Final project | PENTACODE

In 2014, Malek and his team conducted a study on two lakes named Chini and Bera. They collected samples from 2005 to 2009. The data sample consisted of 11 parameters which were used to predicate Dissolved Oxygen  concentration. The Dissolved Oxygen concentration was dichotomized into three different levels such as, High, Medium and Low. They ranked the input parameters and they used forward selection method to determine the optimum parameters that yield the lowest errors and highest accuracy. The initial results showed that pH, temperature and conductivity significantly affect the prediction of Dissolved Oxygen. Then, they applied SVM model using the Anova kernel with those parameters yielded 74% accuracy rate. They concluded that using dichotomized value of Dissolved Oxygen yields higher prediction accuracy than using precise Dissolved Oxygen  value and ANOVA is the most appropriate kernel to obtain the highest accuracy.

At Terengganu River, Malaysia, a study was conducted to predict Dissolved Oxygen using SVM. They conducted the study for two different stations using the five parameters such as, pH, temperature, electrical conductivity and Nitrate and Ammonia Nitrogen. They used SVM with its non-linear and stochastic modelling proficiencies. The performance of the model was evaluated using three statistical indexed such as, Mean Squared Error (MSE), Coefficient of Efficiency (CE) and coefficient of Correlation (CC). They concluded that SVM can give robust and precise result and able to give fairly accurate predictions. It can also help in optimizing the water quality monitoring programs.

                                                         This research work aims to compare the performance of the data mining algorithms with soil limitations and soil conditions in respect of the following characteristics: Acidity, Alkalinity and sodality, Salinity, Phosphorus fixation, cracking and swelling properties, Depth, Soil density and Nutrient content. This overall process of finding useful knowledge in raw data involves the following steps: 1.      Developing an understanding of the application domain 2.      Creating a target dataset based on an intelligent way of selecting data by focusing on a subset of variables or data samples 3.      Data cleaning and pre–processing 4.      Data reduction and projection 5.      Choo...

                                                                 Pipe breaks in urban water distribution network lead to significant economic and social costs, putting the service quality as well as the profit of water utilities at risk. In this method we use Data mining prediction method to detect pipe failures. For this prediction they used raw dataset provided by the water utility consists of records of over 500,000 water pipes, adding up to almost 6,000 kilometers in length. In here pipe break prediction task as a ranking problem, which tries to rank pipes according to their break risks, without estimating the true risks.                                                         ...

What are the steps used in Machine Learning? There are 5 basic steps used to perform a machine learning task: Collecting data : Be it the raw data from excel, access, text files etc., this step (gathering past data) forms the foundation of the future learning. The better the variety, density and volume of relevant data, better the learning prospects for the machine becomes. Preparing the data : Any analytical process thrives on the quality of the data used. One needs to spend time determining the quality of data and then taking steps for fixing issues such as missing data and treatment of outliers. Exploratory analysis is perhaps one method to study the nuances of the data in details thereby burgeoning the nutritional content of the data. Training a model : This step involves choosing the appropriate algorithm and representation of data in the form of the model. The cleaned data is split into two parts – train and test (proportion depending on the p...

When do we use KNN algorithm? KNN can be used for both classification and regression predictive problems. However, it is more widely used in classification problems in the industry. To evaluate any technique we generally look at 3 important aspects: 1. Ease to interpret output 2. Calculation time 3. Predictive Power Let us take a few examples to  place KNN in the scale : KNN algorithm fairs across all parameters of considerations. It is commonly used for its easy of interpretation and low calculation time. How does the KNN algorithm work? Let’s take a simple case to understand this algorithm. Following is a spread of red circles (RC) and green squares (GS) : You intend to find out the class of the blue star (BS) . BS can either be RC or GS and nothing else. The “K” is KNN algorithm is the nearest neighbors we wish to take vote from. Let’s say K = 3. Hence, we will now make a circle with BS as center just as big as to enclose only three data points on the p...

Predicting and Analyzing Water Quality using Machine Learning  A Comprehensive Model   INTRODUCTION                                                                 This issue has been addressed in many previous researches, however, more work needs to be done in terms of effectiveness, reliability, accuracy as well as usability of the current water quality management methodologies. The goal of this study is to develop a water quality prediction model with the help of water quality factors using Artificial Neural Network (ANN) and time-series analysis. Previous works about Water Quality prediction have also been analyzed and future improvements have been proposed in this paper. The deteriorating quality of natural water resources like lakes, streams and estuaries, is one of the direst and most worr...

Machine Learning Algorithms