Fruit2You wholesaler has a warehouse that stores a variety of fruits and vegetables. When fruit is brought to the warehouse, various types of fruit might be mixed together especially between orange and apple which come from the same farm The wholesaler aims to have a machine that will sort the fruit according to type. Currently, there is a conveyer belt on which the fiuit is loaded. This conveyer passes through a set of sensors, which measure three properties of the fruit: shape, texture and weight. These sensors are somewhat primitive. The shape sensor will output as 1 if the fiuit is approximately round and as - 1 if it is more elliptical. The texture sensor will output as 1 if the surface of the fruit is smooth and as -1 if it is rough. The weight sensor will output as 1 if the fruit is more than 450g and as -1 if it is less than 450g. As a control engineer, you have been instructed to propose an automatic sorting system using neural network which able to decide what kind of fruit is on the conveyer so that the fruit can be directed to the correct storage bin as illustrated in Figure Q4. As each fruit will pass through all the sensors, it can be represented by a three-dimensional vector as below: shape p= texture whereas a prototype of orange (p1) would be represented by weight 1 and a prototype of apple (p2) would be represented by [1 a) By using the Supervised Hebbian Learning method, obtained the weighted matrix and analyse the performance of the proposed neural network model. (5 marks) b) Apply the Unsupervised Hebbian Learning method to obtain the network weighted and analyse the performance of the proposed neural network model. (7 marks) c) Apply the Perceptrons Learning method to obtain the network weighted and analyse the performance of the proposed neural network model. Choose a=1, and e=0.5. (8 marks) d) Based on the evaluation and results obtained from (a)-(), which model you will propose to the management. Why? (5 marks) Hint :- Assume that there are only two kinds of fruit on the conveyor: apples and oranges whereas output 1 represents apples and output - 1 represents oranges. Neural Network Sensors Sorter Apples Oranges Figure Q4 Fruit2You wholesaler has a warehouse that stores a variety of fruits and vegetables. When fruit is brought to the warehouse, various types of fruit might be mixed together especially between orange and apple which come from the same farm The wholesaler aims to have a machine that will sort the fruit according to type. Currently, there is a conveyer belt on which the fiuit is loaded. This conveyer passes through a set of sensors, which measure three properties of the fruit: shape, texture and weight. These sensors are somewhat primitive. The shape sensor will output as 1 if the fiuit is approximately round and as - 1 if it is more elliptical. The texture sensor will output as 1 if the surface of the fruit is smooth and as -1 if it is rough. The weight sensor will output as 1 if the fruit is more than 450g and as -1 if it is less than 450g. As a control engineer, you have been instructed to propose an automatic sorting system using neural network which able to decide what kind of fruit is on the conveyer so that the fruit can be directed to the correct storage bin as illustrated in Figure Q4. As each fruit will pass through all the sensors, it can be represented by a three-dimensional vector as below: shape p= texture whereas a prototype of orange (p1) would be represented by weight 1 and a prototype of apple (p2) would be represented by [1 a) By using the Supervised Hebbian Learning method, obtained the weighted matrix and analyse the performance of the proposed neural network model. (5 marks) b) Apply the Unsupervised Hebbian Learning method to obtain the network weighted and analyse the performance of the proposed neural network model. (7 marks) c) Apply the Perceptrons Learning method to obtain the network weighted and analyse the performance of the proposed neural network model. Choose a=1, and e=0.5. (8 marks) d) Based on the evaluation and results obtained from (a)-(), which model you will propose to the management. Why? (5 marks) Hint :- Assume that there are only two kinds of fruit on the conveyor: apples and oranges whereas output 1 represents apples and output - 1 represents oranges. Neural Network Sensors Sorter Apples Oranges Figure Q4