Patricia Arroba, Rajkumar Buyya, Román Cárdenas, José L. Risco‐Martín, José M. Moya
The advent of edge computing holds immense promise for advancing the digitization of society, ushering in critical applications that elevate the overall quality of life. Yet, the practical implementation of the edge paradigm proves more challenging than anticipated, encountering disruptions primarily due to the constraints of applying conventional cloud‐based strategies at the network's periphery. Increasingly influenced by sustainability commitments, industry regulations currently view edge computing as a potential threat, primarily due to the energy inefficiency of solutions situated in close proximity to data generation sources and the rising density of computing. This paper presents a proactive strategy to transform the perceived threat into an opportunity, steering the sustainable evolution of future edge infrastructures to make them both environmentally and economically competitive for accelerated adoption. The vision outlined addresses key challenges associated with edge deployment and operation, emphasizing energy efficiency, fault‐tolerant automation, and collaborative orchestration. The proposed approach integrates two‐phase immersion cooling, formal modeling, machine learning, and federated management to effectively harness heterogeneity, propelling the sustainability of edge computing. To substantiate the efficacy of this approach, the paper details initial efforts towards establishing the sustainability of an edge infrastructure designed for an Advanced Driver Assistance Systems application.
{"title":"Sustainable edge computing: Challenges and future directions","authors":"Patricia Arroba, Rajkumar Buyya, Román Cárdenas, José L. Risco‐Martín, José M. Moya","doi":"10.1002/spe.3340","DOIUrl":"https://doi.org/10.1002/spe.3340","url":null,"abstract":"The advent of edge computing holds immense promise for advancing the digitization of society, ushering in critical applications that elevate the overall quality of life. Yet, the practical implementation of the edge paradigm proves more challenging than anticipated, encountering disruptions primarily due to the constraints of applying conventional cloud‐based strategies at the network's periphery. Increasingly influenced by sustainability commitments, industry regulations currently view edge computing as a potential threat, primarily due to the energy inefficiency of solutions situated in close proximity to data generation sources and the rising density of computing. This paper presents a proactive strategy to transform the perceived threat into an opportunity, steering the sustainable evolution of future edge infrastructures to make them both environmentally and economically competitive for accelerated adoption. The vision outlined addresses key challenges associated with edge deployment and operation, emphasizing energy efficiency, fault‐tolerant automation, and collaborative orchestration. The proposed approach integrates two‐phase immersion cooling, formal modeling, machine learning, and federated management to effectively harness heterogeneity, propelling the sustainability of edge computing. To substantiate the efficacy of this approach, the paper details initial efforts towards establishing the sustainability of an edge infrastructure designed for an Advanced Driver Assistance Systems application.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140932019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mansi Sahi, Nitin Auluck, Akramul Azim, Md Al Maruf
The Internet of Things (IoT) has gained widespread importance in recent time. However, the related issues of security and privacy persist in such IoT networks. Owing to device limitations in terms of computational power and storage, standard protection approaches cannot be deployed. In this article, we propose a lightweight distributed intrusion detection system (IDS) framework, called FCAFE‐BNET (Fog based Context Aware Feature Extraction using BranchyNET). The proposed FCAFE‐BNET approach considers versatile network conditions, such as varying bandwidths and data loads, while allocating inference tasks to cloud/edge resources. FCAFE‐BNET is able to adjust to dynamic network conditions. This can be advantageous for applications with particular quality of service requirements, such as video streaming or real‐time communication, ensuring a steady and reliable performance. Early exit deep neural networks (DNNs) have been employed for faster inference generation at the edge. Often, the weights that the model learns in the initial layer may be sufficiently qualified to perform the required classification tasks. Instead of using subsequent layers of DNNs for generating the inference, we have employed the early‐exit mechanism in the DNNs. Such DNNs help to predict a wide range of testing samples through these early‐exit branches, upon crossing a threshold. This method maintains the confidence values corresponding to the inference. Employing this approach, we achieved a faster inference, with significantly high accuracy. Comparative studies exploit manual feature extraction techniques, that can potentially overlook certain valuable patterns, thus degrading classification performance. The proposed framework converts textual/tabular data into 2‐D images, allowing the DNN model to autonomously learns its own features. This conversion scheme facilitated the identification of various intrusion types, ranging from 5 to 14 different categories. FCAFE‐BNET works for both network‐based and host‐based IDS: NIDS and HIDS. Our experiments demonstrate that, in comparison with recent approaches, FCAFE‐BNET achieves a 39.12%–50.23% reduction in the total inference time on benchmark real‐world datasets, such as: NSL‐KDD, UNSW‐NB 15, ToN_IoT, and ADFA_LD.
