Previous Issue

Table of Contents

Information, Volume 10, Issue 5 (May 2019)

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Readerexternal link to open them.
Cover Story (view full-size image) Recommender systems have gained a lot of popularity due to their widespread adoption in various [...] Read more.
View options order results:
result details:
Displaying articles 1-22
Export citation of selected articles as:
Open AccessArticle
A Computation-Efficient Group Key Distribution Protocol Based on a New Secret Sharing Scheme
Information 2019, 10(5), 175; https://doi.org/10.3390/info10050175
Received: 21 March 2019 / Revised: 27 April 2019 / Accepted: 8 May 2019 / Published: 10 May 2019
Viewed by 214 | PDF Full-text (2052 KB) | HTML Full-text | XML Full-text
Abstract
With the development of 5G and the Internet of Things (IoT), mobile terminals are widely used in various applications under multicast scenarios. However, due to the limited computation resources of mobile terminals, reducing the computation cost of members in group key distribution processes [...] Read more.
With the development of 5G and the Internet of Things (IoT), mobile terminals are widely used in various applications under multicast scenarios. However, due to the limited computation resources of mobile terminals, reducing the computation cost of members in group key distribution processes of dynamic groups has become an important issue. In this paper, we propose a computation-efficient group key distribution (CEGKD) protocol. First, an improved secret sharing scheme is proposed to construct faster encryption and decryption algorithms. Second, the tree structure of logical key hierarchy (LKH) is employed to implement a simple and effective key-numbering method. Theoretical analysis is given to prove that the proposed protocol meets forward security and backward security. In addition, the experiment results show that the computation cost of CEGKD on the member side is reduced by more than 85% compared with that of the LKH scheme. Full article
(This article belongs to the Section Information and Communications Technology)
Figures

Figure 1

Open AccessArticle
Sequeval: An Offline Evaluation Framework for Sequence-Based Recommender Systems
Information 2019, 10(5), 174; https://doi.org/10.3390/info10050174
Received: 15 April 2019 / Revised: 30 April 2019 / Accepted: 7 May 2019 / Published: 10 May 2019
Viewed by 245 | PDF Full-text (473 KB) | HTML Full-text | XML Full-text
Abstract
Recommender systems have gained a lot of popularity due to their large adoption in various industries such as entertainment and tourism. Numerous research efforts have focused on formulating and advancing state-of-the-art of systems that recommend the right set of items to the right [...] Read more.
Recommender systems have gained a lot of popularity due to their large adoption in various industries such as entertainment and tourism. Numerous research efforts have focused on formulating and advancing state-of-the-art of systems that recommend the right set of items to the right person. However, these recommender systems are hard to compare since the published evaluation results are computed on diverse datasets and obtained using different methodologies. In this paper, we researched and prototyped an offline evaluation framework called Sequeval that is designed to evaluate recommender systems capable of suggesting sequences of items. We provide a mathematical definition of such sequence-based recommenders, a methodology for performing their evaluation, and the implementation details of eight metrics. We report the lessons learned using this framework for assessing the performance of four baselines and two recommender systems based on Conditional Random Fields (CRF) and Recurrent Neural Networks (RNN), considering two different datasets. Sequeval is publicly available and it aims to become a focal point for researchers and practitioners when experimenting with sequence-based recommender systems, providing comparable and objective evaluation results. Full article
(This article belongs to the Special Issue Modern Recommender Systems: Approaches, Challenges and Applications)
Figures

Figure 1

Open AccessArticle
Interactivity in Cybermedia News: An Interview with Journalists in Colombia, Peru, and Ecuador
Information 2019, 10(5), 173; https://doi.org/10.3390/info10050173
Received: 11 April 2019 / Revised: 6 May 2019 / Accepted: 6 May 2019 / Published: 9 May 2019
Viewed by 249 | PDF Full-text (569 KB) | HTML Full-text | XML Full-text
Abstract
Interactivity is a factor on which cyber journalism is based and summarizes participation options between a user and the medium, a user with other users, and a user with editors. In this study, we focus on the latter in three countries—Colombia, Peru, and [...] Read more.
Interactivity is a factor on which cyber journalism is based and summarizes participation options between a user and the medium, a user with other users, and a user with editors. In this study, we focus on the latter in three countries—Colombia, Peru, and Ecuador—, which have been identified owing to their technological gap and the emerging importance of online communication for their respective societies. Through 35 in-depth interviews with journalists from these countries, we analyzed the concept of interactivity of these professionals and their relationship with users. The results revealed that the journalists positively valued civic contributions as a space for diagnosis, although they do not perceive its informational value, as they relate them to the context of opinions. These results verify the prevalence of journalism as strongly influenced by conventional offline production routines. Full article
(This article belongs to the Special Issue Digital Citizenship and Participation 2018)
Figures

