Sheharyar K. Profile

JELAJAHI

0,0

(0 ulasan)

Sekarang Anda mengikuti

Kesalahan mengikuti pengguna.

Pengguna ini tidak mengizinkan pengguna mengikuti dia.

Anda sudah mengikuti pengguna ini.

Paket keanggotaan Anda hanya boleh punya 0 follow. Tingkatkan di sini.

Berhasil berhenti mengikuti

Kesalahan mengikuti pengguna.

Anda telah berhasil merekomendasikan

Kesalahan merekomendasikan pengguna.

Ada sesuatu yang salah. Silakan muat ulang halaman dan coba lagi.

Email berhasil diverifikasi.

$10 USD / jam

wah cantt,

pakistan

$10 USD / jam

Saat ini 7:30 PM di sini

Bergabung Januari 5, 2012

0 Rekomendasi

Sheharyar K.

@sherykhan186

0,0

(0 ulasan)

0,0

$10 USD / jam

wah cantt,

pakistan

$10 USD / jam

N/A

Pekerjaan Selesai

N/A

Sesuai Anggaran

N/A

Tepat Waktu

N/A

Tingkat Rekrut Ulang

Research, Machine Learning ,Matlab, Python Tasks

I am Sheharyar Khan, a dedicated Computer Science professional with a recently acquired Master of Science (MS) degree from the University of Engineering and Technology Taxila, where I graduated with distinction, achieving a cumulative GPA of 3.58. Here is my research gate profile [login to view URL] My academic journey has been marked by a profound passion for research, specifically centered around Human Activity Recognition using smartphone sensors and Brain-Computer Interface (BCI) technologies employing EEG headsets. Research Achievements: During my master's program, I have made significant contributions to the field of computer science, resulting in the authorship and co-authorship of impactful papers. Notable among these are: "A Framework for Daily Living Activity Recognition using Fusion of Smartphone Inertial Sensors Data" . "User Recognition based on Gait Pattern via Smartwatch Accelerometer in Unrestricted Environment". "Identification of Human Activity and Associated Context Using Smartphone Inertial Sensors in Unrestricted Environment" "Statistical Analysis of Cricket Leagues Using Principal Component Analysis". "A Machine Learning Based Depression Screening Framework using Temporal Domain Features of the Electroencephalography Signals" "Classification of Human Physical Activities and Postures During Everyday Life". "Motorbike Driving Activity Recognition Using Smartphone Motion Sensors". "EEG-Based Depression Detection: A Temporal Domain Feature-Centric Machine Learning Approach". Teaching Experience: In addition to my research accomplishments, I bring over eight years of teaching experience as a Lab Instructor at the University of Engineering and Technology Taxila. I've had the privilege of instructing and guiding undergraduate students in pivotal courses, including Computer Fundamentals, Programming Fundamentals, Data Structures, Object-Oriented Programming, Wireless Mobile Networks, Machine Learning, and Digital Image Processing. My unique blend of academic rigor, research prowess, and teaching expertise positions me as a well-rounded professional ready to contribute to innovative projects and academic endeavors.

Lihat semua Research Analysts in Pakistan

Hubungi Sheharyar K. mengenai pekerjaan Anda

Portofolio

Violin Plot For Study of Major Depressive Disorder

Deep Learning Model Plots

Magnetometer Data is Plotted

Spectrogram is created and then draw a signal

Plots in Python

11828688

A machine learning based depression screening framework

Image Segmentation

Violin Plot For Study of Major Depressive Disorder

Deep Learning Model Plots

Magnetometer Data is Plotted

Plots in Python

11828688

A machine learning based depression screening framework

Image Segmentation

Ulasan

Perubahan tersimpan

Tidak ada ulasan terlihat di sini!

Pengalaman

University of Engineering and Technology Taxila

Mei 2016 - Sekarang

Conducting Lab Courses Include Programming /Machine Learning / Digital Image Processing

Edukasi

MS Computer Science

Pakistan

2019 - 2023

(4 tahun)

Msc Computer Science

University of Wah,

Pakistan

2013 - 2015

(2 tahun)

Kualifikasi

Hitech University

2024

Conduct Three day Workshop on Machine Learning. In which we discuss the Data Preprocessing , Supervise Learning Algorithms and Classification and Regression.

Publikasi

Optimal Feature-Centric Approach for EEG-Based Human Emotion Identification

IEEE (ICACS)

Twenty-five temporal domain features were extracted from this dataset. Correlation-based feature selection technique is applied to select the significant features for the classification of three mental states. The selected EEG features are classified using four distinct classifiers. It is evident from the results, that the Random Forest achieves the highest classification accuracy of 98.61%.

An EEG-Driven Framework for Emotion Recognition During Gameplay

IEEE (ICACS)

Gaming transcends mere entertainment, serving as a unique realm to explore human emotions. This research utilizes (BCI) technology, specifically (EEG) signals, to unravel player emotions. Leveraging datasets like GAMEEMO, our study employs various data and feature extraction processes to detect emotions (boring, calm, horror, funny) with a accuracy of 98.21%, achieved by the Random Forest model.

A machine learning based depression screening framework using temporal domain features of the EEG

PLOS ONE

This study uses EEG data acquired from 55 participants using 3 electrodes in the resting-state condition. Twelve temporal domain features are extracted from the EEG data by creating a non-overlapping window of 10 seconds, which is presented to a novel feature selection mechanism.The highest classification accuracy of 96.36% is achieved using BF-Tree using a feature vector length of 12. The proposed framework could be used in psychiatric settings, providing valuable support to psychiatrists.