Datasets Of Different Nature Research Articles

RNeuMark: A Riemannian EEG Analysis Framework for Neuromarketing

Neuromarketing exploits neuroimaging techniques so as to reinforce the predictive power of conventional marketing tools, like questionnaires and focus groups. Electroencephalography (EEG) is the most commonly encountered neuroimaging technique due to its non-invasiveness, low-cost, and its very recent embedding in wearable devices. The transcription of brainwave patterns to consumer attitude is supported by various signal descriptors, while the quest for profitable novel ways is still an open research question. Here, we suggest the use of sample covariance matrices as alternative descriptors, that encapsulate the coordinated neural activity from distinct brain areas, and the adoption of Riemannian geometry for their handling. We first establish the suitability of Riemannian approach for neuromarketing-related problems and then suggest a relevant decoding scheme for predicting consumers’ choices (e.g., willing to buy or not a specific product). Since the decision-making process involves the concurrent interaction of various cognitive processes and consequently of distinct brain rhythms, the proposed decoder takes the form of an ensemble classifier that builds upon a multi-view perspective, with each view dedicated to a specific frequency band. Adopting a standard machine learning procedure, and using a set of trials (training data) in conjunction with the associated behavior labels (“buy”/ “not buy”), we train a battery of classifiers accordingly. Each classifier is designed to operate in the space recovered from the inter-trial distances of SCMs and to cast a rhythm-depended decision that is eventually combined with the predictions of the rest ones. The demonstration and evaluation of the proposed approach are performed in 2 neuromarketing-related datasets of different nature. The first is employed to showcase the potential of the suggested descriptor, while the second to showcase the decoder’s superiority against popular alternatives in the field.

Deep Learning for Road Traffic Forecasting: Does it Make a Difference?

Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems, in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth their benefits and downsides. This paper focuses on critically analyzing the state of the art in what refers to the use of Deep Learning for this particular Intelligent Transportation Systems research area. To this end, we elaborate on the findings distilled from a review of publications from recent years, based on two taxonomic criteria. A posterior critical analysis is held to formulate questions and trigger a necessary debate about the issues of Deep Learning for traffic forecasting. The study is completed with a benchmark of diverse short-term traffic forecasting methods over traffic datasets of different nature, aimed to cover a wide spectrum of possible scenarios. Our experimentation reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date that should be addressed by the community in prospective studies. These insights reveal new challenges and research opportunities in road traffic forecasting, which are enumerated and discussed thoroughly, with the intention of inspiring and guiding future research efforts in this field.

Mixed methods on Instagram research: Methodological challenges in data analysis and visualization

In this article, we will present our insights on key methodological challenges emerged from the Selfiestories project, focused on selfies as personal narratives on Instagram. In this research, we approached the selfie practice in the context of user’s personal narratives (Georgakopoulou, 2016, From narrating the self to posting self(ies): A small stories approach to selfies. Open Linguistics 2(1): 300–317.) embedded in the everyday. We opted for a mixed methodology (Creswell and Creswell, 2017) resonating on the notion of remix (Markham, 2013, Remix cultures, remix methods: Reframing qualitative inquiry for social media contexts. In: Denzin N and Giardina M (eds) Global Dimensions of Qualitative Inquiry. pp. 63–81.), thus combining fieldwork and ethnographic techniques with quantitative data obtained through an Instagram data extractor. This approach proved to be challenging in the process of establishing a dialogue between data sets of different nature. At this stage, we considered visualization as a valuable technique for analysis and communication, particularly in those case studies where fieldwork and data extraction from Instagram were conducted simultaneously. Decisions made regarding visualization processes posed different challenges regarding the intermingling of qualitative and quantitative data and the layout of our results. After a contextualization of our research and methodology, we will analyze the challenges and limitations of visualizations in our research. Taking into account the time-based dimension of personal narratives in Instagram, emphasized in some of our case studies, such as events, we will document our own process in looking for the best possible ways to present a more balanced account of our synchronous qualitative and quantitative data. We will do so against the temporal background of the experience of the first day of the Primavera Sound 2016, where we conducted fieldwork while extracting data from Instagram. After carrying out different tests with alternative visualization tools and formats, we chose to work with timeline tools, particularly those who offered a narrative layout against the backdrop of experience time. In a research where time and synchrony play a pivotal role, we suggest that adding a temporal dimension in visualization could be a way of connecting both perspectives, thus allowing to present different sources and types of data together, while also expanding the role that storytelling can play in visualizing data.

Comparing spatial networks: A one-size-fits-all efficiency-driven approach.

Spatial networks are a powerful framework for studying a large variety of systems belonging to a broad diversity of contexts: from transportation to biology, from epidemiology to communications, and migrations, to cite a few. Spatial networks can be described in terms of their total cost (i.e., the total amount of resources needed for building or traveling their connections). Here, we address the issue of how to gauge and compare the quality of spatial network designs (i.e., efficiency vs. total cost) by proposing a two-step methodology. First, we assess the network's design by introducing a quality function based on the concept of network's efficiency. Second, we propose an algorithm to estimate computationally the upper bound of our quality function for a given network. Complementarily, we provide a universal expression to obtain an approximated upper bound to any spatial network, regardless of its size. Smaller differences between the upper bound and the empirical value correspond to better designs. Finally, we test the applicability of this analytic tool set on spatial network data-sets of different nature.

Spatial Resolution Enhancement Mapping of Hyperspectral Image via Pixel Filling Algorithm

The classification of hyperspectral data by means of per pixel classifiers forces each mixed pixel to map onto a single class, whereas sub-pixel classifiers are incapable of spatial arrangement of the land cover classes at its sub-pixel level. Super resolution mapping technique takes advantage of fractional abundance of each pixel and its surrounding pixels to make the classified image much finer spatial resolution. The pixel to be super resolved (PTS) is divided into equal number of rows and columns, according to pre-defined zoom factor. The spatial proximity of the pixel is also considered in mapping at the sub-pixel level of the hyperspectral data. Now, each sub-pixel of the PTS is modelled as linear combination of number of sub-pixels allotted to the neighbouring pixels with pre-defined weights, and here they are 8 and 17, which directly depend upon the spatial location or proximity of the sub-pixels of PTS and neighbouring pixels. Irrespective of the sizes of the classes, all classes are treated equal while filling the sub-pixels in that PTS, which preserves small classes or targets of the image. Experiments have been carried out on a synthetic data and two hyperspectral datasets of different nature. The overall accuracy of super resolution mapping for synthetic data comes to be 96.3% for the whole image, while the accuracy for super resolved of only mixed pixels comes to be 86.3%. Further, experiments on real hyperspectral datasets have been carried out, and the overall accuracy comes to be more than 95% for both the datasets.

Transductive non-linear semantic embedding for multi-class classification

This paper presents a method for semi-supervised multi-class classification based on matrix factorization. The method called semi-supervised online kernel matrix factorization (SS-OKMF) performs a semantic embedding by finding a non-linear mapping to a low-dimensional semantic space. An important characteristic of the SS-OKMF method is that the new low-dimensional semantic representation can be learned in a semi-supervised fashion. Therefore, the annotated instances can be used to maximize the discrimination between classes, but also, the non-annotated instances can be exploited to estimate the intrinsic manifold structure of the data. The non-linear modeling is based on kernel methods with a learning-in-a-budget strategy that allows keeping low memory requirements. This strategy, along with an online formulation based on stochastic gradient descent, reduces the computation time and keeps low computational requirements in large-scale problems. According to the experimental evaluation performed on several datasets of different nature (i.e. images, biosignals, and synthetic data), SS-OKMF, in comparison with several non-linear supervised, unsupervised and semi-supervised dimensionality reduction methods, presents a competitive performance in classification tasks under a transductive learning setup preserving a lower computational cost.

Energy Consumption in Compact Integer Vectors: A Study Case

In the field of algorithms and data structures analysis and design, most of the researchers focus only on the space/time trade-off, and little attention has been paid to energy consumption. Moreover, most of the efforts in the field of Green Computing have been devoted to hardware-related issues, being green software in its infancy. Optimizing the usage of computing resources, minimizing power consumption or increasing battery life are some of the goals of this field of research. As an attempt to address the most recent sustainability challenges, we must incorporate the energy consumption as a first-class constraint when designing new compact data structures. Thus, as a preliminary work to reach that goal, we first need to understand the factors that impact on the energy consumption and their relation with compression. In this work, we study the energy consumption required by several integer vector representations. We execute typical operations over datasets of different nature. We can see that, as commonly believed, energy consumption is highly related to the time required by the process, but not always. We analyze other parameters, such as number of instructions, number of CPU cycles, memory loads, among others.

Centrality Metrics in Dynamic Networks: A Comparison Study

For a long time, researchers have worked on defining different metrics able to characterize the importance of nodes in static networks. Recently, researchers have introduced extensions that consider the dynamics of networks. These extensions study the time-evolution of the importance of nodes, which is an important question that has yet received little attention in the context of temporal networks. They follow different approaches for evaluating a node's importance at a given time and the value of each approach remains difficult to assess. In order to study this question more in depth, we compare in this paper a method we recently introduced to three other existing methods. We use several datasets of different nature, and show and explain how these methods capture different notions of importance. We also show that in some cases it might be meaningless to try to identify nodes that are globally important. Finally, we highlight the role of inactive nodes, that still can be important as a relay for future communications.

Feature Level-Sets: Generalizing Iso-Surfaces to Multi-Variate Data.

Iso-surfaces or level-sets provide an effective and frequently used means for feature visualization. However, they are restricted to simple features for uni-variate data. The approach does not scale when moving to multi-variate data or when considering more complex feature definitions. In this paper, we introduce the concept of traits and feature level-sets, which can be understood as a generalization of level-sets as it includes iso-surfaces, and fiber surfaces as special cases. The concept is applicable to a large class of traits defined as subsets in attribute space, which can be arbitrary combinations of points, lines, surfaces and volumes. It is implemented into a system that provides an interface to define traits in an interactive way and multiple rendering options. We demonstrate the effectiveness of the approach using multi-variate data sets of different nature, including vector and tensor data, from different application domains.

Hybrid multicriteria fuzzy classification of network traffic patterns, anomalies, and protocols

Traffic classification in computer networks has very significant roles in network operation, management, and security. Examples include controlling the flow of information, allocating resources effectively, provisioning quality of service, detecting intrusions, and blocking malicious and unauthorized access. This problem has attracted a growing attention over years and a number of techniques have been proposed ranging from traditional port-based and payload inspection of TCP/IP packets to supervised, unsupervised, and semi-supervised machine learning paradigms. With the increasing complexity of network environments and support for emerging mobility services and applications, more robust and accurate techniques need to be investigated. In this paper, we propose a new supervised hybrid machine-learning approach for ubiquitous traffic classification based on multicriteria fuzzy decision trees with attribute selection. Moreover, our approach can handle well the imbalanced datasets and zero-day applications (i.e., those without previously known traffic patterns). Evaluating the proposed methodology on several benchmark real-world traffic datasets of different nature demonstrated its capability to effectively discriminate a variety of traffic patterns, anomalies, and protocols for unencrypted and encrypted traffic flows. Comparing with other methods, the performance of the proposed methodology showed remarkably better classification accuracy.

Exploring high-level features for detecting cyberpedophilia

In this paper, we suggest a list of high-level features and study their applicability in detection of cyberpedophiles. We used a corpus of chats downloaded from http://www.perverted-justice.com and two negative datasets of different nature: cybersex logs available online, and the NPS chat corpus. The classification results show that the NPS data and the pedophiles’ conversations can be accurately discriminated from each other with character n-grams, while in the more complicated case of cybersex logs there is need for high-level features to reach good accuracy levels. In this latter setting our results show that features that model behaviour and emotion significantly outperform the low-level ones, and achieve a 97% accuracy.

Architectural and Markovian factors of echo state networks

Echo State Networks (ESNs) constitute an emerging approach for efficiently modeling Recurrent Neural Networks (RNNs). In this paper we investigate some of the main aspects that can be accounted for the success and limitations of this class of models. In particular, we propose complementary classes of factors related to contractivity and architecture of reservoirs and we study their relative relevance. First, we show the existence of a class of tasks for which ESN performance is independent of the architectural design. The effect of the Markovian factor, characterizing a significant class within these cases, is shown by introducing instances of easy/hard tasks for ESNs featured by contractivity of reservoir dynamics. In the complementary cases, for which architectural design is effective, we investigate and decompose the aspects of network design that allow a larger reservoir to progressively improve the predictive performance. In particular, we introduce four key architectural factors: input variability, multiple time-scales dynamics, non-linear interactions among units and regression in an augmented feature space. To investigate the quantitative effects of the different architectural factors within this class of tasks successfully approached by ESNs, variants of the basic ESN model are proposed and tested on instances of datasets of different nature and difficulty. Experimental evidences confirm the role of the Markovian factor and show that all the identified key architectural factors have a major role in determining ESN performances.

Logic based methods for SNPs tagging and reconstruction

SNPs are positions of the DNA sequences where the differences among individuals are embedded. The knowledge of such SNPs is crucial for disease association studies, but even if the number of such positions is low (about 1% of the entire sequence), the cost to extract the complete information is actually very high. Recent studies have shown that DNA sequences are structured into blocks of positions, that are conserved during evolution, where there is strong correlation among values (alleles) of different loci. To reduce the cost of extracting SNPs information, the block structure of the DNA has suggested to limit the process to a subset of SNPs, the so-called Tag SNPs, that are able to maintain the most of the information contained in the whole sequence. In this paper, we apply a technique for feature selection based on integer programming to the problem of Tag SNP selection. Moreover, to test the quality of our approach, we consider also the problem of SNPs reconstruction, i.e. the problem of deriving unknown SNPs from the value of Tag SNPs and propose two reconstruction methods, one based on a majority vote and the other on a machine learning approach. We test our algorithm on two public data sets of different nature, providing results that are, when comparable, in line with the related literature. One of the interesting aspects of the proposed method is to be found in its capability to deal simultaneously with very large SNPs sets, and, in addition, to provide highly informative reconstruction rules in the form of logic formulas.

Exploitation of high‐density DInSAR data points of the Umbria‐Marche (Italy) 1997 seismic sequence for fault characteristics

High spatial resolution DInSAR data for the Umbria Marche 1997 seismic sequence are exploited by relaxing constraints derived from datasets of different nature, such as seismologically derived fault dimensions. DInSAR data are thus inverted for a realistic slip distribution over the faults, in terms of depth distribution and roughness, which allows us to relocate the main faults and to minimize the misfit between the vertical displacement pattern derived from DInSAR and model predictions. Our analysis reveals that slip affected not only the shallowest part of the fault system but also its deepest part, rupturing the whole seismogenic layer of the crust down to 10 km, reaching slip values up to 30 cm at the base of the seismogenic layer. Misfit is reduced by a factor of two with respect to previous analyses based on a smaller number of digitized fringe points.

Generalized bilinear models

Generalized bilinear models are presented for the statistical analysis of two-way arrays. These models combine bilinear models and generalized linear modeling, and yield a family of models that includes many existing models, as well as suggest other potentially useful ones. This approach both unifies and extends models for two-way arrays, including the ability to treat response and explanatory variables differently in the models, and the incorporation of external information about the variables directly into the analysis. A unifying framework for the generalized bilinear models is provided by considering four particular cases which have been proposed and used in the existing statistical literature. A three-step procedure is proposed to analyze data sets by generalized bilinear models. Two data sets of different nature are analyzed.