Muhammad Uzair Z. Profile

4,9

(108 anmeldelser)

Du følger nu

Fejl under følg af bruger.

Denne bruger har ikke tilladt andre bruger at følge dem.

Du følger allerede denne bruger.

Din medlemsskabsplan tillader kun at følge 0. Opgrader her.

Du følger nu ikke længere

Kunne ikke stoppe med at følge bruger.

Du har nu anbefalet

Kunne ikke anbefale bruger.

Noget gik galt. Forny venligst siden og prøv igen.

Email verificeret.

$50 USD / time

nottingham,

united kingdom

$50 USD / time

Det er i øjeblikket 8:44 PM her

Tilmeldt februar 2, 2018

2 Anbefalinger

Muhammad Uzair Z.

@uzairrzahid

4,9

(108 anmeldelser)

6,4

82%

$50 USD / time

nottingham,

united kingdom

$50 USD / time

95 %

Jobs færdiggjort

85 %

Indenfor budgettet

84 %

Til tiden

23 %

Genansættelsesrate

ML | DL | AI | Python | MATLAB

As a Machine Learning and AI developer, I have a strong passion for technology and 5+ years of experience in delivering cutting-edge solutions to clients. My areas of expertise include neural networks, biomedical imaging, and other advanced machine learning techniques. In addition to my technical skills, I am also well-versed in web technologies and have a proven track record of problem-solving using various programming languages. My goal is always to exceed client expectations and ensure that their satisfaction is my top priority. If you are looking for a dedicated and skilled developer who can deliver desired outcomes, please do not hesitate to hire me.

Se alle Matlab and Mathematica Engineers i United Kingdom

Kontakt Muhammad Uzair Z. omkring dit job

Log ind for at diskutere detaljerne via chat.

Portefølje

Robust R-Peak Detection in Low-Quality Holter ECGs Using 1D

I implemented two techniques for auto-FER.

First, I retrained AlexNet, used transfer learning for classification(Transfer Learning).

Second, I used AlexNet for feature extraction and cascaded it with an SVM for classification.

I achieved 93% accuracy with AlexNet and 95% with AlexNet-SVM cascade which is comparable with the contemporary methods that give 96-98%. Data augmentation and training with larger dataset can improve the accuracy with deep learning

I used JAFFE Data Set to train my both models.

Facial Expression Recognition

The program is made with a GUI (graphical user interface) to be clear and easy to use. The images dataset which the search is made on are stored in a the folder “images”, the main GUI is coded in the two files “CBIR.fig” and”CBIR.m” but the process of features extraction is made by the code “Extract_features.m”. First the query image is loaded at this point all the previously mentioned features are extracted from the image then it is shown in the main GUI platform under title “Loaded image”. Then the extracted features are compares to the already saved and processed database where the distance between the query image and all images in the dataset is calculated. Finally the nearest ten images to the query image are shown in the GUI.

More details can be found at my Github account.
https://github.com/MUzairZahid

Content Based Image Retrieval (MATLAB)

Train a convolutional neural network (ConvNet) for an image classification task and use the trained model for detecting cars.

CNN for Image Classification

In this project, I implemented an automated algorithm to classify, from a single short ECG lead recording , whether the recording shows normal sinus rhythm, atrial fibrillation (AF), an alternative rhythm, or is too noisy to be classified.

Heart Arrhythmia Classification using ECG Signal

Anmeldelser

Ændringer gemt

Viser 1 - 5 ud af 50+ anmeldelser

Filtrer anbefalinger ud fra:

5,0

€100,00 EUR

Deep learning

He handled that challenge like a true professional.

Python

Software Architecture

Machine Learning (ML)

Deep Learning

Zrax H.

@marouenkadri24

•

1 år siden

5,0

€200,00 EUR

Project for Muhammad Uzair Z. -- 3

Nice work , on the time . in one word it's the best one .

Matlab and Mathematica

Algorithm

Electrical Engineering

Machine Learning (ML)

+1 mere

Zrax H.

@marouenkadri24

•

1 år siden

5,0

€170,00 EUR

Project for Muhammad Uzair Z.

excellent work as usual

Matlab and Mathematica

Algorithm

Electrical Engineering

Machine Learning (ML)

+1 mere

Zrax H.

@marouenkadri24

•

1 år siden

5,0

$300,00 AUD

Multivariate classification using autosklearn -- 2

Yet more repeat business with Muhammah. I'll be going straight back for more.

Matlab and Mathematica

Algorithm

Electrical Engineering

Machine Learning (ML)

Data Science

Jacob A.

@mintgreenstrat

•

1 år siden

5,0

€100,00 EUR

Project 33868659 has been deleted

Excellent work. Delivered exactly what I requested quickly and professionally.

Zrax H.

@marouenkadri24

•

1 år siden

Erfaring

Qatar University

dec. 2019 - Nuværende

Working as a researcher in the field of Biomedical Imaging, Signal Processing, Machine Learning and Deep Learning.

CE FAR LAB

jan. 2018 - Nuværende

I am working a project which involves object tracking and localization using live video feed from camera which will be used to help visually blind people.

SIGMA LABS NUST (Research Lab for Signal Processing And Machine Learning)

apr. 2017 - sep. 2017 (5 måneder, 1 dag)

I was involved in development of a portable, remote respiratory and physical activity monitoring system.

Uddannelse

MS Electrical Engineering (Signal Processing and Machine Learning)

National University of Science and Technology,

Pakistan

2016 - 2018

(2 år)

BS Telecom

University of Engineering and Technology, Taxila,

Pakistan

2012 - 2016

(4 år)

Kvalifikationer

Coursera

2018

Publikationer

Global ECG Classification by Self-Operational Neural Networks with Feature Injection

IEEE Transactions on Biomedical Engineering

Global (inter-patient) ECG classification for arrhythmia detection over Electrocardiogram (ECG) signal is a challenging task for both humans and machines. The main reason is the significant variations of both normal and arrhythmic ECG patterns among patients. In this study, we propose a novel approach for inter-patient ECG classification using a compact 1D Self-ONN by exploiting morphological and timing information in heart cycles.

Robust Peak Detection for Holter ECGs by Self-Organized Operational Neural Networks

IEEE Transactions on Neural Networks and Learning Systems

In this study, to further boost the peak detection performance along with an elegant computational efficiency, we propose 1D Self-Organized Operational Neural Networks (Self-ONNs) with generative neurons. The experimental results over the China Physiological Signal Challenge-2020 (CPSC) dataset show that the proposed 1D Self-ONNs can significantly surpass the state-of-the-art deep CNN with less computational complexity.

Robust R-Peak Detection in Low-Quality Holter ECGs using 1D Convolutional Neural Network

IEEE Transactions on Biomedical Engineering

In this study, a novel implementation of the 1D Convolutional Neural Network (CNN) is used integrated with a verification model. Experimental results demonstrate that the proposed systematic approach achieves 99.30% F1-score, 99.69% recall, and 98.91% precision in CPSC-DB, which is the best R-peak detection performance ever achieved. Results also demonstrate similar or better performance than most competing algorithms on MIT-DB with 99.83% F1-score, 99.85% recall, and 99.82% precision.