Search results for: time series models

Authors: Abdullah A. AlShaher

Abstract:

In this paper, we demonstrate how regression curves can be used to recognize 2D non-rigid handwritten shapes. Each shape is represented by a set of non-overlapping uniformly distributed landmarks. The underlying models utilize 2^nd order of polynomials to model shapes within a training set. To estimate the regression models, we need to extract the required coefficients which describe the variations for a set of shape class. Hence, a least square method is used to estimate such modes. We then proceed by training these coefficients using the apparatus Expectation Maximization algorithm. Recognition is carried out by finding the least error landmarks displacement with respect to the model curves. Handwritten isolated Arabic characters are used to evaluate our approach.

Keywords: character recognition, regression curves, handwritten Arabic letters, expectation maximization algorithm

Procedia PDF Downloads 145

Authors: Mauro Iannazzone, Carmine D'Agostino

Abstract:

Off-shore wind turbines are currently considered as a reliable source of renewable energy Worldwide and especially in the UK. Most of the operational off-shore wind turbines located in shallow waters (i.e. < 30 m) are supported on monopiles. Monopiles are open-ended steel tubes with diameter ranging between 4 to 6 m. It is expected that future off-shore wind farms will be located in water depths as high as 70 m. Therefore, alternative foundation arrangements are needed. Foundations for off-shore structures normally consist of open-ended piles driven into the soil by means of impact hammers. During pile installation, the soil inside the pile may be mobilized by the increasing shear strength such as to prevent more soil from entering the pile. This phenomenon is known as soil plugging, and represents an important issue as it may change significantly the driving resistance of open-ended piles. In fact, if the plugging formation is unexpected, the installation may require more powerful and more expensive hammers. Engineers need to estimate whether the driven pile will be installed in a plugged or unplugged mode. As a consequence, a prediction of the degree of soil plugging is required in order to correctly predict the drivability of the pile. This work presents a brief review of the state-of-the-art of pile driving and approaches used to predict formation of soil plugs. In addition, a novel analytical approach is proposed, which is based on the vertical equilibrium of a plugged pile. Differently from previous studies, this research takes into account the enhancement of the stress within the soil plug. Finally, the work presents and discusses a series of experimental tests, which are carried out on small-scale models piles to validate the analytical solution.

Keywords: off-shore wind turbines, pile installation, soil plugging, wind energy

Procedia PDF Downloads 312

Authors: P. K. Singhal, R. Naresh, V. Sharma

Abstract:

This paper presents the three optimization models, namely New Binary Artificial Bee Colony (NBABC) algorithm, NBABC with Local Search (NBABC-LS), and NBABC with Genetic Crossover (NBABC-GC) for solving the Wind-Thermal Unit Commitment (WTUC) problem. The uncertain nature of the wind power is incorporated using the Weibull probability density function, which is used to calculate the overestimation and underestimation costs associated with the wind power fluctuation. The NBABC algorithm utilizes a mechanism based on the dissimilarity measure between binary strings for generating the binary solutions in WTUC problem. In NBABC algorithm, an intelligent scout bee phase is proposed that replaces the abandoned solution with the global best solution. The local search operator exploits the neighboring region of the current solutions, whereas the integration of genetic crossover with the NBABC algorithm increases the diversity in the search space and thus avoids the problem of local trappings encountered with the NBABC algorithm. These models are then used to decide the units on/off status, whereas the lambda iteration method is used to dispatch the hourly load demand among the committed units. The effectiveness of the proposed models is validated on an IEEE 10-unit thermal system combined with a wind farm over the planning period of 24 hours.

Keywords: artificial bee colony algorithm, economic dispatch, unit commitment, wind power

Procedia PDF Downloads 375

Authors: Fauzia Dianawati, Riska W. Purnomo

Abstract:

Food and agricultural sector become the biggest sector contributing to inflation in Indonesia. Especially in Wonogiri district, red cayenne pepper was the biggest sector contributing to inflation on 2016. A national statistic proved that in recent five years red cayenne pepper has the highest average level of fluctuation among all commodities. Some factors, like supply chain, price disparity, production quantity, crop failure, and oil price become the possible factor causes high volatility level in red cayenne pepper price. Therefore, this research tries to find the key factor causing fluctuation on red cayenne pepper by using ARCH/GARCH method. The method could accommodate the presence of heteroscedasticity in time series data. At the end of the research, it is statistically found that the second level of supply chain becomes the biggest part contributing to inflation with 3,35 of coefficient in fluctuation forecasting model of red cayenne pepper price. This model could become a reference to the government to determine the appropriate policy in maintaining the price stability of red cayenne pepper.

