Future Internet

13 pages, 3488 KiB

Open AccessArticle

Vehicular Delay-Tolerant Networks with Image Recognition-Based Adaptive Array Antenna for Winter Road Surveillance in Local Areas

by Noriki Uchida, Goshi Sato and Yoshitaka Shibata

Future Internet 2019, 11(9), 203; https://doi.org/10.3390/fi11090203 - 19 Sep 2019

Cited by 2 | Viewed by 3178

Abstract

The rapid growth of the ITS (intelligent transport system) development requires us to realize new kinds of applications, such as the winter road surveillance system. However, it is still necessary to consider the network difficulty areas for LTE (long-term evolution) or 3G transmissions [...] Read more.

The rapid growth of the ITS (intelligent transport system) development requires us to realize new kinds of applications, such as the winter road surveillance system. However, it is still necessary to consider the network difficulty areas for LTE (long-term evolution) or 3G transmissions when one visits sightseeing spots such as ski resorts or spas in mountain areas. Therefore, this paper proposes a winter road surveillance system in the local area based on vehicular delay-tolerant networks. The adaptive array antenna controlled by image recognition with the Kalman filter algorithm is proposed as well to the system in order to realize higher delivery rates. The implementations of the prototype system are presented in this paper as well, and the effectivity of the radio transmission in the prototype system is realized by vehicular image recognition methods and the asynchronous voltage controls for antenna elements for the rapid directional controls of the radio transmission. The experimental results showed that the radio directional controls by the prototype system for the target vehicle can proceed within one second, and that the simulation with the GIS (geographic information system) map pointed out the delivery rates of the proposed method—which are better than those of the epidemic DTN (delay-tolerant networking) routing by the nondirectional antenna. The experiments of the proposed methods indicate a higher efficiency of the data transmissions—even in the mountain area. Furthermore, future research subjects are discussed in this paper. Full article

(This article belongs to the Special Issue Advanced Techniques for Internet, P2P and Cloud Computing—selected papers from 3PGCIC-2018)

► Show Figures

Figure 1

21 pages, 10546 KiB

Open AccessArticle

Ranking by Relevance and Citation Counts, a Comparative Study: Google Scholar, Microsoft Academic, WoS and Scopus

by Cristòfol Rovira, Lluís Codina, Frederic Guerrero-Solé and Carlos Lopezosa

Future Internet 2019, 11(9), 202; https://doi.org/10.3390/fi11090202 - 19 Sep 2019

Cited by 46 | Viewed by 13357

Abstract

Search engine optimization (SEO) constitutes the set of methods designed to increase the visibility of, and the number of visits to, a web page by means of its ranking on the search engine results pages. Recently, SEO has also been applied to academic [...] Read more.

Search engine optimization (SEO) constitutes the set of methods designed to increase the visibility of, and the number of visits to, a web page by means of its ranking on the search engine results pages. Recently, SEO has also been applied to academic databases and search engines, in a trend that is in constant growth. This new approach, known as academic SEO (ASEO), has generated a field of study with considerable future growth potential due to the impact of open science. The study reported here forms part of this new field of analysis. The ranking of results is a key aspect in any information system since it determines the way in which these results are presented to the user. The aim of this study is to analyze and compare the relevance ranking algorithms employed by various academic platforms to identify the importance of citations received in their algorithms. Specifically, we analyze two search engines and two bibliographic databases: Google Scholar and Microsoft Academic, on the one hand, and Web of Science and Scopus, on the other. A reverse engineering methodology is employed based on the statistical analysis of Spearman’s correlation coefficients. The results indicate that the ranking algorithms used by Google Scholar and Microsoft are the two that are most heavily influenced by citations received. Indeed, citation counts are clearly the main SEO factor in these academic search engines. An unexpected finding is that, at certain points in time, Web of Science (WoS) used citations received as a key ranking factor, despite the fact that WoS support documents claim this factor does not intervene. Full article

(This article belongs to the Special Issue Search Engine Optimization)

► Show Figures

Figure 1

21 pages, 1764 KiB

Open AccessArticle

Role-Mining Optimization with Separation-of-Duty Constraints and Security Detections for Authorizations

by Wei Sun, Shiwei Wei, Huaping Guo and Hongbing Liu

Future Internet 2019, 11(9), 201; https://doi.org/10.3390/fi11090201 - 19 Sep 2019

Cited by 5 | Viewed by 3878

Abstract

Role-based access control (RBAC), which has been regarded as one of the most popular access-control mechanisms, is featured by the separation-of-duty constraints, mutually exclusive constraints, and the least-privileges principle. Role mining, a bottom-up role-engineering technology, is an effective method to migrate from a [...] Read more.

Role-based access control (RBAC), which has been regarded as one of the most popular access-control mechanisms, is featured by the separation-of-duty constraints, mutually exclusive constraints, and the least-privileges principle. Role mining, a bottom-up role-engineering technology, is an effective method to migrate from a non-RBAC system to an RBAC system. However, conventional role-mining approaches not only do not consider the separation of duty constraints, but also cannot ensure the security of a constructed RBAC system when the corresponding mined results violate the separation of a duty constraint and/or the least-privileges principle. To solve these problems, this paper proposes a novel method called role-mining optimization with separation-of-duty constraints and security detections for authorizations (RMO_SODSDA), which mainly includes two aspects. First, we present a role-mining-optimization approach for satisfying the separation of duty constraints, and we constructed different variants of mutually exclusive constraints to correctly implement the given separation of duty constraints based on unconstrained role mining. Second, to ensure the security of the constructed system and evaluate authorization performance, we reduced the authorization-query problem to a maximal-satisfiability problem. The experiments validate the effectiveness and efficiency of the proposed method. Full article

(This article belongs to the Section Cybersecurity)

► Show Figures

Figure 1

13 pages, 3694 KiB

Open AccessArticle

Incorporating Background Checks with Sentiment Analysis to Identify Violence Risky Chinese Microblogs

by Yun-Fei Jia, Shan Li and Renbiao Wu

Future Internet 2019, 11(9), 200; https://doi.org/10.3390/fi11090200 - 19 Sep 2019

Cited by 6 | Viewed by 3247

Abstract

Based on Web 2.0 technology, more and more people tend to express their attitude or opinions on the Internet. Radical ideas, rumors, terrorism, or violent contents are also propagated on the Internet, causing several incidents of social panic every year in China. In [...] Read more.

Based on Web 2.0 technology, more and more people tend to express their attitude or opinions on the Internet. Radical ideas, rumors, terrorism, or violent contents are also propagated on the Internet, causing several incidents of social panic every year in China. In fact, most of this content comprises joking or emotional catharsis. To detect this with conventional techniques usually incurs a large false alarm rate. To address this problem, this paper introduces a technique that combines sentiment analysis with background checks. State-of-the-art sentiment analysis usually depends on training datasets in a specific topic area. Unfortunately, for some domains, such as violence risk speech detection, there is no definitive training data. In particular, topic-independent sentiment analysis of short Chinese text has been rarely reported in the literature. In this paper, the violence risk of the Chinese microblogs is calculated from multiple perspectives. First, a lexicon-based method is used to retrieve violence-related microblogs, and then a similarity-based method is used to extract sentiment words. Semantic rules and emoticons are employed to obtain the sentiment polarity and sentiment strength of short texts. Second, the activity risk is calculated based on the characteristics of part of speech (PoS) sequence and by semantic rules, and then a threshold is set to capture the key users. Finally, the risk is confirmed by historical speeches and the opinions of the friend-circle of the key users. The experimental results show that the proposed approach outperforms the support vector machine (SVM) method on a topic-independent corpus and can effectively reduce the false alarm rate. Full article

(This article belongs to the Special Issue Semantic Web Technologies for Sentiment Analysis)

► Show Figures

Figure 1

19 pages, 685 KiB

Open AccessArticle

Enhancing the 3GPP V2X Architecture with Information-Centric Networking

by Marica Amadeo, Claudia Campolo, Antonella Molinaro, Jerome Harri, Christian Esteve Rothenberg and Alexey Vinel

Future Internet 2019, 11(9), 199; https://doi.org/10.3390/fi11090199 - 18 Sep 2019

Cited by 22 | Viewed by 5539

Abstract

Vehicle-to-everything (V2X) communications allow a vehicle to interact with other vehicles and with communication parties in its vicinity (e.g., road-side units, pedestrian users, etc.) with the primary goal of making the driving and traveling experience safer, smarter and more comfortable. A wide set [...] Read more.

Vehicle-to-everything (V2X) communications allow a vehicle to interact with other vehicles and with communication parties in its vicinity (e.g., road-side units, pedestrian users, etc.) with the primary goal of making the driving and traveling experience safer, smarter and more comfortable. A wide set of V2X-tailored specifications have been identified by the Third Generation Partnership Project (3GPP) with focus on the design of architecture enhancements and a flexible air interface to ensure ultra-low latency, highly reliable and high-throughput connectivity as the ultimate aim. This paper discusses the potential of leveraging Information-Centric Networking (ICN) principles in the 3GPP architecture for V2X communications. We consider Named Data Networking (NDN) as reference ICN architecture and elaborate on the specific design aspects, required changes and enhancements in the 3GPP V2X architecture to enable NDN-based data exchange as an alternative/complementary solution to traditional IP networking, which barely matches the dynamics of vehicular environments. Results are provided to showcase the performance improvements of the NDN-based proposal in disseminating content requests over the cellular network against a traditional networking solution. Full article

(This article belongs to the Special Issue 5G-V2X Communications and Networking for Connected and Autonomous Vehicles)

► Show Figures

Figure 1

15 pages, 1833 KiB

Open AccessArticle

Dynamic Group Recommendation Based on the Attention Mechanism

by Haiyan Xu, Yanhui Ding, Jing Sun, Kun Zhao and Yuanjian Chen

Future Internet 2019, 11(9), 198; https://doi.org/10.3390/fi11090198 - 17 Sep 2019

Cited by 13 | Viewed by 3692

Abstract

Group recommendation has attracted significant research efforts for its importance in benefiting group members. The purpose of group recommendation is to provide recommendations to group users, such as recommending a movie to several friends. Group recommendation requires that the recommendation should be as [...] Read more.

Group recommendation has attracted significant research efforts for its importance in benefiting group members. The purpose of group recommendation is to provide recommendations to group users, such as recommending a movie to several friends. Group recommendation requires that the recommendation should be as satisfactory as possible to each member of the group. Due to the lack of weighting of users in different items, group decision-making cannot be made dynamically. Therefore, in this paper, a dynamic recommendation method based on the attention mechanism is proposed. Firstly, an improved density peak clustering (

DPC

) algorithm is used to discover the potential group; and then the attention mechanism is adopted to learn the influence weight of each user. The normalized discounted cumulative gain (NDCG) and hit ratio (HR) are adopted to evaluate the validity of the recommendation results. Experimental results on the CAMRa2011 dataset show that our method is effective. Full article