Figure 1

Open AccessArticle
Link Prediction Based on Deep Convolutional Neural Network
Information 2019, 10(5), 172; https://doi.org/10.3390/info10050172
Received: 28 February 2019 / Revised: 25 April 2019 / Accepted: 5 May 2019 / Published: 9 May 2019
Viewed by 222 | PDF Full-text (1635 KB) | HTML Full-text | XML Full-text
Abstract
In recent years, endless link prediction algorithms based on network representation learning have emerged. Network representation learning mainly constructs feature vectors by capturing the neighborhood structure information of network nodes for link prediction. However, this type of algorithm only focuses on learning topology [...] Read more.
In recent years, endless link prediction algorithms based on network representation learning have emerged. Network representation learning mainly constructs feature vectors by capturing the neighborhood structure information of network nodes for link prediction. However, this type of algorithm only focuses on learning topology information from the simple neighbor network node. For example, DeepWalk takes a random walk path as the neighborhood of nodes. In addition, such algorithms only take advantage of the potential features of nodes, but the explicit features of nodes play a good role in link prediction. In this paper, a link prediction method based on deep convolutional neural network is proposed. It constructs a model of the residual attention network to capture the link structure features from the sub-graph. Further study finds that the information flow transmission efficiency of the residual attention mechanism was not high, so a densely convolutional neural network model was proposed for link prediction. We evaluate our proposed method on four published data sets. The results show that our method is better than several other benchmark algorithms on link prediction. Full article
Figures

Figure 1

Open AccessArticle
Ontological Semantic Annotation of an English Corpus Through Condition Random Fields
Information 2019, 10(5), 171; https://doi.org/10.3390/info10050171
Received: 27 February 2019 / Revised: 28 April 2019 / Accepted: 30 April 2019 / Published: 9 May 2019
Viewed by 224 | PDF Full-text (450 KB) | HTML Full-text | XML Full-text
Abstract
One way to increase the understanding of texts by machines is through adding semantic information to lexical items by including metadata tags, a process also called semantic annotation. There are several semantic aspects that can be added to the words, among them the [...] Read more.
One way to increase the understanding of texts by machines is through adding semantic information to lexical items by including metadata tags, a process also called semantic annotation. There are several semantic aspects that can be added to the words, among them the information about the nature of the concept denoted through the association with a category of an ontology. The application of ontologies in the annotation task can span multiple domains. However, this particular research focused its approach on top-level ontologies due to its generalizing characteristic. Considering that annotation is an arduous task that demands time and specialized personnel to perform it, much is done on ways to implement the semantic annotation automatically. The use of machine learning techniques are the most effective approaches in the annotation process. Another factor of great importance for the success of the training process of the supervised learning algorithms is the use of a sufficiently large corpus and able to condense the linguistic variance of the natural language. In this sense, this article aims to present an automatic approach to enrich documents from the American English corpus through a CRF model for semantic annotation of ontologies from Schema.org top-level. The research uses two approaches of the model obtaining promising results for the development of semantic annotation based on top-level ontologies. Although it is a new line of research, the use of top-level ontologies for automatic semantic enrichment of texts can contribute significantly to the improvement of text interpretation by machines. Full article
(This article belongs to the Special Issue Text Mining: Classification, Clustering, and Summarization)
Figures

Figure 1

Open AccessArticle
Research on the Quantitative Method of Cognitive Loading in a Virtual Reality System
Information 2019, 10(5), 170; https://doi.org/10.3390/info10050170
Received: 20 March 2019 / Revised: 23 April 2019 / Accepted: 4 May 2019 / Published: 8 May 2019
Viewed by 223 | PDF Full-text (1155 KB) | HTML Full-text | XML Full-text
Abstract
Aimed at the problem of how to objectively obtain the threshold of a user’s cognitive load in a virtual reality interactive system, a method for user cognitive load quantification based on an eye movement experiment is proposed. Eye movement data were collected in [...] Read more.
Aimed at the problem of how to objectively obtain the threshold of a user’s cognitive load in a virtual reality interactive system, a method for user cognitive load quantification based on an eye movement experiment is proposed. Eye movement data were collected in the virtual reality interaction process by using an eye movement instrument. Taking the number of fixation points, the average fixation duration, the average saccade length, and the number of the first mouse clicking fixation points as the independent variables, and the number of backward-looking times and the value of user cognitive load as the dependent variables, a cognitive load evaluation model was established based on the probabilistic neural network. The model was validated by using eye movement data and subjective cognitive load data. The results show that the absolute error and relative mean square error were 6.52%–16.01% and 6.64%–23.21%, respectively. Therefore, the model is feasible. Full article
(This article belongs to the Section Artificial Intelligence)
Figures

Figure 1

Open AccessArticle
Dynamic Fault-Tolerant Workflow Scheduling with Hybrid Spatial-Temporal Re-Execution in Clouds
Information 2019, 10(5), 169; https://doi.org/10.3390/info10050169
Received: 25 March 2019 / Revised: 21 April 2019 / Accepted: 24 April 2019 / Published: 5 May 2019
Viewed by 271 | PDF Full-text (430 KB) | HTML Full-text | XML Full-text
Abstract
Improving reliability is one of the major concerns of scientific workflow scheduling in clouds. The ever-growing computational complexity and data size of workflows present challenges to fault-tolerant workflow scheduling. Therefore, it is essential to design a cost-effective fault-tolerant scheduling approach for large-scale workflows. [...] Read more.
Improving reliability is one of the major concerns of scientific workflow scheduling in clouds. The ever-growing computational complexity and data size of workflows present challenges to fault-tolerant workflow scheduling. Therefore, it is essential to design a cost-effective fault-tolerant scheduling approach for large-scale workflows. In this paper, we propose a dynamic fault-tolerant workflow scheduling (DFTWS) approach with hybrid spatial and temporal re-execution schemes. First, DFTWS calculates the time attributes of tasks and identifies the critical path of workflow in advance. Then, DFTWS assigns appropriate virtual machine (VM) for each task according to the task urgency and budget quota in the phase of initial resource allocation. Finally, DFTWS performs online scheduling, which makes real-time fault-tolerant decisions based on failure type and task criticality throughout workflow execution. The proposed algorithm is evaluated on real-world workflows. Furthermore, the factors that affect the performance of DFTWS are analyzed. The experimental results demonstrate that DFTWS achieves a trade-off between high reliability and low cost objectives in cloud computing environments. Full article
(This article belongs to the Section Information Systems)
Figures

