studies undertaken by researchers in order to implement GIS-MCDA and fuzzy method for the site selection problems. The aims of this paper are to provide an overview of the current insight of the topic, an overview of the most MDCA method and fuzzy method used, and to provide a gap for further research. Data analysis in this paper is divided into two sections, i.e. bibliometric analysis and network analysis.

The achievement assessment of salesman is an important part of enterprise. In this paper, six real selling practices to 10 salesmen of a world top 500 company were discussed on account of Fuzzy Borda measurement. The achievement assessment ranking result was 15 years before, auditing current situation of the 10 salesmen proves relevant research measurement and forecast then. The achievement assessment measurement could be used to many different industries.

The research is conducting aimed at making it easier for customers to choose formula milk products based on the nutrients most needed by infants. The method used to analyze the nutritional value data contained in formula milk products is Tahani model database fuzzy. Through several stages of the data calculation process for each variable that is determined, the final result of the processing is in the form of fire strenght or the highest value to the lowest value. The system recommends the right product based on the criteria required by the customer, ranging from the highest to the lowest, except for 0 (zero).

In the process of motion of the ground, the mobile trolley has branches of motion in the direction of the axis of X, Y and Z. However, considering that the mobile robot only has the ability of adjustment of motion on the axis of X and Y, it is said that the mode of the motion of this kind of mobile robots with constraints is not complete. The method of control used in the past is the constraint method of predictive control. The whole mobile robot can be considered as a system including three inputs and three outputs. The motion of the mobile robot in the direction of the axis of Z can be considered as a kind of disturb from the inputs with a certain effect on the axis of X and Y, but the control of the output is converted to the three parts of control used in the motion on the axis of X and Y and the control of the input of disturbance. The three systems with one independent input and one independent output are considered as the predictive control on the system including three inputs and three outputs. In this paper, the parameters of the predictive model are optimized in the way similar to an adaptive fuzzy control and based on errors and change of errors.

The purpose of this research is to analyze whether fuzzy mamdani method can be used to determine roasting time in roasting coffee process. Coffee roasting process is one of the important stages in coffee processing, because in the roasting process will determine the aroma of coffee taste. In the roasting process there is often an error in determining the duration of roasting. Improper roasting process will cause the taste of coffee is not as expected. The variables used in the roasting process include temperature, density, water content of coffee, number of copies, size of fire, and time. Since the value of each variable is unclear or uncertain, a fuzzy logic method is needed to solve this problem. Every variable used in the fuzzy method will be determined its fuzzy set. Observation was done by using temperature data 1100C density 700 gram, water content 13%, quantity 1300 gram, and fire size 500C, from observation data got roasting time 10,19 minute, where time data have match with set fuzzy made. The results show that the proposed fuzzy mamdani method can be used as a decision system in determining coffee roasting time.

The colour quality of koi was affected by the water quality in the pond. Koi fish have a diversity of types differentiated based on the body colour groups, such as one colour pattern, two colour patterns, three colours patterns and even more. Each colour characteristic of the koi have different handling, particularly in the handling of water quality, this is because the colour pigments in the body was affected by the composition of water quality include temperature, pH, TDS, do and salinity. The data of koi fish used were sanke, sowa, kohaku, shiro, yamabuki, ogon and chagoi. The aim of this study is to make an application to inform the condition of the pool water quality that can help breeders to know the water quality that will improve the handling strategies through water media. Tsukamoto Fuzzy method used to produce the three outputs namely water quality, water grade, and water conditions. The output of water quality consists of four categories, namely optimal, moderate, poor, and very poor. The output of water grade consists of grade A to D, while the output of water conditions consist of an excellent, good, bad, and very bad. Input to the application consists of five parameters, namely water temperature, pH, TDS, do and salinity.

In this paper, we propose a local fuzzy method based on the idea of "p-strong" community to detect the disjoint and overlapping communities in networks. In the method, a refined agglomeration rule is designed for agglomerating nodes into local communities, and the overlapping nodes are detected based on the idea of making each community strong. We propose a contribution coefficient to measure the contribution of an overlapping node to each of its belonging communities, and the fuzzy coefficients of the overlapping node can be obtained by normalizing the to all its belonging communities. The running time of our method is analyzed and varies linearly with network size. We investigate our method on the computer-generated networks and real networks. The testing results indicate that the accuracy of our method in detecting disjoint communities is higher than those of the existing local methods and our method is efficient for detecting the overlapping nodes with fuzzy coefficients. Furthermore, the local optimizing scheme used in our method allows us to partly solve the resolution problem of the global modularity.