Zihan Zhang;Alina Gorbunova;Keunho Rhew;Jianjun Shi
Prognostics for electronic packages is an evolving field critical to predicting the reliability and lifespan of electronic systems. This article proposes a novel “structure-aware system-level (SASL)” approach, addressing the limitations of traditional methods that treat components or subsystems as isolated black boxes. SASL examines how individual component degradation propagates, interacts within the package structure, and collectively determines the system's lifetime. The article reviews three key areas: component-level prognostics, package structure, and system-level analysis, offering guidance for future research. It advocates interdisciplinary collaboration to develop practical and interpretable prognostics methods, driving innovation in industries reliant on complex electronic systems.
{"title":"A Review of Prognostics Methods for Electronic Packages: From a Structure-Aware System-Level Perspective","authors":"Zihan Zhang;Alina Gorbunova;Keunho Rhew;Jianjun Shi","doi":"10.1109/TR.2025.3558449","DOIUrl":"https://doi.org/10.1109/TR.2025.3558449","url":null,"abstract":"Prognostics for electronic packages is an evolving field critical to predicting the reliability and lifespan of electronic systems. This article proposes a novel “structure-aware system-level (SASL)” approach, addressing the limitations of traditional methods that treat components or subsystems as isolated black boxes. SASL examines how individual component degradation propagates, interacts within the package structure, and collectively determines the system's lifetime. The article reviews three key areas: component-level prognostics, package structure, and system-level analysis, offering guidance for future research. It advocates interdisciplinary collaboration to develop practical and interpretable prognostics methods, driving innovation in industries reliant on complex electronic systems.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"4116-4130"},"PeriodicalIF":5.7,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yueming Wu;Wenqi Suo;Siyue Feng;Cong Wu;Deqing Zou;Hai Jin
Code clone detection is intended to identify functionally similar code fragments, a matter of escalating significance in contemporary software engineering. Numerous methodologies have been proffered for the detection of code clones, among which graph-based approaches exhibit efficacy in addressing semantic code clones. However, they all only consider the feature extraction of a single sample and ignore the semantic connection between different samples, resulting in the detection effect being unsatisfactory. Simultaneously, the majority of existing methods can only ascertain the presence of clones, lacking the capability to provide nuanced insights into which lines of code exhibit greater similarity. In this article, we advocate a novel PDG-based semantic clone detection method, namely, Keybor which can locate specific cloned lines of code by providing a fine-grained analysis of clone pairs. The highlight of the approach is to consider keywords as a bridge to connect PDG nodes of the target program to retain more semantic information about the functional code. To examine the effectiveness of Keybor, we assess it on a widely used BigCloneBench dataset. Experimental results indicate that Keybor is superior to 14 advanced code clone detection tools (i.e., CCAligner, SourcererCC, Siamese, NIL, NiCad, LVMapper, CCFinder, CloneWorks, Oreo, Deckard, CCGraph, Code2Img, GPT-3.5-turbo, and GPT-4).
{"title":"Fine-Grained Code Clone Detection by Keywords-Based Connection of Program Dependency Graph","authors":"Yueming Wu;Wenqi Suo;Siyue Feng;Cong Wu;Deqing Zou;Hai Jin","doi":"10.1109/TR.2025.3550747","DOIUrl":"https://doi.org/10.1109/TR.2025.3550747","url":null,"abstract":"Code clone detection is intended to identify functionally similar code fragments, a matter of escalating significance in contemporary software engineering. Numerous methodologies have been proffered for the detection of code clones, among which graph-based approaches exhibit efficacy in addressing semantic code clones. However, they all only consider the feature extraction of a single sample and ignore the semantic connection between different samples, resulting in the detection effect being unsatisfactory. Simultaneously, the majority of existing methods can only ascertain the presence of clones, lacking the capability to provide nuanced insights into which lines of code exhibit greater similarity. In this article, we advocate a novel PDG-based semantic clone detection method, namely, <italic>Keybor</i> which can locate specific cloned lines of code by providing a fine-grained analysis of clone pairs. The highlight of the approach is to consider keywords as a bridge to connect PDG nodes of the target program to retain more semantic information about the functional code. To examine the effectiveness of <italic>Keybor</i>, we assess it on a widely used <italic>BigCloneBench</i> dataset. Experimental results indicate that <italic>Keybor</i> is superior to 14 