In our study, we examine the impact of citation network structures on the ability to discern valuable research topics in Computer Science literature. We use the bibliographic information available in the DBLP database to extract candidate phrases from scientific paper abstracts. Following that, we construct citation networks based on direct citation, co-citation and bibliographic coupling relationships between the papers. The candidate research topics, in the form of keyphrases and n-grammes, are subsequently ranked and filtered by a graph-text ranking algorithm. This selection of the highest ranked potential topics is further evaluated by domain experts and through the Wikipedia knowledge base. The results obtained from these citation networks are complementary, returning valid but non-overlapping output phrases between some pairs of networks. In particular, bibliographic coupling appears to capture more unique information than either direct citation or co-citation. These findings point towards the possible added value in combining bibliographic coupling analysis with other structures. At the same time, combining direct citation and co-citation is put into question. We expect our findings to be utilised in method design for research topic identification.

Purpose: This study compared the effects of inpatient-based rehabilitation program of patients with chronic obstructive pulmonary disease (COPD) using non-immersive virtual reality (VR) training with a traditional pulmonary rehabilitation program. The aims of this study were to determine 1) whether rehabilitation featuring both VR as well as exercise training provides benefits over exercise training (ET) alone and 2) whether rehabilitation featuring VR training instead of exercise training provides equivalent benefits. Patients and Methods: The study recruited 106 patients with COPD to a 2-week high-intensity, five times a week intervention. Randomized into three groups, 34 patients participated in a traditional pulmonary rehabilitation program including endurance exercise training (ET), 38 patients participated in traditional pulmonary rehabilitation, including both endurance exercise training and virtual reality training (ET+VR) and 34 patients participated in pulmonary rehabilitation program including virtual reality training but no endurance exercise training (VR). The traditional pulmonary rehabilitation program consisted of fitness exercises, resistance respiratory muscle and relaxation training. Xbox 360^® and Kinect^® Adventures software were used for the VR training of lower and upper body strength, endurance, trunk control and dynamic balance. Comparison of the changes in the Senior Fitness Test was the primary outcome. Analysis was performed using linear mixed-effects models. Results: The comparison between ET and ET+VR groups showed that ET+VR group was superior to ET group in Arm Curl (p< 0.003), Chair stand (p< 0.008), Back scratch (p< 0.002), Chair sit and reach (p< 0.001), Up and go (p< 0.000), 6-min walk test (p< 0.011). Whereas, the comparison between ET and VR groups showed that VR group was superior to ET group in Arm Curl (p< 0.000), Chair stand (p< 0.001), 6-min walk test (p< 0.031). Conclusion: Results suggest that pulmonary rehabilitation program supplemented with VR training is beneficial intervention to improve physical fitness in patients with COPD.

We propose using five data-driven community detection approaches from social networks to partition the label space in the task of multi-label classification as an alternative to random partitioning into equal subsets as performed by RAkELd. We evaluate modularity-maximizing using fast greedy and leading eigenvector approximations, infomap, walktrap and label propagation algorithms. For this purpose, we propose to construct a label co-occurrence graph (both weighted and unweighted versions) based on training data and perform community detection to partition the label set. Then, each partition constitutes a label space for separate multi-label classification sub-problems. As a result, we obtain an ensemble of multi-label classifiers that jointly covers the whole label space. Based on the binary relevance and label powerset classification methods, we compare community detection methods to label space divisions against random baselines on 12 benchmark datasets over five evaluation measures. We discover that data-driven approaches are more efficient and more likely to outperform RAkELd than binary relevance or label powerset is, in every evaluated measure. For all measures, apart from Hamming loss, data-driven approaches are significantly better than RAkELd ( $\alpha =0.05$ ), and at least one data-driven approach is more likely to outperform RAkELd than a priori methods in the case of RAkELd’s best performance. This is the largest RAkELd evaluation published to date with 250 samplings per value for 10 values of RAkELd parameter k on 12 datasets published to date.