Bøger af Ying Liu

In this research, parametric software cost estimation models and their related calibration methods have been analyzed, especially for the COCOMO model and the Bayesian calibration approach. This research combines machine learning techniques and statistical techniques. With this approach, the prediction powers of the COCOMO parametric software cost model are shown to be significantly improved while the variability is decreased with respect to the dataset being analyzed. This research studies not only the accuracy but also the variances of the model and the variables. It can improve the confidence of people who use software cost estimation models, show the prediction power of software cost estimation models after calibration, and make it easier and better to perform software data collection and analysis. However, the research also identifies risks in using the approach, such as dropping parameters that will vary on future projects. This research provides methods that can help an organization to reason about the relationship between the characteristics of the organization and its projects' software development costs and schedules. The methods can thus help the organization to make more cost-effective development decisions and investment decisions. The research also provides new insights on how to combine calibration, stratification, hold-out, and machine learning techniques to produce more accurate parametric models for particular organizations or situations.

Deep learning enables a model constituted by multiple processing layers to learn the data representation with multiple levels of abstraction. In the past decade, deep learning has brought remarkable achievements in many fields of machine learning and pattern recognition, especially in image processing. The state-of-the-art performance in image super-resolution reconstruction, image classification, target detection, image retrieval and other image processing tasks have been greatly improved. This book introduces these image processing technologies based on deep learning, including recent advances, applications in real scenes and future trends. The first chapter introduces image super-resolution reconstruction, which aims to recover high-resolution images from corresponding low-resolution versions. This chapter reviews these image super-resolution methods based on convolutional neural networks and generative adversarial networks on account of internal network structure. The second chapter presents four categories of few-shot image classification algorithms: transfer learning based, meta-learning based, data augmentation based, and multimodal based methods. In the third chapter, deep learning based models for small target detection in video are summarized in detail, which are categorized into one-stage models and two-stage models according to the detection stages. The network structures and plug-in modules for video based small target detection are also explained. The fourth chapter discusses deep learning based cross-modal hashing for image retrieval methods, including the extraction of high-level semantic information and the maintenance of similarity between different mo

This book analyzes of the surplus of production capacity in China. There was no surplus of productive capacity in above industries between 2002 and 2012, and the current surplus is due to poor government policies on real estate prices after 2012.