Semantic Modeling of Ship Collision Reports: Ontology Design, Knowledge Extraction, and Severity Classification

Maritime accidents, such as ship collisions and oil spills, directly affect maritime transportation, pollute the water environment, and indirectly threaten life and property safety. Predicting the maritime accident susceptibility and taking measures in advance can effectively avoid the accident probability and reduce the risk. Therefore, this study established dynamic multi-period (monthly, yearly, and five-yearly) maritime accident prediction models based on the random forest (RF) algorithm and Automatic Identification System (AIS) data for susceptibility assessment. First, based on historical maritime accidents and influencing factor data, we generated the feature matrixes and selected the conditioning factors using the Pearson correlation coefficient. Then, we constructed the accident susceptibility models using the RF method and evaluated the model performances based on the accuracy, recall, precision, F1-measure, ROC, and AUC values. Finally, we developed accident susceptibility maps for different period scales. The results show that the monthly, yearly, and five-yearly models performed well according to the validation values. And the three-period susceptibility maps show similar patterns. The high-susceptibility areas are close to the shore, especially from the Shanghai shore to the Guangxi shore. In addition, the ship density and bathymetry are the most critical factors among the ten influencing factors in the three models, contributing around 25% and 20% of the total information. These models and maps can provide technological support for maritime accident susceptibility assessment on a multi-period scale, which can be helpful for route planning and resource allocation in marine management.

This paper aims to estimate the lower and upper bounds of the number of accidents that have occurred in the Singapore Strait over the past 10 years on the basis of two maritime accident databases: Global Integrated Shipping Information System and Lloyd's List Intelligence. After an evaluation of the incompleteness of these two databases, a novel and tangible method is proposed to estimate the lower and upper bounds of the number of accidents by using Bayesian analysis under mild assumptions. This method produces the following three important results. First, the annual maritime accident occurrence frequency in the Singapore Strait ranges from 17.6 to 33.0; that is, less than 0.005% of vessels could be involved in an accident when passing through the Strait. Second, the reporting performances of both maritime accident databases to the Singapore Strait are less than 62.5%. In other words, more than 37.5% of maritime accidents are not included in the database. Third, ship collisions account for more than 50% of all types of accidents; this result indicates that a high priority should be assigned to reducing the occurrence of ship collisions by enhancing the navigational systems in the Singapore Strait.

This paper investigates the impact of knowledge extraction methods on the effectiveness of RAG (Retrieval-Augmented Generation) systems that utilize knowledge graphs. It highlights that the quality of the knowledge graph, which is formed using various knowledge extraction methods, is crucial for overcoming limitations of large language models (LLMs), such as “hallucinations”. The paper analyzes the architectures of LightRAG and GraphRAG, emphasizing that the selection of an optimal knowledge extraction strategy depends on specific tasks and the subject area. LLMs have advanced significantly, but they have limitations, including generating factually incorrect information (“hallucinations”) and possessing “outdated knowledge”. RAG systems were proposed to address these issues by combining LLMs with external knowledge bases. This approach reduces hallucinations, ensures factual accuracy, solves the problem of outdated knowledge, and increases transparency. Knowledge graphs are powerful tools for structuring information, consisting of entities (nodes) and relations (edges). They enhance RAG systems by enabling more precise and contextually grounded retrieval compared to keyword-based searches. The quality of a knowledge graph depends on the knowledge extraction methods used, which include named entity recognition (NER), relation extraction (RE), entity linking (EL), and event extraction. Different methods, such as rule-based, classical machine learning, and deep learning approaches, have varying trade-offs in terms of accuracy, completeness, and scalability. Entity linking and knowledge graph completion are also crucial for accuracy and richness. LightRAG and GraphRAG are two main graph-based RAG systems. LightRAG uses the knowledge graph as a quick reference, requiring high precision in knowledge extraction to avoid noise degradation. GraphRAG uses the knowledge graph as a domain model, where completeness of extracted knowledge is more critical, though systematic errors are still harmful. Both systems rely on LLMs for knowledge extraction, which makes them dependent on the LLM’s quality and the size of document fragments processed. The theoretical analysis confirms that the effectiveness of RAG systems is critically dependent on knowledge extraction methods. The quality, completeness, and accuracy of the knowledge graph directly influence the RAG system’s ability to provide relevant, accurate, and truthful answers. Different RAG system architectures like LightRAG and GraphRAG have distinct requirements for knowledge graph characteristics, prioritizing either accuracy or completeness in knowledge extraction.

