Open Access

ARTICLE

Yuan Chen¹, Liangtao Duan¹, Weize Sun^{2, *}, Jingxin Xu³
Journal on Big Data, Vol.1, No.3, pp. 107-116, 2019, DOI:10.32604/jbd.2019.07294
Abstract In this work, we address the frequency estimation problem of a complex singletone embedded in the heavy-tailed noise. With the use of the linear prediction (LP) property and l₁-norm minimization, a robust frequency estimator is developed. Since the proposed method employs the weighted l₁-norm on the LP errors, it can be regarded as an extension of the l_p-generalized weighted linear predictor. Computer simulations are conducted in the environment of α-stable noise, indicating the superiority of the proposed algorithm, in terms of its robust to outliers and nearly optimal estimation performance. More >

View

4730

Download

2146

Open Access

ARTICLE

Wangdong Jiang¹, Taian Yang^{1, *}, Guang Sun^{1, 3}, Yucai Li¹, Yixuan Tang², Hongzhang Lv¹, Wenqian Xiang¹
Journal on Big Data, Vol.1, No.3, pp. 117-134, 2019, DOI:10.32604/jbd.2019.08454
Abstract In order to study deeply the prominent problems faced by China’s clean government work, and put forward effective coping strategies, this article analyzes the network information of anti-corruption related news events, which is based on big data technology. In this study, we take the news report from the website of the Communist Party of China (CPC) Central Commission for Discipline Inspection (CCDI) as the source of data. Firstly, the obtained text data is converted to word segmentation and stop words under preprocessing, and then the pre-processed data is improved by vectorization and text clustering, finally,… More >

View

4079

Download

2249

Open Access

ARTICLE

Yue Cai¹, Zeying Song¹, Guang Sun^{1, *}, Jing Wang¹, Ziyi Guo¹, Yi Zuo¹, Xiaoping Fan¹, Jianjun Zhang², Lin Lang¹
Journal on Big Data, Vol.1, No.3, pp. 135-144, 2019, DOI:10.32604/jbd.2019.08274
Abstract Big data technology is changing with each passing day, generating massive amounts of data every day. These data have large capacity, many types, fast growth, and valuable features. The same is true for the stock investment market. The growth of the amount of stock data generated every day is difficult to predict. The price trend in the stock market is uncertain, and the valuable information hidden in the stock data is difficult to detect. For example, the price trend of stocks, profit trends, how to make a reasonable speculation on the price trend of stocks More >

View

3955

Download

3512

Open Access

ARTICLE

Danping Dong^{1, *}, Yue Wu¹, Lizhi Xiong¹, Zhihua Xia¹
Journal on Big Data, Vol.1, No.3, pp. 145-150, 2019, DOI:10.32604/jbd.2019.08706
Abstract This paper proposes a strategy for machine learning in the ciphertext domain. The data to be trained in the linear regression equation is encrypted by SHE homomorphic encryption, and then trained in the ciphertext domain. At the same time, it is guaranteed that the error of the training results between the ciphertext domain and the plaintext domain is in a controllable range. After the training, the ciphertext can be decrypted and restored to the original plaintext training data. More >

View

4478

Download

2167

Open Access

ARTICLE

Mengling Zou¹, Zhengxuan Liu², Xianyi Chen^{3, *}
Journal on Big Data, Vol.1, No.3, pp. 151-158, 2019, DOI:10.32604/jbd.2019.09057
Abstract Image encryption (IE) is a very useful and popular technology to protect the privacy of users. Most algorithms usually encrypt the original image into an image similar to texture or noise, but texture and noise are an obvious visual indication that the image has been encrypted, which is more likely to cause the attacks of enemy. To overcome this shortcoming, many image encryption systems, which convert the original image into a carrier image with visual significance have been proposed. However, the generated cryptographic image still has texture features. In line with the idea of improving More >

View

3316

Download

2115