► Show Figures

Figure 1

Figure 1
Overview of the group recommended. Full article ">Figure 2
(a) Data point distribution and (b) decision diagram. Full article ">Figure 3
Cutoff distance. Full article ">Figure 4
User embedding aggregation based on neural attention. Full article ">Figure 5
<math display="inline"><semantics> <mrow> <mrow> <mi>Neural</mi> <mo> </mo> <mi>collaborative</mi> <mo> </mo> <mi>filtering</mi> <mo> </mo> </mrow> <mrow> <mo>(</mo> <mrow> <mi>NCF</mi> </mrow> <mo>)</mo> </mrow> </mrow> </semantics></math> interactive learning. Full article ">Figure 6
(a) Effectiveness of group recommendation <math display="inline"><semantics> <mrow> <mrow> <mo>(</mo> <mrow> <mi>HR</mi> <mo>@</mo> <mn>10</mn> </mrow> <mo>)</mo> </mrow> </mrow> </semantics></math> and (b) the effectiveness of group recommendation <math display="inline"><semantics> <mrow> <mrow> <mo>(</mo> <mrow> <mi>NDCG</mi> <mo>@</mo> <mn>10</mn> </mrow> <mo>)</mo> </mrow> </mrow> </semantics></math>. Full article ">

25 pages, 5713 KiB

Open AccessArticle

MU R-CNN: A Two-Dimensional Code Instance Segmentation Network Based on Deep Learning

by Baoxi Yuan, Yang Li, Fan Jiang, Xiaojie Xu, Yingxia Guo, Jianhua Zhao, Deyue Zhang, Jianxin Guo and Xiaoli Shen

Future Internet 2019, 11(9), 197; https://doi.org/10.3390/fi11090197 - 13 Sep 2019

Cited by 15 | Viewed by 5141

Abstract

In the context of Industry 4.0, the most popular way to identify and track objects is to add tags, and currently most companies still use cheap quick response (QR) tags, which can be positioned by computer vision (CV) technology. In CV, instance segmentation [...] Read more.

In the context of Industry 4.0, the most popular way to identify and track objects is to add tags, and currently most companies still use cheap quick response (QR) tags, which can be positioned by computer vision (CV) technology. In CV, instance segmentation (IS) can detect the position of tags while also segmenting each instance. Currently, the mask region-based convolutional neural network (Mask R-CNN) method is used to realize IS, but the completeness of the instance mask cannot be guaranteed. Furthermore, due to the rich texture of QR tags, low-quality images can lower intersection-over-union (IoU) significantly, disabling it from accurately measuring the completeness of the instance mask. In order to optimize the IoU of the instance mask, a QR tag IS method named the mask UNet region-based convolutional neural network (MU R-CNN) is proposed. We utilize the UNet branch to reduce the impact of low image quality on IoU through texture segmentation. The UNet branch does not depend on the features of the Mask R-CNN branch so its training process can be carried out independently. The pre-trained optimal UNet model can ensure that the loss of MU R-CNN is accurate from the beginning of the end-to-end training. Experimental results show that the proposed MU R-CNN is applicable to both high- and low-quality images, and thus more suitable for Industry 4.0. Full article

(This article belongs to the Special Issue Manufacturing Systems and Internet of Thing)

► Show Figures

Figure 1

21 pages, 4347 KiB

Open AccessArticle

Evaluating the Degree of Uncertainty of Research Activities in Industry 4.0

by Sirio Cividino, Gianluca Egidi, Ilaria Zambon and Andrea Colantoni

Future Internet 2019, 11(9), 196; https://doi.org/10.3390/fi11090196 - 11 Sep 2019

Cited by 11 | Viewed by 4857

Abstract

Research and development (R&D) are always oriented towards new discoveries, based on original terms or hypotheses, and their concluding outcomes are often uncertain. The present work focused on the degree of uncertainty for R&D activities. In fact, uncertainty makes it difficult to quantify [...] Read more.

Research and development (R&D) are always oriented towards new discoveries, based on original terms or hypotheses, and their concluding outcomes are often uncertain. The present work focused on the degree of uncertainty for R&D activities. In fact, uncertainty makes it difficult to quantify the time and resources needed to achieve a final outcome, create a work plan and budget, and finalize the resulting “innovative” products or services that could be transferred or exchanged in a specific market. The present work attempts to indicate the degree of uncertainty of the research activities developed by a set of firms. The method used aimed to quantify the five criteria defined by the Manual of Frascati. Through the creation of an uncertainty cloud, a cone of uncertainty was defined following an approach based on project management. The evaluation grid was characterized by the decomposition of the different variables divided into quartiles, which allowed for the detection of the evolution of the project and each of its component. The ancillary objective aim was to also observe the development degree of these industries towards a framework of Industry 4.0. Full article

► Show Figures

Figure 1

Figure 1
Geographic distribution of firms selected by region in Italy (in % terms). Full article ">Figure 2
Uncertainty cone. Full article ">Figure 2 Cont.
Uncertainty cone. Full article ">Figure 3
Development of the uncertainty phases based on the coded parameters. Full article ">Figure 4
Calculation of the innovation factor of the project. Full article ">Figure 5
Uncertainty graph by trend line in red and in blue the trend line normalized. Full article ">Figure 6
The variables within the pre-research analysis phase by trend line in red and in blue the trend line normalized Full article ">Figure 7
The basic parameters considered to be systematic are in red, the minimum required level of the parameters is represented by the orange line, and the accessory parameters of systematicity is in blue. Full article ">

21 pages, 282 KiB

Open AccessArticle

ERMOCTAVE: A Risk Management Framework for IT Systems Which Adopt Cloud Computing

by Masky Mackita, Soo-Young Shin and Tae-Young Choe

Future Internet 2019, 11(9), 195; https://doi.org/10.3390/fi11090195 - 10 Sep 2019

Cited by 10 | Viewed by 13388

Abstract

Many companies are adapting cloud computing technology because moving to the cloud has an array of benefits. During decision-making, having processed for adopting cloud computing, the importance of risk management is progressively recognized. However, traditional risk management methods cannot be applied directly to [...] Read more.

