SEED - Syndicate of Embedded & Electronic Design

26/08/2023

Emotion Recognition using EEG Signal Analysis | Machine Learning

In this study, we introduce a machine-learning model that recognizes emotions from Electroencephalogram (EEG) signals. Using the publicly available DREAMERs dataset, we identify 4 emotions - sadness, joy, anger, and pleasure. Our approach involves segmenting EEG signals into 30-second segments, noise reduction with a band-stop filter, and extraction of 5 frequency bands. After applying filters, we obtained 6 time-based features. To address class imbalance, we employ ADASYN, and feature selection is done using the Chi-square algorithm. The Fine K-nearest neighbor (KNN) classifier achieves a 91.1% accuracy, taking around 25 seconds for emotion detection via EEG signals.

Author and Presenter: Muhammad Bilal Sajid

https://youtu.be/7pDj0y3pBpY

Author and Presenter: Muhammad Bilal Sajid Summary:In this study, we introduce a machine-learning model that recognizes emotions from Electroencephalogram (E...

01/08/2023

The SEEDship Program (2023)
SEED is hiring Research Interns for Short/Long term Projects. Candidates with high proficiency in MATLAB, Python, or C, knowledge of Embedded Systems and/or Signal/Image Analysis, and excellent analytical, writing, and presentation skills are required.
Apply now at: https://forms.gle/YvVNAKZveiADFxwT9

Deadline: 04/08/2023

Access Google Forms with a personal Google account or Google Workspace account (for business use).

28/07/2023

Alhamdulillah.........
Let's celebrate the remarkable accomplishment of Muhammad Talal Farhan, an 8th-semester student from the Electronics Engineering Department at the University of Engineering and Technology Taxila. We extend our warmest congratulations to him for publishing his outstanding Journal Article in the prestigious Expert Systems Journal. It's worth noting that Talal conducted this remarkable research during his 6th semester. His work focused on Phonocardiogram Signal Processing, utilizing advanced signal processing techniques and machine learning algorithms to detect cardiac diseases.

We are truly impressed by Talal's dedication and expertise in the field, and we have no doubt that his future holds excellent success. Our heartfelt prayers are with him.

You may find his work at

Timely and accurate detection and diagnosis of heart disorders is a significant problem in the medical community since the mortality rate is increasing. Pulsing of cardiac structures and blood turbul...

19/11/2022

Interesting information...

The first computer mouse was patented on this day in 1970 by the 1998 recipient Douglas Engelbart. Initially known as "X-Y Position Indicator For A Display System," it was nicknamed by Engelbart as "mouse" because the cord looked like a tail. It was not until Apple's Macintosh that the mouse became an ubiquitous companion to the personal computer. Meet the first mouse, which was carved out of wood and had just one button. 🖱️

09/10/2022

Machine Learning | Sign Language Interpretation | EMG

Background:
An electromyogram (EMG) is the electrical measure of muscular activity, which can vary depending on what motion is being performed. The communication gap between the specialized and general public is elevated by sign language. They are able to interact with society thanks to it. While many studies have suggested image-based or multi-modal sensor-based sign language models, this study develops an Italian sign language recognition system using solely EMG.

Authors: Ramla Saif, Muhammad Ahmad
Presenter: Muhammad Ahmad

https://youtu.be/VLR_yRDABPM

Author and Presenter: Muhammad AhmadBackground:Electromyogram (EMG) is the electrical measure of the muscular activity which can vary depending upon what mot...

12/07/2022

In this video, we will show how to implement Fast Fourier Transform (FFT) or Discrete Fourier Transform (DFT) in MATLAB using the built-in fft() function.
1. Fast Fourier Transform | Discrete Fourier Transform
2. Discrete Fourier Transform in MATLAB
3. Frequency Spectrum of Signal
4. Magnitude Spectrum of Signal
5. Phase Spectrum of Signal
6. Visualizing Frequency Components in a Signal
https://youtu.be/OKSjb06QkYc

In this video, we will show how to implement Fast Fourier Transform (FFT) or Discrete Fourier Transform (DFT) in MATLAB using built-in function. Contents o...

04/07/2022

In this video, you will learn how to interface these 7 segments with the switches available on the FPGA board.
This video consists of the following sections:
Introduction
Basics of Seven segments
Seven segment display on Nexys 4 (FPGA) Board
Verilog Code of Seven Segment interfacing with switches
Make new project in Vivado
Input-output pin mapping in vivado
Bit file generation
Downloading the bit file on FPGA Board
Testing on hardware (FPGA) Board
https://youtu.be/OlMYiGm_WX4

The Nexys4 board is a complete, ready-to-use digital circuit development platform based on the latest Artix-7 Field ProgrammableGate Array (FPGA) from Xilinx...

