Munir Naveed

In order to support the development of clinical practice guideline (CPGs) the representation of clinical problems is necessary to actuate the relevant knowledge for well-defined and meaningful CPGs. However, the development process performed on CPGs usually relies on the cognitive models of the domain expert (clinicians) that are often based on technical and procedural knowledge which can carry implications for the development of CPGs. Thus, their formalization as computer-interpretable CPGs provides a better opportunity of influencing clinical practice than narrative guidelines. The focus of this study is on the acquisition of clinical knowledge into computer interpretable form to develop a semantically rich common ontology for CPG development. This study also views the role of the clinical expert as an essential source of transforming this knowledge into a common ontology. To ascertain a comprehensive knowledge representation of CPGs we analyzed abstracts taken from the sub-domains of HeartDiseases related to its diagnosis, possible treatments and interventions and structured them using the protege-OWL formal modelling tool. The completeness and expressiveness of the ontology is then validated using structured and unstructured queries.

The security threats to mobile devices are growing exponentially as the degree of sophistication for these smart devices increase. Mobile devices are not only used for phone calls, they process several enterprise and personal information on daily basis. The comprise to such crucial and private information can cause devastating effects at personal and enterprise levels. In this work, we present a new approach to develop anti-malware programs that can adapt to themselves to the new definitions of the malwares and can detect them in realtime. We propose a machine learning algorithm that can be trained to identify a malicious activity on a smart-phone. We develop a malware and also used existing malwares to generate a training data set to train a malware for detecting the patterns of malicious activities on devices. The paper also presents the key indicators for pattern matching in such cases. The results show that the new definitions of malicious codes are not detectable by existing sophisticated anti-malware programs by using sandboxing techniques. The results also show that all definitions of malwares work under within the same patterns of indicators.

This paper aims to explore the wide range of the problems being faced by the undergraduate students and align an essential set of requirements for the development of a support tool for the students to counter their problems. The problems being faced by the students are unique in terms of their characteristics, mainly influenced by the rapid changes in social, cultural and economic spheres. The supporting tool can play a motivational role in students’ academic success. Enhancing students’ motivation for academic success is a very important aspect which is a serious concern and requires immediate attention. This work presents the essential artifacts for AIPRO (Artificial Intelligence based Professional support tool). AIPRO is proposed as a mobile computing based solution to support activities for learning and engaging in an undergrad academic program. Different fact-finding techniques are used to gather the requirements for AIPRO. The initial results show the requirement of sophisticated scheduling and profiling algorithms for AIPRO.

This work presents a novel approach, socalled RBCM, in modeling a domain to construct contextaware model for mobile computing. RBCM is based on a multivariate regression method to construct a probability density function for action schema in a domain. A machine learning algorithm is applied to map the action schema with a context. RBCM is evaluated using a benchmark dataset. The results are compared with the start-of-the-art rivals of RBCM. The main candidate rivals of RBCM are based on the latest variations of Nayes-bias, MOCART and Decision Tree. The results show that our model outperform its rival techniques in accuracy and precision. RBCM predicts the preferences of the users with a higher accuracy than its rivals. RBCM perform better with the sample size greater than 50.

An adaptive grouping technique for a cooperative coevolutionary model is presented in this paper. The coevolutionary model is based on Monte-Carlo (MC) simulations and evolutionary programming to solve the balancing between exploration and exploitation in coevolution. The proposed model decomposes a large scale optimization problem into sub-problems of varying sizes. The coevoluationary model with a new grouping technique is applied on a retail dataset for sales optimization. The model is also evaluated using two multidimensional benchmark functions. The results indicate a clear advantage of using Monte-Carlo simulations to balance the trade-off between exploration and exploitation in large scale and high dimensional problem spaces.

In this paper, we present a Monte-Carlo policy rollout technique (called MOCART-CGA) for path planning in dynamic and partially observable real-time environments such as Real-time Strategy games. The emphasis is put on fast action selection motivating the use of Monte-Carlo techniques in MOCART-CGA. Exploration of the space is guided by using corridors which direct simulations in the neighbourhood of the best found moves. MOCART-CGA limits how many times a particular state-action pair is explored to balance exploration of the neighbourhood of the state and exploitation of promising actions. MOCART-CGA is evaluated using four standard pathfinding benchmark maps, and over 1000 instances. The empirical results show that MOCART-CGA outperforms existing techniques, in terms of search time, in dynamic and partially observable environments. Experiments have also been performed in static (and partially observable) environments where MOCART-CGA still requires less time to search than its competitors, but typically finds lower quality plans.