Faisal Ghaffar

Faisal Ghaffar, Sarwar Khan, Bunyarit Uyyanonvara et al.

This research aims to develop an efficient system for screening of diabetic retinopathy. Diabetic retinopathy is the major cause of blindness. Severity of diabetic retinopathy is recognized by some features, such as blood vessel area, exudates, haemorrhages and microaneurysms. To grade the disease the screening system must efficiently detect these features. In this paper we are proposing a simple and fast method for detection of diabetic retinopathy. We do pre-processing of grey-scale image and find all labelled connected components (blobs) in an image regardless of whether it is haemorrhages, exudates, vessels, optic disc or anything else. Then we apply some constraints such as compactness, area of blob, intensity and contrast for screening of candidate connectedcomponent responsible for diabetic retinopathy. We obtain our final results by doing some post processing. The results are compared with ground truths. Performance is measured by finding the recall (sensitivity). We took 10 images of dimension 500 * 752. The mean recall is 90.03%.

Faisal Ghaffar

Facial expressions vary from person to person, and the brightness, contrast, and resolution of every random image are different. This is why recognizing facial expressions is very difficult. This article proposes an efficient system for facial emotion recognition for the seven basic human emotions (angry, disgust, fear, happy, sad, surprise, and neutral), using a convolution neural network (CNN), which predicts and assigns probabilities to each emotion. Since deep learning models learn from data, thus, our proposed system processes each image with various pre-processing steps for better prediction. Every image was first passed through the face detection algorithm to include in the training dataset. As CNN requires a large amount of data, we duplicated our data using various filters on each image. Pre-processed images of size 80*100 are passed as input to the first layer of CNN. Three convolutional layers were used, followed by a pooling layer and three dense layers. The dropout rate for the dense layer was 20%. The model was trained by combining two publicly available datasets, JAFFE and KDEF. 90% of the data was used for training, while 10% was used for testing. We achieved maximum accuracy of 78.1 % using the combined dataset. Moreover, we designed an application of the proposed system with a graphical user interface that classifies emotions in real-time.

Faisal Ghaffar, Sarwar Khan, Gaddisa O. et al.

Deep learning is playing a vital role in every field which involves data. It has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using traditional machine learning techniques in the past. In this study we focused on classification of protein sequences with deep learning techniques. The study of amino acid sequence is vital in life sciences. We used different word embedding techniques from Natural Language processing to represent the amino acid sequence as vectors. Our main goal was to classify sequences to four group of classes, that are DNA, RNA, Protein and hybrid. After several tests we have achieved almost 99% of train and test accuracy. We have experimented on CNN, LSTM, Bidirectional LSTM, and GRU.

Sarwar Khan, Faisal Ghaffar, Imad Ali et al.

The classification of amino acids and their sequence analysis plays a vital role in life sciences and is a challenging task. This article uses and compares state-of-the-art deep learning models like convolution neural networks (CNN), long short-term memory (LSTM), and gated recurrent units (GRU) to solve macromolecule classification problems using amino acids. These models have efficient frameworks for solving a broad spectrum of complex learning problems compared to traditional machine learning techniques. We use word embedding to represent the amino acid sequences as vectors. The CNN extracts features from amino acid sequences, which are treated as vectors, then fed to the models mentioned above to train a robust classifier. Our results show that word2vec as embedding combined with VGG-16 performs better than LSTM and GRU. The proposed approach gets an error rate of 1.5%.