Analysis of Unsatisfying User Experiences and Unmet Psychological Needs for Virtual Reality Exergames Using Deep Learning Approach

The number of consumers playing virtual reality games is booming. To speed up product iteration, the user experience team needs to collect and analyze unsatisfying experiences in time. In this paper, we aim to detect the unsatisfying experiences hidden in online reviews of virtual reality exergames using a deep learning method and find out the unmet psychological needs of users based on self-determination theory. Convolutional neural networks for sentence classification (textCNN) are used in this study to classify online reviews with unsatisfying experiences. For comparison, we set eXtreme gradient boosting (XGBoost) with lexical features as the baseline of machine learning. Term frequency-inverse document frequency (TF-IDF) is used to extract keywords from every set of classified reviews. The micro-F1 score of textCNN classifier is 90.00, which is better than 82.69 of XGBoost. The top 10 keywords of every set of reviews reflect relevant topics of unmet psychological needs. This paper explores the potential problems causing unsatisfying experiences and unmet psychological needs in virtual reality exergames through text mining and makes a supplement for experimental studies about virtual reality exergames.

Download Full-text

Extreme Gradient Boosting for Cyberpropaganda Detection

10.3233/faia210012 ◽

2021 ◽

Author(s):

Jaouhar Fattahi ◽

Mohamed Mejri ◽

Marwa Ziadia

Keyword(s):

Machine Learning ◽

Social Networks ◽

Gradient Boosting ◽

The Internet ◽

Bag Of Words ◽

Fake News ◽

Inverse Document Frequency ◽

Document Frequency ◽

Extreme Gradient Boosting ◽

New Phenomena

Propaganda, defamation, abuse, insults, disinformation and fake news are not new phenomena and have been around for several decades. However, with the advent of the Internet and social networks, their magnitude has increased and the damage caused to individuals and corporate entities is becoming increasingly greater, even irreparable. In this paper, we tackle the detection of text-based cyberpropaganda using Machine Learning and NLP techniques. We use the eXtreme Gradient Boosting (XGBoost) algorithm for learning and detection, in tandem with Bag-of-Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) for text vectorization. We highlight the contribution of gradient boosting and regularization mechanisms in the performance of the explored model.

Download Full-text

DeepVF: a deep learning-based hybrid framework for identifying virulence factors using the stacking strategy

Briefings in Bioinformatics ◽

10.1093/bib/bbaa125 ◽

2020 ◽

Cited By ~ 2

Author(s):

Ruopeng Xie ◽

Jiahui Li ◽

Jiawei Wang ◽

Wei Dai ◽

André Leier ◽

...

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Virulence Factors ◽

Bacterial Genome ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Wide Range ◽

Extreme Gradient Boosting ◽

Hybrid Framework

Abstract Virulence factors (VFs) enable pathogens to infect their hosts. A wealth of individual, disease-focused studies has identified a wide variety of VFs, and the growing mass of bacterial genome sequence data provides an opportunity for computational methods aimed at predicting VFs. Despite their attractive advantages and performance improvements, the existing methods have some limitations and drawbacks. Firstly, as the characteristics and mechanisms of VFs are continually evolving with the emergence of antibiotic resistance, it is more and more difficult to identify novel VFs using existing tools that were previously developed based on the outdated data sets; secondly, few systematic feature engineering efforts have been made to examine the utility of different types of features for model performances, as the majority of tools only focused on extracting very few types of features. By addressing the aforementioned issues, the accuracy of VF predictors can likely be significantly improved. This, in turn, would be particularly useful in the context of genome wide predictions of VFs. In this work, we present a deep learning (DL)-based hybrid framework (termed DeepVF) that is utilizing the stacking strategy to achieve more accurate identification of VFs. Using an enlarged, up-to-date dataset, DeepVF comprehensively explores a wide range of heterogeneous features with popular machine learning algorithms. Specifically, four classical algorithms, including random forest, support vector machines, extreme gradient boosting and multilayer perceptron, and three DL algorithms, including convolutional neural networks, long short-term memory networks and deep neural networks are employed to train 62 baseline models using these features. In order to integrate their individual strengths, DeepVF effectively combines these baseline models to construct the final meta model using the stacking strategy. Extensive benchmarking experiments demonstrate the effectiveness of DeepVF: it achieves a more accurate and stable performance compared with baseline models on the benchmark dataset and clearly outperforms state-of-the-art VF predictors on the independent test. Using the proposed hybrid ensemble model, a user-friendly online predictor of DeepVF (http://deepvf.erc.monash.edu/) is implemented. Furthermore, its utility, from the user’s viewpoint, is compared with that of existing toolkits. We believe that DeepVF will be exploited as a useful tool for screening and identifying potential VFs from protein-coding gene sequences in bacterial genomes.