{"title":"Dynamic hierarchical intrusion detection task offloading in IoT edge networks","authors":"Mansi Sahi, Nitin Auluck, Akramul Azim, Md Al Maruf","doi":"10.1002/spe.3338","DOIUrl":"https://doi.org/10.1002/spe.3338","url":null,"abstract":"The Internet of Things (IoT) has gained widespread importance in recent time. However, the related issues of security and privacy persist in such IoT networks. Owing to device limitations in terms of computational power and storage, standard protection approaches cannot be deployed. In this article, we propose a lightweight distributed intrusion detection system (IDS) framework, called FCAFE‐BNET (<jats:styled-content>F</jats:styled-content>og based <jats:styled-content>C</jats:styled-content>ontext <jats:styled-content>A</jats:styled-content>ware <jats:styled-content>F</jats:styled-content>eature <jats:styled-content>E</jats:styled-content>xtraction using <jats:styled-content>B</jats:styled-content>ranchy<jats:styled-content>NET</jats:styled-content>). The proposed FCAFE‐BNET approach considers versatile network conditions, such as varying bandwidths and data loads, while allocating inference tasks to cloud/edge resources. FCAFE‐BNET is able to adjust to dynamic network conditions. This can be advantageous for applications with particular quality of service requirements, such as video streaming or real‐time communication, ensuring a steady and reliable performance. Early exit deep neural networks (DNNs) have been employed for faster inference generation at the edge. Often, the weights that the model learns in the initial layer may be sufficiently qualified to perform the required classification tasks. Instead of using subsequent layers of DNNs for generating the inference, we have employed the early‐exit mechanism in the DNNs. Such DNNs help to predict a wide range of testing samples through these early‐exit branches, upon crossing a threshold. This method maintains the confidence values corresponding to the inference. Employing this approach, we achieved a faster inference, with significantly high accuracy. Comparative studies exploit manual feature extraction techniques, that can potentially overlook certain valuable patterns, thus degrading classification performance. The proposed framework converts textual/tabular data into 2‐D images, allowing the DNN model to autonomously learns its own features. This conversion scheme facilitated the identification of various intrusion types, ranging from 5 to 14 different categories. FCAFE‐BNET works for both network‐based and host‐based IDS: NIDS and HIDS. Our experiments demonstrate that, in comparison with recent approaches, FCAFE‐BNET achieves a 39.12%–50.23% reduction in the total inference time on benchmark real‐world datasets, such as: NSL‐KDD, UNSW‐NB 15, ToN_IoT, and ADFA_LD.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140831487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arsene Indamutsa, Juri Di Rocco, Lissette Almonte, Davide Di Ruscio, A. Pierantonio
As model‐driven engineering gains traction and poses as the new paradigm for software engineering, it raises a need for efficient approaches and tools to manage, discover, and retrieve relevant modeling artifacts. Hence, industry and academia are conceiving effective ways to store, search, and retrieve heterogeneous model artifacts that employ advanced discovery mechanisms. This paper presents MDEForge‐Search, a novel approach to discovering heterogeneous model artifacts over MDEForge, a distributed cloud‐based model repository. We designed advanced discovery mechanisms that retrieve heterogeneous artifacts within their context (megamodel) and reuse them across model management services. In addition, a domain‐specific approach has been proposed to formulate queries in terms of keywords, search tags, conditional operators, quality model assessment services and a transformation chain discoverer. Finally, the applicability of our approach was assessed in a recommender system modeling framework, which, thanks to the operated integration, can rely on the availability of more than 5000 model artifacts currently persisted in our cloud‐based model repository.
