Abstract:Safety cases provide clear, comprehensive, and reliable arguments which mean that a system’s operation under a specific environment meets acceptable safety levels. In safety-critical sectors subject to regulations such as automotive, aviation, and nuclear industries, certification authorities often require the system to undergo a rigorous safety assessment process and thus demonstrate that the system complies with one or more safety standards. The safety case utilization in system development is an emerging technical means to express the safety attributes of safety-critical systems in a structured and comprehensive way. This study briefly introduces the four basic steps of building a safety case, including determining the goal, gathering evidence, constructing arguments, and evaluating the case, and then focuses on the key step of constructing arguments. Meanwhile, eight existing forms of safety case expressions are introduced in detail, containing goal structuring notation (GSN), claim-argument-evidence (CAE), and structured assurance case metamodel (SACM), with their strengths and weaknesses analyzed. Given the significant complexity of the materials required for safety cases, software tools are often adopted as practical methods for constructing and evaluating safety cases. Additionally, seven tools for developing and evaluating safety cases are compared, including astah system safety, gsn2x, NOR-STA, Socrates, ASCE, D-Case Editor, and AdvoCATE. Furthermore, this study delves into multiple challenges in building safety cases. These challenges include data reliability and integrity, complexity and uncertainty management, inconsistencies in regulations and standards, human factor engineering, rapid technological advancements, and challenges in team and interdisciplinary collaboration. Finally, a prospect is provided for the future development of safety cases to reveal their potential utilization and relevant research problems.

Abstract:Data annotation is a key part of the effective operation of most artificial intelligence algorithms. The better the annotation accuracy and quantity, the better the performance of the algorithm. The development of the data annotation industry boosts employment in many cities and towns in China, prompting China to gradually become the center of world data annotation. This study summarizes its development, including origin, application scenarios, classifications, and tasks; lists the commonly used annotation data sets, open source data annotation tools and commercial annotation platforms; proposes the data annotation specification including roles, standards, and processes; gives an example of data annotation in a sentiment analysis. Then, this paper describes the models and characteristics of state-of-the-art algorithms for evaluating annotation results, and compares their advantages and disadvantages. Finally, this paper prospects research focuses and development trends of data annotation from four aspects:tasks, tools, annotation quality, and security.

Abstract:The Business Process Modelling Notation 2.0 (BPMN 2.0) choreography is a de factor standard for capturing the interactions between business processes. Flow-oriented BPMN 2.0 choreographies can exhibit a range of semantic errors in the control flow. The ability to check the semantic correctness of choreographies is thus a desirable feature for modelling tools based on BPMN 2.0 choreographies. However, the semantic analysis of BPMN 2.0 choreographies is hindered by the lack of formal semantic definition of its constructs and the corresponding analysis techniques in the BPMN 2.0 standard specification. This paper defines a formal semantics of BPMN 2.0 choreographies in terms of a mapping to WF-nets. This defined semantics can be used to analyze the structural errors and the control flow errors of BPMN 2.0 choreographies with analysis techniques of Petri nets. The proposed mapping and the semantic analysis have been implemented as a tool. The experimental results show this formalization can identify the semantic errors of choreographies from the BPM AI process model library.

Abstract:In supporting semantic Web, knowledge graphs have played a vital role in many areas such as knowledge QA and semantic search. Therefore, they have become a hot topic in the field of research and engineering. However, it is often costly to build a large-scale knowledge graph with high accuracy. How to balance the accuracy and efficiency, and quickly build a high-quality domain knowledge graph, is a big challenge in the field of knowledge engineering. This paper engages a systematic study on the construction of domain knowledge graphs, and puts forward an accurate and efficient method of constructing domain knowledge graphs as four-steps. This method has been applied to the construction of knowledge graphs of nine subjects in the k12 education of China, and the nine subject knowledge graphs have been developed with high accuracy, which demonstrates that the new method is effective. For example, the geographical knowledge graph, which is constructed using the four-steps method, has 670 thousand instances and 14.21 million triples. And as part of it, the annotation datas knowledge coverage and knowledge accuracy are both above 99%.

Abstract:Canonical correlation analysis (CCA) is a statistical analysis tool for analyzing the correlation between two sets of random variables. CCA requires the data be rigorously paired or one-to-one correspondence among different views due to its correlation definition. However, such requirement is usually not satisfied in real-world applications due to various reasons. Often, only a few paired and a lot of unpaired multi-view data are given, because unpaired multi-view data are relatively easier to be collected and pairing them is difficult, time consuming and even expensive. Such data is referred as semi-paired multi-view data. When facing semi-paired multi-view data, CCA usually performs poorly. To tackle this problem, a semi-paired variant of CCA, named SemiPCCA, is proposed based on the probabilistic model for CCA. The actual meaning of semi- in SemiPCCA is semi-paired rather than semi-supervised as in popular semi-supervised learning literature. The estimation of SemiPCCA model parameters is affected by the unpaired multi-view data which reveal the global structure within each modality. By using artificially generated semi-paired multi-view data sets, the experiment shows that SemiPCCA effectively overcome the over-fitting problem of traditional CCA and PCCA (probabilistic CCA) under the condition of insufficient paired multi-view data and performs better than the original CCA and PCCA. In addition, an automatic image annotation method based on the SemiPCCA is presented. Through estimating the relevance between images and words by using the labelled and unlabeled images together, this method is shown to be more accurate than previous published methods.