01/12/2021

Author and Presenter: Zainoor Ahmad Choudhry
Title: DarkNet-19 based Decision Algorithm for the Diagnosis of Ophthalmic Disorders
Background:
Retinal diseases are identified by conducting different medical examinations primarily of which are visual examinations. One of the key issues in the visual diagnosis of diseases is human error due to poor decision making, for that, an upcoming interdisciplinary technology named computer-aided medical diagnostic system provides precise detection and prediction of disease. In our proposed methodology, images were treated with Contrast Limited Adaptive Histogram Equalization, and deep features were then extracted from the enhanced images. ADASYN was also applied to acquire a balanced dataset. Support Vector Machine classifier was used which yielded a mean accuracy of 93.8%.
Venue: IEEE, 4th International Conference on Innovative Computing (ICIC) 2021

Author and Presenter: Zainoor Ahmad ChoudhryBackground:Retinal diseases are identified by conducting different medical examinations primarily of which are vi...

21/11/2021

Are you prepared to solve some of the world’s most unique challenges? If so, then it’s time to join us, express your individuality, unleash your curiosity and discover new possibilities.
SEED is Hiring some Research Assistants and Potential Internees for some Short/Long term Projects related to System Design Engineering.
The applicant must be having some Excellent Analytical and Communication Skills. Proficiency in LabView, MATLAB, Python, Virtuoso, C++, Verilog would be a plus.
The selected candidate will be a part of research that enables learning the semantics of data; will work towards long-term ambitious research goals, while going through intermediate milestones; will contribute to research that can be applied to Product Development.
Fill the form attached before 3/12/2021:
https://forms.gle/fk1VyhaPRbQLAseT8
It’s time to de/re-fine your career.

10/11/2021

Author and Presenter: Hira Shahid
Title: A Survey on AI-based ECG, PPG, and PCG Signals Based Biometric Authentication System
Project: Cardi-D
Background:
As technology has advanced, so have the electronic crimes in users’ private data. The use of authentication models like face, finger, iris recognition, voice, and other physiological and behavioral verification technologies overcoming traditional security methods like passwords and PIN has been the subject of extensive research lately. A significant amount of research now focuses on physiological signals. Since their advantages of exhibiting identity discrimination power and being acquired only from living bodies avoids the risks of faking someone’s data. This paper aims to briefly address biosignals-based biometric authentication, dominating former conventional technologies as they face compromised quality or resolution of collected photos and security threats like spoofing and copying. A summary of the electrocardiogram (ECG), photoplethysmogram (PPG), and phonocardiogram (PCG) along with their advantages and limitations is provided in this paper.
Venue: IEEE International Conference on Computing, Electronics and Electrical Engineering (ICE Cube 2021)

Author and Presenter: Hira ShahidProject: Cardi-DBackground:As technology has advanced, so have the electronic crimes in user’s private data. The use of auth...

27/10/2021

Author and Presenter: Zain Tariq
Title: Transfer Learning-Based Approach for Detection of COVID-19 from X-Ray Images
Project: Pulmo-D
Background:
In this project, we have performed transfer learning using different pre-trained convolutional neural networks for binary classification of X-ray images into COVID-19 disease and normal. The dataset is gathered from two open sources. Our dataset is consisting of 254 COVID-19 and 310 Normal X-ray images. The pandemic situation all around the world demands an efficient solution so that the disturbance of global health, daily life, and economy can be controlled. In this regard, we introduced the deep feature fusion-based technique which could help to design an embedded system. We fine-tuned and trained the thirteen independent pre-trained models and we found that the Resnet50V2 model performed efficiently for binary classification scenarios. Our proposed technique using transfer learning gives a detection rate of 99.5% for binary classification (Normal and COVID).
Venue: IEEE 4th International Conference on Robotics and Automation in Industry (ICRAI 2021)

Author and Presenter: Zain TariqBackground:In this paper, we have performed transfer learning using different pre-trained convolutional neural networks for b...

18/08/2021

Author and Presenter: Maheen Shakeel
Title: Support vector machine-based diagnosis of Tuberculosis
Project: Pulmo-D

Background:
Tuberculosis is one of the common death-causing diseases in the world and possess a threat to the health of the world population. This study aims to elaborate on the feasibility of developing a setup of a combination of hardware and software, using respiratory sounds for diagnosis of Tuberculosis.

Venue: Mohammad Ali Jinnah University Conference on Informatics and Computing 2021 (MAJICC'21)

Author and Presenter: Maheen Shakeel https://www.researchgate.net/profile/Maheen_ShakeelTitle: Support vector machine-based diagnosis of TuberculosisProject:...