Search results

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

Web users rely heavily on online content make decisions without assessing the veracity of the content. The online content comprising text, image, video or audio may be tampered with to influence public opinion. Since the consumers of online information (misinformation) tend to trust the content when the image(s) supplement the text, image manipulation software is increasingly being used to forge the images. To address the crucial problem of image manipulation, this study focusses on developing a deep-learning-based image forgery detection framework.

The proposed deep-learning-based framework aims to detect images forged using copy-move and splicing techniques. The image transformation technique aids the identification of relevant features for the network to train effectively. After that, the pre-trained customized convolutional neural network is used to train on the public benchmark datasets, and the performance is evaluated on the test dataset using various parameters.

The comparative analysis of image transformation techniques and experiments conducted on benchmark datasets from a variety of socio-cultural domains establishes the effectiveness and viability of the proposed framework. These findings affirm the potential applicability of proposed framework in real-time image forgery detection.

This study bears implications for several important aspects of research on image forgery detection. First this research adds to recent discussion on feature extraction and learning for image forgery detection. While prior research on image forgery detection, hand-crafted the features, the proposed solution contributes to stream of literature that automatically learns the features and classify the images. Second, this research contributes to ongoing effort in curtailing the spread of misinformation using images. The extant literature on spread of misinformation has prominently focussed on textual data shared over social media platforms. The study addresses the call for greater emphasis on the development of robust image transformation techniques.

This study carries important practical implications for various domains such as forensic sciences, media and journalism where image data is increasingly being used to make inferences. The integration of image forgery detection tools can be helpful in determining the credibility of the article or post before it is shared over the Internet. The content shared over the Internet by the users has become an important component of news reporting. The framework proposed in this paper can be further extended and trained on more annotated real-world data so as to function as a tool for fact-checkers.

In the current scenario wherein most of the image forgery detection studies attempt to assess whether the image is real or forged in an offline mode, it is crucial to identify any trending or potential forged image as early as possible. By learning from historical data, the proposed framework can aid in early prediction of forged images to detect the newly emerging forged images even before they occur. In summary, the proposed framework has a potential to mitigate physical spreading and psychological impact of forged images on social media.

This study focusses on copy-move and splicing techniques while integrating transfer learning concepts to classify forged images with high accuracy. The synergistic use of hitherto little explored image transformation techniques and customized convolutional neural network helps design a robust image forgery detection framework. Experiments and findings establish that the proposed framework accurately classifies forged images, thus mitigating the negative socio-cultural spread of misinformation.

This study aims to offer a comprehensive exploration of the potential and challenges associated with sensor fusion-based virtual reality (VR) applications in the context of enhanced physical training. The main objective is to identify key advancements in sensor fusion technology, evaluate its application in VR systems and understand its impact on physical training.

The research initiates by providing context to the physical training environment in today’s technology-driven world, followed by an in-depth overview of VR. This overview includes a concise discussion on the advancements in sensor fusion technology and its application in VR systems for physical training. A systematic review of literature then follows, examining VR’s application in various facets of physical training: from exercise, skill development and technique enhancement to injury prevention, rehabilitation and psychological preparation.

Sensor fusion-based VR presents tangible advantages in the sphere of physical training, offering immersive experiences that could redefine traditional training methodologies. While the advantages are evident in domains such as exercise optimization, skill acquisition and mental preparation, challenges persist. The current research suggests there is a need for further studies to address these limitations to fully harness VR’s potential in physical training.

The integration of sensor fusion technology with VR in the domain of physical training remains a rapidly evolving field. Highlighting the advancements and challenges, this review makes a significant contribution by addressing gaps in knowledge and offering directions for future research.

This paper aims to apply several data mining techniques for predicting the daily precision improvement of Jakarta Islamic Index (JKII) prices based on big data of symmetric volatility in Indonesia’s Islamic stock market.

This research uses big data mining techniques to predict daily precision improvement of JKII prices by applying the AdaBoost, K-nearest neighbor, random forest and artificial neural networks. This research uses big data with symmetric volatility as inputs in the predicting model, whereas the closing prices of JKII were used as the target outputs of daily precision improvement. For choosing the optimal prediction performance according to the criteria of the lowest prediction errors, this research uses four metrics of mean absolute error, mean squared error, root mean squared error and R-squared.

