Salman Karim's repositories
Machine-Learning-TSF-Petroleum-Production
Time series forecasting (TSF) is the task of predicting future values of a given sequence using historical data. Recently, this task has attracted the attention of researchers in the area of machine learning to address the limitations of traditional forecasting methods, which are time-consuming and full of complexity. With the increasing availability of extensive amounts of historical data along with the need of performing accurate production forecasting, particularly a powerful forecasting technique infers the stochastic dependency between past and future values is highly needed. In this research, we applied machine learning approach capable to address the limitations of traditional forecasting approaches and show accurate predictions and showed comparison of different machine learning models. For evaluation purpose, a case study from the petroleum industry domain is carried out using the production data of an actual gas field of Bangladesh. Toward a fair evaluation, the performance of the models were evaluated by measuring the goodness of fit through the coefficient of determination (R2 ) and Root Mean Square Error (RMSE), Mean Squared Error (MSE) , Mean Absolute Error(MAE) and model Accuracy
CO2-Sequestration
Carbon Capture and Sequestration (CCS) has been proposed as a promising and necessary technology for mitigating CO2 and the effects of anthropogenic climate change. Deep geological formations, like saline aquifers, are pointed out as promising areas for large-scale storage of CO2. If CCS is implemented on large scale to make noticeable reductions in atmospheric CO2, then it will require a solid scientific foundation defining the coupled hydrologic–geochemical–geomechanical processes that govern the long-term fate of CO2 in the subsurface, migration behavior of CO2, trapping mechanisms, proper utilization of methods to characterize and select sequestration sites, workflow and evaluation process, simulation methods, subsurface engineering to optimize performance, well placement, injection rate and cost, approaches to ensure safe operation, monitoring technology, remediation methods, regulatory overview, and an institutional approach for managing long-term liability. To address the above issues, we demonstrated, reviewed and developed the overall workflow of the process of CO2 sequestration in this study.
HospitalManagementSystem
A database project using Oracle database, Java Servlet, Hibernate , Design Pattern, Jasper Reports that makes it easier for patient admission, making doctor’s prescription and tracking patient previous history.
AI-For-Medicine-Specialization
I have completed this specialization from Coursera by deeplearning.ai. I have uploaded the solutions of the assignments in this repo.
TimeSeries-CNN
In this project I developed Convolutional Neural Network models for univariate , multivariate , multi-step time series forecasting.
TimeSeries-LSTM
In this project I developed LSTM models for uni-variate , multivariate , multi-step time series forecasting.
BeeHive-BeeClassification
In this learning project, l have explored a dataset with annotated images of bees from various locations of US, captured over several months during 2018, at different hours, from various bees subspecies, and with different health problems. The objective is to do Exploratory Data Analysis, features engineering and develop a CNN model to classify the bees subspecies.
LiveShare
LiveShare is a free, open project that provides browsers and mobile applications with Real-Time Communications (RTC) capabilities via simple APIs. Our mission: To enable rich, high-quality RTC applications to be developed for the browser, mobile platforms, and IoT devices, and allow them all to communicate via a common set of protocols
TicTacToe-ai-java
In this Tic Tac Toe with AI, I have used Alpha-Beta Pruning algorithm and Min Max algorithm.
brainMRIclassification
the objective of this project is to build a CNN model that would classify if subject has a tumor or not base on MRI scan.
Fraud-Detection
Throughout the financial sector, machine learning algorithms are being developed to detect fraudulent transactions. In this project, that is exactly what we are going to be doing as well. Using a dataset of of nearly 28,500 credit card transactions and multiple unsupervised anomaly detection algorithms, we are going to identify transactions with a high probability of being credit card fraud.
MachineLearning
Learning Machine Learning
TSF-AirPollution
Multivariate Multi-Step Time Series Forecasting Models for Air Pollution.