An innovative methodology based on genetic algorithms for array antenna pattern optimization is proposed. the methodology contains two steps: Firstly, two adjacent array elements are bonded by assuming them with ident...
详细信息
Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating high-quality and reliable code remains a formidable task b...
详细信息
ISBN:
(纸本)9798350329964
Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating high-quality and reliable code remains a formidable task because of LLMs' lack of good programming practice, especially in exception handling. In this paper, we first conduct an empirical study and summarize three crucial challenges of LLMs in exception handling, i.e., incomplete exception handling, incorrect exception handling and abuse of try-catch. We then try prompts with different granularities to address such challenges, finding fine-grained knowledge-driven prompts works best. Based on our empirical study, we propose a novel knowledge-driven Prompt Chaining-based code generation approach, name KPC, which decomposes code generation into an AI chain with iterative check-rewrite steps and chains fine-grained knowledge-driven prompts to assist LLMs in considering exception-handling specifications. We evaluate our KPC-based approach with 3,079 code generation tasks extracted from the Java official API documentation. Extensive experimental results demonstrate that the KPC-based approach has considerable potential to ameliorate the quality of code generated by LLMs. It achieves this through proficiently managing exceptions and obtaining remarkable enhancements of 109.86% and 578.57% with static evaluation methods, as well as a reduction of 18 runtime bugs in the sampled dataset with dynamic validation.
Security requirements engineering is a manual and error-prone activity that is often neglected due to the knowledge gap between cybersecurity professionals and software requirements engineers. In this paper, we aim to...
详细信息
ISBN:
(纸本)9781665457019
Security requirements engineering is a manual and error-prone activity that is often neglected due to the knowledge gap between cybersecurity professionals and software requirements engineers. In this paper, we aim to automate the process of recommending and synthesizing security requirements specifications and therefore supporting requirements engineers in soliciting and specifying security requirements. We investigate the use of Relational Generative Adversarial Networks (GANs) in automatically synthesizing security requirements specifications. We evaluate our approach using a real case study of the Court Case Management System (CCMS) developed for the Indiana Supreme Court's Division of State Court Administration. We present an approach based on RelGAN to generate security requirements specifications for the CCMS. We show that RelGAN is practical for synthesizing security requirements specifications as indicated by subject matter experts. Based on this study, we demonstrate promising results for the use of GANs in the software requirements synthesis domain. We also provide a baseline for synthesizing requirements, highlight limitations and weaknesses of RelGAN and define opportunities for further investigations.
Permanent magnet synchronous motors (PMSM) have received intensive attention in recent years as one of the primary drivers for alternative fuel vehicles. the direct torque control (DTC) approach is used in permanent m...
详细信息
To deal with urban distribution challenges, companies are redesigning their distribution networks. this paper studies a two-echelon vehicle routing problem, one of the most employed models, with a heterogeneous fleet ...
详细信息
the proceedings contain 57 papers. the special focus in this conference is on software Technologies. the topics include: Product-Line engineering for Smart Manufacturing: A Systematic Mapping Study on Security Concept...
ISBN:
(纸本)9789897587061
the proceedings contain 57 papers. the special focus in this conference is on software Technologies. the topics include: Product-Line engineering for Smart Manufacturing: A Systematic Mapping Study on Security Concepts;diagnosis Automation Using Similarity Analysis: Application to Industrial Systems;improving Robustness of Satellite Image Processing Using Principal Component Analysis for Explainability;multimodal Approach Based on Autistic Child Behavior Analysis for Meltdown Crisis Detection;Towards Accurate Cervical Cancer Detection: Leveraging Two-Stage CNNs for Pap Smear Analysis;feature Extraction, Learning and Selection in Support of Patch Correctness Assessment;Accurate Recommendation of EV Charging Stations Driven by Availability Status Prediction;RLHR: A Framework for Driving Dynamically Adaptable Questionnaires and Profiling People Using Reinforcement Learning;optimizing Intensive Database Tasks through Caching Proxy Mechanisms;An Evaluation of Risk Management Standards and Frameworks for Assuring Data Security of Medical Device software AI Models;a Systematic Mapping Study on Impact Analysis;HybridCRS-TMS: Integrating Collaborative Recommender System and TOPSIS for Optimal Transport Mode Selection;automated Generation of Web Application Front-end Components from User Interface Mockups;a Webcam Artificial Intelligence-Based Gaze-Tracking Algorithm;an Empirical Examination of the Technical Aspects of Data Sovereignty;asmDocGen: Generating Functional Natural Language Descriptions for Assembly Code;Integrating a LLaMa-based Chatbot with Augmented Retrieval Generation as a Complementary Educational Tool for High School and College Students;artificial Intelligence-Based Detection and Prediction of Giant African Snail (Lissachatina Fulica) Infestation in the Galapagos Islands;six-Layer Industrial Architecture Applied to Predictive Maintenance;Smart Blockchain-Based Information Flow Control for SOA;logging Hypercalls to Learn About the Behavior of Hyper-V.
Removing ground echoes from weather radar images is a topic of great importance due to their significant impact on the accuracy of processed data. To address this challenge, we aim to develop methods that effectively ...
详细信息
A software product line is a set of products that share a set of software features and assets, which satisfy the specific needs of one or more target markets. One common artefact of software product line engineering i...
详细信息
the Team Orienteering Problem with Time Windows ( TOPTW) is a typical variant of the Orienteering Problem (OP) that each node can only provide one time service in a predefined time window, its objective is to maximize...
详细信息
ISBN:
(纸本)9798350386783;9798350386776
the Team Orienteering Problem with Time Windows ( TOPTW) is a typical variant of the Orienteering Problem (OP) that each node can only provide one time service in a predefined time window, its objective is to maximize the total score of visiting nodes with a given number of paths. In this study we propose an improved ALNS(adaptive large neighborhood search) algorithm to solve the TOPTW problem, which clusters nodes according to their features to construct the initial solution, and design knowledge- based removal and repair operators to optimize solutions. To fully evaluate the proposed algorithm, some typical benchmark datasets are taken as the test instance suite and several state-of-the-art algorithms are chosen to compare withthe proposed algorithm. Experimental results show our algorithm has satisfactory accuracy and far better performance.
Logical thinking is essential for organizing one's thoughts and fostering the generation of diverse and innovative ideas. However, acquiring logical thinking skills is not straightforward. this is because individu...
详细信息
暂无评论