10:22Q4: [Principal Component Analysis]a. Write the pseudo-code of the Principal Component Analysis algorithmb. A study revels that the average temperature and energy demanded are correlated in nature. The study help to forecastthe energy demand as a function of the average temperature. The average temperature let x °F and the day's energydemand denoted as 'y' (MWH) were recorded. Compute the principal component of the given data using PCAAlgorithm as a function of Covariance matrix, Eigen values and eigenvectors of the covariance matrix, and FeaturevectorsQ6: [Aprori Algorithm]a.b.Observation NoAverage Temperature (X)Energy Demand (Y)1691462 of 4Q5: [Search Algorithm]a. Write the pseudo-code of the following search algorithmi. Uniform cost searchII. Iterative Deepening Searchb. Discuss the working principle, strength, and limitation of the following search algorithmi.Uniform cost searchii. Iterative Deepening SearchC. Consider the following initial state of eight puzzle problem, solve it using Uniform cost search to level 3 to populate the OPENand CLOSE lista.2370 70164 157 171 163 1784386 2715TIDWrite the pseudo-code of the following Apriori AlgorithmThe following dataset illustrates the list of item for each transaction. The transaction Id is labeled as (TID) likewise the List ofitem labeled (11 to 15) for respective item .The given dataset D consisting of six indivisiual transactions. Let the min.support count = and min.confidence= x 10%. Applythe apriori algorithm to generate all the frequent candidate (Ci), frequent itemsets itemsets (Li). Also, generate the association rules fromfrequent itemsets46 7571 72 74 75188List of ItemsT100 11, 12, 15T200 12, 14T300 12, 13T400 11, 12, 14T500 11,13T600 12, 13T700 11,13T800 11,12,13, 15T900 11, 12, 13Q 7: ANN-Single Layer PerceptronConsider an industrial automation and control application. It has a normalized bi-folded datasetcomprises of pressure and temperature, as shown. The model has a corresponding bi-state output(*1' motor on, '0' motor off). A Single Layer Perceptron (SLP) is required to be designed to classify a two-dimensional data. You aregiven with the following four patterns (pi) along with their target classes (t;)1P1 =tl=0P1 =,12=18 Pl=.12 = P1 =Given that the perceptron has the following initial weights, learning rate, and threshold,3 of 4respectively. Wij=[-0.1 0.2], a=0.1, and 0-0.5.Construct the Neural schema of SLP-ANN with labeled weights and neurons. Also plot the patterns in a two-dimensional space withthe decision boundary.b. Compute the actual output, error, correct percentage recognition, and trained weights for ONE epochs ONLY.Q 8: ANN-Multi-Layer PerceptronConstruct a neural schema of ANN-Multilayer Perception Network with one hidden layer for dataset which comprises of Four inputsand two outputs. Also derive the expression for actual output and trained weights of hidden and output layer using back-propagationlearning methodQ9 [Optimization]We want to construct a box whose base length is 3 times the base width. The material used to build the top and bottom cost $10/ft 2 andthe material used to build the sides cost $6/ft 2. If the box must have a volume of 50ft 3 determine the dimensions that will minimizethe cost to build the box.ucconline.ucc.edu.jm

Q4: [Principal Component Analysis] a. Write the pseudo-code of the Principal Component Analysis algorithm b. A study revels that the average temperature and energy demanded are correlated in nature. The study help to forecast the energy demand as a function of the average temperature. The average temperature let x °F and the day's energy demand denoted as 'y' (MWH) were recorded. Compute the principal component of the given data using PCA Algorithm as a function of Covariance matrix, Eigen values and eigenvectors of the covariance matrix, and Feature vectors Observation No 1 Average Temperature (X) 69 Energy Demand (Y) 146 Q6: [Aprori Algorithm] a. b. 2 of 4 Q5: [Search Algorithm] a. Write the pseudo-code of the following search algorithm i. Uniform cost search ii. Iterative Deepening Search b. Discuss the working principle, strength, and limitation of the following search algorithm Uniform cost search 2 3 4 5 6 7 70 70 71 72 74 164 157 171 163 178 75 188 i. ii. Iterative Deepening Search c. Consider the following initial state of eight puzzle problem, solve it using Uniform cost search to level 3 to populate the OPEN and CLOSE list a. 438 6 27 15 Write the pseudo-code of the following Apriori Algorithm The following dataset illustrates the list of item for each transaction. The transaction Id is labeled as (TID) likewise the List of item labeled (11 to 15) for respective item .The given dataset D consisting of six indivisiual transactions. Let the min.support count = x 10%. Apply the apriori algorithm to generate all the frequent candidate (Ci), frequent itemsets itemsets (Li). Also, generate the association rules from frequent itemsets TID List of Items T100 11, 12, 15 T200 12, 14 1300 12,13 T400 11, 12, 14 T500 11, 13 T600 12,13 1700 11, 13 T800 11,12,13, 15 1900 11, 12, 13 Q 7: ANN-Single Layer Perceptron Consider an industrial automation and control application. It has a normalized bi-folded dataset comprises of pressure and temperature, as shown. The model has a corresponding bi-state output (1 motor on, '0' motor off). A Single Layer Perceptron (SLP) is required to be designed to classify a two-dimensional data. You are given with the following four patterns (pi) along with their target classes (ti) {~=[ ¦}"=0}{m=[ 1'] ¹2²=1}{P=['1}^2=1}{=}^²=1} Given that the perceptron has the following initial weights, learning rate, and threshold, 3 of 4 respectively. Wij=[-0.1 0.2], a-0.1, and 0-0.5. Construct the Neural schema of SLP-ANN with labeled weights and neurons. Also plot the patterns in a two-dimensional space with the decision boundary. b. Compute the actual output, error, correct percentage recognition, and trained weights for ONE epochs ONLY. Q 8: ANN-Multi-Layer Perceptron Construct a neural schema of ANN-Multilayer Perception Network with one hidden layer for dataset which comprises of Four inputs and two outputs. Also derive the expression for actual output and trained weights of hidden and output layer using back-propagation learning method