{"title":"Advanced discovery mechanisms in model repositories","authors":"Arsene Indamutsa, Juri Di Rocco, Lissette Almonte, Davide Di Ruscio, A. Pierantonio","doi":"10.1002/spe.3332","DOIUrl":"https://doi.org/10.1002/spe.3332","url":null,"abstract":"As model‐driven engineering gains traction and poses as the new paradigm for software engineering, it raises a need for efficient approaches and tools to manage, discover, and retrieve relevant modeling artifacts. Hence, industry and academia are conceiving effective ways to store, search, and retrieve heterogeneous model artifacts that employ advanced discovery mechanisms. This paper presents MDEForge‐Search, a novel approach to discovering heterogeneous model artifacts over MDEForge, a distributed cloud‐based model repository. We designed advanced discovery mechanisms that retrieve heterogeneous artifacts within their context (megamodel) and reuse them across model management services. In addition, a domain‐specific approach has been proposed to formulate queries in terms of keywords, search tags, conditional operators, quality model assessment services and a transformation chain discoverer. Finally, the applicability of our approach was assessed in a recommender system modeling framework, which, thanks to the operated integration, can rely on the availability of more than 5000 model artifacts currently persisted in our cloud‐based model repository.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140657455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deepak Puthal, Amit Kumar Mishra, Sambit Kumar Mishra
{"title":"Special issue on collaborative edge computing for secure and scalable Internet of Things","authors":"Deepak Puthal, Amit Kumar Mishra, Sambit Kumar Mishra","doi":"10.1002/spe.3337","DOIUrl":"https://doi.org/10.1002/spe.3337","url":null,"abstract":"","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140612290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Giuseppe Bisicchia, Stefano Forti, Ernesto Pimentel, Antonio Brogi
The problem of managing multi‐service applications on top of Cloud‐Edge networks in a quality of service (QoS)‐aware manner has been thoroughly studied in recent years from a decision‐making perspective. However, only a few studies addressed the problem of actively enforcing such decisions while orchestrating multi‐service applications and considering infrastructure and application variations. In this article, we propose a next‐gen orchestrator prototype based on Docker to achieve the continuous and QoS‐compliant management of multiservice applications on top of geographically distributed Cloud‐Edge resources, in continuity with CI/CD pipelines and infrastructure monitoring tools. Finally, we assess our proposal over a geographically distributed testbed across Italy.
{"title":"Continuous QoS‐compliant orchestration in the Cloud‐Edge continuum","authors":"Giuseppe Bisicchia, Stefano Forti, Ernesto Pimentel, Antonio Brogi","doi":"10.1002/spe.3334","DOIUrl":"https://doi.org/10.1002/spe.3334","url":null,"abstract":"The problem of managing multi‐service applications on top of Cloud‐Edge networks in a quality of service (QoS)‐aware manner has been thoroughly studied in recent years from a decision‐making perspective. However, only a few studies addressed the problem of actively enforcing such decisions while orchestrating multi‐service applications and considering infrastructure and application variations. In this article, we propose a next‐gen orchestrator prototype based on Docker to achieve the continuous and QoS‐compliant management of multiservice applications on top of geographically distributed Cloud‐Edge resources, in continuity with CI/CD pipelines and infrastructure monitoring tools. Finally, we assess our proposal over a geographically distributed testbed across Italy.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140584783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The smart healthcare system (SHS), a significant medical domain underpinning the Internet of Things (IoT), which collects and analyzes health data from many sources to provide better medical treatment. The smart healthcare system is a combination of hardware and software used in the medical care field, providing remote diagnosis and treatment via a patient‐based health data‐sharing system. To increase security, a large variety of authenticated techniques have been developed over the past several decades, most of which are based on conventional number‐theoretic assumptions such as discrete logarithms and integer factorization problems. However, Shor's method is capable of solving number‐theory‐based problems. As a result, Shor's technique might be used to resolve challenging number theory problems on a quantum computer effectively. Therefore, this article presents blockchain‐based healthcare record solutions with lattice RLWE‐based key exchange protocol using a smart card. Blockchain applications may correctly detect errors, including those that are risky, in the medical industry. It can also improve the efficiency, security, and transparency of transferring medical data throughout the healthcare protocol. The formal security of this protocol is shown under the ROM (random oracle model), and the informal security is also given in this article against well‐known attacks. The presented protocol outperforms related earlier mechanisms in terms of communication and computational cost overheads, according to the performance study.
{"title":"Post‐quantum attack resilience blockchain‐assisted data authentication protocol for smart healthcare system","authors":"Lacchita Soni, Harish Chandra, Daya Sagar Gupta","doi":"10.1002/spe.3336","DOIUrl":"https://doi.org/10.1002/spe.3336","url":null,"abstract":"The smart healthcare system (SHS), a significant medical domain underpinning the Internet of Things (IoT), which collects and analyzes health data from many sources to provide better medical treatment. The smart healthcare system is a combination of hardware and software used in the medical care field, providing remote diagnosis and treatment via a patient‐based health data‐sharing system. To increase security, a large variety of authenticated techniques have been developed over the past several decades, most of which are based on conventional number‐theoretic assumptions such as discrete logarithms and integer factorization problems. However, Shor's method is capable of solving number‐theory‐based problems. As a result, Shor's technique might be used to resolve challenging number theory problems on a quantum computer effectively. Therefore, this article presents blockchain‐based healthcare record solutions with lattice RLWE‐based key exchange protocol using a smart card. Blockchain applications may correctly detect errors, including those that are risky, in the medical industry. It can also improve the efficiency, security, and transparency of transferring medical data throughout the healthcare protocol. The formal security of this protocol is shown under the ROM (random oracle model), and the informal security is also given in this article against well‐known attacks. The presented protocol outperforms related earlier mechanisms in terms of communication and computational cost overheads, according to the performance study.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140584654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We present new algorithms for exact string matching of long patterns. Our algorithms read ‐grams at constant distances and are variations of the simplified BNDM algorithm. We demonstrate the competitiveness of our solutions through practical experiments. Many of our algorithms were faster than previous methods for English and DNA patterns between 400 and 50,000 in length. Our algorithms were still better when the preprocessing time was taken into account or when the patterns were taken from a different text of the same type.
我们提出了长模式精确字符串匹配的新算法。我们的算法以恒定距离读取字符串，是简化 BNDM 算法的变体。我们通过实际实验证明了我们的解决方案的竞争力。对于长度在 400 到 50,000 之间的英语和 DNA 模式，我们的许多算法都比以前的方法更快。如果将预处理时间考虑在内，或者图案取自同一类型的不同文本，我们的算法仍然更胜一筹。
{"title":"Searching long patterns with BNDM","authors":"Jorma Tarhio","doi":"10.1002/spe.3335","DOIUrl":"https://doi.org/10.1002/spe.3335","url":null,"abstract":"We present new algorithms for exact string matching of long patterns. Our algorithms read ‐grams at constant distances and are variations of the simplified BNDM algorithm. We demonstrate the competitiveness of our solutions through practical experiments. Many of our algorithms were faster than previous methods for English and DNA patterns between 400 and 50,000 in length. Our algorithms were still better when the preprocessing time was taken into account or when the patterns were taken from a different text of the same type.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140584747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luka Fürst, Tomaž Hovelja, Marko Poženel, Damjan Vavpotič
Effort estimation is an important activity in agile software development. The goal of the presented study was to determine the influence of individual competence on software development effort estimation. In particular, we measured both the accuracy of effort estimation and the duration of the estimation process itself, both for three different estimation methods. The subjects of our study were teams of students of a graduate‐level software engineering course at the University of Ljubljana, Faculty of Computer and Information Science. Based on the grades that individual students attained in their undergraduate study, we classified each team as “high‐competence” or “low‐competence” and additionally as “heterogeneous” or “homogeneous” (the criterion here being the variance of the members' average grades). We found out that there was no significant difference in effort estimation accuracy neither between high‐competence and low‐competence teams nor between heterogeneous and homogeneous teams, regardless of which estimation method was used. However, high‐competence teams spent significantly less time on effort estimation than low‐competence ones. Likewise, for two of the employed estimation methods, heterogeneous teams completed effort estimation in a significantly shorter time than homogeneous teams. These results might benefit both academic and professional community.
{"title":"Impact of competence on agile effort estimation in academic setting","authors":"Luka Fürst, Tomaž Hovelja, Marko Poženel, Damjan Vavpotič","doi":"10.1002/spe.3333","DOIUrl":"https://doi.org/10.1002/spe.3333","url":null,"abstract":"Effort estimation is an important activity in agile software development. The goal of the presented study was to determine the influence of individual competence on software development effort estimation. In particular, we measured both the accuracy of effort estimation and the duration of the estimation process itself, both for three different estimation methods. The subjects of our study were teams of students of a graduate‐level software engineering course at the University of Ljubljana, Faculty of Computer and Information Science. Based on the grades that individual students attained in their undergraduate study, we classified each team as “high‐competence” or “low‐competence” and additionally as “heterogeneous” or “homogeneous” (the criterion here being the variance of the members' average grades). We found out that there was no significant difference in effort estimation accuracy neither between high‐competence and low‐competence teams nor between heterogeneous and homogeneous teams, regardless of which estimation method was used. However, high‐competence teams spent significantly less time on effort estimation than low‐competence ones. Likewise, for two of the employed estimation methods, heterogeneous teams completed effort estimation in a significantly shorter time than homogeneous teams. These results might benefit both academic and professional community.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140584782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Quantum computing resources are predominantly accessible through cloud services, with a potential future shift to edge networks. This paradigm and the increasing global interest in quantum computing have amplified the need for efficient, adaptable resource management strategies and service models for quantum systems. However, many limitations in the quantum resources' quantity, quality, availability, and cost pose significant challenges for conducting research in practical environments. To address these challenges, we proposed iQuantum, a holistic and lightweight discrete‐event simulation toolkit uniquely tailored to model hybrid quantum computing environments. We also present a detailed system model for prototyping and problem formulation in quantum resource management. Through rigorous empirical validation and evaluations using large‐scale quantum workload datasets, we demonstrate the flexibility and applicability of our toolkit in various use cases. iQuantum provides a versatile environment for designing and evaluating quantum resource management policies such as quantum task scheduling, backend selection, hybrid task offloading, and orchestration in the quantum cloud‐edge continuum. Our work endeavors to create substantial contributions to quantum computing modeling and simulation, empowering the creation of future resource management strategies and quantum computing's broader applications.
{"title":"iQuantum: A toolkit for modeling and simulation of quantum computing environments","authors":"H. T. Nguyen, Muhammad Usman, R. Buyya","doi":"10.1002/spe.3331","DOIUrl":"https://doi.org/10.1002/spe.3331","url":null,"abstract":"Quantum computing resources are predominantly accessible through cloud services, with a potential future shift to edge networks. This paradigm and the increasing global interest in quantum computing have amplified the need for efficient, adaptable resource management strategies and service models for quantum systems. However, many limitations in the quantum resources' quantity, quality, availability, and cost pose significant challenges for conducting research in practical environments. To address these challenges, we proposed iQuantum, a holistic and lightweight discrete‐event simulation toolkit uniquely tailored to model hybrid quantum computing environments. We also present a detailed system model for prototyping and problem formulation in quantum resource management. Through rigorous empirical validation and evaluations using large‐scale quantum workload datasets, we demonstrate the flexibility and applicability of our toolkit in various use cases. iQuantum provides a versatile environment for designing and evaluating quantum resource management policies such as quantum task scheduling, backend selection, hybrid task offloading, and orchestration in the quantum cloud‐edge continuum. Our work endeavors to create substantial contributions to quantum computing modeling and simulation, empowering the creation of future resource management strategies and quantum computing's broader applications.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140364928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, we evaluate the programming capabilities of OpenAI's GPT‐3.5 and GPT‐4 models using Swift‐based exam questions from a third‐year university course. The results indicate that both GPT models generally outperform the average student score, yet they do not consistently exceed the performance of the top students. This comparison highlights areas where the GPT models excel and where they fall short, providing a nuanced view of their current programming proficiency. The study also reveals surprising instances where GPT‐3.5 outperforms GPT‐4, suggesting complex variations in AI model capabilities. By providing a clear benchmark of GPT's programming skills in an academic context, our research contributes valuable insights for future advancements in AI programming education and underscores the need for continued development to fully realize AI's potential in educational settings.
{"title":"Evaluate Chat‐GPT's programming capability in Swift through real university exam questions","authors":"Zizhuo Zhang, Lian Wen, Yanfei Jiang, Yongli Liu","doi":"10.1002/spe.3330","DOIUrl":"https://doi.org/10.1002/spe.3330","url":null,"abstract":"In this study, we evaluate the programming capabilities of OpenAI's GPT‐3.5 and GPT‐4 models using Swift‐based exam questions from a third‐year university course. The results indicate that both GPT models generally outperform the average student score, yet they do not consistently exceed the performance of the top students. This comparison highlights areas where the GPT models excel and where they fall short, providing a nuanced view of their current programming proficiency. The study also reveals surprising instances where GPT‐3.5 outperforms GPT‐4, suggesting complex variations in AI model capabilities. By providing a clear benchmark of GPT's programming skills in an academic context, our research contributes valuable insights for future advancements in AI programming education and underscores the need for continued development to fully realize AI's potential in educational settings.","PeriodicalId":21899,"journal":{"name":"Software: Practice and Experience","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140203683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：