Search

Blockchain, the underlying technology of Bitcoin, refers to the public ledger used in a distributed network. Because blockchain does not rely on a central authority, peers have to agree on the state of the ledger among themselves, i.e., they have to reach a consensus on the state of the transactions. The way nodes reach that consensus has gained incredible attention in the literature. Bitcoin uses the Proof-of-Work (PoW) mechanism, as did Ethereum at first. The latter decided to move from PoW to Proof-of-Stake (PoS) because of the high energy consumption required by PoW. To date, many other consensus protocols have been proposed to address the limitations of the seminal ones. In this paper, we inform researchers and practitioners about the current state of consensus protocols research. The aim is to provide an analysis of the research introducing new consensus protocols in order to enable a more unified treatment. To that end, we review 28 new consensus protocols and we propose a four-category classification framework: Origin, Design, Performance and Security. We demonstrate the applicability of the framework by classifying the 28 protocols. Many surveys have already been proposed in the literature and some of them will be discussed later in the paper. Yet, we believe that this work is relevant and important for two reasons. Firstly, blockchain being a fast evolving topic, new consensus protocols emerge regularly and improvements are also put forward on a regular basis. Hence, this work aims at reflecting the latest state-of-the-art in terms of consensus protocols. Secondly, we aim to propose a comprehensive classification framework, integrating knowledge from multiple works in the literature, as well as introducing classification dimensions that have not been proposed before. This work demonstrates that multiple consensus have been proposed in a short period of time, and highlights the differences between these protocols. Furthermore, it is suggested that researchers and practitioners who aim to propose consensus protocols in the future should pay attention to all the dimensions presented in the classification framework.

In this paper we apply a series of Machine Learning models to a recently published unique dataset on the mortality of COVID19 patients. We use a dataset consisting of blood samples of 375 patients admitted to a hospital in the region of Wuhan, China. There are 201 patients who survived hospitalisation and 174 patients who died whilst in hospital. The focus of the paper is not only on seeing which Machine Learning model is able to obtain the absolute highest accuracy but more on the interpretation of what the Machine Learning models provides. We find that age, days in hospital, Lymphocyte and Neutrophils are important and robust predictors when predicting a patients mortality. Furthermore, the algorithms we use allows us to observe the marginal impact of each variable on a case-by-case patient level, which might help practicioneers to easily detect anomalous patterns. This paper analyses the global and local interpretation of the Machine Learning models on patients with COVID19.

This paper introduces a DSS to support coordination in disaster relief distribution.An MIP and an agent-based simulation with optimization procedures are presented.Road closures and off-road as well as unmanned aerial vehicles are considered.Computational experiments are based on flood scenarios of two Austrian regions.Results highlight potentials of coordinated disaster relief distribution. This paper presents a simulation and optimization based decision-support system (DSS) to facilitate disaster relief coordination between private and relief organizations. The DSS simulates disasters and plans shipments of relief goods via transfer points to demand points in the affected area. This enables decision-makers to analyze the last-mile distribution of goods by scheduling and routing trucks, off-road as well as unmanned aerial vehicles. Roads which are closed or opened during a disaster are considered allowing a dynamic adaptation to real world conditions and a comprehensive analysis over a rolling time-horizon. A mixed-integer problem formulation, an agent-based simulation, a heuristic-based scheduling and routing procedure as well as a Tabu Search metaheuristic are applied to analyze the given decision problem. Coordination between private and relief organization shows to be especially beneficial if time-losses resulting from closed roads are high and substantial unexpected demand occurs. Furthermore, results highlight the importance of selecting suitable transfer points and the potential of simulation and optimization based DSSs to improve disaster relief distribution.

This paper presents a model of maritime safety management and its subareas. Furthermore, the paper links the safety management to the maritime traffic safety indicated by accident involvement, incidents reported by Vessel Traffic Service and the results from Port State Control inspections. Bayesian belief networks are applied as the modeling technique and the model parameters are based on expert elicitation and learning from historical data. The results from this new application domain of a Bayesian network based expert system suggest that, although several its subareas are functioning properly, the current status of the safety management on vessels navigating in the Finnish waters has room for improvement; the probability of zero poor safety management subareas is only 0.13. Furthermore, according to the model a good IT system for the safety management is the strongest safety-management related signal of an adequate overall safety management level. If no deficiencies have been discovered during a Port State Control inspection, the adequacy of the safety management is almost twice as probable as without knowledge on the inspection history. The resulted model could be applied to performing several safety management related queries and it thus provides support for maritime safety related decision making.

The types of police inquiries performed these days are incredibly diverse. Often data processing architectures are not suited to cope with this diversity since most of the case data is still stored as unstructured text. In this paper Formal Concept Analysis (FCA) is showcased for its exploratory data analysis capabilities in discovering domestic violence intelligence from a dataset of unstructured police reports filed with the regional police Amsterdam-Amstelland in the Netherlands. From this data analysis it is shown that FCA can be a powerful instrument to operationally improve policing practice. For one, it is shown that the definition of domestic violence employed by the police is not always as clear as it should be, making it hard to use it effectively for classification purposes. In addition, this paper presents newly discovered knowledge for automatically classifying certain cases as either domestic or non-domestic violence is. Moreover, it provides practical advice for detecting incorrect classifications performed by police officers. A final aspect to be discussed is the problems encountered because of the sometimes unstructured way of working of police officers. The added value of this paper resides in both using FCA for exploratory data analysis, as well as with the application of FCA for the detection of domestic violence. ispartof: Expert Systems with Applications vol:38 issue:4 pages:3116-3130 status: published

Business process models are becoming available in large numbers due to their widespread use in many industrial applications such as enterprise and quality engineering projects. On the one hand, this raises a challenge as to their proper management: how can it be ensured that the proper process model is always available to the interested stakeholder? On the other hand, the richness of a large set of process models also offers opportunities, for example with respect to the re-use of existing model parts for new models. This paper describes the functionality and architecture of an advanced process model repository, named APROMORE. This tool brings together a rich set of features for the analysis, management and usage of large sets of process models, drawing from state-of-the art research in the field of process modeling. A prototype of the platform is presented in this paper, demonstrating its feasibility, as well as an outlook on the further development of APROMORE.

In this paper, a new methodology is suggested for determining the optimal mix of transport alternatives to minimize total logistics costs when goods are shipped from a supplier to a receiver. The total logistics costs comprise order costs, transportation costs and inventory costs. It is assumed that only a limited number of transport alternatives are capable of shipping the goods from the supplier to the receiver. Moreover, if a certain transport alternative is selected to ship the goods, then its entire capacity is used. These assumptions imply that the number of possible order quantities is finite and that the problem can be formulated as a combinatorial optimization problem. In a first step to explore the use of metaheuristics for optimization problems like these, an Evolutionary Algorithm is developed in this paper. The heuristic is tested on real-life problem instances.

In this paper, we present a method to use advance demand information (ADI), taking the form of request for quotation (RFQ) data, in B2B sales forecasting. We apply supervised machine learning and Natural Language Processing techniques to analyze and learn from RFQs. We apply and test our approach in a case study at a large after-sales service and maintenance provider. After evaluation we found that our approach identifies ∼ 70% of actual sales (recall) with a precision rate of ∼ 50%, which represents a performance improvement of slightly more than a factor 2.5 over the current labor-intensive manual process at the service and maintenance provider. Our research contributes to literature by giving step-by-step guidance on incorporating artificial intelligence in B2B sales forecasting and revealing potential pitfalls along the way. Furthermore, our research gives an indication of the performance improvement that can be expected when adopting supervised machine learning into B2B sales forecasting.

© 2021 Elsevier LtdThis paper investigates an unrelated parallel machine scheduling problem with a restrictive common due date. The objective is to minimize the total sum of earliness/tardiness costs. Using some properties of the problem such as V-Shaped property, optimizing start times of machines, and no idle time between successive jobs, we propose effective construction-based heuristics and local search algorithms for the problem. Using variants of the shortest and longest processing time dispatching rules and job assignment patterns, we propose four different construction algorithms to have a balanced number of jobs or the workload per machine. We construct four deterministic and one stochastic solution improvement heuristic approaches using swap and reinsertion local search mechanisms. In the proposed reinsertion-based local search mechanism, the V-shaped property of each machine is used effectively to determine the proper positions in which the removed job is inserted. After both swap and reinsertion operators, a V-Shaped property preserving mechanism takes place to preserve the V-Shaped property of each machine. We also use an LP formulation in our proposed solution approaches to determine the optimum start times of machines for a given schedule. We compare our proposed heuristics against four metaheuristics, namely simulated annealing, genetic algorithm, artificial bee colony algorithm, and fast ruin and recreate algorithm. A simple lower bound for the optimal objective function value is proposed to show the efficiency of our proposed heuristics. We test our heuristics also in an identical machine environment. The experimental study reveals that the construction and the improvement heuristic methods including swap and reinsertion outperform metaheuristics and other heuristics in solution quality for both identical and unrelated machine environments.

The motivation for the development of the thyroid system has been to help clinicians manage the problem of information overload by supporting the utilization and interpretation of laboratory data. The output from the system is a report that includes a proposal for diagnosis and/or recommendations for extra tests. The diagnosis is proposed on the axis hypothyroidism-euthyroidism-hyperthyroidism.The motivation to evaluate this prototype system is to approach the specifications of the next generation system for the test interpretation in the domain of clinical chemistry. The methodology applied in this paper on the evaluation relates the life-cycle model of the development to the phases of evaluation. According to this methodology evaluation should be done through the whole development cycle. The life-cycle view to evaluation comprises a series of iterative phases during the design and development process and it emphasises the importance of feedback from expert collaborators and potential end-users. The evaluation study described in this paper describes development of a prototype system for thyroid disorders. Of special interest are the validity of the system in application and the acceptability of the system by the users.

The aim of this paper is the generation of a time-series based statistical data-driven procedure in order to track an outbreak. At first are used univariate time series models in order to predict the evolution of the reported cases. Moreover, are considered combinations of the models in order to provide more accurate and robust results. Additionally, statistical probability distributions are considered in order to generate future scenarios. Final step is the build and use of an epidemiological model (tSIR) and the calculation of an epidemiological ratio (R0) for estimating the termination of the outbreak. The time series models include Exponential Smoothing and ARIMA approaches from the classical models, also Feed-Forward Artificial Neural Networks and Multivariate Adaptive Regression Splines from the machine learning toolbox. Combinations include simple mean, Newbolt-Granger and Bates-Granger approaches. Finally, the tSIR model and the R0 ratio are used for estimating the spread and the reversion of the pandemic. The suggested procedure is used to track the COVID-19 epidemic in Greece. This epidemic has appeared in China in December 2019 and has been widespread since then to all over the world. Greece is the center of this empirical study as is considered an early successful paradigm of resistance against the virus.

In the last years social networks have emerged as a critical mean for information spreading bringing along several advantages. At the same time, unverified and instrumentally relevant information statements in circulation, named as rumours, are becoming a potential threat to the society. For this reason, although the identification in social microblogs of which topic is a rumour has been studied in several works, there is the need to detect if a post is either a rumor or not. In this paper we cope with this last challenge presenting a novel rumour detection system that leverages on newly designed features, including influence potential and network characteristics measures. We tested our approach on a real dataset composed of health-related posts collected from Twitter microblog. We observe promising results, as the system is able to correctly detect about 90% of rumours, with acceptable levels of precision.

