Search results for: system models

Authors: Ophir Nave

Abstract:

In our research, we present the concept of singularly perturbed vector field (SPVF) method, and its application to thermal explosion of diesel spray combustion. Given a system of governing equations, which consist of hidden Multi-scale variables, the SPVF method transfer and decompose such system to fast and slow singularly perturbed subsystems (SPS). The SPVF method enables us to understand the complex system, and simplify the calculations. Later powerful analytical, numerical and asymptotic methods (e.g method of integral (invariant) manifold (MIM), the homotopy analysis method (HAM) etc.) can be applied to each subsystem. We compare the results obtained by the methods of integral invariant manifold and SPVF apply to spray droplets combustion model. The research deals with the development of an innovative method for extracting fast and slow variables in physical mathematical models. The method that we developed called singular perturbed vector field. This method based on a numerical algorithm applied to global quasi linearization applied to given physical model. The SPVF method applied successfully to combustion processes. Our results were compared to experimentally results. The SPVF is a general numerical and asymptotical method that reveals the hierarchy (multi-scale system) of a given system.

Keywords: polydisperse spray, model reduction, asymptotic analysis, multi-scale systems

Procedia PDF Downloads 220

Authors: Ahmed Elaksher, Islam Omar

Abstract:

Accurate geometric relation algorithms are imperative in Earth and planetary satellite and aerial image processing, particularly for high-resolution images that are used for topographic mapping. Most of these satellites carry push-broom sensors. These sensors are optical scanners equipped with linear arrays of CCDs. These sensors have been deployed on most EOSs. In addition, the LROC is equipped with two push NACs that provide 0.5 meter-scale panchromatic images over a 5 km swath of the Moon. The HiRISE carried by the MRO and the HRSC carried by MEX are examples of push-broom sensor that produces images of the surface of Mars. Sensor models developed in photogrammetry relate image space coordinates in two or more images with the 3D coordinates of ground features. Rigorous sensor models use the actual interior orientation parameters and exterior orientation parameters of the camera, unlike approximate models. In this research, we generate a generic push-broom sensor model to process imageries acquired through linear array cameras and investigate its performance, advantages, and disadvantages in generating topographic models for the Earth, Mars, and the Moon. We also compare and contrast the utilization, effectiveness, and applicability of available photogrammetric techniques and softcopies with the developed model. We start by defining an image reference coordinate system to unify image coordinates from all three arrays. The transformation from an image coordinate system to a reference coordinate system involves a translation and three rotations. For any image point within the linear array, its image reference coordinates, the coordinates of the exposure center of the array in the ground coordinate system at the imaging epoch (t), and the corresponding ground point coordinates are related through the collinearity condition that states that all these three points must be on the same line. The rotation angles for each CCD array at the epoch t are defined and included in the transformation model. The exterior orientation parameters of an image line, i.e., coordinates of exposure station and rotation angles, are computed by a polynomial interpolation function in time (t). The parameter (t) is the time at a certain epoch from a certain orbit position. Depending on the types of observations, coordinates, and parameters may be treated as knowns or unknowns differently in various situations. The unknown coefficients are determined in a bundle adjustment. The orientation process starts by extracting the sensor position and, orientation and raw images from the PDS. The parameters of each image line are then estimated and imported into the push-broom sensor model. We also define tie points between image pairs to aid the bundle adjustment model, determine the refined camera parameters, and generate highly accurate topographic maps. The model was tested on different satellite images such as IKONOS, QuickBird, and WorldView-2, HiRISE. It was found that the accuracy of our model is comparable to those of commercial and open-source software, the computational efficiency of the developed model is high, the model could be used in different environments with various sensors, and the implementation process is much more cost-and effort-consuming.

Keywords: photogrammetry, push-broom sensors, IKONOS, HiRISE, collinearity condition

Procedia PDF Downloads 63

Authors: Stefan Papastefanou

Abstract:

Artificial intelligence (AI) is an interdisciplinary field of computer science with the aim of creating intelligent machine behavior. Early approaches to AI have been configured to operate in very constrained environments where the behavior of the AI system was previously determined by formal rules. Knowledge was presented as a set of rules that allowed the AI system to determine the results for specific problems; as a structure of if-else rules that could be traversed to find a solution to a particular problem or question. However, such rule-based systems typically have not been able to generalize beyond the knowledge provided. All over the world and especially in IT-heavy industries such as the United States, the European Union, Singapore, and China, machine learning has developed to be an immense asset, and its applications are becoming more and more significant. It has to be examined how such products of machine learning models can and should be protected by IP law and for the purpose of this paper patent law specifically, since it is the IP law regime closest to technical inventions and computing methods in technical applications. Genetic breeding models are currently less popular than recursive neural network method and deep learning, but this approach can be more easily described by referring to the evolution of natural organisms, and with increasing computational power; the genetic breeding method as a subset of the evolutionary algorithms models is expected to be regaining popularity. The research method focuses on patentability (according to the world’s most significant patent law regimes such as China, Singapore, the European Union, and the United States) of AI inventions and machine learning. Questions of the technical nature of the problem to be solved, the inventive step as such, and the question of the state of the art and the associated obviousness of the solution arise in the current patenting processes. Most importantly, and the key focus of this paper is the problem of patenting inventions that themselves are developed through machine learning. The inventor of a patent application must be a natural person or a group of persons according to the current legal situation in most patent law regimes. In order to be considered an 'inventor', a person must actually have developed part of the inventive concept. The mere application of machine learning or an AI algorithm to a particular problem should not be construed as the algorithm that contributes to a part of the inventive concept. However, when machine learning or the AI algorithm has contributed to a part of the inventive concept, there is currently a lack of clarity regarding the ownership of artificially created inventions. Since not only all European patent law regimes but also the Chinese and Singaporean patent law approaches include identical terms, this paper ultimately offers a comparative analysis of the most relevant patent law regimes.

Keywords: algorithms, inventor, genetic breeding models, machine learning, patentability

Procedia PDF Downloads 109

Authors: Iulia E. Falcan

Abstract:

The transition of the European power sector towards a clean, renewable energy (RE) system faces the challenge of meeting power demand in times of low wind speed and low solar radiation, at a reasonable cost. This is likely to be achieved through a combination of 1) energy storage technologies, 2) development of the cross-border power grid, 3) installed overcapacity of RE and 4) dispatchable power sources – such as biomass. This paper uses NASA; derived hourly data on weather patterns of sixteen European countries for the past twenty-five years, and load data from the European Network of Transmission System Operators-Electricity (ENTSO-E), to develop a stochastic optimization model. This model aims to understand the synergies between the four classes of technologies mentioned above and to determine the optimal configuration of the energy technologies portfolio. While this issue has been addressed before, it was done so using deterministic models that extrapolated historic data on weather patterns and power demand, as well as ignoring the risk of an unbalanced grid-risk stemming from both the supply and the demand side. This paper aims to explicitly account for the inherent uncertainty in the energy system transition. It articulates two levels of uncertainty: a) the inherent uncertainty in future weather patterns and b) the uncertainty of fully meeting power demand. The first level of uncertainty is addressed by developing probability distributions for future weather data and thus expected power output from RE technologies, rather than known future power output. The latter level of uncertainty is operationalized by introducing a Conditional Value at Risk (CVaR) constraint in the portfolio optimization problem. By setting the risk threshold at different levels – 1%, 5% and 10%, important insights are revealed regarding the synergies of the different energy technologies, i.e., the circumstances under which they behave as either complements or substitutes to each other. The paper concludes that allowing for uncertainty in expected power output - rather than extrapolating historic data - paints a more realistic picture and reveals important departures from results of deterministic models. In addition, explicitly acknowledging the risk of an unbalanced grid - and assigning it different thresholds - reveals non-linearity in the cost functions of different technology portfolio configurations. This finding has significant implications for the design of the European energy mix.

Keywords: cross-border grid extension, energy storage technologies, energy system transition, stochastic portfolio optimization

Procedia PDF Downloads 171

Authors: Cristina Schreiner, Romeo Ciobanu, Marius Pislaru

Abstract:

This paper aims to build a system based on fuzzy models that can be implemented in the assessment of ecological systems, to determine appropriate methods of action for reducing adverse effects on environmental and implicit the population. The model proposed provides new perspective for environmental assessment, and it can be used as a practical instrument for decision-making.

Keywords: ecosystem model, environmental security, fuzzy logic, sustainability of habitable regions

Procedia PDF Downloads 422

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 91

Authors: Kudzanayi Chiteka, Wellington Makondo

Abstract:

The whole world is on the drive to go green owing to the negative effects of burning fossil fuels. Therefore, there is immediate need to identify and utilise alternative renewable energy sources. Among these energy sources solar energy is one of the most dominant in Zimbabwe. Solar power plants used to generate electricity are entirely dependent on solar radiation. For planning purposes, solar radiation values should be known in advance to make necessary arrangements to minimise the negative effects of the absence of solar radiation due to cloud cover and other naturally occurring phenomena. This research focused on the prediction of Global Horizontal Irradiation values for the sixth day given values for the past five days. Artificial intelligence techniques were used in this research. Three models were developed based on Support Vector Machines, Radial Basis Function, and Feed Forward Back-Propagation Artificial neural network. Results revealed that Support Vector Machines gives the best results compared to the other two with a mean absolute percentage error (MAPE) of 2%, Mean Absolute Error (MAE) of 0.05kWh/m²/day root mean square (RMS) error of 0.15kWh/m²/day and a coefficient of determination of 0.990. The other predictive models had prediction accuracies of MAPEs of 4.5% and 6% respectively for Radial Basis Function and Feed Forward Back-propagation Artificial neural network. These two models also had coefficients of determination of 0.975 and 0.970 respectively. It was found that prediction of GHI values for the future days is possible using artificial intelligence-based predictive models.

