Natural Language Processing Based Method for Clustering and Analysis of Aviation Safety Narratives

Resisting the (re-)medicalisation of dying and grief in the post-digital age: Natural language processing and qualitative analysis of data from internet support forums

In the mid-twentieth century, the social movement of death revivalism sought to resist the medicalisation of dying and grief through promotion of the dying person retaining autonomy, and societal openness toward death and bereavement. Despite this advocacy, present-day dying in high income countries is largely institutionalised, with value placed on control over the body and emotions. These phenomena are at odds with the ambitions of death revivalism, and demonstrate the re-medicalisation of dying and grief. Furthermore, contemporary society is continually advancing into the post-digital age, reflected in digital technologies being a tacit part of human existence. Within this framework, this study aims to investigate how people living with life-limiting illness and their loved ones experience, negotiate, and resist medicalisation of dying and grief through online internet forums. We collected posts through web-scraping and utilised Natural Language Processing techniques to select 7048 forum posts from 2003 to 2020, and initially categorise data, before utilising Inductive Thematic Analysis, which generated two major themes. The theme of 'Comfort' describes online forums facilitating psychosocial support which was often used to compensate for systemic deficiencies, especially during the Covid-19 pandemic. Common sources of comfort included animal companions and spirituality, in stark contrast with the medicalised model. The theme of 'Capability' describes online forums acting as solutions for people facing disempowering care systems, including providing information on legal rights and benefits which may not be otherwise easily available, and facilitating collective advocacy. Our findings indicate that community-led online forums can play an effective and sustainable role in democratising care and retaining agency when facing life-limiting illness and grief. Future palliative and bereavement care research must focus on how online forums can be integrated into existing systems, made transparent and accessible, be adequately funded and structured, and be optimised, including compensating for service disruption encountered during future pandemics.

A Scoping Literature Review of Natural Language Processing Application to Safety Occurrence Reports

Safety occurrence reports can contain valuable information on how incidents occur, revealing knowledge that can assist safety practitioners. This paper presents and discusses a literature review exploring how Natural Language Processing (NLP) has been applied to occurrence reports within safety-critical industries, informing further research on the topic and highlighting common challenges. Some of the uses of NLP include the ability for occurrence reports to be automatically classified against categories, and entities such as causes and consequences to be extracted from the text as well as the semantic searching of occurrence databases. The review revealed that machine learning models form the dominant method when applying NLP, although rule-based algorithms still provide a viable option for some entity extraction tasks. Recent advances in deep learning models such as Bidirectional Transformers for Language Understanding are now achieving a high accuracy while eliminating the need to substantially pre-process text. The construction of safety-themed datasets would be of benefit for the application of NLP to occurrence reporting, as this would allow the fine-tuning of current language models to safety tasks. An interesting approach is the use of topic modelling, which represents a shift away from the prescriptive classification taxonomies, splitting data into “topics”. Where many papers focus on the computational accuracy of models, they would also benefit from real-world trials to further inform usefulness. It is anticipated that NLP will soon become a mainstream tool used by safety practitioners to efficiently process and gain knowledge from safety-related text.

Research on Aviation Safety Prediction Based on Variable Selection and LSTM

Accurate prediction of aviation safety levels is significant for the efficient early warning and prevention of incidents. However, the causal mechanism and temporal character of aviation accidents are complex and not fully understood, which increases the operation cost of accurate aviation safety prediction. This paper adopts an innovative statistical method involving a least absolute shrinkage and selection operator (LASSO) and long short-term memory (LSTM). We compiled and calculated 138 monthly aviation insecure events collected from the Aviation Safety Reporting System (ASRS) and took minor accidents as the predictor. Firstly, this paper introduced the group variables and the weight matrix into LASSO to realize the adaptive variable selection. Furthermore, it took the selected variable into multistep stacked LSTM (MSSLSTM) to predict the monthly accidents in 2020. Finally, the proposed method was compared with multiple existing variable selection and prediction methods. The results demonstrate that the RMSE (root mean square error) of the MSSLSTM is reduced by 41.98%, compared with the original model; on the other hand, the key variable selected by the adaptive spare group lasso (ADSGL) can reduce the elapsed time by 42.67% (13 s). This shows that aviation safety prediction based on ADSGL and MSSLSTM can improve the prediction efficiency of the model while keeping excellent generalization ability and robustness.

