scholarly journals Stock Trend Prediction Using Deep Learning Approach on Technical Indicator and Industrial Specific Information

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 250
Author(s):  
Kittisak Prachyachuwong ◽  
Peerapon Vateekul
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Predictive Accuracy ◽  
Model Performance ◽  
Specific Information ◽  
Trend Prediction ◽  
Textual Information ◽  
Economic News ◽  
Technical Indicator ◽  
Memory Network

A stock trend prediction has been in the spotlight from the past to the present. Fortunately, there is an enormous amount of information available nowadays. There were prior attempts that have tried to forecast the trend using textual information; however, it can be further improved since they relied on fixed word embedding, and it depends on the sentiment of the whole market. In this paper, we propose a deep learning model to predict the Thailand Futures Exchange (TFEX) with the ability to analyze both numerical and textual information. We have used Thai economic news headlines from various online sources. To obtain better news sentiment, we have divided the headlines into industry-specific indexes (also called “sectors”) to reflect the movement of securities of the same fundamental. The proposed method consists of Long Short-Term Memory Network (LSTM) and Bidirectional Encoder Representations from Transformers (BERT) architectures to predict daily stock market activity. We have evaluated model performance by considering predictive accuracy and the returns obtained from the simulation of buying and selling. The experimental results demonstrate that enhancing both numerical and textual information of each sector can improve prediction performance and outperform all baselines.

Knowledge Enhanced LSTM for Coreference Resolution on Biomedical Texts

2021 ◽  
Author(s):  
Yufei Li ◽  
Xiaoyong Ma ◽  
Xiangyu Zhou ◽  
Pengzhen Cheng ◽  
Kai He ◽  
...  
Keyword(s):  
Information Integration ◽  
Short Term Memory ◽  
Superior Performance ◽  
Supplementary Information ◽  
Specific Information ◽  
Coreference Resolution ◽  
Fine Grained ◽  
Domain Specific ◽  
Memory Network ◽  
Biomedical Texts

Abstract Motivation Bio-entity Coreference Resolution focuses on identifying the coreferential links in biomedical texts, which is crucial to complete bio-events’ attributes and interconnect events into bio-networks. Previously, as one of the most powerful tools, deep neural network-based general domain systems are applied to the biomedical domain with domain-specific information integration. However, such methods may raise much noise due to its insufficiency of combining context and complex domain-specific information. Results In this paper, we explore how to leverage the external knowledge base in a fine-grained way to better resolve coreference by introducing a knowledge-enhanced Long Short Term Memory network (LSTM), which is more flexible to encode the knowledge information inside the LSTM. Moreover, we further propose a knowledge attention module to extract informative knowledge effectively based on contexts. The experimental results on the BioNLP and CRAFT datasets achieve state-of-the-art performance, with a gain of 7.5 F1 on BioNLP and 10.6 F1 on CRAFT. Additional experiments also demonstrate superior performance on the cross-sentence coreferences. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals A Hybrid Deep Learning Model for Predicting Protein Hydroxylation Sites

2018 ◽  
Vol 19 (9) ◽  
pp. 2817 ◽  
Author(s):  
Haixia Long ◽  
Bo Liao ◽  
Xingyu Xu ◽  
Jialiang Yang
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Learning Model ◽  
New Drugs ◽  
Post Translational Modifications ◽  
Novel Approach ◽  
Benchmark Datasets ◽  
Memory Network ◽  
Scoring Matrix ◽  
Deep Learning Model

Protein hydroxylation is one type of post-translational modifications (PTMs) playing critical roles in human diseases. It is known that protein sequence contains many uncharacterized residues of proline and lysine. The question that needs to be answered is: which residue can be hydroxylated, and which one cannot. The answer will not only help understand the mechanism of hydroxylation but can also benefit the development of new drugs. In this paper, we proposed a novel approach for predicting hydroxylation using a hybrid deep learning model integrating the convolutional neural network (CNN) and long short-term memory network (LSTM). We employed a pseudo amino acid composition (PseAAC) method to construct valid benchmark datasets based on a sliding window strategy and used the position-specific scoring matrix (PSSM) to represent samples as inputs to the deep learning model. In addition, we compared our method with popular predictors including CNN, iHyd-PseAAC, and iHyd-PseCp. The results for 5-fold cross-validations all demonstrated that our method significantly outperforms the other methods in prediction accuracy.

scholarly journals Using BiLSTM Networks for Context-Aware Deep Sensitivity Labelling on Conversational Data

2020 ◽  
Vol 10 (24) ◽  
pp. 8924
Author(s):  
Antreas Pogiatzis ◽  
Georgios Samakovitis
Keyword(s):  
Conditional Random Fields ◽  
Short Term Memory ◽  
Model Performance ◽  
Design Feature ◽  
Sensitive Information ◽  
Context Aware ◽  
Improve Model ◽  
Unseen Data ◽  
Memory Network ◽  
Series Of Experiments

