This study proposes a deep learning approach for stock price prediction by bridging the long short-term memory with gated recurrent unit. In its evaluation, the mean absolute error and mean square error were used. The model proposed is an extension of the study of Hossain et al. established in 2018 with an MSE of 0.00098 as its lowest error. The current proposed model is a mix of the bidirectional LSTM and bidirectional GRU resulting in 0.00000008 MSE as the lowest error recorded. The LSTM model recorded 0.00000025 MSE, the GRU model recorded 0.00000077 MSE, and the LSTM + GRU model recorded 0.00000023 MSE. Other combinations of the existing models such as the bi-directional LSTM model recorded 0.00000019 MSE, bi-directional GRU recorded 0.00000011 MSE, bidirectional LSTM + GRU recorded 0.00000027 MSE, LSTM and bi-directional GRU recorded 0.00000020 MSE.

Construction of an Ensemble Scheme for Stock Price Prediction Using Deep Learning Techniques

The present work aims to analyze the time-series data (TSD) from movies and support constructing the movie recommendation system. Referencing the Internet of Things (IoT) technology as the framework, a time-series data analysis system for movies is built based on the recurrent neural network (RNN) and multifractal detrended mobility cross-correlation analysis (MF-DCCA) method. First, the traditional RNN model is improved by replacing the conventional convolution operation with spatial adaptive convolution. Specifically, an additional convolution layer is used to obtain the position parameters required for adaptive convolution to improve the model performance to capture the characteristics of spatial-temporal transformation. Then, the MF-DCCA method is optimized to reduce the interference of noise signals to the analysis processing of TSD from movies. Finally, the TSD analysis system is tested for performance verification. The test results indicate that the method proposed here has outstanding stability and runs smoothly. When the prediction scheme is long short-term memory (LSTM) (L = 20), the similarity of the LSTM (L = 20) network under one frame is 0.977; the similarity of the LSTM (L = 20) network under nine frames is 0.727. This system provides a specific idea for applying the RNN model and MF-DCCA method in analyzing TSD from movies.

/pdf/analysis-on-time-series-data-from-movie-using-mf-dcca-method-3vl7hiac.pdf

Analysis on Time-Series Data from Movie Using MF-DCCA Method and Recurrent Neural Network Model Under the Internet of Things

Abstract This paper proposes an effective method for measuring the non-smoothness of time series data: Dirichlet mean energy function. The method expresses the time series data as an n-dimensional vector based on its own properties, and then abstracts the time series model as a chain graph model based on directed graph theory. The incidence matrix of the time series data is established based on the constructed chain graph model, and the Dirichlet mean energy function is defined in the form of matrix function. The Dirichlet mean energy function can quantitatively express the non-smoothness of time series data. The contribution of this paper is to proposes an effective mathematical tool for measuring the non-smoothness of time series data based on graph theory and matrix theory. In future work, we will further validate the validity of this tool in more application areas and extend this method to high-dimensional time series data. 

/pdf/a-method-for-measuring-the-non-smoothness-of-time-series-11y5th9z.pdf

A Method for Measuring the Non-Smoothness of Time Series Data: Dirichlet Mean Energy Function

Extractive text summarization is an approach to automatic text summarization whose main purpose is to reduce the size of the document while preserving the information of the original document. In this study, 7-phase preprocessing is proposed as a preprocessing composition to clean text data so that it is ready to enter data into the summary method such as machine learning. The composition of 7-phase preprocessing is data frame by sentence, remove title from data frame, lower caseing, remove punctuations, remove stop words, tokenizing and stemming. The preprocessing model was tested on the DUC 2002 dataset which is a news document. The performance of the proposed preprocessing stage for extractive summarization showed superior results compared to the combination of other comparison preprocessing stages with ROUGE-1 measurements (recall, precision, and F-1).

The 7-Phases Preprocessing Based On Extractive Text Summarization

Extractive text summarization is an approach to automatic text summarization whose main purpose is to reduce the size of the document while preserving the information of the original document. In this study, 7-phase preprocessing is proposed as a preprocessing composition to clean text data so that it is ready to enter data into the summary method such as machine learning. The composition of 7-phase preprocessing is data frame by sentence, remove title from data frame, lower caseing, remove punctuations, remove stop words, tokenizing and stemming. The preprocessing model was tested on the DUC 2002 dataset which is a news document. The performance of the proposed preprocessing stage for extractive summarization showed superior results compared to the combination of other comparison preprocessing stages with ROUGE-1 measurements (recall, precision, and F-1). 

