A novel grasshopper optimization algorithm based on swarm state difference and its application

The grasshopper optimization algorithm (GOA) has received extensive attention from scholars in various real applications in recent years because it has a high local optima avoidance mechanism compared to other meta-heuristic algorithms. However, the small step moves of grasshopper lead to slow convergence. When solving larger-scale optimization problems, this shortcoming needs to be solved. In this paper, an enhanced grasshopper optimization algorithm based on solitarious and gregarious states difference is proposed. The algorithm consists of three stages: the first stage simulates the behavior of solitarious population learning from gregarious population; the second stage merges the learned population into the gregarious population and updates each grasshopper; and the third stage introduces a local operator to the best position of the current generation. Experiments on the benchmark function show that the proposed algorithm is better than the four representative GOAs and other metaheuristic algorithms in more cases. Experiments on the ontology matching problem show that the proposed algorithm outperforms all metaheuristic-based method and beats more the state-of-the-art systems.

On Interim Cognitive Diagnostic Computerized Adaptive Testing in Learning Context

Interim assessment occurs throughout instruction to provide feedback about what students know and have achieved. Different from the current available cognitive diagnostic computerized adaptive testing (CD-CAT) design that focuses on assessment at a single time point, the authors discuss several designs of interim CD-CAT that are suitable in the learning context. The interim CD-CAT differs from the current available CD-CAT designs primarily because students’ mastery profile (i.e., skills mastery) changes due to learning, and new attributes are added periodically. Moreover, hierarchies exist among attributes taught sequentially and such information could be used during item selection. Two specific designs are considered: The first one is when new attributes are taught in Stage II, but the student mastery status of the previously taught attributes stays the same. The second design is when both new attributes are taught, and previously taught attributes can be further learned or forgotten in Stage II. For both designs, the authors propose an individual prior, which considers a person’s learning history and population learning model, to start an interim CD-CAT. Simulation results show that the Stage II CD-CAT using individual prior outperforms the methods using population priors. The GDINA (generalized deterministic inputs, noisy, “and” gate) diagnostic index (GDI) is extended to accommodate item hierarchies, and analytic results are provided to further illustrate the types of items that are most popular during item selection. As the first study that focuses on the application of CD-CAT in a learning context, the methods and results present herein showed the great promise of using CD-CAT to monitor learning.

Sleeping with Tuberculosis: Do over-crowded university hostels in Kenya increase TB transmission among youths - A pilot study

Background Understanding the magnitude of Tuberculosis (TB) transmission among the youth is a global priority as the disease burden shifts to this population. Learning institutions host overcrowded accommodation and classrooms, especially in resource limited contexts. Understanding the global threat of the youth as an infection pool on the wider population is highlighted in the global response to COVID 19. This pilot study aimed to test the feasibility of recruiting university students’ contacts and demonstrate transmission of TB in Pwani University, Kilifi County-Kenya. Materials and Methods A pilot study among Pwani University TB index cases receiving treatment at the Kilifi County Hospital was conducted. Index cases who consented provided information about their household and social contacts. Contacts were identified and screened using a World Health Organization (WHO) symptom-based questionnaire. Their sputum samples were analysed using GeneXpert. Multivariate log-binomial regression was used to determine demographic and clinical characteristics associated with TB infection among contacts with TB index patients. Results A total of 51 index cases were recruited, median (IQR) age of 21 (20–23) years and 31 (61%) were males. 156 contacts were screened, median (IQR) age of 23 (20–23) years, 80 (51%) were males and 76 (49%) were household contacts. Among the 156 TB contacts, 5 participants were confirmed positive for TB: prevalence of 3.2% (95% CI 1.0 to 7.3%). 8/156 (5.1%, (95% CI 2.2 to 10%) contacts, had clinical diagnosed TB despite having a negative GeneXpert result. In total 13/156 contacts had either confirmed or clinical diagnosed TB; 8.3% (95% CI 4.5 to 14%). Sharing a bed with an index case was the only factor significantly associated with TB infection among the five contacts with GeneXpert diagnosed TB. Conclusion Students sleeping in crowded hostels promote TB transmission within universities informing TB control interventions. Collaborating with existing national TB programme systems is a feasible approach to recruit people with active disease and their social contacts. Expansion of this approach to a larger population of students with TB infection may demonstrate the magnitude of TB transmission within universities, and the wider local communities.

On the Design of Interim Cognitive Diagnostic Computerized Adaptive Testing (CD-CAT) in Learning Context

Interim assessment occurs throughout instruction to provide feedback about what students know and have achieved (Popham, 2008; Shepard, 2009). Different from the current available cognitive diagnostic computerized adaptive testing (CD-CAT) design that focuses on assessment at a single time point, we discuss several designs of interim CD-CAT that are suitable in the learning context. The interim CD-CAT differs from the current available CD-CAT designs primarily because students’ mastery profile (i.e., skills mastery) changes due to learning, and new attributes are added periodically. Moreover, hierarchies exist among attributes taught sequentially and such information could be used during item selection. Two specific designs are considered: the first one is when new attributes are taught in stage II but the student mastery status of the previously taught attributes stay the same. The second design is when both new attributes are taught and previously taught attributes can be further learned or forgotten in stage II. For both designs, we propose an individual prior, which takes into account a person’s learning history and population learning model, to start an interim CD-CAT. Simulation results show that the new method outperforms the current method that treats each interim CD-CAT independently. The generalized diagnostic index (GDI) is extended to accommodate item hierarchies, and analytic results are provided to further illustrate the types of items that are most popular during item selection.

An Approach to Data Reduction for Learning from Big Datasets: Integrating Stacking, Rotation, and Agent Population Learning Techniques

In the paper, several data reduction techniques for machine learning from big datasets are discussed and evaluated. The discussed approach focuses on combining several techniques including stacking, rotation, and data reduction aimed at improving the performance of the machine classification. Stacking is seen as the technique allowing to take advantage of the multiple classification models. The rotation-based techniques are used to increase the heterogeneity of the stacking ensembles. Data reduction makes it possible to classify instances belonging to big datasets. We propose to use an agent-based population learning algorithm for data reduction in the feature and instance dimensions. For diversification of the classifier ensembles within the rotation also, alternatively, principal component analysis and independent component analysis are used. The research question addressed in the paper is formulated as follows: does the performance of a classifier using the reduced dataset be improved by integrating the data reduction mechanism with the rotation-based technique and the stacking?

Comparación de los LMS Moodle y CourseSites de Blackboard usando el modelo de aceptación tecnológica TAM / Comparison of LMS Moodle and Blackboard CourseSites using the technology acceptance model TAM

Este artículo presenta un análisis comparativo de dos sistemas de gestión de aprendizaje Learning Management Systems (LMS): Moodle y CourseSites de Blackboard. El estudio se realizó para evaluar la aceptación de ambos sistemas por parte de los estudiantes, utilizando el Modelo de Aceptación de Tecnología (TAM). Este estudio analizó la aceptación de una herramienta tecnológica en los estudiantes. El TAM se basa en un cuestionario compuesto por seis variables y veintiocho preguntas. Concretamente se estudió una muestra representativa de estudiantes que utilizan ambos LMS para el desarrollo de sus actividades de clase, en la Facultad de Ciencias de la Ingeniería en la Universidad Estatal de Milagro. Con la aplicación de la teoría de la prueba de hipótesis de diferencia entre proporciones se evidenció, de manera estadística, que en la población analizada el aprendizaje es mejor en CourseSites que Moodle. Además, que CourseSites ofrece una mayor facilidad de uso y por lo tanto es más “amigable y divertido”. Por otra parte, los estudiantes se consideraron capaces de utilizar las dos herramientas. En general, este estudio muestra la conveniencia de adoptar CourseSites como una herramienta para el aprendizaje virtual. AbstractIn this article a comparative analysis of two learning management systems (LMS) is presented; Moodle and Blackboard CourseSites. A study was conducted using the Technology Acceptance Model (TAM) to evaluate the acceptability of each system amongst students. The TAM is based on a questionnaire composed of six variables and twenty questions. The authors worked with a representative sample of students using both LMS to carry out their class activities in the Faculty of Engineering at the Public University of Milagro in Ecuador. By applying the statistical hypothesis testing based on the theory of proportional difference it was revealed that in the analyzed population learning is better using CourseSites than Moodle. CourseSites offers greater ease of use and is thus more “friendly and fun. Students considered themselves capable of using both tools. In general, this study showed the desirability of adopting CourseSites as a tool for virtual learning.