Expert Systems最新文献

Sentiment analysis, crucial for discerning emotional tones in text, relies on manual annotation to train machine learning models and is considered the gold standard for creating annotated corpora. However, this process is time-consuming, labour-intensive, and prone to biases. This paper proposes an automatic annotation approach for the Twitter-based Arabic Mental Illness (AMI) dataset, which encompasses both Modern Standard Arabic and Dialectal Arabic. The approach leverages transfer learning with existing manually annotated datasets and three advanced Arabic language models to automate annotation, thereby enriching Arabic as a low-resource language with labelled sentiment data. Validation was conducted by comparing the automatically generated annotations to manual annotation on the same dataset, achieving strong inter-annotator agreement with a Cohen's Kappa statistic of k = 0.8457. Additionally, various baseline models were evaluated on the AMI dataset, identifying AraBERT as the top performer with the highest F1 score and accuracy.

Healthcare robots are cyberphysical systems designed to assist older adults and reduce the burden on healthcare professionals and family caregivers. These robots can perform various tasks, including delivering medications on time, promoting physical activity, and cultivating social connections by contacting family and friends. As the global population ages, healthcare robots are emerging as critical technology to support older adults and alleviate the burden on healthcare systems. However, their widespread adoption is hindered by significant challenges, including inflexible hard-coded functionalities, high development and training costs, and a common lack of cultural adaptability. Extended reality (XR) and digital twin (DT) technologies offer a transformative approach to overcome these hurdles by enabling safe, scalable, and cost-effective virtual training environments. This paper presents a systematic review of the literature at the intersection of XR, DT, and healthcare robotics, adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We not only present a thematic analysis of current research but also identify key fundamental challenges in existing robot training methodologies and analyse the field's evolutionary trends through visualisations. Based on our synthesis, we propose a conceptual framework and guidelines for developing future healthcare robots that are not only technologically advanced but also personalised, empathetic, and culturally sensitive. The purpose of this survey is to provide a roadmap for researchers and practitioners to take advantage of these convergent technologies, with the intention of creating a more effective and humane healthcare ecosystem for ageing populations around the world.

This article presents a novel approach for real-time posture recognition in monitoring scenarios, utilising a virtual camera simulated on a UAV within virtual environments. Leveraging the MediaPipe Pose library, key points of the body skeleton are extracted, focusing on a subset of 8 key points for computational efficiency. Through the integration of heuristic algorithms based on physical proportions of the human body, the proposed methodology provides accurate estimations of three distinct postures: lying, standing, and sitting. This heuristic-based approach offers a computationally efficient alternative to traditional machine learning and deep learning methods, ensuring real-time performance and scalability. The efficiency of the framework is demonstrated through experiments that show its potential applications in various fields, including healthcare, virtual reality, and human-computer interaction. This approach achieved an average precision of 98.08% for virtual images. Success rates were 100%, 95.8%, and 98.9% for standing, sitting, and lying postures, respectively. Furthermore, the original classification model, which was tuned for virtual images, was tested on real images without any alteration to the parameter values. Its good performance demonstrates its potential for generalisation and application in diverse environments. Overall, this work contributes to the advancement of posture recognition technology, offering a versatile and accessible solution for posture analysis in dynamic monitoring environments.

Our study delves into the crucial issue of road safety by examining the intricate dynamics of driver behaviour, often resulting in tragic accidents. The importance of comprehending these behaviours is acknowledged, leading us to propose an innovative decision-making support model that integrates the analytic hierarchy process (AHP) with the best worst method (BWM) in a fuzzy context. Our objective is to effectively evaluate the overall influence of driver behaviour on road safety while reducing ambiguity in assessments. In a practical case study involving skilled drivers in Budapest, Hungary, a thorough survey was conducted to prioritise key driving behaviour factors that impact road safety. Our findings reveal ‘errors’ as the most vital aspect, followed by specific behaviours like ‘colliding when reversing without observation’ and ‘driving under the influence of alcohol’. By simplifying the survey procedure and offering practical insights, our unified model improves decision-making for policymakers striving to tackle road safety issues efficiently. To conclude, our research showcases the effectiveness of merging AHP and BWM methodologies in a fuzzy setting to obtain valuable perspectives on road safety concerns, ultimately aiding in the advancement of sustainable transportation systems.

2025. “RETRACTION: Using Electroencephalogram Classification in a Convolutional Neural Network, Infer Privacy on Healthcare Internet of Things 5.0.” Expert Systems 42: 13813. https://doi.org/10.1111/exsy.13813.

Kishan Bhushan Sahay reached out to the editorial office after the retraction was published to inform the journal that he had not consented to the submission or publication of this article, which the publisher has confirmed. Accordingly, the retraction text is corrected to:

The above article, published online on 03 March 2022 in Wiley Online Library (wileyonlinelibrary.com), has been retracted by agreement between the journal Editor-in-Chief, David Camacho, and John Wiley & Sons Ltd. The article was submitted as part of a guest-edited special issue. Following publication, it has come to our attention that the article was not reviewed in line with the journal's peer review standards and was solely accepted on the basis of a compromised peer review process. Furthermore, relevant information about the research concept, the authentication method, and the source or nature of the patients' data are missing. As a result, the conclusions presented are considered invalid. Kishan Bhushan Sahay stated that he did not give consent to the submission and publication of this manuscript.

In this work we implement Bayesian surprise as a method to sift through sequences of discrete patterns and identify any unusual or interesting patterns that deviate from known sequences. Surprise is a biological trait inherent in humans and animals and is essential for many creative acts and efforts of discovery. Numerous technical domains are comprised of discrete elements in sequences such as e-commerce transactions, genome data searching, online financial transactions of many types, criminal cyber-attacks and life-course data from sociology. In addition to the complexity and computational burden of this type of problem is the issue of their rarity. Many anomalies are infrequent and may defy categorisation; therefore, they are not suited to classification solutions. We test our methods on four discrete datasets (Hospital Sepsis patients, Chess Moves, the Wisconsin Card Sorting Task and BioFamilies) consisting of discrete sequences. Probabilistic Suffix Trees are trained on this data which maintain each discrete symbol's location and position in a given sequence. The trained models are exposed to “new” data where any deviations from learned patterns either in location on the sequence or frequency of occurrence will denote patterns that are unusual compared with the original training data. To assist in the identification of new patterns and to avoid confusing old patterns as new or novel we use Bayesian surprise to detect the discrepancies between what we are expecting and actual results. We can assign the degree of surprise or unexpectedness to any new pattern and provide an indication of why certain patterns are deemed novel or surprising and why others are not.