456 Results Found

Federated learning has been widely applied in automatic speech recognition. However, variations in speaker behaviors result in a significant data imbalance across client devices. Conventional federated speech recognition algorithms typically use fixe...

The use of personalization mechanisms should allow the insurance distributor to reduce exploration costs and adjust the offered insurance product to the needs, features, and situation of each individual client. This study seeks to examine how liabili...

The personalized federated averaging algorithm integrates a federated averaging approach with a model-agnostic meta-learning technique. In real-world heterogeneous scenarios, it is essential to implement additional privacy protection techniques for p...

The integration of AI into power emergency maintenance faces a critical dilemma: centralized training compromises privacy, while standard Federated Learning (FL) struggles with the statistical heterogeneity (Non-IID) of industrial data. Traditional a...

Federated learning trains a neural network model using the client’s data to maintain the benefits of centralized model training while maintaining their privacy. However, if the client data are not independently and identically distributed (non-...

Financial return prediction increasingly relies on both financial text and structured market covariates, but adapting large language models across financial institutions remains difficult because raw data cannot be centralized and clients often exhib...

In recent years, significant progress has been made in the application of federated learning (FL) in various aspects of cyberspace security, such as intrusion detection, privacy protection, and anomaly detection. However, the robustness of federated...

Federated node classification is not easy when clients hold induced subgraphs with different class proportions and different local topology. Existing graph-specific approaches change aggregation, distillation or cross-client knowledge transfer, which...

The assimilation of problematic experiences has been studied as change processes in psychotherapies of different client populations. Several theory-building case studies using the assimilation model have shown how important a meaning bridge is in suc...

Personalized learning pathways are difficult to support in distributed educational systems because learner records cannot always be centralized and one shared federated predictor may not represent heterogeneity across institutions, learning tasks, an...

With the rapid advancement of the Internet and big data technologies, traditional centralized machine learning methods are challenged when dealing with large-scale datasets. Federated Learning (FL), as an emerging distributed machine learning paradig...

The individual experiences of older adults in long-term care are broadly recognized as an important source of information for measuring wellbeing and quality of care. Narrative research is a special type of qualitative research to elicit people’s ind...

This study set out to answer the question ‘Which kinds of agency do refugees perform when dealing with mental health problems of themselves and their children?’. Aiming to gain more insight in why it seems harder for refugee parents and minors than f...

Federated learning is a privacy-preserving distributed machine learning paradigm. However, due to client data heterogeneity, the global model trained by a traditional federated averaging algorithm often exhibits poor generalization ability. To mitiga...

As a privacy-preserving machine learning paradigm, federated learning enables collaborative training across multiple clients without sharing data. However, when there are discrepancies in the data distributions of individual clients, the training acc...

Within a construction project, the clients are categorized as private individuals, private companies, public institutions, etc. In this research, the private client is identified as a non-professional individual building owner and is involved in maki...

Federated learning (FL) is a distributed machine learning paradigm under privacy preservation. However, data heterogeneity among clients leads to the shared global model obtained after training, which cannot fit the distribution of each client’...

The effective training of large-scale distributed deep learning models has become an active and emerging research area in recent years. Federated learning (FL) can address those challenges by training global models through parameter exchange of clien...

This study aimed to explore the experiences of adult clients with hearing loss and their audiologists in using an online tool, the Living Well Tool (LWT), during initial audiology appointments. The LWT is designed to help clients identify when and wh...

The study investigated how pediatric speech-language pathologists (SLPs) applied telepractice to compensate for the loss of in-person services and the dynamics of telepractice use during the COVID-19 pandemic in a rural state. We conducted interviews...

Federated learning (FL) enables collaborative model training across decentralized clients while preserving data privacy, yet real-world deployments still face communication bottlenecks, performance degradation under heterogeneous client data, and lim...

As a popular machine learning method, federated learning (FL) can effectively solve the issues of data silos and data privacy. However, traditional federated learning schemes cannot provide sufficient privacy protection. Furthermore, most secure fede...

WiFi-based human gesture recognition has a wide range of applications in smart homes. Existing methods train gesture classification models by collecting large amounts of WiFi signal data in a centralized manner. However, centralized training faces ch...

Federated learning is a distributed machine learning paradigm, which utilizes multiple clients’ data to train a model. Although federated learning does not require clients to disclose their original data, studies have shown that attackers can i...

Cross-domain recommendation systems frequently require the use of rich source domain information to improve recommendations in the target domain, thereby resolving the data sparsity and cold-start problems, whereas the majority of existing approaches...

In the realm of personalized federated learning, some current methods substitute shared parameters with shared samples created by Generative Adversarial Networks (GANs). This enables each client to independently design the architecture of their neura...

Background/Objectives: People with visual impairments can participate in orientation and mobility (O&M) training to learn how to navigate to their desired destinations. Instructors adapt their approach to each individual client. However, assessme...

With the flourishing development of the Internet of Things (IoT), federated learning has garnered significant attention as a distributed learning method aimed at preserving the privacy of participant data. However, certain IoT devices, such as sensor...

[U25] is a German online-peer-counseling service for adolescents with suicidal ideation, who typically do not seek or receive adequate counseling. We conducted an online survey in order to compare persons who receive online counseling by [U25] compar...

The purpose of the study is to explore the clients’ perceptions of therapeutic changes due to their existential fulfillment experience and authenticity in their relationships with the world. The content of the study reveals the subjective perce...

Safety issues arise during the performance of activities as dementia advances. Occupational therapists collaborate with dementia clients and their caregivers to find solutions and strategies to prolong safe activity participation. Additionally, occup...

This paper considers a callback single-server system with an orbit and a First-Come First-Served (FCFS) service discipline. Customers (users, clients) that encounter a busy server are sent into orbit and then have the option to retry service after an...

Federated learning in heterogeneous data scenarios faces two key challenges. First, the conflict between global models and local personalization complicates knowledge transfer and leads to feature misalignment, hindering effective personalization for...

The implementation and adaptation of the Housing First (HF) model represented profound changes the structure and delivery, goals, and principles of homeless services. These features of homeless services directly influence providers, their work perfor...

While research on psychedelic-assisted therapy (PAT) continues to show promise, challenges in its clinical application persist. One relevant domain includes how supervision might enhance both client and trainee outcomes. Current data suggest that, de...

The consequences of leprosy go beyond the physical, social and psychological, as leprosy can drive persons affected and their families into poverty, stigmatization and disability. This paper describes the impact of a socio-economic development (SED)...

Federated learning (FL) enables cellular traffic prediction without centralizing raw base-station data, but statistical heterogeneity makes a single global model unsuitable for many clients. This paper proposes federated clustering with adaptive pers...

Federated learning (FL), which enables collaborative learning across distributed nodes, confronts a significant heterogeneity challenge, primarily including resource heterogeneity induced by different hardware platforms, and statistical heterogeneity...

In healthcare settings, nurses’ workload, burnout, and job satisfaction are associated to the patient–nurse ratio. Whether this ratio also affects their intention to leave the nursing profession, along with the underlying stress pathway,...

Federated learning ensures the privacy of clients by conducting distributed training on individual client devices and sharing only the model weights with a central server. However, in real-world scenarios, especially in IoT scenarios where devices ha...

How can disparate professions better collaborate in a legal clinic environment to improve the health and wellbeing, legal and social outcomes for patients/clients? In this paper, we explore how an intentional blurring of the boundaries between the he...

To address the limitation of generalization of federated learning under non-independent and identically distributed (Non-IID) data, we propose FedDFPA, a personalized federated learning framework that integrates dynamic parameter fusion and prototype...

Satellite constellation fault diagnosis presents significant challenges, including excessive inter-satellite communication overhead, data heterogeneity, satellite platform heterogeneity, and limited model generalization. To address these issues, this...

Personalized Federated Learning (PFL) seeks to train client-specific models across distributed data silos with heterogeneous distributions. We introduce Sign-Entropy Regularization (SER), a novel entropy-based regularization technique that penalizes...

After-death communication (ADC) is the phenomenon of perceiving spontaneous and direct contact by a deceased loved one. Evidence suggests that ADC is a widespread human experience, particularly for bereaved individuals. Many people who have ADCs repo...

Mental health care is shifting towards more person-centered and community-based health care. Although integrating eHealth within a transforming healthcare setting may help accomplishing the shift, research studying this is lacking. This study aims to...

Traffic flow prediction can guide the rational layout of land use. Accurate traffic flow prediction can provide an important basis for urban expansion planning. This paper introduces a personalized lightweight federated learning framework (PLFL) for...

Data heterogeneity poses a significant challenge in federated learning (FL), which has become a central focus of contemporary research in artificial intelligence. Personalized federated learning (pFL), a specialized branch of FL, seeks to address thi...

The primary prevention of occupational burnout should be considered as a public health priority worldwide. The aim of this study was to evaluate the prevalence of burnout and its associations with the work environment among hospital physicians in the...

The study provides a categorization of the different elements of the “recovery in” model (RIM). The objective is to analyze elements of RIM in positive assessments during home visit interactions. RIM approaches mental illness as a long-te...