Keywords: solar energy, global horizontal irradiation, artificial intelligence, predictive models

Procedia PDF Downloads 274

Authors: Alexandros Pournaras, Anastasia Papadopoulou, Serafim Kontos, Anastasios Karakostas

Abstract:

The air quality of modern cities is an important concern, as poor air quality contributes to human health and environmental issues. Reliable air quality forecasting has, thus, gained scientific and governmental attention as an essential tool that enables authorities to take proactive measures for public safety. In this study, the potential of Machine Learning (ML) models to forecast PM2.5 at local scale is investigated in the city of Thessaloniki, the second largest city in Greece, which has been struggling with the persistent issue of air pollution. ML models, with proven ability to address timeseries forecasting, are employed to predict the PM2.5 concentrations and the respective Air Quality Index 5-days ahead by learning from daily historical air quality and meteorological data from 2014 to 2016 and gathered from two stations with different land use characteristics in the urban fabric of Thessaloniki. The performance of the ML models on PM2.5 concentrations is evaluated with common statistical methods, such as R squared (r²) and Root Mean Squared Error (RMSE), utilizing a portion of the stations’ measurements as test set. A multi-categorical evaluation is utilized for the assessment of their performance on respective AQIs. Several conclusions were made from the experiments conducted. Experimenting on MLs’ configuration revealed a moderate effect of various parameters and training schemas on the model’s predictions. Their performance of all these models were found to produce satisfactory results on PM2.5 concentrations. In addition, their application on untrained stations showed that these models can perform well, indicating a generalized behavior. Moreover, their performance on AQI was even better, showing that the MLs can be used as predictors for AQI, which is the direct information provided to the general public.

Keywords: Air Quality, AQ Forecasting, AQI, Machine Learning, PM2.5

Procedia PDF Downloads 79

Authors: M. Ouassaf, S. Belaid

Abstract:

A series of quinoline derivatives with antimalarial activity were subjected to two-dimensional quantitative structure-activity relationship (2D-QSAR) studies. Three models were implemented using multiple regression linear MLR, a regression partial least squares (PLS), nonlinear regression (MNLR), to see which descriptors are closely related to the activity biologic. We relied on a principal component analysis (PCA). Based on our results, a comparison of the quality of, MLR, PLS, and MNLR models shows that the MNLR (R = 0.914 and R² = 0.835, RCV= 0.853) models have substantially better predictive capability because the MNLR approach gives better results than MLR (R = 0.835 and R² = 0,752, RCV=0.601)), PLS (R = 0.742 and R² = 0.552, RCV=0.550) The model of MNLR gave statistically significant results and showed good stability to data variation in leave-one-out cross-validation. The obtained results suggested that our proposed model MNLR may be useful to predict the biological activity of derivatives of quinoline.

Keywords: antimalarial, quinoline, QSAR, PCA, MLR , MNLR, MLR

Procedia PDF Downloads 157

Authors: Yuchen Sharon Sung, Yingjui Tseng

Abstract:

High-rise residential buildings have become the most mainstream housing pattern in the world’s metropolises under the current trend of urbanization. The facades of high-rise buildings are essential elements of the urban landscape. The skins of these facades are important media between the interior and exterior of high- rise buildings. It not only connects between users and environments, but also plays an important functional and aesthetic role. This research involves a study of skins of high-rise residential buildings using the methodology of shape grammar to find out the rules which determine the combinations of the facade patterns and analyze the patterns’ parameters using software Grasshopper. We chose a number of facades of high-rise residential buildings as source to discover the underlying rules and concepts of the generation of facade skins. This research also provides the rules that influence the composition of facade skins. The items of the facade skins, such as windows, balconies, walls, sun visors and metal grilles are treated as elements in the system of facade skins. The compositions of these elements will be categorized and described by logical rules; and the types of high-rise building facade skins will be modelled by Grasshopper. Then a variety of analyzed patterns can also be applied on other facade skins through this parametric mechanism. Using these patterns established in the models, researchers can analyze each single item to do more detail tests and architects can apply each of these items to construct their facades for other buildings through various combinations and permutations. The goal of these models is to develop a mechanism to generate prototypes in order to facilitate generation of various facade skins.

