The combination of multiple classifiers, commonly referred to as a classifier ensemble, has previously demonstrated the ability to improve classification accuracy in many application domains. As a result this area has attracted significant amount of research in recent years. The aim of this paper has therefore been to provide a state of the art review of the most well-known ensemble techniques with the main focus on bagging, boosting and stacking and to trace the recent attempts, which have been made to improve their performance. Within this paper, we present and compare an updated view on the different modifications of these techniques, which have specifically aimed to address some of the drawbacks of these methods namely the low diversity problem in bagging or the over-fitting problem in boosting. In addition, we provide a review of different ensemble selection methods based on both static and dynamic approaches. We present some new directions which have been adopted in the area of classifier ensembles from a range of recently published studies. In order to provide a deeper insight into the ensembles themselves a range of existing theoretical studies have been reviewed in the paper.

Purpose: How to provide the most useful papers for searchers is a key issue for academic search engines. A lot of research has been carried out to address this problem. However, when evaluating the effectiveness of an academic search engine, most of the previous investigations assume that the only concern of the user is the relevancy of the paper to the query. The authors believe that the usefulness of a paper is determined not only by its relevance to the query but also by other aspects including its publication age and impact in the research community. This is vital, especially when a large number of papers are relevant to the query.Design/methodology/approach: This paper proposes a group of metrics to measure the usefulness of a ranked list of papers. When defining these metrics, three factors, including relevance, publication age and impact, are considered at the same time. To accommodate this, the authors propose a framework to rank papers by a combination of their relevance, publication age and impact scores.Findings: The framework is evaluated with the ACL (Association for Computational Linguistics Anthology Network) dataset. It demonstrates that the proposed ranking algorithm is effective for improving usefulness when two or three aspects of academic papers are considered at the same time, while the relevance of the retrieved papers is slightly down compared with the relevance-only retrieval.Originality/value: To the best of the authors’ knowledge, the proposed multi-objective academic search framework is the first of its kind that is proposed and evaluated with a group of new evaluation metrics.

Application of sensor-based technology within activity monitoring systems is becoming a popular technique within the smart environment paradigm. Nevertheless, the use of such an approach generates complex constructs of data, which subsequently requires the use of intricate activity recognition techniques to automatically infer the underlying activity. This paper explores a cluster-based ensemble method as a new solution for the purposes of activity recognition within smart environments. With this approach activities are modelled as collections of clusters built on different subsets of features. A classification process is performed by assigning a new instance to its closest cluster from each collection. Two different sensor data representations have been investigated, namely numeric and binary. Following the evaluation of the proposed methodology it has been demonstrated that the cluster-based ensemble method can be successfully applied as a viable option for activity recognition. Results following exposure to data collected from a range of activities indicated that the ensemble method had the ability to perform with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers considered as benchmarks.

The updated definition of hypertension by the American College of Cardiology (ACC) and the American Heart Association (AHA) is an important paradigm shift and has lead to extensive discussion. We aimed to examine the association between the updated blood pressure (BP) categories and the risk of cardiovascular diseases (CVDs) with potential modifications from other cardiovascular health metrics (CVHMs). This prospective study included 91,204 participants ≥40 years recruited from 20 community sites across mainland China. Participants were followed up during 2010-2016 for CVD events including nonfatal myocardial infarction, stroke, heart failure, and cardiovascular death. BP categories were defined according to the 2017 ACC/AHA guideline and CVHMs included smoking, physical activity, diet, body-mass index, total cholesterol, and fasting glucose. Overall, 1,985 major CVD events occurred during a mean follow-up of 3.7 years. Having more ideal CVHMs significantly reduced the risk of CVD events in both stage 1 and stage 2 hypertension. Compared with participants without hypertension, participants having ≥4 ideal CVHMs were no longer associated with an increased CVD risk in stage 1 hypertension (HR=1·04; 95% CI=0·83-1·31), but less so in stage 2 hypertension (HR=1·90, 95% CI=1·70-2·13). Such pattern of association was more evident in participants aged <60 years (P for interaction <0·05). Stage 1 hypertension defined by the ACC/AHA identifies individuals at increased CVD risk, which can be attenuated by achieving more preferable cardiovascular health, especially in adults aged <60 years.

Published scholarly articles have increased exponentially in recent years. This growth has brought challenges for academic researchers in locating the most relevant papers in their fields of interest. The reasons for this vary. There is the fundamental problem of synonymy and polysemy, the query terms might be too short, thus making it difficult to distinguish between papers. Also, a new researcher has limited knowledge and often is not sure about what she is looking for until the results are displayed. These issues obstruct scholarly retrieval systems in locating highly relevant publications for a given search query. Researchers seek to tackle these issues. However, the user's intent cannot be addressed entirely by introducing a direct information retrieval technique. In this paper, a novel approach is proposed, which combines query expansion and citation analysis for supporting the scholarly search. It is a two-stage academic search process. Upon receiving the initial search query, in the first stage, the retrieval system provides a ranked list of results. In the second stage, the highest-scoring Term Frequency–Inverse Document Frequency (TF-IDF) terms are obtained from a few top-ranked papers for query expansion behind the scene. In both stages, citation analysis is used in further refining the quality of the academic search. The originality of the approach lies in the combined exploitation of both query expansion by pseudo relevance feedback and citation networks analysis that may bring the most relevant papers to the top of the search results list. The approach is evaluated on the ACL dataset. The experimental results reveal that the technique is effective and robust for locating relevant papers regarding normalized Discounted Cumulative Gain (nDCG), precision, and recall.