Figure 1

Open AccessArticle
Similarity Measures of Linguistic Cubic Hesitant Variables for Multiple Attribute Group Decision-Making
Information 2019, 10(5), 168; https://doi.org/10.3390/info10050168
Received: 4 April 2019 / Revised: 24 April 2019 / Accepted: 24 April 2019 / Published: 5 May 2019
Viewed by 271 | PDF Full-text (263 KB) | HTML Full-text | XML Full-text
Abstract
A linguistic cubic hesitant variable (LCHV) is a hybrid form of linguistic values in group decision-making environments. It is composed of an interval language variable and multiple single-valued language variables given by different decision-makers (DMs). Due to the uncertainty and hesitation of DMs, [...] Read more.
A linguistic cubic hesitant variable (LCHV) is a hybrid form of linguistic values in group decision-making environments. It is composed of an interval language variable and multiple single-valued language variables given by different decision-makers (DMs). Due to the uncertainty and hesitation of DMs, the numbers of language variables in different LCHVs are unequal. Thus, the least common multiple number (LCMN) extension method was adopted. Based on the included angle and distance of two LCHVs, we presented two cosine similarity measures and developed a multiple attribute group decision-making (MAGDM) approach. An example of engineer selection was used to implement the proposed LCHV MAGDM method and demonstrate the simplicity and feasibility of the proposed method. The sensitivity analysis of weight changes for the two measures showed that the similarity measure based on distance was more stable than the similarity measure based on included angle in this application. Full article
Open AccessArticle
A Novel Fractional-Order Grey Prediction Model and Its Modeling Error Analysis
Information 2019, 10(5), 167; https://doi.org/10.3390/info10050167
Received: 23 March 2019 / Revised: 28 April 2019 / Accepted: 28 April 2019 / Published: 5 May 2019
Viewed by 242 | PDF Full-text (671 KB)
Abstract
Based on the grey prediction model GM(1,1), a novel fractional-order grey prediction model is proposed and its modeling error is systematically studied. In this paper, exponential data sequences are generated for numerical simulation. Via the numerical simulation method, the mean absolute percentage error [...] Read more.
Based on the grey prediction model GM(1,1), a novel fractional-order grey prediction model is proposed and its modeling error is systematically studied. In this paper, exponential data sequences are generated for numerical simulation. Via the numerical simulation method, the mean absolute percentage error (MAPE) of the fractional-order GM(1,1) with different values of order and development coefficient is compared to the GM(1,1) and the discrete GM(1,1). The error distribution of the sequences of exponential data is given. The GM(1,1) and the direct modeling GM(1,1) are both special cases of the fractional-order GM(1,1). The conclusion is helpful to further optimize the grey model using fractional-order operators and to expand the applicable bound of GM(1,1). Full article
(This article belongs to the Section Information Processes)
Open AccessArticle
How Much Do Emotional, Behavioral, and Cognitive Factors Actually Impact College Student Attitudes towards English Language Learning? A Quantitative and Qualitative Study
Information 2019, 10(5), 166; https://doi.org/10.3390/info10050166
Received: 13 March 2019 / Revised: 14 April 2019 / Accepted: 15 April 2019 / Published: 5 May 2019
Viewed by 260 | PDF Full-text (805 KB) | HTML Full-text | XML Full-text
Abstract
Researchers have proposed many multidimensional frameworks to identify significant and potential factors, e.g., educational background, positive feelings and career aspirations, that impact English learning attitude in second language acquisition. Yet, there is still very little research to graphically describe the interactions between these [...] Read more.
Researchers have proposed many multidimensional frameworks to identify significant and potential factors, e.g., educational background, positive feelings and career aspirations, that impact English learning attitude in second language acquisition. Yet, there is still very little research to graphically describe the interactions between these factors and how these factors directly or indirectly impact learning attitude. To this end, a questionnaire survey was conducted in Changchun University of Technology. Statistical measures and Bayesian network analysis were introduced to quantitatively and qualitatively analyze the collected data. Furthermore, the significant attitudinal differences between students majoring in the Liberal Arts or Sciences were investigated for the case study. Studying the interaction between these factors can help explain how they positively affect students’ attitudes toward English language learning. To stimulate interest, teachers may take targeted pedagogical approaches or strategies. Full article
(This article belongs to the Section Information Applications)
Figures

Figure 1

Open AccessArticle
An Improved Jacobi-Based Detector for Massive MIMO Systems
Information 2019, 10(5), 165; https://doi.org/10.3390/info10050165
Received: 11 March 2019 / Revised: 4 April 2019 / Accepted: 9 April 2019 / Published: 5 May 2019
Viewed by 257 | PDF Full-text (915 KB) | HTML Full-text | XML Full-text
Abstract
Massive multiple-input-multiple-output (MIMO) is one of the key technologies in the fifth generation (5G) cellular communication systems. For uplink massive MIMO systems, the typical linear detection such as minimum mean square error (MMSE) presents a near-optimal performance. Due to the required direct matrix [...] Read more.
Massive multiple-input-multiple-output (MIMO) is one of the key technologies in the fifth generation (5G) cellular communication systems. For uplink massive MIMO systems, the typical linear detection such as minimum mean square error (MMSE) presents a near-optimal performance. Due to the required direct matrix inverse, however, the MMSE detection algorithm becomes computationally very expensive, especially when the number of users is large. For achieving the high detection accuracy as well as reducing the computational complexity in massive MIMO systems, we propose an improved Jacobi iterative algorithm by accelerating the convergence rate in the signal detection process.Specifically, the steepest descent (SD) method is utilized to achieve an efficient searching direction. Then, the whole-correction method is applied to update the iterative process. As the result, the fast convergence and the low computationally complexity of the proposed Jacobi-based algorithm are obtained and proved. Simulation results also demonstrate that the proposed algorithm performs better than the conventional algorithms in terms of the bit error rate (BER) and achieves a near-optimal detection accuracy as the typical MMSE detector, but utilizing a small number of iterations. Full article
(This article belongs to the Section Information and Communications Technology)
Figures

