Search results for: and validation

Authors: M. C. Pardo-Ferreira, J. C. Rubio-Romero, M. Martínez-Rojas

Abstract:

Resilience Engineering is a new paradigm of safety management that proposes to change the way of managing the safety to focus on the things that go well instead of the things that go wrong. Many complex and high-risk sectors such as air traffic control, health care, nuclear power plants, railways or emergencies, have applied this new vision of safety and have obtained very positive results. In the construction sector, safety management continues to be a problem as indicated by the statistics of occupational injuries worldwide. Therefore, it is important to improve safety management in this sector. For this reason, it is proposed to apply Resilience Engineering to the construction sector. The Construction Phase Health and Safety Plan emerges as a key element for the planning of safety management. One of the key tools of Resilience Engineering is the Resilience Assessment Grid that allows measuring the four essential abilities (respond, monitor, learn and anticipate) for resilient performance. The purpose of this paper is to develop a questionnaire based on the Resilience Assessment Grid, specifically on the ability to learn, to assess whether a Construction Phase Health and Safety Plans helps companies in a construction site to implement this ability. The research process was divided into four stages: (i) initial design of a questionnaire, (ii) validation of the content of the questionnaire, (iii) redesign of the questionnaire and (iii) application of the Delphi method. The questionnaire obtained could be used as a tool to help construction companies to evolve from Safety-I to Safety-II. In this way, companies could begin to develop the ability to learn, which will serve as a basis for the development of the other abilities necessary for resilient performance. The following steps in this research are intended to develop other questions that allow evaluating the rest of abilities for resilient performance such as monitoring, learning and anticipating.

Keywords: resilience engineering, construction sector, resilience assessment grid, construction phase health and safety plan

Procedia PDF Downloads 137

Authors: Nurul Mazni Abdullah, Saw Kian Cheah, Raha Abdul Rahman, Qurratu 'Aini Musthafa

Abstract:

Purpose: Candidemia was associated with high mortality in the critically ill patients. Early candidemia prediction is imperative for preemptive antifungal treatment. This study aimed to externally validate the candidemia risk prediction scores by Jameran et al. (2021) by identifying risk factors of acute kidney injury, renal replacement therapy, parenteral nutrition, and multifocal candida colonization. Methods: This single-center, retrospective observational study included all critically ill patients admitted to the intensive care unit (ICU) in a tertiary referral center from January 2018 to December 2023. The study evaluated the candidemia risk prediction score performance by analysing the occurrence of candidemia within the study period. Patients’ demographic characteristics, comorbidities, SOFA scores, and ICU outcomes were analyzed. Patients who were diagnosed with candidemia prior to ICU admission were excluded. Results: A total of 500 patients were analyzed with 2 dropouts due to incomplete data. Validation analysis showed that the candidemia risk prediction score has a sensitivity of 75.00% (95% CI: 59.66-86.81), specificity of 65.35% (95% CI: 60.78-69.72), positive predictive value of 17.28, and negative predictive value of 96.44. The incidence of candidemia was 8.86%, with no significant differences in demographics or comorbidities except for higher SOFA scoring in the candidemia group. The candidemia group showed significantly longer ICU, hospital LOS, and higher ICU in-hospital mortality. Conclusion: This study concluded the candidemia risk prediction score by Jameran et al. (2021) had good sensitivity and a high negative prediction value. Thus, the risk prediction score was validated for candidemia prediction in critically ill patients.

Keywords: Candidemia, intensive care, acute kidney injury, clinical prediction rule, incidence

Procedia PDF Downloads 7

Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed

Abstract:

The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.

Keywords: streamflow, neural network, optimisation, algorithm

Procedia PDF Downloads 152

Authors: A. Ramachandra Reddy, V. Murugan, Prema Kumari

Abstract:

Residual solvents in Pharmaceutical samples are monitored using gas chromatography with headspace (GC-HS). Based on current regulatory and compendial requirements, measuring the residual solvents are mandatory for all release testing of active pharmaceutical ingredients (API). Generally, isopropyl alcohol is used as the residual solvent in proline and tryptophan; methanol in cysteine monohydrate hydrochloride, glycine, methionine and serine; ethanol in glycine and lysine monohydrate; acetic acid in methionine. In order to have a single method for determining these residual solvents (isopropyl alcohol, ethanol, methanol and acetic acid) in all these 7 amino acids a sensitive and simple method was developed by using gas chromatography headspace technique with flame ionization detection. During development, no reproducibility, retention time variation and bad peak shape of acetic acid peaks were identified due to the reaction of acetic acid with the stationary phase (cyanopropyl dimethyl polysiloxane phase) of column and dissociation of acetic acid with water (if diluent) while applying temperature gradient. Therefore, dimethyl sulfoxide was used as diluent to avoid these issues. But most the methods published for acetic acid quantification by GC-HS uses derivatisation technique to protect acetic acid. As per compendia, risk-based approach was selected as appropriate to determine the degree and extent of the validation process to assure the fitness of the procedure. Therefore, Total error concept was selected to validate the analytical procedure. An accuracy profile of ±40% was selected for lower level (quantitation limit level) and for other levels ±30% with 95% confidence interval (risk profile 5%). The method was developed using DB-Waxetr column manufactured by Agilent contains 530 µm internal diameter, thickness: 2.0 µm, and length: 30 m. A constant flow of 6.0 mL/min. with constant make up mode of Helium gas was selected as a carrier gas. The present method is simple, rapid, and accurate, which is suitable for rapid analysis of isopropyl alcohol, ethanol, methanol and acetic acid in amino acids. The range of the method for isopropyl alcohol is 50ppm to 200ppm, ethanol is 50ppm to 3000ppm, methanol is 50ppm to 400ppm and acetic acid 100ppm to 400ppm, which covers the specification limits provided in European pharmacopeia. The accuracy profile and risk profile generated as part of validation were found to be satisfactory. Therefore, this method can be used for testing of residual solvents in amino acids drug substances.

Keywords: amino acid, head space, gas chromatography, total error

Procedia PDF Downloads 148

Authors: Jamerson Felipe Pereira Lima, Jeane Cecília Bezerra de Melo

Abstract:

The difficulty and cost related to obtaining of protein tertiary structure information through experimental methods, such as X-ray crystallography or NMR spectroscopy, helped raising the development of computational methods to do so. An approach used in these last is prediction of tridimensional structure based in the residue chain, however, this has been proved an NP-hard problem, due to the complexity of this process, explained by the Levinthal paradox. An alternative solution is the prediction of intermediary structures, such as the secondary structure of the protein. Artificial Intelligence methods, such as Bayesian statistics, artificial neural networks (ANN), support vector machines (SVM), among others, were used to predict protein secondary structure. Due to its good results, artificial neural networks have been used as a standard method to predict protein secondary structure. Recent published methods that use this technique, in general, achieved a Q3 accuracy between 75% and 83%, whereas the theoretical accuracy limit for protein prediction is 88%. Alternatively, to achieve better results, support vector machines prediction methods have been developed. The statistical evaluation of methods that use different AI techniques, such as ANNs and SVMs, for example, is not a trivial problem, since different training sets, validation techniques, as well as other variables can influence the behavior of a prediction method. In this study, we propose a prediction method based on artificial neural networks, which is then compared with a selected SVM method. The chosen SVM protein secondary structure prediction method is the one proposed by Huang in his work Extracting Physico chemical Features to Predict Protein Secondary Structure (2013). The developed ANN method has the same training and testing process that was used by Huang to validate his method, which comprises the use of the CB513 protein data set and three-fold cross-validation, so that the comparative analysis of the results can be made comparing directly the statistical results of each method.

Keywords: artificial neural networks, protein secondary structure, protein structure prediction, support vector machines

Procedia PDF Downloads 621

Authors: N. Alias, W. Z. W. Muhammad, M. N. M. Ibrahim, M. Mohamed, H. F. S. Saipol, U. N. Z. Ariffin, N. A. Zakaria, M. S. Z. Suardi

Abstract:

This paper presents the performance comparison of some computation software for solving the boundary element method (BEM). BEM formulation is the numerical technique and high potential for solving the advance mathematical modeling to predict the production of oil well in arbitrarily shaped based on multiple leases reservoir. The limitation of data validation for ensuring that a program meets the accuracy of the mathematical modeling is considered as the research motivation of this paper. Thus, based on this limitation, there are three steps involved to validate the accuracy of the oil production simulation process. In the first step, identify the mathematical modeling based on partial differential equation (PDE) with Poisson-elliptic type to perform the BEM discretization. In the second step, implement the simulation of the 2D BEM discretization using COMSOL Multiphysic and MATLAB programming languages. In the last step, analyze the numerical performance indicators for both programming languages by using the validation of Fortran programming. The performance comparisons of numerical analysis are investigated in terms of percentage error, comparison graph and 2D visualization of pressure on oil production of multiple leases reservoir. According to the performance comparison, the structured programming in Fortran programming is the alternative software for implementing the accurate numerical simulation of BEM. As a conclusion, high-level language for numerical computation and numerical performance evaluation are satisfied to prove that Fortran is well suited for capturing the visualization of the production of oil well in arbitrarily shaped.

Keywords: performance comparison, 2D visualization, COMSOL multiphysic, MATLAB, Fortran, modelling and simulation, boundary element method, reservoir pressure

Procedia PDF Downloads 491

Authors: Pascal Mwenge, Tumisang Seodigeng

Abstract:

The combination of world population and the third industrial revolution led to high demand for fuels. On the other hand, the decrease of global fossil 8fuels deposits and the environmental air pollution caused by these fuels has compounded the challenges the world faces due to its need for energy. Therefore, new forms of environmentally friendly and renewable fuels such as biodiesel are needed. The primary analytical techniques for methanolysis yield monitoring have been chromatography and spectroscopy, these methods have been proven reliable but are more demanding, costly and do not provide real-time monitoring. In this work, the in situ monitoring of biodiesel from sunflower oil using FTIR (Fourier Transform Infrared) has been studied; the study was performed using EasyMax Mettler Toledo reactor equipped with a DiComp (Diamond) probe. The quantitative monitoring of methanolysis was performed by building a quantitative model with multivariate calibration using iC Quant module from iC IR 7.0 software. 15 samples of known concentrations were used for the modelling which were taken in duplicate for model calibration and cross-validation, data were pre-processed using mean centering and variance scale, spectrum math square root and solvent subtraction. These pre-processing methods improved the performance indexes from 7.98 to 0.0096, 11.2 to 3.41, 6.32 to 2.72, 0.9416 to 0.9999, RMSEC, RMSECV, RMSEP and R2Cum, respectively. The R² value of 1 (training), 0.9918 (test), 0.9946 (cross-validation) indicated the fitness of the model built. The model was tested against univariate model; small discrepancies were observed at low concentration due to unmodelled intermediates but were quite close at concentrations above 18%. The software eliminated the complexity of the Partial Least Square (PLS) chemometrics. It was concluded that the model obtained could be used to monitor methanol of sunflower oil at industrial and lab scale.

Keywords: biodiesel, calibration, chemometrics, methanolysis, multivariate analysis, transesterification, FTIR

Procedia PDF Downloads 148

Authors: Kherbache Mehdi

Abstract:

Within the framework of the validation of the Master in business administration marketing and sales in INSIM institute international in management Blida, we get the opportunity to do a professional internship in Sonelgaz Enterprise and a thesis. The thesis deals with the integration of social networking in the communication strategy of a company. The problematic is: How communicate with social network can be a solution for companies? The challenges stressed by this thesis were to suggest limits and recommendations to Sonelgaz Enterprise concerning social networks. The whole social networks represent more than a billion people as a potential target for the companies. Thanks to research and a qualitative approach, we have identified tree valid hypothesis. The first hypothesis allows confirming that using social networks cannot be ignored by any company in its communication strategy. However, the second hypothesis demonstrates that it’s necessary to prepare a strategy that integrates social networks in the communication plan of the company. The risk of this strategy is very limited because failure on social networks is not a restraint for the enterprise, social networking is not expensive and, a bad image which could result from it is not as important in the long-term. Furthermore, the return on investment is difficult to evaluate. Finally, the last hypothesis shows that firms establish a new relation between consumers and brands thanks to the proximity allowed by social networks. After the validation of the hypothesis, we suggested some recommendations to Sonelgaz Enterprise regarding the communication through social networks. Firstly, the company must use the interactivity of social network in order to have fruitful exchanges with the community. We also recommended having a strategy to treat negative comments. The company must also suggest delivering resources to the community thanks to a community manager, in order to have a good relation with the community. Furthermore, we advised using social networks to do business intelligence. Sonelgaz Enterprise can have some creative and interactive contents with some amazing applications on Facebook for example. Finally, we recommended to the company to be not intrusive with “fans” or “followers” and to be open to all the platforms: Twitter, Facebook, Linked-In for example.

