Search results for: asynchronous input

Authors: Souvik Phadikar, Nidul Sinha, Rajdeep Ghosh

Abstract:

In brainwaves research using electroencephalogram (EEG) signals, finding the most relevant and effective feature set for identification of activities in the human brain is a big challenge till today because of the random nature of the signals. The feature extraction method is a key issue to solve this problem. Finding those features that prove to give distinctive pictures for different activities and similar for the same activities is very difficult, especially for the number of activities. The performance of a classifier accuracy depends on this quality of feature set. Further, more number of features result in high computational complexity and less number of features compromise with the lower performance. In this paper, a novel idea of the selection of optimal feature set using a heuristically optimized deep autoencoder is presented. Using various feature extraction methods, a vast number of features are extracted from the EEG signals and fed to the autoencoder deep neural network. The autoencoder encodes the input features into a small set of codes. To avoid the gradient vanish problem and normalization of the dataset, a meta-heuristic search algorithm is used to minimize the mean square error (MSE) between encoder input and decoder output. To reduce the feature set into a smaller one, 4 hidden layers are considered in the autoencoder network; hence it is called Heuristically Optimized Deep Autoencoder (HO-DAE). In this method, no features are rejected; all the features are combined into the response of responses of the hidden layer. The results reveal that higher accuracy can be achieved using optimal reduced features. The proposed HO-DAE is also compared with the regular autoencoder to test the performance of both. The performance of the proposed method is validated and compared with the other two methods recently reported in the literature, which reveals that the proposed method is far better than the other two methods in terms of classification accuracy.

Keywords: autoencoder, brainwave signal analysis, electroencephalogram, feature extraction, feature selection, optimization

Procedia PDF Downloads 97

Authors: Zineb Jibraili, Said Ouhadi, Jorge Arana

Abstract:

Introduction: Organizational performance is recognized by some theorists as one-dimensional concept, and by others as multidimensional. This concept, which is already difficult to apply in traditional companies, is even harder to identify, to measure and to manage when voluntary organizations are concerned, essentially because of the complexity of that form of organizations such as sport clubs who are characterized by the multiple goals and multiple constituencies. Indeed, the new culture of professionalization and modernization around organizational performance emerges new pressures from the state, sponsors, members and other stakeholders which have required these sport organizations to become more performance oriented, or to build their capacity in order to better manage their organizational performance. The evaluation of performance can be made by evaluating the input (e.g. available resources), throughput (e.g. processing of the input) and output (e.g. goals achieved) of the organization. In non-profit organizations (NPOs), questions of performance have become increasingly important in the world of practice. To our knowledge, most of studies used the same methods to evaluate the performance in NPSOs, but no recent study has proposed a club-specific model. Based on a review of the studies that specifically addressed the organizational performance (and effectiveness) of NPSOs at operational level, the present paper aims to provide a multidimensional framework in order to understand, analyse and measure organizational performance of sport clubs. This paper combines all dimensions founded in literature and chooses the most suited of them to our model that we will develop in Moroccan sport clubs case. Method: We propose to implicate our unified model of evaluating organizational performance that takes into account all the limitations found in the literature. On a sample of Moroccan sport clubs ‘Football, Basketball, Handball and Volleyball’, for this purpose we use a qualitative study. The sample of our study comprises data from sport clubs (football, basketball, handball, volleyball) participating on the first division of the professional football league over the period from 2011 to 2016. Each football club had to meet some specific criteria in order to be included in the sample: 1. Each club must have full financial data published in their annual financial statements, audited by an independent chartered accountant. 2. Each club must have sufficient data. Regarding their sport and financial performance. 3. Each club must have participated at least once in the 1st division of the professional football league. Result: The study showed that the dimensions that constitute the model exist in the field with some small modifications. The correlations between the different dimensions are positive. Discussion: The aim of this study is to test the unified model emerged from earlier and narrower approaches for Moroccan case. Using the input-throughput-output model for the sketch of efficiency, it was possible to identify and define five dimensions of organizational effectiveness applied to this field of study.

Keywords: organisational performance, model multidimensional, evaluation organizational performance, sport clubs

Procedia PDF Downloads 298

Authors: Meena Agrawal, Chaitanya P. Agrawal

Abstract:

The power systems are transforming and becoming smarter with innovations in technologies to enable embark simultaneously upon the sustainable energy needs, rising environmental concerns, economic benefits and quality requirements. The advantages provided by inter-connection of renewable energy resources are becoming more viable and dependable with the smart controlling technologies. The limitation of most renewable resources have their diversity and intermittency causing problems in power quality, grid stability, reliability, security etc. is being cured by these efforts. A necessitate of optimal energy management by intelligent Micro-Grids at the distribution end of the power system has been accredited to accommodate sustainable renewable Distributed Energy Resources on large scale across the power grid. All over the world Smart Grids are emerging now as foremost concern infrastructure upgrade programs. The hardware setup includes NI cRIO 9022, Compact Reconfigurable Input Output microcontroller board connected to the PC on a LAN router with three hardware modules. The Real-Time Embedded Controller is reconfigurable controller device consisting of an embedded real-time processor controller for communication and processing, a reconfigurable chassis housing the user-programmable FPGA, Eight hot-swappable I/O modules, and graphical LabVIEW system design software. It has been employed for signal analysis, controls and acquisition and logging of the renewable sources with the LabVIEW Real-Time applications. The employed cRIO chassis controls the timing for the module and handles communication with the PC over the USB, Ethernet, or 802.11 Wi-Fi buses. It combines modular I/O, real-time processing, and NI LabVIEW programmable. In the presented setup, the Analog Input Module NI 9205 five channels have been used for input analog voltage signals from renewable energy sources and NI 9227 four channels have been used for input analog current signals of the renewable sources. For switching actions based on the programming logic developed in software, a module having Electromechanical Relays (single-pole single throw) with 4-Channels, electrically isolated and LED indicating the state of that channel have been used for isolating the renewable Sources on fault occurrence, which is decided by the logic in the program. The module for Ethernet based Data Acquisition Interface ENET 9163 Ethernet Carrier, which is connected on the LAN Router for data acquisition from a remote source over Ethernet also has the module NI 9229 installed. The LabVIEW platform has been employed for efficient data acquisition, monitoring and control. Control logic utilized in program for operation of the hardware switching Related to Fault Relays has been portrayed as a flowchart. A communication system has been successfully developed amongst the sources and loads connected on different computers using Hypertext transfer protocol, HTTP or Ethernet Local Stacked area Network TCP/IP protocol. There are two main I/O interfacing clients controlling the operation of the switching control of the renewable energy sources over internet or intranet. The paper presents experimental results of the briefed setup for intelligent control of the micro-grid for renewable energy sources, besides the control of Micro-Grid with data acquisition and control hardware based on a microcontroller with visual program developed in LabVIEW.

Keywords: data acquisition and control, LabVIEW, microcontroller cRIO, Smart Micro-Grid

Procedia PDF Downloads 309

Authors: Liliia N. Butymova, Vladimir Y. Modorsky, Nikolai A. Shevelev

Abstract:

Prediction of vibration processes in gas transmittal units (GTU) is an urgent problem. Despite numerous scientific publications on the problem of vibrations in general, there are not enough works concerning FSI-modeling interaction processes between several deformable blades in gas-dynamic flow. Since it is very difficult to solve the problem in full scope, with all factors considered, a unidirectional dynamic coupled 1FSI model is suggested for use at the first stage, which would include, from symmetry considerations, two blades, which might be considered as the first stage of solving more general bidirectional problem. ANSYS CFX programmed multi-processor was chosen as a numerical computation tool. The problem was solved on PNRPU high-capacity computer complex. At the first stage of the study, blades were believed oscillating with the same frequency, although oscillation phases could be equal and could be different. At that non-stationary gas-dynamic forces distribution over the blades surfaces is calculated in run of simulation experiment. Oscillations in the “gas — structure” dynamic system are assumed to increase if the resultant of these gas-dynamic forces is in-phase with blade oscillation, and phase shift (φ=0). Provided these oscillation occur with phase shift, then oscillations might increase or decrease, depending on the phase shift value. The most important results are as follows: the angle of phase shift in inter-blade oscillation and the gas-dynamic force depends on the flow velocity, the specific inter-blade gap, and the shaft rotation speed; a phase shift in oscillation of adjacent blades does not always correspond to phase shift of gas-dynamic forces affecting the blades. Thus, it was discovered, that asynchronous oscillation of blades might cause either attenuation or intensification of oscillation. It was revealed that clocking effect might depend not only on the mutual circumferential displacement of blade rows and the gap between the blades, but also on the blade dynamic deformation nature.

Keywords: aeroelasticity, ANSYS CFX, oscillation, phase shift, clocking effect, vibrations

Procedia PDF Downloads 250

Authors: Ginger Egberts, Marianne Schaaphok, Fred Vermolen, Paul van Zuijlen

Abstract:

A few years ago, a promising morphoelastic model was developed for the simulation of contraction formation after burn injuries. Contraction can lead to a serious reduction in physical mobility, like a reduction in the range-of-motion of joints. If this is the case in a healing burn wound, then this is referred to as a contracture that needs medical intervention. The morphoelastic model consists of a set of partial differential equations describing both a chemical part and a mechanical part in dermal wound healing. These equations are solved with the numerical finite element method (FEM). In this method, many calculations are required on each of the chosen elements. In general, the more elements, the more accurate the solution. However, the number of elements increases rapidly if simulations are performed in 2D and 3D. In that case, it not only takes longer before a prediction is available, the computation also becomes more expensive. It is therefore important to investigate alternative possibilities to generate the same results, based on the input parameters only. In this study, a surrogate neural network has been designed to mimic the results of the one-dimensional morphoelastic model. The neural network generates predictions quickly, is easy to implement, and there is freedom in the choice of input and output. Because a neural network requires extensive training and a data set, it is ideal that the one-dimensional FEM code generates output quickly. These feed-forward-type neural network results are very promising. Not only can the network give faster predictions, but it also has a performance of over 99%. It reports on the relative surface area of the wound/scar, the total strain energy density, and the evolutions of the densities of the chemicals and mechanics. It is, therefore, interesting to investigate the applicability of a neural network for the two- and three-dimensional morphoelastic model for contraction after burn injuries.

Keywords: biomechanics, burns, feasibility, feed-forward NN, morphoelasticity, neural network, relative surface area wound

Procedia PDF Downloads 37

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 175

Authors: Vishal V. R. Nandigana, Mohammad Heiranian, Narayana R. Aluru

Abstract:

Graphene material has found tremendous applications in water desalination, DNA sequencing and energy storage. Multiple nanopores are etched to create opening for water desalination and energy storage applications. The nanopores created are of the order of 3-5 nm allowing multiple ions to transport through the pore. In this paper, we present for the first time, molecular dynamics study of single ion transport, where only one ion passes through the graphene nanopore. The diameter of the graphene nanopore is of the same order as the hydration layers formed around each ion. Analogous to single electron transport resulting from ionic transport is observed for the first time. The current-voltage characteristics of such a device are similar to single electron transport in quantum dots. The current is blocked until a critical voltage, as the ions are trapped inside a hydration shell. The trapped ions have a high energy barrier compared to the applied input electrical voltage, preventing the ion to break free from the hydration shell. This region is called “Coulomb blockade region”. In this region, we observe zero transport of ions inside the nanopore. However, when the electrical voltage is beyond the critical voltage, the ion has sufficient energy to break free from the energy barrier created by the hydration shell to enter into the pore. Thus, the input voltage can control the transport of the ion inside the nanopore. The device therefore acts as a binary storage unit, storing 0 when no ion passes through the pore and storing 1 when a single ion passes through the pore. We therefore postulate that the device can be used for fluidic computing applications in chemistry and biology, mimicking a computer. Furthermore, the trapped ion stores a finite charge in the Coulomb blockade region; hence the device also acts a super capacitor.

Keywords: graphene nanomembrane, single ion transport, Coulomb blockade, nanofluidics

Procedia PDF Downloads 305

Authors: Wei Zhao

Abstract:

The pandemic crisis disrupted normal classroom practices so that the constraints of the traditional practice became apparent. This turns out to be new opportunities for technology-based learning and teaching. However, how the technology supports the preschool teachers go through this sudden crisis and how preschool teachers conceived of the use of technology, appropriate and design technological artifacts as a mediator of knowledge construction in order to suit young children’s literacy level are rarely explored. This study addresses these issues by looking at the influence of a web-supported teacher community on changes/shifts in preschool teachers’ epistemological beliefs and practices. This teachers’ professional development community was formulated before the pandemic time and developed virtually throughout the home-based learning caused by Covid-19. It served as a virtual and asynchronous community for those teachers to collaboratively plan for and conduct online lessons using the knowledge-building approach for the purpose of sustaining children’s learning curiosity and opening up new learning opportunities during the lock-down period. The knowledge-building approach helps to increase teachers’ collective responsibility to collaboratively work on shared educational goals in the teacher community and awareness of noticing new ideas or innovations in their classroom. Based on the data collected across five months during and after the lock-down period and the activity theory, results show a dynamic interplay between the evolution of the community culture, the growth of teacher community and teachers’ identity transformation and professional development. Technology is useful in this regard not only because it transforms the geographical distance and new gathering guidelines after the outbreak of pandemic into new ways of communal communication and collaboration. More importantly, while teachers selected, monitored and adapted the technology, it acts as a catalyst for changes in teachers’ old teaching practices and epistemological dispositions.

Keywords: activity theory, changes in epistemology and practice, knowledge building, web-based teachers’ professional development community

Procedia PDF Downloads 165

Authors: Xueyan Hu, Liwen Chen, Weilin He, Sujie Peng

Abstract:

Writing is an important but challenging skill For English language learners. Due to the small amount of time allocated for writing classes at schools, students have relatively few opportunities to practice writing in the classroom. While the practice of integrating listening and speaking activates with writing instruction has been used for adult English language learners, its application for young English learners has seldom been examined due to the challenge of listening and speaking activities for young English language learners. The study attempted to integrating integrating listening and speaking activities with writing instruction for middle school English language learners so as to improving their writing achievements and writing abilities in terms of the word use, coherence, and complexity in their writings. Guided by Gagne's information processing learning theory and memetics, this study conducted a 8-week writing instruction with an experimental class (n=44) and a control class (n=48) . Students in the experimental class participated in a series of listening and retelling activities about a writing sample the teacher used for writing instruction during each period of writing class. Students in the control class were taught traditionally with teachers’ direction instruction using the writing sample. Using the ANCOVA analysis of the scores of students’ writing, word-use, Chinese-English translation and the text structure, this study showed that the experimental writing instruction can significantly improve students’ writing performance. Compared with the students in the control class, the students in experimental class had significant better performance in word use and complexity in their essays. This study provides useful enlightenment for the teaching of English writing for middle school English language learners. Teachers can skillfully use information technology to integrate listening, speaking, and writing teaching, considering students’ language input and output. Teachers need to select suitable and excellent composition templates for students to ensure their high-quality language input.

Keywords: wring instruction, retelling, English language learners, listening and speaking

Procedia PDF Downloads 59

Authors: Jack Nash, Chris Simpson, Holly Hurn, Ronel Terblanche, Alan Mistlin

Abstract:

There is an increasing incidence of mild traumatic brain injury (mTBI) cases throughout sport and with this, a growing interest from governing bodies to ensure these are managed appropriately and player welfare is prioritised. The Berlin consensus statement on concussion in sport recommends a multidisciplinary approach when managing those patients who do not have full resolution of mTBI symptoms. There are as of yet no standardised guideline to follow in the treatment of complex cases mTBI in athletes. The aim of this project was to analyse the outcomes, both clinical and vocational, of all patients admitted to the mild Traumatic Brain Injury (mTBI) service at the UK’s Defence Military Rehabilitation Centre Headley Court between 1st June 2008 and 1st February 2017, as a result of a sport induced injury, and evaluate potential predictive indicators of outcome. Patients were identified from a database maintained by the mTBI service. Clinical and occupational outcomes were ascertained from medical and occupational employment records, recorded prospectively, at time of discharge from the mTBI service. Outcomes were graded based on the vocational independence scale (VIS) and clinical documentation at discharge. Predictive indicators including referral time, age at time of injury, previous mental health diagnosis and a financial claim in place at time of entry to service were assessed using logistic regression. 45 Patients were treated for sport-related mTBI during this time frame. Clinically 96% of patients had full resolution of their mTBI symptoms after input from the mTBI service. 51% of patients returned to work at their previous vocational level, 4% had ongoing mTBI symptoms, 22% had ongoing physical rehabilitation needs, 11% required mental health input and 11% required further vestibular rehabilitation. Neither age, time to referral, pre-existing mental health condition nor compensation seeking had a significant impact on either vocational or clinical outcome in this population. The vast majority of patients reviewed in the mTBI clinic had persistent symptoms which could not be managed in primary care. A consultant-led, multidisciplinary approach to the diagnosis and management of mTBI has resulted in excellent clinical outcomes in these complex cases. High levels of symptom resolution suggest that this referral and treatment pathway is successful and is a model which could be replicated in other organisations with consultant led input. Further understanding of both predictive and individual factors would allow clinicians to focus treatments on those who are most likely to develop long-term complications following mTBI. A consultant-led, multidisciplinary service ensures a large number of patients will have complete resolution of mTBI symptoms after sport-related mTBI. Further research is now required to ascertain the key predictive indicators of outcome following sport-related mTBI.

Keywords: brain injury, concussion, neurology, rehabilitation, sports injury

Procedia PDF Downloads 137

Authors: A. T. Al-Isawi, P. E. F. Collins

Abstract:

The behaviour of structures exposed to fire after an earthquake is not a new area of engineering research, but there remain a number of areas where further work is required. Such areas relate to the way in which seismic excitation is applied to a structure, taking into account the effect of soil-structure interaction (SSI) and the method of analysis, in addition to identifying the excitation load properties. The selection of earthquake data input for use in nonlinear analysis and the method of analysis are still challenging issues. Thus, realistic artificial ground motion input data must be developed to certify that site properties parameters adequately describe the effects of the nonlinear inelastic behaviour of the system and that the characteristics of these parameters are coherent with the characteristics of the target parameters. Conversely, ignoring the significance of some attributes, such as frequency content, soil site properties and earthquake parameters may lead to misleading results, due to the misinterpretation of required input data and the incorrect synthesise of analysis hypothesis. This paper presents a study of the post-earthquake fire (PEF) performance of a multi-storey steel-framed building resting on soft clay, taking into account the effects of the nonlinear inelastic behaviour of the structure and soil, and the soil-structure interaction (SSI). Structures subjected to an earthquake may experience various levels of damage; the geometrical damage, which indicates the change in the initial structure’s geometry due to the residual deformation as a result of plastic behaviour, and the mechanical damage which identifies the degradation of the mechanical properties of the structural elements involved in the plastic range of deformation. Consequently, the structure presumably experiences partial structural damage but is then exposed to fire under its new residual material properties, which may result in building failure caused by a decrease in fire resistance. This scenario would be more complicated if SSI was also considered. Indeed, most earthquake design codes ignore the probability of PEF as well as the effect that SSI has on the behaviour of structures, in order to simplify the analysis procedure. Therefore, the design of structures based on existing codes which neglect the importance of PEF and SSI can create a significant risk of structural failure. In order to examine the criteria for the behaviour of a structure under PEF conditions, a two-dimensional nonlinear elasto-plastic model is developed using ABAQUS software; the effects of SSI are included. Both geometrical and mechanical damages have been taken into account after the earthquake analysis step. For comparison, an identical model is also created, which does not include the effects of soil-structure interaction. It is shown that damage to structural elements is underestimated if SSI is not included in the analysis, and the maximum percentage reduction in fire resistance is detected in the case when SSI is included in the scenario. The results are validated using the literature.

Keywords: Abaqus Software, Finite Element Analysis, post-earthquake fire, seismic analysis, soil-structure interaction

Procedia PDF Downloads 107

Authors: Kuo-Chun Chien, Chia-Hui Chang, Ren-Der Sun

Abstract:

Legal Judgment Prediction (LJP) is a subtask for legal AI. Its main purpose is to use the facts of a case to predict the judgment result. In Taiwan's criminal procedure, when prosecutors complete the investigation of the case, they will decide whether to prosecute the suspect and which article of criminal law should be used based on the facts and evidence of the case. In this study, we collected 305,240 indictments from the public inquiry system of the procuratorate of the Ministry of Justice, which included 169 charges and 317 articles from 21 laws. We take the crime facts in the indictments as the main input to jointly learn the prediction model for law source, article, and charge simultaneously based on the pre-trained Bert model. For single article cases where the frequency of the charge and article are greater than 50, the prediction performance of law sources, articles, and charges reach 97.66, 92.22, and 60.52 macro-f1, respectively. To understand the big performance gap between articles and charges, we used a bipartite graph to visualize the relationship between the articles and charges, and found that the reason for the poor prediction performance was actually due to the wording precision. Some charges use the simplest words, while others may include the perpetrator or the result to make the charges more specific. For example, Article 284 of the Criminal Law may be indicted as “negligent injury”, "negligent death”, "business injury", "driving business injury", or "non-driving business injury". As another example, Article 10 of the Drug Hazard Control Regulations can be charged as “Drug Control Regulations” or “Drug Hazard Control Regulations”. In order to solve the above problems and more accurately predict the article and charge, we plan to include the article content or charge names in the input, and use the sentence-pair classification method for question-answer problems in the BERT model to improve the performance. We will also consider a sequence-to-sequence approach to charge prediction.

Keywords: legal judgment prediction, deep learning, natural language processing, BERT, data visualization

Procedia PDF Downloads 103

Authors: Adham M. Salah, Tariq A. Nagem, Raed A. Abd-Alhameed, James M. Noras

Abstract:

Recently, the demand for wireless communications systems to cover more than one frequency band (multi-band) with high data rate has been increased for both fixed and mobile services. Multiple Input Multiple Output (MIMO) technology is one of the significant solutions for attaining these requirements and to achieve the maximum channel capacity of the wireless communications systems. The main issue associated with MIMO antennas especially in portable devices is the compact space between the radiating elements which leads to limit the physical separation between them. This issue exacerbates the performance of the MIMO antennas by increasing the mutual coupling between the radiating elements. In other words, the mutual coupling will be stronger if the radiating elements of the MIMO antenna are closer. This paper presents a low–profile dual-band (2×1) MIMO antenna that works at 2.4GHz, 5.3GHz and 5.8GHz for wireless local area networks (WLAN) applications. A neutralization line (NL) technique for enhancing the isolation has been used by introducing a strip line with a length of λg/4 at the isolation frequency (2.4GHz) between the radiating elements. The overall dimensions of the antenna are 33.5 x 36 x 1.6 mm³. The fabricated prototype shows a good agreement between the simulated and measured results. The antenna impedance bandwidths are 2.38–2.75 GHz and 4.4–6 GHz for the lower and upper band respectively; the reflection coefficient and mutual coupling are better than -25 dB in both lower and higher bands. The MIMO antenna performance characteristics are reported in terms of the scattering parameters, envelope correlation coefficient (ECC), total active reflection coefficient, capacity loss, antenna gain, and radiation patterns. Analysis of these characteristics indicates that the design is appropriate for the WLAN terminal applications.

Keywords: ECC, neutralization line, MIMO antenna, multi-band, mutual coupling, WLAN

Procedia PDF Downloads 118

Authors: Arpita Mondal, Aurobinda Routray, Sreeraj Puravankara, Rajashree Biswas

Abstract:

The most difficult part of designing a battery management system (BMS) is battery modeling. A good battery model can capture the dynamics which helps in energy management, by accurate model-based state estimation algorithms. So far the most suitable and fruitful model is the equivalent circuit model (ECM). However, in real-time applications, the model parameters are time-varying, changes with current, temperature, state of charge (SOC), and aging of the battery and this make a great impact on the performance of the model. Therefore, to increase the equivalent circuit model performance, the parameter estimation has been carried out in the frequency domain. The battery is a very complex system, which is associated with various chemical reactions and heat generation. Therefore, it’s very difficult to select the optimal model structure. As we know, if the model order is increased, the model accuracy will be improved automatically. However, the higher order model will face the tendency of over-parameterization and unfavorable prediction capability, while the model complexity will increase enormously. In the time domain, it becomes difficult to solve higher order differential equations as the model order increases. This problem can be resolved by frequency domain analysis, where the overall computational problems due to ill-conditioning reduce. In the frequency domain, several dominating frequencies can be found in the input as well as output data. The selective frequency domain estimation has been carried out, first by estimating the frequencies of the input and output by subspace decomposition, then by choosing the specific bands from the most dominating to the least, while carrying out the least-square, recursive least square and Kalman Filter based parameter estimation. In this paper, a second order battery model consisting of three resistors, two capacitors, and one SOC controlled voltage source has been chosen. For model identification and validation hybrid pulse power characterization (HPPC) tests have been carried out on a 2.6 Ah LiFePO₄ battery.

Keywords: equivalent circuit model, frequency estimation, parameter estimation, subspace decomposition

Procedia PDF Downloads 124

Authors: Babar Rasheed, Saad Ghafoor

Abstract:

Introduction: Idea campaigns are commonly held across organizations for generating employee engagement. The contribution is specifically designed to identify and solve prevalent issues. It is argued that numerous organizations fail to achieve their desired goals despite arranging for such campaigns and investing heavily in them. There are however practices that organizations use to achieve higher degree of effectiveness, and these practices may be up for exploration by research to make them usable for the other organizations. Purpose: The aim of this research is to surface the idea management practices of a leading electric company with global operations. The study involves a large sized, multi site organization that is attributed to have added challenges in terms of managing ideas from employees, in comparison to smaller organizations. The study aims to highlight the factors that are looked at as the idea management team strategies for the campaign, sets terms and rewards for it, makes follow up with the employees and lastly, evaluate and award ideas. Methodology: The study is conducted in a leading electric appliance corporation that has a large number of employees and is based in numerous regions of the world. A total of 7 interviews are carried out involving the chief innovation officer, innovation manager and members of idea management and evaluation teams. The interviews are carried out either on Skype or in-person based on the availability of the interviewee. Findings: While this being a working paper and while the study is under way, it is anticipated that valuable information is being achieved about specific details on how idea management systems are governed and how idea campaigns are carried out. The findings may be particularly useful for innovation consultants as resources they can use to promote idea campaigning. The usefulness of the best practices highlighted as a result is, in any case, the most valuable output of this study.

Keywords: employee engagement, motivation, idea campaigns, large organizations, best practices, employees input, organizational output

Procedia PDF Downloads 157

Authors: Robin Molinier

Abstract:

Industrial symbiosis (I.S) rely on two modes of cooperation that are infrastructure sharing and resource substitution to obtain economic and environmental benefits. The former consists in the intensification of use of an asset while the latter is based on the use of waste, fatal energy (and utilities) as alternatives to standard inputs. Both modes, in fact, rely on the shift from a business-as-usual functioning towards an alternative production system structure so that in a business point of view the distinction is not clear. In order to investigate the way those cooperation modes can be distinguished, we consider the stakeholders' interplay in the business model structure regarding their resources and requirements. For infrastructure sharing (following economic engineering literature) the cost function of capacity induces economies of scale so that demand pooling reduces global expanses. Grassroot investment sizing decision and the ex-post pricing strongly depends on the design optimization phase for capacity sizing whereas ex-post operational cost sharing minimizing budgets are less dependent upon production rates. Value is then mainly design driven. For resource substitution, synergies value stems from availability and is at risk regarding both supplier and user load profiles and market prices of the standard input. Baseline input purchasing cost reduction is thus more driven by the operational phase of the symbiosis and must be analyzed within the whole sourcing policy (including diversification strategies and expensive back-up replacement). Moreover, while resource substitution involves a chain of intermediate processors to match quality requirements, the infrastructure model relies on a single operator whose competencies allow to produce non-rival goods. Transaction costs appear higher in resource substitution synergies due to the high level of customization which induces asset specificity, and non-homogeneity following transaction costs economics arguments.

Keywords: business model, capacity, sourcing, synergies

Procedia PDF Downloads 159

Authors: Emir Alaca, Hasbi Apaydin, Rohullah Rahmatullah, Necibe Fusun Oyman Serteller

Abstract:

In recent years, Permanent Magnet Synchronous Motors (PMSMs) have found extensive applications in various industrial sectors, including electric vehicles, wind turbines, and robotics, due to their high performance and low losses. Accurate mathematical modeling of PMSMs is crucial for advanced studies in electric machines. To enhance the effectiveness of graduate-level education, incorporating virtual or real experiments becomes essential to reinforce acquired knowledge. Virtual laboratories have gained popularity as cost-effective alternatives to physical testing, mitigating the risks associated with electrical machine experiments. This study presents a MATLAB-based Graphical User Interface (GUI) for PMSMs. The GUI offers a visual interface that allows users to observe variations in motor outputs corresponding to different input parameters. It enables users to explore healthy motor conditions and the effects of short-circuit faults in the one-phase winding. Additionally, the interface includes menus through which users can access equivalent circuits related to the motor and gain hands-on experience with the mathematical equations used in synchronous motor calculations. The primary objective of this paper is to enhance the learning experience of graduate and doctoral students by providing a GUI-based approach in laboratory studies. This interactive platform empowers students to examine and analyze motor outputs by manipulating input parameters, facilitating a deeper understanding of PMSM operation and control.

Keywords: magnet synchronous motor, mathematical modelling, education tools, winding inter-turn fault

Procedia PDF Downloads 35

Authors: Mustafa El-Halabi

Abstract:

A general model of wiretap channel with states is considered, where the legitimate receiver and the wiretapper’s observations depend on three states S1, S2 and S3. State S1 is non-causally known to the encoder, S2 is known to the receiver, and S3 remains unknown. A secure coding scheme, based using structured-binning, is proposed, and it is shown to achieve the secrecy capacity when the signal at legitimate receiver is a deterministic function of the input.

Keywords: physical layer security, interference, side information, secrecy capacity

Procedia PDF Downloads 366

Authors: Samaneh serraj

Abstract:

Listening anxiety has a detrimental effect on language learners. Through a qualitative study on Iranian EFL learners several factors were identified as having influence on their listening anxiety. These factors were divided into three categories, i.e. individual factors (nerves and emotionality, using inappropriate strategies and lack of practice), input factors (lack of time to process, lack of visual support, nature of speech and level of difficulty) and environmental factors (instructors, peers and class environment).

Keywords: listening Comprehension, Listening Anxiety, Foreign language learners

Procedia PDF Downloads 450

Authors: Mohammad Hossein Mohammadi Sanjani, Ashknaz Oraee, Oriol Gomis Bellmunt, Vinicius Albernaz Lacerda Freitas

Abstract:

The use of distributed and renewable sources in power systems has grown significantly, recently. One the most popular sources are wind farms which have grown massively. However, ¬wind farms are connected to the grid, this can cause problems such as reduced voltage stability, frequency fluctuations and reduced dynamic stability. Variable speed generators (asynchronous) are used due to the uncontrollability of wind speed specially Doubley Fed Induction Generators (DFIG). The most important disadvantage of DFIGs is its sensitivity to voltage drop. In the case of faults, a large volume of reactive power is induced therefore, use of FACTS devices such as SVC and STATCOM are suitable for improving system output performance. They increase the capacity of lines and also passes network fault conditions. In this paper, in addition to modeling the reactive power control system in a DFIG with converter, FACTS devices have been used in a DFIG wind turbine to improve the stability of the power system containing two synchronous sources. In the following paper, recent optimal control systems have been designed to minimize fluctuations caused by system disturbances, for FACTS devices employed. For this purpose, a suitable method for the selection of nine parameters for MPSH-phase-post-phase compensators of reactive power compensators is proposed. The design algorithm is formulated ¬¬as an optimization problem searching for optimal parameters in the controller. Simulation results show that the proposed controller Improves the stability of the network and the fluctuations are at desired speed.

Keywords: renewable energy sources, optimization wind power plant, stability, reactive power compensator, double-feed induction generator, optimal control, genetic algorithm

Procedia PDF Downloads 69

Authors: Hasmayadi Abdul Majid, Yuzman Yusoff, Noor Shelida Salleh

Abstract:

This paper presents the development of a single-ended 38.5 kS/s 10-bit programmable reference SAR ADC which is realized in MIMOS’s 0.35 µm CMOS process. The design uses a resistive DAC, a dynamic comparator with pre-amplifier and a SAR digital logic to create 10 effective bits ADC. A programmable reference circuitry allows the ADC to operate with different input range from 0.6 V to 2.1 V. A single ended 38.5 kS/s 10-bit programmable reference SAR ADC was proposed and implemented in a 0.35 µm CMOS technology and consumed less than 7.5 mW power with a 3 V supply.

Keywords: successive approximation register analog-to-digital converter, SAR ADC, resistive DAC, programmable reference

Procedia PDF Downloads 495

Authors: Mariana Thimotheo, Gabriel Carvalho Ripamonte, Marina De Almeida Nogueira, Silvia Camila Da Costa Aguiar, Marcelo Henrique Santana Ulian, Euclides Braga Malheiros, Isabel Cristina Boleli

Abstract:

Beak plays a fundamental role in the hatching process of the chicks, since it is used for internal and external pipping. The present study examined whether the size of the beak influences the birth period of the broiler chicks in the hatching window. It was analyzed the beak size (length, height and width) of one-hundred twenty nine newly hatched chicks from light eggs (56.22-61.05g) and one-hundred twenty six chicks from heavy eggs (64.95-70.90g), produced by 38 and 45 weeks old broiler breeders (Cobb 500®), respectively. Egg incubation occurred at 37.5°C and 60% RH, with egg turning every hour. Length, height and width of the beaks were measured using a digital caliper (Zaas precision - digital caliper 6", 0.01mm) and the data expressed in millimeters. The beak length corresponded to distance between the tip of the beak and the rictus. The height of the beak was measured in the region of the culmen and its width in the region of the nostrils. Data were analyzed following a 3x2 factorial experimental design, being three birth periods within the hatching window (early: 471.78 to 485.42h, intermediate: 485.43 to 512.27h, and late: 512.28 to 528.72h) and two egg weights (light and heavy). There was a significant interaction between birth period and egg weight for beak height (P < 0.05), which was higher in the intermediate chicks from heavy eggs than in the other chicks from the same egg weight and chicks from light eggs (P < 0.05), that did not differ (P > 0.05). The beak length was influenced only for a birth period, and decreased through the hatch window (early < intermediate < late) (P < 0.05). The width of the beaks was influenced by both main factors, birth period and egg weight (P < 0.05). Early and intermediate chicks had similar beak width, but greater than late chicks, and chicks from heavy eggs presented greater beak width than chicks from light eggs (P < 0.05). In sum, the results show that chicks with longer beak hatch first and that beak length is an important variable for hatch period determination mainly for light eggs.

Keywords: beak dimensions, egg weight, hatching period, hatching window

Procedia PDF Downloads 147

Authors: Ha Phuong Tran, Feng Wang, Jo Dewulf, Hai Trung Huynh, Thomas Schaubroeck

Abstract:

The fast increase and complex components have made waste of electrical and electronic equipment (or e-waste) one of the most problematic waste streams worldwide. Precise information on its size on national, regional and global level has therefore been highlighted as prerequisite to obtain a proper management system. However, this is a very challenging task, especially in developing countries where both formal e-waste management system and necessary statistical data for e-waste estimation, i.e. data on the production, sale and trade of electrical and electronic equipment (EEE), are often lacking. Moreover, there is an inflow of non-registered electronic and electric equipment, which ‘invisibly’ enters the EEE domestic market and then is used for domestic consumption. The non-registration/invisibility and (in most of the case) illicit nature of this flow make it difficult or even impossible to be captured in any statistical system. The e-waste generated from it is thus often uncounted in current e-waste estimation based on statistical market data. Therefore, this study focuses on enhancing e-waste estimation in developing countries and proposing a calculation pathway to quantify the magnitude of the non-registered EEE inflow. An advanced Input-Out Analysis model (i.e. the Sale–Stock–Lifespan model) has been integrated in the calculation procedure. In general, Sale-Stock-Lifespan model assists to improve the quality of input data for modeling (i.e. perform data consolidation to create more accurate lifespan profile, model dynamic lifespan to take into account its changes over time), via which the quality of e-waste estimation can be improved. To demonstrate the above objectives, a case study on televisions (TVs) in Vietnam has been employed. The results show that the amount of waste TVs in Vietnam has increased four times since 2000 till now. This upward trend is expected to continue in the future. In 2035, a total of 9.51 million TVs are predicted to be discarded. Moreover, estimation of non-registered TV inflow shows that it might on average contribute about 15% to the total TVs sold on the Vietnamese market during the whole period of 2002 to 2013. To tackle potential uncertainties associated with estimation models and input data, sensitivity analysis has been applied. The results show that both estimations of waste and non-registered inflow depend on two parameters i.e. number of TVs used in household and the lifespan. Particularly, with a 1% increase in the TV in-use rate, the average market share of non-register inflow in the period 2002-2013 increases 0.95%. However, it decreases from 27% to 15% when the constant unadjusted lifespan is replaced by the dynamic adjusted lifespan. The effect of these two parameters on the amount of waste TV generation for each year is more complex and non-linear over time. To conclude, despite of remaining uncertainty, this study is the first attempt to apply the Sale-Stock-Lifespan model to improve the e-waste estimation in developing countries and to quantify the non-registered EEE inflow to domestic consumption. It therefore can be further improved in future with more knowledge and data.

Keywords: e-waste, non-registered electrical and electronic equipment, TVs, Vietnam

Procedia PDF Downloads 232

Authors: G. Alex Ambrose, Melissa Paulsen, Abrar Fitwi, Masud Akbari

Abstract:

In 2016, a U.S. business college was awarded a sub grant to work with FHI360, a nonprofit human development organization, to support a university in Afghanistan funded by the State Department’s U.S. Agency for International Development (USAID). A newly designed Master’s Degree in Finance and Accounting is being implemented to support Afghanistan’s goal of 20% females in higher education and industry by 2020 and to use finance and accounting international standards to attract capital investment for economic development. This paper will present a case study to describe the co-construction of an approach to an International Flipped Faculty Development Model grounded in blended learning theory. Like education in general, faculty development is also evolving from the traditional face to face environment and interactions to the fully online and now to a best of both blends. Flipped faculty development is both a means and a model for careful integration of the strengths of the synchronous and asynchronous dynamics and technologies with the combination of intentional sequencing to pre-online interactions that prepares and enhances the face to face faculty development and mentorship residencies with follow-up post-online support. Initial benefits from this model include giving the Afghan faculty an opportunity to experience and apply modern teaching and learning strategies with technology in their own classroom. Furthermore, beyond the technological and pedagogical affordances, the reciprocal benefits gained from the mentor-mentee, face-to-face relationship will be explored. Evidence to support this model includes: empirical findings from pre- and post-Faculty Mentor/ Mentee survey results, Faculty Mentorship group debriefs, Faculty Mentorship contact logs, and student early/end of semester feedback. In addition to presenting and evaluating this model, practical challenges and recommendations for replicating international flipped faculty development partnerships will be provided.

Keywords: educational development, faculty development, international development, flipped learning

Procedia PDF Downloads 169

Authors: Sherly M. A., Subhankar Karmakar, Terence Chan, Christian Rau

Abstract:

Floods are one of the most frequent natural disasters, causing widespread devastation, economic damage and threat to human lives. Hydrologic impacts of climate change and intensification of urbanization are two root causes of increased flood occurrences, and recent research trends are oriented towards understanding these aspects. Due to rapid urbanization, population of cities across the world has increased exponentially leading to improperly planned developments. Climate change due to natural and anthropogenic activities on our environment has resulted in spatiotemporal changes in rainfall patterns. The combined effect of both aggravates the vulnerability of urban populations to floods. In this context, an efficient and effective flood risk management with its core component as flood risk mapping is essential in prevention and mitigation of flood disasters. Urban flood risk mapping involves zoning of an urban region based on its flood risk, which depicts the spatiotemporal pattern of frequency and severity of hazards, exposure to hazards, and degree of vulnerability of the population in terms of socio-economic, environmental and infrastructural aspects. Although vulnerability is a key component of risk, its assessment and mapping is often less advanced than hazard mapping and quantification. A synergic effort from technical experts and social scientists is vital for the effectiveness of flood risk management programs. Despite an increasing volume of quality research conducted on urban flood risk, a comprehensive multidisciplinary approach towards flood risk mapping still remains neglected due to which many of the input parameters and definitions of flood risk concepts are imprecise. Thus, the objectives of this review are to introduce and precisely define the relevant input parameters, concepts and terms in urban flood risk mapping, along with its methodology, current status and limitations. The review also aims at providing thought-provoking insights to potential future researchers and flood management professionals.

Keywords: flood risk, flood hazard, flood vulnerability, flood modeling, urban flooding, urban flood risk mapping

Procedia PDF Downloads 562

Authors: Vishal Pareek, Shubham Gupta, Sushil Chandra Jain

Abstract:

With increasing high-speed computation demand the power consumption, heat dissipation and chip size issues are posing challenges for logic design with conventional technologies. Recovery of bit loss and bit errors is other issues that require reversibility and fault tolerance in the computation. The reversible computing is emerging as an alternative to conventional technologies to overcome the above problems and helpful in a diverse area such as low-power design, nanotechnology, quantum computing. Bit loss issue can be solved through unique input-output mapping which require reversibility and bit error issue require the capability of fault tolerance in design. In order to incorporate reversibility a number of combinational reversible logic based circuits have been developed. However, very few sequential reversible circuits have been reported in the literature. To make the circuit fault tolerant, a number of fault model and test approaches have been proposed for reversible logic. In this paper, we have attempted to incorporate fault tolerance in sequential reversible building blocks such as D flip-flop, T flip-flop, JK flip-flop, R-S flip-flop, Master-Slave D flip-flop, and double edge triggered D flip-flop by making them parity preserving. The importance of this proposed work lies in the fact that it provides the design of reversible sequential circuits completely testable for any stuck-at fault and single bit fault. In our opinion our design of reversible building blocks is superior to existing designs in term of quantum cost, hardware complexity, constant input, garbage output, number of gates and design of online testable D flip-flop have been proposed for the first time. We hope our work can be extended for building complex reversible sequential circuits.

Keywords: parity preserving gate, quantum computing, fault tolerance, flip-flop, sequential reversible logic

Procedia PDF Downloads 528

Authors: Myunggon Yoon, Jung-Ho Moon

Abstract:

In this paper, we present a transfer function representation of a general one-dimensional combustor. The input of the transfer function is a heat rate perturbation of a burner and the output is a flow velocity perturbation at the burner. This paper considers a general combustor model composed of multiple cans with different cross sectional areas, along with a non-zero flow rate.

Keywords: combustor, dynamics, thermoacoustics, transfer function

Procedia PDF Downloads 363

Authors: S. Farag, A. Kuperman

Abstract:

In this paper, design of solid-state battery/super capacitor emulator based on dc-dc boost converter is described. The emulator mimics charging behavior of any storage device based on a predefined behavior set by the user. The device is operated by a two-level control structure: high-level emulating controller and low-level input voltage controller. Simulation and experimental results are shown to demonstrate the emulator operation.

Keywords: battery, charger, energy, storage, super capacitor

Procedia PDF Downloads 382

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 138

Authors: Adriana Postal, Silvio C. Sampaio, Marcio A. Villas Boas, Josué P. Castro

Abstract:

This study deals with the estimation of reference evapotranspiration (ET₀) in an agricultural context, focusing on efficient irrigation management to meet the growing interest in the sustainable management of water resources. Given the importance of water in agriculture and its scarcity in many regions, efficient use of this resource is essential to ensure food security and environmental sustainability. The methodology used involved the application of artificial intelligence techniques, specifically Multilayer Perceptron (MLP) Artificial Neural Networks (ANNs), to predict ET₀ in the state of Paraná, Brazil. The models were trained and validated with meteorological data from the Brazilian National Institute of Meteorology (INMET), together with data obtained from a producer's weather station in the western region of Paraná. Two optimizers (SGD and Adam) and different meteorological variables, such as temperature, humidity, solar radiation, and wind speed, were explored as inputs to the models. Nineteen configurations with different input variables were tested; amidst them, configuration 9, with 8 input variables, was identified as the most efficient of all. Configuration 10, with 4 input variables, was considered the most effective, considering the smallest number of variables. The main conclusions of this study show that MLP ANNs are capable of accurately estimating ET₀, providing a valuable tool for irrigation management in agriculture. Both configurations (9 and 10) showed promising performance in predicting ET₀. The validation of the models with cultivator data underlined the practical relevance of these tools and confirmed their generalization ability for different field conditions. The results of the statistical metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²), showed excellent agreement between the model predictions and the observed data, with MAE as low as 0.01 mm/day and 0.03 mm/day, respectively. In addition, the models achieved an R² between 0.99 and 1, indicating a satisfactory fit to the real data. This agreement was also confirmed by the Kolmogorov-Smirnov test, which evaluates the agreement of the predictions with the statistical behavior of the real data and yields values between 0.02 and 0.04 for the producer data. In addition, the results of this study suggest that the developed technique can be applied to other locations by using specific data from these sites to further improve ET₀ predictions and thus contribute to sustainable irrigation management in different agricultural regions. The study has some limitations, such as the use of a single ANN architecture and two optimizers, the validation with data from only one producer, and the possible underestimation of the influence of seasonality and local climate variability. An irrigation management application using the most efficient models from this study is already under development. Future research can explore different ANN architectures and optimization techniques, validate models with data from multiple producers and regions, and investigate the model's response to different seasonal and climatic conditions.

Keywords: agricultural technology, neural networks in agriculture, water efficiency, water use optimization

Procedia PDF Downloads 27