Search

Due to the effects of many deterministic and stochastic factors, it has always been a challenging goal to gain good profits from the stock market. Many methods based on different theories have been proposed in the past decades. However, there has been little research about determining the temporal investment style (i.e., short term, middle term, or long term) for the stock. In this paper, we propose a method to find suitable stock investment styles in terms of investment time. Firstly, biclustering is applied to a matrix that is composed of technical indicators of each trading day to discover trading patterns (regarded as trading rules). Subsequently a k-nearest neighbor (KNN) algorithm is employed to transform the trading rules to the trading actions (i.e., the buy, sell, or no-action signals). Finally, a min-max and quantization strategy is designed for determination of the temporal investment style of the stock. The proposed method was tested on 30 stocks from US bear, bull, and flat markets. The experimental results validate its usefulness. [ABSTRACT FROM AUTHOR]

Using a natural language sentence to describe the content of an image is a challenging but very important task. It is challenging because a description must not only capture objects contained in the image and the relationships among them, but also be relevant and grammatically correct. In this paper a multi-modal embedding model based on gated recurrent units (GRU) which can generate variable-length description for a given image. In the training step, we apply the convolutional neural network (CNN) to extract the image feature. Then the feature is imported into the multi-modal GRU as well as the corresponding sentence representations. The multi-modal GRU learns the inter-modal relations between image and sentence. And in the testing step, when an image is imported to our multi-modal GRU model, a sentence which describes the image content is generated. The experimental results demonstrate that our multi-modal GRU model obtains the state-of-the-art performance on Flickr8K, Flickr30K and MS COCO datasets. [ABSTRACT FROM AUTHOR]

For the safety of low flying aircraft, it will become increasingly important that an aircraft should have the ability to detect and avoid small obstacles in the low flying environment. In recent years, using context information to assist in detecting power lines has shown great potential to better detect power lines at a remote distance. Therefore, how to adequately use the context information for a better detection is a hot issue of concern. This paper proposes a novel auxiliary assisted power line detection method, in which the spatial context disparity of auxiliaries is quantitatively and uniformly evaluated for the first time. As a cognitive strategy, the spatial context disparity depends on two factors, the spatial context peakedness and the spatial context difference. With this cognitive method, objects that achieve high spatial context disparity scores are more suitable for being the auxiliaries of the power lines. Experimental results show that, owing to the spatial context disparity, the proposed method can acquire proper auxiliaries with abundant context information to support the detection, so that better power line detections are achieved comparing to traditional power line detection methods. The proposed power line detection method, which can automatically choose the optimal auxiliaries, is effective and has the potential for practical use in ensuring the flight safety of unmanned air vehicles (UAVs) in the low flying environment. [ABSTRACT FROM AUTHOR]

This paper comprehensively surveys the development of face hallucination (FH), including both face super-resolution and face sketch-photo synthesis techniques. Indeed, these two techniques share the same objective of inferring a target face image (e.g. high-resolution face image, face sketch and face photo) from a corresponding source input (e.g. low-resolution face image, face photo and face sketch). Considering the critical role of image interpretation in modern intelligent systems for authentication, surveillance, law enforcement, security control, and entertainment, FH has attracted growing attention in recent years. Existing FH methods can be grouped into four categories: Bayesian inference approaches, subspace learning approaches, a combination of Bayesian inference and subspace learning approaches, and sparse representation-based approaches. In spite of achieving a certain level of development, FH is limited in its success by complex application conditions such as variant illuminations, poses, or views. This paper provides a holistic understanding and deep insight into FH, and presents a comparative analysis of representative methods and promising future directions. [ABSTRACT FROM AUTHOR]