Future Internet

Research

Jump to: Review

21 pages, 2275 KiB

Open AccessArticle

Target-Oriented Data Annotation for Emotion and Sentiment Analysis in Tourism Related Social Media Data

by Alireza Alaei, Ying Wang, Vinh Bui and Bela Stantic

Future Internet 2023, 15(4), 150; https://doi.org/10.3390/fi15040150 - 19 Apr 2023

Cited by 7 | Viewed by 2336

Abstract

Social media have been a valuable data source for studying people’s opinions, intentions, and behaviours. Such a data source incorporating advanced big data analysis methods, such as machine-operated emotion and sentiment analysis, will open unprecedented opportunities for innovative data-driven destination monitoring and management. [...] Read more.

Social media have been a valuable data source for studying people’s opinions, intentions, and behaviours. Such a data source incorporating advanced big data analysis methods, such as machine-operated emotion and sentiment analysis, will open unprecedented opportunities for innovative data-driven destination monitoring and management. However, a big challenge any machine-operated text analysis method faces is the ambiguity of the natural languages, which may cause an expression to have different meanings in different contexts. In this work, we address the ambiguity challenge by proposing a context-aware dictionary-based target-oriented emotion and sentiment analysis method that incorporates inputs from both humans and machines to introduce an alternative approach to measuring emotions and sentiment in limited tourism-related data. The study makes a methodological contribution by creating a target dictionary specifically for tourism sentiment analysis. To demonstrate the performance of the proposed method, a case of target-oriented emotion and sentiment analysis of posts from Twitter for the Gold Coast of Australia as a tourist destination was considered. The results suggest that Twitter data cover a broad range of destination attributes and can be a valuable source for comprehensive monitoring of tourist experiences at a destination. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

13 pages, 565 KiB

Open AccessArticle

Data Protection and Multi-Database Data-Driven Models

by Lili Jiang and Vicenç Torra

Future Internet 2023, 15(3), 93; https://doi.org/10.3390/fi15030093 - 27 Feb 2023

Cited by 2 | Viewed by 1729

Abstract

Anonymization and data masking have effects on data-driven models. Different anonymization methods have been developed to provide a good trade-off between privacy guarantees and data utility. Nevertheless, the effects of data protection (e.g., data microaggregation and noise addition) on data integration and on [...] Read more.

Anonymization and data masking have effects on data-driven models. Different anonymization methods have been developed to provide a good trade-off between privacy guarantees and data utility. Nevertheless, the effects of data protection (e.g., data microaggregation and noise addition) on data integration and on data-driven models (e.g., machine learning models) built from these data are not known. In this paper, we study how data protection affects data integration, and the corresponding effects on the results of machine learning models built from the outcome of the data integration process. The experimental results show that the levels of protection that prevent proper database integration do not affect machine learning models that learn from the integrated database to the same degree. Concretely, our preliminary analysis and experiments show that data protection techniques have a lower level of impact on data integration than on machine learning models. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

15 pages, 895 KiB

Open AccessArticle

Automatic Detection of Sensitive Data Using Transformer- Based Classifiers

by Michael Petrolini, Stefano Cagnoni and Monica Mordonini

Future Internet 2022, 14(8), 228; https://doi.org/10.3390/fi14080228 - 27 Jul 2022

Cited by 5 | Viewed by 4372

Abstract

The General Data Protection Regulation (GDPR) has allowed EU citizens and residents to have more control over their personal data, simplifying the regulatory environment affecting international business and unifying and homogenising privacy legislation within the EU. This regulation affects all companies that process [...] Read more.

The General Data Protection Regulation (GDPR) has allowed EU citizens and residents to have more control over their personal data, simplifying the regulatory environment affecting international business and unifying and homogenising privacy legislation within the EU. This regulation affects all companies that process data of European residents regardless of the place in which they are processed and their registered office, providing for a strict discipline of data protection. These companies must comply with the GDPR and be aware of the content of the data they manage; this is especially important if they are holding sensitive data, that is, any information regarding racial or ethnic origin, political opinions, religious or philosophical beliefs, trade union membership, data relating to the sexual life or sexual orientation of the person, as well as data on physical and mental health. These classes of data are hardly structured, and most frequently they appear within a document such as an email message, a review or a post. It is extremely difficult to know if a company is in possession of sensitive data at the risk of not protecting them properly. The goal of the study described in this paper is to use Machine Learning, in particular the Transformer deep-learning model, to develop classifiers capable of detecting documents that are likely to include sensitive data. Additionally, we want the classifiers to recognize the particular type of sensitive topic with which they deal, in order for a company to have a better knowledge of the data they own. We expect to make the model described in this paper available as a web service, customized to private data of possible customers, or even in a free-to-use version based on the freely available data set we have built to train the classifiers. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

21 pages, 283655 KiB

Open AccessArticle

Intuitively Searching for the Rare Colors from Digital Artwork Collections by Text Description: A Case Demonstration of Japanese Ukiyo-e Print Retrieval

by Kangying Li, Jiayun Wang, Biligsaikhan Batjargal and Akira Maeda

Future Internet 2022, 14(7), 212; https://doi.org/10.3390/fi14070212 - 18 Jul 2022

Cited by 2 | Viewed by 2676

Abstract

In recent years, artworks have been increasingly digitized and built into databases, and such databases have become convenient tools for researchers. Researchers who retrieve artwork are not only researchers of humanities, but also researchers of materials science, physics, art, and so on. It [...] Read more.

In recent years, artworks have been increasingly digitized and built into databases, and such databases have become convenient tools for researchers. Researchers who retrieve artwork are not only researchers of humanities, but also researchers of materials science, physics, art, and so on. It may be difficult for researchers of various fields whose studies focus on the colors of artwork to find the required records in existing databases, that are color-based and only queried by the metadata. Besides, although some image retrieval engines can be used to retrieve artwork by text description, the existing image retrieval systems mainly retrieve the main colors of the images, and rare cases of color use are difficult to find. This makes it difficult for many researchers who focus on toning, colors, or pigments to use search engines for their own needs. To solve the two problems, we propose a cross-modal multi-task fine-tuning method based on CLIP (Contrastive Language-Image Pre-Training), which uses the human sensory characteristics of colors contained in the language space and the geometric characteristics of the sketches of a given artwork in order to gain better representations of that artwork piece. The experimental results show that the proposed retrieval framework is efficient for intuitively searching for rare colors, and that a small amount of data can improve the correspondence between text descriptions and color information. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

23 pages, 6966 KiB

Open AccessArticle

Analytical Modeling and Empirical Analysis of Binary Options Strategies

by Gurdal Ertek, Aysha Al-Kaabi and Aktham Issa Maghyereh

Future Internet 2022, 14(7), 208; https://doi.org/10.3390/fi14070208 - 6 Jul 2022

Cited by 2 | Viewed by 4896

Abstract

This study analyzes binary option investment strategies by developing mathematical formalism and formulating analytical models. The binary outcome of binary options represents either an increase or a decrease in a parameter, typically an asset or derivative. The investor receives only partial returns if [...] Read more.

This study analyzes binary option investment strategies by developing mathematical formalism and formulating analytical models. The binary outcome of binary options represents either an increase or a decrease in a parameter, typically an asset or derivative. The investor receives only partial returns if the prediction is correct but loses all the investment otherwise. Mainstream research on binary options aims to develop the best dynamic trading strategies. This study focuses on static tactical easy-to-implement strategies and investigates the performance of such strategies in relation to prediction accuracy, payout percentage, and investment strategy decisions. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

16 pages, 1779 KiB

Open AccessArticle

Enhancing Short-Term Sales Prediction with Microblogs: A Case Study of the Movie Box Office

by Jie Zhao, Fangwei Xiong and Peiquan Jin

Future Internet 2022, 14(5), 141; https://doi.org/10.3390/fi14050141 - 4 May 2022

Cited by 5 | Viewed by 2806

Abstract

Microblogs are one of the major social networks in people’s daily life. The increasing amount of timely microblog data brings new opportunities for enterprises to predict short-term product sales based on microblogs because the daily microblogs posted by various users can express people’s [...] Read more.

