scholarly journals Implementation of ANN Classifier for Weather Forecasting

2020 ◽  
Vol 9 (3) ◽  
pp. 2280-2284
Keyword(s):  
Data Mining ◽  
Curve Fitting ◽  
Weather Forecasting ◽  
Quantitative Information ◽  
Present Condition ◽  
Climate Forecast ◽  
Activity Curve ◽  
Ann Classifier ◽  
Future Outcomes

Once quantitative information about the present condition of the environment and barometrical procedures is collected, one can head towards the making of climate conjectures. The climate expectation is essentially found on the recorded time arrangement information. The essential Data mining tasks and Numerical strategies are utilized to get a valuable example from a gigantic volume of informational index. Diverse testing and preparing situations are performed to acquire the precise outcome. To play out these sorts of expectations I am distinguishing the datasets. We gathered the information of a specific locale climate forecast from 1901 to 2001 with 11 traits. The gathered datasets experience the pre-handling. At that point bunching activity, Curve fitting and Extrapolation strategies are applied, continuing with a back spread. The Back spread and Extrapolation results are thought about. The Best future outcomes are anticipated

Overview of Business Intelligence through Data Mining

2014 ◽  
pp. 272-295
Author(s):  
Abdulrahman R. Alazemi ◽  
Abdulaziz R. Alazemi
Keyword(s):  
Data Mining ◽  
Business Intelligence ◽  
Information Technologies ◽  
Customer Relationships ◽  
The Internet ◽  
Competitive Advantages ◽  
Large Databases ◽  
Hidden Knowledge ◽  
Internet Business ◽  
Future Outcomes

The advent of information technologies brought with it the availability of huge amounts of data to be utilized by enterprises. Data mining technologies are used to search vast amounts of data for vital insight regarding business. Data mining is used to acquire business intelligence and to acquire hidden knowledge in large databases or the Internet. Business intelligence can find hidden relations, predict future outcomes, and speculate and allocate resources. This uncovered knowledge helps in gaining competitive advantages, better customer relationships, and even fraud detection. In this chapter, the authors describe how data mining is used to achieve business intelligence. Furthermore, they look into some of the challenges in achieving business intelligence.

Application of Data Mining Techniques in Weather Forecasting

2019 ◽  
pp. 162-174 ◽  
Author(s):  
ThippaReddy Gadekallu ◽  
Bushra Kidwai ◽  
Saksham Sharma ◽  
Rishabh Pareek ◽  
Sudheer Karnam
Keyword(s):  
Data Mining ◽  
Performance Metrics ◽  
Weather Forecasting ◽  
Meteorological Data ◽  
Maximum Temperature ◽  
K Nearest Neighbors ◽  
Data Mining Techniques ◽  
Use Of Data ◽  
The City ◽  
Case Data

Weather forecasting is a vital application in meteorology and has been one of the most scientifically and technologically challenging problems around the world in the last century. In this chapter, the authors investigate the use of data mining techniques in forecasting maximum temperature, rainfall, evaporation, and wind speed. This was carried out using artificial decision tree, naive Bayes, random forest, K-nearest neighbors (IBk) algorithms, and meteorological data collected between 2013 and 2014 from the city of Delhi. The performances of these algorithms were compared using standard performance metrics, and the algorithm which gave the best results used to generate classification rules for the mean weather variables. The results show that given enough case data, data mining techniques can be used for weather forecasting and climate change studies.

Overview of Business Intelligence through Data Mining

2016 ◽  
pp. 49-72 ◽  
Author(s):  
Abdulrahman R. Alazemi ◽  
Abdulaziz R. Alazemi
Keyword(s):  
Data Mining ◽  
Business Intelligence ◽  
Information Technologies ◽  
Customer Relationships ◽  
The Internet ◽  
Competitive Advantages ◽  
Large Databases ◽  
Hidden Knowledge ◽  
Internet Business ◽  
Future Outcomes

The advent of information technologies brought with it the availability of huge amounts of data to be utilized by enterprises. Data mining technologies are used to search vast amounts of data for vital insight regarding business. Data mining is used to acquire business intelligence and to acquire hidden knowledge in large databases or the Internet. Business intelligence can find hidden relations, predict future outcomes, and speculate and allocate resources. This uncovered knowledge helps in gaining competitive advantages, better customer relationships, and even fraud detection. In this chapter, the authors describe how data mining is used to achieve business intelligence. Furthermore, they look into some of the challenges in achieving business intelligence.

Linear Regression on Internet Banking Adoption Dataset Using WEKA

2020 ◽  
Vol 12 (4) ◽  
pp. 29-37
Author(s):  
Nidhi Nigam Verma ◽  
Deepika Pathak
Keyword(s):  
Data Mining ◽  
Linear Regression ◽  
Banking Sector ◽  
Weather Forecasting ◽  
New Technology ◽  
Internet Banking ◽  
Industry Data ◽  
Large Scope ◽  
Banking Business ◽  
Linear Expression

Data mining or knowledge discovery in the database (KDD) is an excellent process to find out valuable information from a large collection of data. Data mining has successfully been used in different fields such as medical, marketing, banking, business, weather forecasting, etc. For the banking industry, data mining, its importance, and its techniques are vital because it helps to extract useful information from a large amount of historical data which enable to make useful decisions. Data mining is very useful for banking sector for better acquiring and targeting new customers and helps to analyze customers and their transaction behaviors. In the recent era, a new technology that has achieved considerable attention, especially among banks, is internet banking. Its large scope of applications, its advantages brings an immoderate change in a common human's life. Linear regression is one of the most commonly used and applied data mining techniques. Linear regression is really a very fast and simple regression algorithm and can give the best performance if the output variable of your data is a linear grouping of your inputs. In this paper, the linear regression is applied on internet banking adoption dataset in order to compute the weights or coefficients of linear expression and provides the predicted class value. The analysis here is done with the help of WEKA tool for data mining.

