Faisal Shehzad

Faisal Shehzad
COMSATS University Islamabad | CUI · Department of Computer Science

MS(Computer Science)

About

20
Publications
4,182
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
24
Citations
Introduction
I am doing research in the COMSENS lab with Dr. Nadeem Javaid. Many people are working in this lab on different domains like Blockchain technology, energy optimization, smart grid, wireless sensor network and data science field. I am researching in the data science field where my core area is to use machine learning (Naive Bayes, decision tree, support vector, etc.) and deep learning techniques (ANN, CNN, GAN, RNN, etc.) to detect non-technical losses from electricity consumption data.
Additional affiliations
February 2019 - October 2020
COMSATS University Islamabad
Position
  • Research Assistant
Description
  • I am working in COMSENS Lab as research assistant of Dr. Nadeem Javaid. We are working on different existing and incomming technologies like Blockchain technology, Smart grid, Data science, etc. I am doing research on machine learning and deep learning algorithms to detect non technical losses in electricity combustion.
Education
September 2019 - August 2021
COMSATS University Islamabad
Field of study
  • Computer science

Publications

Publications (20)
Article
Non-technical losses (NTLs) are one of the major causes of revenue losses for electric utilities. In the literature, various machine learning (ML)/deep learning (DL) approaches are employed to detect NTLs. The existing studies are mostly concerned with tuning the hyperparameters of ML/DL methods for efficient detection of NTL, i.e., electricity the...
Chapter
In this research article, we tackle the following limitations: high misclassification rate, low detection rate and, class imbalance problem and no availability of malicious or theft samples. The class imbalanced problem is severe issue in electricity theft detection that affects the performance of supervised learning methods. We exploit the adaptiv...
Research Proposal
Full-text available
In this synopsis, the first solution introduces a hybrid deep learning model, which tackles the class imbalance problem and curse of dimensionality and low detection rate of existing models. The proposed model integrates benefits of both GoogLeNet and gated recurrent unit. The one dimensional EC data is fed into GRU to remember periodic patterns. W...
Thesis
Full-text available
Data science is an emerging field, which has applications in multiple disciplines; like healthcare, advanced image recognition, airline route planning, augmented reality, targeted advertising, etc. In this thesis, we have exploited its applications in smart grids and financial markets with three major contributions. In the first two contributions,...
Article
For dealing with the electricity theft detection in the smart grids, this article introduces a hybrid deep learning model. The model tackles various issues such as class imbalance problem, curse of dimensionality and low theft detection rate of the existing models. The model integrates the benefits of both GoogLeNet and gated recurrent unit (GRU)....
Article
Full-text available
For dealing with the electricity theft detection in the smart grids, this article introduces a hybrid deep learning model. The model tackles various issues such as class imbalance problem, curse of dimensionality and low theft detection rate of the existing models. The model integrates the benefits of both GoogLeNet and gated recurrent unit (GRU)....
Article
Full-text available
In this paper, two supervised learning models based solutions are proposed for Electricity Theft Detection (ETD). In the first solution, Adaptive Synthetic Edited Nearest Neighbor (ADASYNENN) is used to solve class imbalanced problem. For feature extraction, Locally Linear Embedding (LLE) technique is utilized. Moreover, Self-Attention Generative A...
Conference Paper
Full-text available
In this research article, we tackle the following limitations: high misclassification rate, low detection rate and, class imbalance problem and no availability of malicious or theft samples. The class imbalanced problem is severe issue in electricity theft detection that affects the performance of supervised learning methods. We exploit the adaptiv...
Presentation
Full-text available
Presentation
Full-text available
In this presentation, i explain about artificial neural network, gradient descent problem, chain rule, gradient exploding and vanishing problems, drop layers, weight intialization techniques, weight optimization techniques (gradien descent, adagrad, etc) to reduce to loss value, global minima, local minima and etc.
Presentation
Full-text available
Chapter
Traditional Electronic Business (E-Business) is a process of exchanging goods and services in digital form where payment is done using electronic payment system. In traditional E-Business, banks and financial institutions are used as Third Party (TP) which has many drawbacks. The proposed model is about e-business using Internet of Things (IoT), wh...
Conference Paper
Full-text available
Traditional Electronic Business (E-Business) is a process of exchanging goods and services in digital form where payment is done using electronic payment system. In traditional E-Business, banks and financial institutions are used as Third Party (TP) which has many drawbacks. The proposed model is about e-business using Internet of Things (IoT), wh...
Chapter
During the process of charging, electric vehicle’s location is usually revealed when making payment. This brings about the potential risk to privacy of electric vehicle. We observe that the trade information recorded on blockchain may raise privacy concern and therefore, we propose a blockchain oriented approach to resolve the privacy issue without...
Chapter
The data sharing is the claim of actual scholars datasets to share and reuse in the future from any domain. The rise of blockchain technology has to increase universally and enhancement in share and reuse of scholars datasets. Despite there are numbers of security management frameworks for share data securely. However, those frameworks is a central...
Conference Paper
Full-text available
During the process of charging, electric vehicle's location is usually revealed when making payment. This brings about the potential risk to privacy of electric vehicle. We observe that the trade information recorded on blockchain may raise privacy concern and therefore, we propose a blockchain oriented approach to resolve the privacy issue without...
Conference Paper
Full-text available
The data sharing is the claim of actual scholars datasets to share and reuse in the future from any domain. The rise of blockchain technology has to increase universally and enhancement in share and reuse of scholars datasets. Despite there are numbers of security management frameworks for share data securely. However, those frameworks is a central...

Questions

Question (1)
Question
I am working on electricity theft detection using machine learning techniques. Now, I am performing data preprocessing to removes missing and null values. My concern is that electricity theft can continuously send zero measurements or not?

Network

Cited By

Projects

Projects (4)
Project
Every researcher should support and respectively😇 comment on others uploaded 👍