Development of Whale Optimization Neural Network for Daily Water Level Forecasting

Prediction of water level functioned by the local government Jakarta has only been tidal forecasts or predictions of water levels at sea. At present there is no open and close floodgate regulation system either through mathematical calculations or decision-making models that produce accurate numbers. The purpose of this research is to find out what parameters are involved in determining the floodgate opening using the water flow algorithm (WFA) method. It operated to model the river water flow to get the best decision for opening and closing floodgate in flood control of Manggarai floodgate in Jakarta. This research used quantitative data analysis method. The data reported was real data coming from the field. At the end of this study, the relationship between water level reported every hour and the amount of time needed for the water reservoir at the Manggarai floodgate to be fully alerted has been determined. WFA implemented academically in this study was functioned to predict the flow of water at the Manggarai floodgate, as a result of the flow of water coming from the Katulampa weir. Based on the prediction results of the water discharge, we are able to get the volume of water from the Manggarai floodgate, thus we are able to determine open decisions close at the Manggarai floodgate.

Section: Related Workmentioning

confidence: 99%

Water-Flow-Like Algorithm based Decision Support Model for Flood Control Operation System

2020

“…Tawarish, M. & Satyanarayana [22] in his review emphasized about the decision tree approach and other versatile methods to find the price band. Haur Teng & king Kouk [23] improved the whale optimization technique for dedicated prediction techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

Stock Price Prediction Using Tech News Based Soft Computing Approach

Suganya¹

2020

In the stock market prediction foremost basic factor is the output stock price. What is more there's the test of demonstrating whether the stock market sectors are sure or not. The foregone behavior conclusion of the market is a difficult task and that has been much mentioned by researchers and data science observers. In our proposed work and by day to day stock price observance and intense research we find out that the future stock price information in accordance with particular stock details may influence the stock price significantly. Even though many adhoc methods are there in real time, this concept significantly improves the performance of the stock price prediction with respect to that of environmental factors. Our methodology reads the appropriate news channel and in convergence with the soft computing results a good predictive development. Additionally they accept that the stock trade follows a stochastic procedure, which recommends that the best forecast depends on the present stock information. The suggestions of news will be cross checked with the experts group.

“…The existence of local solutions is one of the problems in addressing optimization in ANN. In a single-objective search area there is only one best solution, often known as the Global Optimum [45].…”

Section: Mlpmentioning

confidence: 99%

Breast Cancer Predictive Analytics Using Supervised Machine Learning Techniques

Akinsola¹

2019

Breast cancer unarguably has been the very prominent disease amongst women as well as the next most dangerous after lung cancer. Early diagnosis and prevention is of paramount importance. Several methods such as micro-array analysis and network analysis have been proffered but they are somewhat expensive and time consuming. There is a need to develop an automated system based on Machine learning techniques to detect breast cancer early. Benign and Malignant tumors were classified using Logistic Regression (LRO), Bayes Network (BNK), Multilayer Perceptron (MLP), Sequential Minimal Optimization (SMO), J48, Naive Bayes (NBS) and Instance Based Learner (IBK) algorithms, which were implemented in Waikato Environment for Knowledge Analysis (WEKA). The breast cancer database for this study was collected from the University of Wisconsin Hospitals, published on California College, Irvive (UCI) website. The five most critical performance metrics when selecting an algorithm in model building in the health related domain are Area Under the ROC Curve (AUC), Receiver Operating Characteristics Curve (ROC), Mean Absolute Error (MAE), Accuracy and Kappa Statistic. In relation to the results of Accuracy, Precision and Kappa Statistic which were evaluated and compared, BNK has best predictive accuracy of 97.14%, followed by SMO with 96.71%, then LOR with 96.57%. On the other hand, LOR has the highest AUC of 99.3%, followed by BNK with 99.2%, then SMO with 96.5%. Beyond accuracy, AUC should be keenly considered in algorithm selection and model building. Therefore, Logistic Regression should be chosen as the best classifier instead of Bayes network for breast cancer optimal prediction.