Many companies are adapting cloud computing technology because moving to the cloud has an array of benefits. During decision-making, having processed for adopting cloud computing, the importance of risk management is progressively recognized. However, traditional risk management methods cannot be applied directly to cloud computing when data are transmitted and processed by external providers. When they are directly applied, risk management processes can fail by ignoring the distributed nature of cloud computing and leaving numerous risks unidentified. In order to fix this backdrop, this paper introduces a new risk management method, Enterprise Risk Management for Operationally Critical Threat, Asset, and Vulnerability Evaluation (ERMOCTAVE), which combines Enterprise Risk Management and Operationally Critical Threat, Asset, and Vulnerability Evaluation for mitigating risks that can arise with cloud computing. ERMOCTAVE is composed of two risk management methods by combining each component with another processes for comprehensive perception of risks. In order to explain ERMOCTAVE in detail, a case study scenario is presented where an Internet seller migrates some modules to Microsoft Azure cloud. The functionality comparison with ENISA and Microsoft cloud risk assessment shows that ERMOCTAVE has additional features, such as key objectives and strategies, critical assets, and risk measurement criteria. Full article

(This article belongs to the Section Network Virtualization and Edge/Fog Computing)

► Show Figures

Figure 1

24 pages, 2816 KiB

Open AccessFeature PaperArticle

25 Years of Bluetooth Technology

by Sherali Zeadally, Farhan Siddiqui and Zubair Baig

Future Internet 2019, 11(9), 194; https://doi.org/10.3390/fi11090194 - 9 Sep 2019

Cited by 50 | Viewed by 15946

Abstract

Bluetooth technology started off as a wireless, short-range cable replacement technology but it has undergone significant developments over the last two decades. Bluetooth radios are currently embedded in almost all computing devices including personal computers, smart phones, smart watches, and even micro-controllers. For [...] Read more.

Bluetooth technology started off as a wireless, short-range cable replacement technology but it has undergone significant developments over the last two decades. Bluetooth radios are currently embedded in almost all computing devices including personal computers, smart phones, smart watches, and even micro-controllers. For many of us, Bluetooth is an essential technology that we use every day. We provide an insight into the history of Bluetooth and its significant design developments over the last 25 years. We also discuss related issues (including security) and Bluetooth as a driving technology for the Internet of Things (IoT). Finally, we also present recent research results obtained with Bluetooth technology in various application areas. Full article

(This article belongs to the Special Issue 10th Anniversary Feature Papers)

► Show Figures

Figure 1

17 pages, 19632 KiB

Open AccessArticle

Satellite Integration into 5G: Accent on First Over-The-Air Tests of an Edge Node Concept with Integrated Satellite Backhaul

by Florian Völk, Konstantinos Liolis, Marius Corici, Joe Cahill, Robert T. Schwarz, Thomas Schlichter, Eric Troudt and Andreas Knopp

Future Internet 2019, 11(9), 193; https://doi.org/10.3390/fi11090193 - 5 Sep 2019

Cited by 24 | Viewed by 7039

Abstract

The 5G vision embraces a broad range of applications including the connectivity in underserved and remote areas. In particular, for these applications, satellites are going to play a role in future 5G networks to provide capacity on trains, vessels, aircraft, and for base [...] Read more.

The 5G vision embraces a broad range of applications including the connectivity in underserved and remote areas. In particular, for these applications, satellites are going to play a role in future 5G networks to provide capacity on trains, vessels, aircraft, and for base stations around the globe. In this paper, a 5G edge node concept, developed and evaluated with over-the-air tests using satellites in the geostationary orbit, is presented. The article covers a testbed demonstration study in Europe with a large-scale testbed including satellites and the latest standardization for the network architecture. The main goal of this testbed is to evaluate how satellite networks can be best integrated within the convergent 5G environment. The over-the-air tests for 5G satellite integration in this article are based on a 3GPP Release 15 core network architecture. Full article

(This article belongs to the Special Issue Satellite Communications in 5G Networks)

► Show Figures

Figure 1

19 pages, 2042 KiB

Open AccessArticle

A Framework for the Detection of Search and Rescue Patterns Using Shapelet Classification

by Konstantinos Kapadais, Iraklis Varlamis, Christos Sardianos and Konstantinos Tserpes

Future Internet 2019, 11(9), 192; https://doi.org/10.3390/fi11090192 - 4 Sep 2019

Cited by 10 | Viewed by 3855

Abstract

The problem of unmanned supervision of maritime areas has attracted the interest of researchers for the last few years, mainly thanks to the advances in vessel monitoring that the Automatic Identification System (AIS) has brought. Several frameworks and algorithms have been proposed for [...] Read more.

The problem of unmanned supervision of maritime areas has attracted the interest of researchers for the last few years, mainly thanks to the advances in vessel monitoring that the Automatic Identification System (AIS) has brought. Several frameworks and algorithms have been proposed for the management of vessel trajectory data, which focus on data compression, data clustering, classification and visualization, offering a wide variety of solutions from vessel monitoring to automatic detection of complex events. This work builds on our previous work in the topic of automatic detection of Search and Rescue (SAR) missions, by developing and evaluating a methodology for classifying the trajectories of vessels that possibly participate in such missions. The proposed solution takes advantage of a synthetic trajectory generator and a classifier that combines a genetic algorithm (GENDIS) for the extraction of informative shapelets from training data and a transformation to the shapelets’ feature space. Using the generator and several SAR patterns that are formally described in naval operations bibliography, it generates a synthetic dataset that is used to train the classifier. Evaluation on both synthetic and real data has very promising results and helped us to identify vessel SAR maneuvers without putting any effort into manual annotation. Full article

(This article belongs to the Special Issue Emerging Techniques of AI for Mobility Analysis and Mining)

► Show Figures

Figure 1

3 pages, 178 KiB

Open AccessComment

Social Network Services Management and Risk of Doocing. Comment on Kim, S.; Park, H.; Choi, M.J. “Negative Impact of Social Network Services Based on Stressor-Stress-Outcome: The Role of Experience of Privacy Violations. Future Internet 2019, 11, 137”

by Stefania Fantinelli and Michela Cortini

Future Internet 2019, 11(9), 191; https://doi.org/10.3390/fi11090191 - 4 Sep 2019

Cited by 1 | Viewed by 3072

Abstract

In light of the recent work by Kim and colleagues about Social Network Service (SNS), examining the individual and SNS characteristics as predictors of SNS fatigue, we hypothesize to enlarge their model to the job context. SNS is a relevant issue in occupational [...] Read more.

In light of the recent work by Kim and colleagues about Social Network Service (SNS), examining the individual and SNS characteristics as predictors of SNS fatigue, we hypothesize to enlarge their model to the job context. SNS is a relevant issue in occupational life as employers use it to have a deeper knowledge of their employees and as a tool of corporate communication. Employees can use SNS as a social platform and as a way to express discontent. In this latter case, the organization can implement a disciplinary procedure toward employees, known as doocing. The perception of privacy violation is strictly related to the fear and awareness of doocing, which in turn can predict SNS fatigue as well. So, it could be worthwhile to extend Kim and colleagues’ model to the workplace with particular attention to the doocing phenomenon. Full article

(This article belongs to the Section Techno-Social Smart Systems)

13 pages, 5680 KiB

Open AccessArticle

Deep Learning-Based Sentimental Analysis for Large-Scale Imbalanced Twitter Data

by Nasir Jamal, Chen Xianqiao and Hamza Aldabbas

Future Internet 2019, 11(9), 190; https://doi.org/10.3390/fi11090190 - 2 Sep 2019

Cited by 12 | Viewed by 4975

Abstract

Emotions detection in social media is very effective to measure the mood of people about a specific topic, news, or product. It has a wide range of applications, including identifying psychological conditions such as anxiety or depression in users. However, it is a [...] Read more.

Emotions detection in social media is very effective to measure the mood of people about a specific topic, news, or product. It has a wide range of applications, including identifying psychological conditions such as anxiety or depression in users. However, it is a challenging task to distinguish useful emotions’ features from a large corpus of text because emotions are subjective, with limited fuzzy boundaries that may be expressed in different terminologies and perceptions. To tackle this issue, this paper presents a hybrid approach of deep learning based on TensorFlow with Keras for emotions detection on a large scale of imbalanced tweets’ data. First, preprocessing steps are used to get useful features from raw tweets without noisy data. Second, the entropy weighting method is used to compute the importance of each feature. Third, class balancer is applied to balance each class. Fourth, Principal Component Analysis (PCA) is applied to transform high correlated features into normalized forms. Finally, the TensorFlow based deep learning with Keras algorithm is proposed to predict high-quality features for emotions classification. The proposed methodology is analyzed on a dataset of 1,600,000 tweets collected from the website ‘kaggle’. Comparison is made of the proposed approach with other state of the art techniques on different training ratios. It is proved that the proposed approach outperformed among other techniques. Full article

(This article belongs to the Special Issue Social Network and Artificial Intelligence)

► Show Figures

Figure 1

16 pages, 1203 KiB

Open AccessArticle

RFID Based Embedded System for Sustainable Food Management in an IoT Network Paradigm

by Raúl Parada, Alfonso Palazón, Carlos Monzo and Joan Melià-Seguí

Future Internet 2019, 11(9), 189; https://doi.org/10.3390/fi11090189 - 1 Sep 2019

Cited by 4 | Viewed by 4996

Abstract

A third of the food produced in the world ends up in the rubbish, enough to put an end to world hunger. On the other hand, society is increasingly concerned to bring healthy eating habits. A RFID (radio frequency identification) food management system [...] Read more.

A third of the food produced in the world ends up in the rubbish, enough to put an end to world hunger. On the other hand, society is increasingly concerned to bring healthy eating habits. A RFID (radio frequency identification) food management system is designed to palliate the previously described issues in an Internet of Things (IoT) network paradigm. It consists of RFID readers placed on a user’s kitchen furniture, which automatically reads food information. There is no need for direct sight between reader and tag, as it occurs through the barcode technology. As a complement, a multi-platform web application is developed, allowing its users to check the date of food expiration and other detailed information. The application notifies the user when a product is about to expire. It also offers recipes that might be prepared with available foods, thus preventing them from being wasted. The recipes are accompanied by their nutritional information, so that the user can exhaustively monitor what he/she eats. This embedded system may provide economic benefits to the manufacturer, since it allows supermarkets to pay for displaying their products advertised through the application. After system deployment, design conclusions are shown, and future improvement points are indicated. Full article

(This article belongs to the Special Issue The Internet of Things for Smart Environments)

► Show Figures

Figure 1

13 pages, 2028 KiB

Open AccessFeature PaperArticle

SEO Practices: A Study about the Way News Websites Allow the Users to Comment on Their News Articles

by Minos-Athanasios Karyotakis, Evangelos Lamprou, Matina Kiourexidou and Nikos Antonopoulos

Future Internet 2019, 11(9), 188; https://doi.org/10.3390/fi11090188 - 30 Aug 2019

Cited by 17 | Viewed by 6862

Abstract

In the current media world, there is a huge debate about the importance of the visibility of a news website in order to secure its existence. Thus, search engine optimization (SEO) practices have emerged in the news media systems around the world. This [...] Read more.

In the current media world, there is a huge debate about the importance of the visibility of a news website in order to secure its existence. Thus, search engine optimization (SEO) practices have emerged in the news media systems around the world. This study aimed to expand the current literature about the SEO practices by focusing on examining, via the walkthrough method, the ways that news companies allow the users to comment on their online news articles. The comments on the news websites are related to the notions of social influence, information diffusion, and play an essential role as a SEO practice, for instance, by providing content and engagement. The examined sample was collected by the most visited news websites’ rankings of alexa.com for a global scale and for the countries Greece and Cyprus. The findings reveal that the news websites throughout the globe use similar features and ways to support the comments of the users. In the meantime, though, a high number of the news websites did not allow the users to use their social media accounts in order to comment the provided news articles, or provided multiple comment platforms. This trend goes against the SEO practices. It is believed that this finding is associated with the difficulty of the news organizations to regulate and protect themselves by the users’ comments that promote, in some case harmful rhetoric and polarization. Full article

(This article belongs to the Special Issue Search Engine Optimization)

► Show Figures

Figure 1

Figure 1
The summary of the methodology. Full article ">Figure 2
Example acquired from <a href="http://www.islandpacket.com" target="_blank">www.islandpacket.com</a>. Full article ">Figure 3
Example acquired from <a href="http://www.timesleader.com" target="_blank">www.timesleader.com</a>. Full article ">Figure 4
The Results of the Study for the International News Websites for the Commenting Platforms (n = 353). Full article ">Figure 5
The Results of the Study for the Greek News Websites for the Commenting Platforms (n = 175). Full article ">Figure 6
The Results of the Study for the Cypriot News Websites for the Commenting Platforms (n = 128). Full article ">Figure 7
The Results of the Study for the First Research Question. Full article ">Figure 8
The Results of the Study for the Second Research Question. Full article ">

18 pages, 3141 KiB

Open AccessArticle

Research on SWIM Services Dynamic Migration Method

by Zhijun Wu, Shengyan Zhou, Liang Liu and Jin Lei

Future Internet 2019, 11(9), 187; https://doi.org/10.3390/fi11090187 - 27 Aug 2019

Cited by 1 | Viewed by 3700

Abstract

Air traffic management (ATM) plays an important role in maintaining and promoting air traffic safety, maintaining air traffic order and ensuring smooth air traffic. As the core of air traffic management, it is essential to ensure the safe and stable operation of system-wide [...] Read more.

Air traffic management (ATM) plays an important role in maintaining and promoting air traffic safety, maintaining air traffic order and ensuring smooth air traffic. As the core of air traffic management, it is essential to ensure the safe and stable operation of system-wide information management (SWIM). Facing the complex and ever-changing network environment, a SWIM services dynamic migration method is proposed in this paper. This method combines SWIM core services to select destination nodes and migrate services. The experiment proves that the method can hide the service node while ensuring service continuity and increase the difficulty of malicious detection. By comparing with others, this method is more suitable for SWIM in terms of invulnerability. The throughput and delay performance of the method can meet the needs of SWIM. Full article

(This article belongs to the Special Issue Security and Privacy in Information and Communication Systems)

► Show Figures

Figure 1

14 pages, 6664 KiB

Open AccessArticle

Sustainable Communication Systems: A Graph-Labeling Approach for Cellular Frequency Allocation in Densely-Populated Areas

by Adebola Orogun, Oluwaseun Fadeyi and Ondrej Krejcar

Future Internet 2019, 11(9), 186; https://doi.org/10.3390/fi11090186 - 26 Aug 2019

Cited by 3 | Viewed by 4026

Abstract

The need for smart and sustainable communication systems has led to the development of mobile communication networks. In turn, the vast functionalities of the global system of mobile communication (GSM) have resulted in a growing number of subscribers. As the number of users [...] Read more.

The need for smart and sustainable communication systems has led to the development of mobile communication networks. In turn, the vast functionalities of the global system of mobile communication (GSM) have resulted in a growing number of subscribers. As the number of users increases, the need for efficient and effective planning of the “limited” frequency spectrum of the GSM is inevitable, particularly in densely-populated areas. As such, there are ongoing discussions about frequency (channel) allocation methods to resolve the challenges of channel allocation, which is a complete NP (Nondeterministic Polynomial time) problem. In this paper, we propose an algorithm for channel allocation which takes into account soft constraints (co-channel interference and adjacent channel interference). By using the Manhattan distance concept, this study shows that the formulation of the algorithm is correct and in line with results in the literature. Hence, the Manhattan distance concept may be useful in other scheduling and optimization problems. Furthermore, this unique concept makes it possible to develop a more sustainable telecommunication system with ease of connectivity among users, even when several subscribers are on a common frequency. Full article

(This article belongs to the Special Issue Smart Solutions in Development of Smart Applications and Systems with Aspect of Usefullness and Sustainability)

► Show Figures

Figure 1

15 pages, 626 KiB

Open AccessArticle

An Improved Method for Named Entity Recognition and Its Application to CEMR

by Ming Gao, Qifeng Xiao, Shaochun Wu and Kun Deng

Future Internet 2019, 11(9), 185; https://doi.org/10.3390/fi11090185 - 26 Aug 2019

Cited by 5 | Viewed by 3547

Abstract

Named Entity Recognition (NER) on Clinical Electronic Medical Records (CEMR) is a fundamental step in extracting disease knowledge by identifying specific entity terms such as diseases, symptoms, etc. However, the state-of-the-art NER methods based on Long Short-Term Memory (LSTM) fail to exploit GPU [...] Read more.

