Search results for: text preprocessing

Authors: Biniam Seifu Debelo, Bheema Lingaiah Thamineni, Hanumesh Kumar Dasari, Ahmed Ali Dawud

Abstract:

Background: One of the most frequent neurological conditions in newborns is neonatal seizures, which may indicate severe neurological dysfunction. They may be caused by a broad range of problems with the central nervous system during or after pregnancy, infections, brain injuries, and/or other health conditions. These seizures may have very subtle or very modest clinical indications because patterns like oscillatory (spike) trains begin with relatively low amplitude and gradually increase over time. This becomes very challenging and erroneous if clinical observation is the primary basis for identifying newborn seizures. Objectives: In this study, a diagnosis system using deep convolutional neural networks is proposed to determine and classify the severity level of neonatal seizures using multichannel neonatal EEG data. Methods: Clinical multichannel EEG datasets were compiled using datasets from publicly accessible online sources. Various preprocessing steps were taken, including converting 2D time series data to equivalent waveform pictures. The proposed models underwent training, and their performance was evaluated. Results: The proposed CNN was used to perform binary classification with an accuracy of 92.6%, F1-score of 92.7%, specificity of 92.8%, and precision of 92.6%. To detect newborn seizures, this model is utilized. Using the proposed CNN model, multiclassification was performed with accuracy rates of 88.6%, specificity rates of 92.18%, F1-score rates of 85.61%, and precision rates of 88.9%. A multiclassification model is used to classify the severity level of neonatal seizures. The results demonstrated that the suggested strategy can assist medical professionals in making accurate diagnoses close to healthcare institutions. Conclusion: The developed system was capable of detecting neonatal seizures and has the potential to be used as a decision-making tool in resource-limited areas with a scarcity of expert neurologists.

Keywords: CNN, multichannel EEG, neonatal seizure, severity identification

Procedia PDF Downloads 7

Authors: Ana Mouta, Ana Paulino

Abstract:

The following text presents the ik.model, a theoretical framework that guided the pedagogical implementation of meaningful educational technology-based projects in formal education worldwide. In this paper, we will focus on how this framework has enabled the development of media literacy projects for early childhood education during the last three years. The methodology that guided educators through the challenge of systematically merging analogic and digital means in dialogic high-quality opportunities of world exploration is explained throughout these lines. The effects of this methodology on early age media literacy development are considered. Also considered is the relevance of this skill in terms of post-contemporary challenges posed to learning.

Keywords: early learning, ik.model, media literacy, pedagogy

Procedia PDF Downloads 295

Authors: Zs. Csanádi, A. Szabó Nagy, J. Szabó, J. Erdős

Abstract:

Atmospheric concentrations of some heavy metal compounds (Pb, Cd, Ni) and the metalloid As were identified and determined in airborne PM2.5 particles in urban sites of Győr, northwest area of Hungary. PM2.5 aerosol samples were collected in two different sampling sites and the trace metal(loid) (Pb, Ni, Cd and As) content were analyzed by atomic absorption spectroscopy. The concentration of PM2.5 fraction was varied between 12.22 and 36.92 μg/m³ at the two sampling sites. The trend of heavy metal mean concentrations regarding the mean value of the two urban sites of Győr was found in decreasing order of Pb > Ni > Cd. The mean values were 7.59 ng/m³ for Pb, 0.34 ng/m³ for Ni and 0.11 ng/m³ for Cd, respectively. The metalloid As could be detected only in 3.57% of the total collected samples. The levels of PM2.5 bounded heavy metals were determined and compared with other cities located in Hungary.

Keywords: aerosol, air quality, heavy metals, PM2.5

Procedia PDF Downloads 270

Authors: Shunzuo Wu, Xudong Luo, Yuanxiu Liao

Abstract:

Recently, the rapid development of deep learning makes artificial intelligence (AI) penetrate into many fields, replacing manual work there. In particular, AI systems also become a research focus in the field of automatic office. To meet real needs in automatic officiating, in this paper we develop an automatic form filling system. Specifically, it uses two classical neural network models and several word embedding models to classify various relevant information elicited from the Internet. When training the neural network models, we use less noisy and balanced data for training. We conduct a series of experiments to test my systems and the results show that our system can achieve better classification results.

Keywords: artificial intelligence and office, NLP, deep learning, text classification

Procedia PDF Downloads 165

Authors: Mohsen Maraoui

Abstract:

In the face of the growth in the quantity of data produced, several methods and techniques appear to remedy the problems of processing and analyzing large amounts of information mainly in the field of teaching. In this paper, we propose an intelligent cloud-based teaching system for E-learning content services. This system makes easy the manipulation of various educational content forms, including text, images, videos, 3 dimensions objects and scenes of virtual reality and augmented reality. We discuss the integration of institutional and external services to provide personalized assistance to university members in their daily activities. The proposed system provides an intelligent solution for media services that can be accessed from smart devices cloud-based intelligent service environment with a fully integrated system.

Keywords: cloud computing, e-learning, indexation, IoT, learning in Arabic language, smart tools

Procedia PDF Downloads 112

Authors: Thiru Vandeyar

Abstract:

The present study set out to determine how Q methodology may be used as an inclusive education policy development process. Utilising Q-methodology as a strategy of inquiry, this qualitative instrumental case study set out to explore how teachers, as a crucial but often neglected human resource, may be included in developing policy. A social constructivist lens and the theoretical moorings of Proudford’s emancipatory approach to educational change anchored in teachers’ ‘writerly’ interpretation of policy text was employed. Findings suggest that Q-method is a unique research approach to include teachers’ voices in policy development. Second, that beliefs, attitudes, and professionalism of teachers to improve teaching and learning using ICT are integral to policy formulation. The study indicates that teachers have unique beliefs about what statements should constitute a school’s information and communication (ICT) policy. Teachers’ experiences are an extremely valuable resource in and should not be ignored in the policy formulation process.

Keywords: teachers, q-methodology, education policy, ICT

Procedia PDF Downloads 66

Authors: Rune Bjerke

Abstract:

Psychologists incline to see creativity as a mental and psychological process. However, creativity is as well results of cultural and social interactions. Therefore, creativity is not a product of individuals in isolation, but of social systems. Creative people get ideas from the influence of others and the immediate cultural environment – a space of knowledge, situations, and practices. Therefore, in this study we apply the systems theory in practice to activate creativity processes in the production of our novel and screenplay writing. We, as storytellers actively seek to get into situations in our everyday lives, our systems, to generate ideas. Within our personal systems, we have the potential to induce situations to realise ideas to our texts, which may be accepted by our gate-keepers and can become socially validated. This is our method of writing – get into situations, get ideas to texts, and test them with family and friends in our social systems. Example of novel text as an outcome of our method is as follows: “Is it a matter of obviousness or had I read it somewhere, that the one who increases his knowledge increases his pain? And also, the other way around, with increased pain, knowledge increases, I thought. Perhaps such a chain of effects explains why the rebel August Strindberg wrote seven plays in ten months after the divorce with Siri von Essen. Shortly after, he tried painting. Neither the seven theatre plays were shown, nor the paintings were exhibited. I was standing in front of Munch's painting Women in Three Stages with chaotic mental images of myself crumpled in a church and a laughing x-girlfriend watching my suffering. My stomach was turning at unpredictable intervals and the subsequent vomiting almost suffocated me. Love grief at the worst. Was it this pain Strindberg felt? Despite the failure of his first plays, the pain must have triggered a form of creative energy that turned pain into ideas. Suffering, thoughts, feelings, words, text, and then, the reader experience. Maybe this negative force can be transformed into something positive, I asked myself. The question eased my pain. At that moment, I forgot the damp, humid air in the Munch Museum. Is it the similar type of Strindberg-pain that could explain the recurring, depressive themes in Munch's paintings? Illness, death, love and jealousy. As a beginning art student at the master's level, I had decided to find the answer. Was it the same with Munch's pain, as with Strindberg - a woman behind? There had to be women in the case of Munch - therefore, the painting “Women in Three Stages”? Who are they, what personality types are they – the women in red, black and white dresses from left to the right?” We, the writers, are using persons, situations and elements in our systems, in a systems theory perspective, to prompt creative ideas. A conceptual model is provided to advance creativity theory.

Keywords: creativity theory, systems theory, novel writing, screenplay writing, sources of creativity in social systems

Procedia PDF Downloads 98

Authors: Minh-Thuan Nguyen, Phuong-Thai Nguyen, Van-Vinh Nguyen, Quang-Minh Nguyen

Abstract:

Research on automatically generating descriptions for e-commerce products is gaining increasing attention in recent years. However, the generated descriptions of their systems are often less informative and attractive because of lacking training datasets or the limitation of these approaches, which often use templates or statistical methods. In this paper, we explore a method to generate production descriptions by using the GPT-2 model. In addition, we apply text paraphrasing and task-adaptive pretraining techniques to improve the qualify of descriptions generated from the GPT-2 model. Experiment results show that our models outperform the baseline model through automatic evaluation and human evaluation. Especially, our methods achieve a promising result not only on the seen test set but also in the unseen test set.

Keywords: GPT-2, product description, transformer, task-adaptive, language model, pretraining

Procedia PDF Downloads 175

Authors: A. Anastasiou, K. S. Tingay

Abstract:

Background: Discovering suitable datasets is an important part of health research, particularly for projects working with clinical data from patients organized in cohorts (cohort data), but with the proliferation of so many national and international initiatives, it is becoming increasingly difficult for research teams to locate real world datasets that are most relevant to their project objectives. We present a method for identifying healthcare institutes in the European Union (EU) which may hold haemato-oncology (HO) data. A key enabler of this research was the bibInsight platform, a scientometric data management and analysis system developed by the authors at Swansea University. Method: A PubMed search was conducted using HO clinical terms taken from previous work. The resulting XML file was processed using the bibInsight platform, linking affiliations to the Global Research Identifier Database (GRID). GRID is an international, standardized list of institutions, including the city and country in which the institution exists, as well as a category of the main business type, e.g., Academic, Healthcare, Government, Company. Countries were limited to the 28 current EU members, and institute type to 'Healthcare'. An article was considered valid if at least one author was affiliated with an EU-based healthcare institute. Results: The PubMed search produced 21,310 articles, consisting of 9,885 distinct affiliations with correspondence in GRID. Of these articles, 760 were from EU countries, and 390 of these were healthcare institutes. One affiliation was excluded as being a veterinary hospital. Two EU countries did not have any publications in our analysis dataset. The results were analysed by country and by individual healthcare institute. Networks both within the EU and internationally show institutional collaborations, which may suggest a willingness to share data for research purposes. Geographical mapping can ensure that data has broad population coverage. Collaborations with industry or government may exclude healthcare institutes that may have embargos or additional costs associated with data access. Conclusions: Data reuse is becoming increasingly important both for ensuring the validity of results, and economy of available resources. The ability to identify potential, specific data sources from over twenty thousand articles in less than an hour could assist in improving knowledge of, and access to, data sources. As our method has not yet specified if these healthcare institutes are holding data, or merely publishing on that topic, future work will involve text mining of data-specific concordant terms to identify numbers of participants, demographics, study methodologies, and sub-topics of interest.

Keywords: data reuse, data discovery, data linkage, journal articles, text mining

Procedia PDF Downloads 97

Authors: Monireh Ahmadi Bani, Adel Khorramrouz, Lalenoor Morvarid, Bagheri Mahtab

Abstract:

Background:- Foot disorders are common in musculoskeletal problems. Plantar pressure distribution measurement is one the most important part of foot disorders diagnosis for quantitative analysis. However, the association of plantar pressure and foot disorders is not clear. With the growth of dataset and machine learning methods, the relationship between foot disorders and plantar pressures can be detected. Significance of the study:- The purpose of this study was to predict the probability of common foot disorders based on peak plantar pressure distribution and center of pressure during walking. Methodologies:- 2323 participants were assessed in a foot therapy clinic between 2015 and 2021. Foot disorders were diagnosed by an experienced physician and then they were asked to walk on a force plate scanner. After the data preprocessing, due to the difference in walking time and foot size, we normalized the samples based on time and foot size. Some of force plate variables were selected as input to a deep neural network (DNN), and the probability of any each foot disorder was measured. In next step, we used support vector machine (SVM) and run dataset for each foot disorder (classification of yes or no). We compared DNN and SVM for foot disorders prediction based on plantar pressure distributions and center of pressure. Findings:- The results demonstrated that the accuracy of deep learning architecture is sufficient for most clinical and research applications in the study population. In addition, the SVM approach has more accuracy for predictions, enabling applications for foot disorders diagnosis. The detection accuracy was 71% by the deep learning algorithm and 78% by the SVM algorithm. Moreover, when we worked with peak plantar pressure distribution, it was more accurate than center of pressure dataset. Conclusion:- Both algorithms- deep learning and SVM will help therapist and patients to improve the data pool and enhance foot disorders prediction with less expense and error after removing some restrictions properly.

Keywords: deep neural network, foot disorder, plantar pressure, support vector machine

Procedia PDF Downloads 321

Authors: B. J. Sandesh, Saurabha Jirgi, S. Vidya, Prakash Eljer, Gowri Srinivasa

Abstract:

In this paper, we propose a framework to help users to search and retrieve the portions in the lecture video of their interest. This is achieved by temporally segmenting and indexing the lecture video using the topic keywords. We use transcribed text from the video and documents relevant to the video topic extracted from the web for this purpose. The keywords for indexing are found by applying the non-negative matrix factorization (NMF) topic modeling techniques on the web documents. Our proposed technique first creates indices on the transcribed documents using the topic keywords, and these are mapped to the video to find the start and end time of the portions of the video for a particular topic. This time information is stored in the index table along with the topic keyword which is used to retrieve the specific portions of the video for the query provided by the users.

Keywords: video indexing and retrieval, lecture videos, content based video search, multimodal indexing

Procedia PDF Downloads 230

Authors: Hania Pasandi

Abstract:

Since its publication in 1856, Madame Bovary has established itself as one of the most adapted texts of French literature. Some eighteen film adaptations and twenty-seven rewritings of Madame Bovary in fiction to date shows a great enthusiasm for recreating Flaubert’s masterpiece in a variety of mediums. Posy Simmonds’ 1999 graphic novel, Gemma Bovery stands out among these adaptations as the graphic novel with its visual and narrative structure offers a new reading experience of Madame Bovary, while combining Emma Bovary’s elements with contemporary social, cultural, and artistic discourses. This paper studies the transposition of Flaubert’s Madame Bovary (1857) to late twentieth-century Britain in Posy Simmonds’ 1999 graphic novel, Gemma Bovery by exploring how it borrows the essential flaubertian themes, from its source text to incorporate it with contemporary cultural trends.

Keywords: graphic novel, Gemma Bovery, Madame Bovary, transposition

Procedia PDF Downloads 131

Authors: Yehudit Dror

Abstract:

Parallelism¬, or as it is called in Arabic, al-muqābala, occupies a central position in the rhetorical discipline of ʻilm al-bayān. Parallelism is used as a figure of textual ornamentation or embellishment and can be divided into several types that are based on the semantics of parallelism and its formative structure. Parallelism in Arabic has received a considerable amount of attention from the Arab rhetorician, which enables understanding the essence of parallelism in Arabic – its types, structure and meaning. However, there are some lacunae in their descriptions concerning the function and thematic restrictions of parallelism in the Qur’ān. In my presentation, which focuses on grammatical parallelism where the two stichos of the parallelism are the same with respect to syntax and morphology, I will show that parallelism has some important roles in the textual arrangement; it may, for example, conclude a thematic section, indicate a turning point in the text or to clarify what has been said previously. In addition, it will be shown that parallelism is not used randomly in the Qurʼān but rather is restricted to repeated themes which carry the most important messages of the Qurʼān, such as God's Might or behavioral patterns of the believers and the non-believers; or it can be used as a stylistic device.

Keywords: grammatical parallelism, half-line, symmetry, Koran

Procedia PDF Downloads 311

Authors: Raja Lahiani

Abstract:

This study is concerned with scrutinising translations into English and French of references to locations in the desert of pre-Islamic Arabia. These references are used in the Source Text (ST) within a poetic image. Reference is made to the names of three different mountains in Arabia, namely Qatan, Sitar, and Yadhbul. As these mountains are referred to in the context of the poet’s description of the density and expansion of the clouds, it is crucial to know that while Sitar and Yadhbul are close to each other, Qatan is far away from them. This distance was functional for the poet to describe the expansion of the clouds. This reflects the spacious place (desert) he handled, and the fact that it was possible for him to physically see what he described. The purpose of this image is for the poet to communicate the vastness of the space he managed to see as he was in a moment of contemplation. Thus, knowledge of this characteristic about the setting is capital for the receiver to understand the communicative function of the verse. A corpus of eighteen translations is gathered. These vary between verse and prose renderings. The methodology adopted in this research work is comparative. Comparison is conducted at both the synchronic and diachronic levels; every translation shall be compared to the ST and then to previous translations. The comparative work will prove at the end that the translators who target historical facts do not necessarily succeed in preserving the image of the ST. It also proves that the more recent the translation is, the deeper the translator’s awareness is the link between imagery, setting, and point of view. Since the late eighteenth century and until nowadays, pre-Islamic poetry has been translated into Western languages. Translators differ as to motives, sources, priorities and intellectual backgrounds. A translator's skopoi undoubtedly affect the way s/he handles aspects of the ST. When it comes to culture-specific aspects and details related to setting, the problem is even more complex. Setting is a very important factor that reveals a great deal of the culture of pre-Islamic Arabia as this is remote in place, historical framework and literary tradition from its translators. History is present in pre-Islamic poetry, which justifies the important literature that has been written to extract information and data from it. These are imbedded not only by signalling given facts, events, and meditations but also by means of references to specific locations and landmarks that used to exist at the time. Spatial setting is an integral part of a literary text as it places it within its historical context. The importance of the translator’s awareness of spatial anthropological data before indulging in the process of translation is tested. This is also crucial in measuring the effect of setting loss and setting gain in translation. The findings of this research would ultimately evaluate the extent to which a comparative methodology is reliable in investigating the role of spatial setting awareness in translation.

Keywords: historical context, translation, comparative literature, spatial setting

Procedia PDF Downloads 234

Authors: Yasmin Tantawi, Mary Beth Rosson

Abstract:

In response to the dearth of information about emoji use for different purposes in different settings, this paper investigates the paralinguistic function of emojis within Twitter communication in the United States. To conduct this investigation, the Twitter feeds from 16 population centers spread throughout the United States were collected from the Twitter public API. One hundred tweets were collected from each population center, totaling to 1,600 tweets. Tweets containing emojis were next extracted using the “emot” Python package; these were then analyzed via the IBM Watson API Natural Language Understanding module to identify the topics discussed. A manual content analysis was then conducted to ascertain the paralinguistic and emotional features of the emojis used in these tweets. We present our characterization of emoji usage in Twitter and discuss implications for the design of Twitter and other text-based communication tools.

Keywords: computer-mediated communication, content analysis, paralinguistics, sociology

Procedia PDF Downloads 147

Authors: Shajida M., Sakthiyadharshini N. P., Kamalesh S., Aswitha B.

Abstract:

Natural Language Processing (NLP) continues to play a strategic part in complaint discovery and medicine discovery during the current epidemic. This abstract provides an overview of performance analysis with a combination of visualization and classification techniques of NLP for a medical chatbot. Sentiment analysis is an important aspect of NLP that is used to determine the emotional tone behind a piece of text. This technique has been applied to various domains, including medical chatbots. In this, we have compared the combination of the decision tree with heatmap and Naïve Bayes with Word Cloud. The performance of the chatbot was evaluated using accuracy, and the results indicate that the combination of visualization and classification techniques significantly improves the chatbot's performance.

Keywords: sentimental analysis, NLP, medical chatbot, decision tree, heatmap, naïve bayes, word cloud

Procedia PDF Downloads 53

Authors: Tharini N. de Silva, Xiao Zhibo, Zhao Rui, Mao Kezhi

Abstract:

Causal relation identification is a crucial task in information extraction and knowledge discovery. In this work, we present two approaches to causal relation identification. The first is a classification model trained on a set of knowledge-based features. The second is a deep learning based approach training a model using convolutional neural networks to classify causal relations. We experiment with several different convolutional neural networks (CNN) models based on previous work on relation extraction as well as our own research. Our models are able to identify both explicit and implicit causal relations as well as the direction of the causal relation. The results of our experiments show a higher accuracy than previously achieved for causal relation identification tasks.

Keywords: causal realtion extraction, relation extracton, convolutional neural network, text representation

Procedia PDF Downloads 695

Authors: Dana Weimann Saks

Abstract:

This study aimed to examine the use of the internet as a source of health-related information (HRI), as well as the change in attitudes following the online search for HRI. The current study sample included 88 participants, randomly divided into two experimental groups. One was given the name of an unfamiliar disease and told to search for information about it using various search engines, and the second was given a text about the disease from a credible scientific source. The study findings show a large percentage of participants used the internet as a source of HRI. Likewise, no differences were found in the extent to which the internet was used as a source of HRI when demographics were compared. Those who searched for the HRI on the internet had more negative opinions and believed symptoms of the disease were worse than the average opinion among those who obtained the information about the disease from a credible scientific source. The Internet clearly influences the participants’ beliefs, regardless of demographic differences.

Keywords: health-related information, internet, young adults, HRI

Procedia PDF Downloads 101

Authors: P. Karimi, A. H. Khedmati Bazkiaei

Abstract:

The main goal of this study is to test differential neural network as a controller of smart structure and is to enumerate its advantages and disadvantages in comparison with other controllers. In this study, the smart structure has been considered as a Euler Bernoulli cantilever beam and it has been tried that it be under control with the use of vibration neural network resulting from movement. Also, a linear observer has been considered as a reference controller and has been compared its results. The considered vibration charts and the controlled state have been recounted in the final part of this text. The obtained result show that neural observer has better performance in comparison to the implemented linear observer.

Keywords: smart material, on-line differential artificial neural network, active control, finite element method

Procedia PDF Downloads 190

Authors: Turquesa Topper

Abstract:

The reflection focuses on recording and explaining the considerations, conceptualizations and methodological approach with which from the University, that is to say, from the academic field, the study of Trends is addressed with the intention of training professionals in the area, an area that requires disciplinary boundaries and builds a polyphonic vision. When referring to the objective of our Laboratory the detection of aesthetic trends of consumption, we find ourselves in the requirement to define our object: trends, aesthetic trends of consumption, more specifically. The pages cover a conception of trends from a theoretical framework that incorporates contributions from linguistics, semiotics, sociology, cultural studies and project disciplines, in order to consolidate a polyphonic look. The text investigates in the pre-discursive aspect of the trends, in the circulation of the notion of style and in the dynamics of affirmation - denial as the constitutive dynamics of Fashion linked to any process of innovation. From such inquiry, it is presented to Fashion as a system that operates directly on the construction of socio-individual identities unfolding through the liquefaction of signs in trends.

Keywords: fashion, methodology, narrative, trends

Procedia PDF Downloads 231

Authors: Jun Xu, Haiyan Xiao

Abstract:

The Analects (Lunyu) is one of the most recognized Confucian classics and one of the earliest Chinese classics that have been translated into English and known to the West. Research on the translation of The Analects has witnessed a transfer from the comparison of the text and language to a wider description of social and cultural contexts. Mainly on the basis of Legge and Waley’s translations of The Analects, this paper integrates Lefevere’s theory of rewriting and Verschueren’s theory of adaptation and explores the influence of ideology and poetics on the translation. It analyses how translators make adaptive decisions in the manipulation of ideology and poetics. It is proved that the English translation of The Analects is the translators’ initiative rewriting of the original work, which is a selective and adaptive process in the multi-layered contexts of the target language. The research on the translation of classics should include both the manipulative factors and translator’s initiative as well.

Keywords: The Analects, ideology, poetics, rewriting, adaptation

Procedia PDF Downloads 253

Authors: Marina Yurievna Aleksandrova

Abstract:

Research of the Holocaust retains value not only for history but also for sociology and psychology. One of the most important fields of study is how people were coping during and after this traumatic event. The aim of this paper is to identify the main contexts of the topic of love and to determine which contexts are more characteristic for different groups of victims of the Holocaust (gender, nationality, age). In this research, transcripts of interviews with Holocaust victims that were collected during 1946 for the "Voices of the Holocaust" project were used as data. Main contexts were analyzed with methods of network analysis and latent semantic analysis and classified by gender, age, and nationality with random forest. The results show that love is articulated and described significantly differently for male and female informants, nationality is shown results with lower values of quality metrics, as well as the age.

Keywords: Holocaust, latent semantic analysis, network analysis, text-mining, random forest

Procedia PDF Downloads 162

Authors: Fares Hedayatit, Arnauld Joly, Panagiotis Papadimitriou

Abstract:

Many machine learning tasks such as text annotation usually require training over very big datasets, e.g., millions of web documents, that can be represented in a sparse input space. State-of the-art tree-based ensemble algorithms cannot scale to such datasets, since they include operations whose running time is a function of the input space size rather than a function of the non-zero input elements. In this paper, we propose an efficient splitting algorithm to leverage input sparsity within decision tree methods. Our algorithm improves training time over sparse datasets by more than two orders of magnitude and it has been incorporated in the current version of scikit-learn.org, the most popular open source Python machine learning library.

Keywords: big data, sparsely representable data, tree-based models, scalable learning

Procedia PDF Downloads 242

Authors: Mareye Zeleke Mekonen

Abstract:

The Kafficho language has distinct issues in information retrieval because of its restricted resources and dearth of standardized methods. In this endeavor, with the cooperation and support of linguists and native speakers, we investigate the creation of information retrieval systems specifically designed for the Kafficho language. The Kafficho information retrieval system allows Kafficho speakers to access information easily in an efficient and effective way. Our objective is to conduct an information retrieval experiment using 220 Kafficho text files, including fifteen sample questions. Tokenization, normalization, stop word removal, stemming, and other data pre-processing chores, together with additional tasks like term weighting, were prerequisites for the vector space model to represent each page and a particular query. The three well-known measurement metrics we used for our word were Precision, Recall, and and F-measure, with values of 87%, 28%, and 35%, respectively. This demonstrates how well the Kaffiho information retrieval system performed well while utilizing the vector space paradigm.

Keywords: Kafficho, information retrieval, stemming, vector space

Procedia PDF Downloads 29

Authors: Komal V. Aher, Sanjay B. Waykar

Abstract:

Nowadays every individual having mobile device with them. In both computer vision and information retrieval Image search is currently hot topic with many applications. The proposed intelligent image search system is fully utilizing multimodal and multi-touch functionalities of smart phones which allows search with Image, Voice, and Text on mobile phones. The system will be more useful for users who already have pictures in their minds but have no proper descriptions or names to address them. The paper gives system with ability to form composite visual query to express user’s intention more clearly which helps to give more precise or appropriate results to user. The proposed algorithm will considerably get better in different aspects. System also uses Context based Image retrieval scheme to give significant outcomes. So system is able to achieve gain in terms of search performance, accuracy and user satisfaction.

Keywords: color space, histogram, mobile device, mobile visual search, multimodal search

Procedia PDF Downloads 346

Authors: Lee Soo-Kyoung, Kim Young-Su

Abstract:

This study established a network related to metabolic syndrome intervention by conducting a social network analysis of titles, keywords, and abstracts, and it identified emerging topics of research. It visualized an interconnection between critical keywords and investigated their frequency of appearance to construe the trends in metabolic syndrome intervention measures used in studies conducted over 38 years (1979–2017). It examined a collection of keywords from 8,285 studies using text rank analyzer, NetMiner 4.0. The analysis revealed 5 groups of newly emerging keywords in the research. By examining the relationship between keywords with reference to their betweenness centrality, the following clusters were identified. Thus if new researchers refer to existing trends to establish the subject of their study and the direction of the development of future research on metabolic syndrome intervention can be predicted.

Keywords: intervention, metabolic syndrome, network analysis, research, the trend

Procedia PDF Downloads 184

Authors: Zheng Baichuan, Li Shenghui, Li Bingqian, Zhang Ning, Chen Kai

Abstract:

Entity alignment (EA) tasks in knowledge graphs often play a pivotal role in the integration of knowledge graphs, where structural differences often exist between the source and target graphs, such as the presence or absence of attribute information and the types of attribute information (text, timestamps, images, etc.). However, most current research efforts are focused on improving alignment accuracy, often along with an increased reliance on specific structures -a dependency that inevitably diminishes their practical value and causes difficulties when facing knowledge graph alignment tasks with varying structures. Therefore, we propose a universal knowledge graph alignment approach that only utilizes the common basic structures shared by knowledge graphs. We have demonstrated through experiments that our method achieves state-of-the-art performance in fair comparisons.

Keywords: knowledge graph, entity alignment, transformer, deep learning

Procedia PDF Downloads 22

Authors: Juha Kettunen

Abstract:

This study analyzes the quality and the size of the strategic network of higher education institutions. The study analyses the concept of fitness for purpose in quality assurance. It also analyses the transaction costs of networking that have consequences on the number of members in the network. Empirical evidence is presented of the Consortium on Applied Research and Professional Education, which is a European strategic network of six higher education institutions. The results of the study support the argument that the number of members in the strategic network should be relatively small to provide high quality results. The practical importance is that networking has been able to promote international research and development projects. The results of this study are important for those who want to design and improve international networks in higher education.

Keywords: balanced scorecard, higher education, social networking, strategic planning

Procedia PDF Downloads 322

Authors: Quentin Lobbe, David Chavalarias, Alexandre Delanoe

Abstract:

The ICT revolution has given birth to an unprecedented world of digital traces and has impacted a wide number of knowledge-driven domains such as science, education or policy making. Nowadays, we are daily fueled by unlimited flows of articles, blogs, messages, tweets, etc. The internet itself can thus be considered as an unsteady hyper-textual environment where websites emerge and expand every day. But there are structures inside knowledge. A given text can always be studied in relation to others or in light of a specific socio-cultural context. By way of their textual traces, human beings are calling each other out: hypertext citations, retweets, vocabulary similarity, etc. We are in fact the architects of a giant web of elements of knowledge whose structures and shapes convey their own information. The global shapes of these digital traces represent a source of collective knowledge and the question of their visualization remains an opened challenge. How can we explore, browse and interact with such shapes? In order to navigate across these growing constellations of words and texts, interdisciplinary innovations are emerging at the crossroad between fields of social and computational sciences. In particular, complex systems approaches make it now possible to reconstruct the hidden structures of textual knowledge by means of multi-scale objects of research such as semantic maps and phylomemies. The phylomemy reconstruction is a generic method related to the co-word analysis framework. Phylomemies aim to reveal the temporal dynamics of large corpora of textual contents by performing inter-temporal matching on extracted knowledge domains in order to identify their conceptual lineages. This study aims to address the question of visualizing the global shapes of online political discussions related to the French presidential and legislative elections of 2017. We aim to build phylomemies on top of a dedicated collection of thousands of French political tweets enriched with archived contemporary news web articles. Our goal is to reconstruct the temporal evolution of online debates fueled by each political community during the elections. To that end, we want to introduce an iterative data exploration methodology implemented and tested within the free software Gargantext. There we combine synchronic and diachronic axis of visualization to reveal the dynamics of our corpora of tweets and web pages as well as their inner syntagmatic and paradigmatic relationships. In doing so, we aim to provide researchers with innovative methodological means to explore online semantic landscapes in a collaborative and reflective way.

Keywords: online political debate, French election, hyper-text, phylomemy

Procedia PDF Downloads 172

Authors: Claudia Rodriguez-Espinosa, Erika Elizabeth Pérez Múzquiz

Abstract:

Since the creation of the “Pueblos Mágicos” program in 2001, a series of social and cultural events had directly affected the heritage conservation of the 121 registered localities until 2018, when the federal government terminated the program. Many studies have been carried out that seek to analyze from different perspectives and disciplines the consequences that these appointments have generated in the “Pueblos Mágicos.” Multidisciplinary groups such as the one headed by Carmen Valverde and Liliana López Levi, have brought together specialists from all over the Mexican Republic to create a set of diagnoses of most of these settlements, and although each one has unique specificities, there is a constant in most of them that has to do with the loss of cultural heritage and that is related to transculturality. There are several factors identified that have fostered a cultural loss, as a direct reflection of the economic crisis that prevails in Mexico. It is important to remember that the origin of this program had as its main objective to promote the growth and development of local economies since one of the conditions for entering the program is that they have less than 20,000 inhabitants. With this goal in mind, one of the first actions that many “Pueblos Mágicos” carried out was to improve or create an infrastructure to receive both national and foreign tourists since this was practically non-existent. Creating hotels, restaurants, cafes, training certified tour guides, among other actions, have led to one of the great problems they face: globalization. Although by itself it is not bad, its impact in many cases has been negative for heritage conservation. The entry into and contact with new cultures has led to the undervaluation of cultural traditions, their transformation and even their total loss. This work seeks to present specific cases of transformation and loss of cultural heritage, as well as to reflect on the problem and propose scenarios in which the negative effects can be reversed. For this text, 36 “Pueblos Mágicos” have been selected for study, based on those settlements that are cited in volumes I and IV (the first and last of the collection) of the series produced by the multidisciplinary group led by Carmen Valverde and Liliana López Levi (researchers from UNAM and UAM Xochimilco respectively) in the project supported by CONACyT entitled “Pueblos Mágicos. An interdisciplinary vision”, of which we are part. This sample is considered representative since it forms 30% of the total of 121 “Pueblos Mágicos” existing at that moment. With this information, the elements of its intangible heritage loss or transformation have been identified in every chapter based on the texts written by the participants of that project. Finally, this text shows an analysis of the effects that this federal program, as a public policy applied to 132 populations, has had on the conservation or transformation of the intangible cultural heritage of the “Pueblos Mágicos.” Transculturality, globalization, the creation of identities and the desire to increase the flow of tourists have impacted the changes that traditions (main intangible cultural heritage) have had in the 18 years that the federal program lasted.

Keywords: public policies, cultural tourism, heritage preservation, pueblos mágicos program

Procedia PDF Downloads 166