Search results for: error floors
376 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 148375 Correlation between Cephalometric Measurements and Visual Perception of Facial Profile in Skeletal Type II Patients
Authors: Choki, Supatchai Boonpratham, Suwannee Luppanapornlarp
Abstract:
The objective of this study was to find a correlation between cephalometric measurements and visual perception of facial profile in skeletal type II patients. In this study, 250 lateral cephalograms of female patients from age, 20 to 22 years were analyzed. The profile outlines of all the samples were hand traced and transformed into silhouettes by the principal investigator. Profile ratings were done by 9 orthodontists on Visual Analogue Scale from score one to ten (increasing level of convexity). 37 hard issue and soft tissue cephalometric measurements were analyzed by the principal investigator. All the measurements were repeated after 2 weeks interval for error assessment. At last, the rankings of visual perceptions were correlated with cephalometric measurements using Spearman correlation coefficient (P < 0.05). The results show that the increase in facial convexity was correlated with higher values of ANB (A point, nasion and B point), AF-BF (distance from A point to B point in mm), L1-NB (distance from lower incisor to NB line in mm), anterior maxillary alveolar height, posterior maxillary alveolar height, overjet, H angle hard tissue, H angle soft tissue and lower lip to E plane (absolute correlation values from 0.277 to 0.711). In contrast, the increase in facial convexity was correlated with lower values of Pg. to N perpendicular and Pg. to NB (mm) (absolute correlation value -0.302 and -0.294 respectively). From the soft tissue measurements, H angles had a higher correlation with visual perception than facial contour angle, nasolabial angle, and lower lip to E plane. In conclusion, the findings of this study indicated that the correlation of cephalometric measurements with visual perception was less than expected. Only 29% of cephalometric measurements had a significant correlation with visual perception. Therefore, diagnosis based solely on cephalometric analysis can result in failure to meet the patient’s esthetic expectation.Keywords: cephalometric measurements, facial profile, skeletal type II, visual perception
Procedia PDF Downloads 130374 A Trend Based Forecasting Framework of the ATA Method and Its Performance on the M3-Competition Data
Authors: H. Taylan Selamlar, I. Yavuz, G. Yapar
Abstract:
It is difficult to make predictions especially about the future and making accurate predictions is not always easy. However, better predictions remain the foundation of all science therefore the development of accurate, robust and reliable forecasting methods is very important. Numerous number of forecasting methods have been proposed and studied in the literature. There are still two dominant major forecasting methods: Box-Jenkins ARIMA and Exponential Smoothing (ES), and still new methods are derived or inspired from them. After more than 50 years of widespread use, exponential smoothing is still one of the most practically relevant forecasting methods available due to their simplicity, robustness and accuracy as automatic forecasting procedures especially in the famous M-Competitions. Despite its success and widespread use in many areas, ES models have some shortcomings that negatively affect the accuracy of forecasts. Therefore, a new forecasting method in this study will be proposed to cope with these shortcomings and it will be called ATA method. This new method is obtained from traditional ES models by modifying the smoothing parameters therefore both methods have similar structural forms and ATA can be easily adapted to all of the individual ES models however ATA has many advantages due to its innovative new weighting scheme. In this paper, the focus is on modeling the trend component and handling seasonality patterns by utilizing classical decomposition. Therefore, ATA method is expanded to higher order ES methods for additive, multiplicative, additive damped and multiplicative damped trend components. The proposed models are called ATA trended models and their predictive performances are compared to their counter ES models on the M3 competition data set since it is still the most recent and comprehensive time-series data collection available. It is shown that the models outperform their counters on almost all settings and when a model selection is carried out amongst these trended models ATA outperforms all of the competitors in the M3- competition for both short term and long term forecasting horizons when the models’ forecasting accuracies are compared based on popular error metrics.Keywords: accuracy, exponential smoothing, forecasting, initial value
Procedia PDF Downloads 172373 Surveillance of Adverse Events Following Immunization during New Vaccines Introduction in Cameroon: A Cross-Sectional Study on the Role of Mobile Technology
Authors: Andreas Ateke Njoh, Shalom Tchokfe Ndoula, Amani Adidja, Germain Nguessan Menan, Annie Mengue, Eric Mboke, Hassan Ben Bachir, Sangwe Clovis Nchinjoh, Yauba Saidu, Laurent Cleenewerck De Kiev
Abstract:
Vaccines serve a great deal in protecting the population globally. Vaccine products are subject to rigorous quality control and approval before use to ensure safety. Even if all actors take the required precautions, some people could still have adverse events following immunization (AEFI) caused by the vaccine composition or an error in its administration. AEFI underreporting is pronounced in low-income settings like Cameroon. The Country introduced electronic platforms to strengthen surveillance. With the introduction of many novel vaccines, like COVID-19 and the novel Oral Polio Vaccine (nOPV) 2, there was a need to monitor AEFI in the Country. A cross-sectional study was conducted from July to December 2022. Data on AEFI per region of Cameroon were reviewed for the past five years. Data were analyzed with MS Excel, and the results were presented in proportions. AEFI reporting was uncommon in Cameroon. With the introduction of novel vaccines in 2021, the health authorities engaged in new tools and training to capture cases. AEFI detected almost doubled using the open data kit (ODK) compared to previous platforms, especially following the introduction of the nOPV2 and COVID-19 vaccines. The AEFI rate was 1.9 and 160 per administered 100 000 doses of nOPV2 and COVID-19 vaccines, respectively. This mobile tool captured individual information for people with AEFI from all regions. The platform helped to identify common AEFI following the use of these new vaccines. The ODK mobile technology was vital in improving AEFI reporting and providing data to monitor using new vaccines in Cameroon.Keywords: adverse events following immunization, cameroon, COVID-19 vaccines, nOPV, ODK
Procedia PDF Downloads 82372 Creating Database and Building 3D Geological Models: A Case Study on Bac Ai Pumped Storage Hydropower Project
Authors: Nguyen Chi Quang, Nguyen Duong Tri Nguyen
Abstract:
This article is the first step to research and outline the structure of the geotechnical database in the geological survey of a power project; in the context of this report creating the database that has been carried out for the Bac Ai pumped storage hydropower project. For the purpose of providing a method of organizing and storing geological and topographic survey data and experimental results in a spatial database, the RockWorks software is used to bring optimal efficiency in the process of exploiting, using, and analyzing data in service of the design work in the power engineering consulting. Three-dimensional (3D) geotechnical models are created from the survey data: such as stratigraphy, lithology, porosity, etc. The results of the 3D geotechnical model in the case of Bac Ai pumped storage hydropower project include six closely stacked stratigraphic formations by Horizons method, whereas modeling of engineering geological parameters is performed by geostatistical methods. The accuracy and reliability assessments are tested through error statistics, empirical evaluation, and expert methods. The three-dimensional model analysis allows better visualization of volumetric calculations, excavation and backfilling of the lake area, tunneling of power pipelines, and calculation of on-site construction material reserves. In general, the application of engineering geological modeling makes the design work more intuitive and comprehensive, helping construction designers better identify and offer the most optimal design solutions for the project. The database always ensures the update and synchronization, as well as enables 3D modeling of geological and topographic data to integrate with the designed data according to the building information modeling. This is also the base platform for BIM & GIS integration.Keywords: database, engineering geology, 3D Model, RockWorks, Bac Ai pumped storage hydropower project
Procedia PDF Downloads 156371 Loss Function Optimization for CNN-Based Fingerprint Anti-Spoofing
Authors: Yehjune Heo
Abstract:
As biometric systems become widely deployed, the security of identification systems can be easily attacked by various spoof materials. This paper contributes to finding a reliable and practical anti-spoofing method using Convolutional Neural Networks (CNNs) based on the types of loss functions and optimizers. The types of CNNs used in this paper include AlexNet, VGGNet, and ResNet. By using various loss functions including Cross-Entropy, Center Loss, Cosine Proximity, and Hinge Loss, and various loss optimizers which include Adam, SGD, RMSProp, Adadelta, Adagrad, and Nadam, we obtained significant performance changes. We realize that choosing the correct loss function for each model is crucial since different loss functions lead to different errors on the same evaluation. By using a subset of the Livdet 2017 database, we validate our approach to compare the generalization power. It is important to note that we use a subset of LiveDet and the database is the same across all training and testing for each model. This way, we can compare the performance, in terms of generalization, for the unseen data across all different models. The best CNN (AlexNet) with the appropriate loss function and optimizers result in more than 3% of performance gain over the other CNN models with the default loss function and optimizer. In addition to the highest generalization performance, this paper also contains the models with high accuracy associated with parameters and mean average error rates to find the model that consumes the least memory and computation time for training and testing. Although AlexNet has less complexity over other CNN models, it is proven to be very efficient. For practical anti-spoofing systems, the deployed version should use a small amount of memory and should run very fast with high anti-spoofing performance. For our deployed version on smartphones, additional processing steps, such as quantization and pruning algorithms, have been applied in our final model.Keywords: anti-spoofing, CNN, fingerprint recognition, loss function, optimizer
Procedia PDF Downloads 132370 Quantitative Evaluation of Supported Catalysts Key Properties from Electron Tomography Studies: Assessing Accuracy Using Material-Realistic 3D-Models
Authors: Ainouna Bouziane
Abstract:
The ability of Electron Tomography to recover the 3D structure of catalysts, with spatial resolution in the subnanometer scale, has been widely explored and reviewed in the last decades. A variety of experimental techniques, based either on Transmission Electron Microscopy (TEM) or Scanning Transmission Electron Microscopy (STEM) have been used to reveal different features of nanostructured catalysts in 3D, but High Angle Annular Dark Field imaging in STEM mode (HAADF-STEM) stands out as the most frequently used, given its chemical sensitivity and avoidance of imaging artifacts related to diffraction phenomena when dealing with crystalline materials. In this regard, our group has developed a methodology that combines image denoising by undecimated wavelet transforms (UWT) with automated, advanced segmentation procedures and parameter selection methods using CS-TVM (Compressed Sensing-total variation minimization) algorithms to reveal more reliable quantitative information out of the 3D characterization studies. However, evaluating the accuracy of the magnitudes estimated from the segmented volumes is also an important issue that has not been properly addressed yet, because a perfectly known reference is needed. The problem particularly complicates in the case of multicomponent material systems. To tackle this key question, we have developed a methodology that incorporates volume reconstruction/segmentation methods. In particular, we have established an approach to evaluate, in quantitative terms, the accuracy of TVM reconstructions, which considers the influence of relevant experimental parameters like the range of tilt angles, image noise level or object orientation. The approach is based on the analysis of material-realistic, 3D phantoms, which include the most relevant features of the system under analysis.Keywords: electron tomography, supported catalysts, nanometrology, error assessment
Procedia PDF Downloads 75369 In vivo Mechanical Characterization of Facial Skin Combining Digital Image Correlation and Finite Element
Authors: Huixin Wei, Shibin Wang, Linan Li, Lei Zhou, Xinhao Tu
Abstract:
Facial skin is a biomedical material with complex mechanical properties of anisotropy, viscoelasticity, and hyperelasticity. The mechanical properties of facial skin are crucial for a number of applications including facial plastic surgery, animation, dermatology, cosmetic industry, and impact biomechanics. Skin is a complex multi-layered material which can be broadly divided into three main layers, the epidermis, the dermis, and the hypodermis. Collagen fibers account for 75% of the dry weight of dermal tissue, and it is these fibers which are responsible for the mechanical properties of skin. Many research on the anisotropic mechanical properties are mainly concentrated on in vitro, but there is a great difference between in vivo and in vitro for mechanical properties of the skin. In this study, we presented a method to measure the mechanical properties of facial skin in vivo. Digital image correlation (DIC) and indentation tests were used to obtain the experiment data, including the deformation of facial surface and indentation force-displacement curve. Then, the experiment was simulated using a finite element (FE) model. Application of Computed Tomography (CT) and reconstruction techniques obtained the real tissue geometry. A three-dimensional FE model of facial skin, including a bi-layer system, was obtained. As the epidermis is relatively thin, the epidermis and dermis were regarded as one layer and below it was hypodermis in this study. The upper layer was modeled as a Gasser-Ogden-Holzapfel (GOH) model to describe hyperelastic and anisotropic behaviors of the dermis. The under layer was modeled as a linear elastic model. In conclusion, the material properties of two-layer were determined by minimizing the error between the FE data and experimental data.Keywords: facial skin, indentation test, finite element, digital image correlation, computed tomography
