Academic procrastination has been reported affecting students' performance in computersupported learning environments. Studies have shown that students who demonstrate higher procrastination tendencies achieve less than the students with lower procrastination tendencies. It is important for a teacher to be aware of the students' behaviors especially their procrastination trends. EDM techniques can be used to analyze data collected through computer-supported learning environments and to predict students' behaviors. In this paper, we present an algorithm called students' academic performance enhancement through homework late/non-submission detection (SAPE) for predicting students' academic performance. This algorithm is designed to predict students with learning difficulties through their homework submission behaviors. First, students are labeled as procrastinators or non-procrastinators using k-means clustering algorithm. Then, different classification methods are used to classify students using homework submission feature vectors. We use ten classification methods, i.e., ZeroR, OneR, ID3, J48, random forest, decision stump, JRip, PART, NBTree, and Prism. A detailed analysis is presented regarding performance of different classification methods for different number of classes. The analysis reveals that in general the prediction accuracy of all methods decreases with increase in the number of classes. However, different methods perform best or worst for different number of classes.INDEX TERMS Blended learning, computer-assisted learning, educational data mining as an inquiry method, e-learning, higher education, learning management systems, online learning.

This paper presents the fusion of project‐based learning (PBL) and collaborative learning (CL) cohesively, coordinated with sensors and Bluetooth advancements, open‐source programming, and open‐source equipment devices, in a specific microcontroller and installed frameworks designing apply autonomy course for the elementary learners. The major purpose of this study is to evaluate the significance of integrating PBL and CL. The course creates capacities and abilities in critical thinking, problem‐solving, independent learning, collaboration, and specialized technical information. Since PBL alone does not guarantee profoundly talented cooperation, it was supplemented with CL. This structure coordinated course substance and understudy pragmatic accomplishment in a reenacted learning environment. The understudies built a line following and Bluetooth‐controlled robots by actualizing control programming on the “Arduino” open‐source platform, just as utilizing remote interchanges as Arduino offers an instinctive advancement condition and different equipment and programming resources that permit quick improvement of microcontroller‐based ventures. The basic findings of this study work reveal that teaching, learning, and student assessment processes can be improved by using PBL when integrated with CL. The research successfully extends onto another group of learners for preparing similar gadgets under different timelines. In addition, this paper also discusses upon the problem identification, selection of the equipment, circuit design, hardware mounting, and critical analysis of the results acquired from the course through the personal learning experience of the teachers as well as in the form of feedback from the two groups of young learners.

No abstract

In the era of Big Data, users prefer to get knowledge rather than pages from Web. Linked Data, a rather new form of knowledge representation and publishing described by RDF, can provide a more precise and comprehensible semantic structure to satisfy the aforementioned requirement. Besides, as the standard query language for RDF data, SPARQL has become the foundation protocol of Linked Data querying. The core idea of RDF Schema (RDFS) is to extend upon RDF vocabulary and allow attachment of semantics to user defined classes and properties. However, RDFS cannot fully utilize the potential of RDF since it cannot express the implicit semantics between linked entities in Linked Data sources. To fill this gap, in this paper, we design a new semantic annotating and reasoning approach that can extend more implicit semantics from different properties. We firstly establish a well‐defined semantically enhanced annotation strategy for Linked Data sources. In particular, we present some new semantic properties for predicates in RDF triples and design a Semantic Matrix for Predicates (SMP). We then propose a novel general Semantically Extended Scheme for Linked Data Sources (SESLDS) to realize the semantic extension over the target Linked Data source through semantically enhanced reasoning. Lastly, based on the experimental analyses, we verify that our proposal has advantages over the initial Linked Data source and can return more valid results.

Summary Traditional feature‐based semantic similarity (SS) approaches exploit the Wikipedia features in term of sets. They evaluate the similarity of concepts based on the commonalities among their feature sets. However, these feature‐based approaches treat all the features equally in similarity evaluation. Therefore, they ignore the underlying statistics of the features and consequently lose the essential semantic details about them. One solution is that each feature can be assigned a specific weight using its statistics. This weight will reflect the relative importance of a feature in similarity evaluation. Therefore, in this paper, based on two statistical models, ie, information content and TFIDF, we propose some hybrid semantic similarity measurement methods. Firstly, we propose some new methods called weighting functions to compute the weights of the features and feature sets in Wikipedia. Secondly, based on the weighting functions, we propose some new weighted feature‐based SS approaches for Wikipedia concepts. Thirdly, we evaluate the proposed methods on well‐known benchmarks for English, German, French, and Spanish languages. Finally, we compare the performance of our methods with the traditional feature‐based and some state‐of‐the‐art SS approaches. The experimental evaluation shows that our weighted methods perform better than the traditional feature‐based and some state‐of‐the‐art approaches in similarity evaluation.