Search results for: inverse models of data envelopment analysis

Authors: Beulah Rani Inbanathan

Abstract:

In the present era, it is vivid from the numerous outcomes that data privacy is being compromised in various ways. Machine learning is one technology that uses the centralized server, and then data is given as input which is being analyzed by the algorithms present on this mentioned server, and hence outputs are predicted. However, each time the data must be sent by the user as the algorithm will analyze the input data in order to predict the output, which is prone to threats. The solution to overcome this issue is federated learning, where the models alone get updated while the data resides on the local machine and does not get exchanged with the other local models. Nevertheless, even on these local models, there are chances of data poisoning, and it is crystal clear from various experiments done by many people. This paper delves into many ways where data poisoning occurs and the many methods through which it is prevalent that data poisoning still exists. It includes the poisoning attacks on IoT devices, Edge devices, Autoregressive model, and also, on Industrial IoT systems and also, few points on how these could be evadible in order to protect our data which is personal, or sensitive, or harmful when exposed.

Keywords: data poisoning, federated learning, Internet of Things, edge computing

Procedia PDF Downloads 87

Authors: Kyle De Freitas, Margaret Bernard

Abstract:

Enabling data mining analysis among a wider audience of educators is an active area of research within the educational data mining (EDM) community. The paper proposes a framework for developing an environment that caters for educators who have little technical data mining skills as well as for more advanced users with some data mining expertise. This framework architecture was developed through the review of the strengths and weaknesses of existing models in the literature. The proposed framework provides a modular architecture for future researchers to focus on the development of specific areas within the EDM process. Finally, the paper also highlights a strategy of enabling analysis through either the use of predefined questions or a guided data mining process and highlights how the developed questions and analysis conducted can be reused and extended over time.

Keywords: educational data mining, learning management system, learning analytics, EDM framework

Procedia PDF Downloads 326

Authors: Ekin Ozer

Abstract:

Assessment of structural reliability is essential for efficient use of civil infrastructure which is subjected hazardous events. Dynamic analysis of finite element models is a commonly used tool to simulate structural behavior and estimate its performance accordingly. However, theoretical models purely based on preliminary assumptions and design drawings may deviate from the actual behavior of the structure. This study proposes up-to-date reliability estimation procedures which engages actual bridge vibration data modifying finite element models for finite element model updating and performing reliability estimation, accordingly. The proposed method utilizes vibration response measurements of bridge structures to identify modal parameters, then uses these parameters to calibrate finite element models which are originally based on design drawings. The proposed method does not only show that reliability estimation based on updated models differs from the original models, but also infer that non-updated models may overestimate the structural capacity.

Keywords: earthquake engineering, engineering vibrations, reliability estimation, structural health monitoring

Procedia PDF Downloads 222

Authors: Akhila Vasudev, Himanshu Kaushik, Tadikonda Venkata Bharat

Abstract:

A large number of mine tailings are produced every year as part of the extraction process of phosphates, gold, copper, and other materials. Mine tailings are high in water content and have very slow dewatering behavior. The efficient design of tailings dam and economical disposal of these slurries requires the knowledge of tailings consolidation behavior. The large-strain consolidation theory closely predicts the self-weight consolidation of these slurries as the theory considers the conservation of mass and momentum conservation and considers the hydraulic conductivity as a function of void ratio. Classical laboratory techniques, such as settling column test, seepage consolidation test, etc., are expensive and time-consuming for the estimation of hydraulic conductivity variation with void ratio. Inverse estimation of the constitutive relationships from the measured settlement versus time curves is explored. In this work, inverse analysis based on metaheuristics techniques will be explored for predicting the hydraulic conductivity parameters for mine tailings from the base excess pore water pressure dissipation curve and the initial conditions of the mine tailings. The proposed inverse model uses particle swarm optimization (PSO) algorithm, which is based on the social behavior of animals searching for food sources. The finite-difference numerical solution of the forward analytical model is integrated with the PSO algorithm to solve the inverse problem. The method is tested on synthetic data of base excess pore pressure dissipation curves generated using the finite difference method. The effectiveness of the method is verified using base excess pore pressure dissipation curve obtained from a settling column experiment and further ensured through comparison with available predicted hydraulic conductivity parameters.

