Search results for: root computation

Authors: David Pham, Yongfeng Zhang

Abstract:

Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes.” For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts an attention mechanism to carefully select the neighborhood nodes for message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. We use a single model to target both the accuracy and explainability of problem spaces and show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor nodes for both better accuracy and enhanced explainability. To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show an increase in both accuracy and explainability.

Keywords: explainable AI, graph attention network, graph neural network, node classification

Procedia PDF Downloads 198

Authors: Sifeddine Abderrahmani, Sonia Bouafia

Abstract:

The finite element method is the most practical tool for the analysis of structures, whatever the geometrical shape and behavior. It is extensively used in many high-tech industries, such as civil or military engineering, for the modeling of bridges, motor bodies, fuselages, and airplane wings. Additionally, experience demonstrates that engineers like modeling their structures using the most basic finite elements. Numerous models of finite elements may be utilized in the numerical analysis depending on the interpolation field that is selected, and it is generally known that convergence to the proper value will occur considerably more quickly with a good displacement pattern than with a poor pattern, saving computation time. The method for creating finite elements using the strain approach (S.B.A.) is presented in this presentation. When the results are compared with those provided by equivalent displacement-based elements, having the same total number of degrees of freedom, an excellent convergence can be obtained through some application and validation tests using recently developed membrane elements, plate bending elements, and flat shell elements. The effectiveness and performance of the strain-based finite elements in modeling structures are proven by the findings for deflections and stresses.

Keywords: finite elements, plate bending, strain approach, displacement formulation, shell element

Procedia PDF Downloads 99

Authors: Qi Xiu, Hiromu Hota, Yohsuke Ishii, Takuya Oda

Abstract:

Recently, collectable manufacturing data are rapidly increasing. On the other hand, mega recall is getting serious as a social problem. Under such circumstances, there are increasing needs for preventing mega recalls by defect analysis such as root cause analysis and abnormal detection utilizing manufacturing data. However, the time to classify strings in manufacturing data by traditional method is too long to meet requirement of quick defect analysis. Therefore, we present String Length Distribution Classification method (SLDC) to correctly classify strings in a short time. This method learns character features, especially string length distribution from Product ID, Machine ID in BOM and asset list. By applying the proposal to strings in actual manufacturing data, we verified that the classification time of strings can be reduced by 80%. As a result, it can be estimated that the requirement of quick defect analysis can be fulfilled.

Keywords: string classification, data quality, feature selection, probability distribution, string length

Procedia PDF Downloads 318

Authors: Gopashis Biswas G. Son

Abstract:

This paper will attempt to explore the notions that the two Caribbean poets- Derek Walcott and Edward Kamau Brathwaite endorse on Caribbean history in their poems. Though both of these poets hold almost the same notion regarding history but their approach is totally different from one another. Coming from a 'hybrid' race, Walcott is aware of the history and acknowledges it and writes in 'mulatto of style'; whereas Brathwaite is enraged by it and attempts to sublimate it to erect a history of the new world. It is Walcott’s view to rise above the delusion and hatred and engulf the world of literature with creativity. On the other hand, Brathwaite holds the grudge which helps him not to forget and forgive the past experience but to transform that very experience into something positive which may help the Caribbean to transform their frustration into something creative and to help the Caribbean to overcome the present struggle against the legacy of colonization. Following discourse analysis, this paper seeks to identify if it is possible to rewrite and re-‘right’ the Caribbean history which has been lost in the route and analyze Walcott and Brathwaite’s attitude towards that very history which has been implemented through their poetry.

Keywords: Caribbean history, colonialism, mulatto of style, Walcott vis-à-vis Brathwaite

Procedia PDF Downloads 158

Authors: A. Bolaji Adesoye, Alimi Olorunfemi

Abstract:

This paper examines the impact of small and medium-scale enterprises (SMEs) credit financing and financial market development and their shocks on the output growth of Nigeria. The study estimated a VAR model for Nigeria using 1970-2013 annual data series. Unit root tests and cointegration are carried out. The study also explores IRFs and FEVDs in a system that includes output, commercial bank loan to SMEs, domestic credit to private sector by banks, money supply, lending rate and investment. Findings suggest that shocks in commercial bank credit to SMEs has a major impact on the output changes of Nigeria. Money supply shocks also have a sizeable impact on output growth variations amidst other financial instruments. Lastly, neutrality of investment does not hold in Nigeria as it also has impact on output fluctuations.

Keywords: SMEs financing, financial development, investment, output, Nigeria

Procedia PDF Downloads 408

Authors: Hashim Bashir

Abstract:

The Vortex generated at the edges of the wing of an Aircraft are called the Wing Tip Vortex. The Wing Tip Vortices are associated with induced drag. The induced drag is responsible for nearly 50% of aircraft total drag and can be reduced through modifications to the wing tip. Some models displace wingtips vortices outwards diminishing the induced drag. Concerning agricultural aircrafts, wing tip vortex position is really important, while spreading products over a plantation. In this work, theoretical calculations were made in order to study the influence in aerodynamic characteristics and vortex position, over Sudanese agricultural aircraft, by the following types of wing tips: delta tip, winglet and down curved. The down curved tip was better for total drag reduction, but not good referring to vortex position. The delta tip gave moderate improvement on aerodynamic characteristic and on vortex position. The winglet had a better vortex position and lift increment, but caused an undesirable result referring to the wing root bending moment. However, winglet showed better development potential for agricultural aircraft.

Keywords: wing tip device, wing tip vortice, agricultural aircaft, winglet

Procedia PDF Downloads 314

Authors: Shyamlal Kumawat

Abstract:

Cloud computing is shifting the approach IT capital are utilized. Cloud computing dynamically delivers convenient, on-demand access to shared pools of software resources, platform and hardware as a service through internet. The cloud computing model—made promising by sophisticated automation, provisioning and virtualization technologies. Users want the ability to access these services including infrastructure resources, how and when they choose. To accommodate this shift in the consumption model technology has to deal with the security, compatibility and trust issues associated with delivering that convenience to application business owners, developers and users. Absent of these issues, trust has attracted extensive attention in Cloud computing as a solution to enhance the security. This paper proposes a trusted computing technology through Standard Resource parameter Based Trust Model in Cloud Computing to select the appropriate cloud service providers. The direct trust of cloud entities is computed on basis of the interaction evidences in past and sustained on its present performances. Various SLA parameters between consumer and provider are considered in trust computation and compliance process. The simulations are performed using CloudSim framework and experimental results show that the proposed model is effective and extensible.

Keywords: cloud, Iaas, Saas, Paas

Procedia PDF Downloads 330

Authors: Yaşar Önal, Aydın Akın

Abstract:

This study was conducted Ismailoglu grape type (Vitis vinifera L.) and its vine which was aged 15 was grown on its own root in a vegetation period of 2013 in Nevşehir province in Turkey. In this research, it was investigated whether the applications of Control (C), 1/3 cluster tip reduction (1/3 CTR), shoot tip reduction (STR), 1/3 CTR + STR, TKI-HUMAS (TKI-HM) (Soil) (S), TKI-HM (Foliar) (F), TKI-HM (S + F), 1/3 CTR + TKI-HM (S), 1/3 CTR + TKI-HM (F), 1/3 CTR + TKI-HM (S+F), STR + TKI-HM (S), STR + TKI-HM (F), STR + TKI-HM (S + F), 1/3 CTR + STR+TKI-HM (S), 1/3 CTR + STR + TKI-HM (F), 1/3 CTR + STR + TKI-HM (S + F) on yield and yield components of Ismailoglu grape type. The results were obtained as the highest fresh grape yield (16.15 kg/vine) with TKI-HM (S), as the highest cluster weight (652.39 g) with 1/3 CTR + STR, as the highest 100 berry weight (419.07 g) with 1/3 CTR + STR + TKI-HM (F), as the highest maturity index (44.06) with 1/3 CTR, as the highest must yield (810.00 ml) with STR + TKI-HM (F), as the highest intensity of L* color (42.04) with TKI-HM (S + F), as the highest intensity of a* color (2.60) with 1/3 CTR + TKI-HM (S), as the highest intensity of b* color (7.16) with 1/3 CTR + TKI-HM (S) applications. To increase the fresh grape yield of Ismailoglu grape type can be recommended TKI-HM (S) application.

Keywords: 1/3 cluster tip reduction, shoot tip reduction, TKI-Humas application, yield and yield components

Procedia PDF Downloads 399

Authors: Kennedy Efosa Ehimwenma, Sujatha Krishnamoorthy, Safiya Al‑Sharji

Abstract:

The probability computation of events is in the interval of [0, 1], which are values that are determined by the number of outcomes of events in a sample space S. The probability Pr(A) that an event A will never occur is 0. The probability Pr(B) that event B will certainly occur is 1. This makes both events A and B a certainty. Furthermore, the sum of probabilities Pr(E₁) + Pr(E₂) + … + Pr(Eₙ) of a finite set of events in a given sample space S equals 1. Conversely, the difference of the sum of two probabilities that will certainly occur is 0. This paper first discusses Bayes, the complement of probability, and the difference of probability for occurrences of learning-events before applying them in the prediction of learning objects in student learning. Given the sum of 1; to make a recommendation for student learning, this paper proposes that the difference of argMaxPr(S) and the probability of student-performance quantifies the weight of learning objects for students. Using a dataset of skill-set, the computational procedure demonstrates i) the probability of skill-set events that have occurred that would lead to higher-level learning; ii) the probability of the events that have not occurred that requires subject-matter relearning; iii) accuracy of the decision tree in the prediction of student performance into class labels and iv) information entropy about skill-set data and its implication on student cognitive performance and recommendation of learning.

Keywords: complement of probability, Bayes’ rule, prediction, pre-assessments, computational education, information theory

Procedia PDF Downloads 161

Authors: M. Helen

Abstract:

Chemical graph serves as a convenient model for any real or abstract chemical system. Dendrimers are novel three dimensional hyper branched globular nanopolymeric architectures. Drug delivery scientists are especially enthusiastic about possible utility of dendrimers as drug delivery tool. Dendrimers like poly L lysine (PLL), poly-propylene imine (PPI) and poly-amidoamine (PAMAM), etc., are used as gene carrier in drug delivery system because of their chemical characteristics. These characteristics of chemical compounds are analysed using topological indices (invariants under graph isomorphism) such as Wiener index, Zagreb index, etc., Prof. V. R. Kulli motivated by the application of Zagreb indices in finding the total π energy and derived Gourava indices which is an improved version over Zagreb indices. In this paper, we study the structure of PLL-Dendrimer that has the following applications: reduction in toxicity, colon delivery, and topical delivery. Also, we determine first and second Gourava indices, first and second hyper Gourava indices, product and sum connectivity Gourava indices for PLL-Dendrimer. Gourava Indices have found applications in Quantitative Structure-Property Relationship (QSPR)/ Quantitative Structure-Activity Relationship (QSAR) studies.

Keywords: connectivity Gourava indices, dendrimer, Gourava indices, hyper GouravaG indices

Procedia PDF Downloads 138

Authors: Abdulkadir Abu Lawal

Abstract:

For the dearth of reliable cardinal numerical data, the linked phenomena in productivity indices such as operational costs and company turnovers, etc. could not be investigated. This would not give us insight to the root of productivity problems at unique sites. So, ordinal ranking by professionals who were most directly involved with construction sites was applied for Kendall’s concordance. Responses gathered from independent architects, builders/engineers, and quantity surveyors were herein analyzed. They were responses based on factors that affect sites productivity, and these factors were categorized as head office factors, resource management effectiveness factors, motivational factors, and training/skill development factors. It was found that productivity is low and has to be improved in order to facilitate Nigerian efforts in bridging its infrastructure deficit. The significance of this work is underlined with the Kendall’s coefficient of concordance of 0.78, while remedial measures must be emphasized to stimulate better productivity. Further detailed study can be undertaken by using Fuzzy logic analysis on wider Delphi survey.

Keywords: factors, Kendall's coefficient of concordance, magnitude of agreement, percentage magnitude of dichotomy, ranking variables

Procedia PDF Downloads 627

Authors: A. Nabhan, Mohamed R. El-Sharkawy, A. Rashed

Abstract:

The main aim of this paper is to dedicate the belt drive system faults like cogs missing, misalignment and belt worm using vibration analysis technique. Experimentally, the belt drive test-rig is equipped to measure vibrations signals under different operating conditions. Finite element 3D model of belt drive system is created and vibration response analyzed using commercial finite element software ABAQUS/CAE.  Root mean square (RMS) and Crest Factor will serve as indicators of average amplitude of envelope analysis signals. The vibration signals pattern obtained from the simulation model and experimental data have the same characteristics. It can be concluded that each case of the RMS is more effective in detecting the defect for acceleration response. While Crest Factor parameter has a response with the displacement and velocity of vibration signals. Also it can be noticed that the model has difficulty in completing the solution when the misalignment angle is higher than 1 degree.

Keywords: simulation model, misalignment, cogs missing, vibration analysis

Procedia PDF Downloads 284

Authors: James Purnama, Riri Fitri Sari

Abstract:

We investigate the machine learning algorithm selection problem in the term of a depth image based eye gaze estimation, with respect to its essential difficulty in reducing the number of required training samples and duration time of training. Statistics based prediction accuracy are increasingly used to assess and evaluate prediction or estimation in gaze estimation. This article evaluates Root Mean Squared Error (RMSE) and R-Squared statistical analysis to assess machine learning methods on depth camera data for gaze estimation. There are 4 machines learning methods have been evaluated: Random Forest Regression, Regression Tree, Support Vector Machine (SVM), and Linear Regression. The experiment results show that the Random Forest Regression has the lowest RMSE and the highest R-Squared, which means that it is the best among other methods.

Keywords: gaze estimation, gaze tracking, eye tracking, kinect, regression model, orange python

Procedia PDF Downloads 538

Authors: Apolinar Picado, Ronald Solís, Rafael Gamero

Abstract:

The thin-layer drying characteristics of instant coffee solution were investigated in a laboratory tunnel dryer. Drying experiments were carried out at three temperatures (80, 100 and 120 °C) and an air velocity of 1.2 m/s. Drying experimental data obtained are fitted to six (6) thin-layer drying models using the non-linear least squares regression analysis. The acceptability of the thin-layer drying model has been based on a value of the correlation coefficient that should be close to one, and low values for root mean square error (RMSE) and chi-square (x²). According to this evaluation, the most suitable model for describing drying process of thin-layer instant coffee solution is the Page model. Further, the effective moisture diffusivity and the activation energy were computed employing the drying experimental data. The effective moisture diffusivity values varied from 1.6133 × 10⁻⁹ to 1.6224 × 10⁻⁹ m²/s over the temperature range studied and the activation energy was estimated to be 162.62 J/mol.

Keywords: activation energy, diffusivity, instant coffee, thin-layer models

Procedia PDF Downloads 262

Authors: Hyun-Koo Kim, Yong-Hun Kim, Soo-Young Suk, Ju H. Park, Ho-Youl Jung

Abstract:

This paper presents an effective speed hump detection process at the day-time. we focus only on round types of speed humps in the day-time dynamic road environment. The proposed speed hump detection scheme consists mainly of two process as stereo matching and speed hump detection process. Our proposed process focuses to speed hump detection process. Speed hump detection process consist of noise reduction step, data fusion step, and speed hemp detection step. The proposed system is tested on Intel Core CPU with 2.80 GHz and 4 GB RAM tested in the urban road environments. The frame rate of test videos is 30 frames per second and the size of each frame of grabbed image sequences is 1280 pixels by 670 pixels. Using object-marked sequences acquired with an on-vehicle camera, we recorded speed humps and non-speed humps samples. Result of the tests, our proposed method can be applied in real-time systems by computation time is 13 ms. For instance; our proposed method reaches 96.1 %.

Keywords: data fusion, round types speed hump, speed hump detection, surface filter

Procedia PDF Downloads 510

Authors: Merouane Salhi, Toufik Zebbiche, Omar Abada

Abstract:

When the stagnation pressure of perfect gas increases, the specific heat and their ratio do not remain constant anymore and start to vary with this pressure. The gas does not remain perfect. Its state equation change and it becomes a real gas. In this case, the effects of molecular size and inter molecular attraction forces intervene to correct the state equation. The aim of this work is to show and discuss the effect of stagnation pressure on supersonic thermo dynamical, physical and geometrical flow parameters, to find a general case for real gas. With the assumptions that Berthelot’s state equation accounts for molecular size and inter molecular force effects, expressions are developed for analyzing supersonic flow for thermally and calorically imperfect gas lower than the dissociation molecules threshold. The designs parameters for supersonic nozzle like thrust coefficient depend directly on stagnation parameters of the combustion chamber. The application is for air. A computation of error is made in this case to give a limit of perfect gas model compared to real gas model.

Keywords: supersonic flow, real gas model, Berthelot’s state equation, Simpson’s method, condensation function, stagnation pressure

Procedia PDF Downloads 524

Authors: A. Ejah Umraeni Salam, M. Tola, M. Selintung, F. Maricar

Abstract:

Clean water is an essential and fundamental human need. Therefore, its supply must be assured by maintaining the quality, quantity and water pressure. However the fact is, on its distribution system, leakage happens and becomes a common world issue. One of the technical causes of the leakage is a leaking pipe. The purpose of the research is how to use the Radial Basis Function Neural (RBFNN) model to detect the location and the magnitude of the pipeline leakage rapidly and efficiently. In this study the RBFNN are trained and tested on data from EPANET hydraulic modeling system. Method of Radial Basis Function Neural Network is proved capable to detect location and magnitude of pipeline leakage with of the accuracy of the prediction results based on the value of RMSE (Root Meant Square Error), comparison prediction and actual measurement approaches 0.000049 for the whole pipeline system.

Keywords: radial basis function neural network, leakage pipeline, EPANET, RMSE

Procedia PDF Downloads 358

Authors: Raphael Naryongo, Philip Ngare, Anthony Waititu

Abstract:

This paper deals with numerical simulation of Wishart processes for a single asset risky pricing model whose volatility is described by Wishart affine diffusion processes. The multi-factor specification of volatility will make the model more flexible enough to fit the stock market data for short or long maturities for better returns. The Wishart process is a stochastic process which is a positive semi-definite matrix-valued generalization of the square root process. The aim of the study is to model the log asset stock returns under the double Wishart stochastic volatility model. The solution of the log-asset return dynamics for Bi-Wishart processes will be obtained through Euler-Maruyama discretization schemes. The numerical results on the asset returns are compared to the existing models returns such as Heston stochastic volatility model and double Heston stochastic volatility model

Keywords: euler schemes, log-asset return, infinitesimal generator, wishart diffusion affine processes

Procedia PDF Downloads 378

Authors: Ankur Sachan

Abstract:

The ability to make quick yet intelligent and value-added decisions to develop new fields has always been of great significance. In situations where the capital expenses and subsurface risk are high, carefully analyzing the inherent uncertainties in the reservoir and how they impact the predicted hydrocarbon accumulation and production becomes a daunting task. The problem is compounded in offshore environments, especially in the presence of heavy oils and disconnected sands where the margin for error is small. Uncertainty refers to the degree to which the data set may be in error or stray from the predicted values. To understand and quantify the uncertainties in reservoir model is important when estimating the reserves. Uncertainty parameters can be geophysical, geological, petrophysical etc. Identification of these parameters is necessary to carry out the uncertainty analysis. With so many uncertainties working at different scales, it becomes essential to have a consistent and efficient way of incorporating them into our analysis. Ranking the uncertainties based on their impact on reserves helps to prioritize/ guide future data gathering and uncertainty reduction efforts. Assigning probabilistic ranges to key uncertainties also enables the computation of probabilistic reserves. With this in mind, this paper, with the help the uncertainty and optimization process in petrel RE shows how the most influential uncertainties can be determined efficiently and how much impact so they have on the reservoir model thus helping in determining a cost effective and accurate model of the reservoir.

Keywords: uncertainty, reservoir model, parameters, optimization analysis

Procedia PDF Downloads 651

Authors: K. Gomathi

Abstract:

Mobile Ad hoc Networks (MANET) is defined as collection of routable wireless mobile nodes with no centralized administration and communicate each other using radio signals. Especially MANETs deployed in hostile environments where hackers will try to disturb the secure data transfer and drain the valuable network resources. Since MANET is battery operated network, preserving the network resource is essential one. For resource constrained computation, efficient routing and to increase the network stability, the network is divided into smaller groups called clusters. The clustering architecture consists of Cluster Head(CH), ordinary node and gateway. The CH is responsible for inter and intra cluster routing. CH election is a prominent research area and many more algorithms are developed using many different metrics. The CH with longer life sustains network lifetime, for this purpose Secondary Cluster Head(SCH) also elected and it is more economical. To nominate efficient CH, a Enhanced Distributed Weighted Clustering Algorithm (EDWCA) has been proposed. This approach considers metrics like battery power, degree difference and speed of the node for CH election. The proficiency of proposed one is evaluated and compared with existing algorithm using Network Simulator(NS-2).

Keywords: MANET, EDWCA, clustering, cluster head

Procedia PDF Downloads 398

Authors: Seda Yavuz, Anıl Çelebi, Aysun Taşyapı Çelebi, Oğuzhan Urhan

Abstract:

Nowadays, demand for using real-time video transmission capable devices is ever-increasing. So, high resolution videos have made efficient video compression techniques an essential component for capturing and transmitting video data. Motion estimation has a critical role in encoding raw video. Hence, various motion estimation methods are introduced to efficiently compress the video. Low bit‑depth representation based motion estimation methods facilitate computation of matching criteria and thus, provide small hardware footprint. In this paper, a hardware implementation of a two-bit transformation based low-complexity motion estimation method using local binary pattern approach is proposed. Image frames are represented in two-bit depth instead of full-depth by making use of the local binary pattern as a binarization approach and the binarization part of the hardware architecture is explained in detail. Experimental results demonstrate the difference between the proposed hardware architecture and the architectures of well-known low-complexity motion estimation methods in terms of important aspects such as resource utilization, energy and power consumption.

Keywords: binarization, hardware architecture, local binary pattern, motion estimation, two-bit transform

Procedia PDF Downloads 311

Authors: Stefan Wagenpfeil, Felix Engel, Paul McKevitt, Matthias Hemmje

Abstract:

Multimedia Indexing and Retrieval is generally designed and implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results but also leads to more complex graph structures. However, graph-traversal-based algorithms for similarity are quite inefficient and computation intensive, especially for large data structures. To deliver fast and effective retrieval, an efficient similarity algorithm, particularly for large graphs, is mandatory. Hence, in this paper, we define a graph-projection into a 2D space (Graph Code) as well as the corresponding algorithms for indexing and retrieval. We show that calculations in this space can be performed more efficiently than graph-traversals due to a simpler processing model and a high level of parallelization. In consequence, we prove that the effectiveness of retrieval also increases substantially, as Graph Codes facilitate more levels of detail in feature fusion. Thus, Graph Codes provide a significant increase in efficiency and effectiveness (especially for Multimedia indexing and retrieval) and can be applied to images, videos, audio, and text information.

Keywords: indexing, retrieval, multimedia, graph algorithm, graph code

Procedia PDF Downloads 161

Authors: Shonak Bansal, Prince Jain, Arun Kumar Singh, Neena Gupta

Abstract:

Recently nature–inspired algorithms have widespread use throughout the tough and time consuming multi–objective scientific and engineering design optimization problems. In this paper, we present extended forms of firefly algorithm to find optimal Golomb ruler (OGR) sequences. The OGRs have their one of the major application as unequally spaced channel–allocation algorithm in optical wavelength division multiplexing (WDM) systems in order to minimize the adverse four–wave mixing (FWM) crosstalk effect. The simulation results conclude that the proposed optimization algorithm has superior performance compared to the existing conventional computing and nature–inspired optimization algorithms to find OGRs in terms of ruler length, total optical channel bandwidth and computation time.

Keywords: channel allocation, conventional computing, four–wave mixing, nature–inspired algorithm, optimal Golomb ruler, lévy flight distribution, optimization, improved multi–objective firefly algorithms, Pareto optimal

Procedia PDF Downloads 320

Authors: Rami El-Hajj Mohamad, Mahmoud Skafi, Ali Massoud Haidar

Abstract:

Several meteorological parameters were used for the prediction of monthly average daily global solar radiation on horizontal using recurrent neural networks (RNNs). Climatological data and measures, mainly air temperature, humidity, sunshine duration, and wind speed between 1995 and 2007 were used to design and validate a feed forward and recurrent neural network based prediction systems. In this paper we present our reference system based on a feed-forward multilayer perceptron (MLP) as well as the proposed approach based on an RNN model. The obtained results were promising and comparable to those obtained by other existing empirical and neural models. The experimental results showed the advantage of RNNs over simple MLPs when we deal with time series solar radiation predictions based on daily climatological data.

Keywords: recurrent neural networks, global solar radiation, multi-layer perceptron, gradient, root mean square error

Procedia PDF Downloads 444

Authors: Amir Rashid

Abstract:

Cloud Computing frameworks empower organizations to cut expenses by outsourcing computation resources on-request. As of now, customers of Cloud service providers have no methods for confirming the privacy and ownership of their information and data. To address this issue we propose the platform of a trusted cloud computing program (TCCP). TCCP empowers Infrastructure as a Service (IaaS) suppliers, for example, Amazon EC2 to give a shout box execution condition that ensures secret execution of visitor virtual machines. Also, it permits clients to bear witness to the IaaS supplier and decide if the administration is secure before they dispatch their virtual machines. This paper proposes a Trusted Cloud Computing Platform (TCCP) for guaranteeing the privacy and trustworthiness of computed data that are outsourced to IaaS service providers. The TCCP gives the deliberation of a shut box execution condition for a client's VM, ensuring that no cloud supplier's authorized manager can examine or mess up with its data. Furthermore, before launching the VM, the TCCP permits a client to dependably and remotely acknowledge that the provider at backend is running a confided in TCCP. This capacity extends the verification of whole administration, and hence permits a client to confirm the data operation in secure mode.

Keywords: cloud security, IaaS, cloud data privacy and integrity, hybrid cloud

Procedia PDF Downloads 299

Authors: Mahmut Yildirim

Abstract:

This paper proposed the bidirectional long short-term memory (Bi-LSTM) network-aided deep learning (DL)-based signal detection for Orthogonal frequency division multiplexing with all index modulation (OFDM-AIM), namely Bi-DeepAIM. OFDM-AIM is developed to increase the spectral efficiency of OFDM with index modulation (OFDM-IM), a promising multi-carrier technique for communication systems beyond 5G. In this paper, due to its strong classification ability, Bi-LSTM is considered an alternative to the maximum likelihood (ML) algorithm, which is used for signal detection in the classical OFDM-AIM scheme. The performance of the Bi-DeepAIM is compared with LSTM network-aided DL-based OFDM-AIM (DeepAIM) and classic OFDM-AIM that uses (ML)-based signal detection via BER performance and computational time criteria. Simulation results show that Bi-DeepAIM obtains better bit error rate (BER) performance than DeepAIM and lower computation time in signal detection than ML-AIM.

Keywords: bidirectional long short-term memory, deep learning, maximum likelihood, OFDM with all index modulation, signal detection

Procedia PDF Downloads 72

Authors: Hyun-Woo Cho

Abstract:

It is quite important to utilize right time and intelligent production monitoring and diagnosis of industrial processes in terms of quality and safety issues. When compared with monitoring task, fault diagnosis represents the task of finding process variables responsible causing a specific fault in the process. It can be helpful to process operators who should investigate and eliminate root causes more effectively and efficiently. This work focused on the active use of combining a nonlinear statistical technique with a preprocessing method in order to implement practical real-time fault identification schemes for data-rich cases. To compare its performance to existing identification schemes, a case study on a benchmark process was performed in several scenarios. The results showed that the proposed fault identification scheme produced more reliable diagnosis results than linear methods. In addition, the use of the filtering step improved the identification results for the complicated processes with massive data sets.

Keywords: diagnosis, filtering, nonlinear statistical techniques, process monitoring

Procedia PDF Downloads 243

Authors: R. Simutis, V. Galvanauskas, D. Levisauskas, J. Repsyte, V. Grincas

Abstract:

This paper deals with advanced state estimation algorithms for estimation of biomass concentration and specific growth rate in a typical fed-batch biotechnological process. This biotechnological process was represented by a nonlinear mass-balance based process model. Extended Kalman Filter (EKF) and Particle Filter (PF) was used to estimate the unmeasured state variables from oxygen uptake rate (OUR) and base consumption (BC) measurements. To obtain more general results, a simplified process model was involved in EKF and PF estimation algorithms. This model doesn’t require any special growth kinetic equations and could be applied for state estimation in various bioprocesses. The focus of this investigation was concentrated on the comparison of the estimation quality of the EKF and PF estimators by applying different measurement noises. The simulation results show that Particle Filter algorithm requires significantly more computation time for state estimation but gives lower estimation errors both for biomass concentration and specific growth rate. Also the tuning procedure for Particle Filter is simpler than for EKF. Consequently, Particle Filter should be preferred in real applications, especially for monitoring of industrial bioprocesses where the simplified implementation procedures are always desirable.

Keywords: biomass concentration, extended Kalman filter, particle filter, state estimation, specific growth rate

Procedia PDF Downloads 428

Authors: Andressa dos Santos Nicolau, João P. da S.C Algusto, Claudio Márcio do N. A. Pereira, Roberto Schirru

Abstract:

In case of abnormal situations, the nuclear power plant (NPP) operators must follow written procedures to check the condition of the plant and to classify the type of emergency. In this paper, we proposed a Real Time Expert System in order to improve operator’s performance in case of transient or accident with reactor shutdown. The expert system’s knowledge is based on the sequence of events (SoE) of known accident and two emergency procedures of the Brazilian Pressurized Water Reactor (PWR) NPP and uses two kinds of knowledge representation: rule and logic trees. The results show that the system was able to classify the response of the automatic protection systems, as well as to evaluate the conditions of the plant, diagnosing the type of occurrence, recovery procedure to be followed, indicating the shutdown root cause, and classifying the emergency level.

Keywords: emergence procedure, expert system, operator support, PWR nuclear power plant

Procedia PDF Downloads 333

Authors: Shrey Sharma, Gunjan Kumar Verma

Abstract:

High density electrical prospecting has been widely used in groundwater investigation, civil engineering and environmental survey. For efficient inversion, the forward modeling routine, sensitivity calculation, and inversion algorithm must be efficient. This paper attempts to provide a brief summary of the past and ongoing developments of the method. It includes reviews of the procedures used for data acquisition, processing and inversion of electrical resistivity data based on compilation of academic literature. In recent times there had been a significant evolution in field survey designs and data inversion techniques for the resistivity method. In general 2-D inversion for resistivity data is carried out using the linearized least-square method with the local optimization technique .Multi-electrode and multi-channel systems have made it possible to conduct large 2-D, 3-D and even 4-D surveys efficiently to resolve complex geological structures that were not possible with traditional 1-D surveys. 3-D surveys play an increasingly important role in very complex areas where 2-D models suffer from artifacts due to off-line structures. Continued developments in computation technology, as well as fast data inversion techniques and software, have made it possible to use optimization techniques to obtain model parameters to a higher accuracy. A brief discussion on the limitations of the electrical resistivity method has also been presented.

Keywords: inversion, limitations, optimization, resistivity

Procedia PDF Downloads 365