Download Full-text

Reply Using Past Replies—A Deep Learning-Based E-Mail Client

Electronics ◽

10.3390/electronics9091353 ◽

2020 ◽

Vol 9 (9) ◽

pp. 1353

Author(s):

Yiwei Feng ◽

M. Asif Naeem ◽

Farhaan Mirza ◽

Ali Tahir

Keyword(s):

Deep Learning ◽

Hybrid Model ◽

Learning Algorithm ◽

Inverse Document Frequency ◽

Help Desk ◽

Deep Learning Algorithm ◽

Document Frequency ◽

Text Prediction ◽

E Mail ◽

Gated Recurrent Unit

Email is the most common and effective source of communication for most enterprises and individuals. In the corporate sector the volume of email received daily is significant while timely reply of each email is important. This generates a huge amount of work for the organisation, in particular for the staff located in the help-desk role. In this paper we present a novel Smart E-mail Management System (SEMS) for handling the issue of E-mail overload. The Term Frequency-Inverse Document Frequency (TF-IDF) model was used for designing a Smart Email Client in previous research. Since TF-IDF does not consider semantics between words, the replies suggested by the model are not very accurate. In this paper we apply Document to Vector (Doc2Vec) and introduce a novel Gated Recurrent Unit Sentence to Vector (GRU-Sent2Vec), which is a hybrid model by combining GRU and Sent2Vec. Both models are more intelligent as compared to TF-IDF. We compare our results from both models with TF-IDF. The Doc2Vec model performs the best on predicting a response for a similar new incoming Email. In our case, since the dataset is too small to require a deep learning algorithm model, the GRU-Sent2Vec hybrid model cannot produce ideal results, whereas in our understanding it is a robust method for long-text prediction.

Download Full-text

Detection and Identification of Organic Pollutants in Drinking Water from Fluorescence Spectra Based on Deep Learning Using Convolutional Autoencoder

Water ◽

10.3390/w13192633 ◽

2021 ◽

Vol 13 (19) ◽

pp. 2633

Author(s):

Jie Yu ◽

Yitong Cao ◽

Fei Shi ◽

Jiegen Shi ◽

Dibo Hou ◽

...

Keyword(s):

Drinking Water ◽

Deep Learning ◽

Fluorescence Spectroscopy ◽

Organic Pollutants ◽

Learning Algorithm ◽

Three Dimensional ◽

Gradient Boosting ◽

Spectral Processing ◽

Extreme Gradient Boosting ◽

Convolutional Autoencoder

Three dimensional fluorescence spectroscopy has become increasingly useful in the detection of organic pollutants. However, this approach is limited by decreased accuracy in identifying low concentration pollutants. In this research, a new identification method for organic pollutants in drinking water is accordingly proposed using three-dimensional fluorescence spectroscopy data and a deep learning algorithm. A novel application of a convolutional autoencoder was designed to process high-dimensional fluorescence data and extract multi-scale features from the spectrum of drinking water samples containing organic pollutants. Extreme Gradient Boosting (XGBoost), an implementation of gradient-boosted decision trees, was used to identify the organic pollutants based on the obtained features. Method identification performance was validated on three typical organic pollutants in different concentrations for the scenario of accidental pollution. Results showed that the proposed method achieved increasing accuracy, in the case of both high-(>10 μg/L) and low-(≤10 μg/L) concentration pollutant samples. Compared to traditional spectrum processing techniques, the convolutional autoencoder-based approach enabled obtaining features of enhanced detail from fluorescence spectral data. Moreover, evidence indicated that the proposed method maintained the detection ability in conditions whereby the background water changes. It can effectively reduce the rate of misjudgments associated with the fluctuation of drinking water quality. This study demonstrates the possibility of using deep learning algorithms for spectral processing and contamination detection in drinking water.

Download Full-text

Automatic Complaints Categorization Using Random Forest and Gradient Boosting

Advance Sustainable Science, Engineering and Technology ◽

10.26877/asset.v3i1.8460 ◽

2021 ◽

Vol 3 (1) ◽

pp. 0210106

Author(s):

Muchamad Taufiq Anwar

Keyword(s):

Random Forest ◽

Gradient Boosting ◽

Future Research ◽

Research Directions ◽

Inverse Document Frequency ◽

The Public ◽

Bangalore City ◽

Document Frequency ◽

Future Research Directions ◽

Multi Class Classification

Capturing and responding to complaints from the public is an important effort to develop a good city/country. This project aims to utilize Data Mining to automatize complaints categorization. More than 35,000 complaints in Bangalore city, India, were retrieved from the “I Change My City” website (https://www.ichangemycity.com). The vector space of the complaints was created using Term Frequency–Inverse Document Frequency (TF-IDF) and the multi-class text classifications were done using Random Forest (RF) and Gradient Boosting (GB). Results showed that both RF and GB have similar performance with an accuracy of 73% on the 10-classes multi-class classification task. Result also showed that the model is highly dependent on the word usage in the complaint's description. Future research directions to increase task performance are also suggested.

