Search results for: implicit neural representations

Authors: Parsa Mahdavi, M. Amin Hariri-Ardebili

Abstract:

The development of accurate machine learning and deep learning models traditionally demands hands-on expertise and a solid background to fine-tune hyperparameters. With the continuous expansion of datasets in various scientific and engineering domains, researchers increasingly turn to machine learning methods to unveil hidden insights that may elude classic regression techniques. This surge in adoption raises concerns about the adequacy of the resultant meta-models and, consequently, the interpretation of the findings. In response to these challenges, automated machine learning (AutoML) emerges as a promising solution, aiming to construct machine learning models with minimal intervention or guidance from human experts. AutoML encompasses crucial stages such as data preparation, feature engineering, hyperparameter optimization, and neural architecture search. This paper provides a comprehensive overview of the principles underpinning AutoML, surveying several widely-used AutoML platforms. Additionally, the paper offers a glimpse into the application of AutoML on various engineering datasets. By comparing these results with those obtained through classical machine learning methods, the paper quantifies the uncertainties inherent in the application of a single ML model versus the holistic approach provided by AutoML. These examples showcase the efficacy of AutoML in extracting meaningful patterns and insights, emphasizing its potential to revolutionize the way we approach and analyze complex datasets.

Keywords: automated machine learning, uncertainty, engineering dataset, regression

Procedia PDF Downloads 40

Authors: Rebecca Lees, Deborah Anderson

Abstract:

Whilst the majority of research into social media in education focuses on the applications for teaching and learning environments, this study looks at how such activities can be managed by investigating the current state of social media regulation within UK higher education. Social media has pervaded almost all aspects of higher education; from marketing, recruitment and alumni relations to both distance and classroom-based learning and teaching activities. In terms of who uses it and how it is used, social media is growing at an unprecedented rate, particularly amongst the target market for higher education. Whilst the platform presents opportunities not found in more traditional methods of communication and interaction, such as speed and reach, it also carries substantial risks that come with inappropriate use, lack of control and issues of privacy. Typically, organisations rely on the concept of a social contract to guide employee behaviour to conform to the expectations of that organisation. Yet, where academia and social media intersect applying the notion of a social contract to enforce governance may be problematic; firstly considering the emphasis on treating students as customers with a growing focus on the use and collection of satisfaction metrics; and secondly regarding the notion of academic’s freedom of speech, opinion and discussion, which is a long-held tradition of learning instruction. Therefore the need for sound governance procedures to support expectations over online behaviour is vital, especially when the speed and breadth of adoption of social media activities has in the past outrun organisations’ abilities to manage it. An analysis of the current level of governance was conducted by gathering relevant policies, guidelines and best practice documentation available online via internet search and institutional requests. The documents were then subjected to a content analysis in the second phase of this study to determine the approach taken by institutions to apply such governance. Documentation was separated according to audience, i.e.: applicable to staff, students or all users. Given many of these included guests and visitors to the institution within their scope being easily accessible was considered important. Yet, within the UK only about half of all education institutions had explicit social media governance documentation available online without requiring member access or considerable searching. Where they existed, the majority focused solely on employee activities and tended to be policy based rather than rooted in guidelines or best practices, or held a fallback position of governing online behaviour via implicit instructions within IT and computer regulations. Explicit instructions over expected online behaviours is therefore lacking within UK HE. Given the number of educational practices that now include significant online components, it is imperative that education organisations keep up to date with the progress of social media use. Initial results from the second phase of this study which analyses the content of the governance documentation suggests they require reading levels at or above the target audience, with some considerable variability in length and layout. Further analysis will add to this growing field of investigating social media governance within higher education.

Keywords: governance, higher education, policy, social media

Procedia PDF Downloads 167

Authors: Krishang Surapaneni

Abstract:

The goal of this project is to determine how to predict important aspects of options, including the ask price. We want to compare different machine learning models to learn the best model and the best hyperparameters for that model for this purpose and data set. Option pricing is a relatively new field, and it can be very complicated and intimidating, especially to inexperienced people, so we want to create a machine learning model that can predict important aspects of an option stock, which can aid in future research. We tested multiple different models and experimented with hyperparameter tuning, trying to find some of the best parameters for a machine-learning model. We tested three different models: a Random Forest Regressor, a linear regressor, and an MLP (multi-layer perceptron) regressor. The most important feature in this experiment is the ask price; this is what we were trying to predict. In the field of stock pricing prediction, there is a large potential for error, so we are unable to determine the accuracy of the models based on if they predict the pricing perfectly. Due to this factor, we determined the accuracy of the model by finding the average percentage difference between the predicted and actual values. We tested the accuracy of the machine learning models by comparing the actual results in the testing data and the predictions made by the models. The linear regression model performed worst, with an average percentage error of 17.46%. The MLP regressor had an average percentage error of 11.45%, and the random forest regressor had an average percentage error of 7.42%

Keywords: finance, linear regression model, machine learning model, neural network, stock price

Procedia PDF Downloads 60

Authors: Reza Mohammadzadeh

Abstract:

The major challenges in geotechnical engineering in underground spaces arise from uncertainties and different probabilities. The collection, collation, and collaboration of existing data to incorporate them in analysis and design for given prospect evaluation would be a reliable, practical problem solving method under uncertainty. Machine learning (ML) is a subfield of artificial intelligence in statistical science which applies different techniques (e.g., Regression, neural networks, support vector machines, decision trees, random forests, genetic programming, etc.) on data to automatically learn and improve from them without being explicitly programmed and make decisions and predictions. In this paper, a conceptual database schema of geotechnical risks in underground coal mining based on a cloud system architecture has been designed. A new approach of risk assessment using a three-dimensional risk matrix supported by the level of knowledge (LoK) has been proposed in this model. Subsequently, the model workflow methodology stages have been described. In order to train data and LoK models deployment, an ML platform has been implemented. IBM Watson Studio, as a leading data science tool and data-driven cloud integration ML platform, is employed in this study. As a Use case, a data set of geotechnical hazards and risk assessment in underground coal mining were prepared to demonstrate the performance of the model, and accordingly, the results have been outlined.

Keywords: data model, geotechnical risks, machine learning, underground coal mining

Procedia PDF Downloads 249

Authors: B. Lokuketagoda, M. Weerakoon, U. Madushan, A. N. Senaratne, K. Y. Abeywardena

Abstract:

Ransomware has become a common threat in past few years and the recent threat reports show an increase of growth in Ransomware infections. Researchers have identified different variants of Ransomware families since 2015. Lack of knowledge of the user about the threat is a major concern. Ransomware detection methodologies are still growing through the industry. Email is the easiest method to send Ransomware to its victims. Uninformed users tend to click on links and attachments without much consideration assuming the emails are genuine. As a solution to this in this paper R-Killer Ransomware detection tool is introduced. Tool can be integrated with existing email services. The core detection Engine (CDE) discussed in the paper focuses on separating suspicious samples from emails and handling them until a decision is made regarding the suspicious mail. It has the capability of preventing execution of identified ransomware processes. On the other hand, Sandboxing and URL analyzing system has the capability of communication with public threat intelligence services to gather known threat intelligence. The R-Killer has its own mechanism developed in its Proactive Monitoring System (PMS) which can monitor the processes created by downloaded email attachments and identify potential Ransomware activities. R-killer is capable of gathering threat intelligence without exposing the user’s data to public threat intelligence services, hence protecting the confidentiality of user data.

Keywords: ransomware, deep learning, recurrent neural networks, email, core detection engine

Procedia PDF Downloads 184

Authors: Vishnu Asokan, Zaid M. Paloba

Abstract:

Flow over cavities is an important area of research due to the significant change in flow physics caused by cavity aspect ratio, free stream Mach number and the nature of upstream boundary layer approaching the cavity leading edge. Cavity flow finds application in aircraft wheel well, weapons bay, combustion chamber of scramjet engines, etc. These flows are highly unsteady, compressible and turbulent and it involves mass entrainment coupled with acoustics phenomenon. Variation of flow dynamics in an angled cavity with a heated and cooled pylon upstream to the cavity with spatial combinations of heat flux addition and removal to the wall studied numerically. The goal of study is to investigate the effect of energy addition, removal to the cavity walls and pylon cavity flow dynamics. Preliminary steady state numerical simulations on inclined cavities with heat addition have shown that wall pressure profiles, as well as the recirculation, are influenced by heat transfer to the compressible fluid medium. Such a hybrid control of cavity flow dynamics in the form of heat transfer and pylon geometry can open out greater opportunities in enhancement of mixing and flame holding requirements of supersonic combustors. Addition of pylon upstream to the cavity reduces the acoustic oscillations emanating from the geometry. A numerical unsteady analysis of supersonic flow past cavities exposed to cavity wall heating and cooling with heated and cooled pylon helps to get a clear idea about the oscillation suppression in the cavity. A Cavity of L/D 4 and aft wall angle 22 degree with an upstream pylon of h/D=1.5 mm with a wall angle 29 degree exposed to supersonic flow of Mach number 2 and heat flux of 40 W/cm² and -40 W/cm² modeled for the above study. In the preliminary study, the domain is modeled and validated numerically with a turbulence model of SST k-ω using an HLLC implicit scheme. Both qualitative and quantitative flow data extracted and analyzed using advanced CFD tools. Flow visualization is done using numerical Schlieren method as the fluid medium gives the density variation. The heat flux addition to the wall increases the secondary vortex size of the cavity and removal of energy leads to the reduction in vortex size. The flow field turbulence seems to be increasing at higher heat flux. The shear layer thickness increases as heat flux increases. The steady state analysis of wall pressure shows that there is variation on wall pressure as heat flux increases. Shift in frequency of unsteady wall pressure analysis is an interesting observation for the above study. The time averaged skin friction seems to be reducing at higher heat flux due to the variation in viscosity of fluid inside the cavity.

Keywords: energy addition, frequency shift, Numerical Schlieren, shear layer, vortex evolution

Procedia PDF Downloads 127

Authors: Isaiah Ifeanyichukwu Agbo

Abstract:

Human speech is capable of serving many purposes. Power and control are not always exercised overtly by linguistic acts, but maybe enacted and exercised in the myriad of taken-for-granted actions of everyday life. Domination, power control, discrimination and mind control exist in human speech and may lead to asymmetrical power relations. In discourse, there are persuasive and manipulative linguistic acts that serve to establish solidarity and identification with the 'we group' and polarize with the 'they group'. Political discourse is crafted to defend and promote the problematic narrative of outright controversial events in a nation’s history thereby sustaining domination, marginalization, manipulation, inequalities and injustices, often without the dominated and marginalized group being aware of them. They are designed and positioned to serve the political and social needs of the producers. Political crisis speeches in Nigeria, just like in other countries concentrate on positive self-image, de-legitimization of political opponents, reframing accusation to one’s advantage, redefining problematic terms and adopting reversal strategy. In most cases, the people are ignorant of the hidden ideological positions encoded in the text. Few researches have been conducted adopting the frameworks of critical discourse analysis and systemic functional linguistics to investigate this situation in the political crisis speeches in Nigeria. In this paper, we focus attention on the analyses of the linguistic, semantic, and ideological elements in selected political crisis speeches in Nigeria to investigate if they create and sustain unequal power relations and manipulative tendencies from the perspectives of Critical Discourse Analysis (CDA) and Systemic Functional Linguistics (SFL). Critical Discourse Analysis unpacks both opaque and transparent structural relationships of power dominance, power relations and control as manifested in language. Critical discourse analysis emerged from a critical theory of language study which sees the use of language as a form of social practice where social relations are reproduced or contested and different interests are served. Systemic function linguistics relates the structure of texts to their function. Fairclough’s model of CDA and Halliday’s systemic functional approach to language study are adopted in this paper. This paper probes into language use that perpetuates inequalities. This study demystifies the hidden implicature of the selected political crisis speeches and reveals the existence of information that is not made explicit in what the political actors actually say. The analysis further reveals the ideological configurations present in the texts. These ideological standpoints are the basis for naturalizing implicit ideologies and hegemonic influence in the texts. The analyses of the texts further uncovered the linguistic and discursive strategies deployed by text producers to manipulate the unsuspecting members of the public both mentally and conceptually in order to enact, sustain and maintain unhealthy power relations at crisis times in the Nigerian political history.

Keywords: critical discourse analysis, language, political crisis, power relations, systemic functional linguistics

Procedia PDF Downloads 315

Authors: Kun Xu, Yuan Xu, Jia Qiao

Abstract:

The document detection plays an important role in optical character recognition and text analysis. Because the traditional detection methods have weak generalization ability, and deep neural network has complex structure and large number of parameters, which cannot be well applied in mobile devices, this paper proposes a lightweight Document Corner Detection Network (DCDNet). DCDNet is a two-stage architecture. The first stage with Encoder-Decoder structure adopts depthwise separable convolution to greatly reduce the network parameters. After introducing the Feature Attention Union (FAU) module, the second stage enhances the feature information of spatial and channel dim and adaptively adjusts the size of receptive field to enhance the feature expression ability of the model. Aiming at solving the problem of the large difference in the number of pixel distribution between corner and non-corner, Weighted Binary Cross Entropy Loss (WBCE Loss) is proposed to define corner detection problem as a classification problem to make the training process more efficient. In order to make up for the lack of Dataset of document corner detection, a Dataset containing 6620 images named Document Corner Detection Dataset (DCDD) is made. Experimental results show that the proposed method can obtain fast, stable and accurate detection results on DCDD.

Keywords: document detection, corner detection, attention mechanism, lightweight

Procedia PDF Downloads 332

Authors: Laura M. F. Bertens

Abstract:

There is a long tradition of visually representing the art historical canon, in schematic overviews and diagrams. This is indicative of the desire for scientific, ‘objective’ knowledge of the kind (seemingly) produced in the natural sciences. These diagrams will, however, always retain an element of subjectivity and the modelling methods colour our perception of the represented information. In recent decades visualisations of art historical data, such as hand-drawn diagrams in textbooks, have been extended to include digital, computational tools. These tools significantly increase modelling strength and functionality. As such, they might be used to deconstruct and amend the very problem caused by traditional visualisations of the canon. In this paper, the use of digital tools for modelling the art historical canon is studied, in order to draw attention to the artificial nature of the static models that art historians are presented with in textbooks and lectures, as well as to explore the potential of digital, dynamic tools in creating new models. To study the way diagrams of the canon mediate the represented information, two modelling methods have been used on two case studies of existing diagrams. The tree diagram Stammbaum der neudeutschen Kunst (1823) by Ferdinand Olivier has been translated to a social network using the program Visone, and the famous flow chart Cubism and Abstract Art (1936) by Alfred Barr has been translated to an ontological model using Protégé Ontology Editor. The implications of the modelling decisions have been analysed in an art historical context. The aim of this project has been twofold. On the one hand the translation process makes explicit the design choices in the original diagrams, which reflect hidden assumptions about the Western canon. Ways of organizing data (for instance ordering art according to artist) have come to feel natural and neutral and implicit biases and the historically uneven distribution of power have resulted in underrepresentation of groups of artists. Over the last decades, scholars from fields such as Feminist Studies, Postcolonial Studies and Gender Studies have considered this problem and tried to remedy it. The translation presented here adds to this deconstruction by defamiliarizing the traditional models and analysing the process of reconstructing new models, step by step, taking into account theoretical critiques of the canon, such as the feminist perspective discussed by Griselda Pollock, amongst others. On the other hand, the project has served as a pilot study for the use of digital modelling tools in creating dynamic visualisations of the canon for education and museum purposes. Dynamic computer models introduce functionalities that allow new ways of ordering and visualising the artworks in the canon. As such, they could form a powerful tool in the training of new art historians, introducing a broader and more diverse view on the traditional canon. Although modelling will always imply a simplification and therefore a distortion of reality, new modelling techniques can help us get a better sense of the limitations of earlier models and can provide new perspectives on already established knowledge.

Keywords: canon, ontological modelling, Protege Ontology Editor, social network modelling, Visone

Procedia PDF Downloads 106

Authors: Sudipta Garai

Abstract:

Films as a cultural, social practice remains a dominant space for creation and destruction of ideologies and practices which make the sociological viewing, analysis, and interpretation of the same a complex affair. It remains the doorway between the interpretations and understanding of the writer/director and the reader/viewer. India, being a multi-linguistic culture, the media plays a much intriguing role than that of newspaper, books, stories, novels or any other medium of expression. Known to be the largest democracy, the State seem to guarantee and safeguard people’s choices and life of dignity through its Fundamental Rights and Directives. However, the laws contradict themselves when it comes to IPC 377 criminalizing anything except penovaginal sexual intercourse restricting alternative sexual preferences and practices questioning its sense of ‘democracy.' In this context, the issue of homosexuality came up in bits and pieces through various representations in ‘popular’ cinema mostly with sudden references of mockery and laughter where the explicit narratives of ‘queer’ seemed missing. Rituparno Ghosh, an eminent film maker of Bengal, came up as the ‘queer’ face in Kolkata specifically through his ‘queer’ trilogy (Memories in March, 2010; Arekti Premer Golpo, 2010; Chitrangada: A Crowning Wish, 2012) coming out of his own closet and speaking about his own sexual choices not only through the explicit narratives in films but also in person which made these films an important point of departure in Bengali film history. A sociological reading of these films through a discourse analysis is being done with the critical questions of ‘choice,' ’freedom,' ‘love and marriage’ and most importantly the ‘change.' This study not only focuses on the films and its analysis of content but also to engage with its audience, queer and not in order to extend beyond the art form into the actual vulnerabilities of life and experiences through informal interviews, focused group discussions and engaging with the real life narratives. A research of this kind is always looked upon as a medium of change hoping for a better world wiping away the discrimination and ‘shame’ the ‘queer’ faces in their everyday life, but a social science research is limited but its ‘time’ and academic boundary where the hope of change might be initiated but not fulfilled. The experiences and reflections of the ‘queer’ not only redefined the narratives of the films but also me as a researcher. The perspectives of the ‘hetero-normative’ informants gave a broader picture of the study and the socio-cultural complications that are intrigued with the ideas of resistance and change. The issues on subjectivity, power, and position couldn’t be wiped out in a study of this kind as both politics and aesthetics become integrated with each other in the creation of any art form be it films or a study of research.

Keywords: cinema, alternative sexualities, narratives, sexual choices, state and society

Procedia PDF Downloads 340

Authors: Jiahui You, Kyung Jae Lee

Abstract:

Hydraulic fracturing fluid (HFF) is widely used in shale reservoir productions. HFF contains diverse chemical additives, which result in the dissolution and precipitation of minerals through multiple chemical reactions. In this study, a new pore-scale Darcy–Brinkman–Stokes (DBS) model coupled with Level Set Method (LSM) is developed to address the microscopic phenomena occurring during the iron–HFF interaction, by numerically describing mass transport, chemical reactions, and pore structure evolution. The new model is developed based on OpenFOAM, which is an open-source platform for computational fluid dynamics. Here, the DBS momentum equation is used to solve for velocity by accounting for the fluid-solid mass transfer; an advection-diffusion equation is used to compute the distribution of injected HFF and iron. The reaction–induced pore evolution is captured by applying the LSM, where the solid-liquid interface is updated by solving the level set distance function and reinitialized to a signed distance function. Then, a smoothened Heaviside function gives a smoothed solid-liquid interface over a narrow band with a fixed thickness. The stated equations are discretized by the finite volume method, while the re-initialized equation is discretized by the central difference method. Gauss linear upwind scheme is used to solve the level set distance function, and the Pressure–Implicit with Splitting of Operators (PISO) method is used to solve the momentum equation. The numerical result is compared with 1–D analytical solution of fluid-solid interface for reaction-diffusion problems. Sensitivity analysis is conducted with various Damkohler number (DaII) and Peclet number (Pe). We categorize the Fe (III) precipitation into three patterns as a function of DaII and Pe: symmetrical smoothed growth, unsymmetrical growth, and dendritic growth. Pe and DaII significantly affect the location of precipitation, which is critical in determining the injection parameters of hydraulic fracturing. When DaII<1, the precipitation uniformly occurs on the solid surface both in upstream and downstream directions. When DaII>1, the precipitation mainly occurs on the solid surface in an upstream direction. When Pe>1, Fe (II) transported deeply into and precipitated inside the pores. When Pe<1, the precipitation of Fe (III) occurs mainly on the solid surface in an upstream direction, and they are easily precipitated inside the small pore structures. The porosity–permeability relationship is subsequently presented. This pore-scale model allows high confidence in the description of Fe (II) dissolution, transport, and Fe (III) precipitation. The model shows fast convergence and requires a low computational load. The results can provide reliable guidance for injecting HFF in shale reservoirs to avoid clogging and wellbore pollution. Understanding Fe (III) precipitation, and Fe (II) release and transport behaviors give rise to a highly efficient hydraulic fracture project.

Keywords: reactive-transport , Shale, Kerogen, precipitation

Procedia PDF Downloads 149

Authors: Alena Radina

Abstract:

On the global stage, national image is shaped by historical memory of wars and alliances, government ideology and particularly media stereotypes which represent countries in positive or negative ways. News magazine covers are a key site for national representation. The object of analysis in this paper is the portrayals of the US, Germany, China, and Russia in the front pages and cover stories of “Time”, “Der Spiegel”, “Beijing Review”, and “Expert”. Political comedy helps people learn about current affairs even if politics is not their area of interest, and thus satire indirectly sets the public agenda. Coupled with satirical messages, cover images and the linguistic messages embedded in the covers become persuasive visual and verbal factors, known to drive about 80% of magazine sales. Preliminary analysis identified satirical elements in magazine covers, which are known to influence and frame understandings and attract younger audiences. Multimodal and transnational comparative framing analyses lay the groundwork to investigate why journalists, editors and designers deploy certain frames rather than others. This research investigates to what degree frames used in covers correlate with frames within the cover stories and what these framings can tell us about media professionals’ representations of their own and other nations. The study sample includes 32 covers consisting of two covers representing each of the four chosen countries from the four magazines. The sampling framework considers two time periods to compare countries’ representation with two different presidents, and between men and women when present. The countries selected for analysis represent each category of the international news flows model: the core nations are the US and Germany; China is a semi-peripheral country; and Russia is peripheral. Examining textual and visual design elements on the covers and images in the cover stories reveals not only what editors believe visually attracts the reader’s attention to the magazine but also how the magazines frame and construct national images and national leaders. The cover is the most powerful editorial and design page in a magazine because images incorporate less intrusive framing tools. Thus, covers require less cognitive effort of audiences who may therefore be more likely to accept the visual frame without question. Analysis of design and linguistic elements in magazine covers helps to understand how media outlets shape their audience’s perceptions and how magazines frame global issues. While previous multimodal research of covers has focused mostly on lifestyle magazines or newspapers, this paper examines the power of current affairs magazines’ covers to shape audience perception of national image.

Keywords: framing analysis, magazine covers, multimodality, national image, satire

Procedia PDF Downloads 80

Authors: David Percy

Abstract:

Landslides are a geologic phenomenon that affects a large number of inhabited places and are constantly being monitored and studied for the prediction of future occurrences. Reconstructability analysis (RA) is a methodology for extracting informative models from large volumes of data that work exclusively with discrete data. While RA has been used in medical applications and social science extensively, we are introducing it to the spatial sciences through applications like landslide prediction. Since RA works exclusively with discrete data, such as soil classification or bedrock type, working with continuous data, such as porosity, requires that these data are binned for inclusion in the model. RA constructs models of the data which pick out the most informative elements, independent variables (IVs), from each layer that predict the dependent variable (DV), landslide occurrence. Each layer included in the model retains its classification data as a primary encoding of the data. Unlike other machine learning algorithms that force the data into one-hot encoding type of schemes, RA works directly with the data as it is encoded, with the exception of continuous data, which must be binned. The usual physical and derived layers are included in the model, and testing our results against other published methodologies, such as neural networks, yields accuracy that is similar but with the advantage of a completely transparent model. The results of an RA session with a data set are a report on every combination of variables and their probability of landslide events occurring. In this way, every combination of informative state combinations can be examined.

Keywords: reconstructability analysis, machine learning, landslides, raster analysis

Procedia PDF Downloads 46

Authors: Farshid Hajati, Federico Girosi, Shima Ghassempour

Abstract:

We present a Deep Belief Network (DBN) method for clustering health trajectories. Deep Belief Network (DBN) is a deep architecture that consists of a stack of Restricted Boltzmann Machines (RBM). In a deep architecture, each layer learns more complex features than the past layers. The proposed method depends on DBN in clustering without using back propagation learning algorithm. The proposed DBN has a better a performance compared to the deep neural network due the initialization of the connecting weights. We use Contrastive Divergence (CD) method for training the RBMs which increases the performance of the network. The performance of the proposed method is evaluated extensively on the Health and Retirement Study (HRS) database. The University of Michigan Health and Retirement Study (HRS) is a nationally representative longitudinal study that has surveyed more than 27,000 elderly and near-elderly Americans since its inception in 1992. Participants are interviewed every two years and they collect data on physical and mental health, insurance coverage, financial status, family support systems, labor market status, and retirement planning. The dataset is publicly available and we use the RAND HRS version L, which is easy to use and cleaned up version of the data. The size of sample data set is 268 and the length of the trajectories is equal to 10. The trajectories do not stop when the patient dies and represent 10 different interviews of live patients. Compared to the state-of-the-art benchmarks, the experimental results show the effectiveness and superiority of the proposed method in clustering health trajectories.

Keywords: health trajectory, clustering, deep learning, DBN

Procedia PDF Downloads 347

Authors: R. Mofeed, N. Elgendy

Abstract:

Cinema constructs mind-spaces that reflect inherent human thoughts and emotions. As a representational art, Cinema would introduce comprehensive images of life phenomena in different ways. The term “represent” suggests verity of meanings; bring into presence, replace or typify. In that sense, Cinema may present a phenomenon through direct embodiment, or introduce a substitute image that replaces the original phenomena, or typify it by relating the produced image to a more general category through a process of abstraction. This research is interested in questioning the type of images that Egyptian Cinema introduces to informal urbanism and how these images were conditioned and reshaped in the last twenty years. The informalities/slums phenomenon first appeared in Egypt and, particularly, Cairo in the early sixties, however, this phenomenon was completely ignored by the state and society until the eighties, and furthermore, its evident representation in Cinema was by the mid-nineties. The Informal City represents the illegal housing developments, and it is a fast growing form of urbanization in Cairo. Yet, this expanding phenomenon is still depicted as the minority, exceptional and marginal through the Cinematic lenses. This paper aims at tracing the forms of representations of the urban informalities in the Egyptian Cinema between 1994 and 2014, and how did that affect the popular mind and its perception of these areas. The paper runs two main lines of inquiry; the first traces the phenomena through a chronological and geographical mapping of the informal urbanism has been portrayed in films. This analysis is based on an academic research work at Cairo University in Fall 2014. The visual tracing through maps and timelines allowed a reading of the phases of ignorance, presence, typifying and repetition in the representation of this huge sector of the city through more than 50 films that has been investigated. The analysis clearly revealed the “portrayed image” of informality by the Cinema through the examined period. However, the second part of the paper explores the “perceived image”. A designed questionnaire is applied to highlight the main features of that image that is perceived by both inhabitants of informalities and other Cairenes based on watching selected films. The questionnaire covers the different images of informalities proposed in the Cinema whether in a comic or a melodramatic background and highlight the descriptive terms used, to see which of them resonate with the mass perceptions and affected their mental images. The two images; “portrayed” and “perceived” are then to be encountered to reflect on issues of repetitions, stereotyping and reality. The formulated stereotype of informal urbanism is finally outlined and justified in relation to both production consumption mechanisms of films and the State official vision of informalities.

Keywords: cinema, informal urbanism, popular mind, representation

Procedia PDF Downloads 277

Authors: Yeliz Karaca, Carlo Cattani

Abstract:

This study focuses on the local Holder exponent as a measure of the function regularity for time series related to finance data. In this study, the attributes of the finance dataset belonging to 13 countries (India, China, Japan, Sweden, France, Germany, Italy, Australia, Mexico, United Kingdom, Argentina, Brazil, USA) located in 5 different continents (Asia, Europe, Australia, North America and South America) have been examined.These countries are the ones mostly affected by the attributes with regard to financial development, covering a period from 2012 to 2017. Our study is concerned with the most important attributes that have impact on the development of finance for the countries identified. Our method is comprised of the following stages: (a) among the multi fractal methods and Brownian motion Holder regularity functions (polynomial, exponential), significant and self-similar attributes have been identified (b) The significant and self-similar attributes have been applied to the Artificial Neuronal Network (ANN) algorithms (Feed Forward Back Propagation (FFBP) and Cascade Forward Back Propagation (CFBP)) (c) the outcomes of classification accuracy have been compared concerning the attributes that have impact on the attributes which affect the countries’ financial development. This study has enabled to reveal, through the application of ANN algorithms, how the most significant attributes are identified within the relevant dataset via the Holder functions (polynomial and exponential function).

Keywords: artificial neural networks, finance data, Holder regularity, multifractals

Procedia PDF Downloads 225

Authors: S. Abera, T. Gidey, W. Terefe

Abstract:

Introduction: Testing for HIV is the key entry point to HIV prevention, treatment, and care and support services. Hence, predictive data mining techniques can greatly benefit to analyze and discover new patterns from huge datasets like that of EDHS 2011 data. Objectives: The objective of this study is to build a predictive modeling for HIV testing and identify determinants of HIV testing for adults with age above fourteen years using data mining techniques. Methods: Cross-Industry Standard Process for Data Mining (CRISP-DM) was used to predict the model for HIV testing and explore association rules between HIV testing and the selected attributes among adult Ethiopians. Decision tree, Naïve-Bayes, logistic regression and artificial neural networks of data mining techniques were used to build the predictive models. Results: The target dataset contained 30,625 study participants; of which 16, 515 (53.9%) were women. Nearly two-fifth; 17,719 (58%), have never been tested for HIV while the rest 12,906 (42%) had been tested. Ethiopians with higher wealth index, higher educational level, belonging 20 to 29 years old, having no stigmatizing attitude towards HIV positive person, urban residents, having HIV related knowledge, information about family planning on mass media and knowing a place where to get testing for HIV showed an increased patterns with respect to HIV testing. Conclusion and Recommendation: Public health interventions should consider the identified determinants to promote people to get testing for HIV.

Keywords: data mining, HIV, testing, ethiopia

Procedia PDF Downloads 470

Authors: Pawel Martynowicz

Abstract:

Vibrations are a crucial problem for slender structures such as towers, masts, chimneys, wind turbines, bridges, high buildings, etc., that is why most of them are equipped with vibration attenuation or fatigue reduction solutions. In this work, a slender structure (i.e., wind turbine tower-nacelle model) equipped with nonlinear, semiactive tuned vibration absorber(s) is analyzed. For this study purposes, magnetorheological (MR) dampers are used as semiactive actuators. Several optimal-based approaches to structural vibration attenuation are investigated against the standard ‘ground-hook’ law and passive tuned vibration absorber(s) implementations. The common approach to optimal control of nonlinear systems is offline computation of the optimal solution, however, so determined open loop control suffers from lack of robustness to uncertainties (e.g., unmodelled dynamics, perturbations of external forces or initial conditions), and thus perturbation control techniques are often used. However, proper linearization may be an issue for highly nonlinear systems with implicit relations between state, co-state, and control. The main contribution of the author is the development as well as numerical and experimental verification of the Pontriagin maximum-principle-based vibration control concepts that produce directly actuator control input (not the demanded force), thus force tracking algorithm that results in control inaccuracy is entirely omitted. These concepts, including one-step optimal control, quasi-optimal control, and optimal-based modified ‘ground-hook’ law, can be directly implemented in online and real-time feedback control for periodic (or semi-periodic) disturbances with invariant or time-varying parameters, as well as for non-periodic, transient or random disturbances, what is a limitation for some other known solutions. No offline calculation, excitations/disturbances assumption or vibration frequency determination is necessary, moreover, all of the nonlinear actuator (MR damper) force constraints, i.e., no active forces, lower and upper saturation limits, hysteresis-type dynamics, etc., are embedded in the control technique, thus the solution is optimal or suboptimal for the assumed actuator, respecting its limitations. Depending on the selected method variant, a moderate or decisive reduction in the computational load is possible compared to other methods of nonlinear optimal control, while assuring the quality and robustness of the vibration reduction system, as well as considering multi-pronged operational aspects, such as possible minimization of the amplitude of the deflection and acceleration of the vibrating structure, its potential and/or kinetic energy, required actuator force, control input (e.g. electric current in the MR damper coil) and/or stroke amplitude. The developed solutions are characterized by high vibration reduction efficiency – the obtained maximum values of the dynamic amplification factor are close to 2.0, while for the best of the passive systems, these values exceed 3.5.

Keywords: magnetorheological damper, nonlinear tuned vibration absorber, optimal control, real-time structural vibration attenuation, wind turbines

Procedia PDF Downloads 106

Authors: Halefom Kidane

Abstract:

This study aims to assess the wind resource potential and characterize the urban area wind patterns in Hawassa City, Ethiopia. The estimation and characterization of wind resources are crucial for sustainable urban planning, renewable energy development, and climate change mitigation strategies. A secondary data collection method was used to carry out the study. The collected data at 2 meters was analyzed statistically and extrapolated to the standard heights of 10-meter and 30-meter heights using the power law equation. The standard deviation method was used to calculate the value of scale and shape factors. From the analysis presented, the maximum and minimum mean daily wind speed at 2 meters in 2016 was 1.33 m/s and 0.05 m/s in 2017, 1.67 m/s and 0.14 m/s in 2018, 1.61m and 0.07 m/s, respectively. The maximum monthly average wind speed of Hawassa City in 2016 at 2 meters was noticed in the month of December, which is around 0.78 m/s, while in 2017, the maximum wind speed was recorded in the month of January with a wind speed magnitude of 0.80 m/s and in 2018 June was maximum speed which is 0.76 m/s. On the other hand, October was the month with the minimum mean wind speed in all years, with a value of 0.47 m/s in 2016,0.47 in 2017 and 0.34 in 2018. The annual mean wind speed was 0.61 m/s in 2016,0.64, m/s in 2017 and 0.57 m/s in 2018 at a height of 2 meters. From extrapolation, the annual mean wind speeds for the years 2016,2017 and 2018 at 10 heights were 1.17 m/s,1.22 m/s, and 1.11 m/s, and at the height of 30 meters, were 3.34m/s,3.78 m/s, and 3.01 m/s respectively/Thus, the site consists mainly primarily classes-I of wind speed even at the extrapolated heights.

Keywords: artificial neural networks, forecasting, min-max normalization, wind speed

Procedia PDF Downloads 49

Authors: Georgia Kremmyda, Angelos Georgoulas, Yiannis Koumpouros, James T. Mottram

Abstract:

There is a growing interest in enhancing the creativity and problem-solving ability of engineering students by expanding their engagement to complex, interdisciplinary problems such as environmental issues, resilience to man-made and natural disasters, global health matters, water needs, increased energy demands, and other global humanitarian challenges. Tackling societal challenges requires knowledgeable and erudite engineers who can handle, combine, transform and create innovative, affordable and sustainable solutions. This view simultaneously complements and challenges current conceptions of an emerging educational movement that, almost without exception, are underpinned by calls for competitive economic growth and technological development. This article reveals a taxonomy of humanitarian attributes to be enabled to professional engineers, through reformed curricula and innovative pedagogies, which once implemented and integrated efficiently in higher engineering education, they will provide students and educators with opportunities to explore interdependencies and connections between resources, sustainable design, societal needs, and the natural environment and to critically engage with implicit and explicit facets of disciplinary identity. The research involves carrying out a study on (a) current practices, best practices and barriers in knowledge organisation, content, and hierarchy in graduate engineering programmes, (b) best practices associated with teaching and research in engineering education around the world, (c) opportunities inherent in general reforms of graduate engineering education and inherent in integrating the humanitarian context throughout engineering education programmes, and, (d) an overarching taxonomy of professional attributes for tackling humanitarian challenges. Research methods involve state-of-the-art literature review on engineering education and pedagogy to resource thematic findings on current status in engineering education worldwide, and qualitative research through three practice dialogue workshops, run in Asia (Vietnam, Indonesia and Bangladesh) involving a variety of national, international and local stakeholders (industries; NGOs, governmental organisations). Findings from this study provide evidence on: (a) what are the professional engineering attributes (skills, experience, knowledge) needed for tackling humanitarian challenges; (b) how we can integrate other disciplines and professions to engineering while defining the professional attributes of engineers who are capable of tackling humanitarian challenges. The attributes will be linked to those discipline(s) and profession(s) that are more likely to enforce the attributes (removing the assumption that engineering education as it stands at the moment can provide all attributes), and; (c) how these attributes shall be supplied; what kind of pedagogies or training shall take place beyond current practices. Acknowledgment: The study is currently in progress and is being undertaken in the framework of the project ENHANCE - ENabling Humanitarian Attributes for Nurturing Community-based Engineering (project No: 598502-EEP-1-2018-1-UK-EPPKA2-CBHE-JP (2018-2582/001-001), funded by the Erasmus + KA2 Cooperation for innovation and the exchange of good practices – Capacity building in the field of Higher Education.

Keywords: professional engineering attributes, engineering education, taxonomy, humanitarian challenges, humanitarian engineering

Procedia PDF Downloads 163

Authors: Ulysse Lecomte, Maryline Thenot

Abstract:

For a long time, disabled people lived in isolation within the family environment, with little interaction with the outside world and a high risk of social exclusion. However, in a number of countries, progress has been made thanks to changes in legislation on the social integration of disabled people, a significant change in attitudes and the development of CSR. But the problem of their social, economic and professional exclusion persists and has been further exacerbated by the COVID-19 pandemic. This societal phenomenon is sufficiently important to be the subject of management science research. We have therefore focused our work on society's current perception of people with disabilities and their possible integration. Our aim is to find out what levers could be put in place to bring about positive change in the situation. We have chosen to focus on the perception of young people in France, who are the new generation responsible for the future of our society and from whom tomorrow's decision-makers, future employers and stakeholders who can influence the living conditions of disabled people will be drawn. Our study sample corresponds to the 18-30 age group, which is the population of young adults likely to have sufficient experience and maturity. The aim of this study is not only to find out how this population currently perceives disability but also to identify the factors influencing this perception and the most effective levers for action to act positively on this phenomenon and thus promote better social integration of people with disabilities in the future. The methodology is based on theoretical and empirical research. The literature review includes a historical and etymological approach to disability, a definition of the different concepts of disability, an approach to disability as a vector of social exclusion and the role of perception and representations in defining the social image of disability. This literature review is followed by an empirical part carried out by means of a questionnaire administered to 110 young people aged 18 to 30. Analysis of our results suggests that, despite a recent improvement, disabled people are still perceived as vulnerable and socially marginalized. The following factors stand out as having a significant influence (positive or negative) on the perception of disability: the individual's familiarity with the 'world of disability', cultural factors, the degree of 'visibility' of the disability and the empathy level of the disabled person him/herself. Others, on the other hand, such as socio-political and economic factors, have little impact on this perception. In addition, it is possible to classify the various levers of action likely to improve the social perception of disability according to their degree of effectiveness. Our study population prioritized training initiatives for the various players and stakeholders (teachers, students, disabled people themselves, companies, sports clubs, etc.). This was followed by communication, e-communication and media campaigns in favour of disability. Lastly, the sample was judged as 'less effective' positive discrimination actions such as setting a minimum percentage for the representation of disabled people in various fields (studies, employment, politics ...).

Keywords: disability, perception, social image, young people, influencing factors, levers for action

Procedia PDF Downloads 16

Authors: Yulia V. Krasavtseva, Tatiana V. Kornilova

Abstract:

Risk-taking behaviors are not only dictated by cognitive components but also involve emotional aspects. Anticipatory emotions, involving both cognitive and affective mechanisms, are involved in decision-making in general, and risk-taking in particular. Affective reactions are prompted when an expectation or prediction is either validated or invalidated in the achieved result. This study aimed to combine predictions, anticipatory emotions, affective reactions, and personality traits in the context of risk-taking behaviors. An experimental online method Emotion and Prediction In a Casino (EPIC) was used, based on a casino-like roulette game. In a series of choices, the participant is presented with progressively riskier roulette combinations, where the potential sums of wins and losses increase with each choice and the participant is given a choice: to 'walk away' with the current sum of money or to 'play' the displayed roulette, thus accepting the implicit risk. Before and after the result is displayed, participants also rate their emotions, using the Self-Assessment Mannequin [Bradley, Lang, 1994], picking a picture, representing the intensity of pleasure, arousal, and dominance. The following personality measures were used: 1) Personal Decision-Making Factors [Kornilova, 2003] assessing risk and rationality; 2) I7 – Impulsivity Questionnaire [Kornilova, 1995] assessing impulsiveness, risk readiness, and empathy and 3) Subjective Risk Intelligence Scale [Craparo et al., 2018] assessing negative attitude toward uncertainty, emotional stress vulnerability, imaginative capability, and problem-solving self-efficacy. Two groups of participants took part in the study: 1) 98 university students (Mage=19.71, SD=3.25; 72% female) and 2) 94 online participants (Mage=28.25, SD=8.25; 89% female). Online participants were recruited via social media. Students with high rationality rated their pleasure and dominance before and after choices as lower (ρ from -2.6 to -2.7, p < 0.05). Those with high levels of impulsivity rated their arousal lower before finding out their result (ρ from 2.5 - 3.7, p < 0.05), while also rating their dominance as low (ρ from -3 to -3.7, p < 0.05). Students prone to risk-rated their pleasure and arousal before and after higher (ρ from 2.5 - 3.6, p < 0.05). High empathy was positively correlated with arousal after learning the result. High emotional stress vulnerability positively correlates with arousal and pleasure after the choice (ρ from 3.9 - 5.7, p < 0.05). Negative attitude to uncertainty is correlated with high anticipatory and reactive arousal (ρ from 2.7 - 5.7, p < 0.05). High imaginative capability correlates negatively with anticipatory and reactive dominance (ρ from - 3.4 to - 4.3, p < 0.05). Pleasure (.492), arousal (.590), and dominance (.551) before and after the result were positively correlated. Higher predictions positively correlated with reactive pleasure and arousal. In a riskier scenario (6/8 chances to win), anticipatory arousal was negatively correlated with the pleasure emotion (-.326) and vice versa (-.265). Correlations occur regardless of the roulette outcome. In conclusion, risk-taking behaviors are linked not only to personality traits but also to anticipatory emotions and affect in a modeled casino setting. Acknowledgment: The study was supported by the Russian Foundation for Basic Research, project 19-29-07069.

Keywords: anticipatory emotions, casino game, risk taking, impulsiveness

Procedia PDF Downloads 114

Authors: Jonas Colin

Abstract:

Standing at the vanguard of AI development, Alpha represents an unprecedented synthesis of logical rigor and human abstraction, meticulously crafted to mirror the user's unique persona and personality, a feat previously unattainable in AI development. Alpha, an avant-garde artefact in the realm of artificial intelligence, epitomizes a paradigmatic shift in personalized digital interaction, amalgamating user-specific dialogic patterns with the sophisticated algorithmic prowess of OpenAI's GPT-3.5 to engender a platform for enhanced metacognitive engagement and individualized user experience. Underpinned by a sophisticated algorithmic framework, Alpha integrates vast datasets through a complex interplay of neural network models and symbolic AI, facilitating a dynamic, adaptive learning process. This integration enables the system to construct a detailed user profile, encompassing linguistic preferences, emotional tendencies, and cognitive styles, tailoring interactions to align with individual characteristics and conversational contexts. Furthermore, Alpha incorporates advanced metacognitive elements, enabling real-time reflection and adaptation in communication strategies. This self-reflective capability ensures continuous refinement of its interaction model, positioning Alpha not just as a technological marvel but as a harbinger of a new era in human-computer interaction, where machines engage with us on a deeply personal and cognitive level, transforming our interaction with the digital world.

Keywords: chatbot, GPT 3.5, metacognition, symbiose

Procedia PDF Downloads 42

Authors: Chih-Chieh Yang, Chung-Neng Huang

Abstract:

In power system, how to improve the fault diagnosis technology of transmission line has always been the primary goal of power grid operators. In recent years, due to the rise of green energy, the addition of all kinds of distributed power also has an impact on the stability of the power system. Because the smart meters are with the function of data recording and bidirectional transmission, the adaptive Fuzzy Neural inference system, ANFIS, as well as the artificial intelligence that has the characteristics of learning and estimation in artificial intelligence. For transmission network, in order to avoid misjudgment of the fault type and location due to the input of these unstable power sources, combined with the above advantages of smart meter and ANFIS, a method for identifying fault types and location of faults is proposed in this study. In ANFIS training, the bus voltage and current information collected by smart meters can be trained through the ANFIS tool in MATLAB to generate fault codes to identify different types of faults and the location of faults. In addition, due to the uncertainty of distributed generation, a wind power system is added to the transmission network to verify the diagnosis correctness of the study. Simulation results show that the method proposed in this study can correctly identify the fault type and location of fault with more efficiency, and can deal with the interference caused by the addition of unstable power sources.

Keywords: ANFIS, fault diagnosis, power system, smart meter

Procedia PDF Downloads 121

Authors: Yuliya E. Leshchenko, Tatyana S. Ostapenko

Abstract:

Language variation is a widespread linguistic phenomenon which can affect different levels of a language system: phonological, morphological, lexical, syntactic, etc. It is obvious that the scope of possible standard alternations within a particular language is limited by a variety of its norms and regulations which set more or less clear boundaries for what is possible and what is not possible for the speakers. The possibility of lexical variation (alternate usage of lexical items within the same contexts) is based on the fact that the meanings of words are not clearly and rigidly defined in the consciousness of the speakers. Therefore, lexical variation is usually connected with unstable relationship between words and their referents: a case when a particular lexical item refers to different types of referents, or when a particular referent can be named by various lexical items. We assume that the scope of lexical variation in bilingual speech is generally wider than that observed in monolingual speech due to the fact that, besides ‘lexical item – referent’ relations it involves the possibility of cross-language variation of L1 and L2 lexical items. We use the term ‘cross-language variation’ to denote a case when two equivalent words of different languages are treated by a bilingual speaker as freely interchangeable within the common linguistic context. As distinct from code-switching which is traditionally defined as the conscious use of more than one language within one communicative act, in case of cross-language lexical variation the speaker does not perceive the alternate lexical items as belonging to different languages and, therefore, does not realize the change of language code. In the paper, the authors present research of lexical variation of adult Komi-Permyak – Russian bilingual speakers. The two languages co-exist on the territory of the Komi-Permyak District in Russia (Komi-Permyak as the ethnic language and Russian as the official state language), are usually acquired from birth in natural linguistic environment and, according to the data of sociolinguistic surveys, are both identified by the speakers as coordinate mother tongues. The experimental research demonstrated that alternation of Komi-Permyak and Russian words within one utterance/phrase is highly frequent both in speech perception and production. Moreover, our participants estimated cross-language word combinations like ‘маленькая /Russian/ нывка /Komi-Permyak/’ (‘a little girl’) or ‘мунны /Komi-Permyak/ домой /Russian/’ (‘go home’) as regular/habitual, containing no violation of any linguistic rules and being equally possible in speech as the equivalent intra-language word combinations (‘учöтик нывка’ /Komi-Permyak/ or ‘идти домой’ /Russian/). All the facts considered, we claim that constant concurrent use of the two languages results in the fact that a large number of their words tend to be intuitively interpreted by the speakers as lexical variants not only related to the same referent, but also referring to both languages or, more precisely, to none of them in particular. Consequently, we can suppose that bilingual mental lexicon includes an extensive ‘fused’ zone of lexical representations that provide the basis for cross-language variation in bilingual speech.

Keywords: bilingualism, bilingual mental lexicon, code-switching, lexical variation

Procedia PDF Downloads 131

Authors: Simone Leonardi, Luca Ardito

Abstract:

Micro-influencers are effective elements in the marketing strategies of companies and institutions because of their capability to create an hyper-engaged audience around a specific topic of interest. In recent years, many scientific approaches and commercial tools have handled the task of detecting this type of social media users. These strategies adopt solutions ranging from rule based machine learning models to deep neural networks and graph analysis on text, images, and account information. This work compares the existing solutions and proposes an ensemble method to generalize them with different input data and social media platforms. The deployed solution combines deep learning models on unstructured data with statistical machine learning models on structured data. We retrieve both social media accounts information and multimedia posts on Twitter and Instagram. These data are mapped into feature vectors for an eXtreme Gradient Boosting (XGBoost) classifier. Sixty different topics have been analyzed to build a rule based gold standard dataset and to compare the performances of our approach against baseline classifiers. We prove the effectiveness of our work by comparing the accuracy, precision, recall, and f1 score of our model with different configurations and architectures. We obtained an accuracy of 0.91 with our best performing model.

Keywords: deep learning, gradient boosting, image processing, micro-influencers, NLP, social media

Procedia PDF Downloads 154

Authors: Riaan Kleyn

Abstract:

Mass wine production companies across the globe are provided with grapes from winegrowers that predominantly utilize mechanical harvesting machines to harvest wine grapes. Mechanical harvesting accelerates the rate at which grapes are harvested, allowing grapes to be delivered faster to meet the demands of wine cellars. The disadvantage of the mechanical harvesting method is the inclusion of material-other-than-grapes (MOG) in the harvested wine grape loads arriving at the cellar which degrades the quality of wine that can be produced. Currently, wine cellars do not have a method to determine the amount of MOG present within wine grape loads. This paper seeks to find an optimal computer vision method capable of detecting the amount of MOG within a wine grape load. A MOG detection method will encourage winegrowers to deliver MOG-free wine grape loads to avoid penalties which will indirectly enhance the quality of the wine to be produced. Traditional image segmentation methods were compared to deep learning segmentation methods based on images of wine grape loads that were captured at a wine cellar. The Mask R-CNN model with a ResNet-50 convolutional neural network backbone emerged as the optimal method for this study to determine the amount of MOG in an image of a wine grape load. Furthermore, a statistical analysis was conducted to determine how the MOG on the surface of a grape load relates to the mass of MOG within the corresponding grape load.

Keywords: computer vision, wine grapes, machine learning, machine harvested grapes

Procedia PDF Downloads 68

Authors: Anastasia Schnitzer, Oliver Rehren

Abstract:

Mental health has become an increasingly important topic in society in recent years, not least due to the challenges posed by the corona pandemic. Along with this, the public has become more and more aware that a lack of enlightenment and proper coping mechanisms may result in a notable risk to develop mental disorders. Yet, there are still many biases against those affected, which are further connected to issues of stigmatization and societal exclusion. One of the main strategies to combat these forms of prejudice and stigma is to induce intergroup contact. More specifically, the Intergroup Contact Theory states engaging in certain types of contact with members of marginalized groups may be an effective way to improve attitudes towards these groups. However, due to the persistent prejudice and stigmatization, affected individuals often do not dare to speak openly about their mental disorders, so that intergroup contact often goes unnoticed. As a result, many people only experience conscious contact with individuals with a mental disorder through media. As an analogy to the Intergroup Contact Theory, the Parasocial Contact Hypothesis proposes that repeatedly being exposed to positive media representations of outgroup members can lead to a reduction of negative prejudices and attitudes towards this outgroup. While there is a growing body of research on the merit of this mechanism, measurements often only consist of 'positive' or 'negative' parasocial contact conditions (or examine the valence or quality of the previous contact with the outgroup); meanwhile, more specific conditions are often neglected. The current study aims to tackle this shortcoming. By scrutinizing the potential of contemporary series as a narrative framework of high quality, we strive to elucidate more detailed aspects of beneficial parasocial contact -for the sake of reducing prejudice and stigma towards individuals with mental disorders. Thus, a two-factorial between-subject online panel study with three measurement points was conducted (N = 95). Participants were randomly assigned to one of two groups, having to watch episodes of either a series with a narrative framework of high (Quality-TV) or low quality (Continental-TV), with one-week interval in-between the episodes. Suitable series were determined with the help of a pretest. Prejudice and stigma towards people with mental disorders were measured at the beginning of the study, before and after each episode, and in a final follow-up one week after the last two episodes. Additionally, parasocial interaction (PSI), quality of contact (QoC), and transportation were measured several times. Based on these data, multivariate multilevel analyses were performed in R using the lavaan package. Latent growth models showed moderate to high increases in QoC and PSI as well as small to moderate decreases in stigma and prejudice over time. Multilevel path analysis with individual and group levels further revealed that a qualitative narrative framework leads to a higher quality of contact experience, which then leads to lower prejudice and stigma, with effects ranging from moderate to high.

Keywords: prejudice, quality of contact, parasocial contact, narrative framework

Procedia PDF Downloads 63

Authors: Kishore Kumar R., Kaustav Sengupta, Shalini Sood Sehgal, Poornima Santhanam

Abstract:

Fashion is a human expression that is constantly changing. One of the prime factors that consistently influences fashion is the change in colour preferences. The role of colour in our everyday lives is very significant. It subconsciously explains a lot about one’s mindset and mood. Analyzing the colours by extracting them from the outfit images is a critical study to examine the individual’s/consumer behaviour. Several research works have been carried out on extracting colours from images, but to the best of our knowledge, there were no studies that extract colours to specific apparel and identify colour patterns geographically. This paper proposes a framework for accurately extracting colours from T-shirt images and predicting dominant colours geographically. The proposed method consists of two stages: first, a U-Net deep learning model is adopted to segment the T-shirts from the images. Second, the colours are extracted only from the T-shirt segments. The proposed method employs the iMaterialist (Fashion) 2019 dataset for the semantic segmentation task. The proposed framework also includes a mechanism for gathering data and analyzing India’s general colour preferences. From this research, it was observed that black and grey are the dominant colour in different regions of India. The proposed method can be adapted to study fashion’s evolving colour preferences.

Keywords: colour analysis in t-shirts, convolutional neural network, encoder-decoder, k-means clustering, semantic segmentation, U-Net model

Procedia PDF Downloads 86

Authors: RAM PAL SINGH, VIKASH CHAUDHARY, MONIKA VERMA

Abstract:

In this paper, we proposed the implementation of optimization based Extreme Learning Machine (ELM) for watermarking of B-channel of color image in discrete wavelet transform (DWT) domain. ELM, a regularization algorithm, works based on generalized single-hidden-layer feed-forward neural networks (SLFNs). However, hidden layer parameters, generally called feature mapping in context of ELM need not to be tuned every time. This paper shows the embedding and extraction processes of watermark with the help of ELM and results are compared with already used machine learning models for watermarking.Here, a cover image is divide into suitable numbers of non-overlapping blocks of required size and DWT is applied to each block to be transformed in low frequency sub-band domain. Basically, ELM gives a unified leaning platform with a feature mapping, that is, mapping between hidden layer and output layer of SLFNs, is tried for watermark embedding and extraction purpose in a cover image. Although ELM has widespread application right from binary classification, multiclass classification to regression and function estimation etc. Unlike SVM based algorithm which achieve suboptimal solution with high computational complexity, ELM can provide better generalization performance results with very small complexity. Efficacy of optimization method based ELM algorithm is measured by using quantitative and qualitative parameters on a watermarked image even though image is subjected to different types of geometrical and conventional attacks.

Keywords: BER, DWT, extreme leaning machine (ELM), PSNR

Procedia PDF Downloads 287