Search results for: back propagation neural network model

Authors: Chih-Hua Chang

Abstract:

This study uses a three-dimensional (3D) fully nonlinear model to simulate the wave generation problem caused by the movement of the seabed. The numerical model is first simplified into two dimensions and then compared with the existing two-dimensional (2D) experimental data and the 2D numerical results of other shallow-water wave models. Results show that this model is different from the earlier shallow-water wave models, with the phase being closer to the experimental results of wave propagation. The results of this study are also compared with those of the 3D experimental results of other researchers. Satisfactory results can be obtained in both the waveform and the flow field. This study assesses the application of the model to simulate the wave caused by the circular (radius r0) terrain rising or falling (moving distance bm). The influence of wave-making parameters r0 and bm are discussed. This study determines that small-range (e.g., r0 = 2, normalized by the static water depth), rising, or sinking terrain will produce significant wave groups in the far field. For large-scale moving terrain (e.g., r0 = 10), uplift and deformation will potentially generate the leading solitary-like waves in the far field.

Keywords: seismic wave, wave generation, far-field waves, seabed deformation

Procedia PDF Downloads 86

Authors: Rachel Y. Zhang, Christopher K. Anderson

Abstract:

A critical aspect of revenue management is a firm’s ability to predict demand as a function of price. Historically hotels have used simple time series models (regression and/or pick-up based models) owing to the complexities of trying to build casual models of demands. Machine learning approaches are slowly attracting attention owing to their flexibility in modeling relationships. This study provides an overview of approaches to forecasting hospitality demand – focusing on the opportunities created by machine learning approaches, including K-Nearest-Neighbors, Support vector machine, Regression Tree, and Artificial Neural Network algorithms. The out-of-sample performances of above approaches to forecasting hotel demand are illustrated by using a proprietary sample of the market level (24 properties) transactional data for Las Vegas NV. Causal predictive models can be built and evaluated owing to the availability of market level (versus firm level) data. This research also compares and contrast model accuracy of firm-level models (i.e. predictive models for hotel A only using hotel A’s data) to models using market level data (prices, review scores, location, chain scale, etc… for all hotels within the market). The prospected models will be valuable for hotel revenue prediction given the basic characters of a hotel property or can be applied in performance evaluation for an existed hotel. The findings will unveil the features that play key roles in a hotel’s revenue performance, which would have considerable potential usefulness in both revenue prediction and evaluation.

Keywords: hotel revenue, k-nearest-neighbors, machine learning, neural network, prediction model, regression tree, support vector machine

Procedia PDF Downloads 133

Authors: Somojit Saha, Rohit K. Chatterjee, Sarit K. Das, Avijit Kar

Abstract:

A new force field is designed for propagation of the parametric contour into deep narrow cortical fold in the application of knowledge based reconstruction of cerebral cortex from MR image of brain. Designing of this force field is highly inspired by the Generalized Gradient Vector Flow (GGVF) model and markedly differs in manipulation of image information in order to determine the direction of propagation of the contour. While GGVF uses edge map as its main driving force, the newly designed force field uses the map of distance between zero valued pixels and their nearest non-zero valued pixel as its main driving force. Hence, it is called Zero-Non-Zero Distance (ZNZD) force field. The objective of this force field is forceful propagation of the contour beyond spurious convergence due to partial volume effect (PVE) in to narrow sulcal fold. Being function of the corresponding non-zero pixel value, the force field has got an inherent property to determine spuriousness of the edge automatically. It is effectively applied along with some morphological processing in the application of cortical reconstruction to breach the hindrance of PVE in narrow sulci where conventional GGVF fails.

Keywords: deformable model, external force field, partial volume effect, cortical reconstruction, MR image of brain

Procedia PDF Downloads 397

Authors: Ioannis Binas, Marios Moschakis

Abstract:

Electrical faults in transmission and distribution networks can have great impact on the electrical equipment used. Fault effects depend on the characteristics of the fault as well as the network itself. It is important to anticipate the network’s behavior during faults when planning a new equipment installation, as well as troubleshooting. Moreover, working backwards, we could be able to estimate the characteristics of the fault when checking the perceived effects. Different transformer winding connections dominantly used in the Greek power transfer and distribution networks and the effects of 1-phase to neutral, phase-to-phase, 2-phases to neutral and 3-phase faults on different locations of the network were simulated in order to present voltage sag characteristics. The study was performed on a generic network with three steps down transformers on two voltage level buses (one 150 kV/20 kV transformer and two 20 kV/0.4 kV). We found that during faults, there are significant changes both on voltage magnitudes and on phase angles. The simulations and short-circuit analysis were performed using the PSCAD simulation package. This paper presents voltage characteristics calculated for the simulated network, with different approaches on the transformer winding connections during symmetrical and asymmetrical faults on various locations.