Figure 1

Open AccessArticle
A Complexity Reduction Scheme for Depth Coding in 3D-HEVC
Information 2019, 10(5), 164; https://doi.org/10.3390/info10050164
Received: 9 March 2019 / Revised: 3 April 2019 / Accepted: 9 April 2019 / Published: 3 May 2019
Viewed by 282 | PDF Full-text (1514 KB) | HTML Full-text | XML Full-text
Abstract
3D-high efficiency video coding (3D-HEVC) is the next-generation compression standard for multiview system applications, which has recently been approved by MPEG and VCEG as an extension of HEVC. To improve the compression efficiency of depth map, several compression tools have been developed for [...] Read more.
3D-high efficiency video coding (3D-HEVC) is the next-generation compression standard for multiview system applications, which has recently been approved by MPEG and VCEG as an extension of HEVC. To improve the compression efficiency of depth map, several compression tools have been developed for a better representation depth edges. These supplementary coding tools together with existing prediction modes can achieve high compression efficiency, but require a very high complexity that restricts the encoders from ongoing application. In this paper, we introduce a fast scheme to reduce complexity of depth coding in inter and intramode prediction procedure. A simulation analysis is performed to study intra and intermode distribution correlations in the depth compression information. Based on that correlation, we exploit two complexity reduction strategies, including early SKIP and adaptive intra prediction selection. Experimental results demonstrate that our scheme can achieve a complexity reduction up to 63.0%, without any noticeable loss of compression efficiency. Full article
(This article belongs to the Section Information Theory and Methodology)
Figures

Figure 1

Open AccessArticle
Spatiotemporal Clustering Analysis of Bicycle Sharing System with Data Mining Approach
Information 2019, 10(5), 163; https://doi.org/10.3390/info10050163
Received: 27 February 2019 / Revised: 21 April 2019 / Accepted: 25 April 2019 / Published: 2 May 2019
Viewed by 293 | PDF Full-text (756 KB) | HTML Full-text | XML Full-text
Abstract
The main objective of this study is to explore the spatiotemporal activities pattern of bicycle sharing system by combining together temporal and spatial attributes variables through clustering analysis method. Specifically, three clustering algorithms, i.e., hierarchical clustering, K-means clustering, expectation maximization clustering, are chosen [...] Read more.
The main objective of this study is to explore the spatiotemporal activities pattern of bicycle sharing system by combining together temporal and spatial attributes variables through clustering analysis method. Specifically, three clustering algorithms, i.e., hierarchical clustering, K-means clustering, expectation maximization clustering, are chosen to group the bicycle sharing stations. The temporal attributes variables are obtained through the statistical analysis of bicycle sharing smart card data, and the spatial attributes variables are quantified by point of interest (POI) data around bicycle sharing docking stations, which reflects the influence of land use on bicycle sharing system. According to the performance of the three clustering algorithms and six cluster validation measures, K-means clustering has been proven as the better clustering algorithm for the case of Ningbo, China. Then, the 477 bicycle sharing docking stations were clustered into seven clusters. The results show that the stations of each cluster have their own unique spatiotemporal activities pattern influenced by people’s travel habits and land use characteristics around the stations. This analysis will help bicycle sharing operators better understand the system usage and learn how to improve the service quality of the existing system. Full article
Figures