Abstract:Automatic image annotation is a challenging research problem involving lots of tags and various features. Aiming at the problem that the image annotation based on the traditional shallow machine learning algorithm has low efficiency and is difficult to apply to complex classification task, this paper proposes an automatic image annotation algorithm based on stacked auto-encoder (SAE) to improve both efficiency and effectiveness of annotation. In this paper, two types of strategies are proposed to solve the main problem of unbalanced data in image annotation. For the annotation model itself, to improve the annotation effect of low frequency tags, a balanced and stacked auto-encoder (B-SAE) that can enhance training for low frequency tags is proposed. Based on this model, a robust balanced and stacked auto-encoder algorithm (RB-SAE) is proposed to increase the annotation stability through enhanced training by group in sub B-SAE model. This strategy ensures that the model itself has a strong ability to deal with the unbalanced data. For the annotation process, taking the unknown image as the starting point, the local equilibrium dataset of the unknown image is constructed, and the high and low frequency attribute of the image is discriminated to determine the different annotation process. The local semantic propagation algorithm (SP) annotates the low frequency images and the RB-SAE algorithm annotates the high frequency images. The framework of attribute discrimination annotation (ADA) is formed to improve the overall image annotation effect. This strategy ensures that the labeling process has a strong ability to deal with unbalanced data. Experimental results generated from three public data sets show that many indicators in the presented model are all improved comparing with the previous models.

Abstract:An electronic medical record (EMR) is a patients individual medical record written by health care providers and stored in digital format in which much medical knowledge and information about patients personal health conditions are kept. The construction of annotated corpus for named entities and entity relations on EMR is a primary and fundamental task for information extraction which plays important role in clinical decision support, practice of evidence-based medicine, and other medical applications. Based on survey of current research on corpus construction for named entities and entity relations on EMR, this research proposes an annotation scheme for named entities and entity relations on Chinese electronic medical records (CEMR) according to characteristics of the records. Under the supervision of physicians, a complete and detailed annotation specification on CEMR is formulated, and an annotated corpus with high agreement is constructed. The corpus comprises 992 medical text documents, and inter-annotator agreement (IAA) of named entity annotations and entity relation annotations attain 0.922 and 0.895, respectively. The work presented in this paper builds substantial foundations for the subsequent research on information extraction in CEMR.

Abstract:Recently, ontology-based intelligent information retrieval systems, aiming to further improve the retrieval performance and intelligence by using ontology, have become one of the hottest topics in the domain of intelligent information retrieval systems. This paper presents an overview of the field of ontology-based intelligent information retrieval systems from a process-oriented perspective, including the system framework, ontology knowledge acquisition and use, key technologies, and evaluation. The prospects for future development and suggestions for possible extensions of the ontology-based intelligent information retrieval systems are also discussed.

Abstract:In dealing with the explosive growth of web images, Web image annotation has become a critical research issue in recent years. Sparse feature selection plays an important role in improving the efficiency and performance of Web image annotation. In this paper, a feature selection framework is proposed with enhanced sparsity for Web image annotation. The new framework, termed as semi-supervised sparse feature selection based on l2,1/2-matix norm with shared subspace learning (SFSLS), selects the most sparse and discriminative features by utilizing l2,1/2-matix norm and obtains the correlation between different features via shared subspace learning. In addition, SFSLS uses graph Laplacian semi-supervised learning to exploit both labeled and unlabeled data simultaneously. An efficient iterative algorithm is designed to optimize the objective function. SFSLS method is compared to other feature selection algorithms on two Web image datasets and the results indicate it is suitable for large-scale Web image annotation.

Abstract:With the rapid increase of embedded computer system applications, the reliability of embedded software has drawn particular attention from researchers and industries. Many methods for testing and verifying reliability of embedded software have been discussed. However, the existing methods are weak in test suite automatic generation and therefore difficult in tackling large numbers of embedded computer applications. In this paper, the method and the technique of generating abstract test suite and their adaptation to a computer platform are presented. An algorithm for translating a LTS (labeled transition system) into BT (behavior tree) is proposed. Consequently, the TTCN (test and testing control notation) abstract test suite that employs BT as logical structure can automatically be generated with respect to the LTS description of embedded software. A TTCN tool set based on the translation algorithm for testing embedded software is introduced, and case study of testing embedded system of Internet of things device is presented.