Information, Volume 10, Issue 8 (August 2019) – 19 articles

The current trend in the European Union (EU) is to support the development of online dispute resolution (ODR) that saves financial and human resources. Therefore, research articles mainly deal with the design of new ODR solutions, without researching the social aspects of using different kinds of ODR solutions. For this reason, the main aim of the article is an empirical evaluation of two kinds of ODR solutions in business-to-business (B2B) relationships from the perspective of a selected social category. The article focuses on: (1) comparing unassisted and smart assisted negotiation while using the artificial intelligence approach; (2) the satisfaction and attitudes of Generation Y members from the Czech and Slovak Republic towards different ways of negotiating. The conclusions of this study can help researchers to design or improve existing ODR solutions, and companies to choose the most suitable managers from Generation Y for B2B negotiation. The results show that Generation Y members prefer computer-mediated communication as compared to face to face negotiation; the participants were more satisfied with the negotiation process when using smart assisted negotiation. Through a computer-mediated negotiation, even sellers with lower emotional stability can maintain an advantageous position. Similarly, buyers with lower agreeableness or higher extraversion can negotiate more favorable terms and offset their loss. Full article

Anomaly detection of network traffic flows is a non-trivial problem in the field of network security due to the complexity of network traffic. However, most machine learning-based detection methods focus on network anomaly detection but ignore the user anomaly behavior detection. In real scenarios, the anomaly network behavior may harm the user interests. In this paper, we propose an anomaly detection model based on time-decay closed frequent patterns to address this problem. The model mines closed frequent patterns from the network traffic of each user and uses a time-decay factor to distinguish the weight of current and historical network traffic. Because of the dynamic nature of user network behavior, a detection model update strategy is provided in the anomaly detection framework. Additionally, the closed frequent patterns can provide interpretable explanations for anomalies. Experimental results show that the proposed method can detect user behavior anomaly, and the network anomaly detection performance achieved by the proposed method is similar to the state-of-the-art methods and significantly better than the baseline methods. Full article

An important problem in machine learning is that, when using more than two labels, it is very difficult to construct and optimize a group of learning functions that are still useful when the prior distribution of instances is changed. To resolve this problem, semantic information G theory, Logical Bayesian Inference (LBI), and a group of Channel Matching (CM) algorithms are combined to form a systematic solution. A semantic channel in G theory consists of a group of truth functions or membership functions. In comparison with the likelihood functions, Bayesian posteriors, and Logistic functions that are typically used in popular methods, membership functions are more convenient to use, providing learning functions that do not suffer the above problem. In Logical Bayesian Inference (LBI), every label is independently learned. For multilabel learning, we can directly obtain a group of optimized membership functions from a large enough sample with labels, without preparing different samples for different labels. Furthermore, a group of Channel Matching (CM) algorithms are developed for machine learning. For the Maximum Mutual Information (MMI) classification of three classes with Gaussian distributions in a two-dimensional feature space, only 2–3 iterations are required for the mutual information between three classes and three labels to surpass 99% of the MMI for most initial partitions. For mixture models, the Expectation-Maximization (EM) algorithm is improved to form the CM-EM algorithm, which can outperform the EM algorithm when the mixture ratios are imbalanced, or when local convergence exists. The CM iteration algorithm needs to combine with neural networks for MMI classification in high-dimensional feature spaces. LBI needs further investigation for the unification of statistics and logic. Full article

This article empirically demonstrates the impacts of truthfully sharing forecast information and using forecast combinations in a fast-moving-consumer-goods (FMCG) supply chain. Although it is known a priori that sharing information improves the overall efficiency of a supply chain, information such as pricing or promotional strategy is often kept proprietary for competitive reasons. In this regard, it is herein shown that simply sharing the retail-level forecasts—this does not reveal the exact business strategy, due to the effect of omni-channel sales—yields nearly all the benefits of sharing all pertinent information that influences FMCG demand. In addition, various forecast combination methods are used to further stabilize the forecasts, in situations where multiple forecasting models are used during operation. In other words, it is shown that combining forecasts is less risky than “betting” on any component model. Full article

Mobile edge computing (MEC) effectively integrates wireless network and Internet technologies and adds computing, storage, and processing functions to the edge of cellular networks. This new network architecture model can deliver services directly from the cloud to the very edge of the network while providing the best efficiency in mobile networks. However, due to the dynamic, open, and collaborative nature of MEC network environments, network security issues have become increasingly complex. Devices cannot easily ensure obtaining satisfactory and safe services because of the numerous, dynamic, and collaborative character of MEC devices and the lack of trust between devices. The trusted cooperative mechanism can help solve this problem. In this paper, we analyze the MEC network structure and device-to-device (D2D) trusted cooperative mechanism and their challenging issues and then discuss and compare different ways to establish the D2D trusted cooperative relationship in MEC, such as social trust, reputation, authentication techniques, and intrusion detection. All these ways focus on enhancing the efficiency, stability, and security of MEC services in presenting trustworthy services. Full article

With the construction of the urban rail transit (URT) network, the explosion of passenger volume is more rapid than the increased capacity of the newly built infrastructure, which results in serious passenger flow congestion (PLC). Understanding the propagation process of PLC is the key to formulate sustainable policies for reducing congestion and optimizing management. This study proposes a susceptible-infected-recovered (SIR) model based on the theories of epidemiological dynamics and complex network to analyze the PLC propagation. We simulate the PLC propagation under various situations, and analyze the sensitivity of PLC propagation to model parameters. Finally, the control strategies of restricting PLC propagation are introduced from two aspects, namely, supply control and demand control. The results indicate that both of the two control strategies contribute to relieving congestion pressure. The propagating scope of PLC is more sensitive when taking mild supply control, whereas, the demand control strategy shows some advantages in flexibly implementing and dealing with serious congestion. These results are of important guidance for URT agencies to understand the mechanism of PLC propagation and formulate appropriate congestion control strategies. Full article

Human eye movement is one of the most important functions for understanding our surroundings. When a human eye processes a scene, it quickly focuses on dominant parts of the scene, commonly known as a visual saliency detection or visual attention prediction. Recently, neural networks have been used to predict visual saliency. This paper proposes a deep learning encoder-decoder architecture, based on a transfer learning technique, to predict visual saliency. In the proposed model, visual features are extracted through convolutional layers from raw images to predict visual saliency. In addition, the proposed model uses the VGG-16 network for semantic segmentation, which uses a pixel classification layer to predict the categorical label for every pixel in an input image. The proposed model is applied to several datasets, including TORONTO, MIT300, MIT1003, and DUT-OMRON, to illustrate its efficiency. The results of the proposed model are quantitatively and qualitatively compared to classic and state-of-the-art deep learning models. Using the proposed deep learning model, a global accuracy of up to 96.22% is achieved for the prediction of visual saliency. Full article

Unmanned and unwomaned aerial vehicles (UAV), or drones, are breaking and creating new boundaries of image-based communication. Using social network analysis and critical discourse analysis, we examine the 60 most popular question threads about drones on Zhihu, China’s largest social question answering platform. We trace how controversial issues around these supposedly novel tech products are mediated, domesticated, visualized, or marginalized via digital representational technology. Supported by Zhihu’s topic categorization algorithm, drone-related discussions form topic clusters. These topic clusters gain currency in the government-regulated cyberspace, where their meanings remain open to widely divergent interpretations and mediation by various agents. We find that the largest drone company DJI occupies a central and strongly interconnected position in the discussions. Drones are, moreover, represented as objects of consumption, technological advancement, national future, and uncertainty. At the same time, the sense-making process of drone-related discussions evokes emerging sets of narrative user identities with potential political effects. Users engage in digital representational technologies publicly and collectively to raise questions and represent their views on new technologies. Therefore, we argue that platforms like Zhihu are essential when studying views of the Chinese citizenry towards technological developments. Full article

There has been an enormous technological boom that impacted all areas of geoscience in the past few decades. Part of the change was also the process of democratization of cartography as well as geographic information systems (GIS), together with new approaches that have emerged, bringing social dimension into cartography and GIS. These new approaches were variously labelled as critical cartography, collaborative mapping, digital citizenship, Bottom-up GIS and Participatory GIS. The paper describes the role of collaborative mapping and digital participation in the process of community building and community assets mapping. Secondly, we will use the examples of Kenya and Peru to support our findings of community development. Thirdly, we will discuss a possible further development within the use of OpenStreetMap (OSM) for remote communities. The analysis compares approaches and experiences in different countries on different continents. Full article

In this paper, I first review signal detection theory (SDT) approaches to perception, and then discuss why it is thought that SDT theory implies that increasing attention improves performance. Our experiments have shown, however, that this is not necessarily true. Subjects had either focused attention on two of four possible locations in the visual field, or diffused attention to all four locations. The stimuli (offset letters), locations, conditions, and tasks were all known in advance, responses were forced-choice, subjects were properly instructed and motivated, and instructions were always valid—conditions which should optimize signal detection. Relative to diffusing attention, focusing attention indeed benefitted discrimination of forward from backward pointing Es. However, focusing made it harder to identify a randomly chosen one of 20 letters. That focusing can either aid or disrupt performance, even when cues are valid and conditions are idealized, is surprising, but it can also be explained by SDT, as shown here. These results warn the experimental researcher not to confuse focusing attention with enhancing performance, and warn the modeler not to assume that SDT is unequivocal. Full article

The ageing population has become an increasing phenomenon world-wide, leading to a growing need for specialised help. Improving the quality of life of older people can lower the risk of depression and social isolation, but it requires a multi-dimensional approach through continuous monitoring and training of the main health domains (e.g., cognitive, motor, nutritional and behavioural). To this end, the use of mobile and e-health services tailored to the user’s needs can help stabilise their health conditions, in terms of physical, mental, and social capabilities. In this context, the INTESA project proposes a set of personalised monitoring and rehabilitation services for older people, based on mobile and wearable technologies ready to be used either at home or in residential long-term care facilities. We evaluated the proposed solution by deploying a suite of services in a nursing home and defining customised protocols to involve both guests (primary users) and nursing care personnel (secondary users). In this paper, we present the extended results obtained after the one-year period of experimentation in terms of technical reliability of the system, Quality of Experience, and user acceptance for both the user categories. Full article

Online cultural heritage resources are widely available through digital libraries maintained by numerous organizations. In order to improve discoverability in cultural heritage, the typical approach is metadata aggregation, a method where centralized efforts such as Europeana improve the discoverability by collecting resource metadata. The redefinition of the traditional data models for cultural heritage resources into data models based on semantic technology has been a major activity of the cultural heritage community. Yet, linked data may bring new innovation opportunities for cultural heritage metadata aggregation. We present the outcomes of a case study that we conducted within the Europeana cultural heritage network. In this study, the National Library of The Netherlands contributed by providing the role of data provider, while the Dutch Digital Heritage Network contributed as an intermediary aggregator that aggregates datasets and provides them to Europeana, the central aggregator. We identified and analyzed the requirements for an aggregation solution for the linked data, guided by current aggregation practices of the Europeana network. These requirements guided the definition of a workflow that fulfils the same functional requirements as the existing one. The workflow was put into practice within this study and has led to the development of software applications for administrating datasets, crawling the web of data, harvesting linked data, data analysis and data integration. We present our analysis of the study outcomes and analyze the effort necessary, in terms of technology adoption, to establish a linked data approach, from the point of view of both data providers and aggregators. We also present the expertise requirements we identified for cultural heritage data analysts, as well as determining which supporting tools were required to be designed specifically for semantic data. Full article

This study focuses on the problem of attack quantification in distribution automation systems (DASs) and proposes a quantitative model of attacks based on the common vulnerability scoring system (CVSS) and attack trees (ATs) to conduct a quantitative and systematic evaluation of attacks on a DAS. In the DAS security architecture, AT nodes are traversed and used to represent the attack path. The CVSS is used to quantify the attack sequence, which is the leaf node in an AT. This paper proposes a method to calculate each attack path probability and find the maximum attack path probability in DASs based on attacker behavior. The AT model is suitable for DAS hierarchical features in architecture. The experimental results show that the proposed model can reduce the influence of subjective factors on attack quantification, improve the probability of predicting attacks on the DASs, generate attack paths, better identify attack characteristics, and determine the attack path and quantification probability. The quantitative results of the model’s evaluation can find the most vulnerable component of a DAS and provide an important reference for developing targeted defensive measures in DASs. Full article

Twitter may be considered to be a decentralized social information processing platform whose users constantly receive their followees’ information feeds, which they may in turn dispatch to their followers. This decentralization is not devoid of hierarchy and heterogeneity, both in terms of activity and attention. In particular, we appraise the distribution of attention at the collective and individual level, which exhibits the existence of attentional constraints and focus effects. We observe that most users usually concentrate their attention on a limited core of peers and topics, and discuss the relationship between interactional and informational attention processes—all of which, we suggest, may be useful to refine influence models by enabling the consideration of differential attention likelihood depending on users, their activity levels, and peers’ positions. Full article

