Dr. Imran Ihsan - Ph.D in Knowledge Graphs, Explainable AI

Navigation

Final Year Projects (27)

#27. MetaClass

A Virtual Reality Based Metaverse Classroom

Tools & Technologies: XR, Unity, Oculus, Metaverse

2022 - 2023
Status: FYP 1

Area: Virtual Reality, XR

#26. Citation Rope

Semantically Connected Citation Graph Generational Tool

Tools & Technologies: Node.js, Angular, Express, MongoDB, jSon, React D3

2021 - 2022
Status: FYP 3

Area: Knowledge Graph, Graph Visualization

#25. P-CAT

Packet Capture Analyzer Tool

Tools & Technologies: Wireshark, PHP/MySQL, HTML/CSS, BootStrap

2021 - 2022
Status: FYP 3

Area: Computer Networks, Protocol Analysis

#24. DDI

Knowledge Graph Embedding for Drug-Drug Interaction

Tools & Technologies: Google Colab, Python, TensorFlow, Spacy

2020 - 2021
Status: FYP 3

Area: Knowledge Graph, Semantic Web, Health Informatics

#23. SMIP

Stock Market Index Prediction Using Linked Open Data

Tools & Technologies: Google Colab, Python, Tweepy, Spacy, NLTK

2020 - 2021
Status: FYP 3

Area: Machine Learning, NLP, Sentiment Analysis, Linked Open Data

#22. TCP

Telecom Churn Prediction Model

Tools & Technologies: Google Colab, Python

2020 - 2021
Status: FYP 3

Area: Machine Learning, Churn Prediction, Data Science

#21. AichQ

A Final Year Project Management System

Tools & Technologies: HTML CSS, BootStrap, Angular JS, MongoDB, Full Stack

2020 - 2021
Status: FYP 3

Area: Web Application, Responsive, Project Management

#20. Emotisys

Automated Analysis of Emotions through Speech Patterns using Machine Learning

Tools & Technologies: PyCharm, TensorFlow, Librosa, Keras, Scipy, Sk-learn, Matplotlib, Numpy, Pandas

2019 - 2020
Status: FYP 3

Area: Machine Learning, Speech Analysis, IMCC

Abstract

This thesis topic is about the detection of emotions through speech patterns. The main concept behind our project is SER that is Speech Emotion Recognition which is the detection of human emotions from speech. It focuses on the point that the human voice often reflects and resonates the emotion behind it. Some of the main classes of emotions that we have worked on are happiness, sadness, fear, neutral, anger, boredom, disgusted etc. One of the main objectives of our project was the collection of data of audio files. With the help of different databases, we obtained the required data sets. Extraction of features out of those audio files was done. Every audio file has various underlying features which are the basis of the differentiation among the audios. Some of those features are Pitch, Frequency, MFCCs, and Spectral Roll Of etc. For the implementation, we worked with Chroma � Short Time Fourier Transform, RMSE, Spectral Rollof, Spectral Centroid, Spectral Flux, Spectral Bandwidth, Zero Crossing Rate (ZCR) and 20 sets of MFCCs The basic problem that we found a solution to, was the maximum accuracy of the detected emotion. A single feature applied on an algorithm, generates a result that is a value in percentage might be totally different to the value generated by the combination of two features applied on the same algorithm. We chose three different datasets from RAVDESS, SAVEE and EMODB Berlin, respectively. For each of these data sets we extracted the features and made the combinations out of them to create feature vectors. Once, it was done, 3 different machine learning models CNN, MLP and SVM were introduced. We applied these algorithms one by one on each dataset to find the accuracy values. All 3 of the datasets generated different accuracy values for each of the model. We found that the dataset from EMODB Berlin had proven to work the best for us. When SVM was applied on it, it gave an accuracy of 82.00 % which is higher than the research paper we referred for this experimentation. We worked with deep learning as well and chose to apply CNN on one of the datasets. WEKA does not support CNN, so we implemented it using Python. The accuracy value we obtained was 72.00 % using EMODB Berlin. After these two, the same dataset was used and MLP was applied on it. This time it gave the highest accuracy of 85.35 %. The implicit aim was the processing of the extracted feature set by machine learning. We applied different algorithms to detect the emotions and generate its accuracy. Since, CNN could not be tested on WEKA its Python implementation was done. This way we had three multiple accuracy values against the three datasets, when 3 different machine learning algorithms were applied on them, respectively. We analyzed and compared the values from all of these approaches. And our goal was to find the best-fit algorithm for a specific feature set which turn out to be an achievement for us since we got 82.00 % and 85.35 % with SVM and MLP respectively.

