Search

This paper introduces a diagnostic model that effectively diagnoses in fourteen different stages, by fusing functional magnetic resonance imaging (fMRI) and structural MRI (sMRI) information. Georgios Theodoridis and Athanasios Tsadiras from the Aristotle University of Thessaloniki, Greece, have authored the seventh paper which is entitled "Applying machine learning techniques to predict and explain subscriber churn of an online drug information platform." Machine learning (ML) and more specifically deep learning (DL) algorithms are considered among the most paramount technologies of both artificial intelligence (AI) and 4 SP th sp industrial revolution. This paper provides an in-depth comparison of various machine learning (ML) techniques and advanced preprocessing methods, in an effort to successfully perform online subscriber churn prediction. [Extracted from the article]

The growing need to use online services has made it necessary to ensure protection against all kinds of cyber-threats. This research effort aims to tackle network security problems as follows: It introduces the hybrid intrusion detection system COREM2 that successfully detects nine cyber-attacks. Its architecture comprises of a two-dimensional convolutional neural network (2-D CNN), a recurrent neural network with long short-term memory layers and a multilayer perceptron. The COREM2 was successfully tested against the timely Kitsune Network Attack Dataset, achieving an overall accuracy of 98.64% and 98.92% in the training and testing phases, respectively. Since this is a multiclass classification effort, the "one-versus-all strategy" was employed to validate the introduced model, which has proved its ability to generalize. COREM2 outperforms other state-of-the-art approaches achieving overall accuracy above 98%, rare for field cyber-security intrusion. We strongly suggest that it can be safely used as a prototype for further research on network security enhancement. Furthermore, this research introduces a holistic approach for cyber intrusion detection, using the COREM2 in order to classify network traffic as benign or malicious. It captures network flow packets in the form of PCAP files (packet capture), and it stores them in.csv files and it evaluates them in order to perform classification in ten classes as provided by the Kitsune Dataset. If the malicious traffic exceeds a certain limit, the model notifies the user to take all necessary actions. The proposed method has an average processing power of 10,000 packets per 8 s. It potentially can be used in any device that has Internet access. [ABSTRACT FROM AUTHOR]

Data-driven methods are implemented using particularly complex scenarios that reflect in-depth perennial knowledge and research. Hence, the available intelligent algorithms are completely dependent on the quality of the available data. This is not possible for real-time applications, due to the nature of the data and the computational cost that is required. This work introduces an Automatic Differentiation Variational Inference (ADVI) Restricted Boltzmann Machine (RBM) to perform real-time anomaly detection of industrial infrastructure. Using the ADVI methodology, local variables are automatically transformed into real coordinate space. This is an innovative algorithm that optimizes its parameters with mathematical methods by choosing an approach that is a function of the transformed variables. The ADVI RBM approach proposed herein identifies anomalies without the need for prior training and without the need to find a detailed solution, thus making the whole task computationally feasible. [ABSTRACT FROM AUTHOR]

The fifth generation (5G) of telecommunications networks is currently commercially deployed. One of their core enabling technologies is cellular Massive Multiple-Input-Multiple-Output (M-MIMO) systems. However, future wireless networks are expected to serve a very large number of devices and the current MIMO networks are not scalable, highlighting the need for novel solutions. At this moment, Cell-free Massive MIMO (CF M-MIMO) technology seems to be the most promising idea in this direction. Despite their appealing characteristics, CF M-MIMO systems face their own challenges, such as power allocation and channel estimation. Deep Learning (DL) has been successfully employed to a wide range of problems in many different research areas, including wireless communications. In this paper, a review of the state-of-the-art DL methods applied to CF M-MIMO communications systems is provided. In addition, the basic characteristics of Cell-free networks are introduced, along with the presentation of the most commonly used DL models. Finally, future research directions are highlighted. [ABSTRACT FROM AUTHOR]

Graph signal processing has recently emerged as a field with applications across a broad spectrum of fields including brain connectivity networks, logistics and supply chains, social media, computational aesthetics, and transportation networks. In this paradigm, signal processing methodologies are applied to the adjacency matrix, seen as a two-dimensional signal. Fundamental operations of this type include graph sampling, the graph Laplace transform, and graph spectrum estimation. In this context, topology similarity metrics allow meaningful and efficient comparisons between pairs of graphs or along evolving graph sequences. In turn, such metrics can be the algorithmic cornerstone of graph clustering schemes. Major advantages of relying on existing signal processing kernels include parallelism, scalability, and numerical stability. This work presents a scheme for training a tensor stack network to estimate the topological correlation coefficient between two graph adjacency matrices compressed with the two-dimensional discrete cosine transform, augmenting thus the indirect decompression with knowledge stored in the network. The results from three benchmark graph sequences are encouraging in terms of mean square error and complexity especially for graph sequences. An additional key point is the independence of the proposed method from the underlying domain semantics. This is primarily achieved by focusing on higher-order structural graph patterns. [ABSTRACT FROM AUTHOR]

The analysis along with the modeling of passenger demand dynamic, which deem to have vital implications on the management and the operation within the entire aviation industry, are regarded to be an extreme challenge. However, air passenger demand introduces reliably complex non-linearity and non-stationarity. In this paper, we have tried to forecast aviation demand with the use of time series and deep learning techniques. We have developed air travel demand estimation and forecasting models, using classical Autoregressive Integrated Moving Average methods (ARIMA), Seasonal approaches (SARIMA) and Deep Learning Neural Networks (DLNN). Moreover, this research has performed a qualitative comparison of the aforementioned techniques aiming to serve as a guideline toward the choice of the optimal modeling approach. The experimental results have shown that the proposed approaches can provide significant assistance in forecasting air travel demand, by producing both accurate and robust results. Therefore, this approach can be utilized as a tool to be reliably employed for air passenger demand forecasting. [ABSTRACT FROM AUTHOR]

Time-series analysis and forecasting problems are generally considered as some of the most challenging and complicated problems in data mining. In this work, we propose a new complete framework for enhancing deep learning time-series models, which is based on a data preprocessing methodology. The proposed framework focuses on conducting a sequence of transformations on the original low-quality time-series data for generating high-quality time-series data, "suitable" for efficiently training and fitting a deep learning model. These transformations are performed in two successive stages: The first stage is based on the smoothing technique for the development of a new de-noised version of the original series in which every value contains dynamic knowledge of the all previous values. The second stage of transformations is performed on the smoothed series and it is based on differencing the series in order to be stationary and be considerably easier fitted and analyzed by a deep learning model. A number of experiments were performed utilizing time-series datasets from the cryptocurrency market, energy sector and financial stock market application domains on both regression and classification problems. The comprehensive numerical experiments and statistical analysis provide empirical evidence that the proposed framework considerably improves the forecasting performance of a deep learning model. [ABSTRACT FROM AUTHOR]

Ensemble learning constitutes one of the most fundamental and reliable strategies for building powerful and accurate predictive models, aiming to exploit the predictions of a number of multiple learners. In this paper, we propose two ensemble prediction models which exploit the classification performance of weight-constrained neural networks (WCNNs). The proposed models are based on Bagging and Boosting, which constitute two of the most popular strategies, to efficiently combine the predictions of WCNN classifiers. We conducted a series of experiments using a variety of benchmarks from UCI repository in order to evaluate the performance of the two proposed models against other state-of-the-art ensemble classifiers. The reported experimental results illustrate the prediction accuracy of the proposed models providing empirical evidence that the hybridization of ensemble learning and WCNNs can build efficient and powerful classification models. [ABSTRACT FROM AUTHOR]

The complexity of threats in the ever-changing environment of modern industry is constantly increasing. At the same time, traditional security systems fail to detect serious threats of increasing depth and duration. Therefore, alternative, intelligent solutions should be used to detect anomalies in the operating parameters of the infrastructures concerned, while ensuring the anonymity and confidentiality of industrial information. Blockchain is an encrypted, distributed archiving system designed to allow for the creation of real-time log files that are unequivocally linked. This ensures the security and transparency of transactions. This research presents, for the first time in the literature, an innovative Blockchain Security Architecture that aims to ensure network communication between traded Industrial Internet of Things devices, following the Industry 4.0 standard and based on Deep Learning Smart Contracts. The proposed smart contracts are implementing (via computer programming) a bilateral traffic control agreement to detect anomalies based on a trained Deep Autoencoder Neural Network. This architecture enables the creation of a secure distributed platform that can control and complete associated transactions in critical infrastructure networks, without the intervention of a single central authority. It is a novel approach that fuses artificial intelligence in the Blockchain, not as a supportive framework that enhances the capabilities of the network, but as an active structural element, indispensable and necessary for its completion. [ABSTRACT FROM AUTHOR]

Tensor clustering is a knowledge management technique which is well known as a major algorithmic and technological driver behind a broad applications spectrum. The latter ranges from multimodal social media analysis and geolocation processing to analytics tailored for large omic data. However, known exact tensor clustering problems when reduced to tensor factorization are provably NP hard. This is attributed in part to the volume of data contained in a tensor, proportional to the product of its dimensions, as well as to the increased interdependency between the tensor entries across its dimensions. One well studied way to circumvent this inherent difficulty is to resort to heuristics. This article presents an enhanced version of a genetic algorithm tailored for community discovery structure in tensors containing spatiosocial data, namely linguistic and geolocation data. The objective function as well as the chromosome fitness functions by design take into account elements of linguistic propagation models. The genetic operators of selection, crossover, and mutation as well as the newly added double mutation operator work directly on the community level. Moreover, various policies for maintaining gene variability across generations are studied in an extensive simulation powered by Google TensorFlow. As with its predecessor, the proposed genetic algorithm has been applied to a dataset consisting of a large number of Tweets and their associated geolocations from the Grand Duchy of Luxembourg, a historically and de facto trilingual country. The results are compared with those obtained from the original genetic algorithm and their differences are interpreted. [ABSTRACT FROM AUTHOR]

The offline evaluation of recommender systems is typically based on accuracy metrics such as the Mean Absolute Error and the Root Mean Squared Error for error rating prediction and Precision and Recall for measuring the quality of the top-N recommendations. However, it is difficult to reproduce the results since there are various libraries that can be used for running experiments and also within the same library there are many different settings that if not taken into consideration when replicating the results might vary. In this paper, we show that within the use of the same library an explanation-based approach can be used to assist in the reproducibility of experiments. Our proposed approach has been experimentally evaluated using a wide range of recommendation algorithms ranging from collaborative filtering to complicated fuzzy recommendation approaches that can solve the filter bubble problem, a real dataset, and the results show that it is both practical and effective. [ABSTRACT FROM AUTHOR]

Due to the boundless expansion of the Web in the last decade, the research community has paid significant attention to the problem of effective searching in the vast information available. In this paper, we introduce a novel framework for improving information retrieval results. Initially, relevant documents are organized in clusters utilizing several metrics combined with language modelling tools. In following, a produced ranked list of the documents is returned to the user for a specific query. This is implemented as the scores between the clusters and the query representations are extracted; next in line, the internal rankings of the documents, per cluster, using these scores as weighting factor, are combined. Our proposed methodology is based on the exploitation of the inter-documents similarities (lexical and/or semantics) after a sophisticated pre-processing step. Our experimental evaluation demonstrates that the proposed algorithm can efficiently improve the quality of the retrieved results. [ABSTRACT FROM AUTHOR]

The backbone of the economy, security and sustainability of a state is inseparably linked to the security of its critical infrastructure. Critical infrastructures define goods, systems or subsystems that are essential to maintain the vital functions of society, health, physical protection, security plus economic and social well-being of citizens. The digital security of critical infrastructures is a very important priority for the well-being of every country, especially nowadays, because of the direct threats dictated by the current international conjuncture and due to the emerging interactions or interconnections developed between the National Critical Infrastructures, internationally. The aim of this research is the development and testing of an Anomaly Detection intelligent algorithm that has the advantage to run very fast with a small portion of the available data and to perform equally well with the existing approaches. Such a system must be characterized by high efficiency and very fast execution. Thus, we present the Gryphon advanced intelligence system. Gryphon is a Semi-Supervised Unary Anomaly Detection System for big industrial data which is employing an evolving Spiking Neural Network (eSNN) One-Class Classifier (eSNN-OCC). This machine learning algorithm corresponds to a model capable of detecting very fast and efficiently, divergent behaviors and abnormalities associated with cyberattacks, which are known as Advanced Persistent Threat (APT). The training process is performed on data related to the normal function of a critical infrastructure. [ABSTRACT FROM AUTHOR]

Forest fires are one of the most serious natural disasters for the countries of the Mediterranean basin and especially for Greece. Studying the climate change effect on the maximization of the problem is a constant objective of the scientific community. This research initially proposes an innovative hybrid version of the statistical Chi-Square test that employs Soft Computing methods. More specifically it introduces the Fuzzy Chi Square Independence test that fuzzifies p values using proper Risk Linguistics, based on Fuzzy Membership functions. In the second stage, it proposes a new Hybrid approach that models the evolution of burned areas in Greece. First it analyzes the parameters and determines the way they affect the problem, by constructing Fuzzy cognitive maps. The system projects into the future and forecasts the evolution of the problem through the years till 2100, based on the variance of average monthly temperature and average rain height (due to climate change) for the months May-October based on various climate models. Historical data for the period 1984-2004 were used to test the system for the areas of Chania and Ilia. [ABSTRACT FROM AUTHOR]

Mining hidden knowledge from available datasets is an extremely time-consuming and demanding process, especially in our era with the vast volume of high-complexity data. Additionally, validation of results requires the adoption of appropriate multifactor criteria, exhaustive testing and advanced error measurement techniques. This paper proposes a novel Hybrid Fuzzy Semi-Supervised Forecasting Framework. It combines fuzzy logic, semi-supervised clustering and semi-supervised classification in order to model Big Data sets in a faster, simpler and more essential manner. Its advantages are clearly shown and discussed in the paper. It uses as few pre-classified data as possible while providing a simple method of safe process validation. This innovative approach is applied herein to effectively model the air quality of Athens city. More specifically, it manages to forecast extreme air pollutants’ values and to explore the parameters that affect their concentration. Also it builds a correlation between pollution and general climatic conditions. Overall, it correlates the built model with the malfunctions caused to the city life by this serious environmental problem. [ABSTRACT FROM AUTHOR]

It is a fact that more and more users are adopting the online digital payment systems via mobile devices for everyday use. This attracts powerful gangs of cybercriminals, which use sophisticated and highly intelligent types of malware to broaden their attacks. Malicious software is designed to run quietly and to remain unsolved for a long time. It manages to take full control of the device and to communicate (via the Tor network) with its Command & Control servers of fast-flux botnets' networks to which it belongs. This is done to achieve the malicious objectives of the botmasters. This paper proposes the development of the computational intelligence anti-malware framework (CIantiMF) which is innovative, ultra-fast and has low requirements. It runs under the android operating system (OS) and its reasoning is based on advanced computational intelligence approaches. The selection of the android OS was based on its popularity and on the number of critical applications available for it. The CIantiMF uses two advanced technology extensions for the ART java virtual machine which is the default in the recent versions of android. The first is the smart anti-malware extension, which can recognize whether the java classes of an android application are benign or malicious using an optimized multi-layer perceptron. The optimization is done by the employment of the biogeography-based optimizer algorithm. The second is the Tor online traffic identification extension, which is capable of achieving malware localization, Tor traffic identification and botnets prohibition, with the use of the online sequential extreme learning machine algorithm. [ABSTRACT FROM AUTHOR]

The need to protect the environment and biodiversity and to safeguard public health require the development of timely and reliable methods for the identification of particularly dangerous invasive species, before they become regulators of ecosystems. These species appear to be morphologically similar, despite their strong biological differences, something that complicates their identification process. Additionally, the localization of the broader space of dispersion and the development of invasive species are considered to be of critical importance in the effort to take proper management measures. The aim of this research is to create an advanced computational intelligence system for the automatic recognition, of invasive or another unknown species. The identification is performed based on the analysis of environmental DNA by employing machine learning methods. More specifically, this research effort proposes a hybrid bio-inspired computational intelligence detection approach. It employs extreme learning machines combined with an evolving Izhikevich spiking neuron model for the automated identification of the invasive fish species ' Lagocephalus sceleratus' extremely dangerous for human health. [ABSTRACT FROM AUTHOR]

Several machine learning models were used to predict interior spruce wood density using data from open-pollinated progeny testing trial. The data set consists of growth (height and diameter which were used to estimate individual tree volume) and wood quality (wood density determined by X-ray densitometry, resistance to drilling, and acoustic velocity) attributes for a total of 1146 trees growing on comparable sites in interior British Columbia. Various machine learning models were developed for estimating wood density. The multilayer feed-forward artificial neural networks and gene expression programming provided the highest predictability as compared to the other methods tested, including those based on classical multiple regression which was considered as the comparisons benchmark. The utilization of machine learning models as a credible method for estimating wood density using available growth data as an indirect method for determining trees wood density is expected to become increasingly helpful to forest managers and tree breeders. [ABSTRACT FROM AUTHOR]

The analysis of air quality and the continuous monitoring of air pollution levels are important subjects of the environmental science and research. This problem actually has real impact in the human health and quality of life. The determination of the conditions which favor high concentration of pollutants and most of all the timely forecast of such cases is really crucial, as it facilitates the imposition of specific protection and prevention actions by civil protection. This research paper discusses an innovative threefold intelligent hybrid system of combined machine learning algorithms HISYCOL (henceforth). First, it deals with the correlation of the conditions under which high pollutants concentrations emerge. On the other hand, it proposes and presents an ensemble system using combination of machine learning algorithms capable of forecasting the values of air pollutants. What is really important and gives this modeling effort a hybrid nature is the fact that it uses clustered datasets. Moreover, this approach improves the accuracy of existing forecasting models by using unsupervised machine learning to cluster the data vectors and trace hidden knowledge. Finally, it employs a Mamdani fuzzy inference system for each air pollutant in order to forecast even more effectively its concentrations. [ABSTRACT FROM AUTHOR]

In natural alluvial channels, the determination of the flow resistance constitutes a problem with additional complexity compared to rigid bed channels, due to the bed morphology transformations and the alterations of the flow properties caused by sediment transport. While there have been steps towards understanding the processes that contribute to flow resistance in an alluvial channel, a robust quantitative model with wide applicability remains elusive. Machine learning offers the ability to exploit available data and generate equations that accurately describe the problem by taking implicitly into account the contributing mechanisms that are difficult to be modeled. In this paper, four machine learning techniques are employed for the mean flow velocity prediction, separately for sand-bed and gravel-bed rivers, namely artificial neural networks, adaptive-network-based fuzzy inference system, symbolic regression based on genetic programming, and support vector regression. The derived models are robust and their results are superior to those of some widely used flow resistance formulae, which compute the mean flow velocity from similar independent hydraulic variables. [ABSTRACT FROM AUTHOR]