Search results for: semantic model

Authors: Thomas Q. Pan, Anika Basu, Chamith S. Rajapakse

Abstract:

Machine learning requires data that is categorized into features that models train on. This topic is important to the field of sports medicine due to the many tools it provides to physicians such as diagnosis support and risk assessment. Physician note that healthcare professionals take are usually unclean and not suitable for model training. The objective of this study was to develop and evaluate an advanced approach for extracting key features from sports medicine data without the need for extensive model training or data labeling. An LLM (Large Language Model) was given a narrative (Physician’s Notes) and prompted to extract four features (details about the patient). The narrative was found in a datasheet that contained six columns: Case Number, Validation Age, Validation Gender, Validation Diagnosis, Validation Body Part, and Narrative. The validation columns represent the accurate responses that the LLM attempts to output. With the given narrative, the LLM would output its response and extract the age, gender, diagnosis, and injured body part with each category taking up one line. The output would then be cleaned, matched, and added to new columns containing the extracted responses. Five ways of checking the accuracy were used: unclear count, substring comparison, LLM comparison, LLM re-check, and hand-evaluation. The unclear count essentially represented the extractions the LLM missed. This can be also understood as the recall score ([total - false negatives] over total). The rest of these correspond to the precision score ([total - false positives] over total). Substring comparison evaluated the validation (X) and extracted (Y) columns’ likeness by checking if X’s results were a substring of Y's findings and vice versa. LLM comparison directly asked an LLM if the X and Y’s results were similar. LLM Re-check prompted the LLM to see if the extracted results can be found in the narrative. Lastly, A selection of 1,000 random narratives was also selected and hand-evaluated to give an estimate of how well the LLM-based feature extraction model performed. With a selection of 10,000 narratives, the LLM-based approach had a recall score of roughly 98%. However, the precision scores of the substring comparison and LLM comparison models were around 72% and 76% respectively. The reason for these low figures is due to the minute differences between answers. For example, the ‘chest’ is a part of the ‘upper trunk’ however, these models cannot detect that. On the other hand, the LLM re-check and subset of hand-tested narratives showed a precision score of 96% and 95%. If this subset is used to extrapolate the possible outcome of the whole 10,000 narratives, the LLM-based approach would be strong in both precision and recall. These results indicated that an LLM-based feature extraction model could be a useful way for medical data in sports to be collected and analyzed by machine learning models. Wide use of this method could potentially increase the availability of data thus improving machine learning algorithms and supporting doctors with more enhanced tools.

Keywords: AI, LLM, ML, sports

Procedia PDF Downloads 12

Authors: Muhammmad Riandhy Anindika Yudhy, Harry Patria, Ramadhani Santoso

Abstract:

Loss of containment is the primary hazard that process safety management is concerned within the oil and gas industry. Escalation to more serious consequences all begins with the loss of containment, starting with oil and gas release from leakage or spillage from primary containment resulting in pool fire, jet fire and even explosion when reacted with various ignition sources in the operations. Therefore, the heart of process safety management is avoiding loss of containment and mitigating its impact through the implementation of safeguards. The most effective safeguard for the case is an early detection system to alert Operations to take action prior to a potential case of loss of containment. The detection system value increases when applied to a long surface pipeline that is naturally difficult to monitor at all times and is exposed to multiple causes of loss of containment, from natural corrosion to illegal tapping. Based on prior researches and studies, detecting loss of containment accurately in the surface pipeline is difficult. The trade-off between cost-effectiveness and high accuracy has been the main issue when selecting the traditional detection method. The current best-performing method, Real-Time Transient Model (RTTM), requires analysis of closely positioned pressure, flow and temperature (PVT) points in the pipeline to be accurate. Having multiple adjacent PVT sensors along the pipeline is expensive, hence generally not a viable alternative from an economic standpoint.A conceptual approach to combine mathematical modeling using computational fluid dynamics and a supervised machine learning model has shown promising results to predict leakage in the pipeline. Mathematical modeling is used to generate simulation data where this data is used to train the leak detection and localization models. Mathematical models and simulation software have also been shown to provide comparable results with experimental data with very high levels of accuracy. While the supervised machine learning model requires a large training dataset for the development of accurate models, mathematical modeling has been shown to be able to generate the required datasets to justify the application of data analytics for the development of model-based leak detection systems for petroleum pipelines. This paper presents a review of key leak detection strategies for oil and gas pipelines, with a specific focus on crude oil applications, and presents the opportunities for the use of data analytics tools and mathematical modeling for the development of robust real-time leak detection and localization system for surface pipelines. A case study is also presented.

Keywords: pipeline, leakage, detection, AI

Procedia PDF Downloads 193

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 185

Authors: Xin Wang, Chaoqun Ma, Zheng Yao

Abstract:

Although green technology innovation faces new opportunities and challenges in the digital era, its theoretical research remains limited. Drawing on the attention-based view, this study employs the spatial Durbin model to investigate the impact of local government digital attention and digital industrial agglomeration on green technology innovation across 30 Chinese provinces from 2011 to 2021, as well as the spatial spillover effects present. The results suggest that both government digital attention and digital industrial agglomeration positively influence green technology innovation in local and neighboring provinces, with digital industrial agglomeration exhibiting a positive moderating effect on this direct local and indirect spatial spillover relationship. The findings of this study provide a new theoretical perspective for green technology innovation research and hold valuable implications for the advancement of the attention-based view and green technology innovation.