Keywords: social network, buzz, communication, consumer, return on investment, internet users, web 2.0, Facebook, Twitter, interaction

Procedia PDF Downloads 422

Authors: Ella Sèdé Maforikan

Abstract:

Sustained water management requires quantitative information and the knowledge of spatiotemporal dynamics of hydrological system within the basin. This can be achieved through the research. Several studies have investigated both surface water and groundwater in Beterou catchment. However, there are few published papers on the application of the SWAT modeling in Beterou catchment. The objective of this study was to evaluate the performance of SWAT to simulate the water balance within the watershed. The inputs data consist of digital elevation model, land use maps, soil map, climatic data and discharge records. The model was calibrated and validated using the Sequential Uncertainty Fitting (SUFI2) approach. The calibrated started from 1989 to 2006 with four years warming up period (1985-1988); and validation was from 2007 to 2020. The goodness of the model was assessed using five indices, i.e., Nash–Sutcliffe efficiency (NSE), the ratio of the root means square error to the standard deviation of measured data (RSR), percent bias (PBIAS), the coefficient of determination (R²), and Kling Gupta efficiency (KGE). Results showed that SWAT model successfully simulated river flow in Beterou catchment with NSE = 0.79, R2 = 0.80 and KGE= 0.83 for the calibration process against validation process that provides NSE = 0.78, R2 = 0.78 and KGE= 0.85 using site-based streamflow data. The relative error (PBIAS) ranges from -12.2% to 3.1%. The parameters runoff curve number (CN2), Moist Bulk Density (SOL_BD), Base Flow Alpha Factor (ALPHA_BF), and the available water capacity of the soil layer (SOL_AWC) were the most sensitive parameter. The study provides further research with uncertainty analysis and recommendations for model improvement and provision of an efficient means to improve rainfall and discharges measurement data.

Keywords: watershed, water balance, SWAT modeling, Beterou

Procedia PDF Downloads 55

Authors: Mohamed Moussaoui

Abstract:

A series of thirty-one potential inhibitors targeting the epidermal growth factor receptor kinase (EGFR), derived from quinazoline, underwent 3D-QSAR analysis using CoMFA and CoMSIA methodologies. The training and test sets of quinazoline derivatives were utilized to construct and validate the QSAR models, respectively, with dataset alignment performed using the lowest energy conformer of the most active compound. The best-performing CoMFA and CoMSIA models demonstrated impressive determination coefficients, with R² values of 0.981 and 0.978, respectively, and Leave One Out cross-validation determination coefficients, Q², of 0.645 and 0.729, respectively. Furthermore, external validation using a test set of five compounds yielded predicted determination coefficients, R² test, of 0.929 and 0.909 for CoMFA and CoMSIA, respectively. Building upon these promising results, eighteen new compounds were designed and assessed for drug likeness and ADMET properties through in silico methods. Additionally, molecular docking studies were conducted to elucidate the binding interactions between the selected compounds and the enzyme. Detailed molecular dynamics simulations were performed to analyze the stability, conformational changes, and binding interactions of the quinazoline derivatives with the EGFR kinase. These simulations provided deeper insights into the dynamic behavior of the compounds within the active site. This comprehensive analysis enhances the understanding of quinazoline derivatives as potential anti-cancer agents and provides valuable insights for lead optimization in the early stages of drug discovery, particularly for developing highly potent anticancer therapeutics

Keywords: 3D-QSAR, CoMFA, CoMSIA, ADMET, molecular docking, quinazoline, molecular dynamic, egfr inhibitors, lung cancer, anticancer

Procedia PDF Downloads 48

Authors: S. Hammoudeh, S. Ghuloum, A. Abdelhakam, A. AlMujalli, M. Opler, Y. Hani, A. Yehya, S. Mari, R. Elsherbiny, Z. Mahfoud, H. Al-Amin

Abstract:

Introduction: Suicidal ideation and attempts are very common in patients with schizophrenia and still contributes to the high mortality in this population. The InterSePT Scale for Suicidal Thinking (ISST) is a validated tool used to assess suicidal ideation in patients with schizophrenia. This research aims to validate the Arabic version of the ISST among the Arabs residing in Qatar. Methods: Patients diagnosed with schizophrenia were recruited from the department of Psychiatry, Rumailah Hospital, Doha, Qatar. Healthy controls were recruited from the primary health care centers in Doha, Qatar. The validation procedures including professional and expert translation, pilot survey and back translation of the ISST were implemented. Diagnosis of schizophrenia was confirmed using the validated Arabic version of Mini International Neuropsychiatric Interview (MINI 6, module K) for schizophrenia. The gold standard was the module B on suicidality from MINI 6 also. This module was administered by a rater who was blinded to the results of ISST. Results: Our sample (n=199) was composed of 98 patients diagnosed with schizophrenia (age 36.03 ± 9.88 years; M/F is 2/1) and 101 healthy participants (age 35.01 ± 8.23 years; M/F is 1/2). Among patients with schizophrenia: 26.5% were married, 17.3% had a college degree, 28.6% were employed, 9% had committed suicide once, and 4.4% had more than 4 suicide attempts. Among the control group: 77.2% were married, 57.4% had a college degree, and 99% were employed. The mean score on the ISST was 2.36 ± 3.97 vs. 0.47 ± 1.44 for the schizophrenia and control groups, respectively. The overall Cronbach’s alpha was 0.91. Conclusions: This is the first study in the Arab world to validate the ISST in an Arabic-based population. The psychometric properties indicate that the Arabic version of the ISST is a valid tool to assess the severity of suicidal ideation in Arabic speaking patients diagnosed with schizophrenia.

Keywords: mental health, Qatar, schizophrenia, suicide

Procedia PDF Downloads 562

Authors: Ahmad Ammar, Umar Khan Khattak, Muhammad Majid

Abstract:

Empirically based lumped hydrologic models have an extensive track record of use for various watershed managements and flood related studies. This study focuses on the impacts of LULC change for 10 year period on the discharge in watershed using lumped model HEC-HMS. The Indus above Tarbela region acts as a source of the main flood events in the middle and lower portions of Indus because of the amount of rainfall and topographic setting of the region. The discharge pattern of the region is influenced by the LULC associated with it. In this study the Landsat TM images were used to do LULC analysis of the watershed. Satellite daily precipitation TRMM data was used as input rainfall. The input variables for model building in HEC-HMS were then calculated based on the GIS data collected and pre-processed in HEC-GeoHMS. SCS-CN was used as transform model, SCS unit hydrograph method was used as loss model and Muskingum was used as routing model. For discharge simulation years 2000 and 2010 were taken. HEC-HMS was calibrated for the year 2000 and then validated for 2010.The performance of the model was assessed through calibration and validation process and resulted R2=0.92 during calibration and validation. Relative Bias for the years 2000 was -9% and for2010 was -14%. The result shows that in 10 years the impact of LULC change on discharge has been negligible in the study area overall. One reason is that, the proportion of built-up area in the watershed, which is the main causative factor of change in discharge, is less than 1% of the total area. However, locally, the impact of development was found significant in built up area of Mansehra city. The analysis was done on Mansehra city sub-watershed with an area of about 16 km2 and has more than 13% built up area in 2010. The results showed that with an increase of 40% built-up area in the city from 2000 to 2010 the discharge values increased about 33 percent, indicating the impact of LULC change on discharge value.

