Search results

Mobile phone-based human activity recognition (HAR) consists of inferring user’s activity type from the analysis of the inertial mobile sensor data. This paper aims to mainly introduce a new classification approach called adaptive k-nearest neighbors (AKNN) for intelligent HAR using smartphone inertial sensors with a potential real-time implementation on smartphone platform.

The proposed method puts forward several modification on AKNN baseline by using kernel discriminant analysis for feature reduction and hybridizing weighted support vector machines and KNN to tackle imbalanced class data set.

Extensive experiments on a five large scale daily activity recognition data set have been performed to demonstrate the effectiveness of the method in terms of error rate, recall, precision, F1-score and computational/memory resources, with several comparison with state-of-the art methods and other hybridization modes. The results showed that the proposed method can achieve more than 50% improvement in error rate metric and up to 5.6% in F1-score. The training phase is also shown to be reduced by a factor of six compared to baseline, which provides solid assets for smartphone implementation.

This work builds a bridge to already growing work in machine learning related to learning with small data set. Besides, the availability of systems that are able to perform on flight activity recognition on smartphone will have a significant impact in the field of pervasive health care, supporting a variety of practical applications such as elderly care, ambient assisted living and remote monitoring.

The purpose of this study is to build and test an accurate offline model by using only a compact training data that can reduce the computational and memory complexity of the system. This provides grounds for developing new innovative hybridization modes in the context of daily activity recognition and smartphone-based implementation. This study demonstrates that the new AKNN is able to classify the data without any training step because it does not use any model for fitting and only uses memory resources to store the corresponding support vectors.

As the world continues to navigate between the “new normal” and the “next normal” of an ongoing pandemic, recovery plans of several tourism destinations are still not bringing desired results. The COVID-19 pandemic has exposed long standing structural weaknesses and gaps in tourism policies worldwide. The formulation of tourism policies based on the pandemic context is therefore a need of the hour. However, due to lock-down and physical distancing measures, data collection for the development of research-based tourism policies has not been possible. In this case, evidence-based policies stand as a workable option. Drawing from the book Tourism Destination Management in a Post-Pandemic Context, this policy document proposes a synthesis of tourism policies embraced by destinations struggling in the pandemic context. Lessons show that rebuilding tourism requires policies that address structural weaknesses, advance key priorities, foster global solidarity and take advantage of new opportunities. This piece of study comes to the conclusion that tourism policies post pandemic need to be based on seven pillars, namely mitigation, vaccination, collaboration, information, promotion, education and investigation.

Diagnosing pain in neonates is difficult but critical. Although approximately thirty manual pain instruments have been developed for neonatal pain diagnosis, most are complex, multifactorial, and geared toward research. The goals of this work are twofold: 1) to develop a new video dataset for automatic neonatal pain detection called iCOPEvid (infant Classification Of Pain Expressions videos), and 2) to present a classification system that sets a challenging comparison performance on this dataset. The iCOPEvid dataset contains 234 videos of 49 neonates experiencing a set of noxious stimuli, a period of rest, and an acute pain stimulus. From these videos 20 s segments are extracted and grouped into two classes: pain (49) and nopain (185), with the nopain video segments handpicked to produce a highly challenging dataset. An ensemble of twelve global and local descriptors with a Bag-of-Features approach is utilized to improve the performance of some new descriptors based on Gaussian of Local Descriptors (GOLD). The basic classifier used in the ensembles is the Support Vector Machine, and decisions are combined by sum rule. These results are compared with standard methods, some deep learning approaches, and 185 human assessments. Our best machine learning methods are shown to outperform the human judges.

The study aims to take a step back and take the big picture of how digital capitalism is changing people's ways of living and production. On that basis, China should enhance its digital governance rationally and develop the digital economy efficiently, thereby bringing its socialist economy to new heights.

The rise of digital capitalism in the 1990s has profoundly changed the ways of consumption, employment, production organization and investment in the realm of capitalism.

Digital Capitalism has not changed the nature of capitalism, that is, exploitation and capital accumulation, which continue only in a more profound, extensive and covert way.

For the economy of socialist China to grow in the new era, China should tap into digital economy platforms, take a people-centered approach and let the people jointly develop the digital economy, share the fruits of development and participate in the governance of the digital economy. The government should leverage its modern digital governance and a high-quality digital economy to meet people's ever-growing demand for a better life.

Many HRM practices are never thoroughly implemented, or are implemented ineffectively. To better understand what line managers need to implement HRM practices effectively, the authors have developed and validated a psychometrically sound measurement instrument dealing with line managers' attributions for effective HRM implementation. Based on the theory of causal attributions, the authors distinguish between internal and external attributions that determine how line managers implement HRM practices on the work floor.

A multidimensional approach has been used, and, after collecting data from 471 line managers, thorough scale development guidelines and validation procedures have been applied for instrument development.

The instrument's psychometric qualities have been assessed by calculating the reliability and validity of line managers' internal attributions – including its composing dimensions of desire and competences – and their external attributions – including the dimensions of support, capacity and policy and procedures. In particular, both convergent and discriminant validity as well as intra-class correlations have been established. The newly developed measures are found to be of good quality. The scales appear to discriminate well between the distinguished groups and show a good variation within groups.

The developed measurement instrument helps HRM professionals to better understand line managers' attributions to effectively implement HRM practices and to provide them with support and training for effective HRM implementation.

Previous research has already identified weaknesses in HRM implementation, but lacked addressing the causes of this. The study presents antecedents for HRM implementation effectiveness, based on the causal attribution theory, and a psychometrically validated instrument to measure these antecedents.