Frontiers in Artificial Intelligence最新文献

Automatic food identification utilizing artificial intelligence (AI) technology in smart refrigerators presents an innovative solution. However, existing studies exhibit significant limitations. Achieving consistent high performance in recognition across varying camera distances and diverse real-world conditions remain a formidable challenge. Current approaches often struggle to accurately recognize items in scenarios involving occlusions, variable distortions, and complex backgrounds, thereby limiting their practical applicability in household environments. This study addresses these deficiencies by enhancing the Feature Pyramid Network (FPN) of YOLACT with an additional layer designed to capture nuanced information. Furthermore, we propose a two-stage data augmentation method that simulates diverse conditions including distortion and occlusion, to generate images that reflect various backgrounds and handheld scenarios. Comparative analyses with previous research and evaluations on our original dataset demonstrate that our approach significantly improves recognition rates for both typical and challenging real-world images. These enhancements contribute to more effective food waste management in households and indicate broader applications for automatic identification systems.

Introduction: The electronic health record (EHR) has greatly expanded healthcare communication between patients and health workers. However, the volume and complexity of EHR messages have increased health workers' cognitive load, impeding effective care delivery and contributing to burnout.

Methods: To understand these potential detriments resulting from EHR communication, we analyzed EHR messages sent between patients and health workers at Emory Healthcare, a large academic healthcare system in Atlanta, Georgia. We quantified the burden of messages interacted with by each health worker type and visualized the communication patterns using graph theory. Our analysis included 76,694 conversations comprising 144,369 messages sent between 47,460 patients and 3,749 health workers across 85 healthcare specialties.

Results: On average, nurses/certified nursing assistants/medical assistants (nurses/CNA/MA) interacted with the most messages (350), followed by non-physician practitioners (NPP) (241), physicians (166), and support staff (155), with the average conversation involving 10.51 interactions before resolution. Network analysis of the communication flow revealed that each health worker was connected to approximately two other health workers (average degree = 2.10). In message sending, support staff led in closeness centrality (0.44), followed by nurses/CNA/MA (0.41), highlighting their key role in fast information spread. For message reception, nurses/CNA/MA (0.51) and support staff (0.41) also had the highest values, underscoring their vital role in the communication network on the receiving end as well.

Discussion: Our analysis demonstrates the feasibility of applying graph theory to understand communication dynamics between patients and health workers and highlights the burden of EHR-based messaging.

Introduction: Individuals with diverse motor abilities often benefit from intensive and specialized rehabilitation therapies aimed at enhancing their functional recovery. Nevertheless, the challenge lies in the restricted availability of neurorehabilitation professionals, hindering the effective delivery of the necessary level of care. Robotic devices hold great potential in reducing the dependence on medical personnel during therapy but, at the same time, they generally lack the crucial human interaction and motivation that traditional in-person sessions provide.

Methods: To bridge this gap, we introduce an AI-based system aimed at delivering personalized, out-of-hospital assistance during neurorehabilitation training. This system includes a rehabilitation training device, affective signal classification models, training exercises, and a socially interactive agent as the user interface. With the assistance of a professional, the envisioned system is designed to be tailored to accommodate the unique rehabilitation requirements of an individual patient. Conceptually, after a preliminary setup and instruction phase, the patient is equipped to continue their rehabilitation regimen autonomously in the comfort of their home, facilitated by a socially interactive agent functioning as a virtual coaching assistant. Our approach involves the integration of an interactive socially-aware virtual agent into a neurorehabilitation robotic framework, with the primary objective of recreating the social aspects inherent to in-person rehabilitation sessions. We also conducted a feasibility study to test the framework with healthy patients.

Results and discussion: The results of our preliminary investigation indicate that participants demonstrated a propensity to adapt to the system. Notably, the presence of the interactive agent during the proposed exercises did not act as a source of distraction; instead, it positively impacted users' engagement.

The integration of artificial intelligence in education has shown great potential to improve student's learning experience through emotion detection and the personalization of learning. Many educational settings lack adequate mechanisms to dynamically adapt to students' emotions, which can negatively impact their academic performance and engagement. This study addresses this problem by implementing a deep reinforcement learning model to detect emotions in real-time and personalize teaching strategies in a hybrid educational environment. Using data from 500 students, captured through cameras, microphones, and biometric sensors and pre-processed with advanced techniques such as histogram equalization and noise reduction, the deep reinforcement learning model was trained and validated to improve the detection accuracy of emotions and the personalization of learning. The results showed a significant improvement in the accuracy of emotion detection, going from 72.4% before the implementation of the system to 89.3% after. Real-time adaptability also increased from 68.5 to 87.6%, while learning personalization rose from 70.2 to 90.1%. K-fold cross-validation with k = 10 confirmed the robustness and generalization of the model, with consistently high scores in all evaluated metrics. This study demonstrates that integrating reinforcement learning models for emotion detection and learning personalization can transform education, providing a more adaptive and student-centered learning experience. These findings identify the potential of these technologies to improve academic performance and student engagement, offering a solid foundation for future research and implementation.

Introduction: Requirements classification is an essential task for development of a successful software by incorporating all relevant aspects of users' needs. Additionally, it aids in the identification of project failure risks and facilitates to achieve project milestones in more comprehensive way. Several machine learning predictors are developed for binary or multi-class requirements classification. However, a few predictors are designed for multi-label classification and they are not practically useful due to less predictive performance.

Method: MLR-Predictor makes use of innovative OkapiBM25 model to transforms requirements text into statistical vectors by computing words informative patterns. Moreover, predictor transforms multi-label requirements classification data into multi-class classification problem and utilize logistic regression classifier for categorization of requirements. The performance of the proposed predictor is evaluated and compared with 123 machine learning and 9 deep learning-based predictive pipelines across three public benchmark requirements classification datasets using eight different evaluation measures.

Results: The large-scale experimental results demonstrate that proposed MLR-Predictor outperforms 123 adopted machine learning and 9 deep learning predictive pipelines, as well as the state-of-the-art requirements classification predictor. Specifically, in comparison to state-of-the-art predictor, it achieves a 13% improvement in macro F1-measure on the PROMISE dataset, a 1% improvement on the EHR-binary dataset, and a 2.5% improvement on the EHR-multiclass dataset.

Discussion: As a case study, the generalizability of proposed predictor is evaluated on softwares customer reviews classification data. In this context, the proposed predictor outperformed the state-of-the-art BERT language model by F-1 score of 1.4%. These findings underscore the robustness and effectiveness of the proposed MLR-Predictor in various contexts, establishing its utility as a promising solution for requirements classification task.

Introduction: This study investigates the application of machine learning (ML) algorithms, a subset of artificial intelligence (AI), to predict financial distress in companies. Given the critical need for reliable financial health indicators, this research evaluates the predictive capabilities of various ML techniques on firm-level financial data.

Methods: The dataset comprises financial ratios and firm-specific variables from 464 firms listed on the TSX. Multiple ML models were tested, including decision trees, random forests, support vector machines (SVM), and artificial neural networks (ANN). Recursive feature elimination with cross-validation (RFECV) and bootstrapped CART were also employed to enhance model stability and feature selection.

Results: The findings highlight key predictors of financial distress, such as revenue growth, dividend growth, cash-to-current liabilities, and gross profit margins. Among the models tested, the ANN classifier achieved the highest accuracy at 98%, outperforming other algorithms.

Discussion: The results suggest that ANN provides a robust and reliable method for financial distress prediction. The use of RFECV and bootstrapped CART contributes to the model's stability, underscoring the potential of ML tools in financial health monitoring. These insights carry valuable implications for auditors, regulators, and company management in enhancing practices around financial oversight and fraud detection.

The aim of the paper is twofold. First to examine the role of the board of directors in facilitating the adoption of AI and ML in Saudi Arabian banking sector. Second, to explore the effectiveness of artificial intelligence and machine learning in protection of Saudi Arabian banking sector from cyberattacks. A qualitative research approach was applied using in-depth interviews with 17 board of directors from prominent Saudi Arabian banks. The present study highlights both the opportunities and challenges of integrating artificial intelligence and machine learning advanced technologies in this highly regulated industry. Findings reveal that advanced artificial intelligence and machine learning technologies offer substantial benefits, particularly in areas like threat detection, fraud prevention, and process automation, enabling banks to meet regulatory standards and mitigate cyber threats efficiently. However, the research also identifies significant barriers, including limited technological infrastructure, a lack of cohesive artificial intelligence strategies, and ethical concerns around data privacy and algorithmic bias. Interviewees emphasized the board of directors' critical role in providing strategic direction, securing resources, and fostering partnerships with artificial intelligence technology providers. The study further highlights the importance of aligning artificial intelligence and machine learning initiatives with national development goals, such as Saudi Vision 2030, to ensure sustained growth and competitiveness. The findings from the present study offer valuable implications for policymakers in banking in navigating the complexities of artificial intelligence and machine learning adoption in financial services, particularly in emerging markets.