Search results for: ensemble empirical mode decomposition (EEMD)

Authors: Fereshteh Chekin, Sepideh Sadeghi

Abstract:

Nickel nanoparticles have attracted much attention because of applications in catalysis, medical diagnostics and magnetic applications. In this work, we reported a simple and low-cost procedure to synthesize nickel oxide nanoparticles (NiO-NPs) by using sodium dodecyl sulphate (SDS) and gelatin as stabilizer. The synthesized NiO-NPs were characterized by a variety of means such as transmission electron microscope (TEM), powder X-ray diffraction (XRD), scanning electron microscope (SEM) and UV-vis spectroscopy. The results show that the NiO nanoparticles with high crystalline can be obtained using this simple method. The grain size measured by TEM was 16 in presence of SDS, which agrees well with the XRD data. SDS plays an important role in the formation of the NiO nanoparticles. Moreover, the NiO nanoparticles have been used as a solid phase catalyst for the decomposition of hydrazine hydrate at room temperatures. The decomposition process has been monitored by UV–vis analysis. The present study showed that nanoparticles are not poisoned after their repeated use in decomposition of hydrazine.

Keywords: nickel oxide nanoparticles, sodium dodecyl sulphate, synthesis, stabilizer

Procedia PDF Downloads 462

Authors: Almaz R. Gazizov, Sergey S. Kharintsev, Myakzyum Kh. Salakhov

Abstract:

This work deals with background signal suppression in tip-enhanced near-field optical microscopy (TENOM). The background appears because an optical signal is detected not only from the subwavelength area beneath the tip but also from a wider diffraction-limited area of laser’s waist that might contain another substance. The background can be reduced by using a taper probe with a grating on its lateral surface where an external illumination causes surface plasmon excitation. It requires the grating with parameters perfectly matched with a given incident light for effective light coupling. This work is devoted to an analysis of the light-grating coupling and a quest of grating parameters to enhance a near-field light beneath the tip apex. The aim of this work is to find the figure of merit of plasmon excitation depending on grating period and location of grating in respect to the apex. In our consideration the metallic grating on the lateral surface of the tapered plasmonic probe is illuminated by a plane wave, the electric field is perpendicular to the sample surface. Theoretical model of efficiency of plasmon excitation and propagation toward the apex is tested by fdtd-based numerical simulation. An electric field of the incident light is enhanced on the grating by every single slit due to lightning rod effect. Hence, grating causes amplitude and phase modulation of the incident field in various ways depending on geometry and material of grating. The phase-modulating grating on the probe is a sort of metasurface that provides manipulation by spatial frequencies of the incident field. The spatial frequency-dependent electric field is found from the angular spectrum decomposition. If one of the components satisfies the phase-matching condition then one can readily calculate the figure of merit of plasmon excitation, defined as a ratio of the intensities of the surface mode and the incident light. During propagation towards the apex, surface wave undergoes losses in probe material, radiation losses, and mode compression. There is an optimal location of the grating in respect to the apex. One finds the value by matching quadratic law of mode compression and the exponential law of light extinction. Finally, performed theoretical analysis and numerical simulations of plasmon excitation demonstrate that various surface waves can be effectively excited by using the overtones of a period of the grating or by phase modulation of the incident field. The gratings with such periods are easy to fabricate. Tapered probe with the grating effectively enhances and localizes the incident field at the sample.

Keywords: angular spectrum decomposition, efficiency, grating, surface plasmon, taper nanoantenna

Procedia PDF Downloads 260

Authors: Sony, Ashok N. Bhaskarwar

Abstract:

Production of hydrogen from a renewable raw material without any co-synthesis of harmful greenhouse gases is the current need for sustainable energy solutions. The sulfur-iodine (SI) thermochemical cycle, using intermediate chemicals, is an efficient process for producing hydrogen at a much lower temperature than that required for the direct splitting of water. No net byproduct forms in the cycle. Hydrogen iodide (HI) decomposition is a crucial reaction in this cycle, as the product, hydrogen, forms only in this step. It is an endothermic, reversible, and equilibrium-limited reaction. The theoretical equilibrium conversion at 550°C is just a meagre of 24%. There is a growing interest, therefore, in enhancing the HI conversion to near-equilibrium values at lower reaction temperatures and by possibly improving the rate. The reaction is relatively slow without a catalyst, and hence catalytic decomposition of HI has gained much significance. Bi-metallic Ni-Co, Ni-Mn, Co-Mn, and tri-metallic Ni-Co-Mn catalysts over zirconia support were tested for HI decomposition reaction. The catalysts were synthesized via a sol-gel process wherein Ni was 3wt% in all the samples, and Co and Mn had equal weight ratios in the Co-Mn catalyst. Powdered X-ray diffraction and Brunauer-Emmett-Teller surface area characterizations indicated the polycrystalline nature and well-developed mesoporous structure of all the samples. The experiments were performed in a vertical laboratory-scale packed bed reactor made of quartz, and HI (55 wt%) was fed along with nitrogen at a WHSV of 12.9 hr⁻¹. Blank experiments at 500°C for HI decomposition suggested conversion of less than 5%. The activities of all the different catalysts were checked at 550°C, and the highest conversion of 23.9% was obtained with the tri-metallic 3Ni-Co-Mn-ZrO₂ catalyst. The decreasing order of the performance of catalysts could be expressed as: 3Ni-Co-Mn-ZrO₂ > 3Ni-2Co-ZrO₂ > 3Ni-2Mn-ZrO₂ > 2.5Co-2.5Mn-ZrO₂. The tri-metallic catalyst remained active till 360 mins at 550°C without any observable drop in its activity/stability. Among the explored catalyst compositions, the tri-metallic catalyst certainly has a better performance for HI conversion when compared to the bi-metallic ones. Owing to their low costs and ease of preparation, these trimetallic catalysts could be used for large-scale hydrogen production.

Keywords: sulfur-iodine cycle, hydrogen production, hydrogen iodide decomposition, bi-, and tri-metallic catalysts

Procedia PDF Downloads 164

Authors: Loai Abdallah, Malik Yousef

Abstract:

A domain space for the data should reflect the actual similarity between objects. Since objects belonging to the same cluster usually share some common traits even though their geometric distance might be relatively large. In general, the Euclidean distance of data points that represented by large number of features is not capturing the actual relation between those points. In this study, we propose a new method to construct a different space that is based on clustering to form a new distance metric. The new distance space is based on ensemble clustering (EC). The EC distance space is defined by tracking the membership of the points over multiple runs of clustering algorithm metric. Over this distance, we train the decision trees classifier (DT-EC). The results obtained by applying DT-EC on 10 datasets confirm our hypotheses that embedding the EC space as a distance metric would improve the performance.

Keywords: ensemble clustering, decision trees, classification, K nearest neighbors

Procedia PDF Downloads 163

Authors: Lei Wang, Yingzhou Ni, Amr M. Bakry, Hao Cheng, Li Liang

Abstract:

Food proteins have been widely used as carrier materials because of their multiple functional properties. In this study, alfa-tocopherol was encapsulated in the oil phase of an oil-in-water emulsion stabilized with whey protein isolate (WPI). The influence of WPI concentration and resveratrol or ascorbic acid on the decomposition of alfa-tocopherol in the emulsion during storage is discussed. Decomposition decreased as WPI concentrations increased. Decomposition was delayed at ascorbic acid/WPI molar ratios lower than 5 but was promoted at higher ratios. Resveratrol partitioned into the oil-water interface by binding to WPI and its cis-isomer is believed to have contributed most of the protective effect of this polyphenol. These results suggest the possibility of using the emulsifying and ligand-binging properties of WPI to produce carriers for simultaneous encapsulation of alfa-tocopherol and resveratrol in a single emulsion system.

Keywords: stability, alfa-tocopherol, resveratrol, whey protein isolate

Procedia PDF Downloads 497

Authors: Sabrina Tabassum

Abstract:

Using Census Data for Housing and Population of Australia 2001, 2006, 2011, and 2016, this paper shows the existence of wage differences between natives and immigrants in Australia. Addressing the heterogeneous nature of immigrants, this study group the immigrants in three broad categories- migrants from English speaking countries and migrants from India and China. Migrants from English speaking countries and India earn more than the natives per week, whereas migrants from China earn far less than the natives per week. Oaxaca decomposition suggests that major part of this differential is unexplained. Using the occupational segregation concept and Brown decomposition, this study indicates that migrants from India and China would have been earned more than the natives if they had the same occupation distribution as natives due to their individual characteristics. Within occupation, wage differences are more prominent than inter-occupation wage differences for immigrants from China and India.

Keywords: Australia, labour, migration, wage

Procedia PDF Downloads 107

Authors: John Gichimu Mbaka, Jan Helmrich Martin von Baumbach, Celia Somlai, Denis Köpfer, Andreas Maeck, Andreas Lorke, Ralf Schäfer

Abstract:

Leaf litter decomposition is an important process providing energy to biotic communities. Additionally, methane gas (CH4) has been identified as an important alternative source of carbon and energy in some freshwater food webs.Flow regulation and dams can strongly alter freshwater ecosystems, but little is known about the effect of small impoundments on leaf litter decomposition and methane derived carbon in streams. In this study, we tested the effect of small water storage impoundments on leaf litter decomposition rates and methane derived carbon. Leaf litter decomposition rates were assessed by comparing treatment sites located close to nine impoundments (Rheinland Pfalz state, Germany) and reference sites located far away from the impoundments.CH4 concentrations were measured in eleven impoundments and correlated with the δ13C values of two subfamilies of chironomid larvae (i.e. Chironomini and Tanypodinae). Leaf litter break down rates were significantly lower in study sites located immediately above the impoundments, especially associated with a reduction in the abundance of shredders. Chironomini larvae had the lower mean δ13C values (‒29.2 to ‒25.5 ‰), than Tanypodinae larvae (‒26.9 to ‒25.3 ‰).No significant relationships were established between CH4 concentrations and δ13C values of chironomids (p> 0.05).Mean δ13C values of chironomid larvae (mean: ‒26.8‰, range: ‒ 29.2‰ to ‒ 25.3‰) were similar to those of sedimentary organic matter (SOM) (mean: ‒28.4‰, range: ‒ 29.3‰ to ‒ 27.1‰) and tree leaf litter (mean: ‒29.8 ‰, range: ‒ 30.5‰ to ‒ 29.1‰). In conclusion, this study demonstrates that small impoundments may have a negative effect on leaf litter decomposition in forest streams and that CH4 has limited influence on the benthic food web in stream impoundments.

Keywords: river functioning, chironomids, Alder tree, stable isotopes, methane oxidation, shredder

Procedia PDF Downloads 706

Authors: Othmane Boughazi, Abdelmadjid Boumedienne, Hachemi Glaoui

Abstract:

This work treats the modeling and simulation of non-linear system behavior of an induction motor using backstepping sliding mode control. First, the direct field oriented control IM is derived. Then, a sliding for direct field oriented control is proposed to compensate the uncertainties, which occur in the control.Finally, the study of Backstepping sliding controls strategy of the induction motor drive. Our non linear system is simulated in MATLAB SIMULINK environment, the results obtained illustrate the efficiency of the proposed control with no overshoot, and the rising time is improved with good disturbances rejections comparing with the classical control law.

Keywords: induction motor, proportional-integral, sliding mode control, backstepping sliding mode control

Procedia PDF Downloads 463

Authors: Rosa Tsegaye Aga, Xuan Jiang, Pavel Vazquez Faci, Siqing Liu, Simon Rayner, Endalkachew Alemu, Markos Abebe

Abstract:

Tuberculosis (TB) is a major cause of disease globally. In most cases, TB is treatable and curable, but only with the proper treatment. There is a time when drug-resistant TB occurs when bacteria become resistant to the drugs that are used to treat TB. Current strategies to identify drug-resistant TB bacteria are laboratory-based, and it takes a longer time to identify the drug-resistant bacteria and treat the patient accordingly. But machine learning (ML) and data science approaches can offer new approaches to the problem. In this study, we propose to develop an ML-based model to predict the antibiotic resistance phenotypes of TB isolates in minutes and give the right treatment to the patient immediately. The study has been using the whole genome sequence (WGS) of TB isolates as training data that have been extracted from the NCBI repository and contain different countries’ samples to build the ML models. The reason that different countries’ samples have been included is to generalize the large group of TB isolates from different regions in the world. This supports the model to train different behaviors of the TB bacteria and makes the model robust. The model training has been considering three pieces of information that have been extracted from the WGS data to train the model. These are all variants that have been found within the candidate genes (F1), predetermined resistance-associated variants (F2), and only resistance-associated gene information for the particular drug. Two major datasets have been constructed using these three information. F1 and F2 information have been considered as two independent datasets, and the third information is used as a class to label the two datasets. Five machine learning algorithms have been considered to train the model. These are Support Vector Machine (SVM), Random forest (RF), Logistic regression (LR), Gradient Boosting, and Ada boost algorithms. The models have been trained on the datasets F1, F2, and F1F2 that is the F1 and the F2 dataset merged. Additionally, an ensemble approach has been used to train the model. The ensemble approach has been considered to run F1 and F2 datasets on gradient boosting algorithm and use the output as one dataset that is called F1F2 ensemble dataset and train a model using this dataset on the five algorithms. As the experiment shows, the ensemble approach model that has been trained on the Gradient Boosting algorithm outperformed the rest of the models. In conclusion, this study suggests the ensemble approach, that is, the RF + Gradient boosting model, to predict the antibiotic resistance phenotypes of TB isolates by outperforming the rest of the models.

Keywords: machine learning, MTB, WGS, drug resistant TB

Procedia PDF Downloads 26

Authors: Khalid Mujaljal, Hassan Alhajhoj

Abstract:

This paper empirically investigates the influence of oil price fluctuations on the key macroeconomic variables of the Kingdom of Saudi Arabia using unrestricted VAR methodology. Two analytical tools- Granger-causality and variance decomposition are used. The Granger-causality test reveals that almost all specifications of oil price shocks significantly Granger-cause GDP and demonstrates evidence of causality between oil price changes and money supply (M3) and consumer price index percent (CPIPC) in the case of positive oil price shocks. Surprisingly, almost all specifications of oil price shocks do not Granger-cause government expenditure. The outcomes from variance decomposition analysis suggest that positive oil shocks contribute about 25 percent in causing inflation in the country. Also, contribution of symmetric linear oil price shocks and asymmetric positive oil price shocks is significant and persistent with 25 percent explaining variation in world consumer price index till end of the period.

Keywords: Granger causality, oil prices changes, Saudi Arabian economy, variance decomposition

Procedia PDF Downloads 301

Authors: Malika El Kyal, Ahmed Machmoum

Abstract:

We prove the superlinear convergence of asynchronous multi-splitting methods applied to differential equations. This study is based on the technique of nested sets. It permits to specify kind of the convergence in the asynchronous mode.The main characteristic of an asynchronous mode is that the local algorithm not have to wait at predetermined messages to become available. We allow some processors to communicate more frequently than others, and we allow the communication delays to be substantial and unpredictable. Note that synchronous algorithms in the computer science sense are particular cases of our formulation of asynchronous one.

Keywords: parallel methods, asynchronous mode, multisplitting, ODE

Procedia PDF Downloads 503

Authors: S. Khamtree, T. Ratanawilai, C. Nuntadusit

Abstract:

Rubberwood is a crucial commercial timber in Southern Thailand. All processes in a rubberwood production depend on the knowledge and expertise of the technicians, especially the drying process. This research aims to develop an empirical model for drying kinetics in rubberwood. During the experiment, the temperature of the hot air and the average air flow velocity were kept at 80-100 °C and 1.75 m/s, respectively. The moisture content in the samples was determined less than 12% in the achievement of drying basis. The drying kinetic was simulated using an empirical solver. The experimental results illustrated that the moisture content was reduced whereas the drying temperature and time were increased. The coefficient of the moisture ratio between the empirical and the experimental model was tested with three statistical parameters, R-square (R²), Root Mean Square Error (RMSE) and Chi-square (χ²) to predict the accuracy of the parameters. The experimental moisture ratio had a good fit with the empirical model. Additionally, the results indicated that the drying of rubberwood using the Henderson and Pabis model revealed the suitable level of agreement. The result presented an excellent estimation (R² = 0.9963) for the moisture movement compared to the other models. Therefore, the empirical results were valid and can be implemented in the future experiments.

Keywords: empirical models, rubberwood, moisture ratio, hot air drying

Procedia PDF Downloads 245

Authors: Nermin Sökmen

Abstract:

An effort estimation model is needed for software-intensive projects that consist of hardware, embedded software or some combination of the two, as well as high level software solutions. This paper first focuses on functional decomposition techniques to measure functional complexity of a computer system and investigates its impact on system development effort. Later, it examines effects of technical difficulty and design team capability factors in order to construct the best effort estimation model. With using traditional regression analysis technique, the study develops a system development effort estimation model which takes functional complexity, technical difficulty and design team capability factors as input parameters. Finally, the assumptions of the model are tested.

Keywords: functional complexity, functional decomposition, development effort, technical difficulty, design team capability, regression analysis

Procedia PDF Downloads 264

Authors: Aziz Sezgin, Yuksel Hacioglu, Nurkan Yagiz

Abstract:

Sliding mode controller for a vehicle active suspension system is designed in this study. The widely used quarter car model is preferred and it is aimed to improve the ride comfort of the passengers. The effect of the actuator time delay, which may arise due to the information processing, sensors or actuator dynamics, is also taken into account during the design of the controller. A sliding mode controller was designed that has taken into account the actuator time delay by using Smith predictor. The successful performance of the designed controller is confirmed via numerical results.

Keywords: sliding mode control, active suspension system, actuator, time delay, vehicle

Procedia PDF Downloads 381

Authors: Fabrizio Iezzi, Claudio Valente

Abstract:

The viscous damping in dynamic systems can be proportional or non-proportional. In the first case, the mode shapes are real whereas in the second case they are complex. From an engineering point of view, the complexity of the mode shapes is important in order to quantify the non-proportional damping. Different indices exist to provide estimates of the modal complexity. These indices are or not zero, depending whether the mode shapes are not or are complex. The modal density problem arises in the experimental identification when the dynamic systems have close modal frequencies. Depending on the entity of this closeness, the mode shapes can hold fictitious imaginary quantities that affect the values of the modal complexity indices. The results are the failing in the identification of the real or complex mode shapes and then of the proportional or non-proportional damping. The paper aims to show the influence of the modal density on the values of these indices in case of both proportional and non-proportional damping. Theoretical and pseudo-experimental solutions are compared to analyze the problem according to an appropriate mechanical system.

Keywords: complex mode shapes, dynamic systems identification, modal density, non-proportional damping

Procedia PDF Downloads 362

Authors: Saurabh Sharma, Yong Sun, Bruce Vernham

Abstract:

Accurate prediction of NOx emission is a continuous challenge in the field of diesel engine-out emission modeling. Performing experiments for each conditions and scenario cost significant amount of money and man hours, therefore model-based development strategy has been implemented in order to solve that issue. NOx formation is highly dependent on the burn gas temperature and the O₂ concentration inside the cylinder. The current empirical models are developed by calibrating the parameters representing the engine operating conditions with respect to the measured NOx. This makes the prediction of purely empirical models limited to the region where it has been calibrated. An alternative solution to that is presented in this paper, which focus on the utilization of in-cylinder combustion parameters to form a predictive semi-empirical NOx model. The result of this work is shown by developing a fast and predictive NOx model by using the physical parameters and empirical correlation. The model is developed based on the steady state data collected at entire operating region of the engine and the predictive combustion model, which is developed in Gamma Technology (GT)-Power by using Direct Injected (DI)-Pulse combustion object. In this approach, temperature in both burned and unburnt zone is considered during the combustion period i.e. from Intake Valve Closing (IVC) to Exhaust Valve Opening (EVO). Also, the oxygen concentration consumed in burnt zone and trapped fuel mass is also considered while developing the reported model.  Several statistical methods are used to construct the model, including individual machine learning methods and ensemble machine learning methods. A detailed validation of the model on multiple diesel engines is reported in this work. Substantial numbers of cases are tested for different engine configurations over a large span of speed and load points. Different sweeps of operating conditions such as Exhaust Gas Recirculation (EGR), injection timing and Variable Valve Timing (VVT) are also considered for the validation. Model shows a very good predictability and robustness at both sea level and altitude condition with different ambient conditions. The various advantages such as high accuracy and robustness at different operating conditions, low computational time and lower number of data points requires for the calibration establishes the platform where the model-based approach can be used for the engine calibration and development process. Moreover, the focus of this work is towards establishing a framework for the future model development for other various targets such as soot, Combustion Noise Level (CNL), NO₂/NOx ratio etc.

Keywords: diesel engine, machine learning, NOₓ emission, semi-empirical

Procedia PDF Downloads 93

Authors: Tebogo Emma Makaba, Barnabas Ndlovu Gatsheni

Abstract:

The cities of Johannesburg and Pretoria both located in the Gauteng province are separated by a distance of 58 km. The traffic queues on the Ben Schoeman freeway which connects these two cities can stretch for almost 1.5 km. Vehicle traffic congestion impacts negatively on the business and the commuter’s quality of life. The goal of this paper is to identify variables that influence the flow of traffic and to design a vehicle traffic prediction model, which will predict the traffic flow pattern in advance. The model will unable motorist to be able to make appropriate travel decisions ahead of time. The data used was collected by Mikro’s Traffic Monitoring (MTM). Multi-Layer perceptron (MLP) was used individually to construct the model and the MLP was also combined with Bagging ensemble method to training the data. The cross—validation method was used for evaluating the models. The results obtained from the techniques were compared using predictive and prediction costs. The cost was computed using combination of the loss matrix and the confusion matrix. The predicted models designed shows that the status of the traffic flow on the freeway can be predicted using the following parameters travel time, average speed, traffic volume and day of month. The implications of this work is that commuters will be able to spend less time travelling on the route and spend time with their families. The logistics industry will save more than twice what they are currently spending.

Keywords: bagging ensemble methods, confusion matrix, multi-layer perceptron, vehicle traffic flow

Procedia PDF Downloads 319

Authors: M. Yaqub Khan, Usman Shabbir

Abstract:

History of plasma reveals that continuous struggle of experimentalists and theorists are not fruitful for confinement up to now. It needs a change to bring the research through entropy. Approximately, all the quantities like number density, temperature, electrostatic potential, etc. are connected to entropy. Therefore, it is better to change the way of research. In ion temperature gradient mode with the help of Braginskii model, Boltzmannian electrons, effect of velocity shear is studied inculcating entropy in the magnetoplasma. New dispersion relation is derived for ion temperature gradient mode, and dependence on entropy gradient drift is seen. It is also seen velocity shear enhances the instability but in anomalous transport, its role is not seen significantly but entropy. This work will be helpful to the next step of tokamak and space plasmas.

Keywords: entropy, velocity shear, ion temperature gradient mode, drift

Procedia PDF Downloads 363

Authors: Viji Vijayakumar, R. Divya, A. Vivek

Abstract:

This paper deals with a quadratic boost converter which belongs to cascade boost family, controlled by sliding mode controller. In the cascade boost family, quadratic boost converter is the best trade-off when circuit complexity and modulator saturation is considered. Sliding mode control being a nonlinear control results in a robust and stable system when applied to switching converters which are inherently variable structured systems. The stability of this system is analyzed through Lyapunov’s approach. Analysis is done for load regulation, line regulation and step response of the system. Also these results are compared with that of PID controller based system.

Keywords: DC-DC converter, quadratic boost converter, sliding mode control, PID control

Procedia PDF Downloads 964

Authors: Qihang Zeng, Wei Xu, Ying Shen, Changyuan Yu

Abstract:

In this paper, a highly sensitive fiber-optic curvature sensor based on four mode fiber (FMF) is presented and investigated. The proposed sensing structure is constructed by fusing a section of FMF into two standard single mode fibers (SMFs) concatenated with two no core fiber (NCF), i.e., SMF-NCF-FMF-NCF-SMF structure is fabricated. The length of the NCF is very short about 1 millimeter acting as exciting/recoupling the light from/into the core of the SMF, while the FMF is with 3 centimeters long supporting four eigenmodes including LP₀₁, LP₁₁, LP₂₁ and LP₀₂. High core modes in FMF can be effectively stimulated owing to mismatched mode field distribution and the mainly sensing principle is based on modal interferometer spectrum analysis. Different curvatures induce different strains on the FMF such that affecting the modal excitation, resulting spectrum shifts. One can get the curvature value by tracking the wavelength shifting. Experiments have been done to address the sensing performance, which is about 7.8 nm/m⁻¹ within a range of 1.90 m⁻¹~3.18 m⁻¹.

Keywords: curvature, four mode fiber, highly sensitive, modal interferometer

Procedia PDF Downloads 168

Authors: Vishal Das, Tianyi Mao, Zhicheng Geng, Carmen Flores, Diego Pelloso, Fang Wang

Abstract:

Accurate sell-in and sell-out forecasting is a ubiquitous problem in the retail industry. It is an important element of any demand planning activity. As a global food and beverage company, Nestlé has hundreds of products in each geographical location that they operate in. Each product has its sell-in and sell-out time series data, which are forecasted on a weekly and monthly scale for demand and financial planning. To address this challenge, Nestlé Chilein collaboration with Amazon Machine Learning Solutions Labhas developed their in-house solution of using machine learning models for forecasting. Similar products are combined together such that there is one model for each product category. In this way, the models learn from a larger set of data, and there are fewer models to maintain. The solution is scalable to all product categories and is developed to be flexible enough to include any new product or eliminate any existing product in a product category based on requirements. We show how we can use the machine learning development environment on Amazon Web Services (AWS) to explore a set of forecasting models and create business intelligence dashboards that can be used with the existing demand planning tools in Nestlé. We explored recent deep learning networks (DNN), which show promising results for a variety of time series forecasting problems. Specifically, we used a DeepAR autoregressive model that can group similar time series together and provide robust predictions. To further enhance the accuracy of the predictions and include domain-specific knowledge, we designed an ensemble approach using DeepAR and XGBoost regression model. As part of the ensemble approach, we interlinked the sell-out and sell-in information to ensure that a future sell-out influences the current sell-in predictions. Our approach outperforms the benchmark statistical models by more than 50%. The machine learning (ML) pipeline implemented in the cloud is currently being extended for other product categories and is getting adopted by other geomarkets.

Keywords: sell-in and sell-out forecasting, demand planning, DeepAR, retail, ensemble machine learning, time-series

Procedia PDF Downloads 221

Authors: Sungsik Jo, Hyeonwoo Kim, Iksu Choi, Hunmo Kim

Abstract:

In the SHP, LVDT sensor is for detecting the length changes of the EHA output, and the thrust of the EHA is controlled by the pressure sensor. Sensor is possible to cause hardware fault by internal problem or external disturbance. The EHA of SHP is able to be uncontrollable due to control by feedback from uncertain information, on this paper; the sliding mode observer algorithm estimates the original sensor output information in permanent sensor fault. The proposed algorithm shows performance to recovery fault of disconnection and short circuit basically, also the algorithm detect various of sensor fault mode.

Keywords: smart hybrid powerpack (SHP), electro hydraulic actuator (EHA), permanent sensor fault tolerance, sliding mode observer (SMO), graphic user interface (GUI)

Procedia PDF Downloads 528

Authors: Devansh Desai, Chamandeep Kaur, Nirmal Kullu, George Christopher

Abstract:

Study of aerosols has become very important tool in assuming the climatic changes over a region.Spectral and temporal variability’s in aerosol optical depth(AOD) and size distribution are investigated using ground base measurements over Ahmedabad during the months of January(2013) to may (2013). Angstrom coefficient (ἁ) was found to be higher in winter season (January to march) indicating the dominance of fine mode aerosol concentration over Ahmedabad, and the Angstrom coefficient (ἁ) was found to be lower indicating the dominance of coarse mode aerosol concentration over Ahmedabad. The different values of alpha are observed when calculated over different wavelength ranges indicating bimodal aerosol size distribution. Discrimination of aerosol size during different seasons is made using the coefficient of polynomial fit (ἁ1 and ἁ2) which shows the presence of changing dominant aerosol types as a function of season over Ahmedabad. The ἁ2- ἁ1 value is used to get the confirmation on the dominant aerosol mode over Ahmedabad in both seasons. During pre-monsoon about 90% of AOD spectra is dominated by coarse mode aerosols and during winter about 60% of AOD spectra is dominated by fine mode aerosols. This characterization of aerosols is important in assessing the response of different aerosols type in radiative forcing and over climate of Ahmedabad.

Keywords: radiative forcing, aerosol optical depth, fine mode, coarse mode

Procedia PDF Downloads 476

Authors: Alhadi Bustaman, Soeganda Formalidin, Titin Siswantining

Abstract:

DNA microarray technology is used to analyze thousand gene expression data simultaneously and a very important task for drug development and test, function annotation, and cancer diagnosis. Various clustering methods have been used for analyzing gene expression data. However, when analyzing very large and heterogeneous collections of gene expression data, conventional clustering methods often cannot produce a satisfactory solution. Biclustering algorithm has been used as an alternative approach to identifying structures from gene expression data. In this paper, we introduce a transform technique based on singular value decomposition to identify normalized matrix of gene expression data followed by Mixed-Clustering algorithm and the Lift algorithm, inspired in the node-deletion and node-addition phases proposed by Cheng and Church based on Agglomerative Hierarchical Clustering (AHC). Experimental study on standard datasets demonstrated the effectiveness of the algorithm in gene expression data.

Keywords: agglomerative hierarchical clustering (AHC), biclustering, gene expression data, lymphoma, singular value decomposition (SVD)

Procedia PDF Downloads 257

Authors: Glaoui Hachemi

Abstract:

In this paper, a scheme based on multi-input multi output Fuzzy Sliding Mode control (MIMO-FSMC) for linear speed regulation of winding system is proposed. Once the uncoupled model of the winding system was obtained, a smooth control function with a threshold was selected to indicate how far away the case was from the sliding surface. nevertheless, this control function depends closely on the higher bound of the uncertainties, which generates overlap. So, this size has to be chosen with broad care to obtain high performances. Usually, the upper bound of uncertainties is difficult to know before motor operation, so, a Fuzzy Sliding Mode controller is investigated to resolve this problem, a simple Fuzzy inference mechanism is used to decrease the chattering phenomenon by simple adjustments. A simulation study is achieved and that the indicate fuzzy sliding mode controllers have great potential for use as an alternative to the conventional sliding mode control.

Keywords: Winding system, induction machine, Mechanical tension, Proportional-integral (PI), sliding mode control, Fuzzy logic

Procedia PDF Downloads 67

Authors: Addin Osman, Anwar Ali Yahya, Mohammed Basit Kamal

Abstract:

Datasets or collections are becoming important assets by themselves and now they can be accepted as a primary intellectual output of a research. The quality and usage of the datasets depend mainly on the context under which they have been collected, processed, analyzed, validated, and interpreted. This paper aims to present a collection of program educational objectives mapped to student’s outcomes collected from self-study reports prepared by 32 engineering programs accredited by ABET. The manual mapping (classification) of this data is a notoriously tedious, time consuming process. In addition, it requires experts in the area, which are mostly not available. It has been shown the operational settings under which the collection has been produced. The collection has been cleansed, preprocessed, some features have been selected and preliminary exploratory data analysis has been performed so as to illustrate the properties and usefulness of the collection. At the end, the collection has been benchmarked using nine of the most widely used supervised multiclass classification techniques (Binary Relevance, Label Powerset, Classifier Chains, Pruned Sets, Random k-label sets, Ensemble of Classifier Chains, Ensemble of Pruned Sets, Multi-Label k-Nearest Neighbors and Back-Propagation Multi-Label Learning). The techniques have been compared to each other using five well-known measurements (Accuracy, Hamming Loss, Micro-F, Macro-F, and Macro-F). The Ensemble of Classifier Chains and Ensemble of Pruned Sets have achieved encouraging performance compared to other experimented multi-label classification methods. The Classifier Chains method has shown the worst performance. To recap, the benchmark has achieved promising results by utilizing preliminary exploratory data analysis performed on the collection, proposing new trends for research and providing a baseline for future studies.

Keywords: ABET, accreditation, benchmark collection, machine learning, program educational objectives, student outcomes, supervised multi-class classification, text mining

Procedia PDF Downloads 147

Authors: Soha A. Bahanshal, Vaibhav Verdhan, Bayong Kim

Abstract:

Graduation rates at six-year colleges are becoming a more essential indicator for incoming fresh students and for university rankings. Predicting student graduation is extremely beneficial to schools and has a huge potential for targeted intervention. It is important for educational institutions since it enables the development of strategic plans that will assist or improve students' performance in achieving their degrees on time (GOT). A first step and a helping hand in extracting useful information from these data and gaining insights into the prediction of students' progress and performance is offered by machine learning techniques. Data analysis and visualization techniques are applied to understand and interpret the data. The data used for the analysis contains students who have graduated in 6 years in the academic year 2017-2018 for science majors. This analysis can be used to predict the graduation of students in the next academic year. Different Predictive modelings such as logistic regression, decision trees, support vector machines, Random Forest, Naïve Bayes, and KNeighborsClassifier are applied to predict whether a student will graduate. These classifiers were evaluated with k folds of 5. The performance of these classifiers was compared based on accuracy measurement. The results indicated that Ensemble Classifier achieves better accuracy, about 91.12%. This GOT prediction model would hopefully be useful to university administration and academics in developing measures for assisting and boosting students' academic performance and ensuring they graduate on time.

Keywords: prediction, decision trees, machine learning, support vector machine, ensemble model, student graduation, GOT graduate on time

Procedia PDF Downloads 55

Authors: Ahmed Abbou, Ali Mousmi, Rachid El Akhrif

Abstract:

This research paper aims to reduce the chattering phenomenon due to control by sliding mode control applied on a wind energy conversion system based on the doubly fed induction generator (DFIG). Our goal is to offset the effect of parametric uncertainties and come as close as possible to the dynamic response solicited by the control law in the ideal case and therefore force the active and reactive power generated by the DFIG to accurately follow the reference values which are provided to it. The simulation results using Matlab / Simulink demonstrate the efficiency and performance of the proposed technique while maintaining the simplicity of control by first order sliding mode.

Keywords: correction of the equivalent command, DFIG, induction machine, sliding mode controller

Procedia PDF Downloads 391

Authors: Mohammad Esmaeilpour

Abstract:

One of the important open problems in the field of medical image processing is detection and quantification of small changes. In this poster, we try to investigate that, how the algebraic decomposition techniques can be used for semiautomatically detecting and quantifying subtle changes in Magnetic Resonance (MR) neuroimaging volumes. We mostly focus on the low-rank values of the matrices achieved from decomposing MR image pairs during a period of time. Besides, a skillful neuroradiologist will help the algorithm to distinguish between noises and small changes.

Keywords: magnetic resonance neuroimaging, subtle change detection and quantification, algebraic decomposition, basis functions

Procedia PDF Downloads 450

Authors: Wieslaw Marszalek, Zdzislaw Trzaska

Abstract:

Interesting properties of various one-period loops of singularly perturbed memristive circuits with mixed-mode oscillations (MMOs) are analyzed in this paper. The analysis is mixed, both analytical and numerical and focused on the properties of pinched hysteresis of the memristive element and other one-period loops formed by pairs of time-series solutions for various circuits' variables. The memristive element is the only nonlinear element in the two circuits. A theorem on periods of mixed-mode oscillations of the circuits is formulated and proved. Replacements of memristors by parallel G-C or series R-L circuits for a MMO response with equivalent RMS values is also discussed.

Keywords: mixed-mode oscillations, memristive circuits, pinched hysteresis, one-period loops, singularly perturbed circuits

Procedia PDF Downloads 451