信息工程最新文献

Background

Candida species are the fourth most common etiological agents of late-onset infection in the neonatal intensive care unit (NICU) and are responsible for considerable morbidity and mortality.

Objectives

From November 2023 to February 2024, we investigated the association of mycotic pneumonia with septicemia in 60 neonates, and their roles of mycotic pneumonia in the morbidity and mortality of neonates in two NICUs in the Al-Ramadi Teaching Hospital for Maternity and Children.

Methods

All infants in this study had been diagnosed with septicemia and treated with empirical antimicrobial therapy. An early morning nasogastric tube (NG-tube) was used to collect swallowed sputum by suction for culture and sensitivity testing.

Results

The average white blood count for the neonates was 8547 ± 5884.5 cells/mm². The mean C-reactive protein was 39.3 ± 26 mg/l, the mean serum albumin was 2.9 ± 0.2 g/dl and the positive bacterial blood culture was 28 (46.7 %). 9 (15 %) neonates died during the study period. The NG-tube culture identified fungal growth in all samples. Of these, 49 (81.6 %) were identified as Candida albicans, 6 (10 %) as Candida tropicalis, and 5 (8.3 %) as Cryptococcus laurentii. The bacterial culture results from the NG-tube samples identified 13 (21.6 %) patients with gram-positive bacteria and 47 (78.3 %) with gram-negative bacteria.

Conclusion

We found a prevalence of Candida spp. among neonates in addition to microbial oxygen tube contamination, indicating a biosafety breach in the neonatal unit. Mycotic infection requires global attention as a probable cause of respiratory failure in neonatal septicemia.

The integration of Dynamic Graph Neural Networks (DGNNs) with Smart Manufacturing is crucial as it enables real-time, adaptive analysis of complex data, leading to enhanced predictive accuracy and operational efficiency in industrial environments. To address the problem of poor combination effect and low prediction accuracy of current dynamic graph neural networks in spatial and temporal domains, and over-smoothing caused by traditional graph neural networks, a dynamic graph prediction method based on spatiotemporal binary-domain recurrent-like architecture is proposed: Binary Domain Graph Neural Network (BDGNN). The proposed model begins by utilizing a modified Graph Convolutional Network (GCN) without an activation function to extract meaningful graph topology information, ensuring non-redundant embeddings. In the temporal domain, Recurrent Neural Network (RNN) and residual systems are employed to facilitate the transfer of dynamic graph node information between learner weights, aiming to mitigate the impact of noise within the graph sequence. In the spatial domain, the AdaBoost (Adaptive Boosting) algorithm is applied to replace the traditional approach of stacking layers in a graph neural network. This allows for the utilization of multiple independent graph learners, enabling the extraction of higher-order neighborhood information and alleviating the issue of over-smoothing. The efficacy of BDGNN is evaluated through a series of experiments, with performance metrics including Mean Average Precision (MAP) and Mean Reciprocal Rank (MRR) for link prediction tasks, as well as metrics for traffic speed regression tasks across diverse test sets. Compared with other models, the better experiments results demonstrate that BDGNN model can not only better integrate the connection between time and space information, but also extract higher-order neighbor information to alleviate the over-smoothing phenomenon of the original GCN.

Outbreaks of Monkeypox (mpox) in over 100 non-endemic countries in 2022 represented a serious global health concern. Once a neglected disease, mpox has become a global public health issue. A42R profilin-like protein from mpox (PDB ID: 4QWO) represents a potential new lead for drug development and may interact with various synthetic and natural compounds. In this report, the interaction of A42R profilin-like protein with six phytochemicals found in the medicinal plant Ficus religiosa (abundant in India) was examined. Based on the predicted and compared protein–ligand binding energies, biological properties, IC₅₀ values and toxicity, two compounds, kaempferol (C-1) and piperine (C-4), were selected. ADMET characteristics and quantitative structure–activity relationship (QSAR) of these two compounds were determined, and molecular dynamics (MD) simulations were performed. In silico examination of the kaempferol (C-1) and piperine (C-4) interactions with A42R profilin-like protein gave best-pose ligand-binding energies of –6.98 and –5.57 kcal/mol, respectively. The predicted IC₅₀ of C-1 was 7.63 μM and 82 μM for C-4. Toxicity data indicated that kaempferol and piperine are non-mutagenic, and the QSAR data revealed that piperlongumine (5.92) and piperine (5.25) had higher log P values than the other compounds examined. MD simulations of A42R profilin-like protein in complex with C-1 and C-4 were performed to examine the stability of the ligand–protein interactions. As/C and C-4 showed the highest affinity and activities, they may be suitable lead candidates for developing mpox therapeutic drugs. This study should facilitate discovering and synthesizing innovative therapeutics to address other infectious diseases.

The fault diagnosis of cargo UAVs (Unmanned Aerial Vehicles) is crucial to ensure the safety of logistics distribution. In the context of smart logistics, the new trend of utilizing knowledge graph (KG) for fault diagnosis is gradually emerging, bringing new opportunities to improve the efficiency and accuracy of fault diagnosis in the era of Industry 4.0. The operating environment of cargo UAVs is complex, and their faults are typically closely related to it. However, the available data only considers faults and maintenance data, making it difficult to diagnose faults accurately. Moreover, the existing KG suffers from the problem of confusing entity boundaries during the extraction process, which leads to lower extraction efficiency. Therefore, a fault diagnosis knowledge graph (FDKG) for cargo UAVs constructed based on multi-domain fusion and incorporating an attention mechanism is proposed. Firstly, the multi-domain ontology modeling is realized based on the multi-domain fault diagnosis concept analysis expression model and multi-dimensional similarity calculation method for cargo UAVs. Secondly, a multi-head attention mechanism is added to the BERT-BILSTM-CRF network model for entity extraction, relationship extraction is performed through ERNIE, and the extracted triples are stored in the Neo4j graph database. Finally, the DJI cargo UAV failure is taken as an example for validation, and the results show that the new model based on multi-domain fusion data is better than the traditional model, and the precision rate, recall rate, and F1 value can reach 87.52%, 90.47%, and 88.97%, respectively.

Artificial intelligence empowers the rapid development of autonomous intelligent systems (AISs), but it still struggles to cope with open, complex, dynamic, and uncertain environments, limiting its large-scale industrial application. Reliable human feedback provides a mechanism for aligning machine behavior with human values and holds promise as a new paradigm for the evolution and enhancement of machine intelligence. This paper analyzes the engineering insights from ChatGPT and elaborates on the evolution from traditional feedback to human feedback. Then, a unified framework for self-evolving intelligent driving (ID) based on human feedback is proposed. Finally, an application in the congested ramp scenario illustrates the effectiveness of the proposed framework.