Search results

For privacy protection, federated learning based on data separation allows machine learning models to be trained on remote devices or in isolated data devices. However, due to the limited resources such as bandwidth and power of local devices, communication in federated learning can be much slower than in local computing. This study aims to improve communication efficiency by reducing the number of communication rounds and the size of information transmitted in each round.

This paper allows each user node to perform multiple local trainings, then upload the local model parameters to a central server. The central server updates the global model parameters by weighted averaging the parameter information. Based on this aggregation, user nodes first cluster the parameter information to be uploaded and then replace each value with the mean value of its cluster. Considering the asymmetry of the federated learning framework, adaptively select the optimal number of clusters required to compress the model information.

While maintaining the loss convergence rate similar to that of federated averaging, the test accuracy did not decrease significantly.

By compressing uplink traffic, the work can improve communication efficiency on dynamic networks with limited resources.

This study proposes a collaborative federated learning (CFL) framework to address personal data transmission and retention issues for artificial intelligence (AI)-enabled video surveillance in public spaces.

This study examines specific challenges for long-term people monitoring in public spaces and defines AI-enabled video surveillance requirements. Based on the requirements, this study proposes a CFL framework to gradually adapt AI models’ knowledge while reducing personal data transmission and retention. The framework uses three different federated learning strategies to rapidly learn from different new data sources while minimizing personal data transmission and retention to a central machine.

The findings confirm that the proposed CFL framework can help minimize the use of personal data without compromising the AI model's performance. The gradual learning strategies help develop AI-enabled video surveillance that continuously adapts for long-term deployment in public spaces.

This study makes two specific contributions to advance the development of AI-enabled video surveillance in public spaces. First, it examines specific challenges for long-term people monitoring in public spaces and defines AI-enabled video surveillance requirements. Second, it proposes a CFL framework to minimize data transmission and retention for AI-enabled video surveillance. The study provides comprehensive experimental results to evaluate the effectiveness of the proposed framework in the context of facial expression recognition (FER) which involves large-scale datasets.

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 is to identify global trends in disruptive technological change and map the social and policy implications, particularly as they relate to the educational ecosystem and main stakeholders across all levels of education.

The authors conducted a two-stage meta-analysis of 1,155 scholarly, peer-reviewed articles. The investigation involves a systematized literature review for data identification and collation adhering to defined selection criteria, and a network analysis to scrutinize data, consolidate information and unveil correlations and patterns from the literature review to produce a set of recommendations.

The study unveiled educational trends related to disruptive technologies and delineated four principal clusters representing how these technologies are transforming the education ecosystem. Additionally, a series of transversal aspects that reveal a societal vulnerability toward future prospects in the realms of ethics, sustainability, resilience, security, and policy were identified.

The findings spotlight an enlarging chasm between industry (and society at large) and conventional education, where many transformations triggered by disruptive technologies remain absent from teaching and learning systems. The study further offers recommendations and envisions potential scenarios, urging stakeholders to respond based on their positions concerning disruptive technologies.

Expanding from the meta-analysis of pertinent literature, this paper offers four collections of curated resources, four mini case studies and four scenarios for policymakers and local communities to consider, enabling them to plot courses for their optimal futures.

This study examines the case of an initial training, called “Dojo”, invented and implemented at a production site in the Czech Republic. It clarifies the initial training program implementation process and offers a conceptual framework for cooperative management of subsidiary activities at the site and firm.

This study conducts an in-depth analysis of qualitative data from the Czech production site over a five-year period. The theoretical base is the theorization and labeling phase of management innovation (MI), the final phase of which legitimizes a new management practice. Interview data, archival data, pictures and financial data are used for the analysis.

To legitimize the Dojo in the operational flow controlled by the site and firm, the Czech production site acquires validation of the Dojo from employees and board members of the Japanese and European headquarters, helping the site build trustful relationships with them. Training programs, process standardization and skills standardization of the workers offer benefits to the trainees, production site and firm.

The authors offer theoretical insights into MI at the subsidiary-level, which past studies have not differentiated at the firm-level. The authors also provide details of the implementation and management of initial training for newly hired blue-collar workers at the production site. The findings complement related literature on human resource management and operational management.

The purpose of this paper is to explore the scope for action of local human resource managers, who are employed in foreign subsidiaries of multinational companies (MNCs), for implementing training activities. These managers are situated in relationships to headquarters and the local environment. Related to this is the question whether MNCs contribute to the local skill base by implementing training activities or whether they exploit the existing skill formation system.

This study focusses on German subsidiaries of MNCs with headquarters in the USA and the UK, France, China and Japan. The study is based on 107 expert interviews with subsidiary managers and representatives of local stakeholder organisations, such as educational organisations, chambers, economic promotion agencies and governmental bodies in Germany.