Keywords: LULC change, HEC-HMS, Indus Above Tarbela, SCS-CN

Procedia PDF Downloads 512

Authors: Mehmet Oren, Susan Pedersen, Sevket C. Cetin

Abstract:

Despite the frequently criticized disadvantages of the traditional used paper and pencil assessment, it is the most frequently used method in our schools. Although assessments do an acceptable measurement, they are not capable of measuring all the aspects and the richness of learning and knowledge. Also, many assessments used in schools decontextualize the assessment from the learning, and they focus on learners’ standing on a particular topic but do not concentrate on how student learning changes over time. For these reasons, many scholars advocate that using simulations and games (S&G) as a tool for assessment has significant potentials to overcome the problems in traditionally used methods. S&G can benefit from the change in technology and provide a contextualized medium for assessment and teaching. Furthermore, S&G can serve as an instructional tool rather than a method to test students’ learning at a particular time point. To investigate the potentials of using educational games as an assessment and teaching tool, this study presents the implementation and the validation of an automated embedded assessment (AEA), which can constantly monitor student learning in the game and assess their performance without intervening their learning. The experiment was conducted on an undergraduate level engineering course (Digital Circuit Design) with 99 participant students over a period of five weeks in Spring 2016 school semester. The purpose of this research study is to examine if the proposed method of AEA is valid to assess student learning in a 3D Educational game and present the implementation steps. To address this question, this study inspects three aspects of the AEA for the validation. First, the evidence-centered design model was used to lay out the design and measurement steps of the assessment. Then, a confirmatory factor analysis was conducted to test if the assessment can measure the targeted latent constructs. Finally, the scores of the assessment were compared with an external measure (a validated test measuring student learning on digital circuit design) to evaluate the convergent validity of the assessment. The results of the confirmatory factor analysis showed that the fit of the model with three latent factors with one higher order factor was acceptable (RMSEA < 0.00, CFI =1, TLI=1.013, WRMR=0.390). All of the observed variables significantly loaded to the latent factors in the latent factor model. In the second analysis, a multiple regression analysis was used to test if the external measure significantly predicts students’ performance in the game. The results of the regression indicated the two predictors explained 36.3% of the variance (R2=.36, F(2,96)=27.42.56, p<.00). It was found that students’ posttest scores significantly predicted game performance (β = .60, p < .000). The statistical results of the analyses show that the AEA can distinctly measure three major components of the digital circuit design course. It was aimed that this study can help researchers understand how to design an AEA, and showcase an implementation by providing an example methodology to validate this type of assessment.

Keywords: educational video games, automated embedded assessment, assessment validation, game-based assessment, assessment design

Procedia PDF Downloads 421

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: Mikiyas Adugna

Abstract:

Effort estimation is among the activities carried out in software development processes. An accurate model of estimation leads to project success. The method of agile effort estimation is a complex task because of the dynamic nature of software development. Researchers are still conducting studies on agile effort estimation to enhance prediction accuracy. Due to these reasons, we investigated and proposed a model on LASSO and Elastic Net regression to enhance estimation accuracy. The proposed model has major components: preprocessing, train-test split, training with default parameters, and cross-validation. During the preprocessing phase, the entire dataset is normalized. After normalization, a train-test split is performed on the dataset, setting training at 80% and testing set to 20%. We chose two different phases for training the two algorithms (Elastic Net and LASSO) regression following the train-test-split. In the first phase, the two algorithms are trained using their default parameters and evaluated on the testing data. In the second phase, the grid search technique (the grid is used to search for tuning and select optimum parameters) and 5-fold cross-validation to get the final trained model. Finally, the final trained model is evaluated using the testing set. The experimental work is applied to the agile story point dataset of 21 software projects collected from six firms. The results show that both Elastic Net and LASSO regression outperformed the compared ones. Compared to the proposed algorithms, LASSO regression achieved better predictive performance and has acquired PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The result implies LASSO regression algorithm trained model is the most acceptable, and higher estimation performance exists in the literature.

Keywords: agile software development, effort estimation, elastic net regression, LASSO

Procedia PDF Downloads 71

Authors: Catarina Belchior, Catarina Martins, Sara Mendes, Ana Rita S. Valente, Elsa Marta Soares

Abstract:

Introduction: The negative feelings and attitudes that a person who stutters can develop are extremely relevant when considering assessment and intervention in Speech and Language Therapy. This relates to the fact that the person who stutters can experience feelings such as shame, fear and negative beliefs when communicating. Considering the complexity and importance of integrating diverse aspects in stuttering intervention, it is central to identify those emotions as early as possible. Therefore, this research aimed to achieve the translation, adaptation to European Portuguese and to analyze the content validation of the Preschooler Awareness Stuttering Survey (Abbiati, Guitar & Hutchins, 2015), an instrument that allows the assessment of the impact of stuttering on preschool children who stutter considering feelings and attitudes. Methodology: Cross-sectional descriptive qualitative research. The following methodological procedures were followed: translation, back-translation, panel of experts and pilot study. This abstract describes the results of the first three phases of this process. The translation was accomplished by two Speech Language Therapists (SLT). Both professionals have more than five years of experience and are users of English language. One of them has a broad experience in the field of stuttering. Back-translation was conducted by two bilingual individuals without experience in health or any knowledge about the instrument. The panel of experts was composed by 3 different SLT, experts in the field of stuttering. Results and Discussion: In the translation and back-translation process it was possible to verify differences in semantic and idiomatic equivalences of several concepts and expressions, as well as the need to include new information to enhance the understanding of the application of the instrument. The meeting between the two translators and the researchers allowed the achievement of a consensus version that was used in back-translation. Considering adaptation and content validation, the main change made by the experts was the conceptual equivalence of the questions and answers of the instrument's sheets. Considering that in the translated consensus version the questions began with various nouns such as 'is' or 'the cow' and that the answers did not contain the adverb 'much' as in the original instrument, the panel agreed that it would be more appropriate if the questions all started with 'how' and that all the answers should present the adverb 'much'. This decision was made to ensure that the translate instrument would be similar to the original and so that the results obtained could be comparable between the original and the translated instrument. There was also elaborated one semantic equivalence between concepts. The panel of experts found that all other items and specificities of the instrument were adequate, concluding the adequacy of the instrument considering its objectives and its intended target population. Conclusion: This research aspires to diversify the existing validated resources in this scope, adding a new instrument that allows the assessment of preschool children who stutter. Consequently, it is hoped that this instrument will provide a real and reliable assessment that can lead to an appropriate therapeutic intervention according to the characteristics and needs of each child.

Keywords: stuttering, assessment, feelings and attitudes, speech language therapy

Procedia PDF Downloads 149

Authors: Mindaugas Liaudanskas, Darius Kviklys, Kristina Zymonė, Raimondas Raudonis, Jonas Viškelis, Norbertas Uselis, Pranas Viškelis, Valdimaras Janulis

Abstract:

Apples are among the most commonly consumed fruits in the world. Based on data from the year 2014, approximately 84.63 million tons of apples are grown per annum. Apples are widely used in food industry to produce various products and drinks (juice, wine, and cider); they are also used unprocessed. Apples in human diet are an important source of different groups of biological active compounds that can positively contribute to the prevention of various diseases. They are a source of various biologically active substances – especially vitamins, organic acids, micro- and macro-elements, pectins, and phenolic, triterpenic, and other compounds. Triterpenic compounds, which are characterized by versatile biological activity, are the biologically active compounds found in apples that are among the most promising and most significant for human health. A specific analytical procedure including sample preparation and High Performance Liquid Chromatography (HPLC) analysis was developed, optimized, and validated for the detection of triterpenic compounds in the samples of different apples, their peels, and flesh from widespread apple cultivars 'Aldas', 'Auksis', 'Connel Red', 'Ligol', 'Lodel', and 'Rajka' grown in Lithuanian climatic conditions. The conditions for triterpenic compound extraction were optimized: the solvent of the extraction was 100% (v/v) acetone, and the extraction was performed in an ultrasound bath for 10 min. Isocratic elution (the eluents ratio being 88% (solvent A) and 12% (solvent B)) for a rapid separation of triterpenic compounds was performed. The validation of the methodology was performed on the basis of the ICH recommendations. The following characteristics of validation were evaluated: the selectivity of the method (specificity), precision, the detection and quantitation limits of the analytes, and linearity. The obtained parameters values confirm suitability of methodology to perform analysis of triterpenic compounds. Using the optimised and validated HPLC technique, four triterpenic compounds were separated and identified, and their specificity was confirmed. These compounds were corosolic acid, betulinic acid, oleanolic acid, and ursolic acid. Ursolic acid was the dominant compound in all the tested apple samples. The detected amount of betulinic acid was the lowest of all the identified triterpenic compounds. The greatest amounts of triterpenic compounds were detected in whole apple and apple peel samples of the 'Lodel' cultivar, and thus apples and apple extracts of this cultivar are potentially valuable for use in medical practice, for the prevention of various diseases, for adjunct therapy, for the isolation of individual compounds with a specific biological effect, and for the development and production of dietary supplements and functional food enriched in biologically active compounds. Acknowledgements. This work was supported by a grant from the Research Council of Lithuania, project No. MIP-17-8.

Keywords: apples, HPLC, triterpenic compounds, validation

Procedia PDF Downloads 173

Authors: Pinna Beatrice., Laini Alex, Negro Giovanni, Burgazzi Gemma, Viaroli Pierluigi, Vezza Paolo

Abstract:

Habitat models rarely consider macroinvertebrates as ecological targets in rivers. Available approaches mainly focus on single macroinvertebrate species, not addressing the ecological needs and functionality of the entire community. This research aimed to provide an approach to model the habitat of the macroinvertebrate community. The approach is based on the recently developed Flow-T index, together with a Random Forest (RF) regression, which is employed to apply the Flow-T index at the meso-habitat scale. Using different datasets gathered from both field data collection and 2D hydrodynamic simulations, the model has been calibrated in the Trebbia river (2019 campaign), and then validated in the Trebbia, Taro, and Enza rivers (2020 campaign). The three rivers are characterized by a braiding morphology, gravel riverbeds, and summer low flows. The RF model selected 12 mesohabitat descriptors as important for the macroinvertebrate community. These descriptors belong to different frequency classes of water depth, flow velocity, substrate grain size, and connectivity to the main river channel. The cross-validation R² coefficient (R²𝒸ᵥ) of the training dataset is 0.71 for the Trebbia River (2019), whereas the R² coefficient for the validation datasets (Trebbia, Taro, and Enza Rivers 2020) is 0.63. The agreement between the simulated results and the experimental data shows sufficient accuracy and reliability. The outcomes of the study reveal that the model can identify the ecological response of the macroinvertebrate community to possible flow regime alterations and to possible river morphological modifications. Lastly, the proposed approach allows extending the MesoHABSIM methodology, widely used for the fish habitat assessment, to a different ecological target community. Further applications of the approach can be related to flow design in both perennial and non-perennial rivers, including river reaches in which fish fauna is absent.

Keywords: ecological flows, macroinvertebrate community, mesohabitat, river habitat modeling

Procedia PDF Downloads 94

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

Abstract:

Quantitative structure-retention relationship (QSRR) analysis was used to predict the chromatographic behavior of s-triazine derivatives by using theoretical descriptors computed from the chemical structure. Fundamental basis of the reported investigation is to relate molecular topological descriptors with chromatographic behavior of s-triazine derivatives obtained by reversed-phase (RP) thin layer chromatography (TLC) on silica gel impregnated with paraffin oil and applied ethanol-water (φ = 0.5-0.8; v/v). Retention parameter (RM0) of 14 investigated s-triazine derivatives was used as dependent variable while simple connectivity index different orders were used as independent variables. The best QSRR model for predicting RM0 value was obtained with simple third order connectivity index (3χ) in the second-degree polynomial equation. Numerical values of the correlation coefficient (r=0.915), Fisher's value (F=28.34) and root mean square error (RMSE = 0.36) indicate that model is statistically significant. In order to test the predictive power of the QSRR model leave-one-out cross-validation technique has been applied. The parameters of the internal cross-validation analysis (r2CV=0.79, r2adj=0.81, PRESS=1.89) reflect the high predictive ability of the generated model and it confirms that can be used to predict RM0 value. Multivariate classification technique, hierarchical cluster analysis (HCA), has been applied in order to group molecules according to their molecular connectivity indices. HCA is a descriptive statistical method and it is the most frequently used for important area of data processing such is classification. The HCA performed on simple molecular connectivity indices obtained from the 2D structure of investigated s-triazine compounds resulted in two main clusters in which compounds molecules were grouped according to the number of atoms in the molecule. This is in agreement with the fact that these descriptors were calculated on the basis of the number of atoms in the molecule of the investigated s-triazine derivatives.

Keywords: s-triazines, QSRR, chemometrics, chromatography, molecular descriptors

Procedia PDF Downloads 393

Authors: Lorenzo Cocola, Massimo Fedel, Dragiša Savić, Bojana Danilović, Luca Poletto

Abstract:

An instrument for the detection and evaluation of gaseous carbon dioxide in the headspace of closed containers has been developed in the context of Packsensor Italian-Serbian joint project. The device is based on Tunable Diode Laser Absorption Spectroscopy (TDLAS) with a Wavelength Modulation Spectroscopy (WMS) technique in order to accomplish a non-invasive measurement inside closed containers of fermented dairy products (yogurts and fermented cheese in cups and bottles). The purpose of this instrument is the continuous monitoring of carbon dioxide concentration during incubation and storage of products over a time span of the whole shelf life of the product, in the presence of different microorganisms. The instrument’s optical front end has been designed to be integrated in a thermally stabilized incubator. An embedded computer provides processing of spectral artifacts and storage of an arbitrary set of calibration data allowing a properly calibrated measurement on many samples (cups and bottles) of different shapes and sizes commonly found in the retail distribution. A calibration protocol has been developed in order to be able to calibrate the instrument on the field also on containers which are notoriously difficult to seal properly. This calibration protocol is described and evaluated against reference measurements obtained through an industry standard (sampling) carbon dioxide metering technique. Some sets of validation test measurements on different containers are reported. Two test recordings of carbon dioxide concentration evolution are shown as an example of instrument operation. The first demonstrates the ability to monitor a rapid yeast growth in a contaminated sample through the increase of headspace carbon dioxide. Another experiment shows the dissolution transient with a non-saturated liquid medium in presence of a carbon dioxide rich headspace atmosphere.

Keywords: TDLAS, carbon dioxide, cups, headspace, measurement

Procedia PDF Downloads 324

Authors: Mercedes Bertotto, Marcelo Bello, Hector Goicoechea, Veronica Fusca

Abstract:

The National Service of Agri-Food Health and Quality (SENASA), controls honey to detect contamination by synthetic or natural chemical substances and establishes and controls the traceability of the product. The utility of near-infrared spectroscopy for the detection of adulteration of honey with high fructose corn syrup (HFCS) was investigated. First of all, a mixture of different authentic artisanal Argentinian honey was prepared to cover as much heterogeneity as possible. Then, mixtures were prepared by adding different concentrations of high fructose corn syrup (HFCS) to samples of the honey pool. 237 samples were used, 108 of them were authentic honey and 129 samples corresponded to honey adulterated with HFCS between 1 and 10%. They were stored unrefrigerated from time of production until scanning and were not filtered after receipt in the laboratory. Immediately prior to spectral collection, honey was incubated at 40°C overnight to dissolve any crystalline material, manually stirred to achieve homogeneity and adjusted to a standard solids content (70° Brix) with distilled water. Adulterant solutions were also adjusted to 70° Brix. Samples were measured by NIR spectroscopy in the range of 650 to 7000 cm⁻¹. The technique of specular reflectance was used, with a lens aperture range of 150 mm. Pretreatment of the spectra was performed by Standard Normal Variate (SNV). The ant colony optimization genetic algorithm sample selection (ACOGASS) graphical interface was used, using MATLAB version 5.3, to select the variables with the greatest discriminating power. The data set was divided into a validation set and a calibration set, using the Kennard-Stone (KS) algorithm. A combined method of Potential Functions (PF) was chosen together with Partial Least Square Linear Discriminant Analysis (PLS-DA). Different estimators of the predictive capacity of the model were compared, which were obtained using a decreasing number of groups, which implies more demanding validation conditions. The optimal number of latent variables was selected as the number associated with the minimum error and the smallest number of unassigned samples. Once the optimal number of latent variables was defined, we proceeded to apply the model to the training samples. With the calibrated model for the training samples, we proceeded to study the validation samples. The calibrated model that combines the potential function methods and PLSDA can be considered reliable and stable since its performance in future samples is expected to be comparable to that achieved for the training samples. By use of Potential Functions (PF) and Partial Least Square Linear Discriminant Analysis (PLS-DA) classification, authentic honey and honey adulterated with HFCS could be identified with a correct classification rate of 97.9%. The results showed that NIR in combination with the PT and PLS-DS methods can be a simple, fast and low-cost technique for the detection of HFCS in honey with high sensitivity and power of discrimination.

Keywords: adulteration, multivariate analysis, potential functions, regression

Procedia PDF Downloads 125

Authors: Anh Nguyen, Jane Fisher, Thach Tran, Anh T. T. Tran

Abstract:

Trait Emotional Intelligence is the knowledge, beliefs, and attitudes an individual has about their own and other people’s emotions. It is believed that trait emotional intelligence is a component of personality. Petrides’ Trait Emotional Intelligence Questionnaire (TEIQue) is well regarded and well-established, with validation data about its functioning among adults from many countries. However, there is little data yet about its use among Asian populations, including adolescents. The aims were to translate and culturally verify the Trait Emotional Intelligence Adolescent Short Form (TEIQue-ASF) and investigate content validity, construct validity, and reliability among adolescents attending high schools in Vietnam. Content of the TEIQue-ASF was translated (English to Vietnamese) and back-translated (Vietnamese to English) in consultation with bilingual and bicultural health researchers and pilot tested among 51 potential respondents. Phraseology and wording were then adjusted and the final version is named the VN-TEIQue-ASF. The VN-TEIQue-ASF’s properties were investigated in a cross-sectional elf-report survey among high school students in Central Vietnam. In total 1,546 / 1,573 (98.3%) eligible students from nine high schools in rural, urban, and coastline areas completed the survey. Explanatory Factor Analysis yielded a four-factor solution, including some with facets that loaded differently compared to the original version: Well-being, Emotion in Relationships, Emotion Self-management, and Emotion Sensitivity. The Cronbach’s alpha of the global score for the VN-TEIQue-ASF was .77. The VN-TEIQue-ASF is comprehensible and has good content and construct validity and reliability among adolescents in Vietnam. The factor structure is only partly replicated the original version. The VN-TEIQue-ASF is recommended for use in school or community surveys and professional study in education, psychology, and public health to investigate the trait emotional intelligence of adolescents in Vietnam.

