Special Issue "Statistical Machine Learning for Multimodal Data Analysis"

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Signal and Data Analysis".

Deadline for manuscript submissions: closed (1 November 2020).

Special Issue Editor

Prof. Dr. Athanasios Voulodimos
E-Mail Website
Guest Editor
Department of Informatics and Computer Engineering, University of West Attica, Agiou Spiridonos 28, 122 43 Egaleo, Greece
Interests: machine learning; artificial intelligence; multimedia; intelligent systems; pervasive computing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Methods and algorithms in statistical machine learning explore relationships between variables in large, complex datasets in supervised, unsupervised or semi-supervised manners. Significant research results have been presented in recent years on a variety of topics, including linear and nonlinear regression, classification, clustering, resampling methods, model selection, and regularization. Furthermore, the latest strides in deep, reinforcement, and adversarial learning in conjunction with increasing availability of data from a wide variety of modalities (visual, thermal, hyperspectral, audio/speech, textual, radar, network traffic, energy, Channel State Information, and others) provide great opportunities and at the same time significant challenges for theoretical advancements and novel practical developments in a variety of application domains. This Special Issue solicits original research papers as well as review articles and short communications in the above-described areas. Topics of interest include, without being limited to, the following:

  • Statistical machine learning and pattern recognition techniques for fusion and/or understanding of multimodal, multisensorial, and/or heterogeneous data;
  • Deep learning and reinforcement learning for multimodal data and signal analysis;
  • Generative adversarial networks for multimodal data analysis;
  • Optimization methods for training of statistical models and tuning of hyperparameters;
  • Quantitative evaluation, comparison and benchmarking of statistical learning methods;
  • Statistical methods for handling class imbalance and data irregularities;
  • Explainability and interpretability in statistical machine learning;
  • Applications of statistical machine learning in real-world problems.

Dr. Athanasios Voulodimos
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Statistical machine learning
  • Pattern recognition
  • Deep learning
  • Reinforcement learning
  • Adversarial learning
  • Hyperparameter optimization
  • Multisensorial data fusion and analysis
  • Multimodal signal processing
  • Explainability and interpretability in machine learning