advanced code clone detection tools (i.e., <italic>CCAligner</i>, <italic>SourcererCC</i>, <italic>Siamese</i>, <italic>NIL</i>, <italic>NiCad</i>, <italic>LVMapper</i>, <italic>CCFinder</i>, <italic>CloneWorks</i>, <italic>Oreo</i>, <italic>Deckard</i>, <italic>CCGraph</i>, <italic>Code2Img</i>, <italic>GPT-3.5-turbo</i>, and <italic>GPT-4</i>).","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3427-3441"},"PeriodicalIF":5.7,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The continuous evolution of semiconductor packaging demands highly reliable redistribution layer (RDL) architectures to support next-generation electronic systems. However, ensuring RDL reliability remains a formidable challenge due to multiphysics interactions, including mechanical stress-induced fatigue, thermal expansion mismatches, and high-frequency signal integrity degradation. This article presents a comprehensive review of RDL reliability across mechanical, thermal, and electrical domains, identifying key failure mechanisms and research gaps. To address these challenges, we introduce an AI-driven optimization framework that integrates machine learning–assisted chip layout optimization, adaptive thermal management, and real-time signal integrity enhancement. Utilizing deep reinforcement learning and graph neural networks, this study demonstrates how AI can dynamically optimize RDL routing, enhance power distribution networks, and mitigate localized heating effects. Furthermore, we explore the integration of AI-driven predictive modeling into electronic design automation tools, enabling real-time multiphysics co-optimization of RDL architectures. This study establishes a structured framework for future research, bridging the gap between theoretical modeling and practical fabrication. By incorporating AI-assisted design methodologies, next-generation RDL architectures can achieve superior reliability, enhanced performance, and improved scalability, supporting applications in 5G communications, high-performance computing, and heterogeneous integration technologies.
{"title":"Reliability Study of Critical Structural Redistribution Layers in Advanced Packaging: A Review","authors":"Jiajie Jin;Peisheng Liu;Yaohui Deng;Zhao Zhang","doi":"10.1109/TR.2025.3556255","DOIUrl":"https://doi.org/10.1109/TR.2025.3556255","url":null,"abstract":"The continuous evolution of semiconductor packaging demands highly reliable redistribution layer (RDL) architectures to support next-generation electronic systems. However, ensuring RDL reliability remains a formidable challenge due to multiphysics interactions, including mechanical stress-induced fatigue, thermal expansion mismatches, and high-frequency signal integrity degradation. This article presents a comprehensive review of RDL reliability across mechanical, thermal, and electrical domains, identifying key failure mechanisms and research gaps. To address these challenges, we introduce an AI-driven optimization framework that integrates machine learning–assisted chip layout optimization, adaptive thermal management, and real-time signal integrity enhancement. Utilizing deep reinforcement learning and graph neural networks, this study demonstrates how AI can dynamically optimize RDL routing, enhance power distribution networks, and mitigate localized heating effects. Furthermore, we explore the integration of AI-driven predictive modeling into electronic design automation tools, enabling real-time multiphysics co-optimization of RDL architectures. This study establishes a structured framework for future research, bridging the gap between theoretical modeling and practical fabrication. By incorporating AI-assisted design methodologies, next-generation RDL architectures can achieve superior reliability, enhanced performance, and improved scalability, supporting applications in 5G communications, high-performance computing, and heterogeneous integration technologies.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3371-3382"},"PeriodicalIF":5.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the application and rapid development of high-performance computing and cloud computing technology, the scale of the interconnection network has appeared to grow exponentially. Network attacks have become increasingly sophisticated and stealthy. To reach a high reliable network system, widespread attention has been paid to fault diagnosis. In this article, we put forward a reliable and adaptive self-diagnosis strategy, the $h$-extra $r$-component conditional diagnosability, denoted by $ct_{r}^{h}(G)$. Then, we provide a theoretical derivation to characterize the $h$-extra $r$-component conditional diagnosability of bubble sort networks $B_{n}$ under the PMC model. Furthermore, we develop a fast and adaptive fault self-diagnosis algorithm FAFD-PMC to detect all faulty units. Extensive experiments are implemented and applied to synthetic networks and real networks in terms of accuracy (ACCR), true negative rate, false positive rate, recall, and precision, which demonstrates the ACCR/efficiency of our algorithm.
