Saad Razzaq

Automated Change Request Triage Using Alpha Frequency Matrix

Software changes are inevitable in large and long lived projects. Successful applications require proper handling and assignment of change requests (CRs). In large projects, a number of CRs are generated daily. These CRs should be resolved timely. We present an automated approach to assign CRs to appropriate developers. We use Alphabet Frequency Matrix (AFM) to classify CRs into developer classes. We apply machine learning techniques on the AFM data sets for classification. We find that AFM can be used to achieve an average accuracy from 27% to 53% with precision 25% to 55% and recall 28% to 56%.

Modified cat swarm optimization for clustering

Clustering is one of the most challenging optimization problems. Many Swarm Intelligence techniques including Ant Colony optimization (ACO), Particle Swarm Optimization (PSO), and Honey Bee Optimization (HBO) have been used to solve clustering. Cat Swarm Optimization (CSO) is one of the newly proposed heuristics in swarm intelligence, which is generated by observing the behavior of cats, and has been used for clustering and numerical function optimization. CSO based clustering is dependent on a pre-specified value of K i.e. Number of Clusters. In this paper we have proposed a “Modified Cat Swam Optimization (MCSO)” heuristic to discover clusters based on the nature of data rather than user specified K. MCSO performs a data scan to determine the initial cluster centers. We have compared the results of MCSO with CSO to demonstrate the enhanced efficiency and accuracy of our proposed technique.

Residual Recurrent Highway Networks for Learning Deep Sequence Prediction Models

A contemporary approach for acquiring the computational gains of depth in recurrent neural networks (RNNs) is to hierarchically stack multiple recurrent layers. However, such performance gains come with the cost of challenging optimization of hierarchal RNNs (HRNNs) which are deep both hierarchically and temporally. The researchers have exclusively highlighted the significance of using shortcuts for learning deep hierarchical representations and deep temporal dependencies. However, no significant efforts are made to unify these finding into a single framework for learning deep HRNNs. We propose residual recurrent highway network (R2HN) that contains highways within temporal structure of the network for unimpeded information propagation, thus alleviating gradient vanishing problem. The hierarchical structure learning is posed as residual learning framework to prevent performance degradation problem. The proposed R2HN contain significantly reduced data-dependent parameters as compared to related methods. The experiments on language modeling (LM) tasks have demonstrated that the proposed architecture leads to design effective models. On LM experiments with Penn TreeBank, the model achieved 60.3 perplexity and outperformed baseline and related models that we tested.

Zombies Arena: fusion of reinforcement learning with augmented reality on NPC

Augmented reality (AR) is a discipline having less cognizance but it is the door to new advance technologies. Accustomed games doesn’t facilitate user to physically interact with the surroundings which resulted into reduced learning capabilities. Our objective is to develop AR based first person shooter game empowering reinforcement learning. This act as a building block to capacitate users to interact with the physical environment. Non-player characters will be able to learn and adopt strategy more wisely after each move to capacitate players. Game is played by hundred users at different stages. Reported results are summarized in experiment section.

Massively parallel palmprint identification system using GPU

Automated human authentication is becoming increasingly important in today’s world due to increased need of security and surveillance applications deployed in almost all premises and installations. In this regard, palmprint biometric based identification has gained a lot of attention in recent years. However, due to large size of palmprint images and presence of principal lines, wrinkles, creases, and other noises, there are large number of inaccurate minutiae present. The computational requirement of palmprint identification is also quite large and it takes a lot of time to find identity of a palmprint in large database. In this study, a novel palmprint identification solution has been proposed that increases the accuracy of minutia detection based on improved frequency estimation and a novel region-quality based minutia extraction algorithm. Furthermore, a novel, efficient and highly accurate minutiae based encoding and matching algorithm is proposed that is designed to achieve maximum parallelism, and it is further accelerated using graphical processing unit. The results of the proposed palmprint identification demonstrate high accuracy and much faster identification speeds in comparison with current state of the art. Therefore, it can be considered as a robust, efficient and practical solution for palmprint based identification systems.

Automated Diagnosis and Cause Analysis of Cesarean Section Using Machine Learning Techniques

Machine learning techniques provide learning mechanism that can be used to induce knowledge from data. A few studies exist on the use of machine learning techniques for medical diagnosis, prediction and treatment. In this study we evaluate different machine learning techniques for birth classification (cesarean or normal). Data on cesarean section is collected and different medical factors are identified that result in cesarean births. A birth classification model is built using decision tree and artificial neural networks. It can classify the births into normal and cesarean with an average accuracy, precision and recall of 80%, 85% and 84% respectively. Association rule mining is used to extract disease patterns from the collected data. It highlights the important medical factors that are associated with cesarean births.