The study reveals that headquarters introduce general schemes for training. In addition to these MNC-internal trainings, local managers use their information advantage over headquarters to implement dual training activities.

The training activities of subsidiaries are dependent on the institutional settings of the host country.

Albeit dual training activities are laborious and tie the local managers down for the medium and long term, the future need of the subsidiary for adequately skilled workforce prompts local managers’ engagement in implementing dual training activities.

Subsidiaries contribute to the local skill base and do not act in a free-rider position, at least in the German variety of capitalism.

The study deepens insights on distanced relations within and how subsidiaries generate scope for action by using this kind of relationships.

An abundance of techniques has been presented so forth for waste classification but, they deliver inefficient results with low accuracy. Their achievement on various repositories is different and also, there is insufficiency of high-scale databases for training. The purpose of the study is to provide high security.

In this research, optimization-assisted federated learning (FL) is introduced for thermoplastic waste segregation and classification. The deep learning (DL) network trained by Archimedes Henry gas solubility optimization (AHGSO) is used for the classification of plastic and resin types. The deep quantum neural networks (DQNN) is used for first-level classification and the deep max-out network (DMN) is employed for second-level classification. This developed AHGSO is obtained by blending the features of Archimedes optimization algorithm (AOA) and Henry gas solubility optimization (HGSO). The entities included in this approach are nodes and servers. Local training is carried out depending on local data and updations to the server are performed. Then, the model is aggregated at the server. Thereafter, each node downloads the global model and the update training is executed depending on the downloaded global and the local model till it achieves the satisfied condition. Finally, local update and aggregation at the server is altered based on the average method. The Data tag suite (DATS_2022) dataset is used for multilevel thermoplastic waste segregation and classification.

By using the DQNN in first-level classification the designed optimization-assisted FL has gained an accuracy of 0.930, mean average precision (MAP) of 0.933, false positive rate (FPR) of 0.213, loss function of 0.211, mean square error (MSE) of 0.328 and root mean square error (RMSE) of 0.572. In the second level classification, by using DMN the accuracy, MAP, FPR, loss function, MSE and RMSE are 0.932, 0.935, 0.093, 0.068, 0.303 and 0.551.

The multilevel thermoplastic waste segregation and classification using the proposed model is accurate and improves the effectiveness of the classification.

The purpose of this study is to identify the professional skills and competencies of accountants that support a successful implementation of International Financial Reporting Standards (IFRS). The authors further investigate the extent to which professional accountants have developed these skills through professional training.

In the survey, Indonesian accountants were provided with a list of 47 skill items under nine categories of professional skills and were asked to rate the importance of each skill item and to indicate the level of priority given to the development of the skill items in the professional training they have undertaken. Their responses provide insights into the skills needed for applying IFRS and the adequacy of professional training in providing these skills.

The authors find that accounting judgement is considered to be the most necessary skill for applying IFRS. Likewise, the findings show that ethical skills and certain generic skills are also perceived to be necessary for adequate application of IFRS, while skills relating to cultural sensitivity are viewed as least important. The findings further demonstrate that professional training programmes need to emphasise the development of judgement and other relevant skills that are important skill categories for applying IFRS.

This study extends the literature on IFRS implementation through a specific focus on the professional skills required by accountants.

These findings have important policy implications for the standard-setters, regulators, auditors and to professional training providers across the world, such as professional accounting associations, accounting firms and educational institutions, for evaluating the content of the training and education programmes being delivered to accountants to prepare them with the relevant skills for applying IFRS.

This study is one of the first to examine the importance of various types of skills necessary for accountants in applying IFRS and the extent to which these skills have been developed through the professional accounting training provided.

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD and FL-lSVM. These algorithms are designed to address the challenge of large-scale ImageNet classification.

The authors’ FL-lSGD and FL-lSVM trains in a parallel and incremental manner to build an ensemble local classifier on Raspberry Pis without requiring data exchange. The algorithms load small data blocks of the local training subset stored on the Raspberry Pi sequentially to train the local classifiers. The data block is split into k partitions using the k-means algorithm, and models are trained in parallel on each data partition to enable local data classification.

Empirical test results on the ImageNet data set show that the authors’ FL-lSGD and FL-lSVM algorithms with 4 Raspberry Pis (Quad core Cortex-A72, ARM v8, 64-bit SoC @ 1.5GHz, 4GB RAM) are faster than the state-of-the-art LIBLINEAR algorithm run on a PC (Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32GB RAM).

Efficiently addressing the challenge of large-scale ImageNet classification, the authors’ novel federated learning algorithms of local classifiers have been tailored to work on the Raspberry Pi. These algorithms can handle 1,281,167 images and 1,000 classes effectively.