Figure 1

Open AccessArticle
Cross-Domain Text Sentiment Analysis Based on CNN_FT Method
Information 2019, 10(5), 162; https://doi.org/10.3390/info10050162
Received: 25 February 2019 / Revised: 13 April 2019 / Accepted: 22 April 2019 / Published: 1 May 2019
Viewed by 300 | PDF Full-text (1109 KB)
Abstract
Transfer learning is one of the popular methods for solving the problem that the models built on the source domain cannot be directly applied to the target domain in the cross-domain sentiment classification. This paper proposes a transfer learning method based on the [...] Read more.
Transfer learning is one of the popular methods for solving the problem that the models built on the source domain cannot be directly applied to the target domain in the cross-domain sentiment classification. This paper proposes a transfer learning method based on the multi-layer convolutional neural network (CNN). Interestingly, we construct a convolutional neural network model to extract features from the source domain and share the weights in the convolutional layer and the pooling layer between the source and target domain samples. Next, we fine-tune the weights in the last layer, named the fully connected layer, and transfer the models from the source domain to the target domain. Comparing with the classical transfer learning methods, the method proposed in this paper does not need to retrain the network for the target domain. The experimental evaluation of the cross-domain data set shows that the proposed method achieves a relatively good performance. Full article
(This article belongs to the Section Information Processes)
Open AccessArticle
FastText-Based Intent Detection for Inflected Languages
Information 2019, 10(5), 161; https://doi.org/10.3390/info10050161
Received: 15 January 2019 / Revised: 12 April 2019 / Accepted: 25 April 2019 / Published: 1 May 2019
Viewed by 324 | PDF Full-text (856 KB) | HTML Full-text | XML Full-text
Abstract
Intent detection is one of the main tasks of a dialogue system. In this paper, we present our intent detection system that is based on fastText word embeddings and a neural network classifier. We find an improvement in fastText sentence vectorization, which, in [...] Read more.
Intent detection is one of the main tasks of a dialogue system. In this paper, we present our intent detection system that is based on fastText word embeddings and a neural network classifier. We find an improvement in fastText sentence vectorization, which, in some cases, shows a significant increase in intent detection accuracy. We evaluate the system on languages commonly spoken in Baltic countries—Estonian, Latvian, Lithuanian, English, and Russian. The results show that our intent detection system provides state-of-the-art results on three previously published datasets, outperforming many popular services. In addition to this, for Latvian, we explore how the accuracy of intent detection is affected if we normalize the text in advance. Full article
(This article belongs to the Special Issue Artificial Intelligence—Methodology, Systems, and Applications)
Figures

Figure 1

Open AccessArticle
P2P Botnet Detection Based on Nodes Correlation by the Mahalanobis Distance
Information 2019, 10(5), 160; https://doi.org/10.3390/info10050160
Received: 7 February 2019 / Revised: 7 April 2019 / Accepted: 9 April 2019 / Published: 1 May 2019
Viewed by 273 | PDF Full-text (3118 KB) | HTML Full-text | XML Full-text
Abstract
Botnets are a common and serious threat to the Internet. The search for the infected nodes of a P2P botnet is affected by the number of commonly connected nodes, with a lower detection accuracy rate for cases with fewer commonly connected nodes. However, [...] Read more.
Botnets are a common and serious threat to the Internet. The search for the infected nodes of a P2P botnet is affected by the number of commonly connected nodes, with a lower detection accuracy rate for cases with fewer commonly connected nodes. However, this paper calculates the Mahalanobis distance—which can express correlations between data—between indirectly connected nodes through traffic with commonly connected nodes, and establishes a relationship evaluation model among nodes. An iterative algorithm is used to obtain the correlation coefficient between the nodes, and the threshold is set to detect P2P botnets. The experimental results show that this method can effectively detect P2P botnets with an accuracy of >85% when the correlation coefficient is high, even in cases with fewer commonly connected nodes. Full article
(This article belongs to the Section Information and Communications Technology)
Figures

Figure 1

Open AccessArticle
Improving Intrusion Detection Model Prediction by Threshold Adaptation
Information 2019, 10(5), 159; https://doi.org/10.3390/info10050159
Received: 26 February 2019 / Revised: 10 April 2019 / Accepted: 25 April 2019 / Published: 30 April 2019
Viewed by 326 | PDF Full-text (8031 KB) | HTML Full-text | XML Full-text
Abstract
Network traffic exhibits a high level of variability over short periods of time. This variability impacts negatively on the accuracy of anomaly-based network intrusion detection systems (IDS) that are built using predictive models in a batch learning setup. This work investigates how adapting [...] Read more.
Network traffic exhibits a high level of variability over short periods of time. This variability impacts negatively on the accuracy of anomaly-based network intrusion detection systems (IDS) that are built using predictive models in a batch learning setup. This work investigates how adapting the discriminating threshold of model predictions, specifically to the evaluated traffic, improves the detection rates of these intrusion detection models. Specifically, this research studied the adaptability features of three well known machine learning algorithms: C5.0, Random Forest and Support Vector Machine. Each algorithm’s ability to adapt their prediction thresholds was assessed and analysed under different scenarios that simulated real world settings using the prospective sampling approach. Multiple IDS datasets were used for the analysis, including a newly generated dataset (STA2018). This research demonstrated empirically the importance of threshold adaptation in improving the accuracy of detection models when training and evaluation traffic have different statistical properties. Tests were undertaken to analyse the effects of feature selection and data balancing on model accuracy when different significant features in traffic were used. The effects of threshold adaptation on improving accuracy were statistically analysed. Of the three compared algorithms, Random Forest was the most adaptable and had the highest detection rates. Full article
(This article belongs to the Special Issue Machine Learning for Cyber-Security)
Figures