Keywords: local government digital attention, digital industrial agglomeration, green technology innovation, attention-based view

Procedia PDF Downloads 70

Authors: Firas M. Tuaimah, Huda M. Abdul Abbas

Abstract:

Accurate Short Term Load Forecasting (STLF) is essential for a variety of decision making processes. However, forecasting accuracy can drop due to the presence of uncertainty in the operation of energy systems or unexpected behavior of exogenous variables. Interval Type 2 Fuzzy Logic System (IT2 FLS), with additional degrees of freedom, gives an excellent tool for handling uncertainties and it improved the prediction accuracy. The training data used in this study covers the period from January 1, 2012 to February 1, 2012 for winter season and the period from July 1, 2012 to August 1, 2012 for summer season. The actual load forecasting period starts from January 22, till 28, 2012 for winter model and from July 22 till 28, 2012 for summer model. The real data for Iraqi power system which belongs to the Ministry of Electricity.

Keywords: short term load forecasting, prediction interval, type 2 fuzzy logic systems, electric, computer systems engineering

Procedia PDF Downloads 398

Authors: Bekalu Melis Alehegn, Dagnenet Sultan Alemu

Abstract:

The insufficiency of water is the most severe restraint for the expansion of agriculture in arid and semi-arid areas. An important strategy for increasing water productivity and improving water productivity deficit irrigation at different growth stages is important to advance the yield and Water Productivity of barley in water scarce areas. A field experiment was conducted at the Koga irrigation scheme in Ethiopia to examine barley yield response to different irrigation regimes and validate the aqua crop model. The experimental setup comprised six randomized treatments (T) with three replications for one irrigation season because of financial limitations. The irrigation regimes were selected 100%, 75%, and 50% application levels in different growth stages of gross irrigation requirements using trial and error in order to select the optimal water application level. The treatments were: no stress at all (T1), 25% stressed during all crop stages (T2), 50% stressed at all stages (T3), 50% stressed at the development stage (T4), 50% stressed at mid-stage (T5) and 50% stress at initial and late season (T6). The agronomic parameters, including canopy cover, biomass, and grain yield, were collected to compare the ground-based crop yield and the aqua crop model. The results showed that the initial and late stages and stress 25% through the whole season were the right time for practice deficit irrigation without significant yield reduction. The highest (2.62kg/m³) and the lowest (2.03 kg/m³) water productivity were found under T3 and T4, respectively. The stress of 50% at the mid-growth stage and stress 50% of the full irrigation water requirement at all growth stages significantly (α=5%) affected the canopy expansion, biomass and yield production. The aqua Crop model performed well in simulating the yield of barley for most of the treatments (R2 = 0.84 and RMSE = 0.7 t ha–¹).

Keywords: aqua crop, barley, deficit irrigation, irrigation regimes, water productivity

Procedia PDF Downloads 30

Authors: Leila Vafajoo, Feria Ghanaat, Alireza Mohmadi Kartalaei, Amin Ghalebi

Abstract:

Petrochemical industries are playing an important role in producing wastewaters. Nowadays different methods are employed to treat these materials. The goal of the present research was to reduce the COD of a petrochemical wastewater via adsorption technique using a commercial granular activated carbon (GAC) as adsorbent. In the current study, parameters of kinetic models as well as; adsorption isotherms were determined through utilizing the Langmuir and Freundlich isotherms. The key parameters of KL= 0.0009 and qm= 33.33 for the former and nf=0.5 and Kf= 0.000004 for the latter isotherms resulted. Moreover, a correlation coefficient of above 90% for both cases proved logical use of such isotherms. On the other hand, pseudo-first and -second order kinetics equations were implemented. These resulted in coefficients of k1=0.005 and qe=2018 as well as; K2=0.009 and qe=1250; respectively. In addition, obtaining the correlation coefficients of 0.94 and 0.68 for these 1st and 2nd order kinetics; respectively indicated advantageous use of the former model. Furthermore, a significant experimental reduction of the petrochemical wastewater COD revealed that, using GAC for the process undertaken was an efficient mean of treatment. Ultimately, the current investigation paved down the road for predicting the system’s behavior on industrial scale.

Keywords: petrochemical wastewater, adsorption, granular activated carbon, equilibrium isotherm, kinetic model

Procedia PDF Downloads 363

Authors: Isabelle Snyder

Abstract:

Microgrid protection presents challenges to conventional protection techniques due to the low induced fault current. Protection relays present in microgrid applications require a combination of settings groups to adjust based on the architecture of the microgrid in islanded and grid-connected mode. In a radial system where the microgrid is at the other end of the feeder, directional elements can be used to identify the direction of the fault current and switch settings groups accordingly (grid connected or microgrid connected). However, with multiple microgrid connections, this concept becomes more challenging, and the direction of the current alone is not sufficient to identify the source of the fault current contribution. ORNL has previously developed adaptive relaying schemes through other DOE-funded research projects that will be evaluated and used as a baseline for this research. The four protection techniques in this study are the following: (1) Adaptive Current only Protection System (ACPS), Intentional (2) Unbalanced Control for Protection Control (IUCPC), (3) Adaptive Protection System with Communication Controller (APSCC) (4) Adaptive Model-Driven Protective Relay (AMDPR). The first two methods focus on identifying the islanded mode without communication by monitoring the current sequence component generated by the system (ACPS) or induced with inverter control during islanded mode (IUCPC) to identify the islanding condition without communication at the relay to adjust the settings. These two methods are used as a backup to the APSCC, which relies on a communication network to communicate the islanded configuration to the system components. The fourth method relies on a short circuit model inside the relay that is used in conjunction with communication to adjust the system configuration and computes the fault current and adjusts the settings accordingly.