{"title":"A Novel Adaptive System-Level Fault Self-Diagnosis Algorithm and Its Applications","authors":"Fuxing Liao;Jiafei Liu;Chia-Wei Lee;Sun-Yuan Hsieh;Jingli Wu","doi":"10.1109/TR.2025.3553903","DOIUrl":"https://doi.org/10.1109/TR.2025.3553903","url":null,"abstract":"With the application and rapid development of high-performance computing and cloud computing technology, the scale of the interconnection network has appeared to grow exponentially. Network attacks have become increasingly sophisticated and stealthy. To reach a high reliable network system, widespread attention has been paid to fault diagnosis. In this article, we put forward a reliable and adaptive self-diagnosis strategy, the <inline-formula><tex-math>$h$</tex-math></inline-formula>-extra <inline-formula><tex-math>$r$</tex-math></inline-formula>-component conditional diagnosability, denoted by <inline-formula><tex-math>$ct_{r}^{h}(G)$</tex-math></inline-formula>. Then, we provide a theoretical derivation to characterize the <inline-formula><tex-math>$h$</tex-math></inline-formula>-extra <inline-formula><tex-math>$r$</tex-math></inline-formula>-component conditional diagnosability of bubble sort networks <inline-formula><tex-math>$B_{n}$</tex-math></inline-formula> under the PMC model. Furthermore, we develop a fast and adaptive fault self-diagnosis algorithm FAFD-PMC to detect all faulty units. Extensive experiments are implemented and applied to synthetic networks and real networks in terms of accuracy (ACCR), true negative rate, false positive rate, recall, and precision, which demonstrates the ACCR/efficiency of our algorithm.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"4294-4305"},"PeriodicalIF":5.7,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
High-level synthesis (HLS) tools have been widely used in field-programmable gate array (FPGA) design to convert C/C++ code to hardware description language code. Unfortunately, HLS tools are susceptible to bugs, which can introduce serious vulnerabilities in FPGA products, leading to substantial losses. However, the characteristics of these bugs (e.g., root causes and bug-prone stages) have never been systematically studied, which significantly hinders developers from effectively handling HLS tool bugs. To this end, we conduct the first empirical study to uncover HLS tool bug characteristics. We collect 349 bugs of a widely used HLS tool, namely Bambu. We study the root causes, buggy stages, and bug fixes of these bugs by applying a multiperson collaboration method. Finally, 13 valuable findings are summarized. We find 14 categories of root causes in Bambu bugs; most bugs (22.1%) are caused by incorrect implementation of IR processing; the front end of Bambu is more bug-prone; to fix these bugs, 2.27 files and 80.19 lines of code need to be modified on average. We also present the insights gained from 95 Vitis HLS bugs. From these findings, we suggest that developers could use an on-the-fly code generator configuration method to generate suitable testing programs for HLS tool bug detection and apply large language models to assist in fixing HLS tool bugs.
{"title":"Insights From Bugs in FPGA High-Level Synthesis Tools: An Empirical Study of Bambu Bugs","authors":"Zun Wang;He Jiang;Xiaochen Li;Shikai Guo;Xu Zhao;Yi Zhang","doi":"10.1109/TR.2025.3547739","DOIUrl":"https://doi.org/10.1109/TR.2025.3547739","url":null,"abstract":"High-level synthesis (HLS) tools have been widely used in field-programmable gate array (FPGA) design to convert C/C++ code to hardware description language code. Unfortunately, HLS tools are susceptible to bugs, which can introduce serious vulnerabilities in FPGA products, leading to substantial losses. However, the characteristics of these bugs (e.g., root causes and bug-prone stages) have never been systematically studied, which significantly hinders developers from effectively handling HLS tool bugs. To this end, we conduct the first empirical study to uncover HLS tool bug characteristics. We collect 349 bugs of a widely used HLS tool, namely Bambu. We study the root causes, buggy stages, and bug fixes of these bugs by applying a multiperson collaboration method. Finally, 13 valuable findings are summarized. We find 14 categories of root causes in Bambu bugs; most bugs (22.1%) are caused by incorrect implementation of IR processing; the front end of Bambu is more bug-prone; to fix these bugs, 2.27 files and 80.19 lines of code need to be modified on average. We also present the insights gained from 95 Vitis HLS bugs. From these findings, we suggest that developers could use an on-the-fly code generator configuration method to generate suitable testing programs for HLS tool bug detection and apply large language models to assist in fixing HLS tool bugs.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3341-3355"},"PeriodicalIF":5.7,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Eldor Abdukhamidov;Mohammed Abuhamad;Simon S. Woo;Eric Chan-Tin;Tamer Abuhmed
Deep neural network (DNN) models are susceptible to adversarial samples in white-box and opaqueenvironments. Although previous studies have shown high attack success rates, coupling DNN models with interpretation models could offer a sense of security when a human expert is involved. However, in white-box environments, interpretable deep learning systems (IDLSes) have been shown to be vulnerable to malicious manipulations. As access to the components of IDLSes is limited in opaquesettings, it becomes more challenging for the adversary to fool the system. In this work, we propose a Query-efficient Score-based opaque attack against IDLSes, which requires no knowledge of the target model and its coupled interpretation model. By continuously refining the adversarial samples created based on feedback scores from the IDLS, our approach effectively reduces the number of model queries and navigates the search space to identify perturbations that can fool the system. We evaluate the attack's effectiveness on four convolutional neural network (CNN) models and two interpretation models, using both ImageNet and CIFAR datasets. Our results show that the proposed approach is query-efficient with a high attack success rate that can reach more than 95%, and an average transferability success rate of 69%. We have also demonstrated that our attack is resilient against various preprocessing defense techniques.
