
Muhammad Shah JahanHitec University · Computer Science
Muhammad Shah Jahan
MS Computer Software Engineering
About
9
Publications
4,870
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
33
Citations
Citations since 2017
Introduction
Muhammad Shah Jahan currently MS(CSE) Student at the Department of Software Engineering, NUST College of Electrical & Mechanical Engineering. Muhammad Shah does research in NLP,NLG,AL,ML, Data Mining and Software Engineering.
Additional affiliations
September 2021 - present
November 2019 - December 2020
RISETech
Position
- Engineer
Description
- A robust deep bidirectional language model and other deep learning and AI projects
November 2017 - March 2018
Coding Pixels
Position
- Web developer
Description
- I was responsible for Web development and some lead work.IT was an on going project which i have to join in middle.I have to work on codeignator .
Education
September 2018 - July 2022
October 2013 - August 2018
Publications
Publications (9)
This paper analyzes and evaluate the current level of Software Project Management And its tolls in practice in IT Industry of Pakistan. 90% IT project in Pakistan are outsourced and many international companies have built their offshore IT companies in Pakistan due to cheap employment. As mostly projects are from developed countries and are large a...
A software must do what it intends to do. The quality is core factor in IT Industry and in software products. The quality of the product is main concern of the producer and the main requirement of a customer. Software testing is the core activity of quality assurance and very important phase of software development life cycle. Quality of any system...
Feature Selection (FS) is the core part of data processing pipeline. Use of ensemble in FS is a relatively new approach aiming at producing more diversity in feature dataset, which provides better performance as well as more robust and accurate result. An aggregation step combined the output of each FS method and generate the Single feature Subset....
In transfer learning, two major activities, i.e., pretraining and fine-tuning, are carried out to perform downstream tasks. e advent of transformer architecture and bidirectional language models, e.g., bidirectional encoder representation from transformer (BERT), enables the functionality of transfer learning. Besides, BERT bridges the limitations...
In transfer learning a model is pre-trained on a large unsupervised dataset and then fine-tuned on domain-specific downstream tasks. BERT is the first true-natured deep bidirectional language model which reads the input from both sides of input to better understand the context of a sentence by solely relying on the Attention mechanism. This study p...
Risks are intrinsic part of any software project. Most software projects face severe risk during the development process, but some find minor risks. Vulnerabilities of these risks are a threat to the quality of a software product. One of the main causes that may lead to failure of the project is negligence to perform risk assessment due to a lack o...
Blockchain nodes are essential part of a blockchain network. The quality of blockchain nodes are very crucial as these are building blocks of a network. The failure of nodes may lead to the failure of network. In this paper we have discussed the meta-model for stress testing on blockchain nodes, which will test blockchain nodes. Meta-model is based...
Projects
Projects (5)
our project goal is to trained a pretrained model on larger dataset(spanbased) with change setting and parameter sharing and produce improved results
we developed a meta-model for stress testing on block chain nodes.it will be used as a meta for future testing by researchers
The goal of this project is when there is a large set of functional requirement carry same priority assigned by customer then how can we prioritize to which requirement needs to be first implement and in which cycle.We introduced a novel technique to prioritize the functional requirements on the base of non functional requirements.