In today’s big data era, there are a large number of unstructured information resources on the web. Natural language processing researchers have been working hard to figure out how to extract useful information from them. Entity Relation Extraction is a crucial step in Information Extraction and provides technical support for Knowledge Graphs, Intelligent Q&A systems and Intelligent Retrieval. In this paper, we present a comprehensive history of entity relation extraction and introduce the relation extraction methods based on Machine Mearning, the relation extraction methods based on Deep Learning and the relation extraction methods for open domains. Then we summarize the characteristics and representative results of each type of method and introduce the common datasets and evaluation systems for entity relation extraction. Finally, we summarize current entity relation extraction methods and look forward to future technologies.

Prediction of body mass index status from voice signals based on machine learning for automated medical applications

VTS has been operated at the ports and coastal areas in order to prevent maritime accidents and improve transport efficiency, as described in IMO Resolution A.857(20), Guideline for VTS. To reduce the ship collision, we need to understand the factors of the traffic characteristics which is related with collisions. Although many considerable studies have been conducted over the past several years to prevent ship collisions, the results are not practical. We investigated the correlation among statistical parameters of vessel speed, traffic flow, and potential collision rate in VTS area. Finally, This research provides persuasive evidence to enforce an safe speed to reduce ship collisions in VTS area.

Road accidents are a major critical problem in recent days, which cause death, severe injuries, disabilities to human lives, and substantial economic losses worldwide. A detailed analysis of the factors responsible for the accidents is required to reduce the accident rate. In this study, a descriptive analysis has been performed in-depth to identify the significant factors influencing accident severity. Machine learning techniques have been applied to predict the severity of accidents considering location, time, infrastructure, and environmental conditions-related factors that may cause road accidents. Here the findings of this study emphasize that the mediate severity of accidents have a high frequency of occurring rather than severities of very low and high risk. Moreover, the factors like infrastructure, day of the week, and weather conditions influence the severity of accidents differently. The Random Forest algorithm took the best performance with 97.2% high accuracy in predicting the severity of road traffic accidents. These results can guide relevant parties to identify dangerous situations and take the necessary actions to improve road safety by reducing accidents.

Random forest (RF) is a competitive machine learning theorem, while one of the big challenges for it is imbalanced real-world data. A Two-dimensional-reduction RF (2DRRF) is presented in this paper, which is optimized based on traditional RF and three innovation points as follows. To improve RF in terms of performance on imbalanced data, a two-dimensional-reduction approach is created. Then, a modified T-link is proposed focusing on detecting and reducing safe samples. Moreover, a biased sampling manner is employed to build up optimal training datasets. Across 13 imbalanced datasets from KEEL-dataset with imbalance-ratio ranging from 6.38 to 129.44, experiments are carried out indicating that 2DRRF steadily holds advantages over the other two relevant implementations of RF in terms of accuracy, recall, precision and F-value.

BackgroundBiodiversity is the assortment of life on earth covering evolutionary, ecological, biological, and social forms. To preserve life in all its variety and richness, it is imperative to monitor the current state of biodiversity and its change over time and to understand the forces driving it. This need has resulted in numerous works being published in this field. With this, a large amount of textual data (publications) and metadata (e.g. dataset description) has been generated. To support the management and analysis of these data, two techniques from computer science are of interest, namely Named Entity Recognition (NER) and Relation Extraction (RE). While the former enables better content discovery and understanding, the latter fosters the analysis by detecting connections between entities and, thus, allows us to draw conclusions and answer relevant domain-specific questions. To automatically predict entities and their relations, machine/deep learning techniques could be used. The training and evaluation of those techniques require labelled corpora.New informationIn this paper, we present two gold-standard corpora for Named Entity Recognition (NER) and Relation Extraction (RE) generated from biodiversity datasets metadata and abstracts that can be used as evaluation benchmarks for the development of new computer-supported tools that require machine learning or deep learning techniques. These corpora are manually labelled and verified by biodiversity experts. In addition, we explain the detailed steps of constructing these datasets. Moreover, we demonstrate the underlying ontology for the classes and relations used to annotate such corpora.

