Search results for: shared frailty survival models

Authors: Yogendra Sisodia

Abstract:

Researchers are becoming more interested in extracting useful information from legal documents thanks to the development of large-scale language models in natural language processing (NLP), and deep learning has accelerated the creation of powerful text mining models. Legal fields like contracts benefit greatly from semantic text search since it makes it quick and easy to find related clauses. After collecting sentence embeddings, it is relatively simple to locate sentences with a comparable meaning throughout the entire legal corpus. The author of this research investigated two pre-trained language models for this task: MiniLM and Roberta, and further fine-tuned them on Legal Contracts. The author used Multiple Negative Ranking Loss for the creation of sentence transformers. The fine-tuned language models and sentence transformers showed promising results.

Keywords: legal contracts, multiple negative ranking loss, natural language inference, sentence transformers, semantic textual similarity

Procedia PDF Downloads 107

Authors: Pugazhenthan Thangaraju

Abstract:

Background: Since the pandemic began, more than millions of people have become infected with COVID-19. Globally, researchers are working for safe and effective treatments for this disease. Remdesivir is a drug that has been approved for the treatment of COVID-19. Many aspects are still being considered that may influence the future use of remdesivir. Aim: To assess the safety and efficacy of Remdesivir in hospitalized adult patients diagnosed with moderate and severe COVID-19. Methods: It was a record-based retrospective cohort study conducted between April 1st, 2020 and June 30th, 2021 at the tertiary care teaching hospital All India Institutes of Medical Sciences (AIIMS), Raipur Results: There were a total of 10,559 medical records of COVID-19 patients of which 1034 records were included in this study. Overall, irrespective of the survival status, there was statistical significant difference observed between the WHO score at the time of admission and discharge. Clinical improvement among the survivors was found to be statistically significant. Conclusion: Remdesivir's potential efficacy against coronaviruses has so far been limited to in vitro studies and animal models. However, information about COVID-19 is rapidly expanding. Several clinical trials for the treatment of COVID-19 with remdesivir are now underway. However, the findings of this study support remdesivir as a promising agent in the fight against SARS-CoV-2.

Keywords: Remdesivir, COVID-19, SARS-CoV-2, antiviral, RNA-dependent RNA polymerase, viral pneumonia

Procedia PDF Downloads 65

Authors: Herlandson C. Moura, Jorge H. Bidinotto, Eduardo M. Belo

Abstract:

The present work proposes the development of an adaptive control system which enables the suppression of Pilot Induced Oscillations (PIO) in Digital Fly-By-Wire (DFBW) aircrafts. The proposed system consists of a Modified Model Reference Adaptive Control (M-MRAC) integrated with the Gain Scheduling technique. The PIO oscillations are detected using a Real Time Oscillation Verifier (ROVER) algorithm, which then enables the system to switch between two reference models; one in PIO condition, with low proneness to the phenomenon and another one in normal condition, with high (or medium) proneness. The reference models are defined in a closed loop condition using the Linear Quadratic Regulator (LQR) control methodology for Multiple-Input-Multiple-Output (MIMO) systems. The implemented algorithms are simulated in software implementations with state space models and commercial flight simulators as the controlled elements and with pilot dynamics models. A sequence of pitch angles is considered as the reference signal, named as Synthetic Task (Syntask), which must be tracked by the pilot models. The initial outcomes show that the proposed system can detect and suppress (or mitigate) the PIO oscillations in real time before it reaches high amplitudes.

Keywords: adaptive control, digital Fly-By-Wire, oscillations suppression, PIO

Procedia PDF Downloads 134

Authors: Riona Dighe

Abstract:

This research attempts to identify an alternative approach to the measurement of Gross National Happiness (GNH). It uses artificial intelligence (AI), incorporating natural language processing (NLP) and sentiment analysis to measure GNH. We use ‘off the shelf’ NLP models responsible for the sentiment analysis of a sentence as a building block for this research. We constructed an algorithm using NLP models to derive a sentiment analysis score against sentences. This was then tested against a sample of 20 respondents to derive a sentiment analysis score. The scores generated resembled human responses. By utilising the MLP classifier, decision tree, linear model, and K-nearest neighbors, we were able to obtain a test accuracy of 89.97%, 54.63%, 52.13%, and 47.9%, respectively. This gave us the confidence to use the NLP models against sentences in websites to measure the GNH of a country.