Keywords: Phase angle shift, power quality, transformer winding connections, voltage sag propagation

Procedia PDF Downloads 139

Authors: Anshul Gupta, T. Shankar

Abstract:

In this paper, we had analyzed the call drop to provide a good quality of service to user. By optimizing it we can increase the coverage area and also the reduction of interference and congestion created in a network. Basically handover is the transfer of call from one cell site to another site during a call. Here we have analyzed the whole network by two method-statistic model and analytic model. In statistic model we have collected all the data of a network during busy hour and normal 24 hours and in analytic model we have the equation through which we have to find the call drop probability. By avoiding unnecessary handovers we can increase the number of calls per hour. The most important parameter is co-efficient of variation on which the whole paper discussed.

Keywords: coefficient of variation, mean, standard deviation, call drop probability, handover

Procedia PDF Downloads 491

Authors: Syed Atif Hassan, Luv Mehta, Syed Asif Hassan

Abstract:

Hit song science is a field of investigation wherein machine learning techniques are applied to music tracks in order to extract such features from audio signals which can capture information that could explain the popularity of respective tracks. Record companies invest huge amounts of money into recruiting fresh talents and churning out new music each year. Gaining insight into the basis of why a song becomes popular will result in tremendous benefits for the music industry. This paper aims to extract basic musical and more advanced, acoustic features from songs while also taking into account external factors that play a role in making a particular song popular. We use a dataset derived from popular Spotify playlists divided by genre. We use ten genres (blues, classical, country, disco, hip-hop, jazz, metal, pop, reggae, rock), chosen on the basis of clear to ambiguous delineation in the typical sound of their genres. We feed these features into three different classifiers, namely, SVM with RBF kernel, a deep neural network, and a recurring neural network, to build separate predictive models and choosing the best performing model at the end. Predicting song popularity is particularly important for the music industry as it would allow record companies to produce better content for the masses resulting in a more competitive market.

Keywords: classifier, machine learning, music tracks, popularity, prediction

Procedia PDF Downloads 663

Authors: Sanaa Rashed Abdallah, Yasser F. Hassan

Abstract:

The paper will introduce an approach where a rough sets, gene expression programming and rough neural networks are used cooperatively for learning and classification support. The Objective of gene expression programming rough neural networks (GEP-RNN) approach is to obtain new classified data with minimum error in training and testing process. Starting point of gene expression programming rough neural networks (GEP-RNN) approach is an information system and the output from this approach is a structure of rough neural networks which is including the weights and thresholds with minimum classification error.

Keywords: rough sets, gene expression programming, rough neural networks, classification

Procedia PDF Downloads 383

Authors: Jian Xu, Xiaochun Yun, Yongzheng Zhang, Yafei Sang, Zhenyu Cheng

Abstract:

Network attack prevention is a critical research area of information security. Network attack would be oppressed if attribution techniques are capable to trace back to the attackers after the hacking event. Therefore attributing these attacks to a particular identification becomes one of the important tasks when analysts attempt to differentiate and profile the attacker behind a piece of attack trace. To assist analysts in expose attackers behind the scenes, this paper researches on the connections between attribution traces and proposes probabilistic relevance based attribution patterns. This method facilitates the evaluation of the plausibility relevance between different traceable identifications. Furthermore, through analyzing the connections among traces, it could confirm the existence probability of a certain organization as well as discover its affinitive partners by the means of drawing relevance matrix from attribution traces.

Keywords: attribution trace, probabilistic relevance, network attack, attacker identification

Procedia PDF Downloads 366

Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle

Abstract:

Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.

Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3

Procedia PDF Downloads 66

Authors: Jessica Liqin Kong

Abstract:

Female engineers and scientists face unique challenges in their careers that make the development of professional networks crucial, but also more difficult. Working to overcome these challenges, ‘The Network’ was established in 2013 at the Queensland University of Technology (QUT) in Australia as an alumni chapter with the purpose of evoking continuous positive change for female participation and retention in science, technology, engineering and mathematics (STEM). ‘The Network’ adopts an innovative model for a Women in STEM alumni chapter which was inspired by the cradle to cradle approach to engagement, and the concept of growing and harvesting individual and collective social capital through a variety of initiatives. ‘The Network’ fosters an environment where the values exchanged in social and professional relationships can be capitalized for both current and future women in STEM. The model of ‘The Network’ acts as a simulation and opportunity for participants to further develop their leadership and other soft skills through learning, building and experimenting with ‘The Network’.

Keywords: women in STEM, engagement, Cradle-to-Cradle, social capital

Procedia PDF Downloads 284

Authors: Yang Yang, Dan Liu

Abstract:

Anomaly detection models for network flow based on machine learning have poor detection performance under extremely unbalanced training data conditions and also have slow detection speed and large resource consumption when deploying on network edge devices. Embedding multi-teacher knowledge distillation (mKD) in anomaly detection can transfer knowledge from multiple teacher models to a single model. Inspired by this, we proposed a state-of-the-art model, mKDNAD, to improve detection performance. mKDNAD mine and integrate the knowledge of one-dimensional sequence and two-dimensional image implicit in network flow to improve the detection accuracy of small sample classes. The multi-teacher knowledge distillation method guides the train of the student model, thus speeding up the model's detection speed and reducing the number of model parameters. Experiments in the CICIDS2017 dataset verify the improvements of our method in the detection speed and the detection accuracy in dealing with the small sample classes.

Keywords: network flow anomaly detection (NAD), multi-teacher knowledge distillation, machine learning, deep learning

Procedia PDF Downloads 122

Authors: Sung Hyun You, Jeong Hoon Kim, Dae Ki Kim, Choon Ki Ahn

Abstract:

In this paper, we proposed a new strategy for estimating indoor temperature based on the modified resistance capacitance (R–C) network thermal dynamic model. Using minimum variance finite impulse response (FIR) filter, accurate indoor temperature estimation can be achieved. Our study is clarified by the experimental validation of the proposed indoor temperature estimation method. This experiment scenario environment is composed of a demand response (DR) server and home energy management system (HEMS) in a test bed.

Keywords: energy consumption, resistance-capacitance network model, demand response, finite impulse response filter

Procedia PDF Downloads 447

Authors: Dachuan Shi, M. Hecht, Y. Ye

Abstract:

With the trend of digitalization in railway freight transport, a large number of freight wagons in Germany have been equipped with telematics devices, commonly placed on the wagon body. A telematics device contains a GPS module for tracking and a 3-axis accelerometer for shock detection. Besides these basic functions, it is desired to use the integrated accelerometer for condition monitoring without any additional sensors. Wheel flats as a common type of failure on wheel tread cause large impacts on wagons and infrastructure as well as impulsive noise. A large wheel flat may even cause safety issues such as derailments. In this sense, this paper proposes a machine learning approach for wheel flat detection by using car body accelerations. Due to suspension systems, impulsive signals caused by wheel flats are damped significantly and thus could be buried in signal noise and disturbances. Therefore, it is very challenging to detect wheel flats using car body accelerations. The proposed algorithm considers the envelope spectrum of car body accelerations to eliminate the effect of noise and disturbances. Subsequently, a 1-D convolutional neural network (CNN), which is well known as a deep learning method, is constructed to automatically extract features in the envelope-frequency domain and conduct classification. The constructed CNN is trained and tested on field test data, which are measured on the underframe of a tank wagon with a wheel flat of 20 mm length in the operational condition. The test results demonstrate the good performance of the proposed algorithm for real-time fault detection.

Keywords: fault detection, wheel flat, convolutional neural network, machine learning

Procedia PDF Downloads 131

Authors: Yiwei Huang, Chunyu Zhao, Jingjing Ding

Abstract:

Electrical Resistivity Tomography has been widely used in the medicine and the geology, such as the imaging of the lung impedance and the analysis of the soil impedance, etc. Linear Back Projection is the core algorithm of Electrical Resistivity Tomography, but the traditional Linear Back Projection can not make full use of the information of the electric field. In this paper, an imaging method of Parallel Electrode Linear Back Projection for Electrical Resistivity Tomography is proposed, which generates the electric field distribution that is not linearly related to the traditional Linear Back Projection, captures the new information and improves the imaging accuracy without increasing the number of electrodes by changing the connection mode of the electrodes. The simulation results show that the accuracy of the image obtained by the inverse operation obtained by the Parallel Electrode Linear Back Projection can be improved by about 20%.

Keywords: electrical resistivity tomography, finite element simulation, image optimization, parallel electrode linear back projection

Procedia PDF Downloads 153

Authors: Hyun Joon Chang, Jae In Kim, Sungsoo Na

Abstract:

Kinesin-1 (hereafter called kinesin) is a molecular motor protein that moves cargos toward the end of microtubules using the energy of adenosine triphosphate (ATP) hydrolysis. When kinesin is inactive, its tail autoinhibits the motor chain in order to prevent from reacting with the ATP by cross-linking of the tail domain to the motor domains at two positions. However, the morphological study of kinesin during autoinhibition is yet remained obscured. In this study, we report the effect of the binding site of the tail domain using the normal mode analysis of the elastic network model on kinesin in the tail-free form and tail-bind form. Considering the relationship between the connectivity of conventional network model with respect to the cutoff length and the functionality of the binding site of the tail, we revaluated the network model to observe the key role of the tail domain in its structural aspect. Contingent on the existence of the tail domain, the results suggest the morphological stability of the motor domain. Furthermore, employing the results from normal mode analysis, we have determined the strain energy of the neck linker, an essential portion of the motor domain for ATP hydrolysis. The results of the neck linker also converge to the same indication, i.e. the morphological analysis of the motor domain.

Keywords: elastic network model, Kinesin-1, autoinhibition

Procedia PDF Downloads 455

Authors: Prabu Duplex

Abstract:

Due to stringent emission regulation targets, large-scale transition to renewable energy sources is a global challenge, and wind power plays a significant role in the solution vector. This scenario has led to the construction of offshore wind farms, and several wind farms are planned in the shallow waters where the marine habitat exists. It raises concerns over impacts of underwater noise on marine species, for example bridge constructions in the ocean straits. Dangerous to aquatic life, the environmental organisations say, the bridge would be devastating, since ocean straits are important place of transit for marine mammals. One of the highest concentrations of biodiversity in the world is concentrated these areas. The investigation of ship noise and piling noise that may happen during bridge construction and in operation is therefore vital. Once the source levels are known the receiver levels can be modelled. With this objective this work investigates the key requirement of the software that can model transmission loss in high frequencies that may occur during construction or operation phases. Most propagation models are 2D solutions, calculating the propagation loss along a transect, which does not include horizontal refraction, reflection or diffraction. In many cases, such models provide sufficient accuracy and can provide three-dimensional maps by combining, through interpolation, several two-dimensional (distance and depth) transects. However, in some instances the use of 2D models may not be sufficient to accurately model the sound propagation. A possible example includes a scenario where an island or land mass is situated between the source and receiver. The 2D model will result in a shadow behind the land mass where the modelled transects intersect the land mass. Diffraction will occur causing bending of the sound around the land mass. In such cases, it may be necessary to use a 3D model, which accounts for horizontal diffraction to accurately represent the sound field. Other scenarios where 2D models may not provide sufficient accuracy may be environments characterised by a strong up-sloping or down sloping seabed, such as propagation around continental shelves. In line with these objectives by means of a case study, this work addresses the importance of 3D interactions in underwater acoustics. The methodology used in this study can also be used for other 3D underwater sound propagation studies. This work assumes special significance given the increasing interest in using underwater acoustic modeling for environmental impacts assessments. Future work also includes inter-model comparison in shallow water environments considering more physical processes known to influence sound propagation, such as scattering from the sea surface. Passive acoustic monitoring of the underwater soundscape with distributed hydrophone arrays is also suggested to investigate the 3D propagation effects as discussed in this article.

Keywords: underwater acoustics, naval, maritime, cetaceans

Procedia PDF Downloads 19

Authors: Stylianos Kampakis

Abstract:

This paper presents a new algorithm for neural networks called “Input Dropout with Aggressive Re-weighting” (IDAR) aimed specifically at datasets with many useless features. IDAR combines two techniques (dropout of input neurons and aggressive re weighting) in order to eliminate the influence of noisy features. The technique can be seen as a generalization of dropout. The algorithm is tested on two different benchmark data sets: a noisy version of the iris dataset and the MADELON data set. Its performance is compared against three other popular techniques for dealing with useless features: L2 regularization, LASSO and random forests. The results demonstrate that IDAR can be an effective technique for handling data sets with many useless features.

Keywords: neural networks, feature selection, regularization, aggressive reweighting

Procedia PDF Downloads 455

Authors: Bitewulign Mekonnen

Abstract:

Context: This scientific paper focuses on the use of near-infrared (NIR) spectroscopy to determine glucose concentration in aqueous solutions accurately and rapidly. The study compares six different machine learning methods for predicting glucose concentration and also explores the development of a deep learning model for classifying NIR spectra. The objective is to optimize the detection model and improve the accuracy of glucose prediction. This research is important because it provides a comprehensive analysis of various machine-learning techniques for estimating aqueous glucose concentrations. Research Aim: The aim of this study is to compare and evaluate different machine-learning methods for predicting glucose concentration from NIR spectra. Additionally, the study aims to develop and assess a deep-learning model for classifying NIR spectra. Methodology: The research methodology involves the use of machine learning and deep learning techniques. Six machine learning regression models, including support vector machine regression, partial least squares regression, extra tree regression, random forest regression, extreme gradient boosting, and principal component analysis-neural network, are employed to predict glucose concentration. The NIR spectra data is randomly divided into train and test sets, and the process is repeated ten times to increase generalization ability. In addition, a convolutional neural network is developed for classifying NIR spectra. Findings: The study reveals that the SVMR, ETR, and PCA-NN models exhibit excellent performance in predicting glucose concentration, with correlation coefficients (R) > 0.99 and determination coefficients (R²)> 0.985. The deep learning model achieves high macro-averaging scores for precision, recall, and F1-measure. These findings demonstrate the effectiveness of machine learning and deep learning methods in optimizing the detection model and improving glucose prediction accuracy. Theoretical Importance: This research contributes to the field by providing a comprehensive analysis of various machine-learning techniques for estimating glucose concentrations from NIR spectra. It also explores the use of deep learning for the classification of indistinguishable NIR spectra. The findings highlight the potential of machine learning and deep learning in enhancing the prediction accuracy of glucose-relevant features. Data Collection and Analysis Procedures: The NIR spectra and corresponding references for glucose concentration are measured in increments of 20 mg/dl. The data is randomly divided into train and test sets, and the models are evaluated using regression analysis and classification metrics. The performance of each model is assessed based on correlation coefficients, determination coefficients, precision, recall, and F1-measure. Question Addressed: The study addresses the question of whether machine learning and deep learning methods can optimize the detection model and improve the accuracy of glucose prediction from NIR spectra. Conclusion: The research demonstrates that machine learning and deep learning methods can effectively predict glucose concentration from NIR spectra. The SVMR, ETR, and PCA-NN models exhibit superior performance, while the deep learning model achieves high classification scores. These findings suggest that machine learning and deep learning techniques can be used to improve the prediction accuracy of glucose-relevant features. Further research is needed to explore their clinical utility in analyzing complex matrices, such as blood glucose levels.

Keywords: machine learning, signal processing, near-infrared spectroscopy, support vector machine, neural network

Procedia PDF Downloads 94

Authors: Shital Suresh Borse, Vijayalaxmi Kadroli

Abstract:

E-commerce industries nowadays implement the latest AI, ML Techniques to improve their own performance and prediction accuracy. This helps to gain a huge profit from the online market. Ant Colony Optimization, Genetic algorithm, Particle Swarm Optimization, Neural Network & GWO help many e-commerce industries for up-gradation of their predictive performance. These algorithms are providing optimum results in various applications, such as stock price prediction, prediction of drug-target interaction & user ratings of similar products in e-commerce sites, etc. In this study, customer reviews will play an important role in prediction analysis. People showing much interest in buying a lot of services& products suggested by other customers. This ultimately increases net profit. In this work, a convolution neural network (CNN) is proposed which further is useful to optimize the prediction accuracy of an e-commerce website. This method shows that CNN is used to optimize hyperparameters of GWO algorithm using an appropriate coding scheme. Accurate model results are verified by comparing them to PSO results whose hyperparameters have been optimized by CNN in Amazon's customer review dataset. Here, experimental outcome proves that this proposed system using the GWO algorithm achieves superior execution in terms of accuracy, precision, recovery, etc. in prediction analysis compared to the existing systems.

Keywords: prediction analysis, e-commerce, machine learning, grey wolf optimization, particle swarm optimization, CNN

Procedia PDF Downloads 113

Authors: Alexander S. Andreev, Olga A. Peregudova

Abstract:

In this paper, we propose a discrete tracking control of nonholonomic mobile robots with two degrees of freedom. The electro-mechanical model of a mobile robot moving on a horizontal surface without slipping, with two rear wheels controlled by two independent DC electric, and one front roal wheel is considered. We present back-stepping design based on the Euler approximate discrete-time model of a continuous-time plant. Theoretical considerations are verified by numerical simulation. The work was supported by RFFI (15-01-08482).

Keywords: actuator dynamics, back stepping, discrete-time controller, Lyapunov function, wheeled mobile robot

Procedia PDF Downloads 415

Authors: Dávid Kovács, Bálint Csanády, Dániel Boros, Iván Ivkovic, Lóránt Nagy, Dalma Tóth-Lakits, László Márkus, András Lukács

Abstract:

The modeling practice of financial instruments has seen significant change over the last decade due to the recognition of time-dependent and stochastically changing correlations among the market prices or the prices and market characteristics. To represent this phenomenon, the Stochastic Correlation Process (SCP) has come to the fore in the joint modeling of prices, offering a more nuanced description of their interdependence. This approach has allowed for the attainment of realistic tail dependencies, highlighting that prices tend to synchronize more during intense or volatile trading periods, resulting in stronger correlations. Evidence in statistical literature suggests that, similarly to the volatility, the SCP of certain stock prices follows rough paths, which can be described using fractional differential equations. However, estimating parameters for these equations often involves complex and computation-intensive algorithms, creating a necessity for alternative solutions. In this regard, the Fractional Ornstein-Uhlenbeck (fOU) process from the family of fractional processes offers a promising path. We can effectively describe the rough SCP by utilizing certain transformations of the fOU. We employed neural networks to understand the behavior of these processes. We had to develop a fast algorithm to generate a valid and suitably large sample from the appropriate process to train the network. With an extensive training set, the neural network can estimate the process parameters accurately and efficiently. Although the initial focus was the fOU, the resulting model displayed broader applicability, thus paving the way for further investigation of other processes in the realm of financial mathematics. The utility of SCP extends beyond its immediate application. It also serves as a springboard for a deeper exploration of fractional processes and for extending existing models that use ordinary Wiener processes to fractional scenarios. In essence, deploying both SCP and fractional processes in financial models provides new, more accurate ways to depict market dynamics.

Keywords: fractional Ornstein-Uhlenbeck process, fractional stochastic processes, Heston model, neural networks, stochastic correlation, stochastic differential equations, stochastic volatility

Procedia PDF Downloads 118

Authors: Hosuk Shin, Young-Hyun Seo, Eunhak Lee, Seung-Young Kho

Abstract:

Currently, in Seoul, users have the privilege to avoid riding crowded buses with the installation of Bus Information System (BIS). BIS has three levels of on-board bus ridership level information (spacious, normal, and crowded). However, there are flaws in the system due to it being real time which could provide incomplete information to the user. For example, a bus comes to the station, and on the BIS it shows that the bus is crowded, but on the stop that the user is waiting many people get off, which would mean that this station the information should show as normal or spacious. To fix this problem, this study predicts the bus ridership level using smart card data to provide more accurate information about the passenger ridership level on the bus. An Artificial Neural Network (ANN) is an interconnected group of nodes, that was created based on the human brain. Forecasting has been one of the major applications of ANN due to the data-driven self-adaptive methods of the algorithm itself. According to the results, the ANN algorithm was stable and robust with somewhat small error ratio, so the results were rational and reasonable.

Keywords: smartcard data, ANN, bus, ridership

Procedia PDF Downloads 167

Authors: Jehnming Lin

Abstract:

In the laser cleavage of glass, the laser is mostly adopted as a heat source to generate a thermal stress state on the substrates. The crack propagation of the soda-lime glass in the laser thermal cleavage with the straight-turning paths was investigated in this study experimentally and numerically. The crack propagation was visualized by a high speed camera with the off-line examination on the micro-crack propagation. The temperature and stress distributions induced by the laser heat source were calculated by ANSYS software based on the finite element method (FEM). With the cutting paths in various turning directions, the experimental and numerical results were in comparison and verified. The fracture modes due to the normal and shear stresses were verified at the turning point of the laser cleavage path. It shows a significant variation of the stress profiles along the straight-turning paths and causes a change on the fracture modes.

Keywords: laser cleavage, glass, fracture, stress analysis

Procedia PDF Downloads 229

Authors: Feng Yang

Abstract:

Machine learning (ML), especially deep learning (DL), has been extensively applied to many applications in recently years and gained great success in solving different problems, including scientific problems. However, conventional ML/DL methodologies are purely data-driven which have the limitations, such as need of ample amount of labelled training data, lack of consistency to physical principles, and lack of generalizability to new problems/domains. Recently, there is a growing consensus that ML models need to further take advantage of prior knowledge to deal with these limitations. Physics-informed machine learning, aiming at integration of physics/domain knowledge into ML, has been recognized as an emerging area of research, especially in the recent 2 to 3 years. In this work, physics-informed ML, specifically physics-informed neural network (NN), is employed and implemented to estimate the displacements at x, y, z directions in a solid mechanics problem that is controlled by equilibrium equations with boundary conditions. By incorporating the physics (i.e. the equilibrium equations) into the learning process of NN, it is showed that the NN can be trained very efficiently with a small set of labelled training data. Experiments with different settings of the NN model and the amount of labelled training data were conducted, and the results show that very high accuracy can be achieved in fulfilling the equilibrium equations as well as in predicting the displacements, e.g. in setting the overall displacement of 0.1, a root mean square error (RMSE) of 2.09 × 10−4 was achieved.

Keywords: deep learning, neural network, physics-informed machine learning, solid mechanics

Procedia PDF Downloads 150

Authors: Bing Li, Zhi Li, Yilong Yang

Abstract:

Web classification can promote the quality of service discovery and management in the service repository. It is widely used to locate developers desired services. Although traditional classification methods based on supervised learning models can achieve classification tasks, developers need to manually mark web services, and the quality of these tags may not be enough to establish an accurate classifier for service classification. With the doubling of the number of web services, the manual tagging method has become unrealistic. In recent years, the attention mechanism has made remarkable progress in the field of deep learning, and its huge potential has been fully demonstrated in various fields. This paper designs a multi-head attention graph convolutional network (MHAGCN) service classification method, which can assign different weights to the neighborhood nodes without complicated matrix operations or relying on understanding the entire graph structure. The framework combines the advantages of the attention mechanism and graph convolutional neural network. It can classify web services through automatic feature extraction. The comprehensive experimental results on a real dataset not only show the superior performance of the proposed model over the existing models but also demonstrate its potentially good interpretability for graph analysis.

Keywords: attention mechanism, graph convolutional network, interpretability, service classification, service discovery

Procedia PDF Downloads 135

Authors: Kaoutar Abbahaddou, Mohammed Salah Chiadmi

Abstract:

The need to find a relevant way to predict the next-day price of a stock index is a real concern for many financial stakeholders and researchers. We have known across years the proliferation of several methods. Nevertheless, among all these methods, the most controversial one is a machine learning algorithm that claims to be reliable, namely neural networks. Thus, the purpose of this article is to study the prediction power of neural networks in the particular case of Islamic finance as it is an under-looked area. In this article, we will first briefly present a review of the literature regarding neural networks and Islamic finance. Next, we present the architecture and principles of artificial neural networks most commonly used in finance. Then, we will show its empirical application on two Islamic stock indexes. The accuracy rate would be used to measure the performance of the algorithm in predicting the right price the next day. As a result, we can conclude that artificial neural networks are a reliable method to predict the next-day price for Islamic indices as it is claimed for conventional ones.

Keywords: Islamic finance, stock price prediction, artificial neural networks, machine learning

Procedia PDF Downloads 237

Authors: Jayanta Kumar Ghosh, Swastik Sunil Goriwale, Himangshu Sarkar

Abstract:

Groundwater is one of the most valuable natural resources that society consumes for its domestic, industrial, and agricultural water supply. Its bulk and indiscriminate consumption affects the groundwater resource. Often, it has been found that the groundwater recharge rate is much lower than its demand. Thus, to maintain water and food security, it is necessary to monitor and management of groundwater storage. However, it is challenging to estimate groundwater storage (GWS) by making use of existing hydrological models. To overcome the difficulties, machine learning (ML) models are being introduced for the evaluation of groundwater level (GWL). Thus, the objective of this research work is to develop an ML-based model for the prediction of GWL. This objective has been realized through the development of an artificial neural network (ANN) model based on hydro-gravimetry. The model has been developed using training samples from field observations spread over 8 months. The developed model has been tested for the prediction of GWL in an observation well. The root means square error (RMSE) for the test samples has been found to be 0.390 meters. Thus, it can be concluded that the hydro-gravimetric-based ANN model can be used for the prediction of GWL. However, to improve the accuracy, more hydro-gravimetric parameter/s may be considered and tested in future.

Keywords: machine learning, hydro-gravimetry, ground water level, predictive model

Procedia PDF Downloads 127

Authors: Ons Slimene, Aroua Taamallah, Maha Khemaja

Abstract:

In recent years, human activity recognition (HAR) has been a key area of research due to its diverse applications. It has garnered increasing attention in the field of computer vision. HAR plays an important role in people’s daily lives as it has the ability to learn advanced knowledge about human activities from data. In HAR, activities are usually represented by exploiting different types of sensors, such as embedded sensors or visual sensors. However, these sensors have limitations, such as local obstacles, image-related obstacles, sensor unreliability, and consumer concerns. Recently, several deep learning-based approaches have been proposed for HAR and these approaches are classified into two categories based on the type of data used: vision-based approaches and sensor-based approaches. This research paper highlights the importance of multimodal data fusion from skeleton data obtained from videos and data generated by embedded sensors using deep neural networks for achieving HAR. We propose a deep multimodal fusion network based on a twostream architecture. These two streams use the Convolutional Neural Network combined with the Bidirectional LSTM (CNN BILSTM) to process skeleton data and data generated by embedded sensors and the fusion at the feature level is considered. The proposed model was evaluated on a public OPPORTUNITY++ dataset and produced a accuracy of 96.77%.

Keywords: human activity recognition, action recognition, sensors, vision, human-centric sensing, deep learning, context-awareness

Procedia PDF Downloads 101

Authors: Emanuel Teixeira, Anderson Ramos, Marisa Lourenço, Fernando J. Velez, Jon M. Peha

Abstract:

This article discusses the benefit cost analysis aspects of millimetre wavebands (mmWaves) and Super High Frequency (SHF). The devaluation along the distance of the carrier-to-noise-plus-interference ratio with the coverage distance is assessed by considering two different path loss models, the two-slope urban micro Line-of-Sight (UMiLoS) for the SHF band and the modified Friis propagation model, for frequencies above 24 GHz. The equivalent supported throughput is estimated at the 5.62, 28, 38, 60 and 73 GHz frequency bands and the influence of carrier-to-noise-plus-interference ratio in the radio and network optimization process is explored. Mostly owing to the lessening caused by the behaviour of the two-slope propagation model for SHF band, the supported throughput at this band is higher than at the millimetre wavebands only for the longest cell lengths. The benefit cost analysis of these pico-cellular networks was analysed for regular cellular topologies, by considering the unlicensed spectrum. For shortest distances, we can distinguish an optimal of the revenue in percentage terms for values of the cell length, R ≈ 10 m for the millimeter wavebands and for longest distances an optimal of the revenue can be observed at R ≈ 550 m for the 5.62 GHz. It is possible to observe that, for the 5.62 GHz band, the profit is slightly inferior than for millimetre wavebands, for the shortest Rs, and starts to increase for cell lengths approximately equal to the ratio between the break-point distance and the co-channel reuse factor, achieving a maximum for values of R approximately equal to 550 m.

Keywords: millimetre wavebands, SHF band, SINR, cost benefit analysis, 5G

Procedia PDF Downloads 141

Authors: Lokes Parvatha Kumaran S., Sakthi Jay Mahenthar C., Sathyaprakash P., Jayakumar V., Shobanadevi A.

Abstract:

With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. But even the most powerful classical supercomputers find it difficult to execute these tasks. With the recent development of quantum computing, researchers and tech-giants strive for new quantum circuits for machine learning tasks, as present works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. But it is strenuous to simulate classical deep learning models on existing quantum computing platforms due to the inflexibility of deep quantum circuits. As a consequence, it is essential to design viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Reinforcement Learning by remodeling the experience replay and target network into a representation of VQC. In addition, to reduce the number of model parameters, quantum information encoding schemes are used to achieve better results than the classical neural networks. VQCs are employed to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and the target network.

Keywords: quantum computing, quantum machine learning, variational quantum circuit, deep reinforcement learning, quantum information encoding scheme

Procedia PDF Downloads 134