Figure 1

Open AccessArticle
Efficient Ensemble Classification for Multi-Label Data Streams with Concept Drift
Information 2019, 10(5), 158; https://doi.org/10.3390/info10050158
Received: 20 February 2019 / Revised: 14 April 2019 / Accepted: 18 April 2019 / Published: 28 April 2019
Viewed by 329 | PDF Full-text (1610 KB) | HTML Full-text | XML Full-text
Abstract
Most existing multi-label data streams classification methods focus on extending single-label streams classification approaches to multi-label cases, without considering the special characteristics of multi-label stream data, such as label dependency, concept drift, and recurrent concepts. Motivated by these challenges, we devise an efficient [...] Read more.
Most existing multi-label data streams classification methods focus on extending single-label streams classification approaches to multi-label cases, without considering the special characteristics of multi-label stream data, such as label dependency, concept drift, and recurrent concepts. Motivated by these challenges, we devise an efficient ensemble paradigm for multi-label data streams classification. The algorithm deploys a novel change detection based on Jensen–Shannon divergence to identify different kinds of concept drift in data streams. Moreover, our method tries to consider label dependency by pruning away infrequent label combinations to enhance classification performance. Empirical results on both synthetic and real-world datasets have demonstrated its effectiveness. Full article
Figures

Figure 1

Open AccessArticle
DGA CapsNet: 1D Application of Capsule Networks to DGA Detection
Information 2019, 10(5), 157; https://doi.org/10.3390/info10050157
Received: 26 February 2019 / Revised: 19 April 2019 / Accepted: 23 April 2019 / Published: 27 April 2019
Viewed by 377 | PDF Full-text (912 KB) | HTML Full-text | XML Full-text
Abstract
Domain generation algorithms (DGAs) represent a class of malware used to generate large numbers of new domain names to achieve command-and-control (C2) communication between the malware program and its C2 server to avoid detection by cybersecurity measures. Deep learning has proven successful in [...] Read more.
Domain generation algorithms (DGAs) represent a class of malware used to generate large numbers of new domain names to achieve command-and-control (C2) communication between the malware program and its C2 server to avoid detection by cybersecurity measures. Deep learning has proven successful in serving as a mechanism to implement real-time DGA detection, specifically through the use of recurrent neural networks (RNNs) and convolutional neural networks (CNNs). This paper compares several state-of-the-art deep-learning implementations of DGA detection found in the literature with two novel models: a deeper CNN model and a one-dimensional (1D) Capsule Networks (CapsNet) model. The comparison shows that the 1D CapsNet model performs as well as the best-performing model from the literature. Full article
(This article belongs to the Special Issue Machine Learning for Cyber-Security)
Figures