Keywords: ARCH/GARCH, forecasting, red cayenne pepper, volatility, supply chain

Procedia PDF Downloads 186

Authors: Dehni Abdellatif, Lounis Mourad

Abstract:

The new approach of applied spatial geostatistics in materials sciences, agriculture accuracy, agricultural statistics, permitted an apprehension of managing and monitoring the water and groundwater qualities in a relationship with salt-affected soil. The anterior experiences concerning data acquisition, spatial-preparation studies on optical and multispectral data has facilitated the integration of correction models of electrical conductivity related with soils temperature (horizons of soils). For tomography apprehension, this physical parameter has been extracted from calibration of the thermal band (LANDSAT ETM+6) with a radiometric correction. Our study area is Oran region (Northern West of Algeria). Different spectral indices are determined such as salinity and sodicity index, the Combined Spectral Reflectance Index (CSRI), Normalized Difference Vegetation Index (NDVI), emissivity, Albedo, and Sodium Adsorption Ratio (SAR). The approach of geostatistical modeling of electrical conductivity (salinity), appears to be a useful decision support system for estimating corrected electrical resistivity related to the temperature of surface soils, according to the conversion models by substitution, the reference temperature at 25°C (where hydrochemical data are collected with this constraint). The Brightness temperatures extracted from satellite reflectance (LANDSAT ETM+) are used in consistency models to estimate electrical resistivity. The confusions that arise from the effects of salt stress and water stress removed followed by seasonal application of the geostatistical analysis in Geographic Information System (GIS) techniques investigation and monitoring the variation of the electrical conductivity in the alluvial aquifer of Es-Sénia for the salt-affected soil.

Keywords: geostatistical modelling, landsat, brightness temperature, conductivity

Procedia PDF Downloads 441

Authors: T. Yılmaz, Ş. Tavman

Abstract:

In this study, optimization of ultrasound assisted extraction (UAE) of hemicellulose based polysaccharides from plant waste material has been studied. Selected material is hazelnut skin. Extraction variables for the operation are extraction time, amplitude and application temperature. Optimum conditions have been evaluated depending on responses such as amount of wet crude polysaccharide, total carbohydrate content and dried sample. Pretreated hazelnut skin powders were used for the experiments. 10 grams of samples were suspended in 100 ml water in a jacketed vessel with additional magnetic stirring. Mixture was sonicated by immersing ultrasonic probe processor. After the extraction procedures, ethanol soluble and insoluble sides were separated for further examinations. The obtained experimental data were analyzed by analysis of variance (ANOVA). Second order polynomial models were developed using multiple regression analysis. The individual and interactive effects of applied variables were evaluated by Box Behnken Design. The models developed from the experimental design were predictive and good fit with the experimental data with high correlation coefficient value (R2 more than 0.95). Extracted polysaccharides from hazelnut skin are assumed to be pectic polysaccharides according to the literature survey of Fourier Transform Spectrometry (FTIR) analysis results. No more change can be observed between spectrums of different sonication times. Application of UAE at optimized condition has an important effect on extraction of hemicellulose from plant material by satisfying partial hydrolysis to break the bounds with other components in plant cell wall material. This effect can be summarized by varied intensity of microjets and microstreaming at varied sonication conditions.

Keywords: hazelnut skin, optimization, polysaccharide, ultrasound assisted extraction

Procedia PDF Downloads 331

Authors: Rahul Jain, Pradhir Parmar, Dhruvesh Patel

Abstract:

Planning and drawing are the important aspects of civil engineering. For testing theories about spatial location and interaction between land uses and related activities the computer based solution of urban models are used. The planner’s primary interest is in creation of 3D models of building and to obtain the terrain surface so that he can do urban morphological mappings, virtual reality, disaster management, fly through generation, visualization etc. 3D city models have a variety of applications in urban studies. Gujarat International Finance Tec-City (GIFT) is an ongoing construction site between Ahmedabad and Gandhinagar, Gujarat, India. It will be built on 3590000 m2 having a geographical coordinates of North Latitude 23°9’5’’N to 23°10’55’’ and East Longitude 72°42’2’’E to 72°42’16’’E. Therefore to develop 3D city models of GIFT city, the base map of the city is collected from GIFT office. Differential Geographical Positioning System (DGPS) is used to collect the Ground Control Points (GCP) from the field. The GCP points are used for the registration of base map in QGIS. The registered map is projected in WGS 84/UTM zone 43N grid and digitized with the help of various shapefile tools in QGIS. The approximate height of the buildings that are going to build is collected from the GIFT office and placed on the attribute table of each layer created using shapefile tools. The Shuttle Radar Topography Mission (SRTM) 1 Arc-Second Global (30 m X 30 m) grid data is used to generate the terrain of GIFT city. The Google Satellite Map is used to place on the background to get the exact location of the GIFT city. Various plugins and tools in QGIS are used to convert the raster layer of the base map of GIFT city into 3D model. The fly through tool is used for capturing and viewing the entire area in 3D of the city. This paper discusses all techniques and their usefulness in 3D city model creation from the GCP, base map, SRTM and QGIS.

Keywords: 3D model, DGPS, GIFT City, QGIS, SRTM

Procedia PDF Downloads 247

Authors: Mohammad Hosein Panahi, Naser Yazdani

Abstract:

we present a technical trading strategy that leverages the FinBERT language model and financial news analysis with a focus on news related to a subset of Nasdaq 100 stocks. Our approach surpasses the baseline Range Break-out strategy in the Bitcoin market, yielding a remarkable 24.8% increase in the win ratio for all Friday trades and an impressive 48.9% surge in short trades specifically on Fridays. Moreover, we conduct rigorous hypothesis testing to establish the statistical significance of these improvements. Our findings underscore considerable potential of our NLP-driven approach in enhancing trading strategies and achieving greater profitability within financial markets.