Keywords: base excess pore pressure, hydraulic conductivity, large strain consolidation, mine tailings

Procedia PDF Downloads 133

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 141

Authors: Lu Yung-Hsiang, Chang Kuming, Dai Yi-Fang, Liao Ching-Yi

Abstract:

According to Taiwan’s administrative division of future land planning may lead farmer association and service areas facing recombination or merger. Thus, merger combination and the economic benefit of the farmer association are worth to be discussed. The farmer association in the merger, which may cause some then will not be consolidated, or consolidate two, or ever more to one association. However, under what condition to merge is greatest, as one of observation of this study. In addition, research without using simulation methods and only on the credit department rather whole farmer association. Therefore, this paper will use the simulation approach, and examine both the merge of farmer association and the condition under which the benefits are the greatest. The data of this study set include 266 farmer associations in Taiwan period 2012 to 2013. Empirical results showed that the number of the farmer association optimal simulation combination is 108.After the merger from the first stage can be reduced by 60% of the farmers’ association. The cost saving effects of the post-merger is not different. The cost efficiency of the farmers’ association improved it. The economies of scale and scope would decrease by the merger. The research paper hopes the finding will benefit the future merger of the farmers’ association.

Keywords: simulation merger, farmer association, assurance region, data envelopment analysis

Procedia PDF Downloads 350

Authors: Alaa Fezai, Anuj Sharma, Wolfgang Mueller-Hirsch, André Zimmermann

Abstract:

Viscoelastic materials have been widely used in the automotive industry over the last few decades with different functionalities. Besides their main application as a simple and efficient surface damping treatment, they may ensure optimal operating conditions for on-board electronics as thermal interface or sealing layers. The dynamic behavior of viscoelastic materials is generally dependent on many environmental factors, the most important being temperature and strain rate or frequency. Prior to the reliability analysis of systems including viscoelastic layers, it is, therefore, crucial to accurately predict the dynamic and lifetime behavior of these materials. This includes the identification of the dynamic material parameters under critical temperature and frequency conditions along with a precise damage localization and identification methodology. The goal of this work is twofold. The first part aims at applying an inverse viscoelastic material-characterization approach for a wide frequency range and under different temperature conditions. For this sake, dynamic measurements are carried on a single lap joint specimen using an electrodynamic shaker and an environmental chamber. The specimen consists of aluminum beams assembled to adapter plates through a viscoelastic adhesive layer. The experimental setup is reproduced in finite element (FE) simulations, and frequency response functions (FRF) are calculated. The parameters of both the generalized Maxwell model and the fractional derivatives model are identified through an optimization algorithm minimizing the difference between the simulated and the measured FRFs. The second goal of the current work is to guarantee an on-line detection of the damage, i.e., delamination in the viscoelastic bonding of the described specimen during frequency monitored end-of-life testing. For this purpose, an inverse technique, which determines the damage location and size based on the modal frequency shift and on the change of the mode shapes, is presented. This includes a preliminary FE model-based study correlating the delamination location and size to the change in the modal parameters and a subsequent experimental validation achieved through dynamic measurements of specimen with different, pre-generated crack scenarios and comparing it to the virgin specimen. The main advantage of the inverse characterization approach presented in the first part resides in the ability of adequately identifying the material damping and stiffness behavior of soft viscoelastic materials over a wide frequency range and under critical temperature conditions. Classic forward characterization techniques such as dynamic mechanical analysis are usually linked to limitations under critical temperature and frequency conditions due to the material behavior of soft viscoelastic materials. Furthermore, the inverse damage detection described in the second part guarantees an accurate prediction of not only the damage size but also its location using a simple test setup and outlines; therefore, the significance of inverse numerical-experimental approaches in predicting the dynamic behavior of soft bonding layers applied in automotive electronics.

Keywords: damage detection, dynamic characterization, inverse approaches, vibration testing, viscoelastic layers

Procedia PDF Downloads 205

Authors: Vigen Arakelian

Abstract:

This paper deals with the study of devices for displacement of the mould base of blow-molding machines. The displacement of the mould in the studied case is carried out by a linear actuator, which ensures the descent of the mould base and by extension springs, which return the letter in the initial position. The aim of this paper is to study the inverse dynamics of the device for displacement of the mould base of blow-molding machines and to determine its optimum parameters for higher rate of production. In the other words, it is necessary to solve the inverse dynamic problem to find the equation of motion linking applied forces with displacements. This makes it possible to determine the stiffness coefficient of the spring to turn the mold base back to the initial position for a given time. The obtained results are illustrated by a numerical example. It is shown that applying a spring with stiffness returns the mould base of the blow molding machine into the initial position in 0.1 sec.