#19. Fallup

Fall Risk Assessment and Prediction Based on Gait Analysis
IGNITE NGIRI PKR 58,000

Tools & Technologies: Pandas, Matplotlib, Sklearn, Glob, TensorFlow, Apachi POI, Google API, SQ Lite, Android Studio, FitBit Api

2019 - 2020
Status: FYP 3

Area: Machine Learning, Health Informatics, Gait Analysis, Wrist Wearable, IOT

#18. GlucoGaurd

Smartphone Based Continuous Glucose Monitoring
IGNITE NGIRI PKR, 55,000

Tools & Technologies: Pandas, Numpy, Matplotlib, Scikit-Learn, Google Collab

2019 - 2020
Status: FYP 3

Area: Machine Learning, Health Informatics, Supervised Learning

#17. PSLO

Pakistan Sign Language Ontology
Best Project Award - Pakistan Science Fair 2019

Tools & Technologies: NLTK, POS Tagger, Protege, RDF/RDFs, OWL

2019 - 2020
Status: FYP 3

Area: Ontology, Sign Language, Bilingual, NLP

#16. Trivia

Knowledge Graph Embedding in Citation Data

Tools & Technologies: Spacy, Ampligraph, Tensorflow, Numpy, Pandas, Matplotlib, Seaborn, Scikit learn, Xgboost

2019 - 2020
Status: FYP 3

Area: Knowledge Graph, Scientometrics, Citation Analysis, NLP, Semantic Web

#15. WHINY

Audio Pattern Recognition of Crying Baby

Tools & Technologies: Pandas, SKlearn, PyAudio Analysis, LibROSA, Matplotlob, Joblib, Transformer API, Numpy, Pickle

2019 - 2020
Status: FYP 3

Area: Machine Learning, Audio Pattern Recognition, Regression

#14. Smart Buddy

Detection and Classification of Breast Cancer Abnormalities

Tools & Technologies: Tensorflow, Github, Keras, Inception V3, Sigmoid, Max Pooling, Relu Activation Function, Matplotlib

2019 - 2020
Status: FYP 3

Area: Deep Learning, Health Informatics, CNN, Supervised Learning

#13. DEVA

Decentralized Voting Application

Tools & Technologies:

2019 - 2020
Status: FYP 3

Area: BlockChain, Ethereum, Cyber Security

#12. LVO

Levin's Verb Ontology

Tools & Technologies: RDF, RDFs, OWL, SWRL Rules, Prot�g�

2019 - 2020
Status: FYP 3

Area: Ontology, Semantic Web, NLP

#11. AU360

Air University 360 Degree Experience
Air University PKR. 150,000

Tools & Technologies: 3D Vista, Adobe Photoshop, CorelDraw

2018 - 2019
Status: FYP 3

Area: Virtual Reality, 360 Experience

#10. PHASSE

Pharmaceutical Semantic Search Engine
Best Project Award - ICTMPCL 2019

Tools & Technologies: Microsoft .NET Framework, Android Studio, RDF/RDFa, SPARQL, Python, NLP, Bio2RDF

2018 - 2019
Status: FYP 3

Area: Semantic Web, Linked Open Data, Faceted Search, Bio2RDF

#9. IntelliAgents

Multi Machine Learning Agents in Unity using TensorFlow

Tools & Technologies: Unity3D, Tensor-Flow Hub

2018 - 2019
Status: FYP 3

Area: Gaming Machine Learning, Deep_Learning, TensorFlow

#8. OSAP

Ontology Based Semantic Authoring and Publishing

Tools & Technologies: Microsoft .NET MVC, Microsoft SQL Server, RDF/RDFa, SPARQL, GraphViz, OWL

