Browsing by Author "Fernandez-Sanz, L."

Now showing 1 - 3 of 3

Citation - WoS: 17
Citation - Scopus: 30
Analysis of Cultural and Gender Influences on Teamwork Performance for Software Requirements Analysis in Multinational Environments
(Wiley, 2012) Fernandez-Sanz, L.; Misra, Sanjay; Computer Engineering
Software development is mainly a social activity where teams of developers should work as a coordinated unit to fulfill the needs of customers. Studies have shown the importance of teamwork ability as the main skill for software professionals both in local settings and in global software development. Teamwork performance can be evaluated according to different approaches but we need deeper analysis within software teams of differences in individuals' performance related to culture, nationality or even gender. We applied a simple evaluation experience named teamwork benefits awareness (TBA) to groups of last-year students of computing degrees with experience as junior IT professionals during intensive multinational workshops based on international software projects. TBA allowed to measure individual and team performance during a requirements analysis session based on a real project. Results segmented by nationality and gender are presented and analysed in comparison with the data collected from computing professionals in local settings. In general, no significant differences have been found out although interesting relations are suggested with two Hofstede's country indicators. TBA is also perceived as a good technique for highlighting both teamwork benefits as well as the nature of real situations of software requirements analysis and orientation to customer needs.
Citation - WoS: 19
Citation - Scopus: 31
An Artificial Neural Network Model for Road Accident Prediction: a Case Study of a Developing Country
(Budapest Tech, 2014) Ogwueleka, Francisca Nonyelum; Misra, Sanjay; Ogwueleka, Toochukwu Chibueze; Fernandez-Sanz, L.; Computer Engineering; Computer Engineering
Road traffic accidents (RTA) are one of the major root causes of the unnatural loses of human beings all over the world. Although the rates of RTAs are decreasing in most developed countries, this is not the case in developing countries. The increase in the number of vehicles and inefficient drivers on the road, as well as to the poor conditions and maintenance of the roads, are responsible for this crisis in developing countries. In this paper, we produce a design of an Artificial Neural Network (ANN) model for the analysis and prediction of accident rates in a developing country. We apply the most recent (1998 to 2010) data to our model. In the design, the number of vehicles, accidents, and population were selected and used as model parameters. The sigmoid and linear functions were used as activation functions with the feed forward-back propagation algorithm. The performance evaluation of the model signified that the ANN model is better than other statistical methods in use.
Citation - WoS: 7
Citation - Scopus: 12
Genetic Algorithm and Tabu Search Memory With Course Sandwiching (gats_cs) for University Examination Timetabling
(Tech Science Press, 2020) Abayomi-Alli, A.; Misra, S.; Fernandez-Sanz, L.; Abayomi-Alli, O.; Edun, A. R.; Computer Engineering
University timetable scheduling is a complicated constraint problem because educational institutions use timetables to maximize and optimize scarce resources, such as tine and space. In this paper, an examination timetable system using Genetic Algorithm and Tabu Search memory with course sandwiching (GAT_CS), was developed fora lame public University. The concept of Genetic Algorithm with Selection and Evaluation was implemented while the memory properties of Tabu Search and course sandwiching replaced Crossover and Mutation. The result showed that GAT_CS had hall allocation accuracies of 96.07% and 99.02%, unallocated score of 3.93% and 0.98% for first and second semesters, respectively. It also automatically sandwiched (scheduled) multiple examinations into single halls with a simulation time in the range of 20-29.5 seconds. The GAT_CS outperformed previous related works on the same timetable dataset. It could, however, be improved to reduce clashes, duplications, multiple examinations and to accommodate more system-defined constraints.