Time series data are an extremely important type of data in the real world. Time series data gradually accumulate over time. Due to the dynamic growth in time series data, they tend to have higher dimensions and large data scales. When performing cluster analysis on this type of data, there are shortcomings in using traditional feature extraction methods for processing. To improve the clustering performance on time series data, this study uses a recurrent neural network (RNN) to train the input data. First, an RNN called the long short-term memory (LSTM) network is used to extract the features of time series data. Second, pooling technology is used to reduce the dimensionality of the output features in the last layer of the LSTM network. Due to the long time series, the hidden layer in the LSTM network cannot remember the information at all times. As a result, it is difficult to obtain a compressed representation of the global information in the last layer. Therefore, it is necessary to combine the information from the previous hidden unit to supplement all of the data. By stacking all the hidden unit information and performing a pooling operation, a dimensionality reduction effect of the hidden unit information is achieved. In this way, the memory loss caused by an excessively long sequence is compensated. Finally, considering that many time series data are unbalanced data, the unbalanced K-means (UK-means) algorithm is used to cluster the features after dimensionality reduction. The experiments were conducted on multiple publicly available time series datasets. The experimental results show that LSTM-based feature extraction combined with the dimensionality reduction processing of the pooling technology and cluster processing for imbalanced data used in this study has a good effect on the processing of time series data.

/pdf/a-novel-long-and-short-term-memory-network-with-time-series-2d3fuzysoc.pdf

A Novel Long- and Short-Term Memory Network with Time Series Data Analysis Capabilities

With the rapid development of we-media information dissemination, WeChat official accounts platform has become an important way for people to obtain health related knowledge. However, the platform information is redundant, miscellaneous, and overloaded. In order to meet the increasingly accurate and efficient knowledge service needs of users, reorganizing and aggregating document knowledge resources is effective. If we use the way of artificial recognition to filter information, it will inevitably cause huge labor and time cost, and the effect is very little in front of massive articles. This paper proposes a text summarization method for the WeChat platform based on improved TextRank that takes into account both user demands and sentence features during the summarization process. The data source crawled from the Sogou WeChat platform. The results show that the TextRank algorithm has obvious hints on the accuracy of text summarization extraction after fusing the Word2vec model. The improved TextRank method, integrating user demands and sentence features into the model, makes the results of text summarization closer to the theme of the article and more able to meet the user demand. According to the complexity of the algorithm, this method is not suitable for the automatic summarization of long or multiple documents.

/pdf/automatic-text-summarization-for-public-health-wechat-kkk6zwv5.pdf

Automatic Text Summarization for Public Health WeChat Official Accounts Platform Base on Improved TextRank

The paper discusses the issue of stress among students and proposes using lighting to alleviate stress levels [3]. The authors discuss various techniques for managing stress, including exercise, sleep, and socialization, and suggest that lighting can be used to address seasonal affective disorder (SAD) [4][5]. The paper outlines the challenges faced during the experiment and design, including creating a reliable survey, user interface design, and data privacy. The authors propose using a weighted score for survey responses and adopting simple designs for the app interface. The paper concludes by discussing the potential benefits of using lighting to alleviate stress levels and identifying areas for future research.

Psychological Lights: An Intelligent LED System to Relief Youth Stress Level using AI and Internet of the things

Comparisons between different global navigation satellite system (GNSS) signals and GNSS-reflectometry (GNSS-R) satellite systems can provide valuable suggestions for future development of the GNSS-R instrument and signal processing method. This article evaluates the ocean altimetry performance of multiple GNSS constellation signals using raw intermediate frequency data collected by Cyclone GNSS (CYGNSS) and TechDemoSat-1 (TDS-1) satellites. Data used for the evaluation include observations of GPS L1, Galileo E1, and BDS B1 band signal. The specular point position and the ground-truth bistatic delay are calculated through the HALF method. After ionospheric, tropospheric, and tide corrections, the sea surface height can be retrieved; and then the height is compared with the DTU18 mean sea surface model derived one. Based on the GNSS-R satellite-collected observations, an optimal incoherent integral duration is determined. By making use of the optimal duration, the CYGNSS-based ranging delay estimating accuracy can reach up to 2.38 m, 1.98 m, and 1.91 m for GPS, Galileo and BDS, respectively; and the TDS-1 based one can reach up to 5.46 m and 3.84 m for GPS and Galileo, respectively. The results can provide suggestion on the strategies of multi-constellation observations fusion to improve the altimetry accuracy.

https://www.frontiersin.org/articles/10.3389/feart.2022.1079255/pdf

Zixuan Cheng

Papers

A Novel Long- and Short-Term Memory Network with Time Series Data Analysis Capabilities

Automatic Text Summarization for Public Health WeChat Official Accounts Platform Base on Improved TextRank

Psychological Lights: An Intelligent LED System to Relief Youth Stress Level using AI and Internet of the things

Evaluation of spaceborne GNSS-R based sea surface altimetry using multiple constellation signals