scholarly journals Precipitation Prediction for South West Monsoon Over Karnataka using Supervised Learning Technique

2019 ◽  
Vol 8 (3) ◽  
pp. 4450-4454
Keyword(s):  
Data Mining ◽  
Association Rules ◽  
Weather Forecasting ◽  
Grid Point ◽  
Time Series Prediction ◽  
Data Mining Technique ◽  
Data Framework ◽  
South West ◽  
South West Monsoon ◽  
West Monsoon

Weather forecasting is a major field of study in the area of Meteorology. Data Scientists, meteorologists and weather forecasters are implementing the experimentation of weather forecasting base on numerical and statistical methods. Traditional models used the fluid and thermal dynamic strategies for grid-point time series prediction based on few inherited constraints, such as the adoption of incomplete boundary rules, model assumptions and numerical instabilities. The nominated work is focused on finding the south west monsoon months’ precipitation patterns over the specific stations of Karnataka State. A multi-dimensional data framework for climate database with implementation online based data analysis has been developed. This works is carried out on the basis of monsoons that have prevailed during a year for the past 10 years. The proposed model emphasis the implementation of the association rules which has been extracted by the supervised classifier approach of data mining algorithms. The data mining technique of association rules emphasis the occurrence of the precipitation and will be helpful to take decisions in advance to the day to day operations in business, agriculture, water management and etc.

scholarly journals Weather Forecasting and Climate Changing Using Data Mining Application

IJARCCE ◽  
2015 ◽  
pp. 19-21 ◽  
Author(s):  
Ankita Joshi ◽  
Bhagyashri Kamble ◽  
Vaibhavi Joshi ◽  
Komal Kajale ◽  
Nutan Dhange
Keyword(s):  
Data Mining ◽  
Weather Forecasting ◽  
Using Data ◽  
Data Mining Application

Analysis of Myocardial Time-Activity Curves of 123I-Heptadecanoic Acid I. Curve Fitting

1987 ◽  
Vol 26 (06) ◽  
pp. 241-247 ◽  
Author(s):  
F. C. Visser ◽  
C. M. B. Duwel ◽  
P. D. Bezemer ◽  
G. Westera ◽  
A. J. P. Karreman ◽  
...  
Keyword(s):  
Curve Fitting ◽  
Background Activity ◽  
Half Time ◽  
Time Activity ◽  
Time Value ◽  
Fitting Method ◽  
Activity Curve ◽  
Strong Relation ◽  
Curve Fitting Method

Myocardial time-activity curves can be described by two or more parameters. To establish the optimal curve fitting method 33 myocardial time-activity curves were analyzed with different curve fitting methods: monoexponential, biexponential and monoexponential plus constant. A background correction was not applied. Biexponential curve fitting resulted in redundancy of parameters. Optimal curve fitting was obtained with monoexponential plus constant. The constant represents the background activity together with the stored radiolabelled lipids and the half-time value represents the wash-out of radioiodide from the myocardium. A strong relation was found between the constant and the half-time value: small errors in the determination of the constant (background activity) resulted in considerable errors of the half-time value. It is concluded that optimal analysis of a myocardial time-activity curve can be performed with a monoexponential plus constant without earlier correction for background activity.

Rules Extraction using Data Mining in Historical Data

2016 ◽  
pp. 263-279
Author(s):  
Manish Kumar ◽  
Shashank Srivastava
Keyword(s):  
Data Mining ◽  
Weather Forecasting ◽  
Satellite Communications ◽  
Building Blocks ◽  
Predictive Analysis ◽  
Rule Based ◽  
Using Data ◽  
Rules Extraction ◽  
The Impact ◽  
Expected Outcomes

Rules are the smallest building blocks of data mining that produce the evidence for expected outcomes. Many organizations like weather forecasting, production and sales, satellite communications, banks, etc. have adopted this mode of technological understanding not for the enhanced productivity but to attain stability by analyzing past records and preparing a rule-based strategy for the future. Rules may be extracted in different ways depending on the requirements and the dataset from that has to be extracted. This chapter covers various methodologies for extracting such rules. It presents the impact of rule extraction for the predictive analysis in decision making.

Employing Neural Networks in Data Mining

2011 ◽  
pp. 433-437
Author(s):  
Mohamed Salah Hamdi
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Risk Management ◽  
Operating Systems ◽  
Predictive Models ◽  
Mining Technology ◽  
Business Outcomes ◽  
Revenue Growth ◽  
Future Outcomes ◽  
Electronic Information Sharing

Data-mining technology delivers two key benefits: (i) a descriptive function, enabling enterprises, regardless of industry or size, in the context of defined business objectives, to automatically explore, visualize, and understand their data and to identify patterns, relationships, and dependencies that impact business outcomes (i.e., revenue growth, profit improvement, cost containment, and risk management); (ii) a predictive function, enabling relationships uncovered and identified through the data-mining process to be expressed as business rules or predictive models. These outputs can be communicated in traditional reporting formats (i.e., presentations, briefs, electronic information sharing) to guide business planning and strategy. Also, these outputs, expressed as programming code, can be deployed or hard wired into business-operating systems to generate predictions of future outcomes, based on newly generated data, with higher accuracy and certainty.

Sign in / Sign up

Export Citation Format

Share Document