Keywords: adolescents, construct validity, content validity, factor analysis, questionnaire validity, trait emotional intelligence, Vietnam

Procedia PDF Downloads 268

Authors: Mehari Teshome, Lara Agostini, Anna Nosella

Abstract:

The current knowledge-based economy extends intellectual property rights (IPRs) legal research themes into a more strategic and organizational perspectives. From the diverse types of IPRs, patents are the strongest and well-known form of legal protection that influences commercial success and market value. Indeed, from our pilot survey, we understood that firms are less likely to manage their patents and actively used it as a tool for achieving competitive advantage rather they invest resource and efforts for patent application. To this regard, the literature also confirms that insights into how firms manage their patents from a holistic, strategic perspective, and how the portfolio value of patents can be optimized are scarce. Though patent management is an important business tool and there exist few scales to measure some dimensions of patent management, at the best of our knowledge, no systematic attempt has been made to develop a valid and comprehensive measure of it. Considering this theoretical and practical point of view, the aim of this article is twofold: to develop a framework for patent management encompassing all relevant dimensions with their respective constructs and measurement items, and to validate the measurement using survey data from practitioners. Methodology: We used six-step methodological approach (i.e., specify the domain of construct, item generation, scale purification, internal consistency assessment, scale validation, and replication). Accordingly, we carried out a systematic review of 182 articles on patent management, from ISI Web of Science. For each article, we mapped relevant constructs, their definition, and associated features, as well as items used to measure these constructs, when provided. This theoretical analysis was complemented by interviews with experts in patent management to get feedbacks that are more practical on how patent management is carried out in firms. Afterwards, we carried out a questionnaire survey to purify our scales and statistical validation. Findings: The analysis allowed us to design a framework for patent management, identifying its core dimensions (i.e., generation, portfolio-management, exploitation and enforcement, intelligence) and support dimensions (i.e., strategy and organization). Moreover, we identified the relevant activities for each dimension, as well as the most suitable items to measure them. For example, the core dimension generation includes constructs as: state-of-the-art analysis, freedom-to-operate analysis, patent watching, securing freedom-to-operate, patent potential and patent-geographical-scope. Originality and the Study Contribution: This study represents a first step towards the development of sound scales to measure patent management with an overarching approach, thus laying the basis for developing a recognized landmark within the research area of patent management. Practical Implications: The new scale can be used to assess the level of sophistication of the patent management of a company and compare it with other firms in the industry to evaluate their ability to manage the different activities involved in patent management. In addition, the framework resulting from this analysis can be used as a guide that supports managers to improve patent management in firms.

Keywords: patent, management, scale, development, intellectual property rights (IPRs)

Procedia PDF Downloads 147

Authors: Aleksandra Szurlej-Kielanska, Lucyna Pilacka, Dariusz Górecki

Abstract:

The dynamic development of wind energy requires the simultaneous implementation of effective systems minimizing the risk of collisions between birds and wind turbines. Wind turbines are installed in more and more challenging locations, often close to the natural environment of birds. More and more countries and organizations are defining guidelines for the necessary functionality of such systems. The minimum bird detection distance, trajectory tracking, and shutdown time are key factors in eliminating collisions. Since 2020, we have continued the survey on the validation of the subsequent version of the BPS detection and reaction system. Bird protection system (BPS) is a fully automatic camera system which allows one to estimate the distance of the bird to the turbine, classify its size and autonomously undertake various actions depending on the bird's distance and flight path. The BPS was installed and tested in a real environment at a wind turbine in northern Poland and Central Spain. The performed validation showed that at a distance of up to 300 m, the BPS performs at least as well as a skilled ornithologist, and large bird species are successfully detected from over 600 m. In addition, data collected by BPS systems installed in Spain showed that 60% of the detections of all birds of prey were from individuals approaching the turbine, and these detections meet the turbine shutdown criteria. Less than 40% of the detections of birds of prey took place at wind speeds below 2 m/s while the turbines were not working. As shown by the analysis of the data collected by the system over 12 months, the system classified the improved size of birds with a wingspan of more than 1.1 m in 90% and the size of birds with a wingspan of 0.7 - 1 m in 80% of cases. The collected data also allow the conclusion that some species keep a certain distance from the turbines at a wind speed of over 8 m/s (Aquila sp., Buteo sp., Gyps sp.), but Gyps sp. and Milvus sp. remained active at this wind speed on the tested area. The data collected so far indicate that BPS is effective in detecting and stopping wind turbines in response to the presence of birds of prey with a wingspan of more than 1 m.

Keywords: protecting birds, birds monitoring, wind farms, green energy, sustainable development

Procedia PDF Downloads 76

Authors: Ogbonnaya Elom, Francis N. Azunku, Ogochukwu Onah

Abstract:

This study was carried out to determine the correlates of cost effectiveness analysis of rating scale and psycho-productive multiple choice test for assessing students’ performance in rice production. Four research questions were developed and answered, while one hypothesis was formulated and tested. Survey and correlation designs were adopted. The population of the study was 20,783 made up of 20,511 senior secondary (SSII) students and 272 teachers of agricultural science from 221 public secondary schools. Two schools with one intact class of 30 students each was purposely selected as sample based on certain criteria. Four sets of instruments were used for data collection. One of the instruments-the rating scale, was subjected to face and content validation while the other three were subjected to face validation only. Cronbach alpha technique was utilized to determine the internal consistency of the rating scale items which yielded a coefficient of 0.82 while the Kudder-Richardson (K-R 20) formula was involved in determining the stability of the psycho-productive multiple choice test items which yielded a coefficient of 0.80. Method of data collection involved a step-by-step approach in collecting data. Data collected were analyzed using percentage, weighted mean and sign test to answer the research questions while the hypothesis was tested using Spearman rank-order of correlation and t-test statistic. Findings of the study revealed among others, that psycho-productive multiple choice test is more effective than rating scale when the former is applied on the two groups of students. It was recommended among others, that the external examination bodies should integrate the use of psycho- productive multiple choice test into their examination policy and direct secondary schools to comply with it.

Keywords: correlates, cost-effectiveness, psycho-productive multiple-choice scale, rating scale

Procedia PDF Downloads 141

Authors: Sh. Arzani, H. Kazemi Esfeh, Y. Galeh Zadeh, V. Akbari

Abstract:

Ethylene dichloride is a colorless liquid with a smell like chloroform. EDC is classified in the simple hydrocarbon group which is obtained from chlorinating ethylene gas. Its chemical formula is C2H2Cl2 which is used as the main mediator in VCM production. Therefore, the purification process of EDC is important in the petrochemical process. In this study, the purification unit of EDC was simulated, and then validation was performed. Finally, the impact of process parameter was studied for the degree of EDC purity. The results showed that by increasing the feed flow, the reflux impure combinations increase and result in an EDC purity decrease.

Keywords: ethylene dichloride, purification, edc, simulation

Procedia PDF Downloads 316

Authors: Babek Erdebilli

Abstract:

The aim of this study is to develop and describe a new methodology for the Multi-Criteria Decision-Making (MCDM) problem using IFE (Elimination Et Choix Traduisant La Realite (ELECTRE) model. The proposed models enable Decision-Makers (DMs) on the assessment and use Intuitionistic Fuzzy Numbers (IFN). A numerical example is provided to demonstrate and clarify the proposed analysis procedure. Also, an empirical experiment is conducted to validation the effectiveness.

Keywords: multi-criteria decision-making, IFE, DM’s, fuzzy electre model

Procedia PDF Downloads 651

Authors: Ting Lu, Ya-Ru Diao, Fei Fan, Ye Xue, Lei Shi, Xian-e Tang, Meng-jun Zhan, Zhen-hua Deng

Abstract:

Accurate adult age estimation (AAE) is a significant and challenging task in forensic and archeology fields. Attempts have been made to explore optimal adult age metrics, and the rib is considered a potential age marker. The traditional way is to extract age-related features designed by experts from macroscopic or radiological images followed by classification or regression analysis. Those results still have not met the high-level requirements for practice, and the limitation of using feature design and manual extraction methods is loss of information since the features are likely not designed explicitly for extracting information relevant to age. Deep learning (DL) has recently garnered much interest in imaging learning and computer vision. It enables learning features that are important without a prior bias or hypothesis and could be supportive of AAE. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method. Chest CT data were reconstructed using volume rendering (VR). Retrospective data of 2500 patients aged 20.00-69.99 years were obtained between December 2019 and September 2021. Five-fold cross-validation was performed, and datasets were randomly split into training and validation sets in a 4:1 ratio for each fold. Before feeding the inputs into networks, all images were augmented with random rotation and vertical flip, normalized, and resized to 224×224 pixels. ResNeXt was chosen as the DL baseline due to its advantages of higher efficiency and accuracy in image classification. Mean absolute error (MAE) was the primary parameter. Independent data from 100 patients acquired between March and April 2022 were used as a test set. The manual method completely followed the prior study, which reported the lowest MAEs (5.31 in males and 6.72 in females) among similar studies. CT data and VR images were used. The radiation density of the first costal cartilage was recorded using CT data on the workstation. The osseous and calcified projections of the 1 to 7 costal cartilages were scored based on VR images using an eight-stage staging technique. According to the results of the prior study, the optimal models were the decision tree regression model in males and the stepwise multiple linear regression equation in females. Predicted ages of the test set were calculated separately using different models by sex. A total of 2600 patients (training and validation sets, mean age=45.19 years±14.20 [SD]; test set, mean age=46.57±9.66) were evaluated in this study. Of ResNeXt model training, MAEs were obtained with 3.95 in males and 3.65 in females. Based on the test set, DL achieved MAEs of 4.05 in males and 4.54 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. Those results showed that the DL of the ResNeXt model outperformed the manual method in AAE based on CT reconstruction of the costal cartilage and the developed system may be a supportive tool for AAE.

Keywords: forensic anthropology, age determination by the skeleton, costal cartilage, CT, deep learning

Procedia PDF Downloads 73

Authors: Semire Yekta

Abstract:

Many online retailers set up manual review teams to overcome the limitations of automated online fraud detection systems. This study critically examines the strategies they adapt in their decision-making process to set apart fraudulent individuals from non-fraudulent online shoppers. The study uses a mix method research approach. 32 in-depth interviews have been conducted alongside with participant observation and auto-ethnography. The study found out that all steps of the decision-making process are significantly affected by a level of subjectivity, personal understandings of online fraud, preferences and judgments and not necessarily by objectively identifiable facts. Rather clearly knowing who the fraudulent individuals are, the team members have to predict whether they think the customer might be a fraudster. Common strategies used are relying on the classification and fraud scorings in the automated fraud detection systems, weighing up arguments for and against the customer and making a decision, using cancellation to test customers’ reaction and making use of personal experiences and “the sixth sense”. The interaction in the team also plays a significant role given that some decisions turn into a group discussion. While customer data represent the basis for the decision-making, fraud management teams frequently make use of Google search and Google Maps to find out additional information about the customer and verify whether the customer is the person they claim to be. While this, on the one hand, raises ethical concerns, on the other hand, Google Street View on the address and area of the customer puts customers living in less privileged housing and areas at a higher risk of being classified as fraudsters. Phone validation is used as a final measurement to make decisions for or against the customer when previous strategies and Google Search do not suffice. However, phone validation is also characterized by individuals’ subjectivity, personal views and judgment on customer’s reaction on the phone that results in a final classification as genuine or fraudulent.

Keywords: online fraud, data mining, manual review, social construction

Procedia PDF Downloads 343

Authors: Snigdha Sahai, Devaki Chikkavenkatappa Yellappa

Abstract:

This study outlines approaches for testing and validating stochastic models used in epidemiology, focusing on the integration and functional testing of simulation code. It details methods for combining simple functions into comprehensive simulations, distinguishing between deterministic and stochastic components, and applying tests to ensure robustness. Techniques include isolating stochastic elements, utilizing large sample sizes for validation, and handling special cases. Practical examples are provided using R code to demonstrate integration testing, handling of incorrect inputs, and special cases. The study emphasizes the importance of both functional and defensive programming to enhance code reliability and user-friendliness.

Keywords: computational epidemiology, epidemiology, public health, infectious disease modeling, statistical analysis, health data analysis, disease transmission dynamics, predictive modeling in health, population health modeling, quantitative public health, random sampling simulations, randomized numerical analysis, simulation-based analysis, variance-based simulations, algorithmic disease simulation, computational public health strategies, epidemiological surveillance, disease pattern analysis, epidemic risk assessment, population-based health strategies, preventive healthcare models, infection dynamics in populations, contagion spread prediction models, survival analysis techniques, epidemiological data mining, host-pathogen interaction models, risk assessment algorithms for disease spread, decision-support systems in epidemiology, macro-level health impact simulations, socioeconomic determinants in disease spread, data-driven decision making in public health, quantitative impact assessment of health policies, biostatistical methods in population health, probability-driven health outcome predictions

Procedia PDF Downloads 6