Ahmed H. Profile

0,0

(0 comentarios)

Ahora estás siguiendo a

Error al seguir a usuario.

Este usuario no permite que los usuarios lo sigan.

Ya estás siguiendo a este usuario.

Tu plan de membresía solo permite 0 seguimientos. Mejora tu membresía aquí.

Dejaste de seguir correctamente a

Error al dejar de seguir al usuario.

Has recomendado exitosamente a

Error al recomendar al usuario.

Algo salió mal. Por favor, actualiza la página e intenta de nuevo.

Email verificado correctamente.

$25 USD / hora

cairo,

egypt

$25 USD / hora

Aquí son las 2:36 a. m.

Se unió el febrero 11, 2023

0 Recomendaciones

Ahmed H.

@AgHabashy

0,0

(0 comentarios)

0,0

$25 USD / hora

cairo,

egypt

$25 USD / hora

N/A

Trabajos finalizados

N/A

Dentro del presupuesto

N/A

A tiempo

N/A

Tasa de recontratación

Computer and Systems Eng.

Hi there! I'm a PhD student majoring in Machine Learning for biomedical engineering with over 10 years of practical and academic experience in R&D and teaching assistantship. As a Well-Rounded Engineer with a solid multi-discipline engineering background, I have a unique ability to tackle complex problems and deliver innovative solutions. I am also a highly skilled Python developer with extensive experience in using Python for machine learning tasks. I'm familiar with a wide range of libraries and frameworks, including NumPy, pandas, scikit-learn, Keras, and TensorFlow. I am a quick learner with a strong attention to detail, and I am committed to delivering accurate and actionable insights to clients. As a reliable and dedicated professional, I pride myself on my ability to work collaboratively with clients to understand their specific needs and requirements. I am always striving to exceed expectations and deliver high-quality results in a timely manner. If you're looking for a talented and experienced freelancer who can help you achieve your goals, please don't hesitate to get in touch!

Ver todo Python Developers en Egypt

Contacta Ahmed H. sobre tu trabajo

Inicia sesión para comentar cualquier detalle por chat.

Portafolio

11571326

Motor Imagery Classification Enhancement using GAN

10776345

calculate-Inception-Score-for-CIFAR-10-in-Keras

10775081

CNN-hyperparameter_tuning

10775020

ESP8266 Wi-Fi Data Extraction and Sending Code

This code implements a firmware for extracting data from an SBG Ellipse-2N sensor. It configures three serial interfaces - Serial1, Serial2, and Serial3 - to communicate with the sensor and other devices, and reads data from the sensor to extract Euler angles, navigation data, and GPS data. The extracted data is stored in a msg_tx byte array, which is sent to the other devices via Serial3.
The full version of the code on Github:
https://github.com/Ahmed-Habashy/SBG-Ellipse-2N-Sensor-Data-Extraction-Code

SBG-Ellipse-2N-Sensor-Data-Extraction

10773297

Certificate of Introduction to Deep Learning

11571326

Motor Imagery Classification Enhancement using GAN

10776345

calculate-Inception-Score-for-CIFAR-10-in-Keras

10775081

CNN-hyperparameter_tuning

10775020

ESP8266 Wi-Fi Data Extraction and Sending Code

SBG-Ellipse-2N-Sensor-Data-Extraction

10773297

Certificate of Introduction to Deep Learning

Comentarios

Cambios guardados

¡No hay comentarios para ver aquí!

Experiencia

Ain Shams University

sept 2017 - Presente

- Team leader of graduation projects. - Teaching Assistant qualification project. - The recent research focuses on utilizing data science, machine learning and signal processing techniques to develop non-invasive Brain-Computer Interface (BCI) applications.

Ain Shams University

sept 2010 - jun 2017 (6 años, 9 meses)

Instructor for discussion, laboratory and exercise sections of the following undergraduate engineering courses:  Math  C++  Electrical Measurements  Solid State Devices  IC Technology  Automatic control system  Advanced control system  Process Control

Educación

MSc

Ain Shams University,

Egypt

2012 - 2016

(4 años)

bachelor

Ain Shams University,

Egypt

2005 - 2010

(5 años)

Publicaciones

Motor Imagery Classification Enhancement using GAN for EEG Spectrum Image Generation

2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS)

This paper proposes a novel GAN-based approach for generating synthetic spectrum images of Motor Imagery (MI) Electroencephalogram (EEG).The proposed GAN is examined with two Convolutional Neural Network (CNN) architectures in the context of MI classification. Using the public dataset BCI competition IV, our findings reveal that the generated EEG spectrum images using GANs exhibit temporal, spectral, and spatial characteristics similar to the real ones.

Generative adversarial networks in EEG analysis: an overview

Journal of NeuroEngineering and Rehabilitation

This article provides an overview of various techniques and approaches of GANs for augmenting EEG signals. We focus on the utility of GANs in different applications including Brain-Computer Interface (BCI) paradigms such as motor imagery and P300-based systems, in addition to emotion recognition, epileptic seizures detection and prediction, and various other applications.

Comparative Study Among Different Control Techniques for Stabilized Platform

A. G. Habashi, M. M. Ashry, Mohamed H. Mabrouk, G. A. Elnashar

Controlling the LOS for an inertially stabilized platform system subjected to uncertainty is a challenging problem. This paper compares the performance of 5 controllers designed to improve accuracy and reduce stabilized error. These controllers are PI, genetically tuned PI, LQR, LQG, and H∞ controllers. The controllers' ability to reject disturbance and attenuate noise is compared, and results show improved pointing accuracy despite the presence of outer disturbances.

Controller Design for Line of Sight Stabilization System

A. G. Habashi, M. M. Ashry, M. H. Mabrouk, and G. A. Elnashar.

This paper evaluates the effectiveness of different control techniques for LOS stabilization subsystems, including classical PI controller, genetically tuned PI, LQR, LQG, and H∞ controllers. The controllers' performances in normal conditions and robustness to model uncertainty are compared using simulation results. The genetically tuned PI controller and the H∞ controller were found to be the most effective in handling model uncertainty.