This paper examines the capacity utility of machine gaining knowledge of within the clinical putting to enhance organizational overall performance and affected person effects. The paper begins by means of offering a t...
详细信息
This paper describes a study on the design and implementation of a smart crop harvesting system that applies artificial intelligence (AI) technology to address some of the major challenges facing modern agriculture, p...
详细信息
Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size, large language models have shown the ability of in-context ...
详细信息
ISBN:
(纸本)9798350329964
Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size, large language models have shown the ability of in-context learning (ICL). ICL employs task instructions and a few examples as demonstrations, and then inputs the demonstrations to the language models for making predictions. This new learning paradigm is training-free and has shown impressive performance in various natural language processing and code intelligence tasks. However, the performance of ICL heavily relies on the quality of demonstrations, e.g., the selected examples. It is important to systematically investigate how to construct a good demonstration for code-related tasks. In this paper, we empirically explore the impact of three key factors on the performance of ICL in code intelligence tasks: the selection, order, and number of demonstration examples. We conduct extensive experiments on three code intelligence tasks including code summarization, bug fixing, and program synthesis. Our experimental results demonstrate that all the above three factors dramatically impact the performance of ICL in code intelligence tasks. Additionally, we summarize our findings and provide takeaway suggestions on how to construct effective demonstrations, taking into account these three perspectives. We also show that a carefully-designed demonstration based on our findings can lead to substantial improvements over widely-used demonstration construction methods, e.g., improving BLEU-4, EM, and EM by at least 9.90%, 175.96%, and 50.81% on code summarization, bug fixing, and program synthesis, respectively.
The project we are interested in involves designing and developing a smartphone application for patients participating in a clinical trial about chronic respiratory diseases, as well as a desktop application for healt...
详细信息
ISBN:
(纸本)9798350319569
The project we are interested in involves designing and developing a smartphone application for patients participating in a clinical trial about chronic respiratory diseases, as well as a desktop application for healthcare professionals involved in monitoring the patients. This system serves a dual purpose: (i) encourage patients to follow multi-activity pathways and receive feedback;(ii) enable the care team to monitor patients' condition and notify them of milestones. In this article, we demonstrate how the main stakeholders (medical experts, physical activity specialists, nutritionists) were integrated into the requirements engineering phase, resulting in the establishment of textual specifications, UML models, and UPPAAL models. This approach has proven to be beneficial in terms of sharing knowledge, validating the telerehabilitation processes, and verifying their liveness and safety properties. Despite the stakeholders' lack of training in modelling and verification techniques, they greatly appreciated this approach.
The Internet of Things (IoT) bridges the physical and digital worlds by utilizing sensors, actuators, communication technologies, computing power, and data analytics to enable precise monitoring and control of the sur...
详细信息
Autonomous driving is the future development trend of the automotive industry, while autonomous vehicles mainly rely on interconnected systems and software that control their operation. System software vulnerabilities...
详细信息
Autonomous driving is the future development trend of the automotive industry, while autonomous vehicles mainly rely on interconnected systems and software that control their operation. System software vulnerabilities lead to serious safety hazards for vehicles. Therefore, automatic driving safety test is an important link to further improve the safety of autonomous vehicle. Fuzzing, as an automated vulnerability testing technology, exhibits outstanding vulnerability exploration capabilities when dealing with complex software systems. Aiming to explore the potential of fuzzing for widespread application in autonomous driving systems, this paper provides a systematic summary of widely used open-source fuzzing tools. Through an in-depth analysis of the characteristics of autonomous driving systems, the study identifies key challenges currently faced by research in this field, including: 1) difficulty in comprehensively considering input dimensions;2) challenges in uncovering issues related to multifunctional collaborative concurrency;3) mismatch of security issue categories. In response to these challenges, the research proposes corresponding recommendations, providing guidance for future related research.
—This paper focuses on the issue of information and knowledge management for master students in Chinese universities. According to some foreign learners’ statements, the information from official channels is fragmen...
详细信息
Almost five billion people now use the internet for Various purposes like education, research, banking, and health. It became a vital part of our day-to-day life but it also increases the security threat to multiple f...
详细信息
In recent years, the rapid development of deep neural networks and their application technologies has propelled autonomous driving systems (ADS) towards commercialisation. However, due to the high safety requirements ...
详细信息
ISBN:
(纸本)9783031808883;9783031808890
In recent years, the rapid development of deep neural networks and their application technologies has propelled autonomous driving systems (ADS) towards commercialisation. However, due to the high safety requirements of ADSs, ensuring their safety and reliability remains a critical challenge in softwareengineering. Existing testing methods focus on simple driving scenarios with few traffic participants, neglecting the impact of high traffic density on ADS driving performance. This paper presents an empirical study exploring how traffic density affects ADS behaviour. We developed a testing framework using two open-source ADSs to generate scenarios with varying traffic densities in a high-fidelity simulator. Our results indicate that changes in traffic density significantly affect ADS performance. Different traffic densities reveal various types of safety violations and help identify potential design flaws in ADSs. This study highlights the importance of considering traffic density in ADS testing and contributes to a better understanding of ADS performance under different traffic conditions.
Many studies have explored the methods of deriving thresholds of object-oriented (i.e. OO) metrics. Unsupervised methods are mainly based on the distributions of metric values, while supervised methods principally res...
详细信息
Many studies have explored the methods of deriving thresholds of object-oriented (i.e. OO) metrics. Unsupervised methods are mainly based on the distributions of metric values, while supervised methods principally rest on the relationships between metric values and defect-proneness of classes. The objective of this study is to empirically examine whether there are effective threshold values of OO metrics by analyzing existing threshold derivation methods with a large-scale meta-analysis. Based on five representative threshold derivation methods (i.e. VARL, ROC, BPP, MFM, and MGM) and 3268 releases from 65 Java projects, we first employ statistical meta-analysis and sensitivity analysis techniques to derive thresholds for 62 OO metrics on the training data. Then, we investigate the predictive performance of five candidate thresholds for each metric on the validation data to explore which of these candidate thresholds can be served as the threshold. Finally, we evaluate their predictive performance on the test data. The experimental results show that 26 of 62 metrics have the threshold effect and the derived thresholds by meta-analysis achieve promising results of GM values and significantly outperform almost all five representative (baseline) thresholds.
暂无评论