This paper proposes a novel symbolic execution path exploration strategy named MS-ALS (Multi-strategy Active Learning Search). MS-ALS integrates multiple heuristic methods and introduces a machine learning model to learn symbolic states of program paths from the training set, aiming to predict the reward of symbolic states of program paths for selecting the optimal states. To obtain an accurate predictive model, this paper employs an active learning approach based on multiple query strategies. It selects symbolic states of program paths with high uncertainty, representativeness, and low redundancy from the pool of states to annotate, feeding back the state samples to the model to guide it towards more accurate predictions. This enables symbolic execution tools to explore input programs more efficiently. Experiments show that MS-ALS achieves higher code coverage and identifies more security violations compared to baseline methods. Additionally, test cases generated by MS-ALS also exhibit higher quality, improving AFL’s path discovery in fuzz testing when used as initial seeds.

Abstract Cross-domain recommendation (CDR) has become an important research direction in the field of recommender systems due to the increasing demand for personalized recommendations across different domains. However, CDR faces multiple challenges, including data sparsity, popularity bias, and long-tail problems. To address these challenges, we propose a novel framework that combines graph contrastive embedding and multi-head cross-attention transfer for cross-domain recommendation, called GCE-MCAT. Specifically, in the pre-training process, we generate more uniform user and item embeddings through contrastive learning, effectively solving the problem of inconsistent data embedding space distribution and recommendation popularity bias. Moreover, we propose a multi-head cross-attention transfer mechanism that allows the model to extract user common and specific domain features from multiple perspectives and perform cross-domain bidirectional knowledge transfer. Finally, we propose a cross-domain feature fusion mechanism that dynamically assigns weights to common user features and specific domain features. This enables the model to more effectively learn common user interests. We evaluate the proposed framework on three real-world CDR datasets and show that GCE-MCAT consistently and significantly improves recommendation performance compared to state-of-the-art methods. In particular, the proposed framework has demonstrated remarkable effectiveness in addressing long-tail distribution and enhancing recommendation novelty, providing users with more diversified recommendations and reducing popularity bias.

In recent years, the study of social-based recommender systems has become an active research topic. We incorporate a combination of static and dynamic interest characteristics to predict users’ real-time dynamic interests, which has rarely been considered in previous studies. In this paper, we propose a graph neural network social recommendation model that integrates static and dynamic feature relationships (FSDFR-GNNSR). The model uses a graph embedding algorithm to extract static features of users and movies, and takes the static features as input to gated recurrent unit (GRU), so that the model can take static features into consideration while modeling user dynamic behavior. Finally, we use graph attention networks to represent the dynamic influence of friends, simplify the update strategy of second-order neighbor nodes. We apply graph pooling operations to improve the generalization ability of the algorithm. Empirical analyses on real datasets show that the proposed approach achieves superior performance to existing approaches.

In recent years, the business scale of my country’s circulation industry has continued to expand, and the output value has continued to increase. The leading role in guiding the transformation of the industrial economy has become more and more important. Based on this, this article discusses the research on the promotion of the Internet of Things technology to the circulation industry in the transformation of the resource‐based economy. The application of RFID technology and wireless sensor technology in the Internet of Things in the circulation industry can greatly improve work efficiency and information transmission accuracy. This article establishes the circulation industry based on the principles of science, system, safety, and relative independence. The evaluation index system analyzes the role of the circulation industry in the transformation of the resource‐based economy in terms of circulation scale, circulation structure, circulation efficiency, circulation innovation, etc., and uses the analytic hierarchy process and entropy method to analyze the collected data. With the support of RFID technology, the output value of the circulation industry in Province Y has reached 140.508 billion yuan in 2019, accounting for about 27% of the tertiary industry, and the number of employees in the circulation industry has also increased to 57.88%, which is a strong boost to the economy of Province Y. It has a greater contribution to the total economic volume. The research of this article has realized the economic transformation of resource‐based cities in the circulation industry and has a certain reference effect for the transformation and upgrading of similar cities.

Electrophysiological tests, especially, electromyogram (EMG) and nerve conduction velocity (NCV) test are commonly used in clinical practice for diagnosis of muscle and nerve diseases. Report-writing of these tests can be problematic for under-experienced physicians and time-consuming for experienced physicians. In this paper, we apply several neural based natural language generation (NLG) methods to automatically generate diagnosis reports, a first attempt in this domain. Specifically, we use tabular diagnostic records of electrophysiological tests to generate Findings & Impression, which together constitute the diagnostic report. We further use gram-based metrics to evaluate our models and conduct a case study for the result.

In this paper, we present a novel electronic health records (EMR) retrieval system that helps to reduce manual in work in cohort identification. Our system effectively uses medical domain knowledge to enhance retrieval performance. In particular, our system first maps raw text of EMR and EMR queries from the text space to concept unique identifiers in the medical concept space, and then searches in the two spaces independently, and finally weights and combines search results adaptively based on several heuristics. Our cross-validation results show that the proposed adaptive weighting mechanism is significantly better than the fixed-weighting mechanism, and also that the joint search is more effective than text-based search or concept-based search. In addition, we introduce an effective approach for external expansion in the concept space.

In this paper, we present a medical record search system which is useful for identifying cohorts required in clinical studies. In particular, we propose a query-adaptive weighting method that can dynamically aggregate and score evidence in multiple medical reports (from different hospital departments or from different tests within the same department) of a patient. Furthermore, we explore several informative features for learning our retrieval model.

The increasing prevalence of electronic health records (EHR), along with the needs for enhanced clinical care, presents new challenges to information retrieval (IR). Many clinical decision-making tasks following the philosophy of Evidence-Based Medicine (EBM) rely on the ability to find relevant health records and gather sufficient clinical evidence under severe time constraints. In this work, we present a system built upon statistical IR methods for searching flat-text health records (i.e. the doctors' notes sections of EHR) for patients with particular conditions specified via a keyword query. In particular, we use multiple external repositories for query expansion, and introduce two novel model weighting methods. Cross-validation results show that our system improves a strong baseline by 30% on mean average precision (MAP), and has a promising overall performance when compared with a manual system doing the same task.