Keywords: quantitative finance, technical analysis, bitcoin market, NLP, language models, FinBERT, technical trading

Procedia PDF Downloads 75

Authors: M. Khazam, M. Altawil, A. Eljabri

Abstract:

Fluid properties in states near a vapor-liquid critical region are the most difficult to measure and to predict with EoS models. The principal model difficulty is that near-critical property variations do not follow the same mathematics as at conditions far away from the critical region. Libyan NC98 field in Sirte basin is a typical example of near critical fluid characterized by high initial condensate gas ratio (CGR) greater than 160 bbl/MMscf and maximum liquid drop-out of 25%. The objective of this paper is to model NC98 phase behavior with the proper selection of EoS parameters and also to model reservoir depletion versus gas cycling option using measured PVT data and EoS Models. The outcomes of our study revealed that, for accurate gas and condensate recovery forecast during depletion, the most important PVT data to match are the gas phase Z-factor and C7+ fraction as functions of pressure. Reasonable match, within -3% error, was achieved for ultimate condensate recovery at abandonment pressure of 1500 psia. The smooth transition from gas-condensate to volatile oil was fairly simulated by the tuned PR-EoS. The predicted GOC was approximately at 14,380 ftss. The optimum gas cycling scheme, in order to maximize condensate recovery, should not be performed at pressures less than 5700 psia. The contribution of condensate vaporization for such field is marginal, within 8% to 14%, compared to gas-gas miscible displacement. Therefore, it is always recommended, if gas recycle scheme to be considered for this field, to start it at the early stage of field development.

Keywords: EoS models, gas-condensate, gas cycling, near critical fluid

Procedia PDF Downloads 318

Authors: Dalal N. Hammod, Ekhlas K. Gbashi

Abstract:

Today, cryptography is used in many applications to achieve high security in data transmission and in real-time communications. AES has long gained global acceptance and is used for securing sensitive data in various industries but has suffered from slow processing and take a large time to transfer data. This paper suggests a method to enhance Advance Encryption Standard (AES) Algorithm based on time and permutation. The suggested method (MAES) is based on modifying the SubByte and ShiftRrows in the encryption part and modification the InvSubByte and InvShiftRows in the decryption part. After the implementation of the proposal and testing the results, the Modified AES achieved good results in accomplishing the communication with high performance criteria in terms of randomness, encryption time, storage space, and avalanche effects. The proposed method has good randomness to ciphertext because this method passed NIST statistical tests against attacks; also, (MAES) reduced the encryption time by (10 %) than the time of the original AES; therefore, the modified AES is faster than the original AES. Also, the proposed method showed good results in memory utilization where the value is (54.36) for the MAES, but the value for the original AES is (66.23). Also, the avalanche effects used for calculating diffusion property are (52.08%) for the modified AES and (51.82%) percentage for the original AES.

Keywords: modified AES, randomness test, encryption time, avalanche effects

Procedia PDF Downloads 248

Authors: Muneeb Ullah, Daishihan, Xiadong Young

Abstract:

Deep learning plays a crucial role in identifying COVID-19 and preventing its spread. To improve the accuracy of COVID-19 diagnoses, it is important to have access to a sufficient number of training images of CXRs (chest X-rays) depicting the disease. However, there is currently a shortage of such images. To address this issue, this paper introduces COVID-19 GAN, a model that uses generative adversarial networks (GANs) to generate realistic CXR images of COVID-19, which can be used to train identification models. Initially, a generator model is created that uses digressive channels to generate images of CXR scans for COVID-19. To differentiate between real and fake disease images, an efficient discriminator is developed by combining the dense connectivity strategy and instance normalization. This approach makes use of their feature extraction capabilities on CXR hazy areas. Lastly, the deep regret gradient penalty technique is utilized to ensure stable training of the model. With the use of 4,062 grape leaf disease images, the Leaf GAN model successfully produces 8,124 COVID-19 CXR images. The COVID-19 GAN model produces COVID-19 CXR images that outperform DCGAN and WGAN in terms of the Fréchet inception distance. Experimental findings suggest that the COVID-19 GAN-generated CXR images possess noticeable haziness, offering a promising approach to address the limited training data available for COVID-19 model training. When the dataset was expanded, CNN-based classification models outperformed other models, yielding higher accuracy rates than those of the initial dataset and other augmentation techniques. Among these models, ImagNet exhibited the best recognition accuracy of 99.70% on the testing set. These findings suggest that the proposed augmentation method is a solution to address overfitting issues in disease identification and can enhance identification accuracy effectively.

Keywords: classification, deep learning, medical images, CXR, GAN.

Procedia PDF Downloads 96

Authors: Alexis Aldo Mendoza Villarroel, Ademir Clemente Villena Zevallos, Cristian Jose Lopez Del Alamo

Abstract:

With the advancement of technology it is now possible to scan entire objects and obtain their digital representation by using point clouds or polygon meshes. However, some objects may be broken or have missing parts; thus, several methods focused on this problem have been proposed based on Geometric Deep Learning, such as GCNN, ACNN, PointNet, among others. In this article an approach from a different paradigm is proposed, using metric data structures to index global descriptors in the spectral domain and allow the recovery of a set of similar models in polynomial time; to later use the Iterative Close Point algorithm and recover the parts of the incomplete model using the geometry and topology of the model with less Hausdorff distance.

Keywords: 3D reconstruction method, point cloud completion, shape completion, similarity search

Procedia PDF Downloads 122

Authors: Gabriel Legorreta Paulin, Marcus I. Bursik, Lilia Arana Salinas, Fernando Aceves Quesada

Abstract:

In volcanic environments, landslides and debris flows occur continually along stream systems of large stratovolcanoes. This is the case on Pico de Orizaba volcano, the highest mountain in Mexico. The volcano has a great potential to impact and damage human settlements and economic activities by landslides. People living along the lower valleys of Pico de Orizaba volcano are in continuous hazard by the coalescence of upstream landslide sediments that increased the destructive power of debris flows. These debris flows not only produce floods, but also cause the loss of lives and property. Although the importance of assessing such process, there is few landslide inventory maps and landslide susceptibility assessment. As a result in México, no landslide susceptibility models assessment has been conducted to evaluate advantage and disadvantage of models. In this study, a comprehensive study of landslide susceptibility models assessment using GIS technology is carried out on the SE flank of Pico de Orizaba volcano. A detailed multi-temporal landslide inventory map in the watershed is used as framework for the quantitative comparison of two landslide susceptibility maps. The maps are created based on 1) the Stability Index MAPping (SINMAP) model by using default geotechnical parameters and 2) by using findings of volcanic soils geotechnical proprieties obtained in the field. SINMAP combines the factor of safety derived from the infinite slope stability model with the theory of a hydrologic model to produce the susceptibility map. It has been claimed that SINMAP analysis is reasonably successful in defining areas that intuitively appear to be susceptible to landsliding in regions with sparse information. The validations of the resulting susceptibility maps are performed by comparing them with the inventory map under LOGISNET system which provides tools to compare by using a histogram and a contingency table. Results of the experiment allow for establishing how the individual models predict the landslide location, advantages, and limitations. The results also show that although the model tends to improve with the use of calibrated field data, the landslide susceptibility map does not perfectly represent existing landslides.

Keywords: GIS, landslide, modeling, LOGISNET, SINMAP

Procedia PDF Downloads 313

Authors: Georgia Pozoukidou

Abstract:

TELUM software is a land use model designed specifically to help metropolitan planning organizations (MPOs) prepare their transportation improvement programs and fulfill their numerous planning responsibilities. In this context obtaining, preparing, and validating socioeconomic forecasts are becoming fundamental tasks for an MPO in order to ensure that consistent population and employment data are provided to travel demand models. Chittenden County Metropolitan Planning Organization of Vermont State was used as a case study to test the applicability of TELUM land use model. The technical insights and lessons learned from the land use model application have transferable value for all MPOs faced with land use forecasting development and transportation modelling.

Keywords: calibration data requirements, land use models, land use planning, metropolitan planning organizations

Procedia PDF Downloads 292

Authors: Wei Zhao, Yuxuan Yao, Hao Chen

Abstract:

In order to find out the mechanical properties and failure behavior of lithium-ion batteries, drop hammer impact experiments and finite element simulations are carried out on batteries with different packed angles. Firstly, a drop hammer impact experiment system, which is based on the DHR-1808 drop hammer and oscilloscope, is established, and then a drop test of individual batteries and packed angles of 180 ° and 120 ° are carried out. The image of battery deformation, force-time curve and voltage-time curve are recorded. Secondly, finite element models of individual batteries and two packed angles are established, and the results of the test and simulation are compared. Finally, the mechanical characteristics and failure behavior of lithium-ion battery modules with the packed arrangement of 6 * 6 and packing angles of 180 °, 120 °, 90 ° and 60 ° are analyzed under the same velocity with different battery packing angles, and the same impact energy with different impact velocity and different packing angles. The result shows that the individual battery is destroyed completely in the drop hammer impact test with an initial impact velocity of 3m/s and drop height of 459mm, and the voltage drops to close to 0V when the test ends. The voltage drops to 12V when packed angle of 180°, and 3.6V when packed angle of 120°. It is found that the trend of the force-time curve between simulation and experiment is generally consistent. The difference in maximum peak value is 3.9kN for a packing angle of 180° and 1.3kN for a packing angle of 120°. Under the same impact velocity and impact energy, the strain rate of the battery module with a packing angle of 180° is the lowest, and the maximum stress can reach 26.7MPa with no battery short-circuited. The research under our experiment and simulation shows that the lithium-ion battery module with a packing angle of 180 ° is the least likely to be damaged, which can sustain the maximum stress under the same impact load.

Keywords: battery module, finite element simulation, power battery, packing angle

Procedia PDF Downloads 70

Authors: André Python

Abstract:

To this day, terrorism persists as a worldwide threat, exemplified by the recent deadly attacks in January 2015 in Paris and the ongoing massacres perpetrated by ISIS in Iraq and Syria. In response to this threat, states deploy various counterterrorism measures, the cost of which could be reduced through effective preventive measures. In order to increase the efficiency of preventive measures, policy-makers may benefit from accurate predictive models that are able to capture the complex spatial dynamics of terrorism occurring at a local scale. Despite empirical research carried out at country-level that has confirmed theories explaining the diffusion processes of terrorism across space and time, scholars have failed to assess diffusion’s theories on a local scale. Moreover, since scholars have not made the most of recent statistical modelling approaches, they have been unable to build up predictive models accurate in both space and time. In an effort to address these shortcomings, this research suggests a novel approach to systematically assess the theories of terrorism’s diffusion on a local scale and provide a predictive model of the local spatial dynamics of terrorism worldwide. With a focus on the lethal terrorist events that occurred after 9/11, this paper addresses the following question: why and how does lethal terrorism diffuse in space and time? Based on geolocalised data on worldwide terrorist attacks and covariates gathered from 2002 to 2013, a binomial spatio-temporal point process is used to model the probability of terrorist attacks on a sphere (the world), the surface of which is discretised in the form of Delaunay triangles and refined in areas of specific interest. Within a Bayesian framework, the model is fitted through an integrated nested Laplace approximation - a recent fitting approach that computes fast and accurate estimates of posterior marginals. Hence, for each location in the world, the model provides a probability of encountering a lethal terrorist attack and measures of volatility, which inform on the model’s predictability. Diffusion processes are visualised through interactive maps that highlight space-time variations in the probability and volatility of encountering a lethal attack from 2002 to 2013. Based on the previous twelve years of observation, the location and lethality of terrorist events in 2014 are statistically accurately predicted. Throughout the global scope of this research, local diffusion processes such as escalation and relocation are systematically examined: the former process describes an expansion from high concentration areas of lethal terrorist events (hotspots) to neighbouring areas, while the latter is characterised by changes in the location of hotspots. By controlling for the effect of geographical, economical and demographic variables, the results of the model suggest that the diffusion processes of lethal terrorism are jointly driven by contagious and non-contagious factors that operate on a local scale – as predicted by theories of diffusion. Moreover, by providing a quantitative measure of predictability, the model prevents policy-makers from making decisions based on highly uncertain predictions. Ultimately, this research may provide important complementary tools to enhance the efficiency of policies that aim to prevent and combat terrorism.

Keywords: diffusion process, terrorism, spatial dynamics, spatio-temporal modeling

Procedia PDF Downloads 351

Authors: Yufen Qin

Abstract:

Text sentiment transfer is an important branch of text style transfer. The goal is to generate text with another sentiment attribute based on a text with a specific sentiment attribute while maintaining the content and semantic information unrelated to sentiment unchanged in the process. There are currently two main challenges in this field: no parallel corpus and text attribute entanglement. In response to the above problems, this paper proposed a novel solution: Mask-Prompt-Rerank. Use the method of masking the sentiment words and then using prompt regeneration to transfer the sentence sentiment. Experiments on two sentiment benchmark datasets and one formality transfer benchmark dataset show that this approach makes the performance of small pre-trained language models comparable to that of the most advanced large models, while consuming two orders of magnitude less computing and memory.

Keywords: language model, natural language processing, prompt, text sentiment transfer

Procedia PDF Downloads 81

Authors: Pontus Backstrom

Abstract:

In the educational literature on peer effects, attention has been brought to the fact that the mechanisms creating peer effects are still to a large extent hidden in obscurity. The hypothesis in this study is that the Frame Factor Theory can be used to explain these mechanisms. At heart of the theory is the concept of “time needed” for students to learn a certain curricula unit. The relations between class-aggregated time needed and the actual time available, steers and hinders the actions possible for the teacher. Further, the theory predicts that the timing and pacing of the teachers’ instruction is governed by a “criterion steering group” (CSG), namely the pupils in the 10th-25th percentile of the aptitude distribution in class. The class composition hereby set the possibilities and limitations for instruction, creating peer effects on individual outcomes. To test if the theory can be applied to the issue of peer effects, the study employs multilevel structural equation modelling (M-SEM) on Swedish TIMSS 2015-data (Trends in International Mathematics and Science Study; students N=4090, teachers N=200). Using confirmatory factor analysis (CFA) in the SEM-framework in MPLUS, latent variables are specified according to the theory, such as “limitations of instruction” from TIMSS survey items. The results indicate a good model fit to data of the measurement model. Research is still in progress, but preliminary results from initial M-SEM-models verify a strong relation between the mean level of the CSG and the latent variable of limitations on instruction, a variable which in turn have a great impact on individual students’ test results. Further analysis is required, but so far the analysis indicates a confirmation of the predictions derived from the frame factor theory and reveals that one of the important mechanisms creating peer effects in student outcomes is the effect the class composition has upon the teachers’ instruction in class.

Keywords: compositional effects, frame factor theory, peer effects, structural equation modelling

Procedia PDF Downloads 134

Authors: Farzad Hosseini Hossein Abadi, Cristina Prieto Sierra, Cesar Álvarez Díaz

Abstract:

Predicting streamflow accurately in flashy catchments prone to floods is a major research and operational challenge in hydrological modeling. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have shown to be promising in achieving accurate hydrological predictions at daily and hourly time scales. In this work, a multi-timescale LSTM (MTS-LSTM) network was applied to the context of regional hydrological predictions at an hourly time scale in flashy catchments. The case study includes 40 catchments allocated in the Basque Country, north of Spain. We explore the impact of hyperparameters on the performance of streamflow predictions given by regional deep learning models through systematic hyperparameter tuning - where optimal regional values for different catchments are identified. The results show that predictions are highly accurate, with Nash-Sutcliffe (NSE) and Kling-Gupta (KGE) metrics values as high as 0.98 and 0.97, respectively. A principal component analysis reveals that a hyperparameter related to the length of the input sequence contributes most significantly to the prediction performance. The findings suggest that input sequence lengths have a crucial impact on the model prediction performance. Moreover, employing catchment-scale analysis reveals distinct sequence lengths for individual basins, highlighting the necessity of customizing this hyperparameter based on each catchment’s characteristics. This aligns with well known “uniqueness of the place” paradigm. In prior research, tuning the length of the input sequence of LSTMs has received limited focus in the field of streamflow prediction. Initially it was set to 365 days to capture a full annual water cycle. Later, performing limited systematic hyper-tuning using grid search, revealed a modification to 270 days. However, despite the significance of this hyperparameter in hydrological predictions, usually studies have overlooked its tuning and fixed it to 365 days. This study, employing a simultaneous systematic hyperparameter tuning approach, emphasizes the critical role of input sequence length as an influential hyperparameter in configuring LSTMs for regional streamflow prediction. Proper tuning of this hyperparameter is essential for achieving accurate hourly predictions using deep learning models.

Keywords: LSTMs, streamflow, hyperparameters, hydrology

Procedia PDF Downloads 70

Authors: Shoujia Fang, Guoqing Ding, Xin Chen

Abstract:

The quality of press-fit assembly is closely related to reliability and safety of product. The paper proposed a keypoint detection method based on convolutional neural network to improve the accuracy of keypoint detection in press-fit curve. It would provide an auxiliary basis for judging quality of press-fit assembly. The press-fit curve is a curve of press-fit force and displacement. Both force data and distance data are time-series data. Therefore, one-dimensional convolutional neural network is used to process the press-fit curve. After the obtained press-fit data is filtered, the multi-layer one-dimensional convolutional neural network is used to perform the automatic learning of press-fit curve features, and then sent to the multi-layer perceptron to finally output keypoint of the curve. We used the data of press-fit assembly equipment in the actual production process to train CNN model, and we used different data from the same equipment to evaluate the performance of detection. Compared with the existing research result, the performance of detection was significantly improved. This method can provide a reliable basis for the judgment of press-fit quality.

Keywords: keypoint detection, curve feature, convolutional neural network, press-fit assembly

Procedia PDF Downloads 230

Authors: C. Okonkwo Ugochukwu, E. Sinebe Jude, N. Odoh Blessing, E. Okafor Christian

Abstract:

In this paper, a modification on repair workshop queuing system using multi priority scheme was carried out. Chi square goodness of fit test was used to determine the random distribution of the inter arrival time and service time of crankshafts that come for maintenance in the workshop. The chi square values obtained for all the prioritized classes show that the distribution conforms to Poisson distribution. The mean waiting time in queue results of non-preemptive priority for 1st, 2nd and 3rd classes show 0.066, 0.09, and 0.224 day respectively, while preemptive priority show 0.007, 0.036 and 0.258 day. However, when non priority is used, which obviously has no class distinction it amounts to 0.17 days. From the results, one can observe that the preemptive priority system provides a very dramatic improvement over the non preemptive priority as it concerns arrivals that are of higher priority. However, the improvement has a detrimental effect on the low priority class. The trend of the results is similar to the mean waiting time in the system as a result of addition of the actual service time. Even though the mean waiting time for the queue and that of the system for no priority takes the least time when compared with the least priority, urgent and semi-urgent jobs will terribly suffer which will most likely result in reneging or balking of many urgent jobs. Hence, the adoption of priority scheme in this type of scenario will result in huge profit to the Company and more customer satisfaction.

Keywords: queue, priority class, preemptive, non-preemptive, mean waiting time

Procedia PDF Downloads 396

Authors: Donggun Lee, Q-Han Park

Abstract:

Due to its coarse grid, the Pseudo-Spectral Time Domain (PSTD) method has advantages against the Finite Difference Time Domain (FDTD) method in terms of memory requirement and operation time. However, since the efficiency of parallelization is much lower than that of FDTD, PSTD is not a useful method for a large-scale electromagnetic simulation in a parallel platform. In this paper, we propose the parallelization technique of the hybrid PSTD-FDTD (HPF) method which simultaneously possesses the efficient parallelizability of FDTD and the quick speed and low memory requirement of PSTD. Parallelization cost of the HPF method is exactly the same as the parallel FDTD, but still, it occupies much less memory space and has faster operation speed than the parallel FDTD. Experiments in distributed memory systems have shown that the parallel HPF method saves up to 96% of the operation time and reduces 84% of the memory requirement. Also, by combining the OpenMP library to the MPI library, we further reduced the operation time of the parallel HPF method by 50%.

Keywords: FDTD, hybrid, MPI, OpenMP, PSTD, parallelization

Procedia PDF Downloads 148

Authors: Priscilla Eng Lian Murphy

Abstract:

This study examines the nature of student conceptions of mathematics in higher education using quantitative research methods. This study validates the Short Form of Conception of Mathematics survey as well as reveals the epistemological nature of student conceptions of mathematics. Using a random sample of mathematics students in Australia and New Zealand (N=274), this paper highlighted three key findings, of relevance to lecturers in higher education. Firstly, descriptive data shows that mathematics students in Australia and New Zealand reported that mathematics is about numbers and components, models and life. Secondly, models conceptions of mathematics predicted strong examination performances using regression analyses; and thirdly, there is a positive correlation between high mathematics examination scores and cohesive conceptions of mathematics.

Keywords: higher education, learning mathematics, mathematics performances, student conceptions of mathematics

Procedia PDF Downloads 264

Authors: Clement Leroy, Guillaume Boitel

Abstract:

This paper presents a comparative benchmarking review of a steady and transient three-dimensional (3D) flow computations in centrifugal pump using commercial (AnsysCFX) and open source (OpenFOAM) computational fluid dynamics (CFD) software. In centrifugal rotor-dynamic pump, the fluid enters in the impeller along to the rotating axis to be accelerated in order to increase the pressure, flowing radially outward into another stage, vaned diffuser or volute casing, from where it finally exits into a downstream pipe. Simulations are carried out at the best efficiency point (BEP) and part load, for single-phase flow with several turbulence models. The results are compared with overall performance report from experimental data. The use of CFD technology in industry is still limited by the high computational costs, and even more by the high cost of commercial CFD software and high-performance computing (HPC) licenses. The main objectives of the present study are to define OpenFOAM methodology for high-quality 3D steady and transient turbomachinery CFD simulation to conduct a thorough time-accurate performance analysis. On the other hand a detailed comparisons between computational methods, features on latest Ansys release 18 and OpenFOAM is investigated to assess the accuracy and industrial applications of those solvers. Finally an automated connected workflow (IoT) for turbine blade applications is presented.

Keywords: benchmarking, CFX, internet of things, openFOAM, time-accurate, turbomachinery

Procedia PDF Downloads 205

Authors: Desta Gebretekle Shiferaw, Balakrishna Kalluraya

Abstract:

Oxadiazoles and their derivatives with thioether functionalities represent a new and exciting class of physiologically active heterocyclic compounds. Several molecules with these moieties play a vital role in pharmaceuticals because of their diverse biological activities. This paper describes a new class of 1,3,4- oxadiazole-2-thioethers with acetophenone, coumarin, and N-phenyl acetamide residues (S-alkylation), with the hope that the addition of various biologically active molecules will have a synergistic effect on anticancer activity. The structure of the synthesized title compounds was determined by the combined methods of IR, proton-NMR, carbon-13-NMR, and mass spectrometry. Further, all the newly prepared molecules were assessed against their antioxidant activity. Furthermore, four compounds were assessed for their molecular docking interactions and cytotoxicity activity. The synthesized derivatives have shown moderate antioxidant activity compared to the standard BHA. The IC50 of the tilted molecules (11b, 11c, 13b, and 14b) observed for in vitro anti-cancer activities were 11.20, 15.73, 59.61, and 27.66 g/ml at 72-hour treatment time against the A549 cell lines, respectively. The tested compounds' biological evaluation showed that 11b is the most effective molecule in the series.

Keywords: antioxidant activity, cytotoxicity activity, molecular docking, 1, 3, 4-Oxadiazole-2 thioether derivatives

Procedia PDF Downloads 90

Authors: Ahmad R. Zamani, Luigi Sanguigno, Angelo R. Maligno

Abstract:

A 3D woven composite, designed for automotive applications, is studied using Abaqus Finite Element (FE) software suite. Python scripts were developed to build FE models of the woven composite in Complete Abaqus Environment (CAE). They can read TexGen or WiseTex files and automatically generate consistent meshes of the fabric and the matrix. A user menu is provided to help define parameters for the FE models, such as type and size of the elements in fabric and matrix as well as the type of matrix-fabric interaction. Node-to-node constraints were imposed to guarantee periodicity of the deformed shapes at the boundaries of the representative volume element of the composite. Tensile loads in three axes and biaxial loads in x-y directions have been applied at different Fibre Volume Fractions (FVFs). A simple damage model was implemented via an Abaqus user material (UMAT) subroutine. Existing tools for homogenization were also used, including voxel mesh generation from TexGen as well as Abaqus Micromechanics plugin. Linear relations between homogenised elastic properties and the FVFs are given. The FE models of composite exhibited balanced behaviour with respect to warp and weft directions in terms of both stiffness and strength.

Keywords: 3D woven composite (3DWC), meso-scale finite element model, homogenisation of elastic material properties, Abaqus Python scripting

Procedia PDF Downloads 145

Authors: Karim Hamidi Machekposhti, Hossein Sedghi

Abstract:

The probability distributions are the best method for forecasting of extreme hydrologic phenomena such as rainfall and flood flows. In this research, in order to determine suitable probability distribution for estimating of annual extreme rainfall and flood flows (discharge) series with different return periods, precipitation with 40 and discharge with 58 years time period had been collected from Karkheh River at Iran. After homogeneity and adequacy tests, data have been analyzed by Stormwater Management and Design Aid (SMADA) software and residual sum of squares (R.S.S). The best probability distribution was Log Pearson Type III with R.S.S value (145.91) and value (13.67) for peak discharge and Log Pearson Type III with R.S.S values (141.08) and (8.95) for maximum discharge in Jelogir Majin and Pole Zal stations, respectively. The best distribution for maximum precipitation in Jelogir Majin and Pole Zal stations was Log Pearson Type III distribution with R.S.S values (1.74&1.90) and then Pearson Type III distribution with R.S.S values (1.53&1.69). Overall, the Log Pearson Type III distributions are acceptable distribution types for representing statistics of extreme hydrologic phenomena in Karkheh River at Iran with the Pearson Type III distribution as a potential alternative.

Keywords: Karkheh River, Log Pearson Type III, probability distribution, residual sum of squares

Procedia PDF Downloads 197

Authors: Hajer Chaker Ben Hadj Kacem, Thouraya Slama, Néjiba El Yetim Zribi

Abstract:

This paper analyzes the effects of gender, affiliation, prior work experience, social work, and vicarious learning through family role models on entrepreneurial skills development by students when they have learned through the entrepreneurship method in Tunisia. Authors suggest that these variables enhance the development of students’ entrepreneurial skills when combined with teaching through entrepreneurship. The article assesses the impact of these combinations by comparing their effects on the development of thirteen students’ entrepreneurial competencies, namely entrepreneurial mindset, core self-evaluation, entrepreneurial attitude, entrepreneurial knowledge, creativity, financial literacy, managing ambiguity, marshaling of resources, planning, teaching methods, entrepreneurial teachers, innovative employee, and Entrepreneurial intention. Authors use a two-sample independent t-test to make the comparison, and the results indicate that, when combined with teaching through the entrepreneurship method, students with prior work experience developed better six entrepreneurial skills; students with social work developed better three entrepreneurial skills, men developed better four entrepreneurial skills than women. However, all students developed their entrepreneurial skills through this practical method regardless of their affiliation and their vicarious learning through family role models.

Keywords: affiliation, entrepreneurial skills, gender, role models, social work, teaching through entrepreneurship, vicarious learning, work experience

Procedia PDF Downloads 110

Authors: Mahesh K. Chudasama, Harit K. Raval

Abstract:

3-roller conical bending process is widely used in the industries for manufacturing of conical sections and shells. It involves static as well dynamic bending stages. Analytical models for prediction of bending force during static as well as dynamic bending stage are available in the literature. In this paper, bending forces required for static bending stage and dynamic bending stages have been compared using the analytical models. It is concluded that force required for dynamic bending is very less as compared to the bending force required during the static bending stage.

Keywords: analytical modeling, cone frustum, dynamic bending, static bending

Procedia PDF Downloads 307

Authors: Sharon Li, Zhonghang Xia

Abstract:

Post-database search is an essential phase in peptide identification using tandem mass spectrometry (MS/MS) to refine peptide-spectrum matches (PSMs) produced by database search engines. These engines frequently face difficulty differentiating between correct and incorrect peptide assignments. Despite advances in statistical and machine learning methods aimed at improving the accuracy of peptide identification, challenges remain in selecting critical features for these models. In this study, two machine learning models—a random forest tree and a support vector machine—were applied to three datasets to enhance PSMs. SHAP values were utilized to determine the significance of each feature within the models. The experimental results indicate that the random forest model consistently outperformed the SVM across all datasets. Further analysis of SHAP values revealed that the importance of features varies depending on the dataset, indicating that a feature's role in model predictions can differ significantly. This variability in feature selection can lead to substantial differences in model performance, with false discovery rate (FDR) differences exceeding 50% between different feature combinations. Through SHAP value analysis, the most effective feature combinations were identified, significantly enhancing model performance.

Keywords: peptide identification, SHAP value, feature selection, random forest tree, support vector machine

Procedia PDF Downloads 23