| Font + -
You are here:   HomeProgrammes OfferedPostgraduateMSc. (IT Technopreneurship)Research

Research

Category: Research

Research Seminar: Vulgarisation of Natural Language Processing
2014-12-04
Time 1500 until 1630
Meeting Room 7th Floor
Assoc. Prof. Dr. Bali Ranaivo
N/A
N/A
One of the senses of the word "vulgarisation" is” the act of making something attractive to the general public" (WordNet 2.1). This talk will attempt to present, using layman's words, the main ideas behind the term "natural language processing" (NLP). After this presentation, which should not exceed 45mn, it is hoped that NLP is no longer a mysterious, difficult, or insignificant subject.
N/A
none
2014/15
1
N/A
Read more...
 
Category: Research

Research Review: Triad-based Contextualisation Approach to Better Understanding a Critical Issue
2014-11-20
Time 1500 until 1630
Meeting Room 7th Floor
Lim Chia Yean
Dr. Vincent Khoo Kay Teong
Assoc. Prof. Muhammad Rafie Hj. Mohd. Arshad
A long-standing problem exists on the delivery of the expected solution to the users in a typical software development lifecycle. Somehow, the deliverables are different from the different parties involved. Could the differences be due to poor communications? Could they be due to poor understanding of the requirement? Could they be perhaps due to the omission of a proper context? This research is about contextualisation of any critical and complex issue, which includes three processes namely, context characterisation, representation, and interpretation. In the case of a critical software requirement, it is first qualified by one or more sets of criteria. Each set of the criteria is then converted to a set of triads. In each triad, a respondent is required to answer a question with respect to two other previously responded reference questions. Suppose a triad consists of three related relationships such as (A > B) and (B > C). A respondent is required to give a response whether (A > C) is true or otherwise. If (A > C) is responded to be true, the triad is considered to be consistent. A negative response would render the triad to be inconsistent. At the end of a contextualisation process, there would then be one set of consistent triads and another set of inconsistent triads. Unlike other contextualisation approaches which focus on the positive outcomes and only what the user wants, the proposed approach also covers what the user does not want and what the user has never previously thought of. In this research, it has been unexpectedly found that the one-to-many relationships in both sets of the triads can provide much better insights for the understanding of the software requirements. However, it is found in this research that if one or more inconsistent triads are detected, more than one cycle of the approach with different numbers of criteria must be carried out. If (A > C) can be true in one triad and false in other triads, the aforementioned additional processes must be carried out to identify different contexts in which the reverse relationship (A not> C) is true. Repeating a contextualisation process with different numbers of criteria is certainly a laborious task. Can a machine learning (ML) system be trained to help contextualise many different sets of criteria? Are there advanced analytical tools available for analysing the large number of relationships resulting from the responses automatically generated by a machine learning system? What if many types of respondents are involved? How can the derived contexts be integrated? Is the proposed contextualisation approach a silver bullet to better understanding a critical issue? The answer is ‘No’, not without the applications of some machine learning systems and the advanced analytics tools. But this research is certainly a good starting point.
N/A
none
2014/15
1
N/A
Read more...
 
Category: Research

Research Review: Harmony Search Hyper-heuristic for Scheduling Problems
2014-11-13
Time 1000 until 1130
Meeting Room 7th Floor
Khairul Anwar
Prof. Dr. Ahamad Tajudin Khader
Dr. Mohammed Azmi Al-Betar
This thesis is concerned with the investigation of hyper-heuristic methods. Hyper-heuristic is a new trend in optimization methods. Basically hyper-heuristic can be referred as a method to find the best heuristic to solve an optimization problem on hand. The main motivation of using hyper-heuristic is to produce a general method that can be used to solve different hard optimisation problems. In this thesis we proposed a new hyper-heuristic framework named as Harmony Search-based Hyper-heuristic (HSHH). The original idea was to apply a sequence of low-level heuristics to a selected solution in order to produce good quality solutions to given problem. Therefore, to achieve this goal, we combine three main operators in harmony search algorithm: memory consideration, random consideration and pitch adjustment as a high level heuristic in order to select and generate a sequence of improvement low-level heuristics. To demonstrate the effectiveness of the method, we apply the proposed method to three timetabling and scheduling problems, taken from the real world and our results are compared with those of other heuristic methods in the literature. Experimentally, the HSHH approach can achieve comparable results with other methods and in several instances, HSHH are able to produces competitive results with those obtained using other sophisticated methods.
N/A
none
2014/15
1
N/A
 
Category: Research

Research Review: A Study on Ontology-based and Hybrid Genetic Algorithms Approach in Menu Planning Model for Malaysian Old Folks Home
2014-10-23
Time 1500 until 1630
Meeting Room 7th Floor
Ngo Hea Choon
Assoc. Prof. Dr. Cheah Yu-N
N/A
The number of elderly in Malaysia is not only rising rapidly but also in their life expectancies. Increasing number of old age group presents a real challenge to nutritionists and health professionals. Thus, proper nutrition for the elderly is important to maintain the health and well-being of older people that can leads fulfilling and independent lives. This research presents a study on menu planning using ontology-based and hybrid genetic algorithms approach for Malaysian old folks home in general and cancer disease in particular. Nowadays, there are many diet recommendation systems in the market that provide general advice to the clients. These systems are still insufficient to provide customized diet plan based on the older people who might be at risk of malnutrition. We are attempted to consider elderly with certain chronic disease such as cancer, diabetes, chronic kidney disease, hypertension and hyperlipidemia. In this work, we take into account the elderly with cancer disease to support their nutrition plan. In the aims to discover diets and food products that deliver health to elderly, ontology is used to classify nutrients, food groups and meal structure. Following that, Hybrid genetic algorithms are employed to ensure that the constructed menu is satisfied all the objectives and predefined constraints. Instead of Boolean logic, a fuzzy logic control system was applied in modeling of membership functions of fuzzy sets for estimating nutrition needs in elderly with cancer disease. Fuzzy membership functions are constructed to describe the range of nutrients intake in the range from deficient to excess amounts. It is important to guide dietitians towards a standardized dietary management along the nutrition care process for cancer patients in order to improve patients’ outcome. The proposed work aims to (i) produce a diet plan representation based on diet plan ontology; (ii) design a planning engine by integrating genetic algorithms with local search technique to enhance menu plan; (iii) develop a special menu plan to cater patients with cancer disease using fuzzy reasoning mechanism. The evidence from this study showed that the proposed methods yield significant improvement in menu planning model.
N/A
none
2013/14
1
N/A
 

Related Topics

Contact Us

Home
Address:
School of Computer Sciences
Universiti Sains Malaysia
11800 USM, Penang, Malaysia
Tel: (+604) 653 3888 ext. 3647/3610
Fax: (+604) 657 3335

Best View

Screen Resolution:
1280 x 1024 or above with

Firefox Logo
FireFox6
or above

Google Chrome Logo
Google
Chrome

Internet Explorer 7 Logo
IE 6
or above

Opera Logo
Opera11.5
or above

**For IE users, please UNCHECK the `Compatibility View` setting at Tools menu for a proper view.

Login