An important part of Open Data is of a statistical nature and describes economic and social indicators monitoring population size, inflation, trade, and employment. Combining and analyzing Open Data from multiple datasets and sources enable the performance of advanced data analytics scenarios that could result in valuable services and data products. However, it is still difficult to discover and combine Open Statistical Data that reside in different data portals. Although Linked Open Statistical Data (LOSD) provide standards and approaches to facilitate combining statistics on the Web, various interoperability challenges still exist. In this paper, we propose an Interoperability Framework for LOSD, comprising definitions of LOSD interoperability conflicts as well as modelling practices currently used by six official open government data portals. Towards this end, we combine a top-down approach that studies interoperability conflicts in the literature with a bottom-up approach that studies the modelling practices of data portals. We define two types of LOSD schema-level conflicts, namely naming conflicts and structural conflicts. Naming conflicts result from using different URIs. Structural conflicts result from different practices of modelling the structure of data cubes. Only two out of the 19 conflicts are currently resolved and 11 can be resolved according to literature. Full article

Recent deep learning approaches have shown promising results for named entity recognition (NER). A reasonable assumption for training robust deep learning models is that a sufficient amount of high-quality annotated training data is available. However, in many real-world scenarios, labeled training data is scarcely present. In this paper we consider two use cases: generic entity extraction from financial and from biomedical documents. First, we have developed a character based model for NER in financial documents and a word and character based model with attention for NER in biomedical documents. Further, we have analyzed how transfer learning addresses the problem of limited training data in a target domain. We demonstrate through experiments that NER models trained on labeled data from a source domain can be used as base models and then be fine-tuned with few labeled data for recognition of different named entity classes in a target domain. We also witness an interest in language models to improve NER as a way of coping with limited labeled data. The current most successful language model is BERT. Because of its success in state-of-the-art models we integrate representations based on BERT in our biomedical NER model along with word and character information. The results are compared with a state-of-the-art model applied on a benchmarking biomedical corpus. Full article

Collecting speech data for a low-resource language is challenging when funding and resources are limited. This paper describes the process of designing, creating and using the Paldaruo Speech Corpus for developing speech technology for Welsh. Specifically, this paper focuses on the crowdsourcing of data using an app on smartphones and mobile devices, allowing speakers from across Wales to contribute. We discuss the development of reading prompts: isolated words and full sentences, as well as the metadata collected from contributors. We also provide background on the design of the Paldaruo App as well as the main uses for the corpus and its availability and licensing. The corpus was designed for the development of speech recognition for Welsh and has been used to create a number of other resources. These methods can be extended to other languages, and suggestions for other low-resource languages are discussed. Full article

Given its generality in applications and its high time-efficiency on big data-sets, in recent years, the technique of text filtering through pattern matching has been attracting increasing attention from the field of information retrieval and Natural language Processing (NLP) research communities at large. That being the case, however, it has yet to be seen how this technique and its algorithms, (e.g., Wu–Manber, which is also considered in this paper) can be applied and adopted properly and effectively to Uyghur, a low-resource language that is mostly spoken by the ethnic Uyghur group with a population of more than eleven-million in Xinjiang, China. We observe that technically, the challenge is mainly caused by two factors: (1) Vowel weakening and (2) mismatching in semantics between affixes and stems. Accordingly, in this paper, we propose Wu–Manber–Uy, a variant of an improvement to Wu–Manber, dedicated particularly for working on the Uyghur language. Wu–Manber–Uy implements a stem deformation-based pattern expansion strategy, specifically for reducing the mismatching of patterns caused by vowel weakening and spelling errors. A two-way strategy that applies invigilation and control on the change of lexical meaning of stems during word-building is also used in Wu–Manber–Uy. Extra consideration with respect to Word2vec and the dictionary are incorporated into the system for processing Uyghur. The experimental results we have obtained consistently demonstrate the high performance of Wu–Manber–Uy. Full article

This contribution provides a systematic literature review of Human Activity Recognition for Production and Logistics. An initial list of 1243 publications that complies with predefined Inclusion Criteria was surveyed by three reviewers. Fifty-two publications that comply with the Content Criteria were analysed regarding the observed activities, sensor attachment, utilised datasets, sensor technology and the applied methods of HAR. This review is focused on applications that use marker-based Motion Capturing or Inertial Measurement Units. The analysed methods can be deployed in industrial application of Production and Logistics or transferred from related domains into this field. The findings provide an overview of the specifications of state-of-the-art HAR approaches, statistical pattern recognition and deep architectures and they outline a future road map for further research from a practitioner’s perspective. Full article