Md. Saifuddin Khalid

A Belief Rule-Based Expert System to Diagnose Influenza

Influenza is a viral disease that usually affects the nose, throat, bronchi, and seldom lungs. This disease spreads as seasonal epidemics around the world, with an annual attack rate of estimated at 5%-10% in adults and 20%-30% in children. Thus, influenza is regarded as one of the critical health hazards of the world. Early diagnosis (consisting of determination of signs and symptoms) of this disease can lessen its severity significantly. Examples of signs and symptoms of this disease consist of cough, fever, headache, bireme, nasal congestion, nasal polyps and sinusitis. These signs and symptoms cannot be measured with near-100% certainty due to varying degrees of uncertainties such as vagueness, imprecision, randomness, ignorance, and incompleteness. Consequently, traditional diagnosis, carried out by a physician, is unable to deliver desired accuracy. Hence, this paper presents the design, development and application of an expert system to diagnose influenza under uncertainty. The recently developed generic belief rule-based inference methodology by using the evidential reasoning (RIMER) approach is employed to develop this expert system, termed as Belief Rule Based Expert System (BRBES). The RIMER approach can handle different types of uncertainties, both in knowledge representation, and in inference procedures. The knowledge-base of this system was constructed by using records of the real patient data along with in consultation with the Influenza specialists of Bangladesh. Practical case studies were used to validate the BRBES. The system generated results are effective and reliable than from manual system in terms of accuracy.

Exploring the use of iPads in Danish schools

Mobile devices, especially the integration and adoption of iPads in school classrooms, is gaining emphasis across the research and development forums of academic, policy, organizational, political, and public spheres. In April 2012, the Danish government announced that they would allocate DKK 500 million to develop the use of IT in elementary schools in Denmark. Since then, many municipalities have purchased iPads for schools for large sums. The existing literature, however, says very little about how these IT resources are being used or should be used in teaching. This paper contributes to the knowledge of how teachers and students use iPads in school contexts. During fall 2013, three elementary schools’ second and sixth graders were observed, and their subject teachers were interviewed. The researchers applied a social constructivist perspective and a qualitative research design, using grounded theory methodology. The relevant factors identified were available knowledge and adoptable practice (including innovation evaluation, subject culture, learning activity design, and teachers’ and students’ skill level with iPads); advantages (including mobility, multimodality, access to information, startup time, and differentiated learning environments); and adoption barriers (including accessibility, training, and economy) as seen in relation to technology, pedagogy, and content. The paper concludes that the identified nature of knowledge, practices, and barriers are similar to the trend of integrating and adopting desktop computers and other educational technologies. However, there are some unique advantages that iPad and other mobile devices can enable through apps, readiness, etc. Policies and strategies should be adopted to combine training and maintenance along with ensuring access to iPads.

A belief rule-based expert system to assess mental disorder under uncertainty

Mental disorder is a change of mental or behavioral pattern that causes sufferings and impairs the ability to function in ordinary life. In psychopathology, the assessment methods of mental disorder contain various types of uncertainties associated with signs and symptoms. This study identifies a method that addresses the issue of uncertainty in assessing mental disorder. The fuzzy logic knowledge representation schema can address uncertainty associated with linguistic terms including ambiguity, imprecision, and vagueness. However, fuzzy logic is incapable of addressing uncertainty due to ignorance, incompleteness, and randomness. So, a belief rule-based expert system (BRBES) has been designed and developed with the capability of handling the uncertainties mentioned. Evidential reasoning works as the inference engine and the belief rule base as the knowledge representation schema in this BRBES. The study shows that the results generated by BRBES are more reliable than that of Fuzzy Rule-based expert system and from a human expert.

Numerical round-off error in cellular phone services billing system

Cellular phone services billing for per minute tariff plan and 1-second pulse involve floating point division and multiplication operation to calculate per call bill. Monthly customer billing involves addition operations on per call bills, which are floating point numbers. Round-off errors occur due to floating point numberspsila computer representation limitations and for storing limited significant figures during billing. The study analyzed post-paid itemized bills of a cellular phone service operator in Bangladesh and identified that accumulated round-off error for active post-paid subscribers is significantly high for subscriber group of large number. The research recommends a per second tariff plan to completely eliminate round-off error which also reduces floating point number operations.

Representation of intangible cultural heritage of Bangladesh through social media

ABSTRACT UNESCO has declared Baul songs in 2008 and Traditional Art of Jamdani Weaving in 2013 as ‘Intangible Cultural Heritage of Humanity,’ stating its importance in Bangladesh as a symbol of identity, dignity, and self-recognition. Bangladesh is one of the next 11 countries in the world with approximately 160 million people is experiencing an exponential growth of social media users. Towards the goal of strategically representing and diffusing ICH through social media, this study explores the current roles of social media in the transmission of ICH in the virtual world through content analysis. The potential roles of social media in the process of preserving ICH offer a space for building awareness, creating knowledge, and diffusion of innovations.

A Belief Rule-Based Expert System to Assess Bronchiolitis Suspicion from Signs and Symptoms Under Uncertainty

Bronchiolitis is an acute viral infection of the bronchioles—a common disease that affects millions of children around the world. Clinically, the disease is suspected by observing the signs and symptoms. The signs and symptoms are difficult to measure with 100% certainty, which make suspecting Bronchiolitis inaccurate while suspecting severity level as well. So, the paper aims at designing and developing a Belief Rule-Based Expert System (BRBES), which can suspect Bronchiolitis under uncertainty and increase accuracy. Belief rule based inference methodology has been considered to develop the inference engine of the expert system while the belief rule base has been used to develop the knowledge-base. The reliability of the BRBES has been tested by using real patient data and compared with the expert opinion.

Considerations and Methods for Usability Testing with Children

In this paper, the authors draw on methods used in the field of interaction design, emphasizing a user-centred design approach including methods such as usability testing, design metaphors, interview with users, video observations, focus groups, and think aloud sessions. However, a challenge of these methods is that they are designed for adults and are not necessarily appropriate to investigations including children. The guiding questions for this systematic literature review are (1) the motivation for conducting usability tests with children, and (2) the kind of methodological, practical, and ethical considerations that should be considered when involving children in usability studies. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist and PRISMA flow diagram are applied in order to assure the quality of the process of this investigation. Nine articles are analyzed and then synthesized by applying the constant comparative method. The synthesis of the literature review is based on the identified thematic priorities, which are categorized as follows: (1) the motivation for involving children as test persons in design processes, (2) definitions of usability, (3) practical considerations, (4) methodological considerations, and (5) ethical considerations.

Usability evaluation of a video conferencing system in a university's classroom

The integration of video conferencing systems (VCS) have increased significantly in the classrooms and administrative practices of higher education institutions. The VCSs discussed in the existing literature can be broadly categorized as desktop systems (e.g. Scopia), WebRTC or Real-Time Communications (e.g. Google Hangout, Adobe Connect, Cisco WebEx, and appear.in), and dedicated (e.g. Polycom). There is a lack of empirical study on usability evaluation of the interactive systems in educational contexts. This study identifies usability errors and measures user satisfaction of a dedicated VCS in a Danish universitys classrooms. This work contributes (1) to the methodological approach that uses mixed methods to collect and analyze data from users as part of a summative evaluation, (2) to demonstrate the methods applied by independent usability evaluator using field study approach, (3) to the usability evaluation literature dealing with empirical evaluation methods. PACT (people, activity, context, and technology) analysis of participant observation and interview data shows a lack of user guide, training, IT support, and vendor coordination. Software usability measurement inventory (SUMI) analysis of 12 user responses results below average score. Post-study system test by the vendor has identified cabling and setup error. Applying SUMI followed by qualitative methods might enrich evaluation outcomes.