2018 - 2019
Status: FYP 3

Area: Semantic Web, Ontology, LATEX

#7. RPAT

Research Paper Analytic Tool

Tools & Technologies: Microsoft .NET Framework, Microsoft SQL Server, Python NLTK, SPYDER, D3 JS Visulaization

2018 - 2019
Status: FYP 3

Area: Scientometrics, Data Science, NLP

#6. TeachTech

Lets Teach Together

Tools & Technologies: Microsoft .NET MVC, Microsoft SQL Server, Node JS, HTML5, Web Sockets, WebRTC

2018 - 2019
Status: FYP 3

Area: eLearning, Collaborative Learning

#5. Health Hub

An AI Based Heart Attack Prediction App
Microsoft Imagine Cup 2018 - Regional Winner

Tools & Technologies: Microsoft .NET Framework, ASP.NET MVC, ARDUINO, Bayesian Network, SQL Server, Microsoft Azure

2017 - 2018
Status: FYP 3

Area: AI, Machine Learning, Bio Tech, Wearable

#4. CSAT

Citation Sentiment Analysis Tool
First Prize Winner - AirTech 2016

Tools & Technologies: Microsoft .NET Framework, C#, Python, GraphViz, TikkaDotNet, Stanford Core NLP, Lemma Sharp, NLTK, Metro Framework

2016 - 2017
Status: FYP 3

Area: Semantic Web, NLP, Sentiment Analysis

#3. SABAQ

Semantic E-Learning and Experience Tracking App

Tools & Technologies: APS.NET, C#, SPARQL, RDF/RDFs, dotNetRDF, QuickGraph, Graphviz, HTML5, CSS, Bootstrap, JQuery

2016 - 2017
Status: FYP 3

Area: eLearning, Semantic_Web, Noorani Qaida

#2. BiBEd

Online Bibliography Editor

Tools & Technologies: ASP.NET MVC, C#, HTML 5, BootStrap, JavaScript, Microsoft SQL Server

2015 - 2016
Status: FYP 3

Area: Citation, Data Mining, Web Services

#1. SPoint

A Semantic Based E-Learning Content Development Tool

Tools & Technologies: Microsoft .NET Framework, Semantic UI, HTML 5, CSS 3, JavaScript

2014 - 2015
Status: FYP 3

Area: ELearning, MOOCs, SemanticWeb

Supervision - Final Year Projects

Final Year Projects (27)

MetaClass - A Virtual Reality Based Metaverse Classroom

Abstract

Citation Rope - Semantically Connected Citation Graph Generational Tool

Abstract

P-CAT - Packet Capture Analyzer Tool

Abstract

DDI - Knowledge Graph Embedding for Drug-Drug Interaction

Abstract

SMIP - Stock Market Index Prediction Using Linked Open Data

Abstract

TCP - Telecom Churn Prediction Model

Abstract

AichQ - A Final Year Project Management System

Abstract

Emotisys - Automated Analysis of Emotions through Speech Patterns using Machine Learning

Abstract

Fallup - Fall Risk Assessment and Prediction Based on Gait Analysis

Abstract

GlucoGaurd - Smartphone Based Continuous Glucose Monitoring

Abstract

PSLO - Pakistan Sign Language Ontology

Abstract

Trivia - Knowledge Graph Embedding in Citation Data

Abstract

WHINY - Audio Pattern Recognition of Crying Baby

Abstract

Smart Buddy - Detection and Classification of Breast Cancer Abnormalities

Abstract

DEVA - Decentralized Voting Application

Abstract

LVO - Levin's Verb Ontology

Abstract

AU360 - Air University 360 Degree Experience

Abstract

PHASSE - Pharmaceutical Semantic Search Engine

Abstract

IntelliAgents - Multi Machine Learning Agents in Unity using TensorFlow

Abstract

OSAP - Ontology Based Semantic Authoring and Publishing

Abstract

RPAT - Research Paper Analytic Tool

Abstract

TeachTech - Lets Teach Together

Abstract

Health Hub - An AI Based Heart Attack Prediction App

Abstract

CSAT - Citation Sentiment Analysis Tool

Abstract

SABAQ - Semantic E-Learning and Experience Tracking App

Abstract

BiBEd - Online Bibliography Editor

Abstract

SPoint - A Semantic Based E-Learning Content Development Tool

Abstract