Named Entity Recognition (NER) on Clinical Electronic Medical Records (CEMR) is a fundamental step in extracting disease knowledge by identifying specific entity terms such as diseases, symptoms, etc. However, the state-of-the-art NER methods based on Long Short-Term Memory (LSTM) fail to exploit GPU parallelism fully under the massive medical records. Although a novel NER method based on Iterated Dilated CNNs (ID-CNNs) can accelerate network computing, it tends to ignore the word-order feature and semantic information of the current word. In order to enhance the performance of ID-CNNs-based models on NER tasks, an attention-based ID-CNNs-CRF model, which combines the word-order feature and local context, is proposed. Firstly, position embedding is utilized to fuse word-order information. Secondly, the ID-CNNs architecture is used to extract global semantic information rapidly. Simultaneously, the attention mechanism is employed to pay attention to the local context. Finally, we apply the CRF to obtain the optimal tag sequence. Experiments conducted on two CEMR datasets show that our model outperforms traditional ones. The F1-scores of 94.55% and 91.17% are obtained respectively on these two datasets, and both are better than LSTM-based models. Full article

(This article belongs to the Section Big Data and Augmented Intelligence)

► Show Figures

Figure 1

Figure 1
The left figure shows the traditional Bi-LSTM model. The input of the current moment of the Bi-LSTM model depends on the output of the previous moment, so at time i, the calculation must be iterative from left to right and iteratively calculated from right to left. The figure on the right is the Iterated Dilated (ID)-CNNs model. It is similar to the CNN structure and can be calculated in parallel. In addition, the receptive field is expanded between layers, so that global semantic information can be obtained. Full article ">Figure 2
The extraction module of the word representation. The one on the far left is character embedding; the middle one is word embedding; and the two on the right are part of speech embedding and position embedding. Full article ">Figure 3
Attention-based ID-CNN-CRF architecture. We stacked 4 Dilated CNN blocks, each as shown in Figure 5. To simplify the drawing, we used <math display="inline"><semantics> <mrow> <mi>S</mi> <mi>t</mi> <mi>a</mi> <mi>c</mi> <mi>k</mi> <mi>e</mi> <mi>d</mi> <mspace width="0.277778em"/> <mi>B</mi> <mi>l</mi> <mi>o</mi> <mi>c</mi> <mi>k</mi> <mi>s</mi> </mrow> </semantics></math> to represent all the layers in the middle. For the output <math display="inline"><semantics> <msubsup> <mi>b</mi> <mrow> <mi>t</mi> </mrow> <mi>L</mi> </msubsup> </semantics></math> at position t (the orange unit with four circles), we calculated its similarity with all the output units and took them as weights <math display="inline"><semantics> <mrow> <mo stretchy="false">{</mo> <msub> <mi>α</mi> <mrow> <mi>t</mi> <mo>,</mo> <mn>1</mn> </mrow> </msub> <mo>,</mo> <mo>…</mo> <mo>,</mo> <msub> <mi>α</mi> <mrow> <mi>t</mi> <mo>,</mo> <mi>i</mi> </mrow> </msub> <mo>,</mo> <mo>…</mo> <mo>,</mo> <msub> <mi>α</mi> <mrow> <mi>t</mi> <mo>,</mo> <mi>n</mi> </mrow> </msub> <mo stretchy="false">}</mo> </mrow> </semantics></math>. The output was multiplied by the corresponding weight and then summed as the attention vector <math display="inline"><semantics> <msub> <mi>a</mi> <mi>t</mi> </msub> </semantics></math>. Concatenate <math display="inline"><semantics> <msub> <mi>a</mi> <mi>t</mi> </msub> </semantics></math> with <math display="inline"><semantics> <msubsup> <mi>b</mi> <mrow> <mi>t</mi> </mrow> <mi>L</mi> </msubsup> </semantics></math>, and add a full connection layer to map it into the category space. Finally, the optimal tag sequence was obtained by CRF. Full article ">Figure 4
Normal CNN (left) acts on a continuous position of the input matrix and continuously slides to do convolution and pooling. The dilated CNN (right) adds a dilation width to the filter. When it acts on the input matrix, it skips the input data in the middle of all the dilation width, and the size of the filter matrix itself remains the same, so the filter achieves a wider input. Full article ">Figure 5
A dilated CNN block. The input is a sequence of texts, each of which is the word representation of <a href="#futureinternet-11-00185-f002" class="html-fig">Figure 2</a> (for example, 15 words are entered). The circles just represent the concept of dimensions. Layer 1 has a coefficient of expansion of 1 to obtain a receptive field of 3. Layer 2 expands by 1 on the basis of Layer 1; although the receptive field in Layer 2 is still 3, the receptive field in the input is 7. Take the orange unit of Layer 3 as an example: all related neurons are connected by thick lines, and the receptive field is 15. Each unit of each layer is connected to the three units of the previous layer; the number of parameters remains unchanged, but the receptive field increases geometrically. Full article ">Figure 6
The chart on the left shows the effect of changes in the different embedding dimensions of CCKS2017 on the F1-score of the model (the chart on the right is CCKS2018). The abscissa represents different dimensions, and the ordinate represents the F1-score of the model on the test set. Full article ">

17 pages, 522 KiB

Open AccessArticle

Mobility-Enabled Edge Server Selection for Multi-User Composite Services

by Wenming Zhang, Yiwen Zhang, Qilin Wu and Kai Peng

Future Internet 2019, 11(9), 184; https://doi.org/10.3390/fi11090184 - 25 Aug 2019

Cited by 8 | Viewed by 4778

Abstract

In mobile edge computing, a set of edge servers is geographically deployed near the mobile users such that accessible computing capacities and services can be provided to users with low latency. Due to user’s mobility, one fundamental and critical problem in mobile edge [...] Read more.

