145 results
Search Results
Now showing 1 - 10 of 145
Article Citation - WoS: 7Citation - Scopus: 13An Expert System for the Diagnosis of Sexually Transmitted Diseases - Esstd(Ios Press, 2017) Thompson, Temitope; Sowunmi, Olaperi; Misra, Sanjay; Fernandez-Sanz, Luis; Crawford, Broderick; Soto, RicardoOver 93 million people get ill with sexually transmitted diseases in sub-Saharan Africa. However, research has shown that people with sexually transmitted diseases find it difficult to share their problem with a physician due to societal discrimination in Africa. Due to this problem, we have implemented a medical expert system for diagnosing sexually transmitted diseases (ESSTD) that maintains the anonymity of the individuals. The patients diagnose themselves by answering questions provided by the system. This paper presents the design and development of the system. Forward chaining rules were used to implement the knowledge base and the system is easily accessible on mobile platforms. The Java Expert System Shell was used for its inference engine and the system was validated by domain experts. It is useful because it helps to maintain anonymity for patients with STD.Conference Object Citation - WoS: 2A Multi-Paradigm Complexity Metric (mcm)(Springer-verlag Berlin, 2011) Misra, Sanjay; Akman, Ibrahim; Cafer, FeridHuge amount of researches and software metrics have been proposed for procedural and object-oriented languages. However, there are only few metrics available in the literature related with multi-paradigm programming languages. In this paper, we propose a metric to evaluate the code written in multi-paradigm language. Our proposed metric can be used for most of the programming paradigms, including both procedural and object-oriented languages.Conference Object Comparative Study of Cognitive Complexity Measures(Ieee, 2008) Misra, Sanjay; Mısra, Sanjay; Akman, Ibrahim; Akman, Kamil İbrahim; Mısra, Sanjay; Akman, Kamil İbrahim; Computer Engineering; Computer EngineeringComplexity metrics are used to predict critical information about reliability and maintainability of software systems. Cognitive complexity measure based on cognitive informatics, plays an important role in understanding the fundamental characteristics of software, therefore directly affects the understandability and maintainability of software systems. In this paper, we compared available cognitive complexity measures and evaluated cognitive weight complexity measure in terms of Weyuker's properties.Article Citation - WoS: 104Citation - Scopus: 163Cassava Disease Recognition From Low-Quality Images Using Enhanced Data Augmentation Model and Deep Learning(Wiley, 2021) Abayomi-Alli, Olusola Oluwakemi; Damasevicius, Robertas; Misra, Sanjay; Maskeliunas, RytisImprovement of deep learning algorithms in smart agriculture is important to support the early detection of plant diseases, thereby improving crop yields. Data acquisition for machine learning applications is an expensive task due to the requirements of expert knowledge and professional equipment. The usability of any application in a real-world setting is often limited by unskilled users and the limitations of devices used for acquiring images for classification. We aim to improve the accuracy of deep learning models on low-quality test images using data augmentation techniques for neural network training. We generate synthetic images with a modified colour value distribution to expand the trainable image colour space and to train the neural network to recognize important colour-based features, which are less sensitive to the deficiencies of low-quality images such as those affected by blurring or motion. This paper introduces a novel image colour histogram transformation technique for generating synthetic images for data augmentation in image classification tasks. The approach is based on the convolution of the Chebyshev orthogonal functions with the probability distribution functions of image colour histograms. To validate our proposed model, we used four methods (resolution down-sampling, Gaussian blurring, motion blur, and overexposure) for reducing image quality from the Cassava leaf disease dataset. The results based on the modified MobileNetV2 neural network showed a statistically significant improvement of cassava leaf disease recognition accuracy on lower-quality testing images when compared with the baseline network. The model can be easily deployed for recognizing and detecting cassava leaf diseases in lower quality images, which is a major factor in practical data acquisition.Article Citation - WoS: 31Citation - Scopus: 50Neural Network and Classification Approach in Identifying Customer Behavior in the Banking Sector: a Case Study of an International Bank(Wiley, 2015) Ogwueleka, Francisca Nonyelum; Misra, Sanjay; Colomo-Palacios, Ricardo; Fernandez, LuisThe customer relationship focus for banks is in development of main competencies and strategies of building strong profitable customer relationships through considering and managing the customer impression, influence on the culture of the bank, satisfactory treatment, and assessment of valued relationship building. Artificial neural networks (ANNs) are used after data segmentation and classification, where the designed model register records into two class sets, that is, the training and testing sets. ANN predicts new customer behavior from previously observed customer behavior after executing the process of learning from existing data. This article proposes an ANN model, which is developed using a six-step procedure. The