Keywords: facade skin, grasshopper, high-rise residential building, shape grammar

Procedia PDF Downloads 510

Authors: Sajjad Negahban, Ruihe Wang, Baojiang Sun

Abstract:

Gas-lift dual gradient drilling is a solution for deepwater drilling challenges. As well, Continuous development of drilling technology leads to increase employment of mineral oil based drilling fluids and synthetic-based drilling fluids, which have adequate characteristics such as: high rate of penetration, lubricity, shale inhibition and low toxicity. The paper discusses utilization of nitrified mineral oil base drilling for deepwater drilling and for more accurate prediction of pressure in DGD at marine riser, solubility and bubble pressure were considered in steady state hydraulic model. The Standing bubble pressure and solubility correlations, and two models which were acquired from experimental determination were applied in hydraulic model. The effect of the black oil correlations, and new solubility and bubble pressure models was evaluated on the PVT parameters such as oil formation volume factor, density, viscosity, volumetric flow rate. Eventually, the consequent simulated pressure profile due to these models was presented.

Keywords: solubility, bubble pressure, gas-lift dual gradient drilling, steady state hydraulic model

Procedia PDF Downloads 278

Authors: Elison Eduardo Jardim Bierhals, Claudineia Brazil, Deivid Pires, Rafael Haag, Elton Gimenez Rossini

Abstract:

The objective of this work is to evaluate the results of solar radiation projections between 2006 and 2013 for the state of Rio Grande do Sul, Brazil. The projections are provided by the General Circulation Models (MCGs) belonging to the Coupled Model Intercomparison Phase 5 (CMIP5). In all, the results of the simulation of six models are evaluated, compared to monthly data, measured by a network of thirteen meteorological stations of the National Meteorological Institute (INMET). The performance of the models is evaluated by the Nash coefficient and the Bias. The results are presented in the form of tables, graphs and spatialization maps. The ACCESS1-0 RCP 4.5 model presented the best results for the solar radiation simulations, for the most optimistic scenario, in much of the state. The efficiency coefficients (CEF) were between 0.95 and 0.98. In the most pessimistic scenario, HADGen2-AO RCP 8.5 had the best accuracy among the analyzed models, presenting coefficients of efficiency between 0.94 and 0.98. From this validation, solar radiation projection maps were elaborated, indicating a seasonal increase of this climatic variable in some regions of the Brazilian territory, mainly in the spring.

Keywords: climate change, projections, solar radiation, validation

Procedia PDF Downloads 209

Authors: Inna Kornienko, Svetlana Guryeva, Natalia Danilova, Elena Petersen

Abstract:

Drug toxicity often goes undetected until clinical trials, the most expensive and dangerous phase of drug development. Both human cell culture and animal studies have limitations that cannot be overcome by improvements in drug testing protocols. Tissue engineering is an emerging alternative approach to creating models of human malignant tumors for experimental oncology, personalized medicine, and drug discovery studies. This new generation of bioengineered tumors provides an opportunity to control and explore the role of every component of the model system including cell populations, supportive scaffolds, and signaling molecules. An area that could greatly benefit from these models is cancer research. Recent advances in tissue engineering demonstrated that decellularized tissue is an excellent scaffold for tissue engineering. Decellularization of donor organs such as heart, liver, and lung can provide an acellular, naturally occurring three-dimensional biologic scaffold material that can then be seeded with selected cell populations. Preliminary studies in animal models have provided encouraging results for the proof of concept. Decellularized Organs preserve organ microenvironment, which is critical for cancer metastasis. Utilizing 3D tumor models results greater proximity of cell culture morphological characteristics in a model to its in vivo counterpart, allows more accurate simulation of the processes within a functioning tumor and its pathogenesis. 3D models allow study of migration processes and cell proliferation with higher reliability as well. Moreover, cancer cells in a 3D model bear closer resemblance to living conditions in terms of gene expression, cell surface receptor expression, and signaling. 2D cell monolayers do not provide the geometrical and mechanical cues of tissues in vivo and are, therefore, not suitable to accurately predict the responses of living organisms. 3D models can provide several levels of complexity from simple monocultures of cancer cell lines in liquid environment comprised of oxygen and nutrient gradients and cell-cell interaction to more advanced models, which include co-culturing with other cell types, such as endothelial and immune cells. Following this reasoning, spheroids cultivated from one or multiple patient-derived cell lines can be utilized to seed the matrix rather than monolayer cells. This approach furthers the progress towards personalized medicine. As an initial step to create a new ex vivo tissue engineered model of a cancer tumor, optimized protocols have been designed to obtain organ-specific acellular matrices and evaluate their potential as tissue engineered scaffolds for cultures of normal and tumor cells. Decellularized biomatrix was prepared from animals’ kidneys, urethra, lungs, heart, and liver by two decellularization methods: perfusion in a bioreactor system and immersion-agitation on an orbital shaker with the use of various detergents (SDS, Triton X-100) in different concentrations and freezing. Acellular scaffolds and tissue engineered constructs have been characterized and compared using morphological methods. Models using decellularized matrix have certain advantages, such as maintaining native extracellular matrix properties and biomimetic microenvironment for cancer cells; compatibility with multiple cell types for cell culture and drug screening; utilization to culture patient-derived cells in vitro to evaluate different anticancer therapeutics for developing personalized medicines.

Keywords: 3D models, decellularization, drug discovery, drug toxicity, scaffolds, spheroids, tissue engineering

Procedia PDF Downloads 301

Authors: Lovesh Goyal, Pushkar Dave, Prajyot Jadhav, GonnaYaswanth, Sakshi Giri, Sahil Dharme, Rushika Joshi, Rishabh Verma, Shital Chiddarwar

Abstract:

With the rising need for human-robot interaction, researchers have proposed and tested multiple models with varying degrees of success. A few of these models performed on aerial platforms are commonly known as Tethered Aerial Systems. These aerial vehicles may be powered continuously by a tether cable, which addresses the predicament of the short battery life of quadcopters. This system finds applications to minimize humanitarian efforts for industrial, medical, agricultural, and service uses. However, a significant challenge in employing such systems is that it necessities attaining smooth and secure robot-human interaction while ensuring that the forces from the tether remain within the standard comfortable range for the humans. To tackle this problem, a hybrid control method that could switch between two control techniques: constant control input and the steady-state solution, is implemented. The constant control approach is implemented when a person is far from the target location, and error is thought to be eventually constant. The controller switches to the steady-state approach when the person reaches within a specific range of the goal position. Both strategies take into account human velocity feedback. This hybrid technique enhances the outcomes by assisting the person to reach the desired location while decreasing the human's unwanted disturbance throughout the process, thereby keeping the interaction between the robot and the subject smooth.

Keywords: unmanned aerial vehicle, tethered system, physical human-robot interaction, hybrid control

Procedia PDF Downloads 98

Authors: Sumit Sen, Sohan Khedekar, Umang Shinde, Shivam Bhargava

Abstract:

This study has been undertaken to investigate whether the deep learning models are able to predict the future stock prices by training the model with the historical stock price data. Since this work required time series analysis, various models are present today to perform time series analysis such as Recurrent Neural Network LSTM, ARIMA and Facebook Prophet. Applying these models the movement of stock price of stocks are predicted and also tried to provide the future prediction of the stock price of a stock. Final product will be a stock price prediction web application that is developed for providing the user the ease of analysis of the stocks and will also provide the predicted stock price for the next seven days.

Keywords: Autoregressive Integrated Moving Average, Deep Learning, Long Short Term Memory, Time-series

Procedia PDF Downloads 143

Authors: E. Karami, M. Bohloul, P. Najmadi

Abstract:

The superconducting system is a suitable system for quantum computers. Quantum entanglement is a fundamental phenomenon that is key to the power of quantum computers. Quantum entanglement has been studied in different superconducting systems. In this paper, we are investigating a superconducting two-qubit system as a macroscopic system. These systems include two coupled Quantronium circuits. We calculate quantum entanglement and thermalization for system evolution and compare them. We observe, thermalization and entanglement have different behavior, and equilibrium thermal state has maximum entanglement.

Keywords: macroscopic system, quantum entanglement, thermalization, superconducting system

Procedia PDF Downloads 156

Authors: Toktam Khatibi

Abstract:

Self-supervised learning (SSL) includes machine learning models that are trained on one aspect and/or one part of the input to learn other aspects and/or part of it. SSL models are divided into two different categories, including pre-text task-based models and contrastive learning ones. Pre-text tasks are some auxiliary tasks learning pseudo-labels, and the trained models are further fine-tuned for downstream tasks. However, one important disadvantage of SSL using pre-text task solving is defining an appropriate pre-text task for each image dataset with a variety of image modalities. Therefore, it is required to design an appropriate pretext task automatically for each dataset and each downstream task. To the best of our knowledge, the automatic designing of pretext tasks for image analysis has not been considered yet. In this paper, we present a framework based on In-context learning that describes each task based on its input and output data using a pre-trained image transformer. Our proposed method combines the input image and its learned description for optimizing the pre-text task design and its hyper-parameters using Meta-learning models. The representations learned from the pre-text tasks are fine-tuned for solving the downstream tasks. We demonstrate that our proposed framework outperforms the compared ones on unseen tasks and image modalities in addition to its superior performance for previously known tasks and datasets.

Keywords: in-context learning (ICL), meta learning, self-supervised learning (SSL), vision-language domain, transformers

Procedia PDF Downloads 81

Authors: Gerardo Ayala-Jaimes, Gilberto Gonzalez-Avalos, Allen A. Castillo, Alejandra Jimenez

Abstract:

The modeling of a single-phase cycloconverter in Bond Graph is presented, which includes an alternating current power supply, hybrid dynamics, switch control, and resistive load; this approach facilitates the integration of systems across different energy domains and structural analysis. Cycloconverters, used in motor control, demonstrate the viability of graphical modeling. The use of Bonds is proposed to model the hybrid interaction of the system, and the results are displayed through simulations using 20Sim and Multisim software. The motivation behind developing these models with a graphical approach is to design and build low-cost energy converters, thereby making the main contribution of this document the modeling and simulation of a single-phase cycloconverter.

Keywords: bond graph, hybrid system, rectifier, cycloconverter, modelling

Procedia PDF Downloads 40

Authors: Paul Ojeaga

Abstract:

Can the level of innovation use drive un-validated business models across regions? To what extent does industrial sector attractiveness drive firm’s success across regions at the time of start-up? This study examines the role of innovation on start-up success in six regions of the world (namely Sub Saharan Africa, the Middle East and North Africa, Latin America, South East Asia Pacific, the European Union and the United States representing North America) using macroeconomic variables. While there have been studies using firm level data, results from such studies are not suitable for national policy decisions. The need to drive a regional innovation policy also begs for an answer, therefore providing room for this study. Results using dynamic panel estimation show that innovation counts in the early infancy stage of new business life cycle. The results are robust even after controlling for time fixed effects and the study present variance-covariance estimation robust standard errors.

Keywords: industrial economics, un-validated business models, scalable models, entrepreneurship

Procedia PDF Downloads 283

Authors: Eugene Stepanov, Arkadi Ponossov

Abstract:

Many mathematical models used in biological and other applications are ill-posed. The reason for that is the nature of differential equations, where the nonlinearities are assumed to be step functions, which is done to simplify the analysis. Prominent examples are switched systems arising from gene regulatory networks and neural field equations. This simplification leads, however, to theoretical and numerical complications. In the presentation, it is proposed to apply the theory of hybrid feedback controls to regularize the problem. Roughly speaking, one attaches a finite state control (‘automaton’), which follows the trajectories of the original system and governs its dynamics at the points of ill-posedness. The construction of the automaton is based on the classification of the attractors of the specially designed adjoint dynamical system. This ‘hybridization’ is shown to regularize the original switched system and gives rise to efficient hybrid numerical schemes. Several examples are provided in the presentation, which supports the suggested analysis. The method can be of interest in other applied fields, where differential equations contain step-like nonlinearities.

Keywords: hybrid feedback control, ill-posed problems, singular perturbation analysis, step-like nonlinearities

Procedia PDF Downloads 247

Authors: Prajwal Prakash Vasisht, Sharath Rajamurthy, Nishanth Dara

Abstract:

In a supervised machine learning approach, metrics such as precision, accuracy, and coverage can be calculated using ground truth labels to help in model tuning, evaluation, and selection. In an unsupervised setting, however, where the data has no ground truth, there are few interpretable metrics that can guide us to do the same. Our approach creates a framework to adapt the Intersection over Union metric, referred to as Adapted IoU, usually used to evaluate supervised learning models, into the unsupervised domain, which solves the problem by factoring in subject matter expertise and intuition about the ideal output from the model. This metric essentially provides a scale that allows us to compare the performance across numerous unsupervised models or tune hyper-parameters and compare different versions of the same model.

Keywords: general metric, unsupervised learning, classification, intersection over union

Procedia PDF Downloads 50

Authors: Hang Yang, Jiahao Liu, Jichao Li, Kewei Yang, Minghao Li, Bingfeng Ge

Abstract:

The system-of-systems (SoS) are utilized to characterize networks formed by integrating individual complex systems that demonstrate interdependence and interconnectedness. Research on the disintegration issue in SoS is significant in improving network survivability, maintaining network security, and optimizing SoS architecture. Accordingly, this study proposes an integrated framework called resilience-oriented disintegration in SoS (SoSRD), for modeling and solving the issue of SoS disintegration. Firstly, a SoS disintegration index (SoSDI) is presented to evaluate the disintegration effect of SoS. This index provides a practical description of the disintegration process and is the first integration of the network disintegration model and resilience models. Subsequently, we propose a resilience-oriented disintegration method based on reinforcement learning (RDRL) to enhance the efficiency of SoS disintegration. This method is not restricted by the problem scenario as well as considering the coexistence of disintegration (node/link removal) and recovery (node/link addition) during the process of SoS disintegration. Finally, the effectiveness and superiority of the proposed SoSRD are demonstrated through a case study. We demonstrate that our proposed framework outperforms existing indexes and methods in both node and link disintegration scenarios, providing a fresh perspective on network disintegration. The findings provide crucial insights into dismantling harmful SoS and designing a more resilient SoS.

Keywords: system-of-systems, disintegration index, resilience, reinforcement learning

Procedia PDF Downloads 18

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 341

Authors: Amjaad Alsalamah, Liyakathunsia Syed

Abstract:

Transportation is an essential need for many people to go to their work, school, and home. In particular, the main common method inside many cities is to drive the car. Driving a car can be an easy job to reach the destination and load all stuff in a reasonable time. However, deciding to find a parking lot for a car can take a long time using the traditional system that can issue a paper ticket for each customer. The old system cannot guarantee a parking lot for all customers. Also, payment methods are not always available, and many customers struggled to find their car among a numerous number of cars. As a result, this research focuses on providing an online smart parking system in order to save time and budget. This system provides a flexible management system for both parking owner and customers by receiving all request via the online system and it gets an accurate result for all available parking and its location.

Keywords: smart parking system, IoT, tracking system, process model, cost, time

Procedia PDF Downloads 337

Authors: Kostas Kouvaris, Anastasia Eleftheriou, Georgios A. Sarantitis, Apostolos Chondronasios

Abstract:

To achieve the objective of almost zero carbon energy solutions by 2050, the EU needs to accelerate the development of integrated, highly efficient and environmentally friendly solutions. In this direction, district heating and cooling (DHC) emerges as a viable and more efficient alternative to conventional, decentralized heating and cooling systems, enabling a combination of more efficient renewable and competitive energy supplies. In this paper, we develop a forecasting tool for near real-time local weather and thermal energy demand predictions for an entire DHC network. In this fashion, we are able to extend the functionality and to improve the energy efficiency of the DHC network by predicting and adjusting the heat load that is distributed from the heat generation plant to the connected buildings by the heat pipe network. Two case-studies are considered; one for Vransko, Slovenia and one for Montpellier, France. The data consists of i) local weather data, such as humidity, temperature, and precipitation, ii) weather forecast data, such as the outdoor temperature and iii) DHC operational parameters, such as the mass flow rate, supply and return temperature. The external temperature is found to be the most important energy-related variable for space conditioning, and thus it is used as an external parameter for the energy demand models. For the development of the forecasting tool, we use state-of-the-art deep neural networks and more specifically, recurrent networks with long-short-term memory cells, which are able to capture complex non-linear relations among temporal variables. Firstly, we develop models to forecast outdoor temperatures for the next 24 hours using local weather data for each case-study. Subsequently, we develop models to forecast thermal demand for the same period, taking under consideration past energy demand values as well as the predicted temperature values from the weather forecasting models. The contributions to the scientific and industrial community are three-fold, and the empirical results are highly encouraging. First, we are able to predict future thermal demand levels for the two locations under consideration with minimal errors. Second, we examine the impact of the outdoor temperature on the predictive ability of the models and how the accuracy of the energy demand forecasts decreases with the forecast horizon. Third, we extend the relevant literature with a new dataset of thermal demand and examine the performance and applicability of machine learning techniques to solve real-world problems. Overall, the solution proposed in this paper is in accordance with EU targets, providing an automated smart energy management system, decreasing human errors and reducing excessive energy production.

Keywords: machine learning, LSTMs, district heating and cooling system, thermal demand

Procedia PDF Downloads 143

Authors: Rene Hellmuth, Jorg Frohnmayer

Abstract:

The requirements of the factory planning and the building concerned have changed in the last years. Factory planning has the task of designing products, plants, processes, organization, areas, and the building of a factory. Regular restructuring gains more importance in order to maintain the competitiveness of a factory. Even today, the methods and process models used in factory planning are predominantly based on the classical planning principles of Schmigalla, Aggteleky and Kettner, which, however, are not specifically designed for reorganization. In addition, they are designed for a largely static environmental situation and a manageable planning complexity as well as for medium to long-term planning cycles with a low variability of the factory. Existing approaches already regard factory planning as a continuous process that makes it possible to react quickly to adaptation requirements. However, digital factory models are not yet used as a source of information for building data. Approaches which consider building information modeling (BIM) or digital factory models in general either do not refer to factory conversions or do not yet go beyond a concept. This deficit can be further substantiated. A method for factory conversion planning using a current digital building model is lacking. A corresponding approach must take into account both the existing approaches to factory planning and the use of digital factory models in practice. A literature review will be conducted first. In it, approaches to classic factory planning and approaches to conversion planning are examined. In addition, it will be investigated which approaches already contain digital factory models. In the second step, an approach is presented how digital factory models based on building information modeling can be used as a basis for augmented reality tablet applications. This application is suitable for construction sites and provides information on the costs and time required for conversion variants. Thus a fast decision making is supported. In summary, the paper provides an overview of existing factory planning approaches and critically examines the use of digital tools. Based on this preliminary work, an approach is presented, which suggests the sensible use of digital factory models for decision support in the case of conversion variants of the factory building. The augmented reality application is designed to summarize the most important information for decision-makers during a reconstruction process.

Keywords: augmented reality, digital factory model, factory planning, restructuring

Procedia PDF Downloads 138

Authors: Igor Filikhin, Vladimir M. Suslov, Roman Ya. Kezerashvili, Branislav Vlahivic

Abstract:

The mass-polarization term of the three-body kinetic energy operator is evaluated for different systems which include two identical particles: A+A+B. The term has to be taken into account for the analysis of AB- and AA-interactions based on experimental data for two- and three-body ground state energies. In this study, we present three-body calculations within the framework of a potential model for the kaonic clusters K−K−p and ppK−, nucleus 3H and hypernucleus 6 ΛΛHe. The systems are well clustering as A+ (A+B) with a ground state energy E2 for the pair A+B. The calculations are performed using the method of the Faddeev equations in configuration space. The phenomenological pair potentials were used. We show a correlation between the mass ratio mA/mB and the value δB of the mass-polarization term. For bosonic-like systems, this value is defined as δB = 2E2 − E3, where E3 is three-body energy when VAA = 0. For the systems including three particles with spin(isospin), the models with average AB-potentials are used. In this case, the Faddeev equations become a scalar one like for the bosonic-like system αΛΛ. We show that the additional energy conected with the mass-polarization term can be decomposite to a sum of the two parts: exchenge related and reduced mass related. The state of the system can be described as the following: the particle A1 is bound within the A + B pair with the energy E2, and the second particle A2 is bound with the pair with the energy E3 − E2. Due to the identity of A particles, the particles A1 and A2 are interchangeable in the pair A + B. We shown that the mass polarization δB correlates with a type of AB potential using the system αΛΛ as an example.

Keywords: three-body systems, mass polarization, Faddeev equations, nuclear interactions

Procedia PDF Downloads 377

Authors: Meriem Mossaddek, El Mehdi Laadissi, El Mehdi Loualid, Chouaib Ennawaoui, Sohaib Bouzaid, Abdelowahed Hajjaji

Abstract:

An electrochemical system is a subset of mechatronic systems that includes a wide variety of batteries and nickel-cadmium, lead-acid batteries, and lithium-ion. Those structures have several non-linear behaviors and uncertainties in their running range. This paper studies an effective technique for modeling Lithium-Ion (Li-Ion) batteries using a Nonlinear Auto-Regressive model with exogenous input (NARX). The Artificial Neural Network (ANN) is trained to employ the data collected from the battery testing process. The proposed model is implemented on a Li-Ion battery cell. Simulation of this model in MATLAB shows good accuracy of the proposed model.

Keywords: lithium-ion battery, neural network, energy storage, battery model, nonlinear models

Procedia PDF Downloads 117

Authors: Aleksei Samarin, Artyom Nazarenko, Valentin Malykh

Abstract:

Image enhancement is becoming more and more popular, especially on mobile devices. Nowadays, it is a common approach to enhance an image using a convolutional neural network (CNN). Such a network should be of significant size; otherwise, a possibility for the artifacts to occur is overgrowing. The existing large CNNs are computationally expensive, which could be crucial for mobile devices. Another important flaw of such models is they are poorly interpretable. There is another approach to image enhancement, namely, the usage of predefined filters in combination with the prediction of their applicability. We present an approach following this paradigm, which outperforms both existing CNN-based and filter-based approaches in the image enhancement task. It is easily adaptable for mobile devices since it has only 47 thousand parameters. It shows the best SSIM 0.919 on RANDOM250 (MIT Adobe FiveK) among small models and is thrice faster than previous models.

Keywords: universal filter, image enhancement, neural networks, computer vision

Procedia PDF Downloads 102

Authors: Rishabh Nagpal, Riya Uchagaonkar, Venkata Naga Narasimha Ashish Mernedi, Ahmed Hambaba

Abstract:

The rapid evolution of technology in the communication sector continually seeks to bridge the gap between different communities, notably between the deaf community and the hearing world. This project develops a comprehensive American Sign Language (ASL) recognition system, leveraging the advanced capabilities of convolutional neural networks (CNNs) and vision transformers (ViTs) to interpret and translate ASL in real-time. The primary objective of this system is to provide an effective communication tool that enables seamless interaction through accurate sign language interpretation. The architecture of the proposed system integrates dual networks -VGG16 for precise spatial feature extraction and vision transformers for contextual understanding of the sign language gestures. The system processes live input, extracting critical features through these sophisticated neural network models, and combines them to enhance gesture recognition accuracy. This integration facilitates a robust understanding of ASL by capturing detailed nuances and broader gesture dynamics. The system is evaluated through a series of tests that measure its efficiency and accuracy in real-world scenarios. Results indicate a high level of precision in recognizing diverse ASL signs, substantiating the potential of this technology in practical applications. Challenges such as enhancing the system’s ability to operate in varied environmental conditions and further expanding the dataset for training were identified and discussed. Future work will refine the model’s adaptability and incorporate haptic feedback to enhance the interactivity and richness of the user experience. This project demonstrates the feasibility of an advanced ASL recognition system and lays the groundwork for future innovations in assistive communication technologies.

Keywords: sign language, computer vision, vision transformer, VGG16, CNN

Procedia PDF Downloads 44