Nowadays, the range of cloud services offered by cloud providers varies sharply and poses a challenge for cloud consumers aiming for the most cost-effective and compliant solutions, especially when operating highly scalable microservice architectures. A remedy can be provided by a cloud brokerage intelligent mechanism selecting cloud services across multiple clouds on behalf of consumers by considering individual goals and requirements. In this paper, we present the Cloud Service Purchasing Problem (CSPP) which aims to minimize costs while incorporating specific consumer and application task requirements. To solve this problem, we propose a mixed-integer programming model and two large neighborhood search approaches. Using well-defined problem instances incorporating data from real cloud providers, we conduct several computational experiments to evaluate the performance of the proposed algorithms. They exhibit a competitive performance providing solutions for all scenarios within short computational times. Finally, the significance of this problem and decision support approaches is analyzed by comparing usage patterns with respect to different nowadays cloud providers and offered virtual machine types for various scenarios.

This paper proposes an interpretable non-model sharing collaborative data analysis method as one of the federated learning systems, which is an emerging technology to analyze distributed data. Analyzing distributed data is essential in many applications such as medical, financial, and manufacturing data analyses due to privacy, and confidentiality concerns. In addition, interpretability of the obtained model has an important role for practical applications of the federated learning systems. By centralizing intermediate representations, which are individually constructed in each party, the proposed method obtains an interpretable model, achieving a collaborative analysis without revealing the individual data and learning model distributed over local parties. Numerical experiments indicate that the proposed method achieves better recognition performance for artificial and real-world problems than individual analysis., 16 pages, 3 figures, 3 tables

© 2020 Elsevier Ltd Time-series classification has been addressed by a plethora of machine-learning techniques, including neural networks, support vector machines, Bayesian approaches, and others. It is an accepted fact, however, that the plain vanilla 1-nearest neighbor (1NN) classifier, combined with an elastic distance measure such as Dynamic Time Warping (DTW), is competitive and often superior to more complex classification methods, including the majority-voting k-nearest neighbor (kNN) classifier. With this paper we continue our investigation of the kNN classifier on time-series data and the impact of various classic distance-based vote weighting schemes by considering constrained versions of four common elastic distance measures: DTW, Longest Common Subsequence (LCS), Edit Distance with Real Penalty (ERP), and Edit Distance on Real sequence (EDR). By performing experiments on the entire UCR Time Series Classification Archive we show that weighted kNN is able to consistently outperform 1NN. Furthermore, we provide recommendations for the choices of the constraint width parameter r, neighborhood size k, and weighting scheme, for each mentioned elastic distance measure.

In benthic macroinvertebrate biomonitoring systems, the target is to determine the status of ecosystems based on several biological indices. To increase cost-efficiency, computer-based taxa identification for image data has recently been developed. Taxa identification errors can, however, have strong effects on the indices and thus on the determination of the ecological status. In order to shift the biomonitoring process towards automated expert systems, we need a clear understanding on the bias caused by automation. In this paper, we examine eleven classification methods in the case of macroinvertebrate image data and show how their classification errors propagate into different biological indices. We evaluate 14 richness, diversity, dominance and similarity indices commonly used in biomonitoring. Besides the error rate of the classification method, we discuss the potential effect of different types of identification errors. Finally, we provide recommendations on indices that are least affected by the automatic identification errors and could be used in automated biomonitoring. We thank the Academy of Finland (projects 288584 (Kiranyaz), 295854 (Iosidis), 289364 (Gabbouj), 289076 (rje, Krkkinen) and 289104 (Meissner)) and the Ellen and Artturi Nyyssnen foundation for the grant of rje. The authors would like to thank Marko Vikstedt for the preparation of the monitoring data and Tuomas Turpeinen for the image data. We kindly thank Antti Penttinen for fruitful discussions and support. Scopus

The wide spread of fake news has caused huge losses to both governments and the public. Many existing works on fake news detection utilized spreading information like propagators profiles and the propagation structure. However, such methods face the difficulty of data collection and cannot detect fake news at the early stage. An alternative approach is to detect fake news solely based on its content. Early content-based methods rely on manually designed linguistic features. Such shallow features are domain-dependent, and cannot easily be generalized to cross-domain data. Recently, many natural language processing tasks resort to deep learning methods to learn word, sentence, and document representations. In this paper, we propose a novel graph-based neural network model named SemSeq4FD for early fake news detection based on enhanced text representations. In SemSeq4FD, we model the global pair-wise semantic relations between sentences as a complete graph, and learn the global sentence representations via a graph convolutional network with self-attention mechanism. Considering the importance of local context in conveying the sentence meaning, we employ a 1D convolutional network to learn the local sentence representations. The two representations are combined to form the enhanced sentence representations. Then a LSTM-based network is used to model the sequence of enhanced sentence representations, yielding the final document representation for fake news detection. Experiments conducted on four real-world datasets in English and Chinese, including cross-source and cross-domain datasets, demonstrate that our model can outperform the state-of-the-art methods., Highlights • An enhanced text representation model for content-based early fake news detection. • Global semantic relations between sentences modeled with graph convolution network. • Local sentence representation extracted by applying 1D convolution on local context. • Document representation obtained by incorporating the sentence order through LSTM. • Generalization ability verified on cross-source and cross-domain datasets.