Keywords: adaptive relaying, microgrid protection, sequence components, islanding detection, communication controlled protection, integrated short circuit model

Procedia PDF Downloads 95

Authors: Shu-Yu Chung, Ying-Fang Wang, Shih-Min Wang

Abstract:

To conduct long-term exposure assessments are important for workers exposed to chemicals with chronic effects. However, it usually encounters with several constrains, including cost, workers' willingness, and interference to work practice, etc., leading to inadequate long-term exposure data in the real world. In this study, an integrated approach was developed for conducting long-term exposure assessment for welding workers in a shipbuilding factory. A laboratory study was conducted to yield the fume generation rates under various operating conditions. The results and the measured environmental conditions were applied to the near field/far field (NF/FF) model for predicting long term fume exposures via the Monte Carlo simulation. Then, the predicted long-term concentrations were used to determine the prior distribution in Bayesian decision analysis (BDA). Finally, the resultant posterior distributions were used to assess the long-term exposure and serve as basis for initiating control strategies for shipbuilding workers. Results show that the NF/FF model was a suitable for predicting the exposures of metal contents containing in welding fume. The resultant posterior distributions could effectively assess the long-term exposures of shipbuilding welders. Welders' long-term Fe, Mn and Pb exposures were found with high possibilities to exceed the action level indicating preventive measures should be taken for reducing welders' exposures immediately. Though the resultant posterior distribution can only be regarded as the best solution based on the currently available predicting and monitoring data, the proposed integrated approach can be regarded as a possible solution for conducting long term exposure assessment in the field.

Keywords: Bayesian decision analysis, exposure assessment, near field and far field model, shipbuilding industry, welding fume

Procedia PDF Downloads 142

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are playing an increasingly important role in automated customer service. These models, which are able to recognize complex relationships between input and output sequences, are crucial for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the focus of the model during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the domain of chatbots using the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Utilizing the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k=3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k=3). These results emphasize the crucial influence of selecting an appropriate attention-scoring function in improving the performance of seq2seq models for chatbots. Particularly, the model that integrates tanh activation proves to be a promising approach to improve the quality of chatbots in the customer support context.

Keywords: attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence

Procedia PDF Downloads 78

Authors: R. Marandi, H. Shahrir, T. Nejad Ghaffar Borhani, M. Kamaruddin

Abstract:

In the present study, a steady state population balance model was developed to predict the polymer particle size distribution (PSD) in ethylene gas phase fluidized bed olefin polymerization reactors. The multilayer polymeric flow model (MPFM) was used to calculate the growth rate of a single polymer particle under intra-heat and mass transfer resistance. The industrial plant data were used to calculate the growth rate of polymer particle and the polymer PSD. Numerical simulations carried out to describe the influence of effective monomer diffusion coefficient, polymerization rate and initial catalyst size on the catalyst particle growth and final polymer PSD. The results present that the intra-heat and mass limitation is important for the ethylene polymerization, the growth rate of particle and the polymer PSD in the fluidized bed reactor. The effect of the agglomeration on the PSD is also considered. The result presents that the polymer particle size distribution becomes broader as the agglomeration exits.

Keywords: population balance, olefin polymerization, fluidized bed reactor, particle size distribution, agglomeration

Procedia PDF Downloads 333

Authors: Jenifer Alam, Rima Chatterjee

Abstract:

Upper Assam sedimentary basin is one of the oldest commercially producing basins of India. Being in a tectonically active zone, estimation of tectonic strain and stress magnitudes has vast application in hydrocarbon exploration and exploitation. This East North East –West South West trending shelf-slope basin encompasses the Bramhaputra valley extending from Mikir Hills in the southwest to the Naga foothills in the northeast. Assam Shelf lying between the Main Boundary Thrust (MBT) and Naga Thrust area is comparatively free from thrust tectonics and depicts normal faulting mechanism. The study area is bounded by the MBT and Main Central Thrust in the northwest. The Belt of Schuppen in the southeast, is bordered by Naga and Disang thrust marking the lower limit of the study area. The entire Assam basin shows low-level seismicity compared to other regions of northeast India. Pore pressure (PP), vertical stress magnitude (SV) and horizontal stress magnitudes have been estimated from two wells - N1 and T1 located in Upper Assam. N1 is located in the Assam gap below the Bramhaputra river while T1, lies in the Belt of Schuppen. N1 penetrates geological formations from top Alluvial through Dhekiajuli, Girujan, Tipam, Barail, Kopili, Sylhet and Langpur to the granitic basement while T1 in trusted zone crosses through Girujan Suprathrust, Tipam Suprathrust, Barail Suprathrust to reach Naga Thrust. Normal compaction trend is drawn through shale points through both wells for estimation of PP using the conventional Eaton sonic equation with an exponent of 1.0 which is validated with Modular Dynamic Tester and mud weight. Observed pore pressure gradient ranges from 10.3 MPa/km to 11.1 MPa/km. The SV has a gradient from 22.20 to 23.80 MPa/km. Minimum and maximum horizontal principal stress (Sh and SH) magnitudes under isotropic conditions are determined using poroelastic model. This approach determines biaxial tectonic strain utilizing static Young’s Modulus, Poisson’s Ratio, SV, PP, leak off test (LOT) and SH derived from breakouts using prior information on unconfined compressive strength. Breakout derived SH information is used for obtaining tectonic strain due to lack of measured SH data from minifrac or hydrofracturing. Tectonic strain varies from 0.00055 to 0.00096 along x direction and from -0.0010 to 0.00042 along y direction. After obtaining tectonic strains at each well, the principal horizontal stress magnitudes are calculated from linear poroelastic model. The magnitude of Sh and SH gradient in normal faulting region are 12.5 and 16.0 MPa/km while in thrust faulted region the gradients are 17.4 and 20.2 MPa/km respectively. Model predicted Sh and SH matches well with the LOT data and breakout derived SH data in both wells. It is observed from this study that the stresses SV>SH>Sh prevailing in the shelf region while near the Naga foothills the regime changes to SH≈SV>Sh area corresponds to normal faulting regime. Hence this model is a reliable tool for predicting stress magnitudes from well logs under active tectonic regime in Upper Assam Basin.

Keywords: Eaton, strain, stress, poroelastic model

Procedia PDF Downloads 216

Authors: Pintip Vajarothai, Saad Al-Jibouri, Johannes I. M. Halman

Abstract:

Public investment projects are primarily aimed at achieving development strategies to increase national economies of scale and overall improvement in a country. However, experience shows that public projects, particularly in developing countries, struggle or fail to fulfill the immediate needs of local communities. In many cases, the reason for that is that projects are selected in a subjective manner and that a major part of the problem is related to the evaluation criteria and techniques used. The evaluation process is often based on a broad strategic economic effects rather than real benefits of projects to society or on the various needs from different levels (e.g. national, regional, local) and conditions (e.g. long-term and short-term requirements). In this paper, an extensive literature review of the types of criteria used in the past by various researchers in project evaluation and selection process is carried out and the effectiveness of such criteria and techniques is discussed. The paper proposes substitute social and project sustainability criteria to improve the conditions of local people and in particular the disadvantaged groups of the communities. Furthermore, it puts forward a way for modelling the interaction between the selected criteria and the achievement of the social goals of the affected community groups. The described work is part of developing a broader decision model for public investment project selection by integrating various aspects and techniques into a practical methodology. The paper uses Thailand as a case to review what and how the various evaluation techniques are currently used and how to improve the project evaluation and selection process related to social and sustainability issues in the country. The paper also uses an example to demonstrates how to test the feasibility of various criteria and how to model the interaction between projects and communities. The proposed model could be applied to other developing and developed countries in the project evaluation and selection process to improve its effectiveness in the long run.

Keywords: evaluation criteria, developing countries, public investment, project selection methodology

Procedia PDF Downloads 277

Authors: Hossein Agheshlui, Stephan Matthai

Abstract:

In fractured rock masses open fractures tend to act as the main pathways of fluid flow. The permeability of a rock fracture depends on its aperture. The change of aperture with stress can cause a many-orders-of-magnitude change in the hydraulic conductivity at moderate compressive stress levels. In this study, the change of aperture in fragmented rocks is investigated using finite element analysis. A full 3D mechanical model of a simplified version of an outcrop analog is created and studied. A constant initial aperture value is applied to all fractures. Different far field stresses are applied and the change of aperture is monitored considering the block to block interaction. The fragmented rock layer is assumed to be sandwiched between softer layers. Frictional contact forces are defined at the layer boundaries as well as among contacting rock blocks. For a given in situ stress, the blocks slide and contact each other, resulting in new aperture distributions. A map of changed aperture is produced after applying the in situ stress and compared to the initial apertures. Subsequently, the permeability of the system before and after the stress application is compared.

Keywords: fractured rocks, mechanical model, aperture change due to stress, frictional interface

Procedia PDF Downloads 417

Authors: Kyoung-Jae Kim

Abstract:

Collaborative Filtering (CF) is a popular technique for the personalization in the E-commerce domain to reduce information overload. In general, CF provides recommending items list based on other similar users’ preferences from the user-item matrix and predicts the focal user’s preference for particular items by using them. Many recommender systems in real-world use CF techniques because it’s excellent accuracy and robustness. However, it has some limitations including sparsity problems and complex dimensionality in a user-item matrix. In addition, traditional CF does not consider the emotional interaction between users. In this study, we propose recommender systems using social network and singular value decomposition (SVD) to alleviate some limitations. The purpose of this study is to reduce the dimensionality of data set using SVD and to improve the performance of CF by using emotional information from social network data of the focal user. In this study, we test the usability of hybrid CF, SVD and social network information model using the real-world data. The experimental results show that the proposed model outperforms conventional CF models.