In mobile edge computing, a set of edge servers is geographically deployed near the mobile users such that accessible computing capacities and services can be provided to users with low latency. Due to user’s mobility, one fundamental and critical problem in mobile edge computing is how to select edge servers for many mobile users so that the total waiting time is minimized. In this paper, we propose a multi-user waiting time computation model about composite services and show the resource contention of the edge server among mobile users. Then, we introduce a novel and optimal Multi-user Edge server Selection method based on Particle swarm optimization (MESP) in mobile edge computing, which selects edge servers for mobile uses in advance within polynomial time. Extensive simulations on a real-world data-trace show that the MESP algorithm can effectively reduce the total waiting time compared with traditional approaches. Full article

(This article belongs to the Section Network Virtualization and Edge/Fog Computing)

► Show Figures

Figure 1

21 pages, 3007 KiB

Open AccessArticle

A Proof-of-Concept Demonstration of Isolated and Encrypted Service Function Chains

by Håkon Gunleifsen, Thomas Kemmerich and Vasileios Gkioulos

Future Internet 2019, 11(9), 183; https://doi.org/10.3390/fi11090183 - 24 Aug 2019

Cited by 3 | Viewed by 3845

Abstract

Contemporary Service Function Chaining (SFC), and the requirements arising from privacy concerns, call for the increasing integration of security features such as encryption and isolation across Network Function Virtualisation (NFV) domains. Therefore, suitable adaptations of automation and encryption concepts for the development of [...] Read more.

Contemporary Service Function Chaining (SFC), and the requirements arising from privacy concerns, call for the increasing integration of security features such as encryption and isolation across Network Function Virtualisation (NFV) domains. Therefore, suitable adaptations of automation and encryption concepts for the development of interconnected data centre infrastructures are essential. Nevertheless, packet isolation constraints related to the current NFV infrastructure and SFC protocols, render current NFV standards insecure. Accordingly, the goal of our work was an experimental demonstration of a new SFC packet forwarding standard that enables contemporary data centres to overcome these constraints. This article presents a comprehensive view of the developed architecture, focusing on the elements that constitute a new forwarding standard of encrypted SFC packets. Through a Proof-of-Concept demonstration, we present our closing experimental results of how the architecture fulfils the requirements defined in our use case. Full article

(This article belongs to the Section Network Virtualization and Edge/Fog Computing)

► Show Figures

Figure 1

23 pages, 1739 KiB

Open AccessArticle

An Ontology-Based Recommender System with an Application to the Star Trek Television Franchise

by Paul Sheridan, Mikael Onsjö, Claudia Becerra, Sergio Jimenez and George Dueñas

Future Internet 2019, 11(9), 182; https://doi.org/10.3390/fi11090182 - 22 Aug 2019

Cited by 11 | Viewed by 4681

Abstract

Collaborative filtering based recommender systems have proven to be extremely successful in settings where user preference data on items is abundant. However, collaborative filtering algorithms are hindered by their weakness against the item cold-start problem and general lack of interpretability. Ontology-based recommender systems [...] Read more.

Collaborative filtering based recommender systems have proven to be extremely successful in settings where user preference data on items is abundant. However, collaborative filtering algorithms are hindered by their weakness against the item cold-start problem and general lack of interpretability. Ontology-based recommender systems exploit hierarchical organizations of users and items to enhance browsing, recommendation, and profile construction. While ontology-based approaches address the shortcomings of their collaborative filtering counterparts, ontological organizations of items can be difficult to obtain for items that mostly belong to the same category (e.g., television series episodes). In this paper, we present an ontology-based recommender system that integrates the knowledge represented in a large ontology of literary themes to produce fiction content recommendations. The main novelty of this work is an ontology-based method for computing similarities between items and its integration with the classical Item-KNN (K-nearest neighbors) algorithm. As a study case, we evaluated the proposed method against other approaches by performing the classical rating prediction task on a collection of Star Trek television series episodes in an item cold-start scenario. This transverse evaluation provides insights into the utility of different information resources and methods for the initial stages of recommender system development. We found our proposed method to be a convenient alternative to collaborative filtering approaches for collections of mostly similar items, particularly when other content-based approaches are not applicable or otherwise unavailable. Aside from the new methods, this paper contributes a testbed for future research and an online framework to collaboratively extend the ontology of literary themes to cover other narrative content. Full article

(This article belongs to the Special Issue New Perspectives on Semantic Web Technologies and Applications)

► Show Figures

Figure 1

Figure 1
Literary Theme Ontology v0.1.3 class hierarchy overview. (A–D) show “the human condition”, “alternate reality”, “society”, and “the pursuit of knowledge” domain themes to three levels of depth, respectively. Full article ">Figure 2
Star Trek television series episode IMDb user ratings distribution as of December 2018. Full article ">Figure 3
Results for the RSs (recommender systems) built using transcripts, themes, and the ontology of themes. (A) CBF using transcripts; (B) KBF using themes; (C) OBF using themes and ontology. Full article ">Figure 4
Behavior of softness control parameter p from Equation (<a href="#FD8-futureinternet-11-00182" class="html-disp-formula">8</a>) in the OBF recommenders when the number of nearest neighbors k is fixed at 60. Full article ">Figure A1
Story recommender R Shiny web application screenshot. The table lists the top ten most similar episodes to the Voyager episode False Profits. Pairwise episode similarity is determined by applying the cosine index to central themes. The file StarTrek.smt is a background storyset file containing story IDs for all 452 thematically annotated Star Trek television series episodes considered in this work. Full article ">

Journal Menu

Journal Browser

Future Internet, Volume 11, Issue 9 (September 2019) – 22 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI