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.

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.

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.

© 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.

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

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.

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.

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.