Multimodal Classification of Safety-Report Observations

Modern businesses are obligated to conform to regulations to prevent physical injuries and ill health for anyone present on a site under their responsibility, such as customers, employees and visitors. Safety officers (SOs) are engineers, who perform site audits to businesses, record observations regarding possible safety issues and make appropriate recommendations. In this work, we develop a multimodal machine-learning architecture for the analysis and categorization of safety observations, given textual descriptions and images taken from the location sites. For this, we utilize a new multimodal dataset, Safety4All, which contains 5344 safety-related observations created by 86 SOs in 486 sites. An observation consists of a short issue description, written by the SOs, accompanied with images where the issue is shown, relevant metadata and a priority score. Our proposed architecture is based on the joint fine tuning of large pretrained language and image neural network models. Specifically, we propose the use of a joint task and contrastive loss, which aligns the text and vision representations in a joint multimodal space. The contrastive loss ensures that inter-modality representation distances are maintained, so that vision and language representations for similar samples are close in the shared multimodal space. We evaluate the proposed model on three tasks, namely, priority classification of input observations, observation assessment and observation categorization. Our experiments show that inspection scene images and textual descriptions provide complementary information, signifying the importance of both modalities. Furthermore, the use of the joint contrastive loss produces strong multimodal representations and outperforms a baseline simple model in tasks fusion. In addition, we train and release a large transformer-based language model for the Greek language based on the Electra architecture.

Controller Fatigue State Detection Based on ES-DFNN

The fatiguing work of air traffic controllers inevitably threatens air traffic safety. Determining whether eyes are in an open or closed state is currently the main method for detecting fatigue in air traffic controllers. Here, an eye state recognition model based on deep-fusion neural networks is proposed for determination of the fatigue state of controllers. This method uses transfer learning strategies to pre-train deep neural networks and deep convolutional neural networks and performs network fusion at the decision-making layer. The fused network demonstrated an improved ability to classify the target domain dataset. First, a deep-cascaded neural network algorithm was used to realize face detection and eye positioning. Second, according to the eye selection mechanism, the pictures of the eyes to be tested were cropped and passed into the deep-fusion neural network to determine the eye state. Finally, the PERCLOS indicator was combined to detect the fatigue state of the controller. On the ZJU, CEW and ATCE datasets, the accuracy, F1 score and AUC values of different networks were compared, and, on the ZJU and CEW datasets, the recognition accuracy and AUC values among different methods were evaluated based on a comparative experiment. The experimental results show that the deep-fusion neural network model demonstrated better performance than the other assessed network models. When applied to the controller eye dataset, the recognition accuracy was 98.44%, and the recognition accuracy for the test video was 97.30%.

Classification and Analysis of Go-Arounds in Commercial Aviation Using ADS-B Data

Go-arounds are a necessary aspect of commercial aviation and are conducted after a landing attempt has been aborted. It is necessary to conduct go-arounds in the safest possible manner, as go-arounds are the most safety-critical of operations. Recently, the increased availability of data, such as ADS-B, has provided the opportunity to leverage machine learning and data analytics techniques to assess aviation safety events. This paper presents a framework to detect go-around flights, identify relevant features, and utilize unsupervised clustering algorithms to categorize go-around flights, with the objective of gaining insight into aspects of typical, nominal go-arounds and factors that contribute to potentially abnormal or anomalous go-arounds. Approaches into San Francisco International Airport in 2019 were examined. A total of 890 flights that conducted a single go-around were identified by assessing an aircraft’s vertical rate, altitude, and cumulative ground track distance states during approach. For each flight, 61 features relevant to go-around incidents were identified. The HDBSCAN clustering algorithm was leveraged to identify nominal go-arounds, anomalous go-arounds, and a third cluster of flights that conducted a go-around significantly later than other go-around trajectories. Results indicate that the go-arounds detected as being anomalous tended to have higher energy states and deviations from standard procedures when compared to the nominal go-arounds during the first approach, prior to the go-around. Further, an extensive comparison of energy states between nominal flights, anomalous flights, the first approach prior to the go-around, and the second approach following the go-around is presented.