We propose an algorithm for automatic product taxonomy mapping in e-commerce.The algorithm uses word sense disambiguation techniques to handle heterogeneity.Our algorithm copes with composite categories in product category names.We compute path-similarities using lexical relatedness and structural information.Using real-world data, we show that we improve existing state-of-the-art methods. Over the last few years, we have experienced a steady growth in e-commerce. This growth introduces many problems for services that want to aggregate product information and offerings. One of the problems that aggregation services face is the matching of product categories from different Web shops. This paper proposes an algorithm to perform this task automatically, making it possible to aggregate product information from multiple Web sites, in order to deploy it for search, comparison, or recommender systems applications. The algorithm uses word sense disambiguation techniques to address varying denominations between different taxonomies. Path similarity is assessed between source and candidate target categories, based on lexical relatedness and structural information. The main focus of the proposed solution is to improve the disambiguation procedure in comparison to an existing state-of-the-art approach, while coping with product taxonomy-specific characteristics, like composite categories, and re-examining lexical similarity and similarity aggregation in this context. The performance evaluation based on data from three real-world Web shops demonstrates that the proposed algorithm improves the benchmarked approach by 62% on average F 1 -measure.

This paper deals with the topic of learning from unlabeled or noisy-labeled data in the context of a classification problem. In the classification problem the outcome yields one of a discrete set of values thus, assumptions on them could be established to obtain the most likely prediction model at the training stage . In this paper, a novel case-based model selection method is proposed, which combines hypothesis testing from a discrete set of expected outcomes and feature extraction within a cross-validated classification stage. This wrapper-type procedure acts on fully-observable variables under hypothesis-testing and improves the classification accuracy on the test set, or keeps its performance at least at the level of the statistical classifier. The model selection strategy in the cross validation loop allows building an ensemble classifier that could improve the performance of any expert and intelligence system, particularly on small sample-size datasets. Experiments were carried out on several databases yielding a clear improvement on the baseline, i.e., SPECT dataset A c c = 86.35 ± 1.51 , with S e n = 91.10 ± 2.77 , and S p e = 81.11 ± 1.61 . In addition, the CV error estimate for the classifier under our approach was found to be an almost unbiased estimate (as the baseline approach) of the true error that the classifier would incur on independent data.

A state-of the-art survey of FAHP applications is carried out: 190 papers are reviewedPapers are classified based on their: Application area, Theme, Year, Country, etc.Review is summarized in tabular formats/charts to help readers extract quick info.Results and Findings are made available through an online (free) testbedThe testbed makes fuzzy pairwise comparison matrices (from all papers) available As a practical popular methodology for dealing with fuzziness and uncertainty in Multiple Criteria Decision-Making (MCDM), Fuzzy AHP (FAHP) has been applied to a wide range of applications. As of the time of writing there is no state of the art survey of FAHP, we carry out a literature review of 190 application papers (i.e., applied research papers), published between 2004 and 2016, by classifying them on the basis of the area of application, the identified theme, the year of publication, and so forth. The identified themes and application areas have been chosen based upon the latest state-of-the-art survey of AHP conducted by Vaidya, O., & Kumar, S. (2006). Analytic hierarchy process: An overview of applications. European Journal of operational research, 169(1), 1-29.. To help readers extract quick and meaningful information, the reviewed papers are summarized in various tabular formats and charts. Unlike previous literature surveys, results and findings are made available through an online (and free) testbed, which can serve as a ready reference for those who wish to apply, modify or extend FAHP in various applications areas. This online testbed makes also available one or more fuzzy pairwise comparison matrices (FPCMs) from all the reviewed papers (255źmatrices in total).In terms of results and findings, this survey shows that: (i) FAHP is used primarily in the Manufacturing, Industry and Government sectors; (ii) Asia is the torchbearer in this field, where FAHP is mostly applied in the theme areas of Selection and Evaluation; (iii) a significant amount of research papers (43% of the reviewed literature) combine FAHP with other tools, particularly with TOPSIS, QFD and ANP (AHP's variant); (iv) Chang's extent analysis method, which is used for FPCMs' weight derivation in FAHP, is still the most popular method in spite of a number of criticisms in recent years (considered in 57% of the reviewed literature).

The ongoing rapid growth of diversity of data and their wide use to solve different complex tasks requires more sophisticated techniques of knowledge management and automated reasoning. Recent research efforts resulted in a significant number of semantic reference systems enriched with vocabularies, thesauri, terminologies, and ontologies. The extensive use of ontologies in the mainstream computer science has spread to many other branches of knowledge. These branches are included in a new approach to building modern intelligent systems, reusing and sharing pieces of declarative knowledge. In the meanwhile, a lot of effort has been made to produce standard ontologies for medicine and biology. This paper brings an overview and presentation of the state of the art in terminologies, ontologies and important resources/systems and tools for industry and academia in medicine and biology. It could be useful for researchers involved in multidisciplinary and interdisciplinary research areas and projects that include medicine, biology, and information technology.

To propose a flexible knowledge representation.To propose a new similarity measure.To use taxonomies in a conceptualization mechanism.To test some proposed mechanisms with a case-based reasoning for waste treatment. In Case Based Reasoning the representation of a case and the similarity measures are two difficult steps in the conception of a system. Often, these steps are developed to resolve one kind of problem. However, in some of them such as recovery treatment processes generation, it is necessary for the system to be able to modify and adapt the representation of a case and the similarity measures with respect of the context and also the kind of solutions proposed. In this paper, authors introduce a new method to represent cases with a flexibility based on a structure in a connectionist model. This flexibility is needed due to the complexity of cases, the number of possible options and to ensure the durability of the system. In a second main contribution, authors introduce a method for the selection of source cases using abstraction, conceptualisation and inference mechanisms. Finally, authors test their system in a CBR developed on SWI-Prolog with different problems. The CBR is applied to find new recovery processes and try to estimate the new upgraded product generated.

International audience; The increasing importance of ontologies has resulted in the development of a large number of ontologies in both coordinated and non-coordinated efforts. The number and complexity of such ontologies make hard to ontology and tool developers to select which ontologies to use and reuse. So far, there are no mechanism for making such decisions in an informed manner. Consequently, methods for evaluating ontology quality are required. OQuaRE is a method for ontology quality evaluation which adapts the SQuaRE standard for software product quality to ontologies. OQuaRE has been applied to identify the strengths and weaknesses of different ontologies but, so far, this framework has not been evaluated itself. Therefore, in this paper we present the evaluation of OQuaRE, performed by an international panel of experts in ontology engineering. The results include the positive and negative aspects of the current version of OQuaRE, the completeness and utility of the quality metrics included in OQuaRE and the comparison between the results of the manual evaluations done by the experts and the ones obtained by a software implementation of OQuaRE.

This paper proposes a semantic Web service discovery framework for finding semantic Web services by making use of natural language processing techniques. The framework allows searching through a set of semantic Web services in order to find a match with a user query consisting of keywords. By specifying the search goal using keywords, end-users do not need to have knowledge about semantic languages, which makes it easy to express the desired semantic Web services. For matching keywords with semantic Web service descriptions given in WSMO, techniques like part-of-speech tagging, lemmatization, and word sense disambiguation are used. After determining the senses of relevant words gathered from Web service descriptions and the user query, a matching process takes place. The performance evaluation shows that the three proposed matching algorithms are able to effectively perform matching and approximate matching.

In this paper we present a general framework for time-aware decision support systems. The framework uses the state-of-the-art tOWL language for the representation of temporal knowledge and enables temporal reasoning over the information that is represented in a knowledge base. Our approach uses state-of- the-art Semantic Web technology for handling temporal data. Through such an approach, the designer of a system can focus on the application intelligence rather than enforcing/checking data related restrictions manually. Also, there is an increased support for reuse of temporal reasoning tools across applications. We illustrate the applicability of our framework by building a market recommendations aggregation system. This system automatically collects market recommendations from online sources and, based on the past performance of the analysts that issued a recommendation, generates an aggregated recommendation in the form of a buy, hold, or sell advice. We illustrate the flexibility of our proposed system by implementing multiple methods for the aggregation of market recommendations.

An important paradigm in decision-making models is utility-maximization where most models do not include actors' motives. Fuzzy set theory on the other hand offers a method to simulate human decision-making. However, the literature describing expert-driven fuzzy logic models, rarely gives precise details on the methodology (to be) used. To fill the gap, this paper describes a methodology of 10 steps to model individual actor's drivers, motives, hereby taking into account the ecological, social and economic context. Testing the methodology on the composition of mixed farming systems in the Mekong Delta, Vietnam, showed that manual model development is not a waterfall approach but requires feedback loops, except for model implementation. Using feed-back loops, the proposed 10 step method allowed to include human drivers and motives other than utility-maximization and to maintain a degree of transparency hard to achieve when using automated procedures.

While most models of location decisions of firms are based on the principle of utility maximizing behavior, the present study assumes that location decisions are just part of business cycle models, in which location is considered along other business decisions. The business model results in a series of location requirements and these are matched against location characteristics. Given this theoretical perspective, the modeling challenge then becomes how to find the match between firm types and the set of location characteristics using observations of the spatial distribution of firms. In this paper, several Bayesian classifier networks are compared in terms of their performance, using a large data set collected for the Netherlands. Results demonstrate that by taking relationships between predictor variables into account the Bayesian classifiers can improve prediction accuracy compared to commonly used decision tree. From a substantive point of view, our results indicate that different sets of urban characteristics and accessibility requirements are relevant to different office types as reflected in the spatial distribution of these office firms.

The aim of this paper is to describe a fuzzy expert system for load balancing in a symmetric multiprocessor environment. Load balancing algorithms are used to share the load of the system fairly among the processors. The developed load balancing algorithm use on demand based approach instead of the periodic load balancing in order to get fast and fair load balancing with minimal computational overhead. It uses the number of threads per processor and total load of the system as inputs. The method is compared to the periodic and another developed on demand based algorithms. The results show that during the load balancing the periodic algorithm causes temporary idle periods in the processors whereas the developed on demand-based algorithms respond faster to the fluctuating load level, stabilize the load more equally among the processors and increase the performance of the system. The results also proof that the fuzzy load balancer achieves the best load balance among the processors as well as the fastest response time.

Work distribution, as an integral part of business process management, is more widely acknowledged by its’ importance for process-aware information systems. Although there are emerging a wide variety of mechanisms to support work distribution, they less concern performance considerations and cannot balance work distribution requirements and process performance within the change of process conditions. This paper presents an adaptive work distribution mechanism based on reinforcement learning. It considers process performance goals, and then can learn, reason suitable work distribution policies within the change of process conditions. Also, learning-based simulation experiment for addressing work distribution problems of business process management is introduced. The experiment results show that our mechanism outperforms reasonable heuristic or hand-coded approaches to satisfy process performance goals and is feasible to improve current state of business process management.

One of the deficiencies of mutual information is its poor capacity to measure association of words with unsymmetrical co-occurrence, which has large amounts for multi-word expression in texts. Moreover, threshold setting, which is decisive for success of practical implementation of mutual information for multi-word extraction, brings about many parameters to be predefined manually in the process of extracting multiword expressions with different number of individual words. In this paper, we propose a new method as EMICO (Enhanced Mutual Information and Collocation Optimization) to extract substantival multiword expression from text. Specifically, enhanced mutual information is proposed to measure the association of words and collocation optimization is proposed to automatically determine the number of individual words contained in a multiword expression when the multiword expression occurs in a candidate set. Our experiments showed that EMICO significantly improves the performance of substantival multiword expression extraction in comparison with a classic extraction method based on mutual information.

To support the efficient appraisal of and selection from a list of generic business process improvement principles, this paper proposes a strategy for the implementation of business process redesign (BPR). Its backbone is formed by the analytic hierarchy process (AHP) multicriteria method and our earlier research into the popularity and impact of a set of redesign ''best practices''. Using AHP, we derive a classification of most suitable directions for a particular process to be redesigned. Criteria such as the popularity, the impact, the goals and the risks of BPR implementation are taken into account. A case study is included to demonstrate the method's feasibility and effectiveness.

Adaptive consensus seeking in group decision making.Mutual influence modeling.Taking into account human attitude.Multi-criteria problem using bipolarity concept.Consensus processes with or not individual changes. This paper addresses the collaborative group decision making problems considering a consensus processes to achieve a common legitimate solution. The proposed resolution model is based on individual bipolar assessment. Each decision maker evaluates alternatives through selectability and rejectability measures which respectively represent the positive and negative aspects of alternatives considering objectives achievement. The impact of human behavior (influence, individualism, fear, caution, etc.) on decisional capacity has been taken into account. The influence degrees exerted mutually by decision makers are modeled through concordance and discordance measures. The individualistic nature of decision makers has been taken into account from the individualism degree. In order to achieve a common solution(s), models of consensus building are proposed based on the satisficing game theory formalism for collective decision problems. An application example is given to illustrate the proposed concepts.

Academics and practitioners have a common interest in the continuing development of methods and computer applications that support or perform knowledge-intensive engineering tasks. Operations management dysfunctions and lost production time are problems of enormous magnitude that impact the performance and quality of industrial systems as well as their cost of production. Association rule mining is a data mining technique used to find out useful and invaluable information from huge databases. This work develops a better conceptual base for improving the application of association rule mining methods to extract knowledge on operations and information management. The emphasis of the paper is on the improvement of the operations processes. The application example details an industrial experiment in which association rule mining is used to analyze the manufacturing process of a fully integrated provider of drilling products. The study reports some new interesting results with data mining and knowledge discovery techniques applied to a drill production process. Experiment’s results on real-life data sets show that the proposed approach is useful in finding effective knowledge associated to dysfunctions causes.

This paper addresses the issues of machine learning in distributed knowledge systems, which will consist of distributed software agents with problem solving, communication and learning functions. To develop such systems, we must analyze the roles of problem-solving and communication capabilities among knowledge systems. To facilitate the analyses, we propose a computational model: LPC. The model consists of a set of agents with (a) a knowledge base for learned concepts, (b) a knowledge base for problem solving, (c) prolog-based inference mechanisms and (d) a set of beliefs on the reliability of the other agents. Each agent can improve its own problem-solving capabilities by deductive learning from the given problems, by memory-based learning from communications between the agents and by reinforcement learning from the reliability of communications between the other agents. An experimental system of the model has been implemented in Prolog language on a Window-based personal computer. Intensive experiments have been carried out to examine the feasibility of the machine learning mechanisms of agents for problem-solving and communication capabilities. The experimental results have shown that the multiagent system improves the performance of the whole system in problem solving, when each agent has a higher learning ability or when an agent with a very high ability for problem solving joins the organization to cooperate with the other agents in problem solving. These results suggest that the proposed model is useful in analyzing the learning mechanisms applicable to distributed knowledge systems.

Personnel selection process is aimed at choosing the best candidate to fill the defined vacancy in a company. It determines the input quality of personnel and thus plays an important role in human resource management. Given the uncertain, ambiguous, and vague nature of personnel selection process, it requires the application of multi-criteria decision making (MCDM) methods for robust recruitment. This paper hence is aimed at extending the fuzzy MULTIMOORA for linguistic reasoning under group decision making. The fuzzy MULTIMOORA was further modified in this study. The fuzzy MULTIMOORA for group decision making (MULTIMOORAFG) enables to aggregate subjective assessments of the decision-makers and thus offer an opportunity to perform more robust personnel selection procedures. A personnel selection problem illustrated the group decision-making procedure according to MULTIMOORAFG: the enterprise has formed an executive committee consisting of four decision-makers to choose the best candidate from another four participants to fill the vacancy. The committee has decided to consider eight qualitative attributes expressed in linguistic variables. The numerical example exhibited possibilities for improvement of human resources management as well as any other business decision area by applying MULTIMOORAFG.

Research highlights? Start-ups are crucial in the modern economy as they provide dynamism and growth. ? We identify configurations of initial resource bundles, strategy and environment that lead to superior performance in start-ups. ? We rely on data mining for the analysis because it accounts for the premises of configurational theory. ? The results confirm the existence of multivariate ideal configurations and equifinality. Start-ups are crucial in the modern economy as they provide dynamism and growth. Research on the performance of new ventures increasingly investigates initial resources as determinants of success. Initial resources are said to be important because they imprint the firm at start-up, limit its strategic choices, and continue to impact its performance in the long run. The purpose of this paper is to identify configurations of initial resource bundles, strategy and environment that lead to superior performance in start-ups. To date, interdependencies between resources on the one hand and between resources, strategy and environment on the other hand have been neglected in empirical research. We rely on data mining for the analysis because it accounts for premises of configurational theory, including reversed causality, intradimensional interactions, multidimensional dependencies, and equifinality. We apply advanced data mining techniques, in the form of rule extraction from non-linear support vector machines, to induce accurate and comprehensible configurations of resource bundles, strategy and environment. We base our analysis on an extensive survey among 218 Flemish start-ups. Our experiments indicate the good performance of rule extraction technique ALBA. Finally, for comprehensibility, intuitiveness and implementation reasons, the tree is transformed into a decision table.

Vehicle routing problems are at the heart of most decision support systems for real-life distribution problems. In vehicle routing problem a set of routes must be determined at lowest total cost for a number of resources (i.e. fleet of vehicles) located at one or several points (e.g. depots, warehouses) in order to efficiently service a number of demand or supply points. In this paper an efficient evolution strategies algorithm is developed for both capacitated vehicle routing problem and for vehicle routing problem with time window constraints. The algorithm is based on a new multi-parametric mutation procedure that is applied within the 1 + 1 evolution strategies algorithm. Computational testing on six real-life problems and 195 benchmark problems demonstrate that the suggested algorithm is efficient and highly competitive, improving or matching the current best-known solution in 42% of the test cases.

The paper utilizes Port State Control inspection data for discovering interactions between the numbers of various types of deficiencies found on ships and between the deficiencies and ship's involvement in maritime traffic accidents and incidents. Bayesian network models for describing the dependencies of the inspection results, ship age, type, flag, accident involvement, and incidents reported by the Vessel Traffic Service are learned from the Finnish Port State Control data from 2009-2011, 2004-2010 Baltic Sea accident statistics and the reported Gulf of Finland Vessel Traffic Service incidents within 2004-2008. Two alternative Bayesian network algorithms are applied to the model construction. Further, additional models including a hidden variable which represents the complete system and its safety features and which links the accident and incident involvement and Port State Control findings are presented. Based on model-data fit comparisons and 10-fold cross-validation, a constraint-based learning algorithm NPC mainly outperforms the score-based algorithm repeated hill-climbing with random restarts. For the highest scoring models, mutual information and influence of evidence analyses are conducted in order to analyze which network variables and variable states are the most influential ones for determining the accident involvement. The analyses suggest that knowledge on ship type, the Port State Control inspection type and the number of structural conditions related deficiencies are among the ones providing the most information regarding accident involvement and the true state of the hidden system safety variable.

Social networks have become an essential meeting point for millions of individuals willing to publish and consume huge quantities of heterogeneous information. Some studies have shown that the data published in these platforms may contain sensitive personal information and that external entities can gather and exploit this knowledge for their own benefit. Even though some methods to preserve the privacy of social networks users have been proposed, they generally apply rigid access control measures to the protected content and, even worse, they do not enable the users to understand which contents are sensitive. Last but not least, most of them require the collaboration of social network operators or they fail to provide a practical solution capable of working with well-known and already deployed social platforms. In this paper, we propose a new scheme that addresses all these issues. The new system is envisaged as an independent piece of software that does not depend on the social network in use and that can be transparently applied to most existing ones. According to a set of privacy requirements intuitively defined by the users of a social network, the proposed scheme is able to: (i) automatically detect sensitive data in users' publications; (ii) construct sanitized versions of such data; and (iii) provide privacy-preserving transparent access to sensitive contents by disclosing more or less information to readers according to their credentials toward the owner of the publications. We also study the applicability of the proposed system in general and illustrate its behavior in two case studies., Comment: The content of this version is compliant with arXiv's license agreement

A divide-and-conquer method classifying sentence types before sentiment analysis.Classifying sentence types by the number of opinion targets a sentence contain.A data-driven approach automatically extract features from input sentences. Different types of sentences express sentiment in very different ways. Traditional sentence-level sentiment classification research focuses on one-technique-fits-all solution or only centers on one special type of sentences. In this paper, we propose a divide-and-conquer approach which first classifies sentences into different types, then performs sentiment analysis separately on sentences from each type. Specifically, we find that sentences tend to be more complex if they contain more sentiment targets. Thus, we propose to first apply a neural network based sequence model to classify opinionated sentences into three types according to the number of targets appeared in a sentence. Each group of sentences is then fed into a one-dimensional convolutional neural network separately for sentiment classification. Our approach has been evaluated on four sentiment classification datasets and compared with a wide range of baselines. Experimental results show that: (1) sentence type classification can improve the performance of sentence-level sentiment analysis; (2) the proposed approach achieves state-of-the-art results on several benchmarking datasets.

A Knowledge Acquisition learning algorithm is proposed for troubleshooting in LTE.A sensitivity analysis is performed on the proposed algorithm.The algorithm is tested with a live network scenario.The performance has been compared with a Bayesian Network based algorithm. The recent developments in cellular networks, along with the increase in services, users and the demand of high quality have raised the Operational Expenditure (OPEX). Self-Organizing Networks (SON) are the solution to reduce these costs. Within SON, self-healing is the functionality that aims to automatically solve problems in the radio access network, at the same time reducing the downtime and the impact on the user experience. Self-healing comprises four main functions: fault detection, root cause analysis, fault compensation and recovery. To perform the root cause analysis (also known as diagnosis), Knowledge-Based Systems (KBS) are commonly used, such as fuzzy logic. In this paper, a novel method for extracting the Knowledge Base for a KBS from solved troubleshooting cases is proposed. This method is based on data mining techniques as opposed to the manual techniques currently used. The data mining problem of extracting knowledge out of LTE troubleshooting information can be considered a Big Data problem. Therefore, the proposed method has been designed so it can be easily scaled up to process a large volume of data with relatively low resources, as opposed to other existing algorithms. Tests show the feasibility and good results obtained by the diagnosis system created by the proposed methodology in LTE networks.

Research highlights? We employ Machine Learning techniques in species' potential distribution modelling. ? The distribution of 35 species from Latin America was modelled by classifiers. ? The best performance in potential distribution modeling was achieved by random trees. Species' potential distribution modelling consists of building a representation of the fundamental ecological requirements of a species from biotic and abiotic conditions where the species is known to occur. Such models can be valuable tools to understand the biogeography of species and to support the prediction of its presence/absence considering a particular environment scenario. This paper investigates the use of different supervised machine learning techniques to model the potential distribution of 35 plant species from Latin America. Each technique was able to extract a different representation of the relations between the environmental conditions and the distribution profile of the species. The experimental results highlight the good performance of random trees classifiers, indicating this particular technique as a promising candidate for modelling species' potential distribution.

Lenders, such as banks andcredit card companies, use credit scoring models to evaluate the potential risk posed by lending money to customers, and therefore to mitigate losses due to bad credit. Theprofitabilityof the banks thus highly depends on the models used to decide on the customer’s loans. State-of-the-art credit scoring models are based onmachine learningand statistical methods. One of the major problems of this field is that lenders often deal with imbalanced datasets that usually contain many paid loans but very few not paid ones (calleddefaults). Recently, dynamic selection methods combined withensemble methodsandpreprocessing techniqueshave been evaluated to improveclassification modelsin imbalanced datasets presenting advantages over the staticmachine learning methods. In a dynamic selection technique, samples in the neighborhood of each query sample are used to compute the local competence of eachbase classifier. Then, the technique selects only competentclassifiersto predict the query sample. In this paper, we evaluate the suitability of dynamic selection techniques for credit scoring problem, and we present Reduced Minority k-Nearest Neighbors (RMkNN), an approach that enhances state of the art in defining the local region of dynamic selection techniques for imbalanced credit scoring datasets. This proposed technique has a superior prediction performance in imbalanced credit scoring datasets compared to state of the art. Furthermore, RMkNN does not need any preprocessing or sampling method to generate the dynamic selection dataset (called DSEL). Additionally, we observe an equivalence between dynamic selection and static selection classification. We conduct a comprehensive evaluation of the proposed technique against state-of-the-art competitors on six real-world public datasets and one private one. Experiments show that RMkNN improves the classification performance of the evaluated datasets regarding AUC, balanced accuracy, H-measure, G-mean, F-measure, and Recall.

Explainability of artificial intelligence methods has become a crucial issue, especially in the most regulated fields, such as health and finance. In this paper, we provide a global explainable AI method which is based on Lorenz decompositions, thus extending previous contributions based on variance decompositions. This allows the resulting Shapley-Lorenz decomposition to be more generally applicable, and provides a unifying variable importance criterion that combines predictive accuracy with explainability, using a normalised and easy to interpret metric. The proposed decomposition is illustrated within the context of a real financial problem: the prediction of bitcoin prices.

In this paper, we propose a piecewise linear decision tree and its generalized form, namely the (G)PWL-DT, which introduces piecewise linearity and overcomes the discontinuity of the existing piecewise constant decision trees (PWC-DT). The proposed (G)PWL-DT inherits the basic topology and interpretability of decision trees by recursively partitioning the domain into subregions, which are represented by leaf nodes. Rather than the indicator function, the (G)PWL-DT employs rectifier linear units (ReLU) to interpret domain partitions, where the nested ReLUs are combined to formulate the corresponding PWL decision rules. Due to the piecewise linearity of each leaf node, additional boundaries among linear areas are obtained to approach greater flexibility than the existing PWC-DT under the same tree structure, where the continuity can also be guaranteed. Then, an optimization algorithm is constructed analogously based on the second-order approximation. The proposed (G)PWL-DT can be flexibly applied as a novel decision tree in different tree learning methods and it can also be regarded as a simple extension of ReLUs to the framework of tree learning. Numerical experiments verify the effectiveness of the proposed (G)PWL-DT and its potential as an alternative of the existing PWC-DT to approach better performance even with more concise structures.

Natural Language Processing (NLP) is the sub-field of Artificial Intelligence that represents and analyses human language automatically. NLP has been employed in many applications, such as information retrieval, information processing and automated answer ranking. Semantic analysis focuses on understanding the meaning of text. Among other proposed approaches, Latent Semantic Analysis (LSA) is a widely used corpus-based approach that evaluates similarity of text based on the semantic relations among words. LSA has been applied successfully in diverse language systems for calculating the semantic similarity of texts. LSA ignores the structure of sentences, i.e., it suffers from a syntactic blindness problem. LSA fails to distinguish between sentences that contain semantically similar words but have opposite meanings. Disregarding sentence structure, LSA cannot differentiate between a sentence and a list of keywords. If the list and the sentence contain similar words, comparing them using LSA would lead to a high similarity score. In this paper, we propose xLSA, an extension of LSA that focuses on the syntactic structure of sentences to overcome the syntactic blindness problem of the original LSA approach. xLSA was tested on sentence pairs that contain similar words but have significantly different meaning. Our results showed that xLSA alleviates the syntactic blindness problem, providing more realistic semantic similarity scores.

Fire disaster throughout the globe causes social, environmental, and economical damage, making its early detection and instant reporting essential for saving human lives and properties. Smoke detection plays a key role in early fire detection but majority of the existing methods are limited to either indoor or outdoor surveillance environments, with poor performance for hazy scenarios. In this paper, we present a Convolutional Neural Network (CNN)-based smoke detection and segmentation framework for both clear and hazy environments. Unlike existing methods, we employ an efficient CNN architecture, termed EfficientNet, for smoke detection with better accuracy. We also segment the smoke regions using DeepLabv3+, which is supported by effective encoders and decoders along with a pixel-wise classifier for optimum localization. Our smoke detection results evince a noticeable gain up to 3% in accuracy and a decrease of 0.46% in False Alarm Rate (FAR), while segmentation reports a significant increase of 2% and 1% in global accuracy and mean Intersection over Union (IoU) scores, respectively. This makes our method a best fit for smoke detection and segmentation in real-world surveillance settings.