The Fuzzy Inference Rules ( Rule Block )

We did 3 different test to help conclude the water quality. The first testing/station i did was to see what kind of critters were living in the water. Then, my next group was to take a test to see if eutrophication was in the water. We also took

The first station we had was counting crustaceans and macroinvertebrates in the water. We found 113 critters that belonged in group 1 which means it is quality water. There were 2 organisms in group 2 which was somewhat quality water. Also, 16 critters in group 3 which means the water is very polluted. Overall, based on the critter

For standard backpropagation algorithm, an approximate steepest descent rule will be used. The performance index is approximated by equation

In order to evaluate the efficiency of the proposed method over original Apriori and FApriori [9], experiment has been conducted several times and compared the results in 3 ways.

Apart from the single objective functions considered for this problem, a combined function is also used to perform the multi-objective optimization for the FMS parameters. The function and the variable limits are given using following function. Equal weights are considered for all the responses in this multi-objective optimization problem. Hence W1 and W2 are equal to 0.5.

We have performed three test to investigate the concentration of metal, pH of water, water temperature and the level of dissolved oxygen in the river. It helps us to discover the reason of the event and find out solution.

Water Quality & Contamination Abstract My report was based on how ground water may be affected by many containments present in our surroundings. I believed that all of the water samples would have been contaminated once mixed with the soil. As I predicted vinegar filtered through the soil and came out fairly clean.

pH of (7.68, 7.95) for the sample and its duplicate and they were within the normal ranges of the surface water pH (6.5-9.0). Conductivity of (178, 186) µS/cm for the sample and its duplicate and they were within the normal ranges of (150 to 500 µS/cm) that support diverse aquatic life. TDS of (106, 111) PPM for the sample and its duplicate and they are within the normal ranges ˂ 500 PPM, “in areas of especially hard water or high salinity, TDS values may be as high as 500 mg/L”. Temperature of (51.8, 55.5) F° for the sample and its duplicate and they were within the normal ranges ˂ 77 F°. Nitrate of (0.2, 0.8) mg/l for the sample and it duplicate and they were within normal ranges of the surface water Nitrate ˂ 1 mg/l.

The results for DO include 12/3/12: 3.2 Mg/L, 13/3/13 29 Mg/L, 14/3/14 66.73 Mg/L or % saturation? 15/3/15 92% saturation, 15/9/15 85% saturation. I think 66.73 result was % saturation so that is the result I am using. Recordings of Freshwater Creek on the 22nd of February 2016 show results of DO in both Mg/L and % saturation, these results are 6.32 Mg/L and 80% saturation and for air temp 27.13 Degrees Celsius. Resource 4 shows that water and air temperature coincide with the amount of average/normal Mg/L of DO and Degrees Celsius. For 27.13 Degrees Celsius the Mg/L should be around 8, since the result is 6.32 Mg/L this is under normal amount, however it is not at 0 so the water isn’t completely contaminated/polluted. The year 2012 DO was at an extremely low 3.2 Mg/L this could have been a migration of fish such as tilapia which may have caused many fish to die off, however the next year the Mg/L was at 29 which may have been a direct result of either migrant fish killing off other fish or flooding which killed fish. A significant trend to result was the temperature were the temperature only fluctuated by less than 1.5 degree (resource 5) however that trend is broken due to 2016 results of 27.13 Degrees which is an unusual result due to the

A linear formula idea will be used and the decision variables will be labeled as follow:

The aquatic group carried out multiple environmental parameter tests by which two sample of water were taken, at the mouth and body of the Levera Pond, as well as along the seashore of Levera

Wang Ai-zhen , Ren Guo-feng [8] They determine the wash time by observing the input variables like Turbidity and turbidity change rate. In this paper the values are obtained from , the sensor of the washing machine i.e. Turbidity and turbidity change rate which is then passed to the information processing system , to process, the information was sent them to the controller. The value of input parameters are translated into fuzzy variables by the process of fuzzification, using MCU, accordance with the fuzzy inference rules and, the result is the fuzzy value. After defuzzification the crisp value, the washing time is obtained which we modify by the concept of soft computing neural

Following that, the expected values for decision nodes 6 and 7 should also be calculated. The following results were obtained:

Besides these two methods, there are many other methods or hybrid methods derived from them. It has been proven that the AI based methods are more capable and much confidence of finding the global optimum than traditional methods. However, they usually require extensive numbers (population size times generation size) of individuals evaluation that are computationally time-consuming and are not suitable for real-time OPF application. Many efforts have been made in order to reduce the computation time of using AI based method. In [12], the authors used an improved power flow model which combined with GA to accelerate the overall computation time. However, this method can only show the efficiency for the particular case which is steady state OPF without considering transient stability. [13] and [14] used a new AI based method called Jaya Algorithm and Symbiotic Organisms Search Algorithm, respectively, that shown better convergence than other methods from literatures, as a consequence, the computation time is reduced. To be summarized, these methods tried to improve the convergence rate to improve the computation efficiency, however, the numbers of call of power flow are

This section expands a brief explanation of the basic frame-work of the principal component analysis and fuzzy logic,