Filters








12,582 Hits in 4.3 sec

Micro interaction metrics for defect prediction

Taek Lee, Jaechang Nam, DongGyun Han, Sunghun Kim, Hoh Peter In
2011 Proceedings of the 19th ACM SIGSOFT symposium and the 13th European conference on Foundations of software engineering - SIGSOFT/FSE '11  
However, widely used defect prediction metrics such as source code metrics, change churns, and the number of previous defects do not capture developers' direct interactions.  ...  We propose 56 novel micro interaction metrics (MIMs) that leverage developers' interaction information stored in the Mylyn data.  ...  Overall, we expect that future defect prediction models will use more information from developers' direct and micro level interactions for effective defect prediction.  ... 
doi:10.1145/2025113.2025156 dblp:conf/sigsoft/LeeNHKI11 fatcat:s6hjqqq5hnauhcojdu2vtdaboa

Is Complexity-based Clustering of Process Metrics as Effective as in Static Code Metrics

Muhammed Maruf Öztürk
2019 Baltic Journal of Modern Computing  
Cross-project defect prediction (CPDP), which is one of the popular issues of defect prediction, is still intriguing.  ...  Defect prediction is not a new sub-field of software engineering. However, in this field, there are various research problems that are still attractive for many researchers.  ...  Micro-interaction metrics were developed for illustrating implications of developers in software defect prediction (Lee et al., 2016) . They can be defined a sub-type of process metrics.  ... 
doi:10.22364/bjmc.2018.7.1.03 fatcat:phawytgurfgp7kxshsgudzosfm

Bone formation of the porous layer formed of Ti-Ag mesh for GBR membrane applications

Min-Kyung Kang, Seung-Kyun Moon, Jae-Sung Kwon, Soo-Hyuk Uhm, Su-Yeon Im, Kyoung-Nam Kim
2015 Korean Journal of Dental Materials  
nano-metric pores were well separated uniformly over the micro-metric pores.  ...  The surface consisted of nano-metric pores on the micro-metric surface with a hemisphere shape.  ... 
doi:10.14815/kjdm.2015.42.2.143 fatcat:sa5miyipavedhh7okjwvrt5uni

LPViT: A Transformer Based Model for PCB Image Classification and Defect Detection

Kang An, Yanping Zhang
2022 IEEE Access  
In this paper, we propose a transformerbased model, LPViT, for defect detection and classification of PCBs.  ...  We conduct the defect detection task on the dataset DeepPCB, which consists of six different types of PCB defects. Defect detection benefits both manufacturing and recycling of PCBs.  ...  We set the total training epochs to be 2000. 3) PERFORMANCE METRICS We use mean Average Precision(mAP) as the metric for PCB defect detection task.  ... 
doi:10.1109/access.2022.3168861 fatcat:c4s6kavafjdn7ghtu7gs7o3zt4

Practical considerations in deploying statistical methods for defect prediction: A case study within the Turkish telecommunications industry

Ayşe Tosun, Ayşe Bener, Burak Turhan, Tim Menzies
2010 Information and Software Technology  
For the explanations of these metrics, see [1].  ...  Prediction models combine these metrics and defect information as training data to find out which modules are more defect-prone.  ...  Therefore, we used project-level defect prediction for the following experiments.  ... 
doi:10.1016/j.infsof.2010.06.006 fatcat:uoldg3lthbcwxosxkyu3gaaxxi

Comparative Study of Software Defect Prediction and Analysis the Class using Machine Learning Method

2020 International Journal of Engineering and Advanced Technology  
The software defect analysis uses various software products for performance metrics to predict. It helps to find a different relationship between software volume and error size.  ...  It provides a valid defect prediction for the defect identification code. This information is implemented in application software to improve predictive error classes and merit function code.  ...  Therefore, we recommend that you use the Micro Interaction Indicator (MIM), which developer contact information you use.  ... 
doi:10.35940/ijeat.e1161.069520 fatcat:besf4nii4ja7jb574l3l2hzt4m

Dry Textile Forming Simulations: A Benchmarking Exercise

Xiaochuan Sun, Jonathan P.-H. Belnoue, Adam Thompson, Bassam El Said, Stephen R. Hallett
2022 Frontiers in Materials  
In this study, four representative finite element (FE) based modelling techniques and an analytical solution for the prediction of 2D woven fabrics' deformation during forming are compared back-to-back  ...  For completeness and to highlight the importance of considering inter-yarn and preform-to-tool interactions, a kinematic drape algorithm (based on geometrical mapping) is also considered.  ...  This work was funded by the EPSRC platform grant "SIMulation of new manufacturing PROcesses for Composite Structures (SIMPROCS)", (EP/ P027350/1).  ... 
doi:10.3389/fmats.2022.831820 fatcat:p4lnh5qzendl3ak7q2vt3snbti

Machine Learning-Based Corrosion-Like Defect Estimation With Shear-Horizontal Guided Waves Improved by Mode Separation

Mateus Gheorghe de Castro Ribeiro, Alan Conci Kubrusly, Helon Vicente Hultmann Ayala, Steve Dixon
2021 IEEE Access  
This paper investigates the use of machine learning models to analyse the two lowest order SH guided modes, for quantitative size estimation and detection of corrosion-like defects in aluminium plates.  ...  with defects.  ...  Performance metrics for the best cases of each mode separation. Rates such as the TPR and FPR are depicted for each class and considering a macro and micro average.  ... 
doi:10.1109/access.2021.3063736 fatcat:3ewljofdkrdezbjgaymfaes55y

Improving Micro-video Recommendation by Controlling Position Bias [article]

Yisong Yu, Beihong Jin, Jiageng Song, Beibei Li, Yiyuan Zheng, Wei Zhu
2022 arXiv   pre-print
As the micro-video apps become popular, the numbers of micro-videos and users increase rapidly, which highlights the importance of micro-video recommendation.  ...  Although the micro-video recommendation can be naturally treated as the sequential recommendation, the previous sequential recommendation models do not fully consider the characteristics of micro-video  ...  Sequential recommendation is to model user interaction sequences to predict the next item the user will interact with, where an item can be a micro-video.  ... 
arXiv:2208.05315v1 fatcat:wqfzhvtnwfbihgmdctj7etbxze

A Gradient Guided Architecture Coupled With Filter Fused Representations For Micro-crack Detection in Photovoltaic Cell Surfaces

Muhammad Hussain, Tianhua Chen, Sofya Titrenko, Pan Su, Mufti Mahmoud
2022 IEEE Access  
This paper presents a shallow architecture based on Convolutional Neural Networks (CNN) for detecting Micro-cracks in Photovoltaic (PV) cells within the manufacturing environment.  ...  The performance criteria is widened to include accuracy, computational, architectural, and post-deployment metrics.  ...  Micro-cracks are one of the most challenging when it comes to defect detection.  ... 
doi:10.1109/access.2022.3178588 fatcat:bvtvtfmxajhopm4dpts3zhwln4

Multiview Transfer Learning for Software Defect Prediction

Jinyin Chen, Yitao Yang, Keke Hu, Qi Xuan, Yi Liu, Chao Yang
2019 IEEE Access  
With this multiview transfer method, lots of training instances are provided for software defect prediction model to ensure the effectiveness of training labels.  ...  We propose a heterogeneous data orienting multiview transfer learning for software defect prediction, denoted as MTDP, which can achieve different dimensions and granularities features to automatically  ...  [58] , with 81 features, including 42 source code metrics, 16 history metrics (HM), and 24 micro interaction metrics (MIM).  ... 
doi:10.1109/access.2018.2890733 fatcat:ozuuz7afivembcb3yo3rw55h7a

Critical Review on Engineering Mechanical Quality of Green Compacts using Powder Properties

Hojae Yi, Anuranjan Pandeya, Apoorva Karamchandani, Virendra M. Puri
2018 Kona : Powder and Particle  
Such divergent behavior of particulate materials is especially problematic for product developments and reliable operations.  ...  For processes involving particulate materials, mechanical properties of green compacts are of great interest when they are final or intermediate products.  ...  For example, mechanical quality metrics of compacts are often described or determined by inspecting a presence of surface defects such as crack or capping.  ... 
doi:10.14356/kona.2018006 fatcat:yppzzkteirddrpczmuh4ghpyi4

Automatic Micro-Crack Detection of Polycrystalline Solar Cells in Industrial Scene

Tao Fan, Tao Sun, Xiangying Xie, Hu Liu, Zhixiong Na
2022 IEEE Access  
Since it is difficult for other methods to precisely detect other defect types apart from micro-cracks, we further propose a transfer learning method based on MK-MMD to guide the training process of defect  ...  In this paper, we propose a ResNet-based micro-crack detection method to detect the micro-cracks on polycrystalline solar cells.  ...  basis for the model evaluation metrics.  ... 
doi:10.1109/access.2022.3145980 fatcat:h5vxrsznnzhx5fyefzafj6nnom

Metrics and Software Quality Evolution: A Case Study on Open Source Software

Nicholas Drouin, Mourad Badri, Fadel Touré
2013 Journal of clean energy technologies  
This paper aims at analyzing empirically the quality evolution of an open source software using metrics.  ...  We used a control flow based metric (Quality Assurance Indicator -Qi) which we proposed in a previous work.  ...  [15] investigate the significance of different OO metrics for the purpose of predicting maintainability of software. Nagappan et al. [25] focus on mining metrics to predict component failures.  ... 
doi:10.7763/ijcte.2013.v5.742 fatcat:jatsegg6kvftlmyotmeic3prpe

Page 1034 of Journal of Polymer Science. Part B, Polymer Physics Vol. 43, Issue 8 [page]

2005 Journal of Polymer Science. Part B, Polymer Physics  
Note, however, that even micro- meter-sized particles can exhibit line disclinations if they are confined to a small volume.’**1* Defect structures and interaction energies of pairs of colloids immersed  ...  .®’ Sec- ond, the theory must be capable of predicting the equilibrium structures formed by the liquid crys- tal for a given set of confining surfaces; in this work, we use a special case of the Beris-  ... 
« Previous Showing results 1 — 15 out of 12,582 results