Search

The production of vast amounts of data has increased the necessity of applying Machine Learning (ML) and Pattern Recognition (PR) methods that could perform accurate predictive performance without demanding much human effort for collecting and preparing the necessary data. Keeping in mind that annotating instances is one of the most time-consuming procedures during the learning phase of supervised approaches, the role of Semi-supervised Learning (SSL) schemes, which exploit both labeled and unlabeled data, is totally upgraded considering especially the real-word scenarios. The flexibility that is offered through such schemes about combining various learners for mining useful information through unlabeled instances allows the production of several variants of these schemes. Thus, the construction of generic approaches that could achieve robust learning behavior over problems that stem from different scientific fields is the target of current research. Our contribution through this work is the proposal of a Multi-scheme Semi-supervised regression approach (MSSRA) that examines some well-defined conditions about the outputs of each contained learner and provides its decisions to a meta-level learner to produce the final predictions. The results over twenty-five well-known datasets prove the better generalization behavior of the proposed algorithm against the supervised version of the meta-level learner and two state-of-the-art semi-supervised regression (SSR) algorithms.

Although low circulating levels of the vitamin A metabolite, all-trans retinoic acid (ATRA), are associated with increased risk of cardiovascular events and all-cause mortality, few studies have addressed whether cardiac retinoid levels are altered in the failing heart. Here, we showed that proteomic analyses of human and guinea pig heart failure (HF) were consistent with a decline in resident cardiac ATRA. Quantitation of the retinoids in ventricular myocardium by mass spectrometry revealed 32% and 39% ATRA decreases in guinea pig HF and in patients with idiopathic dilated cardiomyopathy (IDCM), respectively, despite ample reserves of cardiac vitamin A. ATRA (2 mg/kg/d) was sufficient to mitigate cardiac remodeling and prevent functional decline in guinea pig HF. Although cardiac ATRA declined in guinea pig HF and human IDCM, levels of certain retinoid metabolic enzymes diverged. Specifically, high expression of the ATRA-catabolizing enzyme, CYP26A1, in human IDCM could dampen prospects for an ATRA-based therapy. Pertinently, a pan-CYP26 inhibitor, talarozole, blunted the impact of phenylephrine on ATRA decline and hypertrophy in neonatal rat ventricular myocytes. Taken together, we submit that low cardiac ATRA attenuates the expression of critical ATRA-dependent gene programs in HF and that strategies to normalize ATRA metabolism, like CYP26 inhibition, may have therapeutic potential.

Applying data mining methods in the educational field has gained a lot of attention among scientists over the last years. Educational Data Mining forms an ever-developing research area aiming to unveil the hidden knowledge in educational data and improve students’ learning behavior and outcomes. To this end, a plethora of data mining methods have already been implemented in various educational settings solving a variety of tasks, among which the prediction of students’ academic performance as well. Decision trees have proven to be a quite effective method for both classification and regression problems showing a number of considerable advantages, such as efficiency, simplicity, flexibility and interpretability. Moreover, configuration of parameter values has often a material impact on building optimal trees in terms of accuracy and/or size. In this context, the main objective of our study is to yield a highly accurate and interpretable classification tree for the early prognosis of students at risk of failing in a university course. Thereby, effective intervention and support actions could be initiated to motivate students and enhance their performance. The experimental results demonstrate that the induction of the C4.5 decision tree classifier through an evolutionary algorithm, such as the Speed -constrained Multi-objective Particle Swarm Optimization algorithm, yields more accurate and easier to construe trees.

Semi-Supervised Learning (SSL) is an ever-growing research area offering a powerful set of methods, either single or multi-view, for exploiting both labeled and unlabeled instances in the most effective manner. Self-training is a representative SSL algorithm which has been efficiently implemented for solving several classification problems in a wide range of scientific fields. Moreover, self-training has served as the base for the development of several self-labeled methods. In addition, gradient boosting is an advanced machine learning technique, a boosting algorithm for both classification and regression problems, which produces a predictive model in the form of decision trees. In this context, the principal objective of this paper is to put forward an improved self-training algorithm for classification tasks utilizing the efficacy of eXtreme Gradient Boosting (XGBoost) trees in a self-labeled scheme in order to build a highly accurate and robust classification model. A number of experiments on benchmark datasets were executed demonstrating the superiority of the proposed method over representative semi-supervised methods, as statistically verified by the Friedman non-parametric test.

The most important asset of semi-supervised learning (SSL) methods is the use of available unlabeled data combined with an enough smaller set of labeled examples, so as to increase the classification accuracy compared with the default procedure of supervised methods, in which during the training only the labeled data are used. The encapsulation of classifier ensembles that produce different models through training process into semi-supervised schemes seems to be a promising strategy for enhanced learning ability. In this work, a Self-trained Rotation Forest (Self-RotF) algorithm and a variant of this (Weighted-Self-RotF) are presented. We performed an in depth comparison with other well-known semi- supervised classification methods on standard benchmark datasets and after having tested their performance with statistical tests, we finally reached to the point that the presented technique had better accuracy in most cases.

Semi-supervised algorithms are well-known for their ability to combine both supervised and unsupervised strategies for optimizing their learning ability under the assumption that only a few examples together with their full feature set are given. In such cases, the use of weak learners as base classifiers is usually preferred, since the iterative behavior of semi-supervised schemes require the building of new temporal models during each new iteration. Locally weighted naive Bayes classifier is such a classifier that encompasses the power of NB and k-NN algorithms. In this work, we have implemented a self-labeled weighted variant of local learner which uses NB as the base classifier of self-training scheme. We performed an in depth comparison with other well-known semi-supervised classification methods on standard benchmark datasets and we reached to the conclusion that the presented technique had better accuracy in most cases.

Plenty of Machine Learning (ML) approaches have been applied all these years over a great variety of tasks, leading to several kind of algorithms that face efficiently specific problems. However, their inability to generalize well enough over data that stem from more generic sources or other specialized occasions that are not connected with their initial field of interest, still remains an open issue. Thus, the interest of data scientists has been shifted towards ensemble learners, which try to leverage the predictive behavior of the contained algorithms, offering improved learning performance and robustness over wide spectrum of posed implications. Thus, an ensemble semi-supervised regressor that operates under the presence of a few examples is presented, covering the applications under which shortage of labeled data is usually met, offering at the same time well enough predictive behavior without spending much computational time, since the fast enough algorithm of M5 plays a crucial role.

The most important asset of semisupervised classification methods is the use of available unlabeled data combined with a clearly smaller set of labeled examples, so as to increase the classification accuracy compared with the default procedure of supervised methods, which on the other hand use only the labeled data during the training phase. Both the absence of automated mechanisms that produce labeled data and the high cost of needed human effort for completing the procedure of labelization in several scientific domains rise the need for semisupervised methods which counterbalance this phenomenon. In this work, a self-trained Logistic Model Trees (LMT) algorithm is presented, which combines the characteristics of Logistic Trees under the scenario of poor available labeled data. We performed an in depth comparison with other well-known semisupervised classification methods on standard benchmark datasets and we finally reached to the point that the presented technique had better accuracy in most cases.

Objective Magnetic resonance imaging (MRI) is the primary imaging technique for evaluation of the brain tumor progression before and after radiotherapy or surgery. The purpose of the current study is to exploit conventional MR modalities in order to identify and segment brain images with neoplasms. Methods Four conventional MR sequences, namely, T1-weighted, gadolinium-enhanced T1-weighted, T2-weighted and fluid attenuation inversion recovery, are combined with machine learning techniques to extract global and local information of brain tissues and model the healthy and neoplastic imaging profiles. Healthy tissue clustering, outlier detection and geometric and spatial constraints are applied to perform a first segmentation which is further improved by a modified multiparametric Random Walker segmentation method. The proposed framework is applied on clinical data from 57 brain tumor patients (acquired by different scanners and acquisition parameters) and on 25 synthetic MR images with tumors. Assessment is performed against expert-defined tissue masks and is based on sensitivity analysis and Dice coefficient. Results The results demonstrate that the proposed multiparametric framework differentiates neoplastic tissues with accuracy similar to most current approaches while it achieves lower computational cost and higher degree of automation. Conclusion This study might provide a decision-support tool for neoplastic tissue segmentation, which can assist in treatment planning for tumor resection or focused radiotherapy.

Brill's Companion to the Reception of Sophocles offers a comprehensive account of the reception of Sophocles’ plays over the centuries, across cultures and within a range of different fields, such as literature, intellectual history, visual arts, music, dance, stage and cinema.

This paper discusses our experience with designing and implementing a new Introduction to Computing course that aims both to introduce students to programming and at the same time to cover key concepts of Computer Science using a hands-on experiential approach. The re-design of the course has put more emphasis on using Python as a tool for studying computer science. It was found that the students enjoyed this approach and responded positively to the challenge. Examples are given on how concepts of binary arithmetic, computer architecture, operating systems, networking have been introduced through Python coding examples and exercises, while the project work introduced the students to the challenges of software development.

The use of acronyms is common in several document categories. With acronyms we avoid the repetitive use of long cumbersome titles and simplify some very wordy and verbose texts. In formal types of texts (e.g. in academic writing), two approaches are used to properly define acronyms within a text. For longer stand-alone works, like a textbook or a thesis, a list of definitions and acronyms used throughout the text is sometimes included near the beginning of the work (e.g. after the table of contents). In shorter texts [e.g. request for comments (RFC), medical, legislation texts], a more direct method of defining acronyms is adopted: acronyms are usually defined at the first point of use in the text with a parenthetical reference after the full title. Unfortunately, not all writers comply with the aforementioned approaches. It is very common for a writer to use unidentified acronyms presupposing that all readers share a common knowledge field (usually the thematic domain of the text) that contains the acronyms’ meanings. But often, this is partially true (or totally false) and the interpretation of some acronyms becomes ambiguous or impossible. In such cases, disambiguation methods can be implemented to support readers (Pustejovsky et al. , 2001; Joshi et al. , 2006; Sumita and Sugaya, 2006). In particular, search engines can help at the identification process regarding acronym definitions, for example, http://www.asas.gr/ (accessed February 2013). However, for all these tools to function properly, they need a knowledge base of acronyms along with their definitions, which is not always available, at least not in every specific topic and not in every language. In this article, we are concerned with legal texts in Modern Greek. According to the Hellenic Organization for Standardization S.A. (http://www.elot.gr, accessed February 2013), there is no standardization on how to create …

Recent advances in pharmacogenomics technologies allow bold steps to be taken towards personalized medicine, more accurate health planning, and personalized drug development. In this framework, systems pharmacology network-based approaches offer an appealing way for integrating multi-omics data and set the basis for defining systems-level drug response biomarkers. On the road to individualized tamoxifen treatment in estrogen receptor-positive breast cancer patients, we examine the dynamics of the attendant pharmacological response mechanisms. By means of an "integromics" network approach, we assessed the tamoxifen effect through the way the high-order organization of interactome (i.e., the modules) is perturbed. To accomplish that, first we integrated the time series transcriptome data with the human protein interaction data, and second, an efficient module-detecting algorithm was applied onto the composite graphs. Our findings show that tamoxifen induces severe modular transformations on specific areas of the interactome. Our modular biomarkers in response to tamoxifen attest to the immunomodulatory role of tamoxifen, and further reveal that it deregulates cell cycle and apoptosis pathways, while coordinating the proteasome and basal transcription factors. To the best of our knowledge, this is the first report that informs the fields of personalized medicine and clinical pharmacology about the actual dynamic interactome response to tamoxifen administration.

Ambiguity is one of the most significant problems in Natural Language Processing. This difficulty may not be apparent to native speakers because of their natural ability at resolving it using contextual information and common sense knowledge. In contrast, current computer applications are still lacking the ability to disambiguate complex texts efficiently. The most common type of ambiguity is lexical ambiguity, and this is noticed even in highly inflectional languages such as Greek. In the present article, all the patterns of predictable lexical ambiguity in Modern Greek Language are registered, verified and quanti- fied as occurred in the Neurolingo computational lexicon, after a study of morpho-syntactic characteristics that differentiate the ambiguous words.

EEG techniques have been widely used for mental fatigue monitoring, which is an important factor for driving safety. In this work, we performed an experiment involving one hour driving simulation. Based on EEG recordings, we created brain functional networks in alpha power band with three different methods, partial directed coherence (PDC), direct transfer function (DTF) and phase lag index (PLI). Then, we performed feature selection and classification between alertness and fatigue states, using the functional connectivity as features. High accuracy (84.7%) was achieved, with 22 discriminative connections from PDC network. The selected features revealed alterations of the functional network due to mental fatigue and specifically reduction of information flow among areas. Finally, a feature ranking is provided, which can lead to electrode minimization for real-time fatigue monitoring applications.

Brill's Companion to the Reception of Sophocles offers a comprehensive account of the reception of Sophocles’ plays over the centuries, across cultures and within a range of different fields, such as literature, intellectual history, visual arts, music, dance, stage and cinema.

Prediction of potential fraudulent activities may prevent both the stakeholders and the appropriate regulatory authorities of national or international level from being deceived. The objective difficulties on collecting adequate data that are obsessed by completeness affects the reliability of the most supervised Machine Learning methods. This work examines the effectiveness of forecasting fraudulent financial statements using semi-supervised classification techniques (SSC) that require just a few labeled examples for achieving robust learning behaviors mining useful data patterns from a larger pool of unlabeled examples. Based on data extracted from Greek firms, a number of comparisons between supervised and semi-supervised algorithms has been conducted. According to the produced results, the later algorithms are favored being examined over several scenarios of different Labeled Ratio (R) values.

Background— Transforming growth factor-β family cytokines have diverse actions in the maintenance of cardiac homeostasis. Activin A is a member of this family whose regulation and function in heart are not well understood at a molecular level. Follistatin-like 3 (Fstl3) is an extracellular regulator of activin A protein, and its function in the heart is also unknown. Methods and Results— We analyzed the expression of various transforming growth factor-β superfamily cytokines and their binding partners in mouse heart. Activin βA and Fstl3 were upregulated in models of myocardial injury. Overexpression of activin A with an adenoviral vector (Ad-actβA) or treatment with recombinant activin A protein protected cultured myocytes from hypoxia/reoxygenation-induced apoptosis. Systemic overexpression of activin A in mice by intravenous injection of Ad-actβA protected hearts from ischemia/reperfusion injury. Activin A induced the expression of Bcl-2, and ablation of Bcl-2 by small interfering RNA abrogated its protective action in myocytes. The protective effect of activin A on cultured myocytes was abolished by treatment with Fstl3 or by a pharmacological activin receptor-like kinase inhibitor. Cardiac-specific Fstl3 knockout mice showed significantly smaller infarcts after ischemia/reperfusion injury that was accompanied by reduced apoptosis. Conclusions— Activin A and Fstl3 are induced in heart by myocardial stress. Activin A protects myocytes from death, and this activity is antagonized by Fstl3. Thus, the relative expression levels of these factors after injury is a determinant of cell survival in the heart.

This paper addresses the problem of automatic induction of the normalized form (lemma) of regular and mildly irregular words with no direct supervision using language-independent algorithms. More specifically, two string distance metric models (i.e. the Levenshtein Edit Distance algorithm and the Dice Coefficient similarity measure) were employed in order to deal with the automatic word lemmatization task by combining two alignment models based on the string similarity and the most frequent inflectional suffixes. The performance of the proposed model has been evaluated quantitatively and qualitatively. Experiments were performed for the Modern Greek and English languages and the results, which are set within the state-of-the-art, have showed that the proposed model is robust (for a variety of languages) and computationally efficient. The proposed model may be useful as a pre-processing tool to various language engineering and text mining applications such as spell-checkers, electronic dictionaries, morphological analyzers etc.

Automatic speech recognition (ASR) task constitutes a well-known issue among fields like Natural Language Processing (NLP), Digital Signal Processing (DSP) and Machine Learning (ML). In this work, a robust supervised classification model is presented (MFCCs + autocor + SVM) for feature extraction of solo speech signals. Mel Frequency Cepstral Coefficients (MFCCs) are exploited combined with Content Based Image Retrieval (CBIR) features extracted from spectrogram produced by each frame of the speech signal. Improvement of classification accuracy using such extended feature vectors is examined against using only MFCCs with several classifiers for three scenarios of different number of speakers.

Classification is one of the most important tasks of data mining techniques, which have been adopted by several modern applications. The shortage of enough labeled data in the majority of these applications has shifted the interest towards using semisupervised methods. Under such schemes, the use of collected unlabeled data combined with a clearly smaller set of labeled examples leads to similar or even better classification accuracy against supervised algorithms, which use labeled examples exclusively during the training phase. A novel approach for increasing semisupervised classification using Cascade Classifier technique is presented in this paper. The main characteristic of Cascade Classifier strategy is the use of a base classifier for increasing the feature space by adding either the predicted class or the probability class distribution of the initial data. The classifier of the second level is supplied with the new dataset and extracts the decision for each instance. In this work, a self-trained NB∇C4.5 classifier algorithm is presented, which combines the characteristics of Naive Bayes as a base classifier and the speed of C4.5 for final classification. We performed an in-depth comparison with other well-known semisupervised classification methods on standard benchmark datasets and we finally reached to the point that the presented technique has better accuracy in most cases.

Brill's Companion to the Reception of Euripides offers a comprehensive account of the reception of Euripides’ plays over the centuries, across cultures and within a range of different fields, such as literature, intellectual history, visual arts, music, dance, stage and cinema.

This paper introduces a statistical framework for extracting medical domain knowledge from heterogeneous corpora. The acquired information is incorporated into a natural language understanding agent and applied to DIKTIS, an existing web-based educational dialogue system for the chemotherapy of nosocomial and community acquired pneumonia, aiming at providing a more intelligent natural language interaction. Unlike the majority of existing dialogue understanding engines, the presented system automatically encodes semantic representation of a user's query using Bayesian networks. The structure of the networks is determined from annotated dialogue corpora using the Bayesian scoring method, thus eliminating the tedious and costly process of manually coding domain knowledge. The conditional probability distributions are estimated during a training phase using data obtained from the same set of dialogue acts. In order to cope with words absent from our restricted dialogue corpus, a separate offline module was incorporated, which estimates their semantic role from both medical and general raw text corpora, correlating them with known lexical-semantically similar words or predefined topics. Lexical similarity is identified on the basis of both contextual similarity and co-occurrence in conjunctive expressions. The evaluation of the platform was performed against the existing language natural understanding module of DIKTIS, the architecture of which is based on manually embedded domain knowledge.

The WATCHER project aims to automate the extraction of language resources from the Internet via an intelligent agent called the 'WATCHER'. This agent (in its final form) will be able to actively search and collect subject-specific and language-specific texts and build corpora and lexicons from them. Although the resources will still have to be checked for validity after their collection, the proposed method requires the minimum of human interaction. Apart from its ability to collect these resources automatically, the WATCHER will also be able to track the evolution of a target language over time by collecting resources annually and presenting their analysis in annual reports. The WATCHER is still under development. This paper presents an overview of its architecture and functionality, and reports recent progress.

The automation of Directory Assistance Services (DAS) through speech is one of the most difficult and demanding applications of human-computer interaction because it deals with very large vocabulary recognition issues. In this paper, we present a spoken dialogue system for automating DAS.1 Taking into account the major difficulties of this endeavor a stepwise approach was adopted. In particular, two prototypes D1.1 (basic approach) and D1.2 (improved version) were developed successively. The results of D1.1 evaluation were used to refine D1.1 and gradually led to D1.2 that was also improved using a feedback approach. Furthermore, the system was extended and optimized so that it can be utilized in real-world conditions. We describe the general architecture and the three stages of the system's development in detail. Evaluation results concerning both the speech recognizer's accuracy and the overall system's performance are provided for all prototypes. Finally, we focus on techniques that handle large vocabulary recognition issues. The use of Directed Acyclic Word Graphs (DAWGs) and context-dependent phonological rules resulted in search space reduction and therefore in faster response, and also in improved accuracy.

The aim of this paper is to present a useful and friendly electronic tool (grammar checker) which will carry out the morphological and syntactic analysis of sentences, phrases and words in order to correct syntactic, grammatical and stylistic errors. We also present the formalism used (the Mnemosyne’s Kanon) and also the particularities of the Greek language that hinder the computational processing. Given that the major problem of modern Greek is the lexical ambiguity we designed the Greek tagger grounded on linguistic criteria for those cases where the lexical ambiguity impede the imprint of the errors in Greek language. The texts that were given for correction to the grammar checker were also corrected by a person. In a very large percentage the grammar checker approximates in accuracy the human-corrector.

Semi-supervised classification methods are based on the use of unlabeled data in combination with a smaller set of labeled examples, in order to increase the classification rate compared with the supervised methods, in which the total training is executed only by the usage of labeled data. In this work, a self-train Logitboost algorithm is presented. The self-train process improves the results by using the accurate class probabilities for which the Logitboost regression tree model is more confident at the unlabeled instances. We performed a comparison with other well-known semi-supervised classification methods on standard benchmark datasets and the presented technique had better accuracy in most cases.

Brill's Companion to the Reception of Euripides offers a comprehensive account of the reception of Euripides’ plays over the centuries, across cultures and within a range of different fields, such as literature, intellectual history, visual arts, music, dance, stage and cinema.

An effective speech brain machine interface requires selecting the best cortical recording sites and signal features for decoding speech production, but also minimal clinical risk for the patient. Motivated by this need to reduce patient risk, the purpose of this study is to detect voice activity (speech onset and offset) automatically from spatial-spectral features of electrocorticographic signals using the optimal number of sensors (minimal invasiveness). ECoG signals were recorded while a subject performed two different syllable repetition tasks. We found that the optimal frequency resolution for detecting voice activity is 8 Hz using 31 sensors out of 55, achieving 98.2% accuracy by employing support vector machines (SVM) as a classifier, and that acceptable accuracy of 96.7% was achieved using 15 sensors, which would permit a less invasive surgery for the placement of electrodes. The proposed voice activity detector may be utilized as a part of an ECoG-based automated natural speech BMI system.

Brain machine interfaces for speech restoration have been extensively studied for more than two decades. The success of such a system will depend in part on selecting the best brain recording sites and signal features corresponding to speech production. The purpose of this study was to detect speech activity automatically from electrocorticographic signals based on joint spatial-frequency clustering of the ECoG feature space. For this study, the ECoG signals were recorded while a subject performed two different syllable repetition tasks. We found that the optimal frequency resolution to detect speech activity from ECoG signals was 8 Hz, achieving 98.8% accuracy by employing support vector machines (SVM) as a classifier. We also defined the cortical areas that held the most information about the discrimination of speech and non-speech time intervals. Additionally, the results shed light on the distinct cortical areas associated with the two syllable repetition tasks and may contribute to the development of portable ECoG-based communication.

The history of classical scholarship abounds with examples of metaphors that function as organic links between past and present. As vehicles for contemporary emulation or allies of particular moral and political ideologies, interpretations of ancient life have mirrored the anxieties and controversies of their times. Alexander the Great has been a prominent figure in such historically contextualized interpretations. A comparative study of the reception of this legendary hero by two leading nineteenth-century historians, George Grote and Konstantinos Paparrigopoulos, provides a platform for reflecting on the influence that different versions of Hellenism have had on the construction of historical narratives. Two contrasting Alexanders emerge from the works of the Victorian radical and the Greek national historiographer. Grote's Alexander was the deadly enemy of ancient liberalism and conqueror of a glorious civilization that was never to be resurrected. Paparrigopoulos's Alexander, in contrast, was a national heroic ancestor who bridged the classical with the Byzantine in the Hellenic world. In this form, Alexander emerged as a symbol of national unity and his achievement became the historical analogue of nation-building.

This paper presents an implementation of a syntactic parser for the Modern Greek language based on the PC-PATR formalism. The Modern Greek language presents a high flexibility in its syntactic structure. The various phrasal categories (noun phrases, verb phrases, prepositional, and adverbial phrases) can be ordered in almost any permutation so as to build valid sentences. The allowable combinations of lexical categories (nouns, verbs, adjectives, etc.) forming the above phrases, as well as the combinations of these phrases, forming clauses, are encoded according to the PC-PATR formalism and are presented in this paper. The presented rules cover the majority of the syntactic phenomena of the Modern Greek language, adequate for speech and natural language applications.

This report confronts the problem of automatic conversion from graphemic to phonetic transcription and vice versa for the Modern Greek language. A single representation is used for both directions of word transformation, based on PC-KIMMO, a development environment originally used for the implementation of two-level morphological processors. The fifty-two two-level rules that are presented have been tested on a set of the 10,000 most frequent Modern Greek words and they describe the Greek phonology in adequate detail for use by a speech-processing system.

Aging is a highly complex biological process and a risk factor for many diseases. Motivated by the high availability of diverse high-throughput data in the mouse model organism, we provide a systemic view of the age-related mechanisms. In particular, we present a robust network-based integrative approach that provides, based on protein interaction and microarray data, reliable modules that alter significantly in terms of expression during aging. Our modular meta-analysis provides novel information about the involvement of several established as well as recently reported longevity-associated pathways across different tissues.

In this paper, we perform spatio-spectral analysis of the human cortex with implanted electrocorticographic (ECoG) electrodes during the voice production process. For this study, the ECoG signals were recorded while the subject performed two-syllable tasks. Additionally, assuming that the speech activity of a subject is expressed as ECoG signal activity disparately distributed over the space of the electrodes, we examined the spectral information in response to the electrode locations. The study was based on spectral features (power spectral density) estimated for each electrode. Quantitative analysis based on the Relief algorithm was followed to estimate the degree of importance of each electrode for describing the voice activity. The experimental results showed that the spectral analysis with resolution of 8 Hz offers the highest voice discrimination performance (94.2%) using support vector machines as classifier. Finally, our analysis showed that during voice activity the frequency bands [168, 208] Hz are mostly affected.

Theorizing Political Participation.- The Internet and Political Participation.- Case Studies.

Part 1: Second Artificial Intelligence Applications in Biomedicine Workshop (AIAB 2012); International audience; The diagnosis of brain neoplasms has been facilitated by the emerging of high-quality imaging techniques, such as Magnetic Resonance Imaging (MRI), while the combination of several sequences from conventional and advanced protocols has increased the diagnostic information. Treatment planning and therapy follow-up require the detection of neoplastic and edematous tissue boundaries, a very time consuming task when manually performed by medical experts based on the 3D MRI data. Automating the detection process is challenging, due to the high diversity in appearance of neoplastic tissue among different patients and, in many cases, similarity between neoplastic and normal tissue. In this paper, we propose an automatic brain tumor segmentation method based on a multilabel multiparametric random walks approach initialized by an outlier detection scheme. Segmentation assessment is performed by measuring spatial overlap between automatic segmentation and manual segmentation performed by medical experts. Good agreement is observed in most of the 26 cases for both neoplastic and edematous tissue. The highest achieved overlapping values were 0.74 and 0.79 for neoplastic and edematous tissue, respectively.

Teaching introduction to computing courses, especially to first year college students, is a challenging endeavor given the increasing difficulty of today’s students with programming and algorithmic thinking. In this paper the experience of introducing collaborative and project based approaches in a first year University course is reported. Both synchronous collaborative learning approaches and asynchronous collaboration through group project work have been introduced in the course using Python as a programming language. The effect of use of these approaches in students’ attitude towards Computer Science and their performance is discussed here.

BACKGROUND The cardioprotective benefits of bradykinin are attributable to activation of its B(2) receptor (B(2)R)-mediated actions and abolished by B(2)R antagonists. The current experiments evaluated the cardioprotective potential of a potent, long-acting B(2)R-selective agonist peptide analogue of bradykinin, the compound NG291. METHODS We compared the extent of cardiac tissue damage and remodeling and expression pattern of selected genes in mice submitted to acute myocardial infarct (MI) and treated for 1 week with either NG291 [Hyp(3),Thi(5),(N)Chg(7),Thi(8)]-bradykinin or with saline delivered via osmotic minipump. RESULTS Active treatment resulted in better ejection fraction (EF) 69 +/- 1% vs. 61 +/- 3.1% (P = 0.01), (vs. 85 +/- 1.3% in sham-operated controls), fractional shortening (FS) 38 +/- 4% vs. 32 +/- 8% (NS) (vs. 53 +/- 1.2 in sham-operated controls), and fewer markers of myocyte apoptosis (TUNEL-positive nuclei 4.9 +/- 1.1% vs. 9.7 +/- 0.03%, P = 0.03). Systolic blood pressure (SBP) at end point was normal at 110 +/- 4.2 in actively treated mice, but tended to be lower at 104 +/- 4.7 mm Hg in saline controls with decreased cardiac systolic capacity. Expression patterns of selected genes to factors related to tissue injury, inflammation, and metabolism (i.e., the B(1)R, B(2)R, endothelial nitric oxide synthase (eNOS), TNF-alpha, cardiomyopathy-associated 3 (Cmya3), and pyruvate dehydrogenase kinase isoenzyme 4 (PDK4)) showed that acute MI induced significant upregulation of these genes, and active treatment prevented or attenuated this upregulation, whereas the B(2)R agonist itself produced no difference in the myocardium of sham-operated mice. CONCLUSIONS Treatment with a selective B(2)R agonist initiated at the time of induction of acute MI in mice had a beneficial effect on cardiac function, tissue remodeling, and inflammation-related tissue gene expression, which may explain its structural and functional benefits.

Anxiety disorders are considered the most prevalent of mental disorders. Nevertheless, the exact reasons that provoke them to patients remain yet not clearly specified, while the literature concerning the environment for monitoring and treatment support is rather scarce warranting further investigation. Toward this direction, in this study a context-aware approach is proposed, aiming to provide medical supervisors with a series of applications and personalized services targeted to exploit the multiparameter contextual data collected through a long-term monitoring procedure. More specifically, an application that assists the archiving and retrieving of the patients' health records was developed, and four treatment supportive services were considered. The three of them focus on the discovery of possible associations between the patient's contextual data; the last service aims at predicting the stress level a patient might suffer from, in a given context. The proposed approach was experimentally evaluated quantitatively (in terms of computational efficiency and time requirements) and qualitatively by experts on the field of mental health domain. The feedback received was very encouraging and the proposed approach seems quite useful to the anxiety disorders' treatment.

Greek to Greeklish transcription does not appear to be a difficult task since it can be achieved by directly mapping each Greek character to a corresponding symbol of the Latin alphabet Nevertheless, such transliteration systems do not simulate efficiently the human way of Greeklish writing, since Greeklish users do not follow a standardized way of transliteration In this paper a stochastic Greek to Greeklish transcriber modeled by real user data is presented The proposed transcriber employs knowledge derived from the analytical processing of 9,288 Greek-Greeklish word pairs annotated by real users and achieves the automatic transcription of any Greek word into a valid Greeklish form in a stochastic way (i.e each Greek symbolset corresponds to a variety of Latin symbols according to the processed data), simulating thus human-like behavior This transcriber could be used as a real-time Greek-to-Greeklish transcriber and/or as a data generator engine used for the performance evaluation of Greeklish-to-Greek transliteration systems.

In the present work we have implemented the Edit Distance (also known as Levenshtein Distance) on a dictionary-based algorithm in order to achieve the automatic induction of the normalized form (lemma) of regular and mildly irregular words with no direct supervision. The algorithm combines two alignment models based on the string similarity and the most frequent inflexional suffixes. In our experiments, we have also examined the language-independency (i.e. independency of the specific grammar and inflexional rules of the language) of the presented algorithm by evaluating its performance on the Modern Greek and English languages. The results were very promising as we achieved more than 95 % of accuracy for the Greek language and more than 96 % for the English language. This algorithm may be useful to various text mining and linguistic applications such as spell-checkers, electronic dictionaries, morphological analyzers, search engines etc.

Recurrent networks constitute an elegant way of increasing the capacity of feedforward networks to deal with complex data in the form of sequences of vectors. They are well known for their power to model temporal dependencies and process sequences for classification, recognition, and transduction. In this paper, we propose a nonmonotone conjugate gradient training algorithm for recurrent neural networks, which is equipped with an adaptive tuning strategy for the nonmonotone learning horizon. Simulation results show that this modification of conjugate gradient is more effective than the original CG in four applications using three different recurrent network architectures.

In the present work we used a word clustering algorithm based on the perplexity criterion, in a Dialogue Act detection framework in order to model the structure of the speech of a user at a dialogue system. Specifically, we constructed an n-gram based model for each target Dialogue Act, computed over the word classes. Then we evaluated the performance of our dialogue system on ten different types of dialogue acts, using an annotated database which contains 1,403,985 unique words. The results were very promising since we achieved about 70% of accuracy using trigram based models.