Withthe rapid development of the medical field, the electronic medical record (EMR) is a rich source of clinical information for medical study. However, electronic medical records are full of redundant information, w...
Withthe rapid development of the medical field, the electronic medical record (EMR) is a rich source of clinical information for medical study. However, electronic medical records are full of redundant information, which increases the difficulty of statistical analysis. the international Classification of Diseases (ICD) is widely used to describe the diagnosis of patients. A reliable automated ICD coding system can improve the quality of clinical decision support. Manual coding is time-consuming, expensive, and error-prone. To reduce coding errors and cost, we aim at developing an ICD code assignment system that automatically and accurately assigns the diagnostic description(DD) to ICD codes. Automated ICD coding is the multi-label classification task, which is to assign the ICD codes to the diagnostic description. In this paper, we apply the Neural Machine Translation(NMT) to the multi-label classification task of the code assignment problem. We proposed RAANMT(Recurrent-Based Encoder and Average Attention-Based Decoder for Neural Machine Translation), which can extract the relationship between the text and the labels to improve the automated ICD coding. Moreover, we implement experiments on Chinese dataset CDTD-TP and English dataset MIMIC III. Extensive experiments show that our RAANMT model can improve the performance of the automated code assignment.
During the COVID-19 pandemic, it is imperative to distribute daily supplies to residents in lockdown communities and collect their household garbage. Unmanned Aerial Vehicle (UAV) logistics offers a contactless soluti...
During the COVID-19 pandemic, it is imperative to distribute daily supplies to residents in lockdown communities and collect their household garbage. Unmanned Aerial Vehicle (UAV) logistics offers a contactless solution, but the limitations of load and maintenance costs must be considered. therefore, it is crucial to plan UAV transportation routes effectively to minimize overall transportation costs. Additionally, the stochasticity of household garbage quality further complicates UAV delivery. We address this issue by formulating the problem as vehicle routing problem with simultaneous stochastic pickups and deliveries (VRPSSPD) and develop a range of swarm intelligent optimization algorithms (SIOAs) to solve it. Our experiments demonstrate that the Artificial Bee Colony (ABC) algorithm and Shuffled Frog Leaping Algorithm (SFLA) are well-suited to this practical problem. Moreover, to address the long convergence time of SFLA, we propose the General Center SFLA based on Roulette Wheel Selection (RWS-GC-SFLA) to improve it. Our experimental results show that RWS-GC-SFLA can improve the convergence time while ensuring solution quality. Finally, we apply RWS-GCSFLA to a practical instance case of UAV logistics in Guangzhou communities and achieved satisfactory results.
As the most severe environmental problem in the 21st century, global warming has become an inevitable and urgent issue to be solved. In this paper, a Forest Carbon Sink (FCS) planning model (Model I) is proposed to il...
As the most severe environmental problem in the 21st century, global warming has become an inevitable and urgent issue to be solved. In this paper, a Forest Carbon Sink (FCS) planning model (Model I) is proposed to illustrate the forest stand composition and evaluate the overall capacity of FCS according to the forest carbon reserve, forest carbon sequestration, forest product carbon content, and carbon sink transfer restriction. Considering the felling cycle further, an ecological FCS model (Model II) is proposed, which pays more attention to the ability to balance the carbon sink benefit and ecological benefit. Based on the difference between Model I and Model II, the felling cycle plays an important role in total FCS. Considering the forest product value, a commercial FCS model (Model III) is proposed, which measures the forest value from two dimensions of carbon sink value and commercial value, and provided Pareto-optimal solutions. To solve the above models, Simulated Annealing-based Differential Evolution (SADE) and its multi-objective variant are developed to provide outstanding decisions for forest managers. Compared to natural forest, annual felling artificial forest achieve a 43.8% increasement on total FCS during 30 years, according to our solutions from SADE.
Accurate transmission line tension prediction is crucial for avoiding power grid suffering from serious lines ice coating, which is a very challenging problem affected by multiple complex reasons, e.g., the massive sh...
Accurate transmission line tension prediction is crucial for avoiding power grid suffering from serious lines ice coating, which is a very challenging problem affected by multiple complex reasons, e.g., the massive sharp changes accompanying the occurrence of ice cover, and the non-negligible association with multiple influencing factors (likes local geographic information and future weather forecasts). In addition, spatial-temporal correlation among different time intervals and different factors leads to their different contribution degrees to prediction. To address these issues, we propose a Globally Attentive Gated Convolutional Network (GAGCN) to integrate multiple sources of Spatial-Temporal information for transmission line icing tension prediction. Specifically, we first comprehensively fuse historical observations and external static factors for simultaneous modelling, second the Global Time-series Attention module is applied to assign different attention to each time step and each feature of the input sequence from a global perspective. then, a Temporal Gated Convolutional Module is subsequently set up to capture the temporal dependence with various subperiods. Finally, future information is fed into the prediction component along with historical information, where the shape and temporal criteria are incorporated into the training objective by a hybrid-loss function so as to capture sharp changes more accurately and timely. Experiments on two real-world datasets demonstrate the superior performance of our GAGCN beyond state-of-the-art methods.
In this study, we present methodologies to process bigdata in complex multimedia forms for sports analytics. Sports analytics is the management and analysis of data collected from sports games to quantify past result...
详细信息
暂无评论