{"title":"Stealthy Query-Efficient OpaqueAttack Against Interpretable Deep Learning","authors":"Eldor Abdukhamidov;Mohammed Abuhamad;Simon S. Woo;Eric Chan-Tin;Tamer Abuhmed","doi":"10.1109/TR.2025.3551717","DOIUrl":"https://doi.org/10.1109/TR.2025.3551717","url":null,"abstract":"Deep neural network (DNN) models are susceptible to adversarial samples in white-box and opaqueenvironments. Although previous studies have shown high attack success rates, coupling DNN models with interpretation models could offer a sense of security when a human expert is involved. However, in white-box environments, interpretable deep learning systems (IDLSes) have been shown to be vulnerable to malicious manipulations. As access to the components of IDLSes is limited in opaquesettings, it becomes more challenging for the adversary to fool the system. In this work, we propose a <italic>Qu</i>ery-efficient <italic>Score</i>-based opaque attack against IDLSes, which requires no knowledge of the target model and its coupled interpretation model. By continuously refining the adversarial samples created based on feedback scores from the IDLS, our approach effectively reduces the number of model queries and navigates the search space to identify perturbations that can fool the system. We evaluate the attack's effectiveness on four convolutional neural network (CNN) models and two interpretation models, using both ImageNet and CIFAR datasets. Our results show that the proposed approach is query-efficient with a high attack success rate that can reach more than 95%, and an average transferability success rate of 69%. We have also demonstrated that our attack is resilient against various preprocessing defense techniques.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3484-3498"},"PeriodicalIF":5.7,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144997821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Supervisory control and data acquisition (SCADA) data from a complex mechanical system, such as a high-speed train power bogie, nonpower bogie, and wind turbine, are widely used for anomaly detection and fault isolation. The SCADA data include measurements of process variables and exogenous covariates for key components in the system. The process variables refer to the performance characteristics of the key component while the exogenous covariates are working loads or working conditions of the complex mechanical system. Dominated by such physical mechanisms as dynamic motion laws of the system, there are complex relationships between the process variables and covariates, that complicate anomaly detection and fault isolation. To solve this problem, we propose a framework that integrates physical knowledge and statistical learning. We first build a spline model to capture the relationship between process variables and exogenous covariates. To make the model interpretable, we use physical knowledge to impose constraints on the model parameters. We then conduct anomaly detection at a system level based on the physical-statistical regression model. Once an anomaly is detected, we propose a Lasso-based method to isolate the faulty components. Our fault isolation method does not require historical failure data or knowing the true number of faulty components. Real-world case studies on power bogies from high-speed trains illustrate the advantages of our framework: the best benchmark achieves at least 2.50% lower F1-score in anomaly detection and 6.01% lower F1-score in fault isolation compared to our method.
{"title":"A Physical-Statistical Framework on Complex Mechanical System Fault Isolation","authors":"Bingxin Yan;Qiuzhuang Sun;Lijuan Shen;Xiaobing Ma","doi":"10.1109/TR.2025.3549216","DOIUrl":"https://doi.org/10.1109/TR.2025.3549216","url":null,"abstract":"Supervisory control and data acquisition (SCADA) data from a complex mechanical system, such as a high-speed train power bogie, nonpower bogie, and wind turbine, are widely used for anomaly detection and fault isolation. The SCADA data include measurements of process variables and exogenous covariates for key components in the system. The process variables refer to the performance characteristics of the key component while the exogenous covariates are working loads or working conditions of the complex mechanical system. Dominated by such physical mechanisms as dynamic motion laws of the system, there are complex relationships between the process variables and covariates, that complicate anomaly detection and fault isolation. To solve this problem, we propose a framework that integrates physical knowledge and statistical learning. We first build a spline model to capture the relationship between process variables and exogenous covariates. To make the model interpretable, we use physical knowledge to impose constraints on the model parameters. We then conduct anomaly detection at a system level based on the physical-statistical regression model. Once an anomaly is detected, we propose a Lasso-based method to isolate the faulty components. Our fault isolation method does not require historical failure data or knowing the true number of faulty components. Real-world case studies on power bogies from high-speed trains illustrate the advantages of our framework: the best benchmark achieves at least 2.50% lower F1-score in anomaly detection and 6.01% lower F1-score in fault isolation compared to our method.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"4091-4105"},"PeriodicalIF":5.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article presents a resilience assessment approach for hybrid ac/dc cyber-physical power system (CPPS), proposing a comprehensive assessment index called cascading failure recovery index (CFRI) that simultaneously considers the system scale and load level in the cascading failure recovery process. First, correlation characteristic matrix-based modeling framework is developed to capture the characteristics of multidimensional heterogeneous power systems, providing a clear description of the cyber-physical coupling network. Besides, the proposed CFRI incorporates cyber-physical coordinated attacks to assess the robustness of hybrid ac/dc power systems under different attack scenarios. The CFRI takes into account the number of nodes, branches, and load levels, enabling an accurate assessment of the disconnection degree and recovery capability of CPPS in case of cascading failures. Finally, simulation studies are conducted on a IEEE 39-bus power system modified with dc transmission lines to validate the effectiveness of the proposed method.
{"title":"Resilience Assessment for Hybrid AC/DC Cyber-Physical Power Systems Under Cascading Failures","authors":"Kaishun Xiahou;Wei Du;Xingye Xu;Zhenjia Lin;Yang Liu;Zhaoxi Liu;Qiuwei Wu","doi":"10.1109/TR.2025.3550523","DOIUrl":"https://doi.org/10.1109/TR.2025.3550523","url":null,"abstract":"This article presents a resilience assessment approach for hybrid ac/dc cyber-physical power system (CPPS), proposing a comprehensive assessment index called cascading failure recovery index (CFRI) that simultaneously considers the system scale and load level in the cascading failure recovery process. First, correlation characteristic matrix-based modeling framework is developed to capture the characteristics of multidimensional heterogeneous power systems, providing a clear description of the cyber-physical coupling network. Besides, the proposed CFRI incorporates cyber-physical coordinated attacks to assess the robustness of hybrid ac/dc power systems under different attack scenarios. The CFRI takes into account the number of nodes, branches, and load levels, enabling an accurate assessment of the disconnection degree and recovery capability of CPPS in case of cascading failures. Finally, simulation studies are conducted on a IEEE 39-bus power system modified with dc transmission lines to validate the effectiveness of the proposed method.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3442-3453"},"PeriodicalIF":5.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiawen Shen;Shikai Guo;Longfeng Chen;Chen Wu;Hui Li;Chenchen Li
The live chats of developers often contain meaningful information in the form of issue–solution pairs. The issue–solution pairs can offer helpful references to others who seek solutions for the similar issues, which can improve software development efficiency by facilitating issue solving. However, previous approaches such as ISPY still struggle with unsatisfactory extraction accuracy, due to the entanglement and complexity of issue-solution pairs' feature information. To address these challenges, we propose an approach named IS-Hunter for mining issue-solution pairs from real-time chat data. Specifically, IS-Hunter consists of four main components: the data preprocessing component disentangles and denoises raw chat logs, the utterance embedding component embeds utterances into vectors that subsequent components can easily process, the feature extraction component obtains textual, heuristic, and contextual feature that determines whether an utterance is topic-relevant, and the issue–solution pair prediction component predicts the utterance whether is an issue or a solution. The experimental results show that the performance of IS-Hunter outperforms the baseline methods in issue-detection and solution-extraction in terms of Precision, Recall, and F1-score. Compared with baseline methods, in issue-detection, IS-Hunter, respectively, achieves an average precision, recall, and F1-score of 0.74, 0.74, and 0.74, and it marks an obvious 4.23% improvement over the state-of-the-art approaches. Simultaneously, in solution-extraction, IS-Hunter achieves an average precision, recall, and F1-score of 0.83, 0.90, and 0.86 which is 4.88% higher than the best baseline methods.
{"title":"Extracting Meaningful Issue–Solution Pair From Collaborative Developer Live Chats","authors":"Jiawen Shen;Shikai Guo;Longfeng Chen;Chen Wu;Hui Li;Chenchen Li","doi":"10.1109/TR.2025.3550412","DOIUrl":"https://doi.org/10.1109/TR.2025.3550412","url":null,"abstract":"The live chats of developers often contain meaningful information in the form of issue–solution pairs. The issue–solution pairs can offer helpful references to others who seek solutions for the similar issues, which can improve software development efficiency by facilitating issue solving. However, previous approaches such as ISPY still struggle with unsatisfactory extraction accuracy, due to the entanglement and complexity of issue-solution pairs' feature information. To address these challenges, we propose an approach named <italic>IS-Hunter</i> for mining issue-solution pairs from real-time chat data. Specifically, <italic>IS-Hunter</i> consists of four main components: the data preprocessing component disentangles and denoises raw chat logs, the utterance embedding component embeds utterances into vectors that subsequent components can easily process, the feature extraction component obtains textual, heuristic, and contextual feature that determines whether an utterance is topic-relevant, and the issue–solution pair prediction component predicts the utterance whether is an issue or a solution. The experimental results show that the performance of IS-Hunter outperforms the baseline methods in issue-detection and solution-extraction in terms of Precision, Recall, and F1-score. Compared with baseline methods, in issue-detection, IS-Hunter, respectively, achieves an average precision, recall, and F1-score of 0.74, 0.74, and 0.74, and it marks an obvious 4.23% improvement over the state-of-the-art approaches. Simultaneously, in solution-extraction, IS-Hunter achieves an average precision, recall, and F1-score of 0.83, 0.90, and 0.86 which is 4.88% higher than the best baseline methods.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3600-3614"},"PeriodicalIF":5.7,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The through silicon via (TSV) arrays play the role of vertical electrical interconnections in the 3-D stacked integrated circuits. However, the coupling crosstalk between the adjacent TSVs increases the interconnection delay and deteriorates the signal integrity in TSV arrays. The crosstalk avoidance code (CAC) techniques based on the Fibonacci numeral system (FNS) or the improved FNS are capable of mitigating the crosstalk in TSV arrays, but the existing schemes are hindered by the hardware overhead, crosstalk suppression ability and switching activity. This article proposes the FNS-based cyclic adjacent transition free CAC with the ouroboros mapping rule for the rectangular and hexagonal TSV arrays. The proposed scheme can reduce the crosstalk even in the presence of the edge effect. Compared with the previous methods, the proposed scheme consumes significantly small hardware overhead in large-scale arrays. And the proposed method can reduce the switching activity on TSVs, thereby alleviating the power consumption in TSV arrays.
{"title":"FNS-CATF-CAC: An Efficient Crosstalk Avoidance Code to Reduce the Switching Activity in TSV Arrays","authors":"Chen Wei;Xiaole Cui","doi":"10.1109/TR.2025.3550972","DOIUrl":"https://doi.org/10.1109/TR.2025.3550972","url":null,"abstract":"The through silicon via (TSV) arrays play the role of vertical electrical interconnections in the 3-D stacked integrated circuits. However, the coupling crosstalk between the adjacent TSVs increases the interconnection delay and deteriorates the signal integrity in TSV arrays. The crosstalk avoidance code (CAC) techniques based on the Fibonacci numeral system (FNS) or the improved FNS are capable of mitigating the crosstalk in TSV arrays, but the existing schemes are hindered by the hardware overhead, crosstalk suppression ability and switching activity. This article proposes the FNS-based cyclic adjacent transition free CAC with the ouroboros mapping rule for the rectangular and hexagonal TSV arrays. The proposed scheme can reduce the crosstalk even in the presence of the edge effect. Compared with the previous methods, the proposed scheme consumes significantly small hardware overhead in large-scale arrays. And the proposed method can reduce the switching activity on TSVs, thereby alleviating the power consumption in TSV arrays.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3856-3870"},"PeriodicalIF":5.7,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","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：