Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-03 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the problems of low prediction accuracy and feature extraction difficulty in complicated stock market, this paper proposed a stock price prediction method based on dynamic mode decomposition and long short-term memory neural network (DMD-LSTM) . Firstly, it used the DMD algorithm to decompose the industry specific stock in the background of plate linkage phenomenon, and extracted the mode feature which included stock trend information. Then, built the LSTM network to establish the relations between stock price and the feature of mode and basic index in different market conditions. The experimental results on Angang Steel (sh600000) show that, the proposed method has the higher forecasting precision compared with the traditional ways in specific condition, which can characterize the trend of stock price changes better .
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-11-29 Cooperative journals: 《计算机应用研究》
Abstract： This paper proposed a fair secure multi-party computation (MPC) protocol to solve the problem that fairness cannot be achieved when there is no honest majority. The protocol constructed a penalty mechanism based on smart contracts which are stored on the blockchain. It includes the MPC phase based on verifiable secret sharing and the fair secret reconstruction phase. The participants can obtain the final output by collecting just t+1 correct shares. The protocol utilized homomorphic commitments to verify the correctness of the secret shares, employed timeouts to identify the premature abort behaviors of malicious parties, and punished the aborting parties financially. Security analysis shows that honest participants can get the final output, otherwise they will get financial compensation. Performance analysis shows that the protocol requires only one coin-transfer round and a large number of complex secret share verification work is off the chain, which ensures the implementation efficiency.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-11-29 Cooperative journals: 《计算机应用研究》
Abstract： In order to cope with the problem of data sparsity and “curse of dimensionality” in text classification, this paper proposes a short text classification framework by taking keyword as featrues and assigning keyword similarity as feature weight. First, it trained a word2vec model with large corpus data, then got keywords of each category text by textrank. And it selected unique keywords from the keywords collection as features. For each feature, it calculated the similarity of words in the short text by word2vec model, and assigned the maximum similarity as the weight of the feature. Finally, it chose KNN and SVM as classifier. Experiments on dataset of Chinese news headlines demonstrate that the accuracy outperforms other usual methods by 6%.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-11-29 Cooperative journals: 《计算机应用研究》
Abstract： Aimed-at lung nodule Benign/Malignant classification, an effective grey scale density distribution feature extraction algorithm which was combined with pattern recognition models to evaluate the classification system was proposed. The proposed feature extraction algorithm first collected a large number of blocks from lung tumor images and determined the distance matrix by calculating the relationships among the image blocks. Then, K-means clustering methods was used to classify the current image blocks and obtained 10 cluster centers. After that, calculated the distribution density features by mapping CT value of nodule image pixels with the 10 cluster centers and extracted a 10-dimensional feature vector. Finally, the extracted feature vectors were divided into training and testing set to identify lung adenocarcinomas risk levels by Random Forest classification model. The classification framework was evaluated in LIDC-IDRI dataset, the average accuracy reached to 0.9008. The proposed method outperforms the most recent techniques, and the experimental results show great robustness of the proposed method for different lung CT image datasets.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-20 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the global optimization problem, this paper proposed a new intelligent algorithm called RGSO, based on SVDD and the root algorithm existed. The root system differentiated into the taproot and the lateral root group. Inspired by this growth behavior, this paper described the growth behavior of the taproot tips based on SVDD. The algorithm constructed the root growth model, and used the point of the highest concentration of nutrients in the soil as the target of global optimization. This paper analyzed the mathematical model of RGSO, and proved its convergence theoretically. In the experiment, this paper compared RGSO with the other three advanced algorithms, and tested the optimization effect with different parameters. The result of the experiment verified the convergence and effectiveness of RGSO, and it indicates that RGSO is an effective algorithm to solve global optimization problem.
Hits
Hits
Downloads
Comment