Search results for: adjoint gradient method
19202 Adaptive Dehazing Using Fusion Strategy
Authors: M. Ramesh Kanthan, S. Naga Nandini Sujatha
Abstract:
The goal of haze removal algorithms is to enhance and recover details of scene from foggy image. In enhancement the proposed method focus into two main categories: (i) image enhancement based on Adaptive contrast Histogram equalization, and (ii) image edge strengthened Gradient model. Many circumstances accurate haze removal algorithms are needed. The de-fog feature works through a complex algorithm which first determines the fog destiny of the scene, then analyses the obscured image before applying contrast and sharpness adjustments to the video in real-time to produce image the fusion strategy is driven by the intrinsic properties of the original image and is highly dependent on the choice of the inputs and the weights. Then the output haze free image has reconstructed using fusion methodology. In order to increase the accuracy, interpolation method has used in the output reconstruction. A promising retrieval performance is achieved especially in particular examples.Keywords: single image, fusion, dehazing, multi-scale fusion, per-pixel, weight map
Procedia PDF Downloads 46519201 Investigating the Influence of Activation Functions on Image Classification Accuracy via Deep Convolutional Neural Network
Authors: Gulfam Haider, sana danish
Abstract:
Convolutional Neural Networks (CNNs) have emerged as powerful tools for image classification, and the choice of optimizers profoundly affects their performance. The study of optimizers and their adaptations remains a topic of significant importance in machine learning research. While numerous studies have explored and advocated for various optimizers, the efficacy of these optimization techniques is still subject to scrutiny. This work aims to address the challenges surrounding the effectiveness of optimizers by conducting a comprehensive analysis and evaluation. The primary focus of this investigation lies in examining the performance of different optimizers when employed in conjunction with the popular activation function, Rectified Linear Unit (ReLU). By incorporating ReLU, known for its favorable properties in prior research, the aim is to bolster the effectiveness of the optimizers under scrutiny. Specifically, we evaluate the adjustment of these optimizers with both the original Softmax activation function and the modified ReLU activation function, carefully assessing their impact on overall performance. To achieve this, a series of experiments are conducted using a well-established benchmark dataset for image classification tasks, namely the Canadian Institute for Advanced Research dataset (CIFAR-10). The selected optimizers for investigation encompass a range of prominent algorithms, including Adam, Root Mean Squared Propagation (RMSprop), Adaptive Learning Rate Method (Adadelta), Adaptive Gradient Algorithm (Adagrad), and Stochastic Gradient Descent (SGD). The performance analysis encompasses a comprehensive evaluation of the classification accuracy, convergence speed, and robustness of the CNN models trained with each optimizer. Through rigorous experimentation and meticulous assessment, we discern the strengths and weaknesses of the different optimization techniques, providing valuable insights into their suitability for image classification tasks. By conducting this in-depth study, we contribute to the existing body of knowledge surrounding optimizers in CNNs, shedding light on their performance characteristics for image classification. The findings gleaned from this research serve to guide researchers and practitioners in making informed decisions when selecting optimizers and activation functions, thus advancing the state-of-the-art in the field of image classification with convolutional neural networks.Keywords: deep neural network, optimizers, RMsprop, ReLU, stochastic gradient descent
Procedia PDF Downloads 12519200 Flow Field Optimization for Proton Exchange Membrane Fuel Cells
Authors: Xiao-Dong Wang, Wei-Mon Yan
Abstract:
The flow field design in the bipolar plates affects the performance of the proton exchange membrane (PEM) fuel cell. This work adopted a combined optimization procedure, including a simplified conjugate-gradient method and a completely three-dimensional, two-phase, non-isothermal fuel cell model, to look for optimal flow field design for a single serpentine fuel cell of size 9×9 mm with five channels. For the direct solution, the two-fluid method was adopted to incorporate the heat effects using energy equations for entire cells. The model assumes that the system is steady; the inlet reactants are ideal gases; the flow is laminar; and the porous layers such as the diffusion layer, catalyst layer and PEM are isotropic. The model includes continuity, momentum and species equations for gaseous species, liquid water transport equations in the channels, gas diffusion layers, and catalyst layers, water transport equation in the membrane, electron and proton transport equations. The Bulter-Volumer equation was used to describe electrochemical reactions in the catalyst layers. The cell output power density Pcell is maximized subjected to an optimal set of channel heights, H1-H5, and channel widths, W2-W5. The basic case with all channel heights and widths set at 1 mm yields a Pcell=7260 Wm-2. The optimal design displays a tapered characteristic for channels 1, 3 and 4, and a diverging characteristic in height for channels 2 and 5, producing a Pcell=8894 Wm-2, about 22.5% increment. The reduced channel heights of channels 2-4 significantly increase the sub-rib convection and widths for effectively removing liquid water and oxygen transport in gas diffusion layer. The final diverging channel minimizes the leakage of fuel to outlet via sub-rib convection from channel 4 to channel 5. Near-optimal design without huge loss in cell performance but is easily manufactured is tested. The use of a straight, final channel of 0.1 mm height has led to 7.37% power loss, while the design with all channel widths to be 1 mm with optimal channel heights obtained above yields only 1.68% loss of current density. The presence of a final, diverging channel has greater impact on cell performance than the fine adjustment of channel width at the simulation conditions set herein studied.Keywords: optimization, flow field design, simplified conjugate-gradient method, serpentine flow field, sub-rib convection
Procedia PDF Downloads 29619199 Profit-Based Artificial Neural Network (ANN) Trained by Migrating Birds Optimization: A Case Study in Credit Card Fraud Detection
Authors: Ashkan Zakaryazad, Ekrem Duman
Abstract:
A typical classification technique ranks the instances in a data set according to the likelihood of belonging to one (positive) class. A credit card (CC) fraud detection model ranks the transactions in terms of probability of being fraud. In fact, this approach is often criticized, because firms do not care about fraud probability but about the profitability or costliness of detecting a fraudulent transaction. The key contribution in this study is to focus on the profit maximization in the model building step. The artificial neural network proposed in this study works based on profit maximization instead of minimizing the error of prediction. Moreover, some studies have shown that the back propagation algorithm, similar to other gradient–based algorithms, usually gets trapped in local optima and swarm-based algorithms are more successful in this respect. In this study, we train our profit maximization ANN using the Migrating Birds optimization (MBO) which is introduced to literature recently.Keywords: neural network, profit-based neural network, sum of squared errors (SSE), MBO, gradient descent
Procedia PDF Downloads 47519198 Energy Potential of Salinity Gradient Mixing: Case Study of Mixing Energies of Rivers of Goa with the Arabian Sea
Authors: Arijit Chakraborty, Anirban Roy
Abstract:
The Indian peninsula is strategically located in the Asian subcontinent with the Himalayas to the North and Oceans surrounding the other three directions with annual monsoons which takes care of water supply to the rivers. The total river water discharge into the Bay of Bengal and the Arabian Sea is 628 km³/year and 274 km³/year, respectively. Thus huge volumes of fresh water meet saline water, and this mixing of two streams of dissimilar salinity gives rise to tremendous mixing energies which can be harvested for various purposes like energy generation using pressure retarded osmosis or reverse electrodialysis. The present paper concentrates on analyzing the energy of mixing for the rivers in Goa. Goa has 10 rivers of various sizes all which meet the Arabian Sea. In the present work, the 8 rivers and their salinity (NaCl concentrations) have been analyzed along with their seasonal fluctuations. Next, a Gibbs free energy formulation has been implemented to analyze the energy of mixing of the selected rivers. The highest and lowest energies according to the seasonal fluctuations have been evaluated, and this provides two important insights into (i) amount of energy that can be harvested and (ii) decision on the location of such systems.Keywords: Gibbs energy, mixing energy, salinity gradient energy, thermodynamics
Procedia PDF Downloads 21119197 Implementation of a Lattice Boltzmann Method for Pulsatile Flow with Moment Based Boundary Condition
Authors: Zainab A. Bu Sinnah, David I. Graham
Abstract:
The Lattice Boltzmann Method has been developed and used to simulate both steady and unsteady fluid flow problems such as turbulent flows, multiphase flow and flows in the vascular system. As an example, the study of blood flow and its properties can give a greater understanding of atherosclerosis and the flow parameters which influence this phenomenon. The blood flow in the vascular system is driven by a pulsating pressure gradient which is produced by the heart. As a very simple model of this, we simulate plane channel flow under periodic forcing. This pulsatile flow is essentially the standard Poiseuille flow except that the flow is driven by the periodic forcing term. Moment boundary conditions, where various moments of the particle distribution function are specified, are applied at solid walls. We used a second-order single relaxation time model and investigated grid convergence using two distinct approaches. In the first approach, we fixed both Reynolds and Womersley numbers and varied relaxation time with grid size. In the second approach, we fixed the Womersley number and relaxation time. The expected second-order convergence was obtained for the second approach. For the first approach, however, the numerical method converged, but not necessarily to the appropriate analytical result. An explanation is given for these observations.Keywords: Lattice Boltzmann method, single relaxation time, pulsatile flow, moment based boundary condition
Procedia PDF Downloads 23119196 Relative Study of the Effect of the Temperature Gradient on Free Vibrations of Clamped Visco-Elastic Rectangular Plates with Linearly and Exponentially Thickness Variations Respectively in Two Directions
Authors: Harvinder Kaur
Abstract:
Rayleigh–Ritz method is a broadly used classical method for the calculation of the natural vibration frequency of a structure in the second or higher order. Here it is used to construct a mathematical model of relative study of the thermal effect on free transverse vibrations of clamped (c-c-c-c type) visco-elastic rectangular plate with linearly and exponentially thickness variations respectively in two directions. Researchers in the field of Engineering always make an effort for better designs of mechanical structures. In-depth study of the vibration behavior of tapered plates with diverse thickness variation under high temperature would ultimately help to finalize the accurate design of a structure. The perfect tapered structure saves weight and as well as expenses. In the present paper, the comparison has been done for deflection and time period corresponding to the first two modes of vibrations of clamped plate for various values of aspect ratio, thermal constants, and taper constants of both the cases.Keywords: Rayleigh-Ritz Method, tapered plates, transverse vibration, thermal constant, visco-elasticity
Procedia PDF Downloads 22919195 Development of Numerical Method for Mass Transfer across the Moving Membrane with Selective Permeability: Approximation of the Membrane Shape by Level Set Method for Numerical Integral
Authors: Suguru Miyauchi, Toshiyuki Hayase
Abstract:
Biological membranes have selective permeability, and the capsules or cells enclosed by the membrane show the deformation by the osmotic flow. This mass transport phenomenon is observed everywhere in a living body. For the understanding of the mass transfer in a body, it is necessary to consider the mass transfer phenomenon across the membrane as well as the deformation of the membrane by a flow. To our knowledge, in the numerical analysis, the method for mass transfer across the moving membrane has not been established due to the difficulty of the treating of the mass flux permeating through the moving membrane with selective permeability. In the existing methods for the mass transfer across the membrane, the approximate delta function is used to communicate the quantities on the interface. The methods can reproduce the permeation of the solute, but cannot reproduce the non-permeation. Moreover, the computational accuracy decreases with decreasing of the permeable coefficient of the membrane. This study aims to develop the numerical method capable of treating three-dimensional problems of mass transfer across the moving flexible membrane. One of the authors developed the numerical method with high accuracy based on the finite element method. This method can capture the discontinuity on the membrane sharply due to the consideration of the jumps in concentration and concentration gradient in the finite element discretization. The formulation of the method takes into account the membrane movement, and both permeable and non-permeable membranes can be treated. However, searching the cross points of the membrane and fluid element boundaries and splitting the fluid element into sub-elements are needed for the numerical integral. Therefore, cumbersome operation is required for a three-dimensional problem. In this paper, we proposed an improved method to avoid the search and split operations, and confirmed its effectiveness. The membrane shape was treated implicitly by introducing the level set function. As the construction of the level set function, the membrane shape in one fluid element was expressed by the shape function of the finite element method. By the numerical experiment, it was found that the shape function with third order appropriately reproduces the membrane shapes. The same level of accuracy compared with the previous method using search and split operations was achieved by using a number of sampling points of the numerical integral. The effectiveness of the method was confirmed by solving several model problems.Keywords: finite element method, level set method, mass transfer, membrane permeability
Procedia PDF Downloads 25019194 Implications of Optimisation Algorithm on the Forecast Performance of Artificial Neural Network for Streamflow Modelling
Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed
Abstract:
The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.Keywords: streamflow, neural network, optimisation, algorithm
Procedia PDF Downloads 15219193 Precise Determination of the Residual Stress Gradient in Composite Laminates Using a Configurable Numerical-Experimental Coupling Based on the Incremental Hole Drilling Method
Authors: A. S. Ibrahim Mamane, S. Giljean, M.-J. Pac, G. L’Hostis
Abstract:
Fiber reinforced composite laminates are particularly subject to residual stresses due to their heterogeneity and the complex chemical, mechanical and thermal mechanisms that occur during their processing. Residual stresses are now well known to cause damage accumulation, shape instability, and behavior disturbance in composite parts. Many works exist in the literature on techniques for minimizing residual stresses in thermosetting and thermoplastic composites mainly. To study in-depth the influence of processing mechanisms on the formation of residual stresses and to minimize them by establishing a reliable correlation, it is essential to be able to measure very precisely the profile of residual stresses in the composite. Residual stresses are important data to consider when sizing composite parts and predicting their behavior. The incremental hole drilling is very effective in measuring the gradient of residual stresses in composite laminates. This method is semi-destructive and consists of drilling incrementally a hole through the thickness of the material and measuring relaxation strains around the hole for each increment using three strain gauges. These strains are then converted into residual stresses using a matrix of coefficients. These coefficients, called calibration coefficients, depending on the diameter of the hole and the dimensions of the gauges used. The reliability of the incremental hole drilling depends on the accuracy with which the calibration coefficients are determined. These coefficients are calculated using a finite element model. The samples’ features and the experimental conditions must be considered in the simulation. Any mismatch can lead to inadequate calibration coefficients, thus introducing errors on residual stresses. Several calibration coefficient correction methods exist for isotropic material, but there is a lack of information on this subject concerning composite laminates. In this work, a Python program was developed to automatically generate the adequate finite element model. This model allowed us to perform a parametric study to assess the influence of experimental errors on the calibration coefficients. The results highlighted the sensitivity of the calibration coefficients to the considered errors and gave an order of magnitude of the precisions required on the experimental device to have reliable measurements. On the basis of these results, improvements were proposed on the experimental device. Furthermore, a numerical method was proposed to correct the calibration coefficients for different types of materials, including thick composite parts for which the analytical approach is too complex. This method consists of taking into account the experimental errors in the simulation. Accurate measurement of the experimental errors (such as eccentricity of the hole, angular deviation of the gauges from their theoretical position, or errors on increment depth) is therefore necessary. The aim is to determine more precisely the residual stresses and to expand the validity domain of the incremental hole drilling technique.Keywords: fiber reinforced composites, finite element simulation, incremental hole drilling method, numerical correction of the calibration coefficients, residual stresses
Procedia PDF Downloads 13219192 Mechanical Properties and Microstructures of the Directional Solidified Zn-Al-Cu Alloy
Authors: Mehmet Izzettin Yilmazer, Emin Cadirli
Abstract:
Zn-7wt.%Al-2.96wt.%Cu eutectic alloy was directionally solidified upwards with different temperature gradients (from 6.70 K/mm to 10.67 K/mm) at a constant growth rate (16.4 Km/s) and also different growth rate (from 8.3 micron/s to 166 micron/s) at a constant temperature gradient (10.67 K/mm) using a Bridgman–type growth apparatus.The values of eutectic spacing were measured from longitudinal and transverse sections of the samples. The dependency of microstructures on the G and V were determined with linear regression analysis and experimental equations were found as λl=8.953xVexp-0.49, λt=5.942xVexp-0.42 and λl=0.008xGexp-1.23, λt=0.024xGexp-0.93. The measurements of microhardness of directionally solidified samples were obtained by using a microhardness test device. The dependence of microhardness HV on temperature gradient and growth rate were analyzed. The dependency of microhardness on the G and V were also determined with linear regression analysis as HVl=110.66xVexp0.02, HVt=111.94xVexp0.02 and HVl=69.66xGexp0.17, HVt=68.86xGexp0.18. The experimental results show that the microhardness of the directionally solidified Zn-Al-Cu alloy increases with increasing the growth rate. The results obtained in this work were compared with the previous similar experimental results.Keywords: directional solidification, eutectic alloys, microstructure, microhardness
Procedia PDF Downloads 45119191 Determination of Marbofloxacin in Pig Plasma Using LC-MS/MS and Its Application to the Pharmacokinetic Studies
Authors: Jeong Woo Kang, MiYoung Baek, Ki-Suk Kim, Kwang-Jick Lee, ByungJae So
Abstract:
Introduction: A fast, easy and sensitive detection method was developed and validated by liquid chromatography tandem mass spectrometry for the determination of marbofloxacin in pig plasma which was further applied to study the pharmacokinetics of marbofloxacin. Materials and Methods: The plasma sample (500 μL) was mixed with 1.5 ml of 0.1% formic acid in MeCN to precipitate plasma proteins. After shaking for 20 min, The mixture was centrifuged at 5,000 × g for 30 min. It was dried under a nitrogen flow at 50℃. 500 μL aliquot of the sample was injected into the LC-MS/MS system. Chromatographic analysis was carried out mobile phase gradient consisting 0.1% formic acid in D.W. (A) and 0.1% formic acid in MeCN (B) with C18 reverse phase column. Mass spectrometry was performed using the positive ion mode and the selected ion monitoring (MRM). Results and Conclusions: The method validation was performed in the sample matrix. Good linearities (R2>0.999) were observed and the quantified average recoveries of marbofloxacin were 87 - 92% at level of 10 ng g-1 -100 ng g-1. The percent of coefficient of variation (CV) for the described method was less than 10 % over the range of concentrations studied. The limits of detection (LOD) and quantification (LOQ) were 2 and 5 ng g-1, respectively. This method has also been applied successfully to pharmacokinetic analysis of marbofloxacin after intravenous (IV), intramuscular (IM) and oral administration (PO). The mean peak plasma concentration (Cmax) was 2,597 ng g-1at 0.25 h, 2,587 ng g-1at 0.44 h and 2,355 ng g-1at 1.58 h for IV, IM and PO, respectively. The area under the plasma concentration-time curve (AUC0–t) was 24.8, 29.0 and 25.2 h μg/mL for IV, IM and PO, respectively. The elimination half-life (T1/2) was 8.6, 13.1 and 9.5 for IV, IM and PO, respectively. Bioavailability (F) of the marbofloxacin in pig was 117 and 101 % for IM and PO, respectively. Based on these result, marbofloxacin does not have any obstacles as therapeutics to develop the oral formulations such as tablets and capsules.Keywords: marbofloxacin, LC-MS/MS, pharmacokinetics, chromatographic
Procedia PDF Downloads 54819190 A Practical and Efficient Evaluation Function for 3D Model Based Vehicle Matching
Authors: Yuan Zheng
Abstract:
3D model-based vehicle matching provides a new way for vehicle recognition, localization and tracking. Its key is to construct an evaluation function, also called fitness function, to measure the degree of vehicle matching. The existing fitness functions often poorly perform when the clutter and occlusion exist in traffic scenarios. In this paper, we present a practical and efficient fitness function. Unlike the existing evaluation functions, the proposed fitness function is to study the vehicle matching problem from both local and global perspectives, which exploits the pixel gradient information as well as the silhouette information. In view of the discrepancy between 3D vehicle model and real vehicle, a weighting strategy is introduced to differently treat the fitting of the model’s wireframes. Additionally, a normalization operation for the model’s projection is performed to improve the accuracy of the matching. Experimental results on real traffic videos reveal that the proposed fitness function is efficient and robust to the cluttered background and partial occlusion.Keywords: 3D-2D matching, fitness function, 3D vehicle model, local image gradient, silhouette information
Procedia PDF Downloads 39919189 The Effects of Heavy Metal and Aromatic Hydrocarbon Pollution on Bees
Authors: Katarzyna Zięba, Hajnalka Szentgyörgyi, Paweł Miśkowiec, Agnieszka Moos-Matysik
Abstract:
Bees are effective pollinators of plants using by humans. However, there is a concern about the fate different species due to their recently decline. Pollution of the environment is described in the literature as one of the causes of this phenomenon. Due to human activities, heavy metals and aromatic hydrocarbons can occur in bee organisms in high concentrations. The presented study aims to provide information on how pollution affects bee quality, taking into account, also the biological differences between various groups of bees. Understanding the consequences of environmental pollution on bees can help to create and promote bee friendly habitats and actions. The analyses were carried out using two contamination gradients with 5 sites on each. The first, mainly heavy metal polluted gradient is stretching approx. 30km from the Bukowno Zinc smelter near Olkusz in the Lesser Poland Voivodship, to the north. The second cuts through the agglomeration of Kraków up to the southern borders of the Ojców National Park. The gradient near Olkusz is a well-described pollution gradient contaminated mainly by zinc, lead, and cadmium. The second gradient cut through the agglomeration of Kraków and end below the Ojców National Park. On each gradient, two bee species were installed: red mason bees (Osmia bicornis) and honey bees (Apis mellifera). Red mason bee is a polylectic, solitary bee species, widely distributed in Poland. Honey bees are a highly social species of bees, with clearly defined casts and roles in the colony. Before installing the bees in the field, samples of imagos of red mason bees and samples of pollen and imagos from each honey bee colony were analysed for zinc, lead cadmium, polycyclic and monocyclic hydrocarbons levels. After collecting the bees from the field, samples of bees and pollen samples for each site were prepared for heavy metal, monocyclic hydrocarbon, and polycyclic hydrocarbon analysis. Analyses of aromatic hydrocarbons were performed with gas chromatography coupled with a headspace sampler (HP 7694E) and mass spectrometer (MS) as detector. Monocyclic compounds were injected into column with headspace sampler while polycyclic ones with manual injector (after solid-liquid extraction with hexane). The heavy metal content (zinc, lead and cadmium) was assessed with flame atomic absorption spectroscopy (FAAS AAnalyst 300 Perkin Elmer spectrometer) according to the methods for honey and bee products described in the literature. Pollution levels found in bee bodies and imago body masses in both species, and proportion of sex in case of red mason bees were correlated with pollution levels found in pollen for each site and colony or trap nest. An attempt to pinpoint the most important form of contamination regarding bee health was also be undertaken based on the achieved results.Keywords: heavy metals, aromatic hydrocarbons, bees, pollution
Procedia PDF Downloads 50819188 Machine Learning Model to Predict TB Bacteria-Resistant Drugs from TB Isolates
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 5219187 InSAR Times-Series Phase Unwrapping for Urban Areas
Authors: Hui Luo, Zhenhong Li, Zhen Dong
Abstract:
The analysis of multi-temporal InSAR (MTInSAR) such as persistent scatterer (PS) and small baseline subset (SBAS) techniques usually relies on temporal/spatial phase unwrapping (PU). Unfortunately, it always fails to unwrap the phase for two reasons: 1) spatial phase jump between adjacent pixels larger than π, such as layover and high discontinuous terrain; 2) temporal phase discontinuities such as time varied atmospheric delay. To overcome these limitations, a least-square based PU method is introduced in this paper, which incorporates baseline-combination interferograms and adjacent phase gradient network. Firstly, permanent scatterers (PS) are selected for study. Starting with the linear baseline-combination method, we obtain equivalent 'small baseline inteferograms' to limit the spatial phase difference. Then, phase different has been conducted between connected PSs (connected by a specific networking rule) to suppress the spatial correlated phase errors such as atmospheric artifact. After that, interval phase difference along arcs can be computed by least square method and followed by an outlier detector to remove the arcs with phase ambiguities. Then, the unwrapped phase can be obtained by spatial integration. The proposed method is tested on real data of TerraSAR-X, and the results are also compared with the ones obtained by StaMPS(a software package with 3D PU capabilities). By comparison, it shows that the proposed method can successfully unwrap the interferograms in urban areas even when high discontinuities exist, while StaMPS fails. At last, precise DEM errors can be got according to the unwrapped interferograms.Keywords: phase unwrapping, time series, InSAR, urban areas
Procedia PDF Downloads 15119186 Constructal Enhancement of Fins Design Integrated to Phase Change Materials
Authors: Varun Joshi, Manish K. Rathod
Abstract:
The latent heat thermal energy storage system is a thrust area of research due to exuberant thermal energy storage potential. The thermal performance of PCM is significantly augmented by installation of the high thermal conductivity fins. The objective of the present study is to obtain optimum size and location of the fins to enhance diffusion heat transfer without altering overall melting time. Hence, the constructal theory is employed to eliminate, resize, and re-position the fins. A numerical code based on conjugate heat transfer coupled enthalpy porosity approached is developed to solve Navier-Stoke and energy equation.The numerical results show that the constructal fin design has enhanced the thermal performance along with the increase in the overall volume of PCM when compared to conventional. The overall volume of PCM is found to be increased by half of total of volume of fins. The elimination and repositioning the fins at high temperature gradient from low temperature gradient is found to be vital.Keywords: constructal theory, enthalpy porosity approach, phase change materials, fins
Procedia PDF Downloads 18119185 Interaction of Non-Gray-Gas Radiation with Opposed Mixed Convection in a Lid-Driven Square Cavity
Authors: Mohammed Cherifi, Abderrahmane Benbrik, Siham Laouar-Meftah, Denis Lemonnier
Abstract:
The present study was conducted to numerically investigate the interaction of non-gray-gas radiation with opposed mixed convection in a vertical two-sided lid-driven square cavity. The opposing flows are simultaneously generated by the vertical boundary walls which slide at a constant speed and the natural convection due to the gradient temperature of differentially heated cavity. The horizontal walls are thermally insulated and perfectly reflective. The enclosure is filled with air-H2O-CO2 gas mixture, which is considered as a non-gray, absorbing, emitting and not scattering medium. The governing differential equations are solved by a finite-volume method, by adopting the SIMPLER algorithm for pressure–velocity coupling. The radiative transfer equation (RTE) is solved by the discrete ordinates method (DOM). The spectral line weighted sum of gray gases model (SLW) is used to account for non-gray radiation properties. Three cases of the effects of radiation (transparent, gray and non-gray medium) are studied. Comparison is also made with the parametric studies of the effect of the mixed convection parameter, Ri (0.1, 1, 10), on the fluid flow and heat transfer have been performed.Keywords: opposed mixed convection, non-gray-gas radiation, two-sided lid-driven cavity, discrete ordinate method, SLW model
Procedia PDF Downloads 31919184 Design and Validation of Different Steering Geometries for an All-Terrain Vehicle
Authors: Prabhsharan Singh, Rahul Sindhu, Piyush Sikka
Abstract:
The steering system is an integral part and medium through which the driver communicates with the vehicle and terrain, hence the most suitable steering geometry as per requirements must be chosen. The function of the chosen steering geometry of an All-Terrain Vehicle (ATV) is to provide the desired understeer gradient, minimum tire slippage, expected weight transfer during turning as these are requirements for a good steering geometry of a BAJA ATV. This research paper focuses on choosing the best suitable steering geometry for BAJA ATV tracks by reasoning the working principle and using fundamental trigonometric functions for obtaining these geometries on the same vehicle itself, namely Ackermann, Anti- Ackermann, Parallel Ackermann. Full vehicle analysis was carried out on Adams Car Analysis software, and graphical results were obtained for various parameters. Steering geometries were achieved by using a single versatile knuckle for frontward and rearward tie-rod placement and were practically tested with the help of data acquisition systems set up on the ATV. Each was having certain characteristics, setup, and parameters were observed for the BAJA ATV, and correlations were created between analytical and practical values.Keywords: all-terrain vehicle, Ackermann, Adams car, Baja Sae, steering geometry, steering system, tire slip, traction, understeer gradient
Procedia PDF Downloads 15419183 Temperature Gradient In Weld Zones During Friction Stir Process Using Finite Element Method
Authors: Armansyah, I. P. Almanar, M. Saiful Bahari Shaari, M. Shamil Jaffarullah
Abstract:
Finite element approach have been used via three-dimensional models by using Altair Hyper Work, a commercially available software, to describe heat gradients along the welding zones (axially and coronaly) in Friction Stir Welding (FSW). Transient thermal finite element analyses are performed in AA 6061-T6 Aluminum Alloy to obtain temperature distribution in the welded aluminum plates during welding operation. Heat input from tool shoulder and tool pin are considered in the model. A moving heat source with a heat distribution simulating the heat generated by frictions between tool shoulder and work piece is used in the analysis. The developed model was then used to show the effect of various input parameters such as total rate of welding speed and rotational speed on temperature distribution in the work piece.Keywords: Frictions Stir Welding (FSW), temperature distribution, Finite Element Method (FEM), altair hyperwork
Procedia PDF Downloads 53619182 Application of Simulated Annealing to Threshold Optimization in Distributed OS-CFAR System
Authors: L. Abdou, O. Taibaoui, A. Moumen, A. Talib Ahmed
Abstract:
This paper proposes an application of the simulated annealing to optimize the detection threshold in an ordered statistics constant false alarm rate (OS-CFAR) system. Using conventional optimization methods, such as the conjugate gradient, can lead to a local optimum and lose the global optimum. Also for a system with a number of sensors that is greater than or equal to three, it is difficult or impossible to find this optimum; Hence, the need to use other methods, such as meta-heuristics. From a variety of meta-heuristic techniques, we can find the simulated annealing (SA) method, inspired from a process used in metallurgy. This technique is based on the selection of an initial solution and the generation of a near solution randomly, in order to improve the criterion to optimize. In this work, two parameters will be subject to such optimisation and which are the statistical order (k) and the scaling factor (T). Two fusion rules; “AND” and “OR” were considered in the case where the signals are independent from sensor to sensor. The results showed that the application of the proposed method to the problem of optimisation in a distributed system is efficiency to resolve such problems. The advantage of this method is that it allows to browse the entire solutions space and to avoid theoretically the stagnation of the optimization process in an area of local minimum.Keywords: distributed system, OS-CFAR system, independent sensors, simulating annealing
Procedia PDF Downloads 49719181 The Morphology and Flash Flood Characteristics of the Transboundary Khowai River: A Catchment Scale Analysis
Authors: Jonahid Chakder, Mahfuzul Haque
Abstract:
Flash flood is among the foremost disastrous characteristic hazards which cause hampering within the environment and social orders due to climate change across the world. In Northeastern region of Bangladesh faces severe flash floods regularly, Such, the Khowai river is a flash flood-prone river. But until now, there are no previous studies about the flash flood of this river. Farmlands Building resilience, protection of crops & fish enclosures of wetland in Habiganj Haor areas, regional roads, and business establishments were submerged due to flash floods. The flash floods of the Khowai River are frequent events, which happened in 1988, 1998, 2000, 2007, 2017, and 2019. Therefore, this study tries to analyze Khowai river morphology, Precipitation, Water level, Satellite image, and Catchment characteristics: a catchment scale analysis that helps to comprehend Khowai river flash flood characteristics and factors of influence. From precipitation analysis, the finding outcome disclosed the data about flash flood accurate zones at the Khowai district watershed. The morphological analysis workout from satellite image and find out the consequence of sinuosity and gradient of this river. The sinuosity indicates that the Khowai river is an antecedent and a meandering river and a meandering river can’t influence the flash flood of any region, but other factors respond here. It is understood that the Khowai river catchment elevation analysis from DEM is directly influenced. The left Baramura and Right Atharamura anticline of the Khowai basin watershed reflects a major impact on the stratigraphy as an impermeable clay layer and this consequence the water passes downward with the drainage pattern and Tributary. This drainage system, the gradient of tributary and their runoff, and the confluence of water in the pre-monsoon season rise the Khowai river water level which influences flash floods (within six hours of Precipitation).Keywords: geology, gradient, tributary, drainage, watershed, flash flood
Procedia PDF Downloads 12619180 Statistical Analysis with Prediction Models of User Satisfaction in Software Project Factors
Authors: Katawut Kaewbanjong
Abstract:
We analyzed a volume of data and found significant user satisfaction in software project factors. A statistical significance analysis (logistic regression) and collinearity analysis determined the significance factors from a group of 71 pre-defined factors from 191 software projects in ISBSG Release 12. The eight prediction models used for testing the prediction potential of these factors were Neural network, k-NN, Naïve Bayes, Random forest, Decision tree, Gradient boosted tree, linear regression and logistic regression prediction model. Fifteen pre-defined factors were truly significant in predicting user satisfaction, and they provided 82.71% prediction accuracy when used with a neural network prediction model. These factors were client-server, personnel changes, total defects delivered, project inactive time, industry sector, application type, development type, how methodology was acquired, development techniques, decision making process, intended market, size estimate approach, size estimate method, cost recording method, and effort estimate method. These findings may benefit software development managers considerably.Keywords: prediction model, statistical analysis, software project, user satisfaction factor
Procedia PDF Downloads 12419179 Enhancing Spatial Interpolation: A Multi-Layer Inverse Distance Weighting Model for Complex Regression and Classification Tasks in Spatial Data Analysis
Authors: Yakin Hajlaoui, Richard Labib, Jean-François Plante, Michel Gamache
Abstract:
This study introduces the Multi-Layer Inverse Distance Weighting Model (ML-IDW), inspired by the mathematical formulation of both multi-layer neural networks (ML-NNs) and Inverse Distance Weighting model (IDW). ML-IDW leverages ML-NNs' processing capabilities, characterized by compositions of learnable non-linear functions applied to input features, and incorporates IDW's ability to learn anisotropic spatial dependencies, presenting a promising solution for nonlinear spatial interpolation and learning from complex spatial data. it employ gradient descent and backpropagation to train ML-IDW, comparing its performance against conventional spatial interpolation models such as Kriging and standard IDW on regression and classification tasks using simulated spatial datasets of varying complexity. the results highlight the efficacy of ML-IDW, particularly in handling complex spatial datasets, exhibiting lower mean square error in regression and higher F1 score in classification.Keywords: deep learning, multi-layer neural networks, gradient descent, spatial interpolation, inverse distance weighting
Procedia PDF Downloads 5219178 Calculated Structural and Electronic Properties of Mg and Bi
Authors: G. Patricia Abdel Rahim, Jairo Arbey Rodriguez M, María Guadalupe Moreno Armenta
Abstract:
The present study shows the structural, electronic and magnetic properties of magnesium (Mg) and bismuth (Bi) in a supercell (1X1X5). For both materials were studied in five crystalline structures: rock salt (NaCl), cesium chloride (CsCl), zinc-blende (ZB), wurtzite (WZ), and nickel arsenide (NiAs), using the Density Functional Theory (DFT), the Generalized Gradient Approximation (GGA), and the Full Potential Linear Augmented Plane Wave (FP-LAPW) method. By means of fitting the Murnaghan's state equation we determine the lattice constant, the bulk modulus and it's derived with the pressure. Also we calculated the density of states (DOS) and the band structure.Keywords: bismuth, magnesium, pseudo-potential, supercell
Procedia PDF Downloads 82219177 Advancements in Predicting Diabetes Biomarkers: A Machine Learning Epigenetic Approach
Authors: James Ladzekpo
Abstract:
Background: The urgent need to identify new pharmacological targets for diabetes treatment and prevention has been amplified by the disease's extensive impact on individuals and healthcare systems. A deeper insight into the biological underpinnings of diabetes is crucial for the creation of therapeutic strategies aimed at these biological processes. Current predictive models based on genetic variations fall short of accurately forecasting diabetes. Objectives: Our study aims to pinpoint key epigenetic factors that predispose individuals to diabetes. These factors will inform the development of an advanced predictive model that estimates diabetes risk from genetic profiles, utilizing state-of-the-art statistical and data mining methods. Methodology: We have implemented a recursive feature elimination with cross-validation using the support vector machine (SVM) approach for refined feature selection. Building on this, we developed six machine learning models, including logistic regression, k-Nearest Neighbors (k-NN), Naive Bayes, Random Forest, Gradient Boosting, and Multilayer Perceptron Neural Network, to evaluate their performance. Findings: The Gradient Boosting Classifier excelled, achieving a median recall of 92.17% and outstanding metrics such as area under the receiver operating characteristics curve (AUC) with a median of 68%, alongside median accuracy and precision scores of 76%. Through our machine learning analysis, we identified 31 genes significantly associated with diabetes traits, highlighting their potential as biomarkers and targets for diabetes management strategies. Conclusion: Particularly noteworthy were the Gradient Boosting Classifier and Multilayer Perceptron Neural Network, which demonstrated potential in diabetes outcome prediction. We recommend future investigations to incorporate larger cohorts and a wider array of predictive variables to enhance the models' predictive capabilities.Keywords: diabetes, machine learning, prediction, biomarkers
Procedia PDF Downloads 5519176 Active Contours for Image Segmentation Based on Complex Domain Approach
Authors: Sajid Hussain
Abstract:
The complex domain approach for image segmentation based on active contour has been designed, which deforms step by step to partition an image into numerous expedient regions. A novel region-based trigonometric complex pressure force function is proposed, which propagates around the region of interest using image forces. The signed trigonometric force function controls the propagation of the active contour and the active contour stops on the exact edges of the object accurately. The proposed model makes the level set function binary and uses Gaussian smoothing kernel to adjust and escape the re-initialization procedure. The working principle of the proposed model is as follows: The real image data is transformed into complex data by iota (i) times of image data and the average iota (i) times of horizontal and vertical components of the gradient of image data is inserted in the proposed model to catch complex gradient of the image data. A simple finite difference mathematical technique has been used to implement the proposed model. The efficiency and robustness of the proposed model have been verified and compared with other state-of-the-art models.Keywords: image segmentation, active contour, level set, Mumford and Shah model
Procedia PDF Downloads 11419175 Investigation of Extreme Gradient Boosting Model Prediction of Soil Strain-Shear Modulus
Authors: Ehsan Mehryaar, Reza Bushehri
Abstract:
One of the principal parameters defining the clay soil dynamic response is the strain-shear modulus relation. Predicting the strain and, subsequently, shear modulus reduction of the soil is essential for performance analysis of structures exposed to earthquake and dynamic loadings. Many soil properties affect soil’s dynamic behavior. In order to capture those effects, in this study, a database containing 1193 data points consists of maximum shear modulus, strain, moisture content, initial void ratio, plastic limit, liquid limit, initial confining pressure resulting from dynamic laboratory testing of 21 clays is collected for predicting the shear modulus vs. strain curve of soil. A model based on an extreme gradient boosting technique is proposed. A tree-structured parzan estimator hyper-parameter tuning algorithm is utilized simultaneously to find the best hyper-parameters for the model. The performance of the model is compared to the existing empirical equations using the coefficient of correlation and root mean square error.Keywords: XGBoost, hyper-parameter tuning, soil shear modulus, dynamic response
Procedia PDF Downloads 20119174 Mathematical Properties of the Resonance of the Inner Waves in Rotating Stratified Three-Dimensional Fluids
Authors: A. Giniatoulline
Abstract:
We consider the internal oscillations of the ocean which are caused by the gravity force and the Coriolis force, for different models with changeable density, heat transfer, and salinity. Traditionally, the mathematical description of the resonance effect is related to the growing amplitude as a result of input vibrations. We offer a different approach: the study of the relation between the spectrum of the internal oscillations and the properties of the limiting amplitude of the solution for the harmonic input vibrations of the external forces. Using the results of the spectral theory of self-adjoint operators in Hilbert functional spaces, we prove that there exists an explicit relation between the localization of the frequency of the external input vibrations with respect to the essential spectrum of proper inner oscillations and the non-uniqueness of the limiting amplitude. The results may find their application in various problems concerning mathematical modeling of turbulent flows in the ocean.Keywords: computational fluid dynamics, essential spectrum, limiting amplitude, rotating fluid, spectral theory, stratified fluid, the uniqueness of solutions of PDE equations
Procedia PDF Downloads 25819173 Comparison of Agree Method and Shortest Path Method for Determining the Flow Direction in Basin Morphometric Analysis: Case Study of Lower Tapi Basin, Western India
Authors: Jaypalsinh Parmar, Pintu Nakrani, Bhaumik Shah
Abstract:
Digital Elevation Model (DEM) is elevation data of the virtual grid on the ground. DEM can be used in application in GIS such as hydrological modelling, flood forecasting, morphometrical analysis and surveying etc.. For morphometrical analysis the stream flow network plays a very important role. DEM lacks accuracy and cannot match field data as it should for accurate results of morphometrical analysis. The present study focuses on comparing the Agree method and the conventional Shortest path method for finding out morphometric parameters in the flat region of the Lower Tapi Basin which is located in the western India. For the present study, open source SRTM (Shuttle Radar Topography Mission with 1 arc resolution) and toposheets issued by Survey of India (SOI) were used to determine the morphometric linear aspect such as stream order, number of stream, stream length, bifurcation ratio, mean stream length, mean bifurcation ratio, stream length ratio, length of overland flow, constant of channel maintenance and aerial aspect such as drainage density, stream frequency, drainage texture, form factor, circularity ratio, elongation ratio, shape factor and relief aspect such as relief ratio, gradient ratio and basin relief for 53 catchments of Lower Tapi Basin. Stream network was digitized from the available toposheets. Agree DEM was created by using the SRTM and stream network from the toposheets. The results obtained were used to demonstrate a comparison between the two methods in the flat areas.Keywords: agree method, morphometric analysis, lower Tapi basin, shortest path method
Procedia PDF Downloads 239