• Journal of the Korea Society of Computer and Information
• /
• v.18 no.2
• /
• pp.127-140
• /
• 2013

We explored the relationship between the level of change awareness and deployment of software process improvement (SPI) approaches using a competing values framework. To measure awareness level of organization's change, we used DICE framework provides means for predicting the outcome of change management initiatives. The four factors for organizaton's change: duration, integrity, commitment, and effort are evaluated and a score is calculated. The DICE(R) score is used to classify projects into win, worry, or woe zones. In this paper, we apply the DICE(R) score as an independent variable to predict the outcome of a software process improvement. Our results indicated that the Organization have a higher chance of success have the better outcome in software process improvement.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.2
• /
• pp.209-219
• /
• 2014

With rapid convergence of information technology and expending role of software, many organizations have taken interested in We explore the relationship between the level of change awareness and deployment of software process improvement (SPI) approaches using a competing values framework. To measure awareness level of organization's change, DICE framework which provides means for predicting the outcome of change management initiatives is used. The four factors for organizaton's change: duration, integrity, commitment, and effort are evaluated and a score is calculated. In this paper, we apply the DICE(R) score as an independent variable to predict the outcome of a software process improvement. Our results indicated that the Organization have a higher chance of success have the better outcome in software process improvement.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.