Keywords: recommender systems, collaborative filtering, social network information, singular value decomposition

Procedia PDF Downloads 294

Authors: A. Calvin Antony, Sakthi Kumar Arul Prakash, V. R. Sanal Kumar

Abstract:

In this paper a unique alpha-beta double piston 'stirling engine' is designed, manufactured and conducted laboratory test to ameliorate the efficiency of the stirling engine. The paper focuses on alpha and beta type engines, capturing their benefits and eradicating their short comings; along with the output observed from the flywheel. In this model alpha engine is kinematically with a piston cylinder arrangement which works quite like a beta engine. The piston of the new cylinder is so designed that it replicates a glued displacer and power piston as similar to that of beta engine. The bigger part of the piston is the power piston, which has a gap around it, while the smaller part of the piston is tightly fit in the cylinder and acts like the displacer piston. We observed that the alpha-beta double piston stirling engine produces 25% increase in power compare to a conventional alpha stirling engine. This working model is a pointer towards for the design and development of an alpha-beta double piston Stirling engine for industrial applications for producing electricity from the heat producing exhaust gases.

Keywords: alpha-beta double piston stirling engine , alpha stirling engine , beta double piston stirling engine , electricity from stirling engine

Procedia PDF Downloads 534

Authors: M. G. Shilina

Abstract:

The interstate economic interaction phenomenon is complex. ‘Economic integration’, as one of its types, can be explored through the prism of international law, the theories of the world economy, politics and international relations. The most objective study of the phenomenon requires a comprehensive multifactoral approach. In new geopolitical realities, the problems of coexistence and possible interconnection of various mechanisms of interstate economic interaction are actively discussed. Currently, the Eurasian continent states support the direction to economic integration. At the same time, the existing international economic law fragmentation in Eurasia is seen as the important problem. The Eurasian space is characterized by a various types of interstate relations: international agreements (multilateral and bilateral), and a large number of cooperation formats (from discussion platforms to organizations aimed at deep integration). For their harmonization, it is necessary to have a clear vision to the phased international economic relations regulation options. In the conditions of rapid development of international economic relations, the modeling (including prognostic) can be optimally used as the main scientific method for presenting the phenomenon. On the basis of this method, it is possible to form the current situation vision and the best options for further action. In order to determine the most objective version of the integration development, the combination of several approaches were used. The normative legal approach- the descriptive method of legal modeling- was taken as the basis for the analysis. A set of legal methods was supplemented by the international relations science prognostic methods. The key elements of the model are the international economic organizations and states' associations existing in the Eurasian space (the Eurasian Economic Union (EAEU), the European Union (EU), the Shanghai Cooperation Organization (SCO), Chinese project ‘One belt-one road’ (OBOR), the Commonwealth of Independent States (CIS), BRICS, etc.). A general term for the elements of the model is proposed - the interstate interaction mechanisms (IIM). The aim of building a model of current and future Eurasian economic integration is to show optimal options for joint economic development of the states and IIMs. The long-term goal of this development is the new economic and political space, so-called the ‘Great Eurasian Community’. The process of achievement this long-term goal consists of successive steps. Modeling the integration architecture and dividing the interaction into stages led us to the following conclusion: the SCO is able to transform Eurasia into a single economic space. Gradual implementation of the complex phased model, in which the SCO+ plays a key role, will allow building an effective economic integration for all its participants, to create an economically strong community. The model can have practical value for politicians, lawyers, economists and other participants involved in the economic integration process. A clear, systematic structure can serve as a basis for further governmental action.

Keywords: economic integration, The Eurasian Economic Union, The European Union, The Shanghai Cooperation Organization, The Silk Road Economic Belt

Procedia PDF Downloads 152

Authors: Lidija R. Jevrić, Sanja O. Podunavac-Kuzmanović, Strahinja Z. Kovačević

Abstract:

The present study deals with the selection of the most suitable quantitative structure-retention relationship (QSRR) models which should be used in prediction of the retention behavior of basic, neutral, acidic and phenolic pesticides which belong to different classes: fungicides, herbicides, metabolites, insecticides and plant growth regulators. Sum of ranking differences (SRD) approach can give a different point of view on selection of the most consistent QSRR model. SRD approach can be applied not only for ranking of the QSRR models, but also for detection of similarity or dissimilarity among them. Applying the SRD analysis, the most similar models can be found easily. In this study, selection of the best model was carried out on the basis of the reference ranking (“golden standard”) which was defined as the row average values of logarithm of retention time (logtr) defined by high performance liquid chromatography (HPLC). Also, SRD analysis based on experimental logtr values as reference ranking revealed similar grouping of the established QSRR models already obtained by hierarchical cluster analysis (HCA).

Keywords: chemometrics, chromatography, pesticides, sum of ranking differences

Procedia PDF Downloads 375

Authors: Khaled Ayfi, Morgan Dal, Frederic Coste, Nicolas Gallienne, Martina Ridlova, Philippe Lorong

Abstract:

In the gas industry, contamination of equipment by metal particles is one of the feared phenomena. Indeed, particles inside equipment can be driven by the gas flow and accumulate in places where the velocity is low. As they constitute a potential ignition hazard, particular attention is paid to the presence of particles in the oxygen industry. Indeed, the heat release from ignited particles may damage the equipment and even result in a loss of integrity. The objective of this work is to support the development of new design criteria. Studying the thermomechanical behavior of this equipment, thanks to numerical simulations, allows us to test the influence of various operating parameters (oxygen pressure, wall thickness, initial operating temperature, nature of the metal, etc.). Therefore, in this study, we propose a numerical model that describes the thermomechanical behavior of various pressurized installations heated locally by the combustion of small particles. This model takes into account the geometric and material nonlinearity and has been validated by the comparison of simulation results with experimental measurements obtained by a new device developed in this work.