Published Papers (8 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Transportation Mode Detection Using an Optimized Long Short-Term Memory Model on Multimodal Sensor Data
Entropy 2021, 23(11), 1457; https://0-doi-org.brum.beds.ac.uk/10.3390/e23111457 - 03 Nov 2021
Viewed by 371
Abstract
The advancement of sensing technologies coupled with the rapid progress in big data analysis has ushered in a new era in intelligent transport and smart city applications. In this context, transportation mode detection (TMD) of mobile users is a field that has gained [...] Read more.
The advancement of sensing technologies coupled with the rapid progress in big data analysis has ushered in a new era in intelligent transport and smart city applications. In this context, transportation mode detection (TMD) of mobile users is a field that has gained significant traction in recent years. In this paper, we present a deep learning approach for transportation mode detection using multimodal sensor data elicited from user smartphones. The approach is based on long short-term Memory networks and Bayesian optimization of their parameters. We conducted an extensive experimental evaluation of the proposed approach, which attains very high recognition rates, against a multitude of machine learning approaches, including state-of-the-art methods. We also discuss issues regarding feature correlation and the impact of dimensionality reduction. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Article
Measuring Software Maintainability with Naïve Bayes Classifier
Entropy 2021, 23(2), 136; https://0-doi-org.brum.beds.ac.uk/10.3390/e23020136 - 22 Jan 2021
Cited by 1 | Viewed by 1303
Abstract
Software products in the market are changing due to changes in business processes, technology, or new requirements from the customers. Maintainability of legacy systems has always been an inspiring task for the software companies. In order to determine whether the software requires maintainability [...] Read more.
Software products in the market are changing due to changes in business processes, technology, or new requirements from the customers. Maintainability of legacy systems has always been an inspiring task for the software companies. In order to determine whether the software requires maintainability by reverse engineering or by forward engineering approach, a system assessment was done from diverse perspectives: quality, business value, type of errors, etc. In this research, the changes required in the existing software components of the legacy system were identified using a supervised learning approach. New interfaces for the software components were redesigned according to the new requirements and/or type of errors. Software maintainability was measured by applying a machine learning technique, i.e., Naïve Bayes classifier. The dataset was designed based on the observations such as component state, successful or error type in the component, line of code of error that exists in the component, component business value, and changes required for the component or not. The results generated by the Waikato Environment for Knowledge Analysis (WEKA) software confirm the effectiveness of the introduced methodology with an accuracy of 97.18%. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Article
How to Utilize My App Reviews? A Novel Topics Extraction Machine Learning Schema for Strategic Business Purposes
Entropy 2020, 22(11), 1310; https://0-doi-org.brum.beds.ac.uk/10.3390/e22111310 - 17 Nov 2020
Viewed by 1000
Abstract
Acquiring knowledge about users’ opinion and what they say regarding specific features within an app, constitutes a solid steppingstone for understanding their needs and concerns. App review utilization helps project management teams to identify threads and opportunities for app software maintenance, optimization and [...] Read more.
Acquiring knowledge about users’ opinion and what they say regarding specific features within an app, constitutes a solid steppingstone for understanding their needs and concerns. App review utilization helps project management teams to identify threads and opportunities for app software maintenance, optimization and strategic marketing purposes. Nevertheless, app user review classification for identifying valuable gems of information for app software improvement, is a complex and multidimensional issue. It requires foresight and multiple combinations of sophisticated text pre-processing, feature extraction and machine learning methods to efficiently classify app reviews into specific topics. Against this backdrop, we propose a novel feature engineering classification schema that is capable to identify more efficiently and earlier terms-words within reviews that could be classified into specific topics. For this reason, we present a novel feature extraction method, the DEVMAX.DF combined with different machine learning algorithms to propose a solution in app review classification problems. One step further, a simulation of a real case scenario takes place to validate the effectiveness of the proposed classification schema into different apps. After multiple experiments, results indicate that the proposed schema outperforms other term extraction methods such as TF.IDF and χ2 to classify app reviews into topics. To this end, the paper contributes to the knowledge expansion of research and practitioners with the purpose to reinforce their decision-making process within the realm of app reviews utilization. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Article
TNT: An Interpretable Tree-Network-Tree Learning Framework using Knowledge Distillation
Entropy 2020, 22(11), 1203; https://0-doi-org.brum.beds.ac.uk/10.3390/e22111203 - 24 Oct 2020
Cited by 3 | Viewed by 1157
Abstract
Deep Neural Networks (DNNs) usually work in an end-to-end manner. This makes the trained DNNs easy to use, but they remain an ambiguous decision process for every test case. Unfortunately, the interpretability of decisions is crucial in some scenarios, such as medical or [...] Read more.
Deep Neural Networks (DNNs) usually work in an end-to-end manner. This makes the trained DNNs easy to use, but they remain an ambiguous decision process for every test case. Unfortunately, the interpretability of decisions is crucial in some scenarios, such as medical or financial data mining and decision-making. In this paper, we propose a Tree-Network-Tree (TNT) learning framework for explainable decision-making, where the knowledge is alternately transferred between the tree model and DNNs. Specifically, the proposed TNT learning framework exerts the advantages of different models at different stages: (1) a novel James–Stein Decision Tree (JSDT) is proposed to generate better knowledge representations for DNNs, especially when the input data are in low-frequency or low-quality; (2) the DNNs output high-performing prediction result from the knowledge embedding inputs and behave as a teacher model for the following tree model; and (3) a novel distillable Gradient Boosted Decision Tree (dGBDT) is proposed to learn interpretable trees from the soft labels and make a comparable prediction as DNNs do. Extensive experiments on various machine learning tasks demonstrated the effectiveness of the proposed method. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Article
Deep-Learning-Based Power Generation Forecasting of Thermal Energy Conversion