Keywords: artificial intelligence, NLP, sentiment analysis, gross national happiness

Procedia PDF Downloads 119

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 266

Authors: Adel Bougamouza, Boualam Remini, Abd El Hadi Ammari, Feteh Sakhraoui

Abstract:

The assessment of sediments being carried by a river is importance for planning and designing of various water resources projects. In this study, Artificial Neural Network Techniques are used to estimate the daily suspended sediment concentration for the corresponding daily discharge flow in the upstream of Foum El Gherza dam, Biskra, Algeria. The FFNN, GRNN, and RBNN models are established for estimating current suspended sediment values. Some statistics involving RMSE and R2 were used to evaluate the performance of applied models. The comparison of three AI models showed that the RBNN model performed better than the FFNN and GRNN models with R2 = 0.967 and RMSE= 5.313 mg/l. Therefore, the ANN model had capability to improve nonlinear relationships between discharge flow and suspended sediment with reasonable precision.

Keywords: artificial neural network, Oued Abiod watershed, feedforward network, generalized regression network, radial basis network, sediment concentration

Procedia PDF Downloads 418

Authors: Do-Jin Jang, Sung-Ah Kim

Abstract:

In designing a kinetic façade, it is hard for the designer to make digital models due to its complex geometry with motion. This paper aims to present a methodology of converting a point cloud of a physical model into a single digital model with a certain topology and motion. The method uses a Microsoft Kinect sensor, and color markers were defined and applied to three paper folding-inspired designs. Although the resulted digital model cannot represent the whole folding range of the physical model, the method supports the designer to conduct a performance-oriented design process with the rough physical model in the reduced folding range.

Keywords: design media, kinetic facades, tangible user interface, 3D scanning

Procedia PDF Downloads 413

Authors: Dejen Alemu, Murray E. Jennex, Temtim Assefa

Abstract:

This paper is investigated to understand the design, the use, and the consequence of Knowledge Management System (KMS) for knowledge systems sharing and integration. A KMS for knowledge systems sharing and integration is designed to meet the challenges raised by knowledge management researchers and practitioners: the technical, the human, and social factors. Agricultural KMS involves various members coming from different Communities of Practice (CoPs) who possess their own knowledge of multiple practices which need to be combined in the system development. However, the current development of the technology ignored the indigenous knowledge of the local communities, which is the key success factor for agriculture. This research employed the multi-methodological approach to KMS research in action research perspective which consists of four strategies: theory building, experimentation, observation, and system development. Using the KMS development practice of Ethiopian agricultural transformation agency as a case study, this research employed an interpretive analysis using primary qualitative data acquired through in-depth semi-structured interviews and participant observations. The Orlikowski's structuration model of technology has been used to understand the design, the use, and the consequence of the KMS. As a result, the research identified three basic components for the architecture of the shared KMS, namely, the people, the resources, and the implementation subsystems. The KMS were developed using web 2.0 tools to promote knowledge sharing and integration among diverse groups of users in a distributed environment. The use of a shared KMS allows users to access diverse knowledge from a number of users in different groups of participants, enhances the exchange of different forms of knowledge and experience, and creates high interaction and collaboration among participants. The consequences of a shared KMS on the social system includes, the elimination of hierarchical structure, enhance participation, collaboration, and negotiation among users from different CoPs having common interest, knowledge and skill development, integration of diverse knowledge resources, and the requirement of policy and guideline. The research contributes methodologically for the application of system development action research for understanding a conceptual framework for KMS development and use. The research have also theoretical contribution in extending structuration model of technology for the incorporation of variety of knowledge and practical implications to provide management understanding in developing strategies for the potential of web 2.0 tools for sharing and integration of indigenous knowledge.

Keywords: communities of practice, indigenous knowledge, participation, structuration model of technology, Web 2.0 tools

Procedia PDF Downloads 253

Authors: Ojoniyi Oluwafeyekikunmi Okiki

Abstract:

Notwithstanding advances in disturbing wound care and control, infections remain a main motive of mortality, morbidity, and financial disruption in tens of millions of wound sufferers around the sector. Animal models have become popular gear for analyzing a big selection of outside worrying wound infections and trying out new antimicrobial techniques. This evaluation covers experimental infections in animal models of surgical wounds, pores and skin abrasions, burns, lacerations, excisional wounds, and open fractures. Animal modes of external stressful wound infections stated via extraordinary investigators vary in animal species used, microorganism traces, the quantity of microorganisms carried out, the dimensions of the wounds, and, for burn infections, the period of time the heated object or liquid is in contact with the skin. As antibiotic resistance continues to grow, new antimicrobial procedures are urgently needed. Those have to be examined using popular protocols for infections in external stressful wounds in animal models.

Keywords: surgical wounds, animals, wound infections, burns, wound models, colony-forming gadgets, lacerated wounds

Procedia PDF Downloads 8

Authors: Debarati Bhaumik, Diptish Dey

Abstract:

Multilevