Search results

Content‐based image retrieval suffers from the semantic gap problem: that images are represented by low‐level visual features, which are difficult to directly match to high‐level concepts in the user's mind during retrieval. To date, visual feature representation is still limited in its ability to represent semantic image content accurately. This paper seeks to address these issues.

In this paper the authors propose a novel meta‐feature feature representation method for scenery image retrieval. In particular some class‐specific distances (namely meta‐features) between low‐level image features are measured. For example the distance between an image and its class centre, and the distances between the image and its nearest and farthest images in the same class, etc.

Three experiments based on 190 concrete, 130 abstract, and 610 categories in the Corel dataset show that the meta‐features extracted from both global and local visual features significantly outperform the original visual features in terms of mean average precision.

Compared with traditional local and global low‐level features, the proposed meta‐features have higher discriminative power for distinguishing a large number of conceptual categories for scenery image retrieval. In addition the meta‐features can be directly applied to other image descriptors, such as bag‐of‐words and contextual features.

Despite increasing attention to employee development, past research has mostly studied performance management systems (PMSs) in relation to task-related behaviors compared to proactive behaviors. Accordingly, this study addresses the relation between PMSs and innovative work behavior (IWB).

Building on signaling theory and human resource management (HRM) system strength research, the authors designed a factorial survey experiment (n = 444) to examine whether PMSs stimulate IWB under different configurations of distinctiveness, consistency and consensus, as well as in the presence of transformational leadership.

Results show that only strong PMSs foster IWB (high distinctiveness, high consistency and high consensus [HHH]). Additional analyses reveal that the individual meta-features of PMS consistency and consensus can also stimulate innovation. Transformational leadership reinforced the relationship between PMS consensus and IWB relationship, but not the relationships of the other meta-features.

The study’s findings suggest that organizations wishing to unlock employees' innovative potential should design PMSs that are visible, comprehensible and relevant. To further reap the innovative gains of employees, organizations could also invest in the coherent and fair application of planning, feedback and evaluation throughout the organization and ensure organizational stakeholders agree on the approach to PMSs.

The study’s findings show that PMS can also inspire proactivity in employees, in the form of IWB and suggest that particular leadership behaviors can complement certain PMS meta-features, and simultaneously also compete with PMS strength, suggesting the whole (i.e. PMS strength) is more than the sum of the parts (i.e. PMS meta-features).

The purpose of this paper is to study heterogeneous transfer learning for activity recognition using heuristic search techniques. Many pervasive computing applications require information about the activities currently being performed, but activity recognition algorithms typically require substantial amounts of labeled training data for each setting. One solution to this problem is to leverage transfer learning techniques to reuse available labeled data in new situations.

This paper introduces three novel heterogeneous transfer learning techniques that reverse the typical transfer model and map the target feature space to the source feature space and apply them to activity recognition in a smart apartment. This paper evaluates the techniques on data from 18 different smart apartments located in an assisted-care facility and compares the results against several baselines.

The three transfer learning techniques are all able to outperform the baseline comparisons in several situations. Furthermore, the techniques are successfully used in an ensemble approach to achieve even higher levels of accuracy.

The techniques in this paper represent a considerable step forward in heterogeneous transfer learning by removing the need to rely on instance – instance or feature – feature co-occurrence data.

The purpose of this paper is to address the challenge of opinion mining in text documents to perform further analysis such as community detection and consistency control. More specifically, we aim to identify and extract opinions from natural language documents and to represent them in a structured manner to identify communities of opinion holders based on their common opinions. Another goal is to rapidly identify similar or contradictory opinions on a target issued by different holders.

For the opinion extraction problem we opted for a supervised approach focusing on the feature selection problem to improve our classification results. On the community detection problem, we rely on the Infomap community detection algorithm and the multi-scale community detection framework used on a graph representation based on the available opinions and social data.

The classification performance in terms of precision and recall was significantly improved by adding a set of “meta-features” based on grouping rules of certain part of speech (POS) instead of the actual words. Concerning the evaluation of the community detection feature, we have used two quality metrics: the network modularity and the normalized mutual information (NMI). We evaluated seven one-target similarity functions and ten multi-target aggregation functions and concluded that linear functions perform poorly for data sets with multiple targets, while functions that calculate the average similarity have greater resilience to noise.

Although our solution relies on existing approaches, we managed to adapt and integrate them in an efficient manner. Based on the initial experimental results obtained, we managed to integrate original enhancements to improve the performance of the obtained results.

Flexible work arrangements (FWAs) are routinely offered in organizational policy, yet employee access to FWAs is highly dependent upon support from their immediate supervisor. There is little empirical research that specifically investigates the role of the human resource function (HR) in supporting managers to implement FWA policy. Through the lens of HR systems theory, the purpose of this paper is to examine how HR supports managers to implement FWAs.

Using a case study in the Australian Insurance industry, this paper analyzes corporate documents and interviews with 47 managers, supervisors and HR staff across four diverse business units.

This study identifies supervisors’ perceived ability to implement FWAs as a potential barrier to utilization. Five mechanisms of HR support to overcome perceived barriers are identified in the data. An HR system that enables managers to support FWAs requires alignment of HR policies; the provision of supportive technology; an HR structure that facilitates proactive advice and support; HR business partners with influence; and managerial training on FWAs.

This paper provides HR practitioners with insights into the mechanisms that can support managers to implement FWAs or other devolved HR policies.

Applying HR systems theory, this case study utilizes the perspectives of senior managers, supervisors and HR staff to explain how the HR function supports or constrains managers in the effective implementation of FWAs.

This study extends extant literature by establishing an integrative framework connecting different forms of HRM attributions (internal HRM well-being attributions and exploiting attributions, and external Labor Law attributions) and a specific single meta-feature of HRM system strength (consistency) to employee well-being.

In total, 279 paired and valid responses from eight manufacturing firms located in three cities in China were analyzed in this two-wave study. PROCESS macro tool was used to examine the mediating role of thriving at work and the moderating role of HRM system consistency in the relationship between HRM attributions and thriving at work.

Thriving at work mediated the relationship between internal HRM exploiting attributions, external Labor Law attributions and employee well-being. On the other hand, internal HRM well-being attributions did not indirectly influence employee well-being through thriving at work. HRM system consistency moderates the association between internal HRM attributions (rather than external Labor Law attributions) and thriving at work.

This research is only concerned with a particular form of external attributions in one country. In fact, there is a wide range of other external HRM attributions (e.g. organizational intention to imitate their competitors in today’s global economy).

Managers should understand that managing the well-being of the workforce is an important part of HRM for responsible organizations and make efforts to improve employees’ affective-motivational states.

The authors offer insights into HRM attributions research by differentiating internal attributions from external Labor Law attributions based on their disparate implications for employee well-being.

The purpose of this study is to examine the role of HR function in supporting supervisors to implement FWA policy.

A case study was carried out in an Australian private sector insurance company where FWA policies had been in place for five years. Data was gathered from semi –structured and in-depth interviews with forty seven HR staff, managers and supervisors from four divisions within the organization covering a range of differing work roles. In addition seven corporate documents relating to flexible working were analyzed.

Five factors are identified as having an influence on the ability of managers to support FWAs through the meta-features of distinctiveness, consistency and consensus: policy alignment (strategic and operational), HR structure which provides support at senior and supervisory levels, influencing skills of HR staff, manager training and education on FWAs and supportive technology.

To improve practice organizations should consider both vertical and horizontal alignment of HR practices, give attention to operational alignment of HR practice, give training and support to supervisors and build direct access to expert advice into the HR structure.

This paper has an original approach in explaining how the HR function supports and constrain managers in implementing FWAs.

The purpose of this paper is to investigate the applicability of meta‐learning to the problem of algorithm recommendation for gene expression data classification.

Meta‐learning was used to provide a preference order of machine learning algorithms, based on their expected performances. Two approaches were considered for such: k‐nearest neighbors and support vector machine‐based ranking methods. They were applied to a set of 49 publicly available microarray datasets. The evaluation of the methods followed standard procedures suggested in the meta‐learning literature.

Empirical evidences show that both ranking methods produce more interesting suggestions for gene expression data classification than the baseline method. Although the rankings are more accurate, a significant difference in the performances of the top classifiers was not observed.

As the experiments conducted in this paper suggest, the use of meta‐learning approaches can provide an efficient data driven way to select algorithms for gene expression data classification.

This paper reports contributions to the areas of meta‐learning and gene expression data analysis. Regarding the former, it supports the claim that meta‐learning can be suitably applied to problems of a specific domain, expanding its current practice. To the latter, it introduces a cost effective approach to better deal with classification tasks.

This study aims to analyze Kickstarter data along with social media data from a data mining perspective. Kickstarter is a crowdfunding financing plataform and is a form of fundraising and is increasingly being adopted as a source for achieving the viability of projects. Despite its importance and adoption growth, the success rate of crowdfunding campaigns was 47% in 2017, and it has decreased over the years. A way of increasing the chances of success of campaigns would be to predict, by using machine learning techniques, if a campaign would be successful. By applying classification models, it is possible to estimate if whether or not a campaign will achieve success, and by applying regression models, the authors can forecast the amount of money to be funded.

The authors propose a solution in two phases, namely, launching and campaigning. As a result, models better suited for each point in time of a campaign life cycle.

The authors produced a static predictor capable of classifying the campaigns with an accuracy of 71%. The regression method for phase one achieved a 6.45 of root mean squared error. The dynamic classifier was able to achieve 85% of accuracy before 10% of campaign duration, the equivalent of 3 days, given a campaign with 30 days of length. At this same period time, it was able to achieve a forecasting performance of 2.5 of root mean squared error.

The authors carry out this research presenting the results with a set of real data from a crowdfunding platform. The results are discussed according to the existing literature. This provides a comprehensive review, detailing important research instructions for advancing this field of literature.

Most prior studies treated human resource management (HRM) strength as a whole, while neglecting the dynamic interactions between distinct components (consensus, consistency and distinctiveness). The authors lack a deep understanding of how different components operate together to influence burnout. To address these gaps, this study aims to adopt signaling theory to investigate the interactions among different components and their impacts on employee burnout.

The authors collected time-lagged data from 231 full-time employees in manufacturing firms in Suzhou, China. The authors used the PROCESS Model 6 and hierarchical multiple regression to analyze the data.

This study found that HRM system consensus and consistency mitigate employee burnout, whereas HRM distinctiveness is not significantly related to burnout. Furthermore, the authors revealed that HRM system consistency (rather than distinctiveness) mediated the relationship between consensus and burnout. Moreover, the authors found the sequential mediating effects of HRM system distinctiveness and consistency on the association between consensus and burnout.

Considering that employees’ well-being problems may be debilitating and overwhelming during the COVID-19 pandemic, it is particularly ethical and timely for managers to direct attention to the role of HRM system strength in addressing employee burnout.

This study advances the HRM system literature by teasing out the interactions between the three pivotal components of HRM strength. Our study is among the first to empirically investigate the internal relationships between the meta-features of the HRM system and employee burnout. In doing so, the authors develop a more nuanced understanding of the collective nature of a strong HRM system that conveys a shared message about HRM to promote well-being.