The paper presents computing engineering students' perceptions of ePortfolios and key considerations for integrating ePortfolios into computing education programs to facilitate students' recognition of acquired competencies. Students, in general, tend to focus primarily on aspects such as the final exam and their final grades, which can lead to a lack of focus on the learning process where they develop skills and competencies. The ePortfolio can be a powerful reflection, self-assessment, and professional development tool and has been found to engage students in the learning process and make invisible learning visible to students. Understanding computing students' perceptions towards ePortfolios can provide insights into how effective ePortfolios are as a learning tool in computing education programs. We derived insight from an ePortfolio introduction session where we introduced 30 computer engineering students with no experience with the ePortfolio to the concept for the first time. Following the session, all students were asked to complete a survey to capture their perspectives and attitudes towards the ePortfolio. Findings reveal that the computing engineering students who participated in the study hold positive perceptions of ePortfolios. The main reason is that they see value in developing an ePortfolio as they believe it enables them to recognize acquired competencies. Based on students' perceptions of ePortfolios, we identify a set of key considerations for higher education institutions when planning to integrate an ePortfolio for recognition of acquired competencies throughout study programs.

This Innovative Practice Full Paper presents how formative assessment using ePortfolio can enhance computing students’ learning experiences and what influences the students’ preference regarding formative assessment method. The international research literature reveals that ePortfolios primarily are used in study areas such as teacher education, creative disciplines, communication, and medicine. This study contributes to ePortfolio research within the discipline of computing education and introduces computing students to the ePortfolio integrated into the LMS Blackboard. The students are used to courses and associated assignments organized in folders in the LMS, but they have no experience with the integrated ePortfolio. We derive insight from thematic analysis of 67 summative reflections written by the students at the end of a course in Collaboration Technology and observation of the students’ ePortfolios throughout the course. Findings in this study reveal two aspects of formative assessment with the ePortfolio that contributed to enhancing computing students’ learning experiences. First, considering the ePortfolio as a process, the students gained professional identity, self-assessment skills, and transferable metacognition skills. Second, seen as a product, the ePortfolio provided the students with a comprehensive overview of achievements across topics and assignments in the course. The students perceived the two aspects as so essential that if they could choose between the ePortfolio and the traditional learning management system (LMS) folder assessment method, they would have preferred the formative assessment with the ePortfolio even though the ePortfolio increases their workload.

In exercise gaming (exergaming), reward systems are typically based on rules/templates from joint movement patterns. These rules or templates need broad ranges in definitions of correct movement patterns to accommodate varying body shapes and sizes. This can lead to inaccurate rewards and, thus, inefficient exercise, which can be detrimental to progress. If exergames are to be used in serious settings like rehabilitation, accurate rewards for correctly performed movements are crucial. This article aims to investigate the level of accuracy machine learning/deep learning models can achieve in classification of correct repetitions naturally elicited from a weight-shifting exergame. Twelve healthy elderly (10F, age 70.4 SD 11.4) are recruited. Movements are captured using a marker-based 3-D motion-capture system. Random forest (RF), support vector machine, k-nearest neighbors, and multilayer perceptron (MLP) are the employed models, trained and tested on whole body movement patterns and on subsets of joints. MLP and RF reached the highest recall and F1-score, respectively, when using combined data from joint subsets. MLP recall range are 91% to 94%, and RF F1-score range 79% to 80%. MLP and RF also reached the highest recall and F1-score in each joint subset, respectively. Here, MLP ranged from 93% to 97% recall, while RF ranged from 73% to 80% F1-score. Recall results, show that >9 out of 10 repetitions are classified correctly, indicating that MLP/RF can be used to identify correctly performed repetitions of a weight-shifting exercise when using full-body data and when using joint subset data.

Datasets for recommender systems are few and often inadequate for the contextualized nature of news recommendation. News recommender systems are both time- and location-dependent, make use of implicit signals, and often include both collaborative and content-based components. In this paper we introduce the Adressa compact news dataset, which supports all these aspects of news recommendation. The dataset comes in two versions, the large 20M dataset of 10 weeks' traffic on Adresseavisen's news portal, and the small 2M dataset of only one week's traffic. We explain the structure of the dataset and discuss how it can be used in advanced news recommender systems.

Cloud computing represents a major change in how IT resources are delivered and consumed and will influence the telecom industry, its future services and business offerings. Generating new revenues through offering cloud-based services is less discussed in the literature, followed by a lack of commonly agreed and complete methodologies for this purpose. In this paper we propose a three-step method combining qualitative and quantitative models for the assessment of telco's new business opportunities, in particular, a combined role of cloud broker and carrier.

One of the major challenges in IT security management is determining how much to spend and where to spend. This requires understanding of the economic issues regarding IT security. Real option analysis presents a viable alternative to traditional economic tools in planning and valuing security investment in uncertain environment. This paper illustrates how decision makers can use real option thinking to articulate and compare different security solutions in terms of their business value in an environment characterized by high levels of uncertainty.

The overall issue is to improve semantic interoperability among and across agent systems. We propose to use explanation as a way to approach that aim. The explanation process is expressed in terms of an explanation ontology shared by the agents who participate to the explanation session. The explanation ontology is defined in a way general enough to support a variety of explanation mechanisms. We describe the explanation ontology and provide a working through example illustrating how the proposed generic ontology can be used to develop specific explanation mechanism. Finally, the ontology is being integrated into a running agent platform - Agora to demonstrate the practical usefulness of the approach.