Download Full-text

A Method of Product Selection Based on Online Reviews

Mobile Information Systems ◽

10.1155/2021/9656315 ◽

2021 ◽

Vol 2021 ◽

pp. 1-16

Author(s):

Xia Liang ◽

Jie Guo ◽

Yan Sun ◽

Xiaoxiao Liu

Keyword(s):

Sentiment Analysis ◽

Rapid Development ◽

Online Reviews ◽

Product Attributes ◽

Product Selection ◽

Inverse Document Frequency ◽

Roulette Wheel Selection ◽

Document Frequency ◽

Criteria Importance

With the rapid development of information technology and market economy, global e-commerce platform develops rapidly. Recently, online reviews are widely available on e-commerce platforms to express customers’ experience of products. When ranking alternative products based on online reviews, how to make full use of the information in online reviews to represent the sentiment analysis results of online reviews is an important prerequisite for decision analysis. To this end, we propose a method for measuring the time utility and support utility of online reviews. Then a method for representing the sentiment analysis results of online reviews in the form of linguistic distribution is proposed. In addition, in view of the attributes and their weights being unknown, we propose a method for extracting product attributes from online reviews by using the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm; and the objective weights of attributes are determined through the Criteria Importance through Intercriteria Correlation (CRITIC) method. Additionally, in order to highlight the differences between the alternatives, the roulette wheel selection algorithm is first used to randomly select product attributes. Then the alternative products can be ranked by the extended Multi-Attributive Border Approximation area Comparison (MABAC) method with mixed information. Finally, we illustrate the applicability of the proposed method through a case study of selecting a 5G mobile phone and simulation experiment.

Download Full-text

PM2.5 Prediction Based on Random Forest, XGBoost, and Deep Learning Using Multisource Remote Sensing Data

Atmosphere ◽

10.3390/atmos10070373 ◽

2019 ◽

Vol 10 (7) ◽

pp. 373 ◽

Cited By ~ 23

Author(s):

Mehdi Zamani Joharestani ◽

Chunxiang Cao ◽

Xiliang Ni ◽

Barjeece Bashir ◽

Somayeh Talebiesfandarani

Keyword(s):

Deep Learning ◽

Random Forest ◽

Meteorological Data ◽

Fine Particulate Matter ◽

Model Performance ◽

Remote Sensing Data ◽

Health Concern ◽

Gradient Boosting ◽

High Concentration ◽

Extreme Gradient Boosting

In recent years, air pollution has become an important public health concern. The high concentration of fine particulate matter with diameter less than 2.5 µm (PM2.5) is known to be associated with lung cancer, cardiovascular disease, respiratory disease, and metabolic disease. Predicting PM2.5 concentrations can help governments warn people at high risk, thus mitigating the complications. Although attempts have been made to predict PM2.5 concentrations, the factors influencing PM2.5 prediction have not been investigated. In this work, we study feature importance for PM2.5 prediction in Tehran’s urban area, implementing random forest, extreme gradient boosting, and deep learning machine learning (ML) approaches. We use 23 features, including satellite and meteorological data, ground-measured PM2.5, and geographical data, in the modeling. The best model performance obtained was R2 = 0.81 (R = 0.9), MAE = 9.93 µg/m3, and RMSE = 13.58 µg/m3 using the XGBoost approach, incorporating elimination of unimportant features. However, all three ML methods performed similarly and R2 varied from 0.63 to 0.67, when Aerosol Optical Depth (AOD) at 3 km resolution was included, and 0.77 to 0.81, when AOD at 3 km resolution was excluded. Contrary to the PM2.5 lag data, satellite-derived AODs did not improve model performance.

Download Full-text

Sovereign Debt and Currency Crises Prediction Models Using Machine Learning Techniques

Symmetry ◽

10.3390/sym13040652 ◽

2021 ◽

Vol 13 (4) ◽

pp. 652

Author(s):

David Alaminos ◽

José Ignacio Peláez ◽

M. Belén Salas ◽

Manuel A. Fernández-Gámez

Keyword(s):