Microblogs are one of the major social networks in people’s daily life. The increasing amount of timely microblog data brings new opportunities for enterprises to predict short-term product sales based on microblogs because the daily microblogs posted by various users can express people’s sentiments on specific products, such as movies and books. Additionally, the social influence of microblogging platforms enables the rapid spread of product information, implemented by users’ forwarding and commenting behavior. To verify the usefulness of microblogs in enhancing the prediction of short-term product sales, in this paper, we first present a new framework that adopts the sentiment and influence features of microblogs. Then, we describe the detailed feature computation methods for sentiment polarity detection and influence measurement. We also implement the Linear Regression (LR) model and the Support Vector Regression (SVR) model, selected as the representatives of linear and nonlinear regression models, to predict short-term product sales. Finally, we take movie box office predictions as an example and conduct experiments to evaluate the performance of the proposed features and models. The results show that the proposed sentiment feature and influence feature of microblogs play a positive role in improving the prediction precision. In addition, both the LR model and the SVR model can lower the MAPE metric of the prediction effectively. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

24 pages, 755 KiB

Open AccessArticle

Building Semantic Knowledge Graphs from (Semi-)Structured Data: A Review

by Vetle Ryen, Ahmet Soylu and Dumitru Roman

Future Internet 2022, 14(5), 129; https://doi.org/10.3390/fi14050129 - 24 Apr 2022

Cited by 40 | Viewed by 9974

Abstract

Knowledge graphs have, for the past decade, been a hot topic both in public and private domains, typically used for large-scale integration and analysis of data using graph-based data models. One of the central concepts in this area is the Semantic Web, with [...] Read more.

Knowledge graphs have, for the past decade, been a hot topic both in public and private domains, typically used for large-scale integration and analysis of data using graph-based data models. One of the central concepts in this area is the Semantic Web, with the vision of providing a well-defined meaning to information and services on the Web through a set of standards. Particularly, linked data and ontologies have been quite essential for data sharing, discovery, integration, and reuse. In this paper, we provide a systematic literature review on knowledge graph creation from structured and semi-structured data sources using Semantic Web technologies. The review takes into account four prominent publication venues, namely, Extended Semantic Web Conference, International Semantic Web Conference, Journal of Web Semantics, and Semantic Web Journal. The review highlights the tools, methods, types of data sources, ontologies, and publication methods, together with the challenges, limitations, and lessons learned in the knowledge graph creation processes. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

14 pages, 897 KiB

Open AccessArticle

Bringing Digital Innovation Strategies and Entrepreneurship: The Business Model Canvas in Open Data Ecosystem and Startups

by Maria Kamariotou and Fotis Kitsios

Future Internet 2022, 14(5), 127; https://doi.org/10.3390/fi14050127 - 21 Apr 2022

Cited by 7 | Viewed by 4400

Abstract

The aim of this paper is to examine and analyze how actors in an open data ecosystem collaborate, as well as their activities, to generate value. Thirteen interviews were conducted with actors in the open data network. The information gathered was used to [...] Read more.

The aim of this paper is to examine and analyze how actors in an open data ecosystem collaborate, as well as their activities, to generate value. Thirteen interviews were conducted with actors in the open data network. The information gathered was used to estimate how the existing ecosystem provides new entrepreneurial opportunities for entities who provide data and for those who utilize data. The business model canvas was used to analyze the findings, and the outcomes are represented from the perspective of each entity in the network. For the purpose of increasing open data’s value, a mind map was developed to show how the findings are connected in an attractive and easy-to-follow manner. Results show that even though there is a lot of interest in open data, a new type of business ecosystem is needed to make a win–win situation possible for everyone in the available data ecosystem. Many reasons and benefits were found in the interviews about why people want to be a part of the open data ecosystem. However, several obstacles must be thoroughly explored and overcome. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

19 pages, 3156 KiB

Open AccessArticle

Interoperable Data Analytics Reference Architectures Empowering Digital-Twin-Aided Manufacturing

by Attila Csaba Marosi, Márk Emodi, Ákos Hajnal, Róbert Lovas, Tamás Kiss, Valerie Poser, Jibinraj Antony, Simon Bergweiler, Hamed Hamzeh, James Deslauriers and József Kovács

Future Internet 2022, 14(4), 114; https://doi.org/10.3390/fi14040114 - 6 Apr 2022

Cited by 6 | Viewed by 4093

Abstract

The use of mature, reliable, and validated solutions can save significant time and cost when introducing new technologies to companies. Reference Architectures represent such best-practice techniques and have the potential to increase the speed and reliability of the development process in many application [...] Read more.

The use of mature, reliable, and validated solutions can save significant time and cost when introducing new technologies to companies. Reference Architectures represent such best-practice techniques and have the potential to increase the speed and reliability of the development process in many application domains. One area where Reference Architectures are increasingly utilized is cloud-based systems. Exploiting the high-performance computing capability offered by clouds, while keeping sovereignty and governance of proprietary information assets can be challenging. This paper explores how Reference Architectures can be applied to overcome this challenge when developing cloud-based applications. The presented approach was developed within the DIGITbrain European project, which aims at supporting small and medium-sized enterprises (SMEs) and mid-caps in realizing smart business models called Manufacturing as a Service, via the efficient utilization of Digital Twins. In this paper, an overview of Reference Architecture concepts, as well as their classification, specialization, and particular application possibilities are presented. Various data management and potentially spatially detached data processing configurations are discussed, with special attention to machine learning techniques, which are of high interest within various sectors, including manufacturing. A framework that enables the deployment and orchestration of such overall data analytics Reference Architectures in clouds resources is also presented, followed by a demonstrative application example where the applicability of the introduced techniques and solutions are showcased in practice. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

19 pages, 1239 KiB

Open AccessArticle

A Data-Driven Approach to Improve Customer Churn Prediction Based on Telecom Customer Segmentation

by Tianyuan Zhang, Sérgio Moro and Ricardo F. Ramos

Future Internet 2022, 14(3), 94; https://doi.org/10.3390/fi14030094 - 16 Mar 2022

Cited by 36 | Viewed by 9292

Abstract

Numerous valuable clients can be lost to competitors in the telecommunication industry, leading to profit loss. Thus, understanding the reasons for client churn is vital for telecommunication companies. This study aimed to develop a churn prediction model to predict telecom client churn through [...] Read more.

Numerous valuable clients can be lost to competitors in the telecommunication industry, leading to profit loss. Thus, understanding the reasons for client churn is vital for telecommunication companies. This study aimed to develop a churn prediction model to predict telecom client churn through customer segmentation. Data were collected from three major Chinese telecom companies, and Fisher discriminant equations and logistic regression analysis were used to build a telecom customer churn prediction model. According to the results, it can be concluded that the telecom customer churn model constructed by regression analysis had higher prediction accuracy (93.94%) and better results. This study will help telecom companies efficiently predict the possibility of and take targeted measures to avoid customer churn, thereby increasing their profits. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

16 pages, 14253 KiB

Open AccessArticle

JoSDW: Combating Noisy Labels by Dynamic Weight

by Yaojie Zhang, Huahu Xu, Junsheng Xiao and Minjie Bian

Future Internet 2022, 14(2), 50; https://doi.org/10.3390/fi14020050 - 2 Feb 2022

Viewed by 2898

Abstract

The real world is full of noisy labels that lead neural networks to perform poorly because deep neural networks (DNNs) are prone to overfitting label noise. Noise label training is a challenging problem relating to weakly supervised learning. The most advanced existing methods [...] Read more.

