Search results for: cloud inference

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 261

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

Abstract:

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

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

Procedia PDF Downloads 64

Authors: Faisal Zaman, Ya Ping Wong, Boon Yian Ng

Abstract:

Point cloud source data for surface reconstruction is usually contaminated with noise and outliers. To overcome this, we present a novel approach using modified kernel density estimation (KDE) technique with bilateral filtering to remove noisy points and outliers. First we present a method for estimating optimal bandwidth of multivariate KDE using particle swarm optimization technique which ensures the robust performance of density estimation. Then we use mean-shift algorithm to find the local maxima of the density estimation which gives the centroid of the clusters. Then we compute the distance of a certain point from the centroid. Points belong to outliers then removed by automatic thresholding scheme which yields an accurate and economical point surface. The experimental results show that our approach comparably robust and efficient.

Keywords: point preprocessing, outlier removal, surface reconstruction, kernel density estimation

Procedia PDF Downloads 338

Authors: Xiaoqin Wang, Li Yin

Abstract:

Background and purpose: In many practices, one estimates causal effects arising from a complex stochastic process, where a sequence of treatments are assigned to influence a certain outcome of interest, and there exist time-dependent covariates between treatments. When covariates are plentiful and/or continuous, statistical modeling is needed to reduce the huge dimensionality of the problem and allow for the estimation of causal effects. Recently, Wang and Yin (Annals of statistics, 2020) derived a new general formula, which expresses these causal effects in terms of the point effects of treatments in single-point causal inference. As a result, it is possible to conduct the modeling via point effects. The purpose of the work is to study the modeling of these causal effects via point effects. Challenges and solutions: The time-dependent covariates often have influences from earlier treatments as well as on subsequent treatments. Consequently, the standard parameters – i.e., the mean of the outcome given all treatments and covariates-- are essentially all different (null paradox). Furthermore, the dimension of the parameters is huge (curse of dimensionality). Therefore, it can be difficult to conduct the modeling in terms of standard parameters. Instead of standard parameters, we have use point effects of treatments to develop likelihood-based parametric approach to the modeling of these causal effects and are able to model the causal effects of a sequence of treatments by modeling a small number of point effects of individual treatment Achievements: We are able to conduct the modeling of the causal effects from a sequence of treatments in the familiar framework of single-point causal inference. The simulation shows that our method achieves not only an unbiased estimate for the causal effect but also the nominal level of type I error and a low level of type II error for the hypothesis testing. We have applied this method to a longitudinal study of COVID-19 mortality among Scandinavian countries and found that the Swedish approach performed far worse than the other countries' approach for COVID-19 mortality and the poor performance was largely due to its early measure during the initial period of the pandemic.

Keywords: causal effect, point effect, statistical modelling, sequential causal inference

Procedia PDF Downloads 196

Authors: Belalia Douma Omar, Bakhta Boukhatem, Mohamed Ghrici

Abstract:

Self-compacting concrete (SCC) developed in Japan in the late 80s has enabled the construction industry to reduce demand on the resources, improve the work condition and also reduce the impact of environment by elimination of the need for compaction. Fuzzy logic (FL) approaches has recently been used to model some of the human activities in many areas of civil engineering applications. Especially from these systems in the model experimental studies, very good results have been obtained. In the present study, a model for predicting compressive strength of SCC containing various proportions of fly ash, as partial replacement of cement has been developed by using Adaptive Neuro-Fuzzy Inference System (ANFIS). For the purpose of building this model, a database of experimental data were gathered from the literature and used for training and testing the model. The used data as the inputs of fuzzy logic models are arranged in a format of five parameters that cover the total binder content, fly ash replacement percentage, water content, super plasticizer and age of specimens. The training and testing results in the fuzzy logic model have shown a strong potential for predicting the compressive strength of SCC containing fly ash in the considered range.

Keywords: self-compacting concrete, fly ash, strength prediction, fuzzy logic

Procedia PDF Downloads 324

Authors: P. K. Purohit, Azad A. Mansoori, Parvaiz A. Khan, Purushottam Bhawre, Sharad C. Tripathi, A. M. Aslam, Malik A. Waheed, Shivangi Bhardwaj, A. K. Gwal

Abstract:

The geomagnetic storm represents the most outstanding example of solar wind-magnetospheric interaction, which causes global disturbances in the geomagnetic field as well as the trigger ionospheric disturbances. We study the behaviour of ionospheric Total Electron Content (TEC) during the geomagnetic storms. For the present investigation we have selected 47 intense geomagnetic storms (Dst ≤ -100nT) that were observed during the solar cycle 23 i.e. during 1998-2006. We then categorized these storms into four categories depending upon their solar sources like Magnetic Cloud (MC), Co-rotating Interaction Region (CIR), SH+ICME and SH+MC. We then studied the behaviour of ionospheric TEC at a mid latitude station Usuda (36.13N, 138.36E), Japan during these storm events produced by four different solar sources. During our study we found that the smooth variations in TEC are replaced by rapid fluctuations and the value of TEC is strongly enhanced during the time of these storms belonging to all the four categories. However, the greatest enhancements in TEC are produced during those geomagnetic storms which are either caused by sheath driven magnetic cloud (SH+MC) or sheath driven ICME (SH+ICME). We also derived the correlation between the TEC enhancements produced during storms of each category with the minimum Dst. We found the strongest correlation exists for the SH+ICME category followed by SH+MC, MC and finally CIR. Since the most intense storms were either caused by SH+ICME or SH+MC while the least intense storms were caused by CIR, consequently the correlation was the strongest with SH+ICME and SH+MC and least with CIR.

Keywords: GPS, TEC, geomagnetic storm, sheath driven magnetic cloud

Procedia PDF Downloads 535

Authors: S. R. Dehghani, G. F. Naterer, Y. S. Muzychka

Abstract:

Wave-impact sea spray creates many droplets which form a spray cloud traveling over marine objects same as marine vessels and offshore structures. In cold climates such as Arctic reigns, sea spray icing, which is ice accretion on cold substrates, is strongly dependent on the wave-impact sea spray. The rate of cooling of droplets affects the process of icing that can yield to dry or wet ice accretion. Trajectories of droplets determine the potential places for ice accretion. Combining two models of trajectories and heat transfer for droplets can predict the risk of ice accretion reasonably. The majority of the cooling of droplets is because of droplet evaporations. In this study, a combined model using trajectory and heat transfer evaluate the situation of a cloud of spray from the generation to impingement. The model uses some known geometry and initial information from the previous case studies. The 3D model is solved numerically using a standard numerical scheme. Droplets are generated in various size ranges from 7 mm to 0.07 mm which is a suggested range for sea spray icing. The initial temperature of droplets is considered to be the sea water temperature. Wind velocities are assumed same as that of the field observations. Evaluations are conducted using some important heading angles and wind velocities. The characteristic of size-velocity dependence is used to establish a relation between initial sizes and velocities of droplets. Time intervals are chosen properly to maintain a stable and fast numerical solution. A statistical process is conducted to evaluate the probability of expected occurrences. The medium size droplets can reach the highest heights. Very small and very large droplets are limited to lower heights. Results show that higher initial velocities create the most expanded cloud of spray. Wind velocities affect the extent of the spray cloud. The rate of droplet cooling at the start of spray formation is higher than the rest of the process. This is because of higher relative velocities and also higher temperature differences. The amount of water delivery and overall temperature for some sample surfaces over a marine vessel are calculated. Comparing results and some field observations show that the model works accurately. This model is suggested as a primary model for ice accretion on marine vessels.

Keywords: evaporation, sea spray, marine icing, numerical solution, trajectory

Procedia PDF Downloads 213

Authors: Dhanuj M. Gandikota

Abstract:

Sensor-derived three-dimensional (3D) point clouds of trees are invaluable in remote sensing analysis for the accurate measurement of key structural metrics, bio-inventory values, spatial planning/visualization, and ecological modeling. Machine learning (ML) holds the potential in addressing the restrictive tradeoffs in cost, spatial coverage, resolution, and information gain that exist in current point cloud sensing methods. Terrestrial laser scanning (TLS) remains the highest fidelity source of both canopy and below-canopy structural features, but usage is limited in both coverage and cost, requiring manual deployment to map out large, forested areas. While aerial laser scanning (ALS) remains a reliable avenue of LIDAR active remote sensing, ALS is also cost-restrictive in deployment methods. Space-borne photogrammetry from high-resolution satellite constellations is an avenue of passive remote sensing with promising viability in research for the accurate construction of vegetation 3-D point clouds. It provides both the lowest comparative cost and the largest spatial coverage across remote sensing methods. However, both space-borne photogrammetry and ALS demonstrate technical limitations in the capture of valuable below-canopy point cloud data. Looking to minimize these tradeoffs, we explored a class of powerful ML algorithms called Deep Learning (DL) that show promise in recent research on 3-D point cloud reconstruction and interpolation. Our research details the efficacy of applying these DL techniques to reconstruct accurate below-canopy point clouds from space-borne and aerial remote sensing through learned patterns of tree species fractal symmetry properties and the supplementation of locally sourced bio-inventory metrics. From our dataset, consisting of tree point clouds obtained from TLS, we deconstructed the point clouds of each tree into those that would be obtained through ALS and satellite photogrammetry of varying resolutions. We fed this ALS/satellite point cloud dataset, along with the simulated local bio-inventory metrics, into the DL point cloud reconstruction architectures to generate the full 3-D tree point clouds (the truth values are denoted by the full TLS tree point clouds containing the below-canopy information). Point cloud reconstruction accuracy was validated both through the measurement of error from the original TLS point clouds as well as the error of extraction of key structural metrics, such as crown base height, diameter above root crown, and leaf/wood volume. The results of this research additionally demonstrate the supplemental performance gain of using minimum locally sourced bio-inventory metric information as an input in ML systems to reach specified accuracy thresholds of tree point cloud reconstruction. This research provides insight into methods for the rapid, cost-effective, and accurate construction of below-canopy tree 3-D point clouds, as well as the supported potential of ML and DL to learn complex, unmodeled patterns of fractal tree growth symmetry.

Keywords: deep learning, machine learning, satellite, photogrammetry, aerial laser scanning, terrestrial laser scanning, point cloud, fractal symmetry

Procedia PDF Downloads 93

Authors: Wided Bakari, Patrice Bellot, Omar Trigui, Mahmoud Neji

Abstract:

This article constitutes an opening to think of the modeling and analysis of Arabic texts in the context of a question-answer system. It is a question of exceeding the traditional approaches focused on morphosyntactic approaches. Furthermore, we present a new approach that analyze a text in order to extract correct answers then transform it to logical predicates. In addition, we would like to represent different levels of information within a text to answer a question and choose an answer among several proposed. To do so, we transform both the question and the text into logical forms. Then, we try to recognize all entailment between them. The results of recognizing the entailment are a set of text sentences that can implicate the user’s question. Our work is now concentrated on an implementation step in order to develop a system of question-answering in Arabic using techniques to recognize textual implications. In this context, the extraction of text features (keywords, named entities, and relationships that link them) is actually considered the first step in our process of text modeling. The second one is the use of techniques of textual implication that relies on the notion of inference and logic representation to extract candidate answers. The last step is the extraction and selection of the desired answer.

Keywords: NLP, Arabic language, question-answering, recognition text entailment, logic forms

Procedia PDF Downloads 332

Authors: Seyed Abbas Tabatabaei, Fereydoon Moghadas Nejad, Mohammad Saed

Abstract:

The bleeding prediction of the asphalt is one of the most complex subjects in the pavement engineering. In this paper, an Adaptive Neuro Fuzzy Inference System (ANFIS) is used for modeling the effect of important parameters on bleeding is trained and tested with the experimental results. bleeding index based on the asphalt film thickness differential as target parameter,asphalt content, temperature depth of two centemeter, heavy traffic, dust to effective binder, Marshall strength, passing 3/4 sieves, passing 3/8 sieves,passing 3/16 sieves, passing NO8, passing NO50, passing NO100, passing NO200 as input parameters. Then, we randomly divided empirical data into train and test sections in order to accomplish modeling. We instructed ANFIS network by 72 percent of empirical data. 28 percent of primary data which had been considered for testing the approprativity of the modeling were entered into ANFIS model. Results were compared by two statistical criterions (R2, RMSE) with empirical ones. Considering the results, it is obvious that our proposed modeling by ANFIS is efficient and valid and it can also be promoted to more general states.

Keywords: bleeding, asphalt film thickness differential, Anfis Modeling

Procedia PDF Downloads 263

Authors: Igor Kuzminov

Abstract:

Till now, the nature of lightning is not established. A hypothesis of the origin of lightning is proposed. The lightning charge is formed by electromagnetic induction. The role of the conductor is performed by the air mass of the cloud. This conductor moves in the Earth's magnetic field. The upper and lower edges of the cloud are the plates of the capacitor. Lightning is a special case of electromagnetic processes in an atmosphere. The category of lightning occurs in the process of accumulation of a charge. The process of accumulation goes constantly, but the charge is not fixed. Naturally, the hypothesis demands the carrying out of additional experiments and official acknowledgement. As the proof of a hypothesis can serve that the maximal lighting activity in an equatorial zone where cosφ it is close to 1. An experiment conducted privately showed that there is a potential difference in the atmosphere at different levels. The probability of applied value development of power installation is great.

Keywords: electromagnetic induction, Earth's magnetic field, plates of the capacitors, charge accumulation

Procedia PDF Downloads 79

Authors: Lucy W. Mburu, Richard Karanja, Simon N. Mwendia

Abstract:

Over recent years, learners have experienced a constant need to access on demand knowledge that is fully aligned with the paradigm of cloud computing. As motivated by the global sustainable development goal to ensure inclusive and equitable learning opportunities, this research has developed a framework hinged on the knowledge-as-a-service architecture that utilizes knowledge from ambient learning systems. Through statistical analysis and decision tree modeling, the study discovers influential variables for ambient learning among university students. The main aim is to generate a platform for disseminating and exploiting the available knowledge to aid the learning process and, thus, to improve educational support on the ambient learning system. The research further explores how collaborative effort can be used to form a knowledge network that allows access to heterogeneous sources of knowledge, which benefits knowledge consumers, such as the developers of ambient learning systems.

Keywords: actionable knowledge, ambient learning, cloud computing, decision trees, knowledge as a service

Procedia PDF Downloads 148

Authors: Amir Hadi Ziaie, Mostafa Hashemi, Shahram Jalalzadeh

Abstract:

It is now known that the end state of the collapse process of a dense star under its own gravity is the formation of a spacetime singularity. This is the spacetime event where the energy density and spacetime curvature diverge, and the classical general relativity breaks down. As we know, a realistic star is composed of fermions so that their spin effects could alter the final fate of the collapse scenario. The underlying theory within which the inclusion of spin effects can be worked out is the Einstein-Cartan theory. In this theory, the spacetime torsion which is defined as a geometrical quantity, is related to an intrinsic angular momentum of fermions (spin). In this work, we study the collapse process of a homogeneous spin fluid in such a framework and show that taking into account the spin effects of the collapsing cloud could prevent the formation of spacetime singularity.

Keywords: gravitational collapse, einstein-cartan theory, spacetime singularity, black hole physics

Procedia PDF Downloads 391

Authors: Anandita Mitro, Archana Srivastava, Bidisha Banerjee

Abstract:

The present paper attempts to analyze the hierarchy and interconnection of factors responsible for the uptake of BCG vaccination in India. The study uses National Family Health Survey (NFHS-5) data which was conducted during 2019-21. The univariate logistic regression method is used to understand the univariate effects while the interconnection effects have been studied using the Categorical Inference Tree (CIT) which is a non-parametric Machine Learning (ML) model. The hierarchy of the factors is further established using Conditional Inference Forest which is an extension of the CIT approach. The results suggest that BCG vaccination coverage was influenced more by system-level factors and awareness than education or socio-economic status. Factors such as place of delivery, antenatal care, and postnatal care were crucial, with variations based on delivery location. Region-specific differences were also observed which could be explained by the factors. Awareness of the disease was less impactful along with the factor of wealth and urban or rural residence, although awareness did appear to substitute for inadequate ANC. Thus, from the policy point of view, it is revealed that certain subpopulations have less prevalence of vaccination which implies that there is a need for population-specific policy action to achieve a hundred percent coverage.

Keywords: vaccination, NFHS, machine learning, public health

Procedia PDF Downloads 45

Authors: Malika Yaici, Anis Oussayah, Mohamed Ahmed Takerrabet

Abstract:

Security of context-aware ubiquitous systems is paramount, and authentication plays an important aspect in cloud computing and ubiquitous computing. Trust management has been identified as vital component for establishing and maintaining successful relational exchanges between trading partners in cloud and ubiquitous systems. Establishing trust is the way to build good relationship with both client and provider which positive activates will increase trust level, otherwise destroy trust immediately. We propose a new context-aware authentication system using a trust management system between client and server, and between servers, a trust which induces partnership, thus to a close cooperation between these servers. We defined the rules (algorithms), as well as the formulas to manage and calculate the trusting degrees depending on context, in order to uniquely authenticate a user, thus a single sign-on, and to provide him better services.

Keywords: ubiquitous computing, authentication, context-awareness, trust management

Procedia PDF Downloads 232

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

In this paper, we present the human action recognition method using the variational Bayesian HMM with the Dirichlet process mixture (DPM) of the Gaussian-Wishart emission model (GWEM). First, we define the Bayesian HMM based on the Dirichlet process, which allows an infinite number of Gaussian-Wishart components to support continuous emission observations. Second, we have considered an efficient variational Bayesian inference method that can be applied to drive the posterior distribution of hidden variables and model parameters for the proposed model based on training data. And then we have derived the predictive distribution that may be used to classify new action. Third, the paper proposes a process of extracting appropriate spatial-temporal feature vectors that can be used to recognize a wide range of human behaviors from input video image. Finally, we have conducted experiments that can evaluate the performance of the proposed method. The experimental results show that the method presented is more efficient with human action recognition than existing methods.

Keywords: human action recognition, Bayesian HMM, Dirichlet process mixture model, Gaussian-Wishart emission model, Variational Bayesian inference, prior distribution and approximate posterior distribution, KTH dataset

Procedia PDF Downloads 344

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 119

Authors: H. Bonakdari, I. Ebtehaj

Abstract:

The prediction of scour depth around bridge piers is frequently considered in river engineering. One of the key aspects in efficient and optimum bridge structure design is considered to be scour depth estimation around bridge piers. In this study, scour depth around bridge piers is estimated using two methods, namely the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN). Therefore, the effective parameters in scour depth prediction are determined using the ANN and ANFIS methods via dimensional analysis, and subsequently, the parameters are predicted. In the current study, the methods’ performances are compared with the nonlinear regression (NLR) method. The results show that both methods presented in this study outperform existing methods. Moreover, using the ratio of pier length to flow depth, ratio of median diameter of particles to flow depth, ratio of pier width to flow depth, the Froude number and standard deviation of bed grain size parameters leads to optimal performance in scour depth estimation.

Keywords: adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), bridge pier, scour depth, nonlinear regression (NLR)

Procedia PDF Downloads 209

Authors: Han Wang, Zhuoxian Dai, Zhe Zhu, Hui Zhang, Zhenyu Zeng

Abstract:

In traditional microscopic traffic simulation, various approaches have been suggested to implement the single-agent behaviors about lane changing and intelligent driver model. However, when it comes to very large metropolitan areas, microscopic traffic simulation requires more resources and become time-consuming, then macroscopic traffic simulation aggregate trends of interests rather than individual vehicle traces. In this paper, we describe the architecture and implementation of the actor system of microscopic traffic simulation, which exploits the distributed architecture of modern-day cloud computing. The results demonstrate that our architecture achieves high-performance and outperforms all the other traditional microscopic software in all tasks. To the best of our knowledge, this the first system that enables single-agent behavior in macroscopic traffic simulation. We thus believe it contributes to a new type of system for traffic simulation, which could provide individual vehicle behaviors in microscopic traffic simulation.

Keywords: actor system, cloud computing, distributed system, traffic simulation

Procedia PDF Downloads 182

Authors: Nyeng P. Gyang

Abstract:

Even though past, current and future trends suggest that multicore and cloud computing systems are increasingly prevalent/ubiquitous, this class of parallel systems is nonetheless underutilized, in general, and barely used for research on employing parallel Delaunay triangulation for parallel surface modeling and generation, in particular. The performances, of actual/physical and virtual/cloud multicore systems/machines, at executing various algorithms, which implement various parallelization strategies of the incremental insertion technique of the Delaunay triangulation algorithm, were evaluated. T-tests were run on the data collected, in order to determine whether various performance metrics differences (including execution time, speedup and efficiency) were statistically significant. Results show that the actual machine is approximately twice faster than the virtual machine at executing the same programs for the various parallelization strategies. Results, which furnish the scalability behaviors of the various parallelization strategies, also show that some of the differences between the performances of these systems, during different runs of the algorithms on the systems, were statistically significant. A few pseudo superlinear speedup results, which were computed from the raw data collected, are not true superlinear speedup values. These pseudo superlinear speedup values, which arise as a result of one way of computing speedups, disappear and give way to asymmetric speedups, which are the accurate kind of speedups that occur in the experiments performed.

Keywords: cloud computing systems, multicore systems, parallel Delaunay triangulation, parallel surface modeling and generation

Procedia PDF Downloads 198

Authors: I. M. L. Nadeesha Jayaweera, Adao Alex Trindade

Abstract:

In choosing a candidate model in likelihood-based modeling via an information criterion, the practitioner is often faced with the difficult task of deciding just how far up the ranked list to look. Motivated by this pragmatic necessity, we construct an uncertainty band for a generalized (model selection) information criterion (GIC), defined as a criterion for which the limit in probability is identical to that of the normalized log-likelihood. This includes common special cases such as AIC & BIC. The method starts from the asymptotic normality of the GIC for the joint distribution of the candidate models in an independent and identically distributed (IID) data framework and proceeds by deriving the (asymptotically) exact distribution of the minimum. The calculation of an upper quantile for its distribution then involves the computation of multivariate Gaussian integrals, which is amenable to efficient implementation via the R package "mvtnorm". The performance of the methodology is tested on simulated data by checking the coverage probability of nominal upper quantiles and compared to the bootstrap. Both methods give coverages close to nominal for large samples, but the bootstrap is two orders of magnitude slower. The methodology is subsequently extended to two other commonly used model structures: regression and time series. In the regression case, we derive the corresponding asymptotically exact distribution of the minimum GIC invoking Lindeberg-Feller type conditions for triangular arrays and are thus able to similarly calculate upper quantiles for its distribution via multivariate Gaussian integration. The bootstrap once again provides a default competing procedure, and we find that similar comparison performance metrics hold as for the IID case. The time series case is complicated by far more intricate asymptotic regime for the joint distribution of the model GIC statistics. Under a Gaussian likelihood, the default in most packages, one needs to derive the limiting distribution of a normalized quadratic form for a realization from a stationary series. Under conditions on the process satisfied by ARMA models, a multivariate normal limit is once again achieved. The bootstrap can, however, be employed for its computation, whence we are once again in the multivariate Gaussian integration paradigm for upper quantile evaluation. Comparisons of this bootstrap-aided semi-exact method with the full-blown bootstrap once again reveal a similar performance but faster computation speeds. One of the most difficult problems in contemporary statistical methodological research is to be able to account for the extra variability introduced by model selection uncertainty, the so-called post-model selection inference (PMSI). We explore ways in which the GIC uncertainty band can be inverted to make inferences on the parameters. This is being attempted in the IID case by pivoting the CDF of the asymptotically exact distribution of the minimum GIC. For inference one parameter at a time and a small number of candidate models, this works well, whence the attained PMSI confidence intervals are wider than the MLE-based Wald, as expected.

Keywords: model selection inference, generalized information criteria, post model selection, Asymptotic Theory

Procedia PDF Downloads 76

Authors: Kazuhiro Tateda, Elisa Gonzalez, Shuhei Ito, Kirstin Heinrich, Kevin Sweetland, Pingping Zhang, Catia Ferreira, Michael Pride, Jennifer Moisi, Sharon Gray, Bennett Lee, Fred Angulo

Abstract:

Clostridium difficile (C. difficile) is the most common cause of antibiotic-associated diarrhea and infectious diarrhea in healthcare settings. Japan has an aging population; the elderly are at increased risk of hospitalization, antibiotic use, and C. difficile infection (CDI). Little is known about the population-based incidence and disease burden of CDI in Japan although limited hospital-based studies have reported a lower incidence than the United States. To understand CDI disease burden in Japan, CLOUD (Clostridium difficile Infection Burden of Disease in Adults in Japan) was developed. CLOUD will derive population-based incidence estimates of the number of CDI cases per 100,000 population per year in Ota-ku (population 723,341), one of the districts in Tokyo, Japan. CLOUD will include approximately 14 of the 28 Ota-ku hospitals including Toho University Hospital, which is a 1,000 bed tertiary care teaching hospital. During the 12-month patient enrollment period, which is scheduled to begin in November 2018, Ota-ku residents > 50 years of age who are hospitalized at a participating hospital with diarrhea ( > 3 unformed stools (Bristol Stool Chart 5-7) in 24 hours) will be actively ascertained, consented, and enrolled by study surveillance staff. A stool specimen will be collected from enrolled patients and tested at a local reference laboratory (LSI Medience, Tokyo) using QUIK CHEK COMPLETE® (Abbott Laboratories). which simultaneously tests specimens for the presence of glutamate dehydrogenase (GDH) and C. difficile toxins A and B. A frozen stool specimen will also be sent to the Pfizer Laboratory (Pearl River, United States) for analysis using a two-step diagnostic testing algorithm that is based on detection of C. difficile strains/spores harboring toxin B gene by PCR followed by detection of free toxins (A and B) using a proprietary cell cytotoxicity neutralization assay (CCNA) developed by Pfizer. Positive specimens will be anaerobically cultured, and C. difficile isolates will be characterized by ribotyping and whole genomic sequencing. CDI patients enrolled in CLOUD will be contacted weekly for 90 days following diarrhea onset to describe clinical outcomes including recurrence, reinfection, and mortality, and patient reported economic, clinical and humanistic outcomes (e.g., health-related quality of life, worsening of comorbidities, and patient and caregiver work absenteeism). Studies will also be undertaken to fully characterize the catchment area to enable population-based estimates. The 12-month active ascertainment of CDI cases among hospitalized Ota-ku residents with diarrhea in CLOUD, and the characterization of the Ota-ku catchment area, including estimation of the proportion of all hospitalizations of Ota-ku residents that occur in the CLOUD-participating hospitals, will yield CDI population-based incidence estimates, which can be stratified by age groups, risk groups, and source (hospital-acquired or community-acquired). These incidence estimates will be extrapolated, following age standardization using national census data, to yield CDI disease burden estimates for Japan. CLOUD also serves as a model for studies in other countries that can use the CLOUD protocol to estimate CDI disease burden.

Keywords: Clostridium difficile, disease burden, epidemiology, study protocol

Procedia PDF Downloads 251

Authors: Manikandan S. P., Sharmila N.

Abstract:

Pain in the neck, intermediate and anterior, and even low back may occur in one or more locations. Numerous factors can lead to back discomfort, which can manifest into sensations in the other parts of your body. Up to 80% of people will have low back problems at a certain stage of their lives, making spine-related pain a highly prevalent ailment. Roughly twice as commonly as neck pain, low back discomfort also happens about as often as knee pain. According to current studies, using digital devices for extended periods of time and poor sitting posture are the main causes of neck and low back pain. There are numerous monitoring techniques provided to enhance the sitting posture for the aforementioned problems. A sophisticated technique to monitor the extended sitting position is suggested in this research based on this problem. The system is made up of an inertial measurement unit, a T-shirt, an Arduino board, a buzzer, and a mobile app with cloud services. Based on the anatomical position of the spinal cord, the inertial measurement unit was positioned on the inner back side of the T-shirt. The IMU (inertial measurement unit) sensor will evaluate the hip position, imbalanced shoulder, and bending angle. Based on the output provided by the IMU, the data will be analyzed by Arduino, supplied through the cloud, and shared with a mobile app for continuous monitoring. The buzzer will sound if the measured data is mismatched with the human body's natural position. The implementation and data prediction with design to identify balanced and unbalanced posture using a posture monitoring t-shirt will be further discussed in this research article.

Keywords: IMU, posture, IOT, textile

Procedia PDF Downloads 76

Authors: B. Madhevan, R. Sakkaravarthi, R. Diya

Abstract:

The number and variety of mobile robot applications are increasing day by day, both in an industry and in our daily lives. First developed as a tool, nowadays mobile robots can be integrated as an entity in Internet-accessible resources. The present work is organized around four potential resources such as cloud computing, Internet of things, Big data analysis and Co-simulation. Further, the focus relies on integrating, analyzing and discussing the need for integrating Internet-accessible resources and the challenges deriving from such integration, and how these issues have been tackled. Hence, the research work investigates the concepts of the Internet-accessible resources from the aspect of the autonomous mobile robots with an overview of the performances of the currently available database systems. IaR is a world-wide network of interconnected objects, can be considered an evolutionary process in mobile robots. IaR constitutes an integral part of future Internet with data analysis, consisting of both physical and virtual things.

Keywords: internet-accessible resources, cloud computing, big data analysis, internet of things, mobile robot

Procedia PDF Downloads 381

Authors: Nicolas M. Beleski, Gustavo A. G. Lugo

Abstract:

Robotic agents are taking more and increasingly important roles in society. In order to make these robots and agents more autonomous and efficient, their systems have grown to be considerably complex and convoluted. This growth in complexity has led recent researchers to investigate forms to explain the AI behavior behind these systems in search for more trustworthy interactions. A current problem in explainable AI is the inner workings with the logic inference process and how to conduct a sensibility analysis of the process of valuation and alteration of beliefs. In a social HRI (human-robot interaction) setup, theory of mind is crucial to ease the intentionality gap and to achieve that we should be able to infer over observed human behaviors, such as cases of cognitive dissonance. One specific case inspired in human cognition is the role emotions play on our belief system and the effects caused when observed behavior does not match the expected outcome. In such scenarios emotions can make a person wrongly assume the antecedent P for an observed consequent Q, and as a result, incorrectly assert that P is true. This form of cognitive dissonance where an unproven cause is taken as truth induces changes in the belief base which can directly affect future decisions and actions. If we aim to be inspired by human thoughts in order to apply levels of theory of mind to these artificial agents, we must find the conditions to replicate these observable cognitive mechanisms. To achieve this, a computational architecture is proposed to model the modulation effect emotions have on the belief system and how it affects logic inference process and consequently the decision making of an agent. To validate the model, an experiment based on the prisoner's dilemma is currently under development. The hypothesis to be tested involves two main points: how emotions, modeled as internal argument strength modulators, can alter inference outcomes, and how can explainable outcomes be produced under specific forms of cognitive dissonance.

Keywords: cognitive architecture, cognitive dissonance, explainable ai, sensitivity analysis, theory of mind

Procedia PDF Downloads 125

Authors: Ahmet Kayabasi, Ali Akdagli

Abstract:

In this study, three robust predicting methods, namely artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) and support vector machine (SVM) were used for computing the resonant frequency of A-shaped compact microstrip antennas (ACMAs) operating at UHF band. Firstly, the resonant frequencies of 144 ACMAs with various dimensions and electrical parameters were simulated with the help of IE3D™ based on method of moment (MoM). The ANN, ANFIS and SVM models for computing the resonant frequency were then built by considering the simulation data. 124 simulated ACMAs were utilized for training and the remaining 20 ACMAs were used for testing the ANN, ANFIS and SVM models. The performance of the ANN, ANFIS and SVM models are compared in the training and test process. The average percentage errors (APE) regarding the computed resonant frequencies for training of the ANN, ANFIS and SVM were obtained as 0.457%, 0.399% and 0.600%, respectively. The constructed models were then tested and APE values as 0.601% for ANN, 0.744% for ANFIS and 0.623% for SVM were achieved. The results obtained here show that ANN, ANFIS and SVM methods can be successfully applied to compute the resonant frequency of ACMAs, since they are useful and versatile methods that yield accurate results.

Keywords: a-shaped compact microstrip antenna, artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM)

Procedia PDF Downloads 432

Authors: Zahra Ahmadi, Fazlollah Adibnia

Abstract:

Scheduling of tasks and the optimal allocation of resources in the cloud are based on the dynamic nature of tasks and the heterogeneity of resources. Applications that are based on the scientific workflow are among the most widely used applications in this field, which are characterized by high processing power and storage capacity. In order to increase their efficiency, it is necessary to plan the tasks properly and select the best virtual machine in the cloud. The goals of the system are effective factors in scheduling tasks and resource selection, which depend on various criteria such as time, cost, current workload and processing power. Multi-criteria decision-making methods are a good choice in this field. In this research, a new method of work planning and resource allocation in a heterogeneous environment based on the modified AHP algorithm is proposed. In this method, the scheduling of input tasks is based on two criteria of execution time and size. Resource allocation is also a combination of the AHP algorithm and the first-input method of the first client. Resource prioritization is done with the criteria of main memory size, processor speed and bandwidth. What is considered in this system to modify the AHP algorithm Linear Max-Min and Linear Max normalization methods are the best choice for the mentioned algorithm, which have a great impact on the ranking. The simulation results show a decrease in the average response time, return time and execution time of input tasks in the proposed method compared to similar methods (basic methods).

Keywords: hierarchical analytical process, work prioritization, normalization, heterogeneous resource allocation, scientific workflow

Procedia PDF Downloads 138

Authors: Ankita R. Bansal, Naren S. Burade

Abstract:

Idea is to create a cloud based virtual lab for Deaf Students, “A language acquisition program using Visual Phonics and Cued Speech” using VMware Virtual Lab. This lab will demonstrate students the sounds of letters associated with the Language, building letter blocks, making words, etc Virtual labs are used for demos, training, for the Lingual development of children in their vernacular language. The main potential benefits are reduced labour and hardware costs, faster response times to users. Virtual Computing Labs allows any of the software as a service solutions, virtualization solutions, and terminal services solutions available today to offer as a service on demand, where a single instance of the software runs on the cloud and services multiple end users. VMWare, XEN, MS Virtual Server, Virtuoso, and Citrix are typical examples.

Keywords: visual phonics, language acquisition, vernacular language, cued speech, virtual lab

Procedia PDF Downloads 591

Authors: Zahra Abdolkarimi, Naser Zouri

Abstract:

Nowadays, there is unbelievable growing of Robots created a collection of complex and motivate subject in robotic and intellectual ornate, also it made a mechatronics style base of theoretical and technical way in Robocop. Additionally, robotics system recommended RoboCup factor as a provider of some standardization and testing method in case of computer discussion widely. The actual purpose of RoboCup is creating independent team of robots in 2050 based of FiFa roles to bring the victory in compare of world star team. In addition, decision making of robots depends to environment reaction, self-player and rival player with using inductive Fuzzy system valuation subsidiary to solve issue of robots in land game. The measure of selection in compare with other methods depends to amount of victories percentage in the same team that plays accidently. Consequences, shows method of our discussion is the best way for Particle Swarm Optimization and Fuzzy system compare to other decision of robotics algorithmic.

Keywords: PSO algorithm, inference fuzzy system, chaos theory, soccer robot league

Procedia PDF Downloads 395

Authors: Ivan Stanev, Maria Koleva

Abstract:

Described are challenges to the Bulgarian e-Customs (BeC) related to low level of interoperability and standardization, inefficient use of available infrastructure, lack of centralized identification and authorization, extremely low level of software process automation, and insufficient quality of data stored in official registers. The technical requirements for BeC are prepared with a focus on domain independent common platform, specialized customs and excise components, high scalability, flexibility, and reusability. The Knowledge Based Automated Software Engineering (KBASE) Common Platform for Automated Programming (CPAP) is selected as an instrument covering BeC requirements for standardization, programming automation, knowledge interpretation and cloud computing. BeC stage 3 results are presented and analyzed. BeC.S3 development trends are identified.

Keywords: service oriented architecture, cloud computing, knowledge based automated software engineering, common platform for automated programming, e-customs

Procedia PDF Downloads 363