Search results for: complex network approach

Authors: Elena Petersen, Inna Kornienko, Svetlana Guryeva, Sergey Simakov

Abstract:

In vitro organoid cultivation requires the simultaneous provision of necessary vascularization and nutrients perfusion of cells during organoid development. However, many aspects of this problem are still unsolved. The functionality of vascular network intergrowth is limited during early stages of organoid development since a function of the vascular network initiated on final stages of in vitro organoid cultivation. Therefore, a microchannel network should be created in early stages of organoid cultivation in hydrogel matrix aimed to conduct and maintain minimally required the level of nutrients perfusion for all cells in the expanding organoid. The network configuration should be designed properly in order to exclude hypoxic and necrotic zones in expanding organoid at all stages of its cultivation. In vitro vascularization is currently the main issue within the field of tissue engineering. As perfusion and oxygen transport have direct effects on cell viability and differentiation, researchers are currently limited only to tissues of few millimeters in thickness. These limitations are imposed by mass transfer and are defined by the balance between the metabolic demand of the cellular components in the system and the size of the scaffold. Current approaches include growth factor delivery, channeled scaffolds, perfusion bioreactors, microfluidics, cell co-cultures, cell functionalization, modular assembly, and in vivo systems. These approaches may improve cell viability or generate capillary-like structures within a tissue construct. Thus, there is a fundamental disconnect between defining the metabolic needs of tissue through quantitative measurements of oxygen and nutrient diffusion and the potential ease of integration into host vasculature for future in vivo implantation. A model is proposed for growth prognosis of the organoid perfusion based on joint simulations of general nutrient diffusion, nutrient diffusion to the hydrogel matrix through the contact surfaces and microchannels walls, nutrient consumption by the cells of expanding organoid, including biomatrix contraction during tissue development, which is associated with changed consumption rate of growing organoid cells. The model allows computing effective microchannel network design giving minimally required the level of nutrients concentration in all parts of growing organoid. It can be used for preliminary planning of microchannel network design and simulations of nutrients supply rate depending on the stage of organoid development.

Keywords: 3D model, consumption model, diffusion, spheroid, tissue organoid

Procedia PDF Downloads 308

Authors: Georgiana Onicescu, Yuqian Shen

Abstract:

Due to the complex nature of geo-referenced data, multicollinearity of the risk factors in public health spatial studies is a commonly encountered issue, which leads to low parameter estimation accuracy because it inflates the variance in the regression analysis. To address this issue, we proposed a two-stage variable selection method by extending the least absolute shrinkage and selection operator (Lasso) to the Bayesian spatial setting, investigating the impact of risk factors to health outcomes. Specifically, in stage I, we performed the variable selection using Bayesian Lasso and several other variable selection approaches. Then, in stage II, we performed the model selection with only the selected variables from stage I and compared again the methods. To evaluate the performance of the two-stage variable selection methods, we conducted a simulation study with different distributions for the risk factors, using geo-referenced count data as the outcome and Michigan as the research region. We considered the cases when all candidate risk factors are independently normally distributed, or follow a multivariate normal distribution with different correlation levels. Two other Bayesian variable selection methods, Binary indicator, and the combination of Binary indicator and Lasso were considered and compared as alternative methods. The simulation results indicated that the proposed two-stage Bayesian Lasso variable selection method has the best performance for both independent and dependent cases considered. When compared with the one-stage approach, and the other two alternative methods, the two-stage Bayesian Lasso approach provides the highest estimation accuracy in all scenarios considered.

Keywords: Lasso, Bayesian analysis, spatial analysis, variable selection

Procedia PDF Downloads 143

Authors: E. Zarei, M. Bazaei, A. Seifi, A. Keshavarzi

Abstract:

Amos Rapoport, based on his anthropology approach, believed that the space origins from the human body and influences on human body mutually. As a holistic approach in architecture, Contextualism describes a collection of views in philosophy which emphasize the context in which an action, utterance, or expression occurs, and argues that, in some important respect, the action, utterance, or expression can only be understood relative to that context. In this approach, the main goal – studying the role of cultural component in the Contextualism construction shaping up, based on Amos Rapoport’s anthropology approach- has being done by descriptive- analytic method. The results of the research indicate that in the field of Contextualism designing, referring to the cultural aspects are as necessary as the physical dimensions of a construction. Rapoport believes that the shape of a construction is influenced by cultural aspects and he suggests a kind of mutual interaction between human and environment that should be considered in housing. The mail goal of contextual architecture is to establish an interaction between environment, human and culture. According to this approach, a desirable design should be in harmony with this approach.

Keywords: Amos Rapoport, anthropology, contextual architecture, culture

Procedia PDF Downloads 400

Authors: Zeineb Ben Azzouz, Wahiba Ben Abdessalem Karaa

Abstract:

The automated extraction of UML class diagram from natural language requirements is a highly challenging task. Many approaches, frameworks and tools have been presented in this field. Nonetheless, the experiments of these tools have shown that there is no approach that can work best all the time. In this context, we propose a new accurate approach to facilitate the automatic mapping from textual requirements to UML class diagram. Our new approach integrates the best properties of statistical Natural Language Processing (NLP) techniques to reduce ambiguity when analysing natural language requirements text. In addition, our approach follows the best practices defined by conceptual modelling experts to determine some patterns indispensable for the extraction of basic elements and concepts of the class diagram. Once the relevant information of class diagram is captured, a XMI document is generated and imported with a CASE tool to build the corresponding UML class diagram.

Keywords: class diagram, user’s requirements, XMI, software engineering

Procedia PDF Downloads 471

Authors: Ameer A. Jebur, William Atherton, Rafid M. Alkhaddar, Edward Loffill

Abstract:

Understanding the behaviour of the piles under the action of the independent lateral loads and the precise prediction of the capacity of piles subjected to different lateral loads are vital topics in foundation design and analysis. Moreover, the laterally loaded behaviour of deep foundations penetrated in cohesive and non-cohesive soils is basically analysed by the Winkler Model (beam on elastic foundation), in which the interaction between the pile embedded depth and contacted soil is simulated by nonlinear p–y curves. The presence of many approaches to interpret the behaviour of soil-pile interaction has resulted in numerous outputs and indicates that no general approach has yet been adopted. The current study presents the result of numerical modelling of the behaviour of steel tubular piles (25.4mm) outside diameter with various embedment depth-to-diameter ratios (L/d) embedded in a sand calibrated chamber of known relative density. The study revealed that the shear strength parameters of the sand specimens and the (L/d) ratios are the most significant factor influencing the response of the pile and its capacity while taking into consideration the complex interaction between the pile and soil. Good agreement has been achieved when comparing the application of this modelling approach with experimental physical modelling carried out by another researcher.

Keywords: deep foundations, slenderness ratio, soil-pile interaction, winkler model (beam on elastic foundation), non-cohesive soil

Procedia PDF Downloads 299

Authors: Siti Aishah Hasbullah

Abstract:

Studies on identification of pork content in food have grown rapidly to meet the Halal food standard in Malaysia. The used mitochondria DNA (mtDNA) approaches for the identification of pig species is thought to be the most precise marker due to the mtDNA genes are present in thousands of copies per cell, the large variability of mtDNA. The standard method commonly used for DNA detection is based on polymerase chain reaction (PCR) method combined with gel electrophoresis but has major drawback. Its major drawbacks are laborious, need longer time and toxic to handle. Therefore, the need for simplicity and fast assay of DNA is vital and has triggered us to develop DNA biosensors for porcine DNA detection. Therefore, the aim of this project is to develop electrochemical DNA biosensor based on ruthenium (II) complex, [Ru(bpy)2(p-PIP)]2+ as DNA hybridization label. The interaction of DNA and [Ru(bpy)2(p-HPIP)]2+ will be studied by electrochemical transduction using Gold Screen-Printed Electrode (GSPE) modified with gold nanoparticles (AuNPs) and succinimide acrylic microspheres. The electrochemical detection by redox active ruthenium (II) complex was measured by cyclic voltammetry (CV) and differential pulse voltammetry (DPV). The results indicate that the interaction of [Ru(bpy)2(PIP)]2+ with hybridization complementary DNA has higher response compared to single-stranded and mismatch complementary DNA. Under optimized condition, this porcine DNA biosensor incorporated modified GSPE shows good linear range towards porcine DNA.

Keywords: gold, screen printed electrode, ruthenium, porcine DNA

Procedia PDF Downloads 309

Authors: Mohammed Raza Mehdi, Kamran Ahmed

Abstract:

Mega-city Karachi has numerous unplanned slum areas and squatter settlements with irregular growth of building structures. Due to weak development policy and lack of development control, such settlements are increasing at a rapid pace. Mapping such areas for planning and infrastructure development requires an integrated approach of socio-spatial and technological tools. Therefore in this study, an attempt is made to create GIS information layers on complex inbound built-up areas of slums at the coastal belt of Karachi by using a stereo pair of satellite images. The outcome expected is technological application to aid planning institutions for crisis management and infrastructure development in irregularly developed slum areas of Karachi, Pakistan.

Keywords: slum, satellite imageries, GIS, Karachi, Pakistan

Procedia PDF Downloads 145

Authors: Danilo López, Johana Hernández, Edwin Rivas

Abstract:

The use of the Multilayer Perceptron Neural Networks (MLPNN) technique is presented to estimate the future state of use of a licensed channel by primary users (PUs); this will be useful at the spectral decision stage in cognitive radio networks (CRN) to determine approximately in which time instants of future may secondary users (SUs) opportunistically use the spectral bandwidth to send data through the primary wireless network. To validate the results, sequences of occupancy data of channel were generated by simulation. The results show that the prediction percentage is greater than 60% in some of the tests carried out.

Keywords: cognitive radio, neural network, prediction, primary user

Procedia PDF Downloads 371

Authors: Boon Lee

Abstract:

Research publication is an essential output of universities because it not only promotes university recognition, it also receives government funding. The history of university research culture has been one of ‘publish or perish’ and universities have consistently encouraged their academics and researchers to produce research articles in reputable journals in order to maintain a level of competitiveness. In turn, the United Kingdom (UK) government funding is determined by the number and quality of research publications. This paper aims to investigate on whether more government funding leads to more quality papers. To that end, the paper employs a Network DEA model to evaluate the UK higher education performance over a period. Sources of efficiency are also determined via second stage regression analysis.

Keywords: efficiency, higher education, network data envelopment analysis, universities

Procedia PDF Downloads 114

Authors: Sanaa Rashed Abdallah, Yasser F. Hassan

Abstract:

The paper will introduce an approach where a rough sets, gene expression programming and rough neural networks are used cooperatively for learning and classification support. The Objective of gene expression programming rough neural networks (GEP-RNN) approach is to obtain new classified data with minimum error in training and testing process. Starting point of gene expression programming rough neural networks (GEP-RNN) approach is an information system and the output from this approach is a structure of rough neural networks which is including the weights and thresholds with minimum classification error.

Keywords: rough sets, gene expression programming, rough neural networks, classification

Procedia PDF Downloads 383

Authors: Khaled Jaber

Abstract:

The estimation of effort in software development is a complex task. The traditional Waterfall approach used to develop software systems requires a lot of time to estimate the effort needed to implement user requirements. Agile manifesto, however, is currently more used in the industry than the Waterfall to develop software systems. In Agile, the user requirement is referred to as a user story. Agile teams mostly use the Fibonacci sequence 1, 2, 3, 5, 8, 11, etc. in estimating the effort needed to implement the user story. This work shows through analysis that the Arithmetic sequence, e.g., 3, 6, 9, 12, etc., is more effective than the Fibonacci sequence in estimating the user stories. This paper mathematically and visually proves the effectiveness of the Arithmetic sequence over the FB sequence.

Keywords: agie, scrum, estimation, fibonacci sequence

Procedia PDF Downloads 205

Authors: Kiran Abdullah, Yanli Chen

Abstract:

An amphiphilic mixed (phthalocyaninato) (porphyrinato) europium triple-decker complex Eu₂(Pc)₂(TPyP) has been synthesized and characterized. Introducing electron-withdrawing pyridyl substituents onto the meso-position of porphyrin ring in the triple-decker to ensure the sufficient hydrophilicity and suitable HOMO and LUMO energy levels and thus successfully realize amphiphilic ambipolar organic semiconductor. Importantly, high sensitive, reproducible p-type and n-type responses towards NH₃ andNO₂ respectively, based on the self-assembled film of the Eu₂(Pc)₂(TPyP) fabricated by a simple solution-based Quasi–Langmuir–Shäfer (QLS) method, have been first revealed. The good conductivity and crystallinity for the QLS film of Eu₂(Pc)₂(TPyP) render it excellent sensing property. This complex is sensitive to both electron-donating NH₃ gas in 5–30 ppm range and electron-accepting NO₂ gas 400–900 ppb range. Due to uniform nano particles there exist effective intermolecular interaction between triple decker molecules. This is the best result of Phthalocyanine–based chemical sensors at room temperature. Furthermore, the responses of the QLS film are all linearly correlated to both NH₃ and NO₂ with excellent sensitivity of 0.04% ppm⁻¹ and 31.9 % ppm⁻¹, respectively, indicating the great potential of semiconducting tetrapyrrole rare earth triple-decker compounds in the field of chemical sensors.

Keywords: ambipolar semiconductor, gas sensing, mixed (phthalocyaninato) (porphyrinato) rare earth complex, Self-assemblies

Procedia PDF Downloads 198

Authors: Nina Ponikvar, Katja Zajc Kejžar

Abstract:

While the positive impacts of heritage on a broad societal spectrum have long been recognized and measured, the economic effects of the heritage sector are often less visible and frequently underestimated. At macro level, economic effects are usually studied based on one of the two mainstream approach, i.e. either the multiplier approach or the value chain approach. Consequently, there is limited comparability of the empirical results due to the use of different methodological approach in the literature. Furthermore, it is also not clear on which criteria the used approach was selected. Our aim is to bring the attention to the difference in the scope of effects that are encompassed by the two most frequent methodological approaches to valuation of economic effects of cultural heritage on macroeconomic level, i.e. the multiplier approach and the value chain approach. We show that while the multiplier approach provides a systematic, theory-based view of economic impacts but requires more data and analysis, the value chain approach has less solid theoretical foundations and depends on the availability of appropriate data to identify the contribution of cultural heritage to other sectors. We conclude that the multiplier approach underestimates the economic impact of cultural heritage, mainly due to the narrow definition of cultural heritage in the statistical classification and the inability to identify part of the contribution of cultural heritage that is hidden in other sectors. Yet it is not possible to clearly determine whether the value chain method overestimates or underestimates the actual economic impact of cultural heritage since there is a risk that the direct effects are overestimated and double counted, but not all indirect and induced effects are considered. Accordingly, these two approaches are not substitutes but rather complementary. Consequently, a direct comparison of the estimated impacts is not possible and should not be done due to the different scope. To illustrate the difference of the impact assessment of the cultural heritage, we apply both approaches to the case of Slovenia in the 2015-2022 period and measure the economic impact of cultural heritage sector in terms of turnover, gross value added and employment. The empirical results clearly show that the estimation of the economic impact of a sector using the multiplier approach is more conservative, while the estimates based on value added capture a much broader range of impacts. According to the multiplier approach, each euro in cultural heritage sector generates an additional 0.14 euros in indirect effects and an additional 0.44 euros in induced effects. Based on the value-added approach, the indirect economic effect of the “narrow” heritage sectors is amplified by the impact of cultural heritage activities on other sectors. Accordingly, every euro of sales and every euro of gross value added in the cultural heritage sector generates approximately 6 euros of sales and 4 to 5 euros of value added in other sectors. In addition, each employee in the cultural heritage sector is linked to 4 to 5 jobs in other sectors.

Keywords: economic value of cultural heritage, multiplier approach, value chain approach, indirect effects, slovenia

Procedia PDF Downloads 75

Authors: Keyi Wang

Abstract:

Similar to the touchscreen, hand gesture based human-computer interaction (HCI) is a technology that could allow people to perform a variety of tasks faster and more conveniently. This paper proposes a training method of an image-based hand gesture image and video clip recognition system using a CNN (Convolutional Neural Network) with a dataset. A dataset containing 6 hand gesture images is used to train a 2D CNN model. ~98% accuracy is achieved. Furthermore, a 3D CNN model is trained on a dataset containing 4 hand gesture video clips resulting in ~83% accuracy. It is demonstrated that a Cozmo robot loaded with pre-trained models is able to recognize static and dynamic hand gestures.

Keywords: deep learning, hand gesture recognition, computer vision, image processing

Procedia PDF Downloads 139

Authors: S. S. Bendib, L. W. Mouss, S. Kalla

Abstract:

This paper proposes a self-organization-based approach for real-time systems design. The addressed issue is the mapping of an application onto an architecture of heterogeneous processors while optimizing both makespan and reliability. Since this problem is NP-hard, a heuristic algorithm is used to obtain efficiently approximate solutions. The proposed approach takes into consideration the quality as well as the diversity of solutions. Indeed, an alternate treatment of the two objectives allows to produce solutions of good quality while a self-organization approach based on the neighborhood structure is used to reorganize solutions and consequently to enhance their diversity. Produced solutions make different compromises between the makespan and the reliability giving the user the possibility to select the solution suited to his (her) needs.

Keywords: embedded real-time systems design, makespan, reliability, self-organization, compromises

Procedia PDF Downloads 134

Authors: S. Dhivya, M. Abirami, M. Farjana Parveen, M. Keerthiga

Abstract:

The development of high-speed railway makes people’s lives more and more convenient; meanwhile, handover is the major problem on high-speed railway communication services. In order to overcome that drawback the architecture of Long-Term Evolution (LTE) femtocell networks is used to improve network performance, and the deployment of a femtocell is a key for bandwidth limitation and coverage issues in conventional mobile network system. To increase the handover performance this paper proposed a multiple input multiple output (MIMO) assisted handoff (MAHO) algorithm. It is a technique used in mobile telecom to transfer a mobile phone to a new radio channel with stronger signal strength and improved channel quality.

Keywords: flawless handover, high-speed train, home evolved Node B, LTE, mobile femtocell, RSS

Procedia PDF Downloads 473

Authors: Peiming Li

Abstract:

This paper presents an innovative blockchain-based approach to enhance the reliability and efficiency of federated learning systems. By integrating a decentralized oracle consensus mechanism into the federated learning framework, we address key challenges of data and model integrity. Our approach utilizes a network of redundant oracles, functioning as independent validators within an epoch-based training system in the federated learning model. In federated learning, data is decentralized, residing on various participants' devices. This scenario often leads to concerns about data integrity and model quality. Our solution employs blockchain technology to establish a transparent and tamper-proof environment, ensuring secure data sharing and aggregation. The decentralized oracles, a concept borrowed from blockchain systems, act as unbiased validators. They assess the contributions of each participant using a Hidden Markov Model (HMM), which is crucial for evaluating the consistency of participant inputs and safeguarding against model poisoning and malicious activities. Our methodology's distinct feature is its epoch-based training. An epoch here refers to a specific training phase where data is updated and assessed for quality and relevance. The redundant oracles work in concert to validate data updates during these epochs, enhancing the system's resilience to security threats and data corruption. The effectiveness of this system was tested using the Mnist dataset, a standard in machine learning for benchmarking. Results demonstrate that our blockchain-oriented federated learning approach significantly boosts system resilience, addressing the common challenges of federated environments. This paper aims to make these advanced concepts accessible, even to those with a limited background in blockchain or federated learning. We provide a foundational understanding of how blockchain technology can revolutionize data integrity in decentralized systems and explain the role of oracles in maintaining model accuracy and reliability.

Keywords: federated learning system, block chain, decentralized oracles, hidden markov model

Procedia PDF Downloads 63

Authors: Timur S. Zaripov, Artur K. Gilfanov, Sergei S. Sazhin, Steven M. Begg, Morgan R. Heikal

Abstract:

The calculation of the concentration of inertial droplets in complex flows is encountered in the modelling of numerous engineering and environmental phenomena; for example, fuel droplets in internal combustion engines and airborne pollutant particles. The results of recent research, focused on the development of methods for calculating concentration and their implementation in the commercial CFD code, ANSYS Fluent, is presented here. The study is motivated by the investigation of the mixture preparation processes in internal combustion engines with direct injection of fuel sprays. Two methods are used in our analysis; the Fully Lagrangian method (also known as the Osiptsov method) and the Eulerian approach. The Osiptsov method predicts droplet concentrations along path lines by solving the equations for the components of the Jacobian of the Eulerian-Lagrangian transformation. This method significantly decreases the computational requirements as it does not require counting of large numbers of tracked droplets as in the case of the conventional Lagrangian approach. In the Eulerian approach the average droplet velocity is expressed as a function of the carrier phase velocity as an expansion over the droplet response time and transport equation can be solved in the Eulerian form. The advantage of the method is that droplet velocity can be found without solving additional partial differential equations for the droplet velocity field. The predictions from the two approaches were compared in the analysis of the problem of a dilute gas-droplet flow around an infinitely long, circular cylinder. The concentrations of inertial droplets, with Stokes numbers of 0.05, 0.1, 0.2, in steady-state and transient laminar flow conditions, were determined at various Reynolds numbers. In the steady-state case, flows with Reynolds numbers of 1, 10, and 100 were investigated. It has been shown that the results predicted using both methods are almost identical at small Reynolds and Stokes numbers. For larger values of these numbers (Stokes — 0.1, 0.2; Reynolds — 10, 100) the Eulerian approach predicted a wider spread in concentration in the perturbations caused by the cylinder that can be attributed to the averaged droplet velocity field. The transient droplet flow case was investigated for a Reynolds number of 200. Both methods predicted a high droplet concentration in the zones of high strain rate and low concentrations in zones of high vorticity. The maxima of droplet concentration predicted by the Osiptsov method was up to two orders of magnitude greater than that predicted by the Eulerian method; a significant variation for an approach widely used in engineering applications. Based on the results of these comparisons, the Osiptsov method has resulted in a more precise description of the local properties of the inertial droplet flow. The method has been applied to the analysis of the results of experimental observations of a liquid gasoline spray at representative fuel injection pressure conditions. The preliminary results show good qualitative agreement between the predictions of the model and experimental data.

Keywords: internal combustion engines, Eulerian approach, fully Lagrangian approach, gasoline fuel sprays, droplets and particle concentrations

Procedia PDF Downloads 257

Authors: Maryam Kheirollahpour, Mahmoud Danaee, Amir Faisal Merican, Asma Ahmad Shariff

Abstract:

Background: The presence of nonlinearity among the risk factors of eating behavior causes a bias in the prediction models. The accuracy of estimation of eating behaviors risk factors in the primary prevention of obesity has been established. Objective: The aim of this study was to explore the potential of a hybrid model of structural equation modeling (SEM) and Artificial Neural Networks (ANN) to predict eating behaviors. Methods: The Partial Least Square-SEM (PLS-SEM) and a hybrid model (SEM-Artificial Neural Networks (SEM-ANN)) were applied to evaluate the factors affecting eating behavior patterns among university students. 340 university students participated in this study. The PLS-SEM analysis was used to check the effect of emotional eating scale (EES), body shape concern (BSC), and body appreciation scale (BAS) on different categories of eating behavior patterns (EBP). Then, the hybrid model was conducted using multilayer perceptron (MLP) with feedforward network topology. Moreover, Levenberg-Marquardt, which is a supervised learning model, was applied as a learning method for MLP training. The Tangent/sigmoid function was used for the input layer while the linear function applied for the output layer. The coefficient of determination (R²) and mean square error (MSE) was calculated. Results: It was proved that the hybrid model was superior to PLS-SEM methods. Using hybrid model, the optimal network happened at MPLP 3-17-8, while the R² of the model was increased by 27%, while, the MSE was decreased by 9.6%. Moreover, it was found that which one of these factors have significantly affected on healthy and unhealthy eating behavior patterns. The p-value was reported to be less than 0.01 for most of the paths. Conclusion/Importance: Thus, a hybrid approach could be suggested as a significant methodological contribution from a statistical standpoint, and it can be implemented as software to be able to predict models with the highest accuracy.

Keywords: hybrid model, structural equation modeling, artificial neural networks, eating behavior patterns

Procedia PDF Downloads 156

Authors: Henry Hexmoor, Kailash Yelasani

Abstract:

We present vehicular platooning as a special case of crowd-sensing framework where sharing sensory information among a crowd is used for their collective benefit. After offering an abstract policy that governs processes involving a vehicular platoon, we review several common scenarios and components surrounding vehicular platooning. We then present a simulated prototype that illustrates efficiency of road usage and vehicle travel time derived from platooning. We have argued that one of the paramount benefits of platooning that is overlooked elsewhere, is the substantial computational savings (i.e., economizing benefits) in acquisition and processing of sensory data among vehicles sharing the road. The most capable vehicle can share data gathered from its sensors with nearby vehicles grouped into a platoon.

Keywords: cloud network, collaboration, internet of things, social network

Procedia PDF Downloads 194

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 132

Authors: S. Mehrab Amiri, Nasser Talebbeydokhti

Abstract:

Modeling sediment transport processes by means of numerical approach often poses severe challenges. In this way, a number of techniques have been suggested to solve flow and sediment equations in decoupled, semi-coupled or fully coupled forms. Furthermore, in order to capture flow discontinuities, a number of techniques, like artificial viscosity and shock fitting, have been proposed for solving these equations which are mostly required careful calibration processes. In this research, a numerical scheme for solving shallow water and Exner equations in fully coupled form is presented. First-Order Centered scheme is applied for producing required numerical fluxes and the reconstruction process is carried out toward using Monotonic Upstream Scheme for Conservation Laws to achieve a high order scheme.  In order to satisfy C-property of the scheme in presence of bed topography, Surface Gradient Method is proposed. Combining the presented scheme with fourth order Runge-Kutta algorithm for time integration yields a competent numerical scheme. In addition, to handle non-prismatic channels problems, Cartesian Cut Cell Method is employed. A trained Multi-Layer Perceptron Artificial Neural Network which is of Feed Forward Back Propagation (FFBP) type estimates sediment flow discharge in the model rather than usual empirical formulas. Hydrodynamic part of the model is tested for showing its capability in simulation of flow discontinuities, transcritical flows, wetting/drying conditions and non-prismatic channel flows. In this end, dam-break flow onto a locally non-prismatic converging-diverging channel with initially dry bed conditions is modeled. The morphodynamic part of the model is verified simulating dam break on a dry movable bed and bed level variations in an alluvial junction. The results show that the model is capable in capturing the flow discontinuities, solving wetting/drying problems even in non-prismatic channels and presenting proper results for movable bed situations. It can also be deducted that applying Artificial Neural Network, instead of common empirical formulas for estimating sediment flow discharge, leads to more accurate results.

Keywords: artificial neural network, morphodynamic model, sediment continuity equation, shallow water equations

Procedia PDF Downloads 187

Authors: N. W. U. D. Chathurani, Shlomo Geva, Vinod Chandran, Proboda Rajapaksha

Abstract:

Selecting an appropriate image representation is the most important factor in implementing an effective Content-Based Image Retrieval (CBIR) system. This paper presents a multi-feature fusion approach for efficient CBIR, based on the distance distribution of features and relative feature weights at the time of query processing. It is a simple yet effective approach, which is free from the effect of features' dimensions, ranges, internal feature normalization and the distance measure. This approach can easily be adopted in any feature combination to improve retrieval quality. The proposed approach is empirically evaluated using two benchmark datasets for image classification (a subset of the Corel dataset and Oliva and Torralba) and compared with existing approaches. The performance of the proposed approach is confirmed with the significantly improved performance in comparison with the independently evaluated baseline of the previously proposed feature fusion approaches.

Keywords: feature fusion, image retrieval, membership function, normalization

Procedia PDF Downloads 345

Authors: Zoran Barac, Maja Martinovic

Abstract:

Higher Education Institutions (HEIs) are a special kind of organization, with its unique purpose and combination of actors. From the societal point of view, they are central institutions in the society that are involved in the activities of education, research, and innovation. At the same time, their societal function derives complex relationships between involved actors, ranging from students, faculty and administration, business community and corporate partners, government agencies, to the general public. HEIs are also particularly interesting as objects of governance research because of their unique public purpose and combination of stakeholders. Furthermore, they are the special type of institutions from an organizational viewpoint. HEIs are often described as “loosely coupled systems” or “organized anarchies“ that implies the challenging nature of their governance models. Governance models of HEIs describe roles, constellations, and modes of interaction of the involved actors in the process of strategic direction and holistic control of institutions, taking into account each particular context. Many governance models of the HEIs are primarily based on the balance of power among the involved actors. Besides the actors’ power and influence, leadership style and environmental contingency could impact the governance model of an HEI. Analyzing them through the frameworks of institutional and contingency theories, HEI governance models originate as outcomes of their institutional and contingency adaptation. HEIs tend to fit to institutional context comprised of formal and informal institutional rules. By fitting to institutional context, HEIs are converging to each other in terms of their structures, policies, and practices. On the other hand, contingency framework implies that there is no governance model that is suitable for all situations. Consequently, the contingency approach begins with identifying contingency variables that might impact a particular governance model. In order to be effective, the governance model should fit to contingency variables. While the institutional context creates converging forces on HEI governance actors and approaches, contingency variables are the causes of divergence of actors’ behavior and governance models. Finally, an HEI governance model is a balanced adaptation of the HEIs to the institutional context and contingency variables. It also encompasses roles, constellations, and modes of interaction of involved actors influenced by institutional and contingency pressures. Actors’ adaptation to the institutional context brings benefits of legitimacy and resources. On the other hand, the adaptation of the actors’ to the contingency variables brings high performance and effectiveness. HEI governance models outlined and analyzed in this paper are collegial, bureaucratic, entrepreneurial, network, professional, political, anarchical, cybernetic, trustee, stakeholder, and amalgam models.

Keywords: governance, governance models, higher education institutions, institutional context, situational context

Procedia PDF Downloads 336

Authors: Zahra Abdolkarimi, Naser Zourikalatehsamad,

Abstract:

Up to 40 years ago, after recognition of epilepsy, it was generally believed that these attacks occurred randomly and suddenly. However, thanks to the advance of mathematics and engineering, such attacks can be predicted within a few minutes or hours. In this way, various algorithms for long-term prediction of the time and frequency of the first attack are presented. In this paper, by considering the nonlinear nature of brain signals and dynamic recorded brain signals, ANFIS model is presented to predict the brain signals, since according to physiologic structure of the onset of attacks, more complex neural structures can better model the signal during attacks. Contribution of this work is the co-evolution algorithm for optimization of ANFIS network parameters. Our objective is to predict brain signals based on time series obtained from brain signals of the people suffering from epilepsy using ANFIS. Results reveal that compared to other methods, this method has less sensitivity to uncertainties such as presence of noise and interruption in recorded signals of the brain as well as more accuracy. Long-term prediction capacity of the model illustrates the usage of planted systems for warning medication and preventing brain signals.

Keywords: co-evolution algorithms, brain signals, time series, neural networks, ANFIS model, physiologic structure, time prediction, epilepsy suffering, illustrates model

Procedia PDF Downloads 282

Authors: X. L. Nguyen, T. Y. Chou, F. Y. Min, F. C. Lin, T. V. Hoang, Y. M. Huang

Abstract:

In Vietnam, land use planning is utilized as an efficient tool for the local government to adjust land use. However, planned locations are facing disapproval from people who live near these planned sites because of environmental problems. The selection of these locations is normally based on the subjective opinion of decision-makers and is not supported by any scientific methods. Many researchers have applied Multi-Criteria Analysis (MCA) methods in which Analytic Hierarchy Process (AHP) is the most popular techniques in combination with Fuzzy set theory for the subject of rationality assessment of land use planning locations. In this research, the Fuzzy set theory and Analytic Network Process (ANP) multi-criteria-based technique were used for the assessment process. The Fuzzy Analytic Hierarchy Process was also utilized, and the output results from two methods were compared to extract the differences. The 20 planned landfills in Hung Ha district, Thai Binh province, Vietnam was selected as a case study. The comparison results indicate that there are different between weights computed by AHP and ANP methods and the assessment outputs produced from these two methods also slight differences. After evaluation of existing planned sites, some potential locations were suggested to the local government for possibility of land use planning adjusts.

Keywords: Analytic Hierarchy Process, Analytic Network Process, Fuzzy set theory, land use planning

Procedia PDF Downloads 421

Authors: Oibar Martinez, Clara Oliver, Jose Miguel Miranda

Abstract:

The study of dispersion phenomena in electromagnetic waves reflected by conductors at infrared and lower frequencies is a topic which finds a number of applications. We aim to explain in this work what are the most relevant ones and how this phenomenon is modeled from both optics and electromagnetics points of view. We also explain here how the amplitude of an electromagnetic wave reflected by a lossy conductor could depend on both the frequency of the incident wave, as well as on the electrical properties of the conductor, and we illustrate this phenomenon with a practical example. The mathematical analysis made by a specialist in electromagnetics or a microwave engineer is apparently very different from the one made by a specialist in optics. We show here how both approaches lead to the same physical result and what are the key concepts which enable one to understand that despite the differences in the equations the solution to the problem happens to be the same. Our study starts with an analysis made by using the complex refractive index and the reflectance parameter. We show how this reflectance has a dependence with the square root of the frequency when the reflecting material is a good conductor, and the frequency of the wave is low enough. Then we analyze the same problem with a less known approach, which is based on the reflection coefficient of the electric field, a parameter that is most commonly used in electromagnetics and microwave engineering. In summary, this paper presents a mathematical study illustrated with a worked example which unifies the modeling of dispersion effects made by specialists in optics and the one made by specialists in electromagnetics. The main finding of this work is that it is possible to reproduce the dependence of the Fresnel reflectance with frequency from the intrinsic impedance of the reflecting media.

Keywords: dispersion, electromagnetic waves, microwaves, optics

Procedia PDF Downloads 129

Authors: Guanghua Zhang, Fubao Wang, Weijun Duan

Abstract:

Convolution neural network (CNN) has attracted more and more attention on recent years. Especially in the field of computer vision and image classification. However, unsupervised learning with CNN has received less attention than supervised learning. In this work, we use a new powerful tool which is deep convolutional generative adversarial networks (DCGANs) to generate images from Sloan Digital Sky Survey. Training by various star and galaxy images, it shows that both the generator and the discriminator are good for unsupervised learning. In this paper, we also took several experiments to choose the best value for hyper-parameters and which could help to stabilize the training process and promise a good quality of the output.

Keywords: convolution neural network, discriminator, generator, unsupervised learning

Procedia PDF Downloads 268

Authors: Kohtaroh Miyamoto

Abstract:

As enterprise computing becomes more and more complex, the costs and technical challenges of IT system maintenance and support are increasing rapidly. One popular approach to managing IT system maintenance is to prepare and use an FAQ (Frequently Asked Questions) system to manage and reuse systems knowledge. Such an FAQ system can help reduce the resolution time for each service incident ticket. However, there is a major problem where over time the knowledge in such FAQs tends to become outdated. Much of the knowledge captured in the FAQ requires periodic updates in response to new insights or new trends in the problems addressed in order to maintain its usefulness for problem resolution. These updates require a systematic approach to define the exact portion of the FAQ and its content. Therefore, we are working on a novel method to hierarchically structure the FAQ and automate the updates of its structure and content. We use structured information and the unstructured text information with the timelines of the information in the service incident tickets. We cluster the tickets by structured category information, by keywords, and by keyword modifiers for the unstructured text information. We also calculate an urgency score based on trends, resolution times, and priorities. We carefully studied the tickets of one of our projects over a 2.5-year time period. After the first 6 months, we started to create FAQs and confirmed they improved the resolution times. We continued observing over the next 2 years to assess the ongoing effectiveness of our method for the automatic FAQ updates. We improved the ratio of tickets covered by the FAQ from 32.3% to 68.9% during this time. Also, the average time reduction of ticket resolution was between 31.6% and 43.9%. Subjective analysis showed more than 75% reported that the FAQ system was useful in reducing ticket resolution times.

Keywords: FAQ system, resolution time, service incident tickets, IT system maintenance

Procedia PDF Downloads 338

Authors: José Anderson Rodrigues de Souza, Teles de Sales Bezerra, Saulo Aislan da Silva Eleuterio, Jeronimo Silva Rocha

Abstract:

Mobile devices are increasingly occupying sectors of society and one of its most important features is mobility. However, the use of mobile devices is subject to the lifetime of the batteries. Thus, the use of energy batteries has become an important issue in the study of wireless network technologies. In this context, new solutions that enable aggregate energy efficiency not only through energy saving, and principally they are evaluated from a more realistic model of energy discharge, if easy adaptation to existing protocols. This paper presents a study on the energy needed and the lifetime for Wireless Sensor Networks (WSN) using a heterogeneous network and applying the LEACH protocol.

Keywords: wireless sensor networks, energy efficiency, heterogeneous, LEACH protocol

Procedia PDF Downloads 580