A Deep Learning Based Approach for Localization and Recognition of Pakistani Vehicle License Plates.

License plate localization is the process of finding the license plate area and drawing a bounding box around it, while recognition is the process of identifying the text within the bounding box. The current state-of-the-art license plate localization and recognition approaches require license plates of standard size, style, fonts, and colors. Unfortunately, in Pakistan, license plates are non-standard and vary in terms of the characteristics mentioned above. This paper presents a deep-learning-based approach to localize and recognize Pakistani license plates with non-uniform and non-standardized sizes, fonts, and styles. We developed a new Pakistani license plate dataset (PLPD) to train and evaluate the proposed model. We conducted extensive experiments to compare the accuracy of the proposed approach with existing techniques. The results show that the proposed method outperformed the other methods to localize and recognize non-standard license plates.

Multiclass Cancer Prediction Based on Copy Number Variation Using Deep Learning.

DNA copy number variation (CNV) is the type of DNA variation which is associated with various human diseases. CNV ranges in size from 1 kilobase to several megabases on a chromosome. Most of the computational research for cancer classification is traditional machine learning based, which relies on handcrafted extraction and selection of features. To the best of our knowledge, the deep learning-based research also uses the step of feature extraction and selection. To understand the difference between multiple human cancers, we developed three end-to-end deep learning models, i.e., DNN (fully connected), CNN (convolution neural network), and RNN (recurrent neural network), to classify six cancer types using the CNV data of 24,174 genes. The strength of an end-to-end deep learning model lies in representation learning (automatic feature extraction). The purpose of proposing more than one model is to find which architecture among them performs better for CNV data. Our best model achieved 92% accuracy with an ROC of 0.99, and we compared the performances of our proposed models with state-of-the-art techniques. Our models have outperformed the state-of-the-art techniques in terms of accuracy, precision, and ROC. In the future, we aim to work on other types of cancers as well.

Ensemble Framework of Deep CNNs for Diabetic Retinopathy Detection.

Diabetic retinopathy (DR) is an eye disease that damages the blood vessels of the eye. DR causes blurred vision or it may lead to blindness if it is not detected in early stages. DR has five stages, i.e., 0 normal, 1 mild, 2 moderate, 3 severe, and 4 PDR. Conventionally, many hand-on projects of computer vision have been applied to detect DR but cannot code the intricate underlying features. Therefore, they result in poor classification of DR stages, particularly for early stages. In this research, two deep CNN models were proposed with an ensemble technique to detect all the stages of DR by using balanced and imbalanced datasets. The models were trained with Kaggle dataset on a high-end Graphical Processing data. Balanced dataset was used to train both models, and we test these models with balanced and imbalanced datasets. The result shows that the proposed models detect all the stages of DR unlike the current methods and perform better compared to state-of-the-art methods on the same Kaggle dataset.

Deep Learning Techniques for Diabetic Retinopathy Detection.

Diabetes occurs due to the excess of glucose in the blood that may affect many organs of the body. Elevated blood sugar in the body causes many problems including Diabetic Retinopathy (DR). DR occurs due to the mutilation of the blood vessels in the retina. The manual detection of DR by ophthalmologists is complicated and time-consuming. Therefore, automatic detection is required, and recently different machine and deep learning techniques have been applied to detect and classify DR. In this paper, we conducted a study of the various techniques available in the literature for the identification/classification of DR, the strengths and weaknesses of available datasets for each method, and provides the future directions. Moreover, we also discussed the different steps of detection, that are: segmentation of blood vessels in a retina, detection of lesions, and other abnormalities of DR.

Identification of microRNA precursors using reduced and hybrid features.

MicroRNAs (also called miRNAs) are a group of short non-coding RNA molecules. They play a vital role in the gene expression of transcriptional and post-transcriptional processes. However, abnormality of their expression has been observed in cancer, heart diseases and nervous system disorders. Therefore for basic research and microRNA based therapy, it is imperative to separate real pre-miRNAs from false ones (hairpin sequences similar to pre-miRNA stem loops). Different conservation and machine learning methods have been applied for the identification of miRNAs. However, machine learning algorithms have gained more popularity than conservative based algorithms in terms of sensitivity and overall performance. Due to the avalanche of RNA sequences discovered in a post-genomic age, it is necessary to construct a predictor for the identification of pre-microRNAs in humans. We have developed a predictor called MicroR-Pred in which the RNA sequences are formulated by a hybrid feature vector. The novelty of the new predictor is in the use of the partial least squares technique followed by the Random Forest and SVM (Support Vector Machine) algorithms for dimension reduction and classification. The performance of the MicroR-Pred model is quite promising compared to other state-of-the-art miRNA predictors. It has achieved 88.40% and 93.90% accuracies for RF and SVM.