Deep Learning ◽

Decision Trees ◽

Financial Crises ◽

Sovereign Debt ◽

Currency Crises ◽

Prediction Models ◽

Debt Crisis ◽

Gradient Boosting ◽

Computational Techniques ◽

Extreme Gradient Boosting

Sovereign debt and currencies play an increasingly influential role in the development of any country, given the need to obtain financing and establish international relations. A recurring theme in the literature on financial crises has been the prediction of sovereign debt and currency crises due to their extreme importance in international economic activity. Nevertheless, the limitations of the existing models are related to accuracy and the literature calls for more investigation on the subject and lacks geographic diversity in the samples used. This article presents new models for the prediction of sovereign debt and currency crises, using various computational techniques, which increase their precision. Also, these models present experiences with a wide global sample of the main geographical world zones, such as Africa and the Middle East, Latin America, Asia, Europe, and globally. Our models demonstrate the superiority of computational techniques concerning statistics in terms of the level of precision, which are the best methods for the sovereign debt crisis: fuzzy decision trees, AdaBoost, extreme gradient boosting, and deep learning neural decision trees, and for forecasting the currency crisis: deep learning neural decision trees, extreme gradient boosting, random forests, and deep belief network. Our research has a large and potentially significant impact on the macroeconomic policy adequacy of the countries against the risks arising from financial crises and provides instruments that make it possible to improve the balance in the finance of the countries.

Download Full-text

Automated diagnostic support system with deep learning algorithms for distinction of Philadelphia chromosome-negative myeloproliferative neoplasms using peripheral blood specimen

Scientific Reports ◽

10.1038/s41598-021-82826-9 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Konobu Kimura ◽

Tomohiko Ai ◽

Yuki Horiuchi ◽

Akihiko Matsuzaki ◽

Kumiko Nishibe ◽

...

Keyword(s):

Deep Learning ◽

Support System ◽

Peripheral Blood ◽

Myeloproliferative Neoplasms ◽

Marrow Cell ◽

Philadelphia Chromosome ◽

Learning System ◽

Gradient Boosting ◽

Extreme Gradient Boosting ◽

Diagnostic Support

AbstractPhiladelphia chromosome-negative myeloproliferative neoplasms (Ph-negative MPNs) such as polycythemia vera (PV), essential thrombocythemia (ET), and primary myelofibrosis are characterized by abnormal proliferation of mature bone marrow cell lineages. Since various non-hematologic disorders can also cause leukocytosis, thrombocytosis and polycythemia, the detection of abnormal peripheral blood cells is essential for the diagnostic screening of Ph-negative MPNs. We sought to develop an automated diagnostic support system of Ph-negative MPNs. Our strategy was to combine the complete blood cell count and research parameters obtained by an automated hematology analyzer (Sysmex XN-9000) with morphological parameters that were extracted using a convolutional neural network deep learning system equipped with an Extreme Gradient Boosting (XGBoost)-based decision-making algorithm. The developed system showed promising performance in the differentiation of PV, ET, and MF with high accuracy when compared with those of the human diagnoses, namely: > 90% sensitivity and > 90% specificity. The calculated area under the curve of the ROC curves were 0.990, 0.967, and 0.974 for PV, ET, MF, respectively. This study is a step toward establishing a universal automated diagnostic system for all types of hematology disorders.

Download Full-text

Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning

Frontiers in Pharmacology ◽

10.3389/fphar.2020.606668 ◽

2020 ◽

Vol 11 ◽

Author(s):

Liangxu Xie ◽

Lei Xu ◽

Ren Kong ◽

Shan Chang ◽

Xiaojun Xu

Keyword(s):

Deep Learning ◽

Short Term Memory ◽

Molecular Descriptor ◽

Predictive Performance ◽

Gradient Boosting ◽

Support Vector ◽

Quantitative Structure ◽

Structure Activity ◽

Extreme Gradient Boosting ◽

The Impact

The accurate predicting of physical properties and bioactivity of drug molecules in deep learning depends on how molecules are represented. Many types of molecular descriptors have been developed for quantitative structure-activity/property relationships quantitative structure-activity relationships (QSPR). However, each molecular descriptor is optimized for a specific application with encoding preference. Considering that standalone featurization methods may only cover parts of information of the chemical molecules, we proposed to build the conjoint fingerprint by combining two supplementary fingerprints. The impact of conjoint fingerprint and each standalone fingerprint on predicting performance was systematically evaluated in predicting the logarithm of the partition coefficient (logP) and binding affinity of protein-ligand by using machine learning/deep learning (ML/DL) methods, including random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), long short-term memory network (LSTM), and deep neural network (DNN). The results demonstrated that the conjoint fingerprint yielded improved predictive performance, even outperforming the consensus model using two standalone fingerprints among four out of five examined methods. Given that the conjoint fingerprint scheme shows easy extensibility and high applicability, we expect that the proposed conjoint scheme would create new opportunities for continuously improving predictive performance of deep learning by harnessing the complementarity of various types of fingerprints.

Download Full-text