Entity relation extraction (RE) is an very important research domain in information extraction, we can regard RE as a classification problem in this paper, RE is still original study field in Chinese language now, maximum entropy (ME)-based machine learning is the first time to be used to extract entity relations between named entities from Chinese texts, Thirteen features have been designed for entity relation extraction, which includes morphology, grammar and semantic feature. The system architecture for RE has been constructed. Experiment shows that the performance is promising. So it is useful for ME-based machine learning to solve RE problem

The task of entity relation extraction discovers new relation facts and enables broader applications of knowledge graph. Distant supervision is widely adopted for relation extraction, which requires large amounts of texts containing entity pairs as training data. However, in some specific domains such as medical-related applications, entity pairs that have certain relations might not appear together, thus it is difficult to meet the requirement for distantly supervised relation extraction. In the light of this challenge, we propose a novel path-based model to discover new entity relation facts. Instead of finding texts for relation extraction, the proposed method extracts path-only information for entity pairs from the current knowledge graph. For each pair of entities, multiple paths can be extracted, and some of them are more useful for relation extraction than others. In order to capture this observation, we employ attention mechanism to assign different weights for different paths, which highlights the useful paths for entity relation extraction. To demonstrate the effectiveness of the proposed method, we conduct various experiments on a large-scale medical knowledge graph. Compared with the state-of-the-art relation extraction methods using the structure of knowledge graph, the proposed method significantly improves the accuracy of extracted relation facts and achieves the best performance.

Ship collisions are one of the most common types of maritime accidents. Assessing the frequency and probability of ship collisions is of great importance as it provides a cost-effective and practical way to mitigate risk. In this paper, we present a review of quantitative ship collision frequency estimation models for waterway risk assessment, accompanied by a classification of the models and a description of their main modelling characteristics. Models addressing the macroscopic perspective in the estimation of ship collision frequency on waterways are reviewed in this paper with a total of 29 models. We extend the existing classification methodology and group the collected models accordingly. Special attention is given to the criteria used to detect potential ship collision candidates, as well as to causation probability and the correlation of models with real ship collision statistics. Limitations of the existing models and future improvement possibilities are discussed. The paper can be used as a guide to understanding current achievements in this field.

This study examines the performance of Random Forest and XGBoost in predicting the diagnosis and severity of respiratory diseases using a simulated dataset of 2,000 patient records. The models were tested on two classification tasks: identifying disease types (e.g., pneumonia, influenza) and classifying severity levels (mild, moderate, severe). Both models achieved perfect accuracy in severity classification, with 1.0000 ± 0.0000 cross-validation scores, demonstrating strong stability under balanced class distributions. However, in the diagnosis task, Random Forest underperformed on minority classes, particularly pneumonia, with a recall of 0.18 and F1-score of 0.31. XGBoost, on the other hand, achieved superior results across all classes, including minority cases, with 0.9825 ± 0.0170 cross-validation accuracy and perfect test set performance. These findings highlight XGBoost’s robustness in handling imbalanced and multiclass medical data, making it a promising candidate for clinical decision support. Future work should address class imbalance and explore explainability techniques to improve trust and transparency in real-world applications.

The accurate severity classification of a bug report is an important aspect of bug fixing. The bug reports are submitted into the bug tracking system with high speed, and owing to this, bug repository size has been increasing at an enormous rate. This increased bug repository size introduces biases in the bug triage process. Therefore, it is necessary to classify the severity of a bug report to balance the bug triaging process. Previously, many machine learning models were proposed for automation of bug severity classification. The accuracy of these models is not up to the mark because they do not extract the important feature patterns for learning the classifier. This paper proposes a novel deep learning model for multiclass severity classification called Bug Severity classification to address these challenges by using a Convolutional Neural Network and Random forest with Boosting (BCR). This model directly learns the latent and highly representative features. Initially, the natural language techniques preprocess the bug report text, and then n-gram is used to extract the features. Further, the Convolutional Neural Network extracts the important feature patterns of respective severity classes. Lastly, the random forest with boosting classifies the multiple bug severity classes. The average accuracy of the proposed model is 96.34% on multiclass severity of five open source projects. The average F-measures of the proposed BCR and the existing approach were 96.43% and 84.24%, respectively, on binary class severity classification. The results prove that the proposed BCR approach enhances the performance of bug severity classification over the state-of-the-art techniques.

Maritime accident prediction in busan port using machine learning: An integrated approach with maritime accident reports and VTS data