Keywords: ignition, oxygen, numerical simulation, thermomechanical behaviour

Procedia PDF Downloads 155

Authors: Chayarat Tantanasarit, Sandhya Babel

Abstract:

Green mussels (Perna viridis) can effectively remove nutrients from seawater through their filtration process. This study aims to estimate 'net' nutrient removal rate by green mussel through calculation of nutrient uptake and release. Nutrients (carbon, nitrogen, and phosphorus) uptake was calculated based on the mussel filtration rate. Nutrient release was evaluated from carbon, nitrogen, and phosphorus released as mussel feces. By subtracting nutrient release from nutrient uptake, net nutrient removal by green mussel can be found as 3302, 380 and 124 mg/year/indv. Mass balance model was employed to simulate nutrient removal in actual green mussel farming conditions. Mussels farm area, seawater flow rate and amount of mussels were considered in the model. Results show that although larger quantity of green mussel farms lead to higher nutrient removal rate, the maximum green mussel cultivation should be taken into consideration as nutrients released through mussel excretion can strongly affect marine ecosystem.

Keywords: carbon, ecretion, filtration, nitrogen, phosphorus

Procedia PDF Downloads 400

Authors: Staņislavs Gendelis, Andris Jakovičs, Jānis Ratnieks, Aigars Laizāns, Dāvids Vardanjans

Abstract:

Dehumidification of biogas at the biomass plants is very important to provide the energy efficient burning of biomethane at the outlet. A few methods are widely used to reduce the water content in biogas, e.g. chiller/heat exchanger based cooling, usage of different adsorbents like PSA, or the combination of such approaches. A quite different method of biogas dehumidification is offered and analyzed in this paper. The main idea is to direct the flow of biogas from the plant around it downwards; thus, creating additional insulation layer. As the temperature in gas shell layer around the plant will decrease from ~ 38°C to 20°C in the summer or even to 0°C in the winter, condensation of water vapor occurs. The water from the bottom of the gas shell can be collected and drain away. In addition, another upward shell layer is created after the condensate drainage place on the outer side to further reducing heat losses. Thus, counterflow biogas heat exchanger is created around the biogas plant. This research work deals with the numerical modelling of biogas flow, taking into account heat exchange and condensation on cold surfaces. Different kinds of boundary conditions (air and ground temperatures in summer/winter) and various physical properties of constructions (insulation between layers, wall thickness) are included in the model to make it more general and useful for different biogas flow conditions. The complexity of this problem is fact, that the temperatures in both channels are conjugated in case of low thermal resistance between layers. MATLAB programming language is used for multiphysical model development, numerical calculations and result visualization. Experimental installation of a biogas plant’s vertical wall with an additional 2 layers of polycarbonate sheets with the controlled gas flow was set up to verify the modelling results. Gas flow at inlet/outlet, temperatures between the layers and humidity were controlled and measured during a number of experiments. Good correlation with modelling results for vertical wall section allows using of developed numerical model for an estimation of parameters for the whole biogas dehumidification system. Numerical modelling of biogas counterflow heat exchanger system placed on the plant’s wall for various cases allows optimizing of thickness for gas layers and insulation layer to ensure necessary dehumidification of the gas under different climatic conditions. Modelling of system’s defined configuration with known conditions helps to predict the temperature and humidity content of the biogas at the outlet.

Keywords: biogas dehumidification, numerical modelling, condensation, biogas plant experimental model

Procedia PDF Downloads 550

Authors: Y. Smirlis, G. Koronakos, S. Plitsos

Abstract:

Shipbrokers assist the ship companies in chartering or selling and buying vessels, acting as intermediates between them and the market. They facilitate deals, providing their expertise, negotiating skills, and knowledge about ship market bargains. Their role is very important as it affects the profitability and market position of a shipping company. Due to their significant contribution, the shipping companies have to employ systematic procedures to evaluate the shipbrokers’ services in order to select the best and, consequently, to achieve the best deals. Towards this, in this paper, we consider shipbrokers as financial service providers, and we formulate the problem of evaluating and selecting shipbrokers’ services as a multi-criteria decision making (MCDM) procedure. The proposed methodology comprises a first normalization step to adjust different scales and orientations of the criteria and a second step that includes the mathematical model to evaluate the performance of the shipbrokers’ services involved in the assessment. The criteria along which the shipbrokers are assessed may refer to their size and reputation, the potential efficiency of the services, the terms and conditions imposed, the expenses (e.g., commission – brokerage), the expected time to accomplish a chartering or selling/buying task, etc. and according to our modelling approach these criteria may be assigned different importance. The mathematical programming model performs a comparative assessment and estimates for the shipbrokers involved in the evaluation, a relative score that ranks the shipbrokers in terms of their potential performance. To illustrate the proposed methodology, we present a case study in which a shipping company evaluates and selects the most suitable among a number of sale and purchase (S&P) brokers. Acknowledgment: This study is supported by the OptiShip project, implemented within the framework of the National Recovery Plan and Resilience “Greece 2.0” and funded by the European Union – NextGenerationEU programme.

Keywords: shipbrokers, multi-criteria decision making, mathematical programming, service-provider selection

Procedia PDF Downloads 89

Authors: V. S. Klimash, Ye Min Thu

Abstract:

Thyristor rectifiers, inverters grid-tied, and AC voltage regulators are widely used in industry, and on electrified transport, they have a lot in common both in the power circuit and in the control system. They have a common mathematical structure and switching processes. At the same time, the rectifier, but the inverter units and thyristor regulators of alternating voltage are considered separately both theoretically and practically. They are written about in different books as completely different devices. The aim of this work is to combine them into one class based on the unity of the equations describing electromagnetic processes, and then, to show this unity on the mathematical model and experimental setup. Based on research from mathematics to the product, a conclusion is made about the methodology for the rapid conduct of research and experimental design work, preparation for production and serial production of converters with a unified bundle. In recent years, there has been a transition from thyristor circuits and transistor in modular design. Showing the example of thyristor rectifiers and AC voltage regulators, we can conclude that there is a unity of mathematical structures and grid-tied thyristor converters.

Keywords: direct current, alternating current, rectifier, AC voltage regulator, generalized mathematical model

Procedia PDF Downloads 250

Authors: Hongyu Chen, Li Jiang

Abstract:

Ubiquitous anomalies endanger the security of our system con- stantly. They may bring irreversible damages to the system and cause leakage of privacy. Thus, it is of vital importance to promptly detect these anomalies. Traditional supervised methods such as Decision Trees and Support Vector Machine (SVM) are used to classify normality and abnormality. However, in some case, the abnormal status are largely rarer than normal status, which leads to decision bias of these methods. Generative adversarial network (GAN) has been proposed to handle the case. With its strong generative ability, it only needs to learn the distribution of normal status, and identify the abnormal status through the gap between it and the learned distribution. Nevertheless, existing GAN-based models are not suitable to process data with discrete values, leading to immense degradation of detection performance. To cope with the discrete features, in this paper, we propose an efficient GAN-based model with specifically-designed loss function. Experiment results show that our model outperforms state-of-the-art models on discrete dataset and remarkably reduce the overhead.

Keywords: GAN, discrete feature, Wasserstein distance, multiple intermediate layers

Procedia PDF Downloads 129

Authors: Pablo Martinez, Emad Mohamed, Osama Mohsen, Yasser Mohamed

Abstract:

Highway and bridge agencies, such as the Ministry of Transportation in Ontario, use the Bridge Condition Index (BCI) which is defined as the weighted condition of all bridge elements to determine the rehabilitation priorities for its bridges. Therefore, accurate forecasting of BCI is essential for bridge rehabilitation budgeting planning. The large amount of data available in regard to bridge conditions for several years dictate utilizing traditional mathematical models as infeasible analysis methods. This research study focuses on investigating different classification models that are developed to predict the bridge condition index in the province of Ontario, Canada based on the publicly available data for 2800 bridges over a period of more than 10 years. The data preparation is a key factor to develop acceptable classification models even with the simplest one, the k-NN model. All the models were tested, compared and statistically validated via cross validation and t-test. A simple k-NN model showed reasonable results (within 0.5% relative error) when predicting the bridge condition in an incoming year.

Keywords: asset management, bridge condition index, data mining, forecasting, infrastructure, knowledge discovery in databases, maintenance, predictive models

Procedia PDF Downloads 191

Authors: Amin Sedighfar, M. R. Moniri

Abstract:

Determination of state of charge (SOC) in today’s world becomes an increasingly important issue in all the applications that include a battery. In fact, estimation of the SOC is a fundamental need for the battery, which is the most important energy storage in Hybrid Electric Vehicles (HEVs), smart grid systems, drones, UPS and so on. Regarding those applications, the SOC estimation algorithm is expected to be precise and easy to implement. This paper presents an online method for the estimation of the SOC of Valve-Regulated Lead Acid (VRLA) batteries. The proposed method uses the well-known Kalman Filter (KF), and Neural Networks (NNs) and all of the simulations have been done with MATLAB software. The NN is trained offline using the data collected from the battery discharging process. A generic cell model is used, and the underlying dynamic behavior of the model has used two capacitors (bulk and surface) and three resistors (terminal, surface, and end), where the SOC determined from the voltage represents the bulk capacitor. The aim of this work is to compare the performance of conventional integration-based SOC estimation methods with a mixed algorithm. Moreover, by containing the effect of temperature, the final result becomes more accurate. 

Keywords: Kalman filter, neural networks, state-of-charge, VRLA battery

Procedia PDF Downloads 193

Authors: Ninlawat Phuangchoke, Waraporn Viyanon, Setta Sasananan

Abstract:

The most important process of the water treatment plant process is the coagulation using alum and poly aluminum chloride (PACL), and the value of usage per day is a hundred thousand baht. Therefore, determining the dosage of alum and PACL are the most important factors to be prescribed. Water production is economical and valuable. This research applies an artificial neural network (ANN), which uses the Levenberg–Marquardt algorithm to create a mathematical model (Soft Jar Test) for prediction chemical dose used to coagulation such as alum and PACL, which input data consists of turbidity, pH, alkalinity, conductivity, and, oxygen consumption (OC) of Bangkhen water treatment plant (BKWTP) Metropolitan Waterworks Authority. The data collected from 1 January 2019 to 31 December 2019 cover changing seasons of Thailand. The input data of ANN is divided into three groups training set, test set, and validation set, which the best model performance with a coefficient of determination and mean absolute error of alum are 0.73, 3.18, and PACL is 0.59, 3.21 respectively.

Keywords: soft jar test, jar test, water treatment plant process, artificial neural network

Procedia PDF Downloads 167

Authors: Elzo Alves Aranha, Marcio M. Araki

Abstract:

Business model (BM) is a term that has been receiving the attention of scholars and practitioners and has been consolidating itself as a field of study and research. Although there is no agreement in the academic literature on the definition of BM, at least there is an explicit agreement: BM defines a logical structure of how an organization creates value, capture value and delivers value for the customers and stakeholders. The lack of understanding about connections and elements among BM and higher education, university, and entrepreneurship education opens a gap in the academic literature. Thus, it is interesting to analyze how BM has been approached by the literature and applied in higher education, university, and entrepreneurship education aimed to know the main streams of research. This is because higher education institutions are characterized by innovation, leading to a greater acceptance of new and modern concepts such as BM. Our research has the main motivation to fill the gap in the academic literature, making it possible to increase the power of understanding about connections and aspects among BM and higher education, university, and entrepreneurship education. The objective of the research is to analyze the main aspects among BM and higher education, university, and entrepreneurship education in academic literature. The research followed the systematic literature review (SLR). The SLR is based on three main factors: clarity, validity, and auditability. 82 academic papers were found in the past 10 years, from 2009-2019. The search was carried out in Science Direct and Periodicos Capes databases. The main findings indicate that there are links between BM and higher education, BM and university, BM, and entrepreneurship education. The main findings are inserted within seven aspects. The findings are innovative and contribute to increase the power of understanding about the connection among BM and higher education, university, and entrepreneurship education in academic literature. The research findings addressed to the gap exposed in academic literature. The research findings have several practical implications, and we highlight only two main ones. First, researchers will be able to use the research findings to mitigate a BM research agenda involving connections between BM and higher education, BM and university, and BM and entrepreneurship education. Second, directors, deans, and university leaders will be able to carry out BM awareness programs, BM professors training programs, and makers planning for the inclusion of BM, as one of the components of the curricula of the undergraduate and graduate courses.

Keywords: business model, entrepreneurship education, higher education, university

Procedia PDF Downloads 187

Authors: Younes El Khchine, Mohammed Sriti

Abstract:

A parametric study has been conducted to analyse the flow around S809 airfoil of a wind turbine in order to better understand the characteristics and effects of laminar separation bubble (LSB) on aerodynamic design for maximizing wind turbine efficiency. Numerical simulations were performed at low Reynolds numbers by solving the Unsteady Reynolds Averaged Navier-Stokes (URANS) equations based on C-type structural mesh and using the γ-Reθt turbulence model. A two-dimensional study was conducted for the chord Reynolds number of 1×10⁵ and angles of attack (AoA) between 0 and 20.15 degrees. The simulation results obtained for the aerodynamic coefficients at various angles of attack (AoA) were compared with XFoil results. A sensitivity study was performed to examine the effects of Reynolds number and free-stream turbulence intensity on the location and length of the laminar separation bubble and the aerodynamic performances of wind turbines. The results show that increasing the Reynolds number leads to a delay in the laminar separation on the upper surface of the airfoil. The increase in Reynolds number leads to an accelerated transition process, and the turbulent reattachment point moves closer to the leading edge owing to an earlier reattachment of the turbulent shear layer. This leads to a considerable reduction in the length of the separation bubble as the Reynolds number is increased. The increase in the level of free-stream turbulence intensity leads to a decrease in separation bubble length and an increase in the lift coefficient while having negligible effects on the stall angle. When the AoA increased, the bubble on the suction airfoil surface was found to move upstream to the leading edge of the airfoil, that causes earlier laminar separation.

Keywords: laminar separation bubble, turbulence intensity, S809 airfoil, transition model, Reynolds number

Procedia PDF Downloads 83

Authors: Valentina Zhang

Abstract:

While facial expression is a complex and individualized behavior, all facial emotion recognition (FER) systems known to us rely on a single facial representation and are trained on universal data. We conjecture that: (i) different facial representations can provide different, sometimes complementing views of emotions; (ii) when employed collectively in a discussion group setting, they enable more accurate emotion reading which is highly desirable in autism care and other applications context sensitive to errors. In this paper, we first study FER using pixel-based DL vs semantics-based DL in the context of deepfake videos. Our experiment indicates that while the semantics-trained model performs better with articulated facial feature changes, the pixel-trained model outperforms on subtle or rare facial expressions. Armed with these findings, we have constructed an adaptive FER system learning from both types of models for dyadic or small interacting groups and further leveraging the synthesized group emotions as the ground truth for individualized FER training. Using a collection of group conversation videos, we demonstrate that FER accuracy and personalization can benefit from such an approach.

Keywords: neurodivergence care, facial emotion recognition, deep learning, ground truth for supervised learning

Procedia PDF Downloads 148