Segmentation of colorectal cancerous regions from 3D Magnetic Resonance (MR) images is a crucial procedure for radiotherapy which conventionally requires accurate delineation of tumour boundaries at an expense of labo...
详细信息
Radiomics aims to extract and analyze large numbers of quantitative features from medical images and is highly promising in staging, diagnosing, and predicting outcomes of cancer treatments. Nevertheless, several chal...
详细信息
Pulsar candidate selection identifies prospective observations of modern radio pulsar surveys for further inspection in search of real pulsars. Typically, human experts visually select valuable candidates and eliminat...
详细信息
ISBN:
(纸本)9781509048410
Pulsar candidate selection identifies prospective observations of modern radio pulsar surveys for further inspection in search of real pulsars. Typically, human experts visually select valuable candidates and eliminate radio frequency interference or other noises. Recently, machine learning methods are adopted to automate this task, which saves human labor and makes it possible for processing millions of observations efficiently. Considering the number of positive training samples are relatively too small and the cost of incorrectly labeling a real pulsar candidate as negative is large, we propose a novel hierarchical candidate-sifting model by emphasizing the cost of incorrect prediction of positive samples and assembling multiple classifiers trained with different weighting parameters. Experiments on three pulsar selection datasets demonstrate our proposed method improves the pulsar-sifting performance a lot according to several standard evaluation metrics.
Deep learning scheme has received significant attention during these years, particularly as a way of building hierarchical representations from unlabeled data for a variety of signal and information processing tasks. ...
详细信息
ISBN:
(纸本)9781509006212
Deep learning scheme has received significant attention during these years, particularly as a way of building hierarchical representations from unlabeled data for a variety of signal and information processing tasks. However, deep neural networks suffer from slow learning speed since most used training algorithms are based on variations of the gradient descent algorithms which require iterative optimization and thus are time-consuming. In addition, a series of control parameters need to be specified empirically which lacks of the theoretical guidance, and current learning algorithms for deep networks are not very suitable to incremental learning scenario. To address these issues, we propose a fast learning scheme in this paper. The basic idea of our approach is to pre-train basic units such as auto-encoders of the deep architecture in an analytical way without any iterative optimization procedure. This scheme is also extended to an incremental learning version. The experimental result shows the superiority of our approach over the state-of-the-art gradient descent based algorithms. To demonstrate the impact of our algorithm on complicated real world applications, we give an example of its performance in astronomical spectra patternrecognition.
Automatic image annotation and tagging is necessary for indexing and searching of images using querying a text. It is widely used in search engines like Google, Yahoo, Baidu, etc. Fast image Tagging (FastTag) algorith...
详细信息
Automatic image annotation and tagging is necessary for indexing and searching of images using querying a text. It is widely used in search engines like Google, Yahoo, Baidu, etc. Fast image Tagging (FastTag) algorithm is proposed to accelerate image annotation process, while keeping the precision of automatic image annotation results. Feature mapping is used to map image features vectors onto higher dimensional feature space. Feature mapping methods plays an important role in automatic image annotation. In this paper, we have compared 6 kernels, among which four kernels are used in homogeneous feature mapping and two kernels are used in discriminative tree based feature mapping, to investigate which feature mapping performs better for automatic image annotation. The performance of these methods has been analyzed by conducting intensive experiments on three different datasets as used by FastTag algorithm in their experiments. We have found that the homogeneous feature mapping with χ 2 kernel is more suitable when used in FastTag algorithm in terms of precision, recall, FI score and N+ measures, and with a relatively acceptable performance.
In order to verify the network traffic decline because by node breakdown, this paper proposes a new type of prediction algorithm (Prediction algorithm based on Discrete-Queue for FARIMA model, PDF). At first, the math...
详细信息
Center nodes have a bigger load and burden with lots of routing in an Ad Hoc Network Model. Congestion of the nodes' packets has a great impact on network performance, especially in wireless networks. This paper p...
详细信息
In this paper, we investigate the efficiency and scalability of Gaussian mixture model based learning algorithm for the detection of Near-Earth objects in large scale astronomy image data. We propose an effective sche...
详细信息
ISBN:
(纸本)9781479938414
In this paper, we investigate the efficiency and scalability of Gaussian mixture model based learning algorithm for the detection of Near-Earth objects in large scale astronomy image data. We propose an effective scheme to reduce the computational complexity of current learning algorithm, this is achieved by adopting the perceptual image hashing method. Our proposed scheme is validated on raw astronomy image data. The experiment results illustrate that both efficiency and scalability are improved significantly in astronomical scenario and other scenario.
Sparse representation classification (SRC) is a new framework for classification and has been successfully applied to face recognition. However, SRC can not well classify the data when they are in the overlap feature ...
详细信息
暂无评论