Information privacy is a critical design feature for any exchange system, with privacy-preserving applications requiring, most of the time, the identification and labelling of sensitive information. However, privacy and the concept of “sensitive information” are extremely elusive terms, as they are heavily dependent upon the context they are conveyed in. To accommodate such specificity, we first introduce a taxonomy of four context classes to categorise relationships of terms with their textual surroundings by meaning, interaction, precedence, and preference. We then propose a predictive context-aware model based on a Bidirectional Long Short Term Memory network with Conditional Random Fields (BiLSTM + CRF) to identify and label sensitive information in conversational data (multi-class sensitivity labelling). We train our model on a synthetic annotated dataset of real-world conversational data categorised in 13 sensitivity classes that we derive from the P3P standard. We parameterise and run a series of experiments featuring word and character embeddings and introduce a set of auxiliary features to improve model performance. Our results demonstrate that the BiLSTM + CRF model architecture with BERT embeddings and WordShape features is the most effective (F1 score 96.73%). Evaluation of the model is conducted under both temporal and semantic contexts, achieving a 76.33% F1 score on unseen data and outperforms Google’s Data Loss Prevention (DLP) system on sensitivity labelling tasks.

scholarly journals Deep Learning based Semantic Similarity Detection using Text Data

2020 ◽  
Vol 49 (4) ◽  
pp. 495-510
Author(s):  
Muhammad Mansoor ◽  
Zahoor ur Rehman ◽  
Muhammad Shaheen ◽  
Muhammad Attique Khan ◽  
Mohamed Habib
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Short Term Memory ◽  
Main Task ◽  
Detection Algorithms ◽  
Similarity Detection ◽  
Novel Approach ◽  
Proposed Model ◽  
Memory Network ◽  
Numeric Data

Similarity detection in the text is the main task for a number of Natural Language Processing (NLP) applications. As textual data is comparatively large in quantity and huge in volume than the numeric data, therefore measuring textual similarity is one of the important problems. Most of the similarity detection algorithms are based upon word to word matching, sentence/paragraph matching, and matching of the whole document. In this research, a novel approach is proposed using deep learning models, combining Long Short Term Memory network (LSTM) with Convolutional Neural Network (CNN) for measuring semantics similarity between two questions. The proposed model takes sentence pairs as input to measure the similarity between them. The model is tested on publicly available Quora’s dataset. The model in comparison to the existing techniques gave 87.50 % accuracy which is better than the previous approaches.

Deep-Kcr: accurate detection of lysine crotonylation sites using deep learning method

2020 ◽  
Author(s):  
Hao Lv ◽  
Fu-Ying Dao ◽  
Zheng-Xing Guan ◽  
Hui Yang ◽  
Yan-Wen Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Short Term Memory ◽  
Information Gain ◽  
Independent Set ◽  
Cost Effective ◽  
Cellular Regulation ◽  
Proposed Model ◽  
Experimental Approaches ◽  
Memory Network

Abstract As a newly discovered protein posttranslational modification, histone lysine crotonylation (Kcr) involved in cellular regulation and human diseases. Various proteomics technologies have been developed to detect Kcr sites. However, experimental approaches for identifying Kcr sites are often time-consuming and labor-intensive, which is difficult to widely popularize in large-scale species. Computational approaches are cost-effective and can be used in a high-throughput manner to generate relatively precise identification. In this study, we develop a deep learning-based method termed as Deep-Kcr for Kcr sites prediction by combining sequence-based features, physicochemical property-based features and numerical space-derived information with information gain feature selection. We investigate the performances of convolutional neural network (CNN) and five commonly used classifiers (long short-term memory network, random forest, LogitBoost, naive Bayes and logistic regression) using 10-fold cross-validation and independent set test. Results show that CNN could always display the best performance with high computational efficiency on large dataset. We also compare the Deep-Kcr with other existing tools to demonstrate the excellent predictive power and robustness of our method. Based on the proposed model, a webserver called Deep-Kcr was established and is freely accessible at http://lin-group.cn/server/Deep-Kcr.

Deep learning-based container throughput forecasting: a triple bottom line approach

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sonali Shankar ◽  
Sushil Punia ◽  
P. Vigneswara Ilavarasan
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Moving Average ◽  
Short Term ◽  
Bottom Line ◽  
Content Type ◽  
Autoregressive Integrated Moving Average ◽  
Forecasting Method ◽  
Memory Network ◽  
Long Short Term Memory

PurposeContainer throughput forecasting plays a pivotal role in strategic, tactical and operational level decision-making. The determination and analysis of the influencing factors of container throughput are observed to enhance the predicting accuracy. Therefore, for effective port planning and management, this study employs a deep learning-based method to forecast the container throughput while considering the influence of economic, environmental and social factors on throughput forecasting.Design/methodology/approachA novel multivariate container throughput forecasting method is proposed using long short-term memory network (LSTM). The external factors influencing container throughput, delineated using triple bottom line, are considered as an input to the forecasting method. The principal component analysis (PCA) is employed to reduce the redundancy of the input variables. The container throughput data of the Port of Los Angeles (PLA) is considered for empirical analysis. The forecasting accuracy of the proposed method is measured via an error matrix. The accuracy of the results is further substantiated by the Diebold-Mariano statistical test.FindingsThe result of the proposed method is benchmarked with vector autoregression (VAR), autoregressive integrated moving average (ARIMAX) and LSTM. It is observed that the proposed method outperforms other counterpart methods. Though PCA was not an integral part of the forecasting process, it facilitated the prediction by means of “less data, more accuracy.”Originality/valueA novel deep learning-based forecasting method is proposed to predict container throughput using a hybridized autoregressive integrated moving average with external factors model and long short-term memory network (ARIMAX-LSTM).

scholarly journals Deep Learning Based on Multi-Decomposition for Short-Term Load Forecasting

Energies ◽  
2018 ◽  
Vol 11 (12) ◽  
pp. 3433 ◽  
Author(s):  
Seon Kim ◽  
Gyul Lee ◽  
Gu-Young Kwon ◽  
Do-In Kim ◽  
Yong-June Shin
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Load Forecasting ◽  
Small Scale ◽  
Intrinsic Mode Functions ◽  
Short Term ◽  
Term Memory ◽  
Load Profile ◽  
Memory Network ◽  
Long Short Term Memory

Load forecasting is a key issue for efficient real-time energy management in smart grids. To control the load using demand side management accurately, load forecasting should be predicted in the short term. With the advent of advanced measuring infrastructure, it is possible to measure energy consumption at sampling rates up to every 5 min and analyze the load profile of small-scale energy groups, such as individual buildings. This paper presents applications of deep learning using feature decomposition for improving the accuracy of load forecasting. The load profile is decomposed into a weekly load profile and then decomposed into intrinsic mode functions by variational mode decomposition to capture periodic features. Then, a long short-term memory network model is trained by three-dimensional input data with three-step regularization. Finally, the prediction results of all intrinsic mode functions are combined with advanced measuring infrastructure measured in the previous steps to determine an aggregated output for load forecasting. The results are validated by applications to real-world data from smart buildings, and the performance of the proposed approach is assessed by comparing the predicted results with those of conventional methods, nonlinear autoregressive networks with exogenous inputs, and long short-term memory network-based feature decomposition.

scholarly journals Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1064
Author(s):  
I Nyoman Kusuma Wardana ◽  
Julian W. Gardner ◽  
Suhaib A. Fahmy
Keyword(s):  
Deep Learning ◽  
Air Quality ◽  
Short Term Memory ◽  
Model Performance ◽  
Learning Model ◽  
Sensor Data ◽  
Raspberry Pi ◽  
Learning Models ◽  
Proposed Model ◽  
Deep Learning Model

Accurate air quality monitoring requires processing of multi-dimensional, multi-location sensor data, which has previously been considered in centralised machine learning models. These are often unsuitable for resource-constrained edge devices. In this article, we address this challenge by: (1) designing a novel hybrid deep learning model for hourly PM2.5 pollutant prediction; (2) optimising the obtained model for edge devices; and (3) examining model performance running on the edge devices in terms of both accuracy and latency. The hybrid deep learning model in this work comprises a 1D Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) to predict hourly PM2.5 concentration. The results show that our proposed model outperforms other deep learning models, evaluated by calculating RMSE and MAE errors. The proposed model was optimised for edge devices, the Raspberry Pi 3 Model B+ (RPi3B+) and Raspberry Pi 4 Model B (RPi4B). This optimised model reduced file size to a quarter of the original, with further size reduction achieved by implementing different post-training quantisation. In total, 8272 hourly samples were continuously fed to the edge device, with the RPi4B executing the model twice as fast as the RPi3B+ in all quantisation modes. Full-integer quantisation produced the lowest execution time, with latencies of 2.19 s and 4.73 s for RPi4B and RPi3B+, respectively.

scholarly journals Deep Learning for emotion analysis in Arabic tweets

2021 ◽  
Author(s):  
ENAS ABDEL HAKIM KHALIL ◽  
Enas .M.F. El Houby ◽  
Hoda .k. Mohamed
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Short Term Memory ◽  
Model Performance ◽  
Support Vector ◽  
Emotion Classification ◽  
Network Layers ◽  
Learning Techniques ◽  
Comparable Performance ◽  
Fully Connected

Abstract Expressing our emotions using text and emojis expressions became widespread through social media such as Facebook, Instagram, Twitter, Weibo, and LinkedIn. Nowadays, both organizations and individuals are interested in using social media to analyze people's opinions and extract sentiments and emotions. We proposed a model for multilabel emotion classification, using a bidirectional Long Short-term Memory BiLSTM deep network. It is evaluated on the Arabic tweets' dataset provided by SemEval 2018 for the E-c task. Several preprocessing steps, including ARLSTEM with some modifications, replacing emojis with corresponding text meaning from a manually built lexicon, and feature vector representation using Aravec word embedding is applied. The novelty in our research that it examines the effect of hyperparameter tuning on model performance, and it uses BiLSTM in all of its deep neural network layers. The proposed model achieves a comparable performance with state-of-the-art models using different machine learning and deep learning techniques. The system achieves about 9% enhancement in validation accuracy compared with the last best model in the same task using Support Vector classifier SVC; it outperforms the other deep neural networks (UNCCTeam) based on fully connected layers in micro F1 metric of about 4.4%.

Sign in / Sign up

Export Citation Format

Share Document