The real world is full of noisy labels that lead neural networks to perform poorly because deep neural networks (DNNs) are prone to overfitting label noise. Noise label training is a challenging problem relating to weakly supervised learning. The most advanced existing methods mainly adopt a small loss sample selection strategy, such as selecting the small loss part of the sample for network model training. However, the previous literature stopped here, neglecting the performance of the small loss sample selection strategy while training the DNNs, as well as the performance of different stages, and the performance of the collaborative learning of the two networks from disagreement to an agreement, and making a second classification based on this. We train the network using a comparative learning method. Specifically, a small loss sample selection strategy with dynamic weight is designed. This strategy increases the proportion of agreement based on network predictions, gradually reduces the weight of the complex sample, and increases the weight of the pure sample at the same time. A large number of experiments verify the superiority of our method. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

22 pages, 533 KiB

Open AccessArticle

Selecting Workers Wisely for Crowdsourcing When Copiers and Domain Experts Co-exist

by Xiu Fang, Suxin Si, Guohao Sun, Quan Z. Sheng, Wenjun Wu, Kang Wang and Hang Lv

Future Internet 2022, 14(2), 37; https://doi.org/10.3390/fi14020037 - 24 Jan 2022

Cited by 1 | Viewed by 2959

Abstract

Crowdsourcing integrates human wisdom to solve problems. Tremendous research efforts have been made in this area. However, most of them assume that workers have the same credibility in different domains and workers complete tasks independently. This leads to an inaccurate evaluation of worker [...] Read more.

Crowdsourcing integrates human wisdom to solve problems. Tremendous research efforts have been made in this area. However, most of them assume that workers have the same credibility in different domains and workers complete tasks independently. This leads to an inaccurate evaluation of worker credibility, hampering crowdsourcing results. To consider the impact of worker domain expertise, we adopted a vector to more accurately measure the credibility of each worker. Based on this measurement and prior task domain knowledge, we calculated fine-grained worker credibility on each given task. To avoid tasks being assigned to dependent workers who copy answers from others, we conducted copier detection via Bayesian analysis. We designed a crowdsourcing system called SWWC composed of a task assignment stage and a truth discovery stage. In the task assignment stage, we assigned tasks wisely to workers based on worker domain expertise calculation and copier removal. In the truth discovery stage, we computed the estimated truth and worker credibility by an iterative method. Then, we updated the domain expertise of workers to facilitate the upcoming task assignment. We also designed initialization algorithms to better initialize the accuracy of new workers. Theoretical analysis and experimental results showed that our method had a prominent advantage, especially under a copying situation. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

21 pages, 1532 KiB

Open AccessArticle

Mobility in Unsupervised Word Embeddings for Knowledge Extraction—The Scholars’ Trajectories across Research Topics

by Gianfranco Lombardo, Michele Tomaiuolo, Monica Mordonini, Gaia Codeluppi and Agostino Poggi

Future Internet 2022, 14(1), 25; https://doi.org/10.3390/fi14010025 - 9 Jan 2022

Cited by 3 | Viewed by 3350

Abstract

In the knowledge discovery field of the Big Data domain the analysis of geographic positioning and mobility information plays a key role. At the same time, in the Natural Language Processing (NLP) domain pre-trained models such as BERT and word embedding algorithms such [...] Read more.

