Muhammad Qaiser Saleem

Teaching and Learning Computer Science at Al Baha University, Saudi Arabia: Insights from a Staff Development Course

In this special session we meet a set of projects in computer science and engineering education at a university in Saudi Arabia. They are the product of a pedagogical development course ran in collaboration with a Swedish university during the academic year 2013/2014. The projects reflect the local situation, with its possibilities and challenges, and suggest steps to take, in the local environment, to enhance education. As such it is a unique document that brings insights from computer science and engineering education into the international literature.

Vehicle Remote Health Monitoring and Prognostic Maintenance System

In many industries inclusive of automotive vehicle industry, predictive maintenance has become more important. It is hard to diagnose failure in advance in the vehicle industry because of the limited availability of sensors and some of the designing exertions. However with the great development in automotive industry, it looks feasible today to analyze sensor’s data along with machine learning techniques for failure prediction. In this article, an approach is presented for fault prediction of four main subsystems of vehicle, fuel system, ignition system, exhaust system, and cooling system. Sensor is collected when vehicle is on the move, both in faulty condition (when any failure in specific system has occurred) and in normal condition. The data is transmitted to the server which analyzes the data. Interesting patterns are learned using four classifiers, Decision Tree, Support Vector Machine, Nearest Neighbor, and Random Forest. These patterns are later used to detect future failures in other vehicles which show the similar behavior. The approach is produced with the end goal of expanding vehicle up-time and was demonstrated on 70 vehicles of Toyota Corolla type. Accuracy comparison of all classifiers is performed on the basis of Receiver Operating Characteristics (ROC) curves.

Semantic ontology for annotated images

In multimedia search the retrieval of an image from a huge data-set are surrounded with extensive widespread concerns. Without procedures, the content of multimedia for semantic-interpretation is not clearly or really available for use. Manual Annotation is the only simple technique that helps to overcome semantic- interpretation. However, manual Annotation is not only time wasting and costly but also encompassed with the absence of concept diversity and semantic gap. This paper extends a semantic ontology method to extract label terms of the annotated image. LabelMe is the annotated data-set of the so far annotated terms. It enhances terms with the support of Knowledge bases of WordNet and ConceptNet, particularly. It supplements the identical synonyms as well as semantically related terms. It further reduces the semantic interpretation as well as increases the Semantic ontology for that annotated term domain. The results of an experiment performed shows that, the synonym terms were 15% and conceptually terms were 79% added along the primary list. It represents concept diversity an enhancement of 119.13% unique terms in the original list.

Semantic Space Expansion and Refinement

The revolutionary developments in the digital technologies have indicated a requirement for technology, that systematizes the huge images dataset for easy search and retrieval. This yields an essential demand for developing highly effective retrieval systems. Recently, wide-ranging research efforts have been made in the field of annotated images. However, image Annotation can tag by one term, which cannot accurately describe its semantic meaning and is still an open issue. This paper presents Semantic Space Expansion, which magnifies the annotated terms of the image into synonyms as well as with conceptual terms, which covered a wide range of semantics. The synonym terms added from the open knowledge base such as, WordNet while conceptually terms added from the open common-scenes knowledge base of ConceptNet. Due to expansions some of the terms are relevant while some of them are irrelevant from knowledge bases. Semantic Expansion Refinement (SER) is designed to filters relevant terms from the expansion list. The result of the experiments showed successfully enhancement of annotated image terms through tagging ratio and degree of retrieval.

Model driven software development: An overview

The vision of the MDSD is an era of software engineering where modelling completely replaces programming i.e. the systems are entirely generated from high-level models, each one specifying a different view of the same system. The MDSD can be seen as the new generation of visual programming languages which provides methods and tools to streamline the process of software engineering. Productivity of the development process is significantly improved by the MDSD approach and it also increases the quality of the resulting software system. The MDSD is particularly suited for those software applications which require highly specialized technical knowledge due to the involvement of complex technologies and the large number of complex and unmanageable standards. In this paper, an overview of the MDSD is presented; the working styles and the main concepts are illustrated in detail.