A5056417442- Forecasting Techniques and Applications
- Stock Market Forecasting Methods
- Energy Load and Power Forecasting
- Time Series Analysis and Forecasting
- Security in Wireless Sensor Networks
- Network Security and Intrusion Detection
- Anomaly Detection Techniques and Applications
National University of Computer and Emerging Sciences
2022-2024
Iqra University
2016-2018
The main objective of this research is to predict the market performance Karachi Stock Exchange (KSE) on day closing using different machine learning techniques. prediction model uses attributes as an input and predicts Positive & Negative. used in includes Oil rates, Gold Silver Interest rate, Foreign (FEX) NEWS social media feed. old statistical techniques including Simple Moving Average (SMA) Autoregressive Integrated (ARIMA) are also input. Single Layer Perceptron (SLP), Multi-Layer...
Securing a network from potential attacks has become great challenge after the advent of sensor networks that consists different sensors connected by wireless settings, to sense and share collected data. Such can be compromised including not limited Denial Services (DOS), Distributed DOS, Man-in-the-Middle types attacks. Detecting these early is challenging task. Like many other fields, Machine Learning Deep utilized here predict attack early. This research uses Long Short-Term Memory (LSTM)...
Time series analysis is pivotal for business and financial decision making, especially with the increasing integration of Internet Things (IoT). However, leveraging time data forecasting requires extensive preprocessing to address challenges such as missing values, heteroscedasticity, seasonality, outliers, noise. Different approaches are necessary univariate multivariate series, Gaussian non-Gaussian stationary versus non-stationary series. Handling alone complex, demanding unique solutions...
Energy is of paramount importance for the world, and it a fundamental driver economic growth development. Industries, businesses, households rely on energy even small task. Due to its high demand, significant portion global population still lacks access reliable affordable sources. Many industries sectors continue waste amounts through inefficiencies. While essential, production consumption can have environmental consequences. Predicting power usage help significantly improve efficiency,...
In this research, a stock market prediction model was proposed to predict performance of Karachi Stock Exchange (KSE), now merged into Pakistan (PSX). The comprised four sub-models that were all based on different machine learning technique. Each sub-model used 6 input attributes including fuel price, commodity, foreign exchange, interest rate, general public sentiment and related NEWS. historical data the also for predicting using statistical techniques like Auto-Regressive Integrated...