Awais Salman Qazi

Mr. Awais Salman Qazi

Computer Science, University of Management and Technology, Lahore, Punjab, Pakistan
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 November 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AQAwais Salman Qazi
Awais Salman Qazi
MFMuhammad Shoaib Farooq
Muhammad Shoaib Farooq
Furqan RustamFurqan Rustam
Furqan Rustam
MVMónica Gracia Villar
Mónica Gracia Villar
CVCarmen Lilí Rodríguez Velasco
Carmen Lilí Rodríguez Velasco
IAImran Ashraf
Imran Ashraf
Facial emotion recognition (FER) is an important and developing topic of research in the field of pattern recognition. The effective application of facial emotion analysis is gaining popularity in surveillance footage, expression analysis, activity recognition, home automation, computer games, stress treatment, patient observation, depression, psychoanalysis, and robotics. Robot interfaces, emotion-aware smart agent systems, and efficient human–computer interaction all benefit greatly from facial expression recognition. This has garnered attention as a key prospect in recent years. However, due to shortcomings in the presence of occlusions, fluctuations in lighting, and changes in physical appearance, research on emotion recognition has to be improved. This paper proposes a new architecture design of a convolutional neural network (CNN) for the FER system and contains five convolution layers, one fully connected layer with rectified linear unit activation function, and a SoftMax layer. Additionally, the feature map enhancement is applied to accomplish a higher detection rate and higher precision. Lastly, an application is developed that mitigates the effects of the aforementioned problems and can identify the basic expressions of human emotions, such as joy, grief, surprise, fear, contempt, anger, etc. Results indicate that the proposed CNN achieves 92.66% accuracy with mixed datasets, while the accuracy for the cross dataset is 94.94%.

31 December 2019 in Lahore Garrison University Research Journal of Computer Science and Information Technology
Verified
Journal Article
Open access
PDF file
WAWaqas Ahmad
Waqas Ahmad
AQAwais Salman Qazi
Awais Salman Qazi
In our research paper, we have introduced a unique and new line code method/technique that will have the capability to send two different codes in parallel or concurrently using a single line code, and this will be achieved without any major loss in the shape of the signal. In our proposed new line code, the structure of our code is based on two already well-known line codes that have been used many times in the data communication field, both of them have been combined together. We can say that our new line coding method is a hybrid encoding scheme. This line code combines the properties of already existing line code techniques. At the receiver end, we have implemented a very easy and basic separation technique that shall help us to separate the real user codes from the added line code, and this will happen without any disturbance or major loss/distortion. There will be no effect on the signal of input data.