Search

Image content prediction with novel deep learning approaches is a hot research topic for many scientific disciplines. Image-based food types recognition and their ingredients is a particularly challenging task, since food dishes are typically deformable objects, usually including complex semantics, which makes the task of defining their structure very difficult. In this paper we introduce a novel web-based system that exploits commercial deep learning based platforms to predict image content for food recognition. In addition to that, the system combines the individual predictions of the platforms to produce more accurate results. Also, we provide a short assessment of the chosen platforms to determine the most efficient one, in the domain of food recognition. The paper is concluded by highlighting the key features of platforms and the advantages of the new presented system.

Video has been widely used as an effective media for delivering varied educational content. The enormous expansion of educational video is due to its effectiveness and to the spectacular evolution of video construction technology. Modern technology allows the rapid and economic development of educational videos as Software Systems. Such videos may be fully developed using software tools without the need for cameras or other expensive resources, e.g. actors. In this paper, we propose a framework for the effective development of Educational Video. The proposed framework consists of a methodology and a set of design guidelines, both oriented towards the achievement of the learning objectives related to an Educational Video. Experimentally, we compare videos produced following the proposed framework with videos produced following a well-known alternative methodology. Experimental results give rise to the success of our approach and encourage further exploration.

The use of chatbots evolved rapidly in numerous fields in recent years, including Marketing, Supporting Systems, Education, Health Care, Cultural Heritage, and Entertainment. In this paper, we first present a historical overview of the evolution of the international community’s interest in chatbots. Next, we discuss the motivations that drive the use of chatbots, and we clarify chatbots’ usefulness in a variety of areas. Moreover, we highlight the impact of social stereotypes on chatbots design. After clarifying necessary technological concepts, we move on to a chatbot classification based on various criteria, such as the area of knowledge they refer to, the need they serve and others. Furthermore, we present the general architecture of modern chatbots while also mentioning the main platforms for their creation. Our engagement with the subject so far, reassures us of the prospects of chatbots and encourages us to study them in greater extent and depth.

The fuzzy lattice reasoning (FLR) neural network was introduced lately based on an inclusion measure function. This work presents a novel FLR extension, namely agglomerative similarity measure FLR, or asmFLR for short, for clustering based on a similarity measure function, the latter (function) may also be based on a metric. We demonstrate application in a metric space emerging from a weighted graph towards partitioning it. The asmFLR compares favorably with four alternative graph-clustering algorithms from the literature in a series of computational experiments on artificial data. In addition, our work introduces a novel index for the quality of clustering, which (index) compares favorably with two popular indices from the literature.

Efficient detection of plagiarism in programming assignments of students is of a great importance to the educational procedure. This paper presents a clustering oriented approach for facing the problem of source code plagiarism. The implemented software, called PDetect, accepts as input a set of program sources and extracts subsets (the clusters of plagiarism) such that each program within a particular subset has been derived from the same original. PDetect proposes the use of an appropriate measure for evaluating plagiarism detection performance and supports the idea of combining different plagiarism detection schemes. Furthermore, a cluster analysis is performed in order to provide information beneficial to the plagiarism detection process. PDetect is designed such that it may be easily adapted over any keyword-based programming language and it is quite beneficial when compared with earlier (state-of-the-art) plagiarism detection approaches.

Recent work has proposed an enhancement of Formal Concept Analysis (FCA) in a tunable, hybrid formal context including both numerical and nominal data [1]. This work introduces FCknn, that is a granular knn classifier based on hybrid concepts, whose effectiveness is demonstrated on benchmark datasets from the literature including both numerical and nominal data. Preliminary experimental results compare well with the results by alternative classifiers from the literature. Formal concepts are interpreted as descriptive decision-making knowledge (rules) induced from the data.