Heaven’s Light is Our Guide
Computer Science & Engineering
Rajshahi University of Engineering & Technology
Course No.: CSE 2102
Course Title: Sessional based on CSE 2101
Experiment No. 1
Name of the Experiment: Implementation of Nearest Neighbor
classification algorithms with and without distorted pattern.
Course Outcomes: CO1
Learning Domain with Level: Cognitive (Applying, Analyzing,
Evaluating & Creating)
Background:
In statistics, the k-nearest neighbors’ algorithm (k-NN) is a
non-parametric supervised learning method first developed by
Evelyn Fix and Joseph Hodges in 1951[1]. It is used for both
classification and regression.
K-nearest Neighbor Classification algorithm:
• Begin by defining the value of k, which represents the number
of nearest neighbors to consider.
• Next, gather and organize the data that will be used for the
analysis. This data should include a set of labeled training
examples and a set of unlabeled test examples.
• For each test example, calculate the distance between the test
example and each training example using a distance metric, such
as Euclidean distance.
• Sort the training examples by their distance to the test
example, with the closest training examples at the top of the
list.
• Select the k training examples that are closest to the test
example.
• Determine the majority label among the k training examples and
assign that label to the test example.
• Repeat steps 3-6 for each test example, then evaluate the
accuracy of the model by comparing the predicted labels to the
true labels.
• If necessary, adjust the value of k or other parameters to
improve the accuracy of the model.
• Once the algorithm is deemed accurate, it can be used to
classify new examples.
Your task is to solve the following activities:
• Describe the characteristic of your dataset.
• Define the ratio of training set and test dataset
• Design a program
o To Apply the K-nearest neighbor algorithm as classifier,
o Analyze the accuracy of the classifier.
o Justify for which dataset, this classifier can not
perform as we expect and why.
Reference:
1. Fix, Evelyn; Hodges, Joseph L. (1951), Discriminatory
Analysis, Nonparametric Discrimination: Consistency
Properties (Report). USAF School of Aviation Medicine,
Randolph Field, Texas.