Entropy 2020, 22(10), 1161; https://0-doi-org.brum.beds.ac.uk/10.3390/e22101161 - 15 Oct 2020
Cited by 1 | Viewed by 728
Abstract
ORC is a heat to power solution to convert low-grade thermal energy into electricity with relative low cost and adequate efficiency. The working of ORC relies on the liquid–vapor phase changes of certain organic fluid under different temperature and pressure. ORC is a [...] Read more.
ORC is a heat to power solution to convert low-grade thermal energy into electricity with relative low cost and adequate efficiency. The working of ORC relies on the liquid–vapor phase changes of certain organic fluid under different temperature and pressure. ORC is a well-established technology utilized in industry to recover industrial waste heat to electricity. However, the frequently varied temperature, pressure, and flow may raise difficulty to maintain a steady power generation from ORC. It is important to develop an effective prediction methodology for power generation in a stable grid system. This study proposes a methodology based on deep learning neural network to the predict power generation from ORC by 12 h in advance. The deep learning neural network is derived from long short-term memory network (LSTM), a type of recurrent neural network (RNN). A case study was conducted through analysis of ORC data from steel company. Different time series methodology including ARIMA and MLP were compared with LSTM in this study and shows the error rate decreased by 24% from LSTM. The proposed methodology can be used to effectively optimize the system warning threshold configuration for the early detection of abnormalities in power generators and a novel approach for early diagnosis in conventional industries. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Article
Twin Least Square Support Vector Regression Model Based on Gauss-Laplace Mixed Noise Feature with Its Application in Wind Speed Prediction
Entropy 2020, 22(10), 1102; https://0-doi-org.brum.beds.ac.uk/10.3390/e22101102 - 29 Sep 2020
Cited by 2 | Viewed by 705
Abstract
In this article, it was observed that the noise in some real-world applications, such as wind power forecasting and direction of the arrival estimation problem, does not satisfy the single noise distribution, including Gaussian distribution and Laplace distribution, but the mixed distribution. Therefore, [...] Read more.
In this article, it was observed that the noise in some real-world applications, such as wind power forecasting and direction of the arrival estimation problem, does not satisfy the single noise distribution, including Gaussian distribution and Laplace distribution, but the mixed distribution. Therefore, combining the twin hyperplanes with the fast speed of Least Squares Support Vector Regression (LS-SVR), and then introducing the Gauss–Laplace mixed noise feature, a new regressor, called Gauss-Laplace Twin Least Squares Support Vector Regression (GL-TLSSVR), for the complex noise. Subsequently, we apply the augmented Lagrangian multiplier method to solve the proposed model. Finally, we apply the short-term wind speed data-set to the proposed model. The results of this experiment confirm the effectiveness of our proposed model. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Article
Ensemble Learning Using Fuzzy Weights to Improve Learning Style Identification for Adapted Instructional Routines
Entropy 2020, 22(7), 735; https://0-doi-org.brum.beds.ac.uk/10.3390/e22070735 - 02 Jul 2020
Cited by 10 | Viewed by 1187
Abstract
Mobile personalized learning can be achieved by the identification of students’ learning styles; however, this happens with the completion of large questionnaires. This task has been reported as tedious and time-consuming, causing random selection of the questionnaires’ choices, and thus, erroneous adaptation to [...] Read more.
Mobile personalized learning can be achieved by the identification of students’ learning styles; however, this happens with the completion of large questionnaires. This task has been reported as tedious and time-consuming, causing random selection of the questionnaires’ choices, and thus, erroneous adaptation to students’ needs, endangering knowledge acquisition. Moreover, mobile environments render the selection of questionnaires’ choices impractical due to confined mobile user interfaces. In view of the above, this paper presents Learnglish, a fully developed mobile language learning system incorporating automatic identification of students’ learning styles according to the Felder-Silverman model (FSLSM) using ensemble classification. In particular, three classifiers, namely SVM, NB and KNN, are combined based on the majority voting rule. The major innovation of this task, apart from the ensemble classification and the mobile learning environment, is that Learnglish takes as input a minimum number of personal (i.e., age and gender) and cognitive characteristics (i.e., prior academic performance categorized using fuzzy weights), and solely four questions pertaining to the FSLSM dimensions, to identify the learning style. Furthermore, Learnglish incorporates adapted instructional routines to create an individualized learning environment based on students’ learning preferences as determined by their style. Learnglish was fully evaluated with very encouraging results. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Article
Weighted Quantile Regression Forests for Bimodal Distribution Modeling: A Loss Given Default Case
Entropy 2020, 22(5), 545; https://0-doi-org.brum.beds.ac.uk/10.3390/e22050545 - 13 May 2020
Cited by 2 | Viewed by 1168
Abstract
Due to various regulations (e.g., the Basel III Accord), banks need to keep a specified amount of capital to reduce the impact of their insolvency. This equity can be calculated using, e.g., the Internal Rating Approach, enabling institutions to develop their own statistical [...] Read more.
Due to various regulations (e.g., the Basel III Accord), banks need to keep a specified amount of capital to reduce the impact of their insolvency. This equity can be calculated using, e.g., the Internal Rating Approach, enabling institutions to develop their own statistical models. In this regard, one of the most important parameters is the loss given default, whose correct estimation may lead to a healthier and riskless allocation of the capital. Unfortunately, since the loss given default distribution is a bimodal application of the modeling methods (e.g., ordinary least squares or regression trees), aiming at predicting the mean value is not enough. Bimodality means that a distribution has two modes and has a large proportion of observations with large distances from the middle of the distribution; therefore, to overcome this fact, more advanced methods are required. To this end, to model the entire loss given default distribution, in this article we present the weighted quantile Regression Forest algorithm, which is an ensemble technique. We evaluate our methodology over a dataset collected by one of the biggest Polish banks. Through our research, we show that weighted quantile Regression Forests outperform “single” state-of-the-art models in terms of their accuracy and the stability. Full article
(This article belongs to the Special Issue Statistical Machine Learning for Multimodal Data Analysis)
Show Figures

Figure 1

Back to TopTop