In the knowledge discovery field of the Big Data domain the analysis of geographic positioning and mobility information plays a key role. At the same time, in the Natural Language Processing (NLP) domain pre-trained models such as BERT and word embedding algorithms such as Word2Vec enabled a rich encoding of words that allows mapping textual data into points of an arbitrary multi-dimensional space, in which the notion of proximity reflects an association among terms or topics. The main contribution of this paper is to show how analytical tools, traditionally adopted to deal with geographic data to measure the mobility of an agent in a time interval, can also be effectively applied to extract knowledge in a semantic realm, such as a semantic space of words and topics, looking for latent trajectories that can benefit the properties of neural network latent representations. As a case study, the Scopus database was queried about works of highly cited researchers in recent years. On this basis, we performed a dynamic analysis, for measuring the Radius of Gyration as an index of the mobility of researchers across scientific topics. The semantic space is built from the automatic analysis of the paper abstracts of each author. In particular, we evaluated two different methodologies to build the semantic space and we found that Word2Vec embeddings perform better than the BERT ones for this task. Finally, The scholars’ trajectories show some latent properties of this model, which also represent new scientific contributions of this work. These properties include (i) the correlation between the scientific mobility and the achievement of scientific results, measured through the H-index; (ii) differences in the behavior of researchers working in different countries and subjects; and (iii) some interesting similarities between mobility patterns in this semantic realm and those typically observed in the case of human mobility. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

19 pages, 7139 KiB

Open AccessArticle

An Efficient Deep Convolutional Neural Network Approach for Object Detection and Recognition Using a Multi-Scale Anchor Box in Real-Time

by Vijayakumar Varadarajan, Dweepna Garg and Ketan Kotecha

Future Internet 2021, 13(12), 307; https://doi.org/10.3390/fi13120307 - 29 Nov 2021

Cited by 13 | Viewed by 3652

Abstract

Deep learning is a relatively new branch of machine learning in which computers are taught to recognize patterns in massive volumes of data. It primarily describes learning at various levels of representation, which aids in understanding data that includes text, voice, and visuals. [...] Read more.

Deep learning is a relatively new branch of machine learning in which computers are taught to recognize patterns in massive volumes of data. It primarily describes learning at various levels of representation, which aids in understanding data that includes text, voice, and visuals. Convolutional neural networks have been used to solve challenges in computer vision, including object identification, image classification, semantic segmentation and a lot more. Object detection in videos involves confirming the presence of the object in the image or video and then locating it accurately for recognition. In the video, modelling techniques suffer from high computation and memory costs, which may decrease performance measures such as accuracy and efficiency to identify the object accurately in real-time. The current object detection technique based on a deep convolution neural network requires executing multilevel convolution and pooling operations on the entire image to extract deep semantic properties from it. For large objects, detection models can provide superior results; however, those models fail to detect the varying size of the objects that have low resolution and are greatly influenced by noise because the features after the repeated convolution operations of existing models do not fully represent the essential characteristics of the objects in real-time. With the help of a multi-scale anchor box, the proposed approach reported in this paper enhances the detection accuracy by extracting features at multiple convolution levels of the object. The major contribution of this paper is to design a model to understand better the parameters and the hyper-parameters which affect the detection and the recognition of objects of varying sizes and shapes, and to achieve real-time object detection and recognition speeds by improving accuracy. The proposed model has achieved 84.49 mAP on the test set of the Pascal VOC-2007 dataset at 11 FPS, which is comparatively better than other real-time object detection models. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

Review

Jump to: Research

17 pages, 3759 KiB

Open AccessReview

Analysis of Electric Vehicles with an Economic Perspective for the Future Electric Market

by Sofana Reka S, Prakash Venugopal, Ravi V, Hassan Haes Alhelou, Amer Al-Hinai and Pierluigi Siano

Future Internet 2022, 14(6), 172; https://doi.org/10.3390/fi14060172 - 31 May 2022

Cited by 15 | Viewed by 9197

Abstract

The automotive industry is marching towards cleaner energy in the impending future. The need for cleaner energy is promoted by the government to a large degree in the global market in order to reduce pollution. Automobiles contribute to an upper scale in regard [...] Read more.