Figure 1

Open AccessArticle
Exploring Whether Data Can be Represented as a Composite Unit in Form Processing Using the Manufacturing of Information Approach
Information 2019, 10(5), 156; https://doi.org/10.3390/info10050156
Received: 5 March 2019 / Revised: 24 April 2019 / Accepted: 24 April 2019 / Published: 26 April 2019
Viewed by 388 | PDF Full-text (918 KB) | HTML Full-text | XML Full-text
Abstract
Data and information quality have been recognized as essential components for improving business efficiency. One approach for the assessment of information quality (IQ) is the manufacturing of information (MI). So far, research using this approach has considered a whole document as one indivisible [...] Read more.
Data and information quality have been recognized as essential components for improving business efficiency. One approach for the assessment of information quality (IQ) is the manufacturing of information (MI). So far, research using this approach has considered a whole document as one indivisible block, which allows document evaluation only at a general level. However, the data inside the documents can be represented as components, which can further be classified according to content and composition. In this paper, we propose a novel model to explore the effectiveness of representing data as a composite unit, rather than indivisible blocks. The input data sufficiency and the relevance of the information output are evaluated in the example of analyzing an administrative form. We found that the new streamlined form proposed resulted in a 15% improvement in IQ. Additionally, we found the relationship between the data quantity and IQ was not a “simple” correlation, as IQ may increase without a corresponding increase in data quantity. We conclude that our study shows that the representation of data as a composite unit is a determining factor in IQ assessment. Full article
(This article belongs to the Section Information Applications)
Figures

Figure 1

Open AccessFeature PaperArticle
Optimizing Parallel Collaborative Filtering Approaches for Improving Recommendation Systems Performance
Information 2019, 10(5), 155; https://doi.org/10.3390/info10050155
Received: 24 March 2019 / Revised: 21 April 2019 / Accepted: 25 April 2019 / Published: 26 April 2019
Viewed by 371 | PDF Full-text (373 KB) | HTML Full-text | XML Full-text
Abstract
Recommender systems are one of the fields of information filtering systems that have attracted great research interest during the past several decades and have been utilized in a large variety of applications, from commercial e-shops to social networks and product review sites. Since [...] Read more.
Recommender systems are one of the fields of information filtering systems that have attracted great research interest during the past several decades and have been utilized in a large variety of applications, from commercial e-shops to social networks and product review sites. Since the applicability of these applications is constantly increasing, the size of the graphs that represent their users and support their functionality increases too. Over the last several years, different approaches have been proposed to deal with the problem of scalability of recommender systems’ algorithms, especially of the group of Collaborative Filtering (CF) algorithms. This article studies the problem of CF algorithms’ parallelization under the prism of graph sparsity, and proposes solutions that may improve the prediction performance of parallel implementations without strongly affecting their time efficiency. We evaluated the proposed approach on a bipartite product-rating network using an implementation on Apache Spark. Full article
(This article belongs to the Special Issue Modern Recommender Systems: Approaches, Challenges and Applications)
Figures

Figure 1

Open AccessReview
Review of the Augmented Reality Systems for Shoulder Rehabilitation
Information 2019, 10(5), 154; https://doi.org/10.3390/info10050154
Received: 22 March 2019 / Revised: 23 April 2019 / Accepted: 23 April 2019 / Published: 26 April 2019
Viewed by 352 | PDF Full-text (1180 KB) | HTML Full-text | XML Full-text
Abstract
Literature shows an increasing interest for the development of augmented reality (AR) applications in several fields, including rehabilitation. Current studies show the need for new rehabilitation tools for upper extremity, since traditional interventions are less effective than in other body regions. This review [...] Read more.
Literature shows an increasing interest for the development of augmented reality (AR) applications in several fields, including rehabilitation. Current studies show the need for new rehabilitation tools for upper extremity, since traditional interventions are less effective than in other body regions. This review aims at: Studying to what extent AR applications are used in shoulder rehabilitation, examining wearable/non-wearable technologies employed, and investigating the evidence supporting AR effectiveness. Nine AR systems were identified and analyzed in terms of: Tracking methods, visualization technologies, integrated feedback, rehabilitation setting, and clinical evaluation. Our findings show that all these systems utilize vision-based registration, mainly with wearable marker-based tracking, and spatial displays. No system uses head-mounted displays, and only one system (11%) integrates a wearable interface (for tactile feedback). Three systems (33%) provide only visual feedback; 66% present visual-audio feedback, and only 33% of these provide visual-audio feedback, 22% visual-audio with biofeedback, and 11% visual-audio with haptic feedback. Moreover, several systems (44%) are designed primarily for home settings. Three systems (33%) have been successfully evaluated in clinical trials with more than 10 patients, showing advantages over traditional rehabilitation methods. Further clinical studies are needed to generalize the obtained findings, supporting the effectiveness of the AR applications. Full article
(This article belongs to the Special Issue Wearable Augmented and Mixed Reality Applications)
Figures

Figure 1

Information EISSN 2078-2489 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top