Keywords: design, mechanisms, dynamics, blow-molding machines

Procedia PDF Downloads 153

Authors: Sanja O. Podunavac-Kuzmanović, Strahinja Z. Kovačević, Lidija R. Jevrić, Stela Jokić

Abstract:

The subject of this paper is to correlate antibacterial behavior of benzimidazole derivatives with their molecular characteristics using chemometric QSAR (Quantitative Structure–Activity Relationships) approach. QSAR analysis has been carried out on the inhibitory activity of benzimidazole derivatives against Staphylococcus aureus. The data were processed by linear least squares (LLS) and artificial neural network (ANN) procedures. The LLS mathematical models have been developed as a calibration models for prediction of the inhibitory activity. The quality of the models was validated by leave one out (LOO) technique and by using external data set. High agreement between experimental and predicted inhibitory acivities indicated the good quality of the derived models. These results are part of the CMST COST Action No. CM1306 "Understanding Movement and Mechanism in Molecular Machines".

Keywords: Antibacterial, benzimidazoles, chemometric, QSAR.

Procedia PDF Downloads 316

Authors: Reza Zakerinejad

Abstract:

Gully erosion is a serious problem that threading the sustainability of agricultural area and rangeland and water in a large part of Iran. This type of water erosion is the main source of sedimentation in many catchment areas in the north of Iran. Since in many national assessment approaches just qualitative models were applied the aim of this study is to predict the spatial distribution of gully erosion processes by means of detail terrain analysis and GIS -based logistic regression in the loess deposition in a case study in the Golestan Province. This study the DEM with 25 meter result ion from ASTER data has been used. The Landsat ETM data have been used to mapping of land use. The TreeNet model as a stochastic modeling was applied to prediction the susceptible area for gully erosion. In this model ROC we have set 20 % of data as learning and 20 % as learning data. Therefore, applying the GIS and satellite image analysis techniques has been used to derive the input information for these stochastic models. The result of this study showed a high accurate map of potential for gully erosion.

Keywords: TreeNet model, terrain analysis, Golestan Province, Iran

Procedia PDF Downloads 535

Authors: Liang Liu, Xiaopeng Luo

Abstract:

In this paper, we propose an accelerated stochastic gradient method with momentum. The momentum term is the weighted average of generated gradients, and the weights decay inverse proportionally with the iteration times. Stochastic gradient descent with momentum (SGDM) uses weights that decay exponentially with the iteration times to generate the momentum term. Using exponential decay weights, variants of SGDM with inexplicable and complicated formats have been proposed to achieve better performance. However, the momentum update rules of our method are as simple as that of SGDM. We provide theoretical convergence analyses, which show both the exponential decay weights and our inverse proportional decay weights can limit the variance of the parameter moving directly to a region. Experimental results show that our method works well with many practical problems and outperforms SGDM.

Keywords: exponential decay rate weight, gradient descent, inverse proportional decay rate weight, momentum

Procedia PDF Downloads 162

Authors: Pranav Gunhal

Abstract:

This paper presents an analysis of sentiment on Twitter towards the Karnataka elections held in 2023, utilizing transformer-based models specifically designed for sentiment analysis in Indic languages. Through an innovative data collection approach involving a combination of novel methods of data augmentation, online data preceding the election was analyzed. The study focuses on sentiment classification, effectively distinguishing between positive, negative, and neutral posts while specifically targeting the sentiment regarding the loss of the Bharatiya Janata Party (BJP) or the win of the Indian National Congress (INC). Leveraging high-performing transformer architectures, specifically IndicBERT, coupled with specifically fine-tuned hyperparameters, the AI models employed in this study achieved remarkable accuracy in predicting the INC’s victory in the election. The findings shed new light on the potential of cutting-edge transformer-based models in capturing and analyzing sentiment dynamics within the Indian political landscape. The implications of this research are far-reaching, providing invaluable insights to political parties for informed decision-making and strategic planning in preparation for the forthcoming 2024 Lok Sabha elections in the nation.

Keywords: sentiment analysis, twitter, Karnataka elections, congress, BJP, transformers, Indic languages, AI, novel architectures, IndicBERT, lok sabha elections

Procedia PDF Downloads 84

Authors: Abiodun Ayodele Sanyaolu

Abstract:

The research was carried out to investigate the time series analysis on quarterly production of fruit juice at the National Horticultural Research Institute Ibadan from 2010 to 2018. Documentary method of data collection was used, and the method of least square and moving average were used in the analysis. From the calculation and the graph, it was glaring that there was increase, decrease, and uniform movements in both the graph of the original data and the tabulated quarter values of the original data. Time series analysis was used to detect the trend in the highest number of fruit juice and it appears to be good over a period of time and the methods used to forecast are additive and multiplicative models. Since it was observed that the production of fruit juice is usually high in January of every year, it is strongly advised that National Horticultural Research Institute should make more provision for fruit juice storage outside this period of the year.

Keywords: fruit juice, least square, multiplicative models, time series

Procedia PDF Downloads 142

Authors: Susmita Panda, Arnab Banerjee, Ajinkya Baxy, Bappaditya Manna

Abstract:

The design of short to medium-span high-speed bridges in critical locations is an essential aspect of vehicle-bridge interaction. Due to dynamic interaction between moving load and bridge, mathematical models or finite element modeling computations become time-consuming. Thus, to reduce the computational effort, a universal approximator using an artificial neural network (ANN) has been used to evaluate the dynamic response of the bridge. The data set generation and training of surrogate models have been conducted over the results obtained from mathematical modeling. Further, the robustness of the surrogate model has been investigated, which showed an error percentage of less than 10% with conventional methods. Additionally, the dependency of the dynamic response of the bridge on various load and bridge parameters has been highlighted through a parametric study.

Keywords: artificial neural network, mode superposition method, moving load analysis, surrogate models

Procedia PDF Downloads 100

Authors: Htet Khaing Lin

Abstract:

This study explores the relationship between a diverse set of variables, encompassing both environmental and socio-economic factors, and poverty levels in the Philippines for the years 2012, 2015, and 2018. Employing Ordinary Least Squares (OLS), Spatial Lag Models (SLM), and Spatial Error Models (SEM), this study delves into the dynamics of key indicators, including daytime and nighttime land surface temperature, cropland surface, urban land surface, rainfall, population size, normalized difference water, vegetation, and drought indices. The findings reveal consistent patterns and unexpected correlations, highlighting the need for nuanced policies that address the multifaceted challenges arising from the interplay of environmental and socio-economic factors.

Keywords: poverty analysis, OLS, spatial lag models, spatial error models, Philippines, google earth engine, satellite data, environmental dynamics, socio-economic factors

Procedia PDF Downloads 99

Authors: Ionel D. Craiu, Mihai Nedelcu

Abstract:

Thin-walled cylinders are often used by the offshore industry as columns of floating installations. Based on observed strains, the inverse Finite Element Method (iFEM) may rebuild the deformation of structures. Structural Health Monitoring uses this approach extensively. However, the number of in-situ strain gauges is what determines how accurate it is, and for shell structures with complicated deformation, this number can easily become too high for practical use. Any thin-walled beam member's complicated deformation can be modeled by the Generalized Beam Theory (GBT) as a linear combination of pre-specified cross-section deformation modes. GBT uses bar finite elements as opposed to shell finite elements. This paper proposes an iFEM/GBT formulation for the shape sensing of thin-walled cylinders based on these benefits. This method significantly reduces the number of strain gauges compared to using the traditional inverse-shell finite elements. Using numerical simulations, dent damage detection is achieved by comparing the strain distributions of the undamaged and damaged members. The effect of noise on strain measurements is also investigated.

Keywords: damage detection, generalized beam theory, inverse finite element method, shape sensing

Procedia PDF Downloads 113

Authors: Hammadi Larbi

Abstract:

The major problem with oil-based drilling muds (reverse emulsions) is their thermodynamic instability and their high tendency to coalescence over time, irreversibly leading to destabilization. Water/Oil reverse emulsion drilling Muds are highly recommended when significant depths are reached. This study aimed to contribute experimentally to the knowledge of the structure (stability) and rheological behavior of drilling mud systems based on water/crude oil inverse emulsions through the investigation of the effect of organophilic clay. The chemical composition of organophilic clay such as VG69 shows a strong presence of silicon oxide (SiO2), followed by aluminum oxide (Al2O3), so these two elements are considered to be the main constituents of organophilic clays. The study also shows that the SiO2/Al2O3 ratio is equal to 3.52, which can be explained by the high content of free silica contained in the organophile clay used. The particle size analysis of the organophilic clays showed that the size of the of the particles analysed is in the range of 30 to 80 μm, this result ensures the correct particle size quality of organophilic clays and allows these powders to be used in Drilling mud systems.The experimental data of steady-state flow measurements are analyzed in the classic way by the Herschel-Bulkley model. Microscopic observation shows that the addition of quantities of organophilic clay type VG69 less than or equal to 3 g leading to the stability of the water/oil inverse emulsions, on the other hand, for quantities greater than 3 g, the emulsions are destabilized. The results obtained also showed that adding 3 g of organophilic clay to the crude oil drilling mud improves their stability by 70%.

Keywords: drilling muds, inverse emulsions, rheological behavior, yield stress, stability, organophilic clay

Procedia PDF Downloads 11

Authors: Y. Tiamaz, N. Souissi

Abstract:

The purpose of this paper is to present a classification of Lean models which aims to capture all the concepts related to this approach and thus facilitate its implementation. This classification allows the identification of the most relevant models according to several dimensions. From this perspective, we present a review and an analysis of Lean models literature and we propose dimensions for the classification of the current proposals while respecting among others the axes of the Lean approach, the maturity of the models as well as their application domains. This classification allowed us to conclude that researchers essentially consider the Lean approach as a toolbox also they design their models to solve problems related to a specific environment. Since Lean approach is no longer intended only for the automotive sector where it was invented, but to all fields (IT, Hospital, ...), we consider that this approach requires a generic model that is capable of being implemented in all areas.

Keywords: lean approach, lean models, classification, dimensions, holistic view

Procedia PDF Downloads 434

Authors: M. P. Nanda Kumar, K. Dheeraj

Abstract:

The design of a feedback controller, so as to minimize a given performance criterion, for a general non-linear dynamical system is difficult; if not impossible. But for a large class of non-linear dynamical systems, the open loop control that minimizes a performance criterion can be obtained using calculus of variations and Pontryagin’s minimum principle. In this paper, the open loop optimal trajectories, that minimizes a given performance measure, is used to train the neural network whose inputs are state variables of non-linear dynamical systems and the open loop optimal control as the desired output. This trained neural network is used as the feedback controller. In other words, attempts are made here to solve the “inverse optimal control problem” by using the state and control trajectories that are optimal in an open loop sense.

Keywords: inverse optimal control, radial basis function, neural network, controller design

Procedia PDF Downloads 553

Authors: Seyoung Kim, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

A database that records average traffic speeds measured at five-minute intervals for all the links in the traffic network of a metropolitan city. While learning from this data the models that can predict future traffic speed would be beneficial for the applications such as the car navigation system, building predictive models for every link becomes a nontrivial job if the number of links in a given network is huge. An advantage of adopting k-nearest neighbor (k-NN) as predictive models is that it does not require any explicit model building. Instead, k-NN takes a long time to make a prediction because it needs to search for the k-nearest neighbors in the database at prediction time. In this paper, we investigate how much we can speed up k-NN in making traffic speed predictions by reducing the amount of data to be searched for without a significant sacrifice of prediction accuracy. The rationale behind this is that we had a better look at only the recent data because the traffic patterns not only repeat daily or weekly but also change over time. In our experiments, we build several different k-NN models employing different sets of features which are the current and past traffic speeds of the target link and the neighbor links in its up/down-stream. The performances of these models are compared by measuring the average prediction accuracy and the average time taken to make a prediction using various amounts of data.

Keywords: big data, k-NN, machine learning, traffic speed prediction

Procedia PDF Downloads 363

Authors: Z. Sadeghi, M. R. Omidkhah, M. E. Masoomi

Abstract:

The purpose of this paper is to examine gas transport behavior of mixed matrix membranes (MMMs) combined with porous particles. Main existing models are categorized in two main groups; two-phase (ideal contact) and three-phase (non-ideal contact). A new coefficient, J, was obtained to express equations for estimating effect of the particle porosity in two-phase and three-phase models. Modified models evaluates with existing models and experimental data using Matlab software. Comparison of gas permeability of proposed modified models with existing models in different MMMs shows a better prediction of gas permeability in MMMs.

Keywords: mixed matrix membrane, permeation models, porous particles, porosity

Procedia PDF Downloads 384

Authors: Amadou Wurry Jallow, Adama N. S. Bah, Karamo Bah, Shih-Ye Wang, Kuo-Chung Chu, Chien-Yeh Hsu

Abstract:

Chronic kidney disease (CKD) is a major public health challenge with high prevalence, rising incidence, and serious adverse consequences. Developing effective risk prediction models is a cost-effective approach to predicting and preventing complications of chronic kidney disease (CKD). This study aimed to develop an accurate machine learning model that can dynamically identify individuals at risk of CKD using various kinds of diagnostic data, with or without laboratory data, at different follow-up points. Creatinine is a key component used to predict CKD. These models will enable affordable and effective screening for CKD even with incomplete patient data, such as the absence of creatinine testing. This retrospective cohort study included data on 19,429 adults provided by a private research institute and screening laboratory in Taiwan, gathered between 2001 and 2015. Univariate Cox proportional hazard regression analyses were performed to determine the variables with high prognostic values for predicting CKD. We then identified interacting variables and grouped them according to diagnostic data categories. Our models used three types of data gathered at three points in time: non-laboratory, laboratory, and metabolic indices data. Next, we used subgroups of variables within each category to train two machine learning models (Random Forest and XGBoost). Our machine learning models can dynamically discriminate individuals at risk for developing CKD. All the models performed well using all three kinds of data, with or without laboratory data. Using only non-laboratory-based data (such as age, sex, body mass index (BMI), and waist circumference), both models predict chronic kidney disease as accurately as models using laboratory and metabolic indices data. Our machine learning models have demonstrated the use of different categories of diagnostic data for CKD prediction, with or without laboratory data. The machine learning models are simple to use and flexible because they work even with incomplete data and can be applied in any clinical setting, including settings where laboratory data is difficult to obtain.

Keywords: chronic kidney disease, glomerular filtration rate, creatinine, novel metabolic indices, machine learning, risk prediction

Procedia PDF Downloads 105

Authors: H. Hruschka

Abstract:

This paper presents the first comparison of the performance of the restricted Boltzmann machine and the deep belief net on binary market basket data relative to binary factor analysis and the two best-known topic models, namely Dirichlet allocation and the correlated topic model. This comparison shows that the restricted Boltzmann machine and the deep belief net are superior to both binary factor analysis and topic models. Managerial implications that differ between the investigated models are treated as well. The restricted Boltzmann machine is defined as joint Boltzmann distribution of hidden variables and observed variables (purchases). It comprises one layer of observed variables and one layer of hidden variables. Note that variables of the same layer are not connected. The comparison also includes deep belief nets with three layers. The first layer is a restricted Boltzmann machine based on category purchases. Hidden variables of the first layer are used as input variables by the second-layer restricted Boltzmann machine which then generates second-layer hidden variables. Finally, in the third layer hidden variables are related to purchases. A public data set is analyzed which contains one month of real-world point-of-sale transactions in a typical local grocery outlet. It consists of 9,835 market baskets referring to 169 product categories. This data set is randomly split into two halves. One half is used for estimation, the other serves as holdout data. Each model is evaluated by the log likelihood for the holdout data. Performance of the topic models is disappointing as the holdout log likelihood of the correlated topic model – which is better than Dirichlet allocation - is lower by more than 25,000 compared to the best binary factor analysis model. On the other hand, binary factor analysis on its own is clearly surpassed by both the restricted Boltzmann machine and the deep belief net whose holdout log likelihoods are higher by more than 23,000. Overall, the deep belief net performs best. We also interpret hidden variables discovered by binary factor analysis, the restricted Boltzmann machine and the deep belief net. Hidden variables characterized by the product categories to which they are related differ strongly between these three models. To derive managerial implications we assess the effect of promoting each category on total basket size, i.e., the number of purchased product categories, due to each category's interdependence with all the other categories. The investigated models lead to very different implications as they disagree about which categories are associated with higher basket size increases due to a promotion. Of course, recommendations based on better performing models should be preferred. The impressive performance advantages of the restricted Boltzmann machine and the deep belief net suggest continuing research by appropriate extensions. To include predictors, especially marketing variables such as price, seems to be an obvious next step. It might also be feasible to take a more detailed perspective by considering purchases of brands instead of purchases of product categories.

Keywords: binary factor analysis, deep belief net, market basket analysis, restricted Boltzmann machine, topic models

Procedia PDF Downloads 199

Authors: Solaine Hachem, Frédéric Bourquin, Dominique Siegert

Abstract:

The brutal collapse of bridges is mainly due to scour. Indeed, the soil erosion in the riverbed around a pier modifies the embedding conditions of the structure, reduces its overall stiffness and threatens its stability. Hence, finding an efficient technique that allows early scour detection becomes mandatory. Vibration analysis is an indirect method for scour detection that relies on real-time monitoring of the bridge. It tends to indicate the presence of a scour based on its consequences on the stability of the structure and its dynamic response. Most of the research in this field has focused on the dynamic behavior of a single pile and has examined the depth of the scour. In this paper, a bridge is fully modeled with all piles and spans and the scour is represented by a reduction in the foundation's stiffnesses. This work aims to identify the vibration modes sensitive to the rigidity’s loss in the foundations so that their variations can be considered as a scour indicator: the decrease in soil-structure interaction rigidity leads to a decrease in the natural frequencies’ values. By using the first-order perturbation method, the expression of sensitivity, which depends only on the selected vibration modes, is established to determine the deficiency of foundations stiffnesses. The solutions are obtained by using the singular value decomposition method for the regularization of the inverse problem. The propagation of uncertainties is also calculated to verify the efficiency of the inverse problem method. Numerical simulations describing different scenarios of scour are investigated on a simplified model of a real composite steel-concrete bridge located in France. The results of the modal analysis show that the modes corresponding to in-plane and out-of-plane piers vibrations are sensitive to the loss of foundation stiffness. While the deck bending modes are not affected by this damage.

Keywords: bridge’s piers, inverse problems, modal sensitivity, scour detection, vibration analysis

Procedia PDF Downloads 104

Authors: P. Sankar, P. James Daniel Paul, Siddhant Sahu

Abstract:

A brief review of the empirical studies on the methodology of the stock market decision support would indicate that they are at a threshold of validating the accuracy of the traditional and the fuzzy, artificial neural network and the decision trees. Many researchers have been attempting to compare these models using various data sets worldwide. However, the research community is on the way to the conclusive confidence in the emerged models. This paper attempts to use the automotive sector stock prices from National Stock Exchange (NSE), India and analyze them for the intra-sectorial support for stock market decisions. The study identifies the significant variables and their lags which affect the price of the stocks using OLS analysis and decision tree classifiers.

Keywords: Indian automotive sector, stock market decisions, equity portfolio analysis, decision tree classifiers, statistical data analysis

Procedia PDF Downloads 485

Authors: Othmane Touri, Sanaa El Filali, El Habib Benlahmar

Abstract:

Natural Language Processing (NLP) has gained significant attention lately. It has proved its ability to analyze and extract insights from unstructured text data in various languages. It is found that one of the most popular NLP applications is sentiment analysis which aims to identify the sentiment expressed in a piece of text, such as positive, negative, or neutral, in multiple languages. While there are several multilingual NLP models available for sentiment analysis, there is a need to investigate their effectiveness in different contexts and applications. In this study, we aim to investigate the effectiveness of different multilingual NLP models for sentiment analysis on a dataset of online product reviews in multiple languages. The performance of several NLP models, including Google Cloud Natural Language API, Microsoft Azure Cognitive Services, Amazon Comprehend, Stanford CoreNLP, spaCy, and Hugging Face Transformers are being compared. The models based on several metrics, including accuracy, precision, recall, and F1 score, are being evaluated and compared to their performance across different categories of product reviews. In order to run the study, preprocessing of the dataset has been performed by cleaning and tokenizing the text data in multiple languages. Then training and testing each model has been applied using a cross-validation approach where randomly dividing the dataset into training and testing sets and repeating the process multiple times has been used. A grid search approach to optimize the hyperparameters of each model and select the best-performing model for each category of product reviews and language has been applied. The findings of this study provide insights into the effectiveness of different multilingual NLP models for Multilingual Sentiment Analysis and their suitability for different languages and applications. The strengths and limitations of each model were identified, and recommendations for selecting the most performant model based on the specific requirements of a project were provided. This study contributes to the advancement of research methods in multilingual NLP and provides a practical guide for researchers and practitioners in the field.

Keywords: NLP, multilingual, sentiment analysis, texts

Procedia PDF Downloads 102

Authors: Young Nam Jo, Moon Jeong Kang, Hong Hee Yoo

Abstract:

Most human vibration models have been modeled as a multibody system consisting of some rigid bodies and spring-dampers. These models are developed for certain posture and conditions. So, the models cannot be used in vibration analysis in various posture and conditions. The purpose of this study is to develop a human vibration model that represent human vibration characteristics under various conditions by employing a musculoskeletal model. To do this, the human vibration model is developed based on biomechanical models. In addition, muscle models are employed instead of spring-dampers. Activations of muscles are controlled by PD controller to maintain body posture under vertical vibration is applied. Each gain value of the controller is obtained to minimize the difference of apparent mass and acceleration transmissibility between experim ent and analysis by using an optimization method.

Keywords: human vibration analysis, hill type muscle model, PD control, whole-body vibration

Procedia PDF Downloads 448

Authors: Slim Namouchi, Bruno Vallet, Imed Riadh Farah

Abstract:

3D urban models provide powerful tools for decision making, urban planning, and smart city services. The accuracy of this 3D based systems is directly related to the quality of these models. Since manual large-scale modeling, such as cities or countries is highly time intensive and very expensive process, a fully automatic 3D building generation is needed. However, 3D modeling process result depends on the input data, the proprieties of the captured objects, and the required characteristics of the reconstructed 3D model. Nowadays, producing 3D real-world model is no longer a problem. Remotely sensed data had experienced a remarkable increase in the recent years, especially data acquired using unmanned aerial vehicles (UAV). While the scanning techniques are developing, the captured data amount and the resolution are getting bigger and more precise. This paper presents a literature review, which aims to identify different methods of automatic 3D buildings extractions either from LiDAR or the combination of LiDAR and satellite or aerial images. Then, we present open source technologies, and data models (e.g., CityGML, PostGIS, Cesiumjs) used to integrate these models in geospatial base layers for smart city services.

Keywords: CityGML, LiDAR, remote sensing, SIG, Smart City, 3D urban modeling

Procedia PDF Downloads 135

Authors: Farzad Sharifi, Raziyeh Shamsi

Abstract:

In this paper, we obtain the projection of inefficient units in data envelopment analysis (DEA) in the case of stochastic inputs and outputs using the multi-objective programming (MOP) structure. In some problems, the inputs might be stochastic while the outputs are deterministic, and vice versa. In such cases, we propose molti-objective DEA-R model, because in some cases (e.g., when unnecessary and irrational weights by the BCC model reduces the efficiency score), an efficient DMU is introduced as inefficient by the BCC model, whereas the DMU is considered efficient by the DEA-R model. In some other case, only the ratio of stochastic data may be available (e.g; the ratio of stochastic inputs to stochastic outputs). Thus, we provide multi objective DEA model without explicit outputs and prove that in-put oriented MOP DEA-R model in the invariable return to scale case can be replacing by MOP- DEA model without explicit outputs in the variable return to scale and vice versa. Using the interactive methods for solving the proposed model, yields a projection corresponding to the viewpoint of the DM and the analyst, which is nearer to reality and more practical. Finally, an application is provided.

Keywords: DEA, MOLP, STOCHASTIC, DEA-R

Procedia PDF Downloads 398

Authors: Ozan Kahraman, Hao Feng

Abstract:

Several models such as Weibull, Modified Gompertz, Biphasic linear, and Log-logistic models have been proposed in order to describe non-linear inactivation kinetics and used to fit non-linear inactivation data of several microorganisms for inactivation by heat, high pressure processing or pulsed electric field. First-order kinetic parameters (D-values and z-values) have often been used in order to identify microbial inactivation by non-thermal processing methods such as ultrasound. Most ultrasonic inactivation studies employed first-order kinetic parameters (D-values and z-values) in order to describe the reduction on microbial survival count. This study was conducted to analyze the E. coli O157:H7 inactivation data by using five microbial survival models (First-order, Weibull, Modified Gompertz, Biphasic linear and Log-logistic). First-order, Weibull, Modified Gompertz, Biphasic linear and Log-logistic kinetic models were used for fitting inactivation curves of Escherichia coli O157:H7. The residual sum of squares and the total sum of squares criteria were used to evaluate the models. The statistical indices of the kinetic models were used to fit inactivation data for E. coli O157:H7 by MTS at three temperatures (40, 50, and 60 0C) and three pressures (100, 200, and 300 kPa). Based on the statistical indices and visual observations, the Weibull and Biphasic models were best fitting of the data for MTS treatment as shown by high R2 values. The non-linear kinetic models, including the Modified Gompertz, First-order, and Log-logistic models did not provide any better fit to data from MTS compared the Weibull and Biphasic models. It was observed that the data found in this study did not follow the first-order kinetics. It is possibly because of the cells which are sensitive to ultrasound treatment were inactivated first, resulting in a fast inactivation period, while those resistant to ultrasound were killed slowly. The Weibull and biphasic models were found as more flexible in order to determine the survival curves of E. coli O157:H7 treated by MTS on apple-carrot juice.

Keywords: Weibull, Biphasic, MTS, kinetic models, E.coli O157:H7

Procedia PDF Downloads 365