back-propagation algorithm is used to train the ANN by adjusting its weights to minimize the difference between the current ANN output and the desired output. An evaluation process is conducted to determine whether the ANN has learned how to perform. The training process is halted periodically, and its performance is tested until an acceptable result is obtained. The principles underlying detection software are grounded in classical statistical decision theory.Conference Object An Evaluation on Developer's Perception of Xml Schema Complexity Metrics for Web Services(Springer-verlag Berlin, 2013) Crasso, Marco; Mateos, Cristian; Coscia, Jose Luis Ordiales; Zunino, Alejandro; Misra, SanjayUndoubtedly, the Service-Oriented Computing (SOC) is not an incipient computing paradigm anymore, while Web Services technologies is now a very mature stack of technologies. Both have been steadily gaining maturity as their adoption in the software industry grew. Accordingly, several metric suites for assessing different quality attributes of Web Services have been recently proposed. In particular, researchers have focused on measuring services interfaces descriptions, which like any other software artifact, have a measurable size, complexity and quality. This paper presents a study that assesses human perception of some recent services interfaces complexity metrics (Basci and Misra's metrics suite). Empirical evidence suggests that a service interface that it is not complex for a software application, in terms of time and space required to analyze it, will not be necessarily well designed, in terms of best practices for designing Web Services. A Likert-based questionnaire was used to gather individuals opinions about this topic.Article Citation - WoS: 20Citation - Scopus: 25A Study on the Key Soft Skills for Successful Participation of Students in Multinational Engineering Education(Tempus Publications, 2017) Fernandez-Sanz, Luis; Teresa Villalba, Maria; Amelio Medina, Jose; Misra, Sanjay; Villalba, Maria Teresa; Medina, José Amelio; Computer EngineeringSoft-skills have proved to be a necessary complement to technical skills in today's multinational workplaces. As universities are facing the challenge of promoting internationalization and mobility in students and teachers, they have to decide how to help their students in developing these skills as well as increase their awareness on the cultural differences in multinational settings. After a long trajectory of participation in multinational educational experiences, the authors launched a survey to check if their previous findings on the preferred soft skills by educational experts and managers still remain valid after 5 years. Another goal of the study was the analysis of the link between preference for specific soft skills and cultural background in each country as characterized by Hofstede's indicators. The data collected from 123 experts from 45 different countries have confirmed the existence of a stable core set of preferred soft skills at global level and also for European countries. Results have also shown links between specific cultural indicators and preference for some soft skills.Article Citation - Scopus: 1Maintaining Software Through Bit-Parallelism and Hashing the Parameterized q-grams(Univ Osijek, Tech Fac, 2012) Prasad, Rajesh; Agarwal, Suneeta; Misra, Sanjay; Sharma, Anuj Kumar; Singh, Alok; Computer EngineeringIn the software maintenance, it is often required to find duplicity present in the codes. Two code fragments are equivalent, if one can be transformed into the other via consistent renaming of identifiers, literals and variables. This equivalency can be detected by parameterized string matching. In this matching, a given pattern is said to match with a substring of the text, if there exists a one-to-one correspondence between symbols of and symbols of. In this paper, we propose an efficient algorithm for this problem by using both the overlapping and non-overlapping q-gram. We show the effect of running time of the algorithm on increasing the duplicity present in the code.Article Citation - WoS: 19Software Development Outsourcing: Challenges and Opportunities in Nigeria(Taylor & Francis inc, 2014) Casado-Lumbreras, Cristina; Colomo-Palacios, Ricardo; Ogwueleka, Francisca N.; Misra, SanjayIn recent years, several emergent regions have become software development sourcing countries. This article investigates the possibilities of sub-Saharan Africa as a sourcing destination in the software field. To find out the reasons why sub-Saharan Africa countries, in general, and Nigeria, in particular, are not considered a destination for global software development projects, the authors interviewed a set of professionals from Europe and Africa. Results indicate that there are many disadvantages and difficulties impeding Nigeria from becoming a preferred sourcing destination, mainly the absence of a strong software industry and the concerns about legislative, fiscal, and commercial premises. On the other hand, it is observed that there are also relevant added values and competitive advantages in Nigeria (English-speaking country, same time zone, and cost); therefore, it can become a potential target for software development outsourcing in the medium and long terms.Article Citation - WoS: 17Citation - Scopus: 30Analysis of Cultural and Gender Influences on Teamwork Performance for Software Requirements Analysis in Multinational Environments(Wiley, 2012) Fernandez-Sanz, L.; Misra, SanjaySoftware 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.