The automotive industry is marching towards cleaner energy in the impending future. The need for cleaner energy is promoted by the government to a large degree in the global market in order to reduce pollution. Automobiles contribute to an upper scale in regard to the level of pollution in the environment. For cleaner energy in automobiles, the industry needs to be revolutionized in all needed ways to a massive extent. The industry has to move from the traditional internal combustion engine, for which the main sources of energy are nonrenewable sources, to alternative methods and sources of energy. The automotive industry is now focusing on electric vehicles, and more research is being highlighted from vehicle manufacturers to find solutions for the problems faced in the field of electrification. Therefore, to accomplish full electrification, there is a long way to go, and this also requires a change in the existing infrastructure in addition to many innovations in the fields of infrastructure and grid connectively as well as the economic impacts of electric vehicles in society. In this work, an analysis of the electric vehicle market with the economic impacts of electric vehicles is studied. This therefore requires the transformation of the automotive industry. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Figure 1

19 pages, 4672 KiB

Open AccessReview

Survey on Videos Data Augmentation for Deep Learning Models

by Nino Cauli and Diego Reforgiato Recupero

Future Internet 2022, 14(3), 93; https://doi.org/10.3390/fi14030093 - 16 Mar 2022

Cited by 31 | Viewed by 6616

Abstract

In most Computer Vision applications, Deep Learning models achieve state-of-the-art performances. One drawback of Deep Learning is the large amount of data needed to train the models. Unfortunately, in many applications, data are difficult or expensive to collect. Data augmentation can alleviate the [...] Read more.

In most Computer Vision applications, Deep Learning models achieve state-of-the-art performances. One drawback of Deep Learning is the large amount of data needed to train the models. Unfortunately, in many applications, data are difficult or expensive to collect. Data augmentation can alleviate the problem, generating new data from a smaller initial dataset. Geometric and color space image augmentation methods can increase accuracy of Deep Learning models but are often not enough. More advanced solutions are Domain Randomization methods or the use of simulation to artificially generate the missing data. Data augmentation algorithms are usually specifically designed for single images. Most recently, Deep Learning models have been applied to the analysis of video sequences. The aim of this paper is to perform an exhaustive study of the novel techniques of video data augmentation for Deep Learning models and to point out the future directions of the research on this topic. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Graphical abstract

24 pages, 3049 KiB

Open AccessReview

Exploring Time-Series Forecasting Models for Dynamic Pricing in Digital Signage Advertising

by Yee-Fan Tan, Lee-Yeng Ong, Meng-Chew Leow and Yee-Xian Goh

Future Internet 2021, 13(10), 241; https://doi.org/10.3390/fi13100241 - 22 Sep 2021

Cited by 10 | Viewed by 5650

Abstract

Audience attention is vital in Digital Signage Advertising (DSA), as it has a significant impact on the pricing decision to advertise on those media. Various environmental factors affect the audience attention level toward advertising signage. Fixed-price strategies, which have been applied in DSA [...] Read more.

Audience attention is vital in Digital Signage Advertising (DSA), as it has a significant impact on the pricing decision to advertise on those media. Various environmental factors affect the audience attention level toward advertising signage. Fixed-price strategies, which have been applied in DSA for pricing decisions, are generally inefficient at maximizing the potential profit of the service provider, as the environmental factors that could affect the audience attention are changing fast and are generally not considered in the current pricing solutions in a timely manner. Therefore, the time-series forecasting method is a suitable pricing solution for DSA, as it improves the pricing decision by modeling the changes in the environmental factors and audience attention level toward signage for optimal pricing. However, it is difficult to determine an optimal price forecasting model for DSA with the increasing number of available time-series forecasting models in recent years. Based on the 84 research articles reviewed, the data characteristics analysis in terms of linearity, stationarity, volatility, and dataset size is helpful in determining the optimal model for time-series price forecasting. This paper has reviewed the widely used time-series forecasting models and identified the related data characteristics of each model. A framework is proposed to demonstrate the model selection process for dynamic pricing in DSA based on its data characteristics analysis, paving the way for future research of pricing solutions for DSA. Full article

(This article belongs to the Special Issue Big Data Analytics, Privacy and Visualization)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Big Data Analytics, Privacy and Visualization

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (17 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI