Most existing e-learning systems strictly require the course instructors to explicitly input the pre-requisite requirements and/or some relationship measures between the involved concepts/modules such that an optimal learning path as a sequence of the involved concepts can be determined for a class or an individual after considering the student's academic performance, educational background, learning interests, learner profile, learning styles, etc. In some cases, the learning path is determined solely by human experts. Since human can be biased, the course instructor's views on the relations of the involved concepts/modules can be imprecise or even contradictory, thus prohibiting any logical deduction of an optimal learning path. Besides, human experts may ignore or possibly be confused by contradictory requirements in the real-world applications. Therefore, we propose a new and systematic framework to develop the next-generation e-learning systems that will perform an explicit semantic analysis on the course materials to extract the individual concepts, and then grouped by a heuristic-based concept clustering algorithm to compute the relationship measures as the basis for extracting the prerequisite requirements/constraints between the involved concepts. Lastly, an evolutionary optimizer will be invoked to return the optimal learning sequence after considering multiple experts' recommended learning sequences which may contain conflicting views in different cases. It is worth noting that our proposed and structured framework with the seamless integration of concept clustering and learning path optimization uniquely represents the first attempt to facilitate the course designers/instructors in providing more personalized and 'systematic' advice (2014) 1(4): 335-352 DOI 10.1007/s40692-014-0016-8 through optimizing the learning path(s) for each individual class/learner. To demonstrate the feasibility of our prototype, we implemented a prototype of the proposed e-learning system framework, and also enhanced the original optimizer with the hill-climbing heuristic. Our empirical evaluation clearly revealed the many possible advantages of our proposal with interesting directions for future investigation.

No abstract

No abstract

No abstract

Nematode worms are one of most abundant metazoan groups on the earth, occupying diverse ecological niches. Accurate recognition or identification of nematodes are of great importance for pest control, soil ecology, bio-geography, habitat conservation and against climate changes. Computer vision and image processing have witnessed a few successes in species recognition of nematodes; however, it is still in great demand. In this paper, we identify two main bottlenecks: (1) the lack of a publicly available imaging dataset for diverse species of nematodes (especially the species only found in natural environment) which requires considerable human resources in field work and experts in taxonomy, and (2) the lack of a standard benchmark of state-of-the-art deep learning techniques on this dataset which demands the discipline background in computer science. With these in mind, we propose an image dataset consisting of diverse nematodes (both laboratory cultured and naturally isolated), which, to our knowledge, is the first time in the community. We further set up a species recognition benchmark by employing state-of-the-art deep learning networks on this dataset. We discuss the experimental results, compare the recognition accuracy of different networks, and show the challenges of our dataset. We make our dataset publicly available at: https: // github. com/ xuequanlu/ I-Nema