The experimental results determine that the optimal technique for predicting the daily precision improvement of the JKII prices in Indonesia’s Islamic stock market is the AdaBoost technique, which generates the optimal predicting performance with the lowest prediction errors, and provides the optimum knowledge from the big data of symmetric volatility in Indonesia’s Islamic stock market. In addition, the random forest technique is also considered another robust technique in predicting the daily precision improvement of the JKII prices as it delivers closer values to the optimal performance of the AdaBoost technique.

This research is filling the literature gap of the absence of using big data mining techniques in the prediction process of Islamic stock markets by delivering new operational techniques for predicting the daily stock precision improvement. Also, it helps investors to manage the optimal portfolios and to decrease the risk of trading in global Islamic stock markets based on using big data mining of symmetric volatility.

This research is a pioneer in using big data mining of symmetric volatility in the prediction of an Islamic stock market index.

This study aims to identify effective behaviors in labor-management negotiation (LMN) and, on that basis, derive overarching psychological principles of successful negotiation in this important context. These empirical findings are used to develop and test a comprehensive negotiation training program.

Twenty-seven practitioners from one of the world’s largest labor unions were interviewed to identify the requirements of effective LMN, resulting in 796 descriptions of single behaviors from 41 negotiation cases.

The analyses revealed 13 categories of behaviors critical to negotiation success. The findings highlight the pivotal role of the union negotiator by illustrating how they lead the negotiations with the other party while also ensuring that their own team and the workforce stand united. To provide guidance for effective LMN, six psychological principles were derived from these behavioral categories. The paper describes a six-day training program developed for LMN based on the empirical findings of this study and the related six principles.

This paper has three unique features: first, it examines the requirements for effective LMN based on a systematic needs assessment. Second, by teaching not only knowledge and skills but also general psychological principles of successful negotiation, the training intervention is aimed at promoting long-term behavioral change. Third, the research presents a comprehensive and empirically-based training program for LMN.

The purpose of this study was to identify the relationship between training and financial performance in cooperative organizations.

To achieve this goal, the fixed-effect panel regression technique was used, from a single database containing hours and amounts invested in training by 35 large Brazilian agribusiness cooperatives over 10 years as the main independent variable of the econometric model. Financial performance was operationalized by the Net Margin and ROE.

It was possible to identify a positive relationship between expenditure on training and the future rate of return and profitability of the organizations in question. The results also indicate that this relationship grows stronger over the first three years after the investments are made and ceases to exist after this period. The findings are robust with regard to a series of alternative explanations and contribute to understanding the relationship between training and organizational performance in financial terms, considering the extent and duration of training.

The originality this study is justified by the pioneering spirit of presenting direct evidence linking investment in training and financial performance and the duration of this relationship. Thus, the study makes a significant contribution to the construction of knowledge on the subject.

This study identifies the policing pre-deployment training content for Korean experts based on needs assessments. Korean policing is at an excellent level to transfer knowledge and skills. Pre-deployment training should be designed systematically and training of trainers approaches should be implemented.

This study used T-tests, Borich needs assessments, and Locus for Focus model analyses to determine the priorities of needs for pre-deployment training in policing. A survey of 116 experienced experts was conducted, with 87 responding (75%).

The study identified 26 factors that deployed law enforcement professionals want to learn from pre-deployment training. These factors were categorized into three areas: research, training design and methods and understanding of partner countries and international development cooperation. The nine highest priorities for training needs were related to understanding the status and conditions of police training in the country to which policing experts are deployed.

This study was limited to Korean policing experts. And the study did not evaluate the validity of the training curriculum or indicators.

Technical assistance in international policing development cooperation aims to train future trainers who can train local police. This study found that limited learner information and poor communication skills can lead to ineffective technical assistance.

This study highlights the importance of knowledge transfer and effective pre-deployment training for policing. The findings can be used to improve training programs and police human resource development.

The purpose of this study is to determine what technological strategies were used within each of the phases of the ADDIE framework when developing content for professional training. The study also examined the affordances of those technologies in training.

A PRISMA systematic review methodology (Moher et al., 2015) was utilized to answer the four questions guiding this study. Specifically, the PRISMA extension Preferred Reporting Items for Systematic Reviews and Meta-Analysis for Protocols (PRISMA-P, Moher et al., 2015) was used to direct each stage of the research, from the literature review to the conclusion. In addition, the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA principles; Liberati et al., 2009) are used to guide the article selection process.

The findings reveal that the majority of the studies were in healthcare (36%) and education (24%) and used an online format (65%). There was a wide distribution of ADDIE used with technology across the globe. The coding for the benefits of technology use in the development of the training solution revealed four trends: 1) usability, 2) learning approaches, 3) learner experience and 4) financial.

This systematic review only examined articles published in English, which may bias the findings to a Western understanding of how technology is used within the ADDIE framework. Furthermore, the study examined only peer-review academic articles from scholarly journals and conferences. While this provided a high level of assurance about the quality of the studies, it does not include other reports directly from training providers and other organizations.

These findings can be used as a springboard for training providers, scholars, funders and practitioners, providing rigorous insight into how technology has been used within the ADDIE framework, the types of technology, and the benefits of using technology. This insight can be used when designing future training solutions with a better understanding of how technology can support learning.

This study provides insight into the uses of technology in training. Many of these findings and uses of technology within ADDIE can also transfer to other aspects of society.

This study is unique in that it provides the scholarly community with the first systematic review to examine what technological strategies were used within each of the phases of the ADDIE structure and how these technologies provided benefits to developing a training solution.

Grounding on the goal-setting theory and flow theory, this study explored the mechanism underlying the association between transfer design (TD); identical elements and training transfer (TT). Specifically, the authors explored a moderated mediation process of trainer performance and motivation to improve work through learning (MTIWL) that has received less consideration in the TT literature.

Data were collected using the retro-perspective survey method. The first survey was administered offline (t1: the day when leadership intervention was completed. Subsequently, trainees were requested to participate in an online survey (t2: 12–14 weeks later). In all, 355 executives participated.

The results of structural equation modeling (SEM) analyses suggested that trainees’ MTIWL mediational impact between leadership intervention triggers (transfer design and identical elements), and TT was supported. In addition, the indirect impact of these variables on TT was found to be significant when the trainer had high performance than when it was low. This confirmed the trainer’s performance as a potential moderator in the TT process.

This study is limited to the exploration of leadership intervention variables on TT. The findings have implications for leadership professionals and scholars who use leadership intervention and motivation metrics to predict TT.

This study offers a moderated mediation mechanism for enhancing TT through leadership intervention triggers. The proposed conceptual model included MTIWL as mediator and trainer performance during leadership intervention as moderator.

Sources highlight that lack of systematic labour training components results in low performance and productivity of labour, which leads the construction industry of many countries to face various challenges. This study aims to quantify the variations in the performance and productivity levels of labour in building construction projects through the applications of effective work-based training components.

A comprehensive literature review and a series of experts’ discussions with action-oriented communication approaches were conducted to develop a set of practices related to labour training, performance assessment and productivity measurements within a framework. The developed practices were applied to around 100 labourers working on nine building construction projects through a construction supervisory training programme.

The study presents the detailed patterns of the significant changes in labour performance and productivity levels. The majority of trained labourers have grown to perform the work process with some relevant theoretical and operational knowledge and skills. The overall results spotlight the significant behavioural changes that can be observed in workforce operations by improving labour performance, which resulted in implementing effective labour-rewarding practices within a framework.

Although the study findings were limited to the Sri Lankan context, the proposed practices can be applied to the industry practices of the construction sector of other developing countries and the other developing industries in similar ways/scenarios.

The study outcomes contribute to uplifting the work qualities of labourers with life-long learning opportunities and unlocking the potential barriers for expanding the local labour supply while controlling the excessive inclination of the local firms towards foreign labour. This paper describes further implications and future scopes of the study elaborately.

The study provides generalised mechanisms and practices that transform the labour characteristics and add new attributes for strengthening the values of construction supervision practices to obtain well-improved work outputs. The study outcomes reinforce the chain relationships among the training elements, labour performance and productivity levels, leading to upgrading current planning and operational management practices, especially adding constructive mechanisms in resource levelling and productivity benchmarking practices.