Procedia PDF Downloads 105368 The Effect of Low Power Laser on CK and Some of Markers Delayed Onset Muscle Soreness (DOMS)
Authors: Bahareh Yazdanparast Chaharmahali
Abstract:
The study showed effect of low power laser therapy on knee range of motion (flexion and extension), resting angle of knee joint, knee circumference and rating of delayed onset muscle soreness induced pain, 24 and 48 hours after eccentric training of knee flexor muscle (hamstring muscle). We investigate the effects of pulsed ultrasound on swelling, relaxed, flexion and extension knee angle and pain. 20 volunteers among girl students of college voluntary participated in this research. After eccentric training, subjects were randomly divided into two groups, control and laser therapy. In day 1 and in order to induce delayed onset muscle soreness, subjects eccentrically trained their knee flexor muscles. In day 2, subjects were randomly divided into two groups: control and low power laser therapy. 24 and 48 hours after eccentric training. Variables (knee flexion and extension, srang of motion, resting knee joint angle and knee circumferences) were measured and analyzed. Data are reported as means ± standard error (SE) and repeated measured was used to assess differences within groups. Methods of treatment (low power laser therapy) have significant effects on delayed onset muscle soreness markers. 24 and 48 hours after training a significant difference was observed between mean pains of 2 groups. This difference was significant between low power laser therapy and C groups. The Bonferroni post hock is significant. Low power laser therapy trophy as used in this study did significantly diminish the effects of delayed – onset muscle soreness on swelling, relaxed – knee extension and flexion angle.Keywords: creatine kinase, DOMS, eccentric training, low power laser
Procedia PDF Downloads 241367 Evaluation of Elements Impurities in Drugs According to Pharmacopoeia by use FESEM-EDS Technique
Authors: Rafid Doulab
Abstract:
Elemental Impurities in the Pharmaceuticals industryis are indispensable to ensure pharmaceuticalssafety for 24 elements. Although atomic absorption and inductively coupled plasma are used in the U.S Pharmacopeia and the European Pharmacopoeia, FESEM with energy dispersive spectrometers can be applied as an alternative analysis method for quantitative and qualitative results for a variety of elements without chemical pretreatment, unlike other techniques. This technique characterizes by shortest time, with more less contamination, no reagent consumption, and generation of minimal residue or waste, as well as sample preparations time limiting, with minimal analysis error. Simple dilution for powder or direct analysis for liquid, we analyzed the usefulness of EDS method in testing with field emission scanning electron microscopy (FESEM, SUPRA 55 Carl Zeiss Germany) with an X-ray energy dispersion (XFlash6l10 Bruker Germany). The samples analyzed directly without coating by applied 5µ of known concentrated diluted sample on carbon stub with accelerated voltage according to sample thickness, the result for this spot was in atomic percentage, and by Avogadro converted factor, the final result will be in microgram. Conclusion and recommendation: The conclusion of this study is application of FESEM-EDS in US pharmacopeia and ICH /Q3D guideline to reach a high-precision and accurate method in element impurities analysis of drugs or bulk materials to determine the permitted daily exposure PDE in liquid or solid specimens, and to obtain better results than other techniques, by the way it does not require complex methods or chemicals for digestion, which interfere with the final results with the possibility of to keep the sample at any time for re analysis. The recommendation is to use this technique in pharmacopeia as standard methods like inductively coupled plasma both ICP-AES, ICP-OES, and ICP-MS.Keywords: pharmacopoeia, FESEM-EDS, element impurities, atomic concentration
Procedia PDF Downloads 112366 Performance Comparison and Visualization of COMSOL Multiphysics, Matlab, and Fortran for Predicting the Reservoir Pressure on Oil Production in a Multiple Leases Reservoir with Boundary Element Method
Authors: N. Alias, W. Z. W. Muhammad, M. N. M. Ibrahim, M. Mohamed, H. F. S. Saipol, U. N. Z. Ariffin, N. A. Zakaria, M. S. Z. Suardi
Abstract:
This paper presents the performance comparison of some computation software for solving the boundary element method (BEM). BEM formulation is the numerical technique and high potential for solving the advance mathematical modeling to predict the production of oil well in arbitrarily shaped based on multiple leases reservoir. The limitation of data validation for ensuring that a program meets the accuracy of the mathematical modeling is considered as the research motivation of this paper. Thus, based on this limitation, there are three steps involved to validate the accuracy of the oil production simulation process. In the first step, identify the mathematical modeling based on partial differential equation (PDE) with Poisson-elliptic type to perform the BEM discretization. In the second step, implement the simulation of the 2D BEM discretization using COMSOL Multiphysic and MATLAB programming languages. In the last step, analyze the numerical performance indicators for both programming languages by using the validation of Fortran programming. The performance comparisons of numerical analysis are investigated in terms of percentage error, comparison graph and 2D visualization of pressure on oil production of multiple leases reservoir. According to the performance comparison, the structured programming in Fortran programming is the alternative software for implementing the accurate numerical simulation of BEM. As a conclusion, high-level language for numerical computation and numerical performance evaluation are satisfied to prove that Fortran is well suited for capturing the visualization of the production of oil well in arbitrarily shaped.Keywords: performance comparison, 2D visualization, COMSOL multiphysic, MATLAB, Fortran, modelling and simulation, boundary element method, reservoir pressure
Procedia PDF Downloads 484365 Data Centers’ Temperature Profile Simulation Optimized by Finite Elements and Discretization Methods
Authors: José Alberto García Fernández, Zhimin Du, Xinqiao Jin
Abstract:
Nowadays, data center industry faces strong challenges for increasing the speed and data processing capacities while at the same time is trying to keep their devices a suitable working temperature without penalizing that capacity. Consequently, the cooling systems of this kind of facilities use a large amount of energy to dissipate the heat generated inside the servers, and developing new cooling techniques or perfecting those already existing would be a great advance in this type of industry. The installation of a temperature sensor matrix distributed in the structure of each server would provide the necessary information for collecting the required data for obtaining a temperature profile instantly inside them. However, the number of temperature probes required to obtain the temperature profiles with sufficient accuracy is very high and expensive. Therefore, other less intrusive techniques are employed where each point that characterizes the server temperature profile is obtained by solving differential equations through simulation methods, simplifying data collection techniques but increasing the time to obtain results. In order to reduce these calculation times, complicated and slow computational fluid dynamics simulations are replaced by simpler and faster finite element method simulations which solve the Burgers‘ equations by backward, forward and central discretization techniques after simplifying the energy and enthalpy conservation differential equations. The discretization methods employed for solving the first and second order derivatives of the obtained Burgers‘ equation after these simplifications are the key for obtaining results with greater or lesser accuracy regardless of the characteristic truncation error.Keywords: Burgers' equations, CFD simulation, data center, discretization methods, FEM simulation, temperature profile
Procedia PDF Downloads 159364 A Segmentation Method for Grayscale Images Based on the Firefly Algorithm and the Gaussian Mixture Model
Authors: Donatella Giuliani
Abstract:
In this research, we propose an unsupervised grayscale image segmentation method based on a combination of the Firefly Algorithm and the Gaussian Mixture Model. Firstly, the Firefly Algorithm has been applied in a histogram-based research of cluster means. The Firefly Algorithm is a stochastic global optimization technique, centered on the flashing characteristics of fireflies. In this context it has been performed to determine the number of clusters and the related cluster means in a histogram-based segmentation approach. Successively these means are used in the initialization step for the parameter estimation of a Gaussian Mixture Model. The parametric probability density function of a Gaussian Mixture Model is represented as a weighted sum of Gaussian component densities, whose parameters are evaluated applying the iterative Expectation-Maximization technique. The coefficients of the linear super-position of Gaussians can be thought as prior probabilities of each component. Applying the Bayes rule, the posterior probabilities of the grayscale intensities have been evaluated, therefore their maxima are used to assign each pixel to the clusters, according to their gray-level values. The proposed approach appears fairly solid and reliable when applied even to complex grayscale images. The validation has been performed by using different standard measures, more precisely: the Root Mean Square Error (RMSE), the Structural Content (SC), the Normalized Correlation Coefficient (NK) and the Davies-Bouldin (DB) index. The achieved results have strongly confirmed the robustness of this gray scale segmentation method based on a metaheuristic algorithm. Another noteworthy advantage of this methodology is due to the use of maxima of responsibilities for the pixel assignment that implies a consistent reduction of the computational costs.Keywords: clustering images, firefly algorithm, Gaussian mixture model, meta heuristic algorithm, image segmentation
Procedia PDF Downloads 211363 LTE Performance Analysis in the City of Bogota Northern Zone for Two Different Mobile Broadband Operators over Qualipoc
Authors: Víctor D. Rodríguez, Edith P. Estupiñán, Juan C. Martínez
Abstract:
The evolution in mobile broadband technologies has allowed to increase the download rates in users considering the current services. The evaluation of technical parameters at the link level is of vital importance to validate the quality and veracity of the connection, thus avoiding large losses of data, time and productivity. Some of these failures may occur between the eNodeB (Evolved Node B) and the user equipment (UE), so the link between the end device and the base station can be observed. LTE (Long Term Evolution) is considered one of the IP-oriented mobile broadband technologies that work stably for data and VoIP (Voice Over IP) for those devices that have that feature. This research presents a technical analysis of the connection and channeling processes between UE and eNodeB with the TAC (Tracking Area Code) variables, and analysis of performance variables (Throughput, Signal to Interference and Noise Ratio (SINR)). Three measurement scenarios were proposed in the city of Bogotá using QualiPoc, where two operators were evaluated (Operator 1 and Operator 2). Once the data were obtained, an analysis of the variables was performed determining that the data obtained in transmission modes vary depending on the parameters BLER (Block Error Rate), performance and SNR (Signal-to-Noise Ratio). In the case of both operators, differences in transmission modes are detected and this is reflected in the quality of the signal. In addition, due to the fact that both operators work in different frequencies, it can be seen that Operator 1, despite having spectrum in Band 7 (2600 MHz), together with Operator 2, is reassigning to another frequency, a lower band, which is AWS (1700 MHz), but the difference in signal quality with respect to the establishment with data by the provider Operator 2 and the difference found in the transmission modes determined by the eNodeB in Operator 1 is remarkable.Keywords: BLER, LTE, network, qualipoc, SNR.
Procedia PDF Downloads 111362 A Hybrid Block Multistep Method for Direct Numerical Integration of Fourth Order Initial Value Problems
Authors: Adamu S. Salawu, Ibrahim O. Isah
Abstract:
Direct solution to several forms of fourth-order ordinary differential equations is not easily obtained without first reducing them to a system of first-order equations. Thus, numerical methods are being developed with the underlying techniques in the literature, which seeks to approximate some classes of fourth-order initial value problems with admissible error bounds. Multistep methods present a great advantage of the ease of implementation but with a setback of several functions evaluation for every stage of implementation. However, hybrid methods conventionally show a slightly higher order of truncation for any k-step linear multistep method, with the possibility of obtaining solutions at off mesh points within the interval of solution. In the light of the foregoing, we propose the continuous form of a hybrid multistep method with Chebyshev polynomial as a basis function for the numerical integration of fourth-order initial value problems of ordinary differential equations. The basis function is interpolated and collocated at some points on the interval [0, 2] to yield a system of equations, which is solved to obtain the unknowns of the approximating polynomial. The continuous form obtained, its first and second derivatives are evaluated at carefully chosen points to obtain the proposed block method needed to directly approximate fourth-order initial value problems. The method is analyzed for convergence. Implementation of the method is done by conducting numerical experiments on some test problems. The outcome of the implementation of the method suggests that the method performs well on problems with oscillatory or trigonometric terms since the approximations at several points on the solution domain did not deviate too far from the theoretical solutions. The method also shows better performance compared with an existing hybrid method when implemented on a larger interval of solution.Keywords: Chebyshev polynomial, collocation, hybrid multistep method, initial value problems, interpolation
Procedia PDF Downloads 120361 Fem Models of Glued Laminated Timber Beams Enhanced by Bayesian Updating of Elastic Moduli
Authors: L. Melzerová, T. Janda, M. Šejnoha, J. Šejnoha
Abstract:
Two finite element (FEM) models are presented in this paper to address the random nature of the response of glued timber structures made of wood segments with variable elastic moduli evaluated from 3600 indentation measurements. This total database served to create the same number of ensembles as was the number of segments in the tested beam. Statistics of these ensembles were then assigned to given segments of beams and the Latin Hypercube Sampling (LHS) method was called to perform 100 simulations resulting into the ensemble of 100 deflections subjected to statistical evaluation. Here, a detailed geometrical arrangement of individual segments in the laminated beam was considered in the construction of two-dimensional FEM model subjected to in four-point bending to comply with the laboratory tests. Since laboratory measurements of local elastic moduli may in general suffer from a significant experimental error, it appears advantageous to exploit the full scale measurements of timber beams, i.e. deflections, to improve their prior distributions with the help of the Bayesian statistical method. This, however, requires an efficient computational model when simulating the laboratory tests numerically. To this end, a simplified model based on Mindlin’s beam theory was established. The improved posterior distributions show that the most significant change of the Young’s modulus distribution takes place in laminae in the most strained zones, i.e. in the top and bottom layers within the beam center region. Posterior distributions of moduli of elasticity were subsequently utilized in the 2D FEM model and compared with the original simulations.Keywords: Bayesian inference, FEM, four point bending test, laminated timber, parameter estimation, prior and posterior distribution, Young’s modulus
Procedia PDF Downloads 279360 An Intelligent Controller Augmented with Variable Zero Lag Compensation for Antilock Braking System
Authors: Benjamin Chijioke Agwah, Paulinus Chinaenye Eze
Abstract:
Antilock braking system (ABS) is one of the important contributions by the automobile industry, designed to ensure road safety in such way that vehicles are kept steerable and stable when during emergency braking. This paper presents a wheel slip-based intelligent controller with variable zero lag compensation for ABS. It is required to achieve a very fast perfect wheel slip tracking during hard braking condition and eliminate chattering with improved transient and steady state performance, while shortening the stopping distance using effective braking torque less than maximum allowable torque to bring a braking vehicle to a stop. The dynamic of a vehicle braking with a braking velocity of 30 ms⁻¹ on a straight line was determined and modelled in MATLAB/Simulink environment to represent a conventional ABS system without a controller. Simulation results indicated that system without a controller was not able to track desired wheel slip and the stopping distance was 135.2 m. Hence, an intelligent control based on fuzzy logic controller (FLC) was designed with a variable zero lag compensator (VZLC) added to enhance the performance of FLC control variable by eliminating steady state error, provide improve bandwidth to eliminate the effect of high frequency noise such as chattering during braking. The simulation results showed that FLC- VZLC provided fast tracking of desired wheel slip, eliminate chattering, and reduced stopping distance by 70.5% (39.92 m), 63.3% (49.59 m), 57.6% (57.35 m) and 50% (69.13 m) on dry, wet, cobblestone and snow road surface conditions respectively. Generally, the proposed system used effective braking torque that is less than the maximum allowable braking torque to achieve efficient wheel slip tracking and overall robust control performance on different road surfaces.Keywords: ABS, fuzzy logic controller, variable zero lag compensator, wheel slip tracking
Procedia PDF Downloads 143359 Hedgerow Detection and Characterization Using Very High Spatial Resolution SAR DATA
Authors: Saeid Gharechelou, Stuart Green, Fiona Cawkwell
Abstract:
Hedgerow has an important role for a wide range of ecological habitats, landscape, agriculture management, carbon sequestration, wood production. Hedgerow detection accurately using satellite imagery is a challenging problem in remote sensing techniques, because in the special approach it is very similar to line object like a road, from a spectral viewpoint, a hedge is very similar to a forest. Remote sensors with very high spatial resolution (VHR) recently enable the automatic detection of hedges by the acquisition of images with enough spectral and spatial resolution. Indeed, recently VHR remote sensing data provided the opportunity to detect the hedgerow as line feature but still remain difficulties in monitoring the characterization in landscape scale. In this research is used the TerraSAR-x Spotlight and Staring mode with 3-5 m resolution in wet and dry season in the test site of Fermoy County, Ireland to detect the hedgerow by acquisition time of 2014-2015. Both dual polarization of Spotlight data in HH/VV is using for detection of hedgerow. The varied method of SAR image technique with try and error way by integration of classification algorithm like texture analysis, support vector machine, k-means and random forest are using to detect hedgerow and its characterization. We are applying the Shannon entropy (ShE) and backscattering analysis in single and double bounce in polarimetric analysis for processing the object-oriented classification and finally extracting the hedgerow network. The result still is in progress and need to apply the other method as well to find the best method in study area. Finally, this research is under way to ahead to get the best result and here just present the preliminary work that polarimetric image of TSX potentially can detect the hedgerow.Keywords: TerraSAR-X, hedgerow detection, high resolution SAR image, dual polarization, polarimetric analysis
Procedia PDF Downloads 227358 Improving Fingerprinting-Based Localization System Using Generative AI
Authors: Getaneh Berie Tarekegn
Abstract:
A precise localization system is crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. The most common method for providing continuous positioning services in outdoor environments is by using a global navigation satellite system (GNSS). Due to nonline-of-sight, multipath, and weather conditions, GNSS systems do not perform well in dense urban, urban, and suburban areas.This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. It also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine
Procedia PDF Downloads 47357 AI-Driven Solutions for Optimizing Master Data Management
Authors: Srinivas Vangari
Abstract:
In the era of big data, ensuring the accuracy, consistency, and reliability of critical data assets is crucial for data-driven enterprises. Master Data Management (MDM) plays a crucial role in this endeavor. This paper investigates the role of Artificial Intelligence (AI) in enhancing MDM, focusing on how AI-driven solutions can automate and optimize various stages of the master data lifecycle. By integrating AI (Quantitative and Qualitative Analysis) into processes such as data creation, maintenance, enrichment, and usage, organizations can achieve significant improvements in data quality and operational efficiency. Quantitative analysis is employed to measure the impact of AI on key metrics, including data accuracy, processing speed, and error reduction. For instance, our study demonstrates an 18% improvement in data accuracy and a 75% reduction in duplicate records across multiple systems post-AI implementation. Furthermore, AI’s predictive maintenance capabilities reduced data obsolescence by 22%, as indicated by statistical analyses of data usage patterns over a 12-month period. Complementing this, a qualitative analysis delves into the specific AI-driven strategies that enhance MDM practices, such as automating data entry and validation, which resulted in a 28% decrease in manual errors. Insights from case studies highlight how AI-driven data cleansing processes reduced inconsistencies by 25% and how AI-powered enrichment strategies improved data relevance by 24%, thus boosting decision-making accuracy. The findings demonstrate that AI significantly enhances data quality and integrity, leading to improved enterprise performance through cost reduction, increased compliance, and more accurate, real-time decision-making. These insights underscore the value of AI as a critical tool in modern data management strategies, offering a competitive edge to organizations that leverage its capabilities.Keywords: artificial intelligence, master data management, data governance, data quality
Procedia PDF Downloads 7356 The Relationships between Energy Consumption, Carbon Dioxide (CO2) Emissions, and GDP for Egypt: Time Series Analysis, 1980-2010
Authors: Jinhoa Lee
Abstract:
The relationships between environmental quality, energy use and economic output have created growing attention over the past decades among researchers and policy makers. Focusing on the empirical aspects of the role of carbon dioxide (CO2) emissions and energy use in affecting the economic output, this paper is an effort to fulfill the gap in a comprehensive case study at a country level using modern econometric techniques. To achieve the goal, this country-specific study examines the short-run and long-run relationships among energy consumption (using disaggregated energy sources: crude oil, coal, natural gas, electricity), CO2 emissions and gross domestic product (GDP) for Egypt using time series analysis from the year 1980-2010. To investigate the relationships between the variables, this paper employs the Augmented Dickey-Fuller (ADF) test for stationarity, Johansen maximum likelihood method for co-integration and a Vector Error Correction Model (VECM) for both short- and long-run causality among the research variables for the sample. The long-run equilibrium in the VECM suggests some negative impacts of the CO2 emissions and the coal and natural gas use on the GDP. Conversely, a positive long-run causality from the electricity consumption to the GDP is found to be significant in Egypt during the period. In the short-run, some positive unidirectional causalities exist, running from the coal consumption to the GDP, and the CO2 emissions and the natural gas use. Further, the GDP and the electricity use are positively influenced by the consumption of petroleum products and the direct combustion of crude oil. Overall, the results support arguments that there are relationships among environmental quality, energy use, and economic output in both the short term and long term; however, the effects may differ due to the sources of energy, such as in the case of Egypt for the period of 1980-2010.Keywords: CO2 emissions, Egypt, energy consumption, GDP, time series analysis
Procedia PDF Downloads 611355 Analysis of a IncResU-Net Model for R-Peak Detection in ECG Signals
Authors: Beatriz Lafuente Alcázar, Yash Wani, Amit J. Nimunkar
Abstract:
Cardiovascular Diseases (CVDs) are the leading cause of death globally, and around 80% of sudden cardiac deaths are due to arrhythmias or irregular heartbeats. The majority of these pathologies are revealed by either short-term or long-term alterations in the electrocardiogram (ECG) morphology. The ECG is the main diagnostic tool in cardiology. It is a non-invasive, pain free procedure that measures the heart’s electrical activity and that allows the detecting of abnormal rhythms and underlying conditions. A cardiologist can diagnose a wide range of pathologies based on ECG’s form alterations, but the human interpretation is subjective and it is contingent to error. Moreover, ECG records can be quite prolonged in time, which can further complicate visual diagnosis, and deeply retard disease detection. In this context, deep learning methods have risen as a promising strategy to extract relevant features and eliminate individual subjectivity in ECG analysis. They facilitate the computation of large sets of data and can provide early and precise diagnoses. Therefore, the cardiology field is one of the areas that can most benefit from the implementation of deep learning algorithms. In the present study, a deep learning algorithm is trained following a novel approach, using a combination of different databases as the training set. The goal of the algorithm is to achieve the detection of R-peaks in ECG signals. Its performance is further evaluated in ECG signals with different origins and features to test the model’s ability to generalize its outcomes. Performance of the model for detection of R-peaks for clean and noisy ECGs is presented. The model is able to detect R-peaks in the presence of various types of noise, and when presented with data, it has not been trained. It is expected that this approach will increase the effectiveness and capacity of cardiologists to detect divergences in the normal cardiac activity of their patients.Keywords: arrhythmia, deep learning, electrocardiogram, machine learning, R-peaks
Procedia PDF Downloads 175354 The Effect of Artificial Intelligence on Electric Machines and Welding
Authors: Mina Malak Zakaria Henin
Abstract:
The finite detail evaluation of magnetic fields in electromagnetic devices shows that the machine cores revel in extraordinary flux patterns consisting of alternating and rotating fields. The rotating fields are generated in different configurations variety, among circular and elliptical, with distinctive ratios between the fundamental and minor axes of the flux locus. Experimental measurements on electrical metal uncovered one-of-a-kind flux patterns that divulge distinctive magnetic losses in the samples below the test. Therefore, electric machines require unique interest throughout the core loss calculation technique to bear in mind the flux styles. In this look, a circular rotational unmarried sheet tester is employed to measure the middle losses in the electric-powered metallic pattern of M36G29. The sample becomes exposed to alternating fields, circular areas, and elliptical fields with axis ratios of zero.2, zero. Four, 0.6 and 0.8. The measured statistics changed into applied on 6-4 switched reluctance motors at 3 distinctive frequencies of interest to the industry 60 Hz, 400 Hz, and 1 kHz. The effects reveal an excessive margin of error, which can arise at some point in the loss calculations if the flux pattern difficulty is overlooked. The mistake in exceptional components of the gadget associated with considering the flux styles may be around 50%, 10%, and a couple of at 60Hz, 400Hz, and 1 kHz, respectively. The future paintings will focus on the optimization of gadget geometrical shape, which has a primary effect on the flux sample on the way to decrease the magnetic losses in system cores.Keywords: converters, electric machines, MEA (more electric aircraft), PES (power electronics systems) synchronous machine, vector control Multi-machine/ Multi-inverter, matrix inverter, Railway tractionalternating core losses, finite element analysis, rotational core losses
Procedia PDF Downloads 12353 Optimization of Biomass Components from Rice Husk Treated with Trichophyton Soudanense and Trichophyton Mentagrophyte and Effect of Yeast on the Bio-Ethanol Yield
Authors: Chukwuma S. Ezeonu, Ikechukwu N. E. Onwurah, Uchechukwu U. Nwodo, Chibuike S. Ubani, Chigozie M. Ejikeme
Abstract:
Trichophyton soudanense and Trichophyton mentagrophyte were isolated from the rice mill environment, cultured and used singly and as di-culture in the treatment of measure quantities of preheated rice husk. Optimized conditions studied showed that carboxymethylcellulase (CMCellulase) activity of 57.61 µg/ml/min was optimum for Trichophyton mentagrophyte heat pretreated rice husk crude enzymes at 50oC and 80oC respectively. Duration of 120 hours (5 days) gave the highest CMcellulase activity of 75.84 µg/ml/min for crude enzyme of Trichophyton mentagrophyte heat pretreated rice husk. However, 96 hours (4 days) duration gave maximum activity of 58.21 µg/ml/min for crude enzyme of Trichophyton soudanense heat pretreated rice husk. Highest CMCellulase activities of 67.02 µg/ml/min and 69.02 µg/ml/min at pH of 5 were recorded for crude enzymes of monocultures of Trichophyton soudanense (TS) and Trichophyton mentagrophyte (TM) heat pretreated rice husk respectively. Biomass components showed that rice husk cooled after heating followed by treatment with Trichophyton mentagrophyte gave 44.50 ± 10.90 (% ± Standard Error of Mean) cellulose as the highest yield. Maximum total lignin value of 28.90 ± 1.80 (% ± SEM) was obtained from pre-heated rice husk treated with di-culture of Trichophyton soudanense and Trichophyton mentagrophyte (TS+TM). The hemicellulose content of 30.50 ± 2.12 (% ± SEM) from pre-heated rice husk treated with Trichophyton soudanense (TS); lignin value of 28.90 ± 1.80 from pre-heated rice husk treated with di-culture of Trichophyton soudanense and Trichophyton mentagrophyte (TS+TM); also carbohydrate content of 16.79 ± 9.14 (% ± SEM) , reducing and non-reducing sugar values of 2.66 ± 0.45 and 14.13 ± 8.69 (% ± SEM) were all obtained from for pre- heated rice husk treated with Trichophyton mentagrophyte (TM). All the values listed above were the highest values obtained from each rice husk treatment. The pre-heated rice husk treated with Trichophyton mentagrophyte (TM) fermented with palmwine yeast gave bio-ethanol value of 11.11 ± 0.21 (% ± Standard Deviation) as the highest yield.Keywords: Trichophyton soudanense, Trichophyton mentagrophyte, biomass, bioethanol, rice husk
Procedia PDF Downloads 671352 Prospective Cohort Study on Sequential Use of Catheter with Misoprostol vs Misoprostol Alone for Second Trimester Medical Abortion
Authors: Hanna Teklu Gebregziabher
Abstract:
Background: A variety of techniques for medical termination of second-trimester pregnancy can be used, but there is no consensus about which is the best. Even though most evidence suggests the combined use of intracervical Foley catheter and vaginal misoprostol is safe, effective, and acceptable method for termination of second-trimester pregnancy, which is comparable to mifepristone-misoprostol combination regimen with lower cost and no additional maternal risks. The use of mifepristone and misoprostol alone with no other procedure is still the most common procedure in different institutions for 2nd-trimester pregnancy. Methods: A cross-sectional comparative prospective study design is employed on women who were admitted for 2nd-trimester medical abortion and medical abortion failed or if there was no change in cervical status after 24 hours of 1st dose of misoprostol. The study was conducted at St. Paulose Hospital Millennium Medical College. A sample of 44 participants in each arm was necessary to give a two-tailed test, a type 1 error of 5%, 80% statistical power, and a 1:1 ratio among groups. Thus, a total of 94 cases, 47 from each arm, were recruited. Data was entered and cleaned by using Epi-info and analyzed using SPSS version 29.0 statistical software and was presented in descriptive and tabular forms. Different variables were cross-tabulated and compared for significant differences and statistical analysis using the chi-square test and independent t-test, to conclude. Result: There was a significant difference between the two groups on induction to expulsion time and number of doses used. The mean ± SD of induction to expulsion time for those used misoprostol alone was 48.09 ± 11.86 and those who used trans-cervical catheter sequentially with misoprostol were 36.7 ±6.772. Conclusion: The use of a trans-cervical Foley catheter in conjunction with misoprostol in a sequential manner is a more effective, safe, and easily accessible procedure. In addition, the cost of utilizing the catheter is less compared to the cost of misoprostol and is readily available. As a good substitute, we advised using Trans-cervical Catether even for medical abortions performed in the second trimester.Keywords: second trimester, medical abortion, catheter, misoprostol
Procedia PDF Downloads 38351 Determinants of Success of University Industry Collaboration in the Science Academic Units at Makerere University
Authors: Mukisa Simon Peter Turker, Etomaru Irene
Abstract:
This study examined factors determining the success of University-Industry Collaboration (UIC) in the science academic units (SAUs) at Makerere University. This was prompted by concerns about weak linkages between industry and the academic units at Makerere University. The study examined institutional, relational, output, and framework factors determining the success of UIC in the science academic units at Makerere University. The study adopted a predictive cross-sectional survey design. Data was collected using a questionnaire survey from 172 academic staff from the six SAUs at Makerere University. Stratified, proportionate, and simple random sampling techniques were used to select the samples. The study used descriptive statistics and linear multiple regression analysis to analyze data. The study findings reveal a coefficient of determination (R-square) of 0.403 at a significance level of 0.000, suggesting that UIC success was 40.3% at a standardized error of estimate of 0.60188. The strength of association between Institutional factors, Relational factors, Output factors, and Framework factors, taking into consideration all interactions among the study variables, was at 64% (R= 0.635). Institutional, Relational, Output and Framework factors accounted for 34% of the variance in the level of UIC success (adjusted R2 = 0.338). The remaining variance of 66% is explained by factors other than Institutional, Relational, Output, and Framework factors. The standardized coefficient statistics revealed that Relational factors (β = 0.454, t = 5.247, p = 0.000) and Framework factors (β = 0.311, t = 3.770, p = 0.000) are the only statistically significant determinants of the success of UIC in the SAU in Makerere University. Output factors (β = 0.082, t =1.096, p = 0.275) and Institutional factors β = 0.023, t = 0.292, p = 0.771) turned out to be statistically insignificant determinants of the success of UIC in the science academic units at Makerere University. The study concludes that Relational Factors and Framework Factors positively and significantly determine the success of UIC, but output factors and institutional factors are not statistically significant determinants of UIC in the SAUs at Makerere University. The study recommends strategies to consolidate Relational and Framework Factors to enhance UIC at Makerere University and further research on the effects of Institutional and Output factors on the success of UIC in universities.Keywords: university-industry collaboration, output factors, relational factors, framework factors, institutional factors
Procedia PDF Downloads 52350 Model for Calculating Traffic Mass and Deceleration Delays Based on Traffic Field Theory
Authors: Liu Canqi, Zeng Junsheng
Abstract:
This study identifies two typical bottlenecks that occur when a vehicle cannot change lanes: car following and car stopping. The ideas of traffic field and traffic mass are presented in this work. When there are other vehicles in front of the target vehicle within a particular distance, a force is created that affects the target vehicle's driving speed. The characteristics of the driver and the vehicle collectively determine the traffic mass; the driving speed of the vehicle and external variables have no bearing on this. From a physical level, this study examines the vehicle's bottleneck when following a car, identifies the outside factors that have an impact on how it drives, takes into account that the vehicle will transform kinetic energy into potential energy during deceleration, and builds a calculation model for traffic mass. The energy-time conversion coefficient is created from an economic standpoint utilizing the social average wage level and the average cost of motor fuel. Vissim simulation program measures the vehicle's deceleration distance and delays under the Wiedemann car-following model. The difference between the measured value of deceleration delay acquired by simulation and the theoretical value calculated by the model is compared using the conversion calculation model of traffic mass and deceleration delay. The experimental data demonstrate that the model is reliable since the error rate between the theoretical calculation value of the deceleration delay obtained by the model and the measured value of simulation results is less than 10%. The article's conclusion is that the traffic field has an impact on moving cars on the road and that physical and socioeconomic factors should be taken into account while studying vehicle-following behavior. The deceleration delay value of a vehicle's driving and traffic mass have a socioeconomic relationship that can be utilized to calculate the energy-time conversion coefficient when dealing with the bottleneck of cars stopping and starting.Keywords: traffic field, social economics, traffic mass, bottleneck, deceleration delay
Procedia PDF Downloads 56349 A Survey on Students' Intentions to Dropout and Dropout Causes in Higher Education of Mongolia
Authors: D. Naranchimeg, G. Ulziisaikhan
Abstract:
Student dropout problem has not been recently investigated within the Mongolian higher education. A student dropping out is a personal decision, but it may cause unemployment and other social problems including low quality of life because students who are not completed a degree cannot find better-paid jobs. The research aims to determine percentage of at-risk students, and understand reasons for dropouts and to find a way to predict. The study based on the students of the Mongolian National University of Education including its Arkhangai branch school, National University of Mongolia, Mongolian University of Life Sciences, Mongolian University of Science and Technology, Mongolian National University of Medical Science, Ikh Zasag International University, and Dornod University. We conducted the paper survey by method of random sampling and have surveyed about 100 students per university. The margin of error - 4 %, confidence level -90%, and sample size was 846, but we excluded 56 students from this study. Causes for exclusion were missing data on the questionnaire. The survey has totally 17 questions, 4 of which was demographic questions. The survey shows that 1.4% of the students always thought to dropout whereas 61.8% of them thought sometimes. Also, results of the research suggest that students’ dropouts from university do not have relationships with their sex, marital and social status, and peer and faculty climate, whereas it slightly depends on their chosen specialization. Finally, the paper presents the reasons for dropping out provided by the students. The main two reasons for dropouts are personal reasons related with choosing wrong study program, not liking the course they had chosen (50.38%), and financial difficulties (42.66%). These findings reveal the importance of early prevention of dropout where possible, combined with increased attention to high school students in choosing right for them study program, and targeted financial support for those who are at risk.Keywords: at risk students, dropout, faculty climate, Mongolian universities, peer climate
Procedia PDF Downloads 393348 Selection of Optimal Reduced Feature Sets of Brain Signal Analysis Using Heuristically Optimized Deep Autoencoder
Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh
Abstract:
In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization
Procedia PDF Downloads 110347 EFL Teachers’ Sequential Self-Led Reflection and Possible Modifications in Their Classroom Management Practices
Authors: Sima Modirkhameneh, Mohammad Mohammadpanah
Abstract:
In the process of EFL teachers’ development, self-led reflection (SLR) is thought to have an imperative role because it may help teachers analyze, evaluate, and contemplate what is happening in their classes. Such contemplations can not only enhance the quality of their instruction and provide better learning environments for learners but also improve the quality of their classroom management (CM). Accordingly, understanding the effect of teachers’ SLR practices may help us gain valuable insights into what possible modifications SLR may bring about in all aspects of EFL teachers' practitioners, especially their CM. The main purpose of this case study was, thus, to investigate the impact of SLR practices of 12 Iranian EFL teachers on their CM based on the universal classroom management checklist (UCMC). In addition, another objective of the current study was to have a clear image of EFL teachers’ perceptions of their own SLR practices and their possible outcomes. By conducting repeated reflective interviews, observations, and feedback of the participants over five teaching sessions, the researcher analyzed the outcomes qualitatively through the process of meaning categorization and data interpretation based on the principles of Grounded Theory. The results demonstrated that EFL teachers utilized SLR practices to improve different aspects of their language teaching skills and CM in different contexts. Almost all participants had positive comments and reactions about the effect of SLR on their CM procedures in different aspects (expectations and routines, behavior-specific praise, error corrections, prompts and precorrections, opportunity to respond, strengths and weaknesses of CM, teachers’ perception, CM ability, and learning process). Otherwise stated, results implied that familiarity with the UCMC criteria and reflective practices contributes to modifying teacher participants’ perceptions about their CM procedure and utilizing the reflective practices in their teaching styles. The results are thought to be valuably beneficial for teachers, teacher educators, and policymakers, who are recommended to pay special attention to the contributions as well as the complexity of reflective teaching. The study concludes with more detailed results and implications and useful directions for future research.Keywords: classroom management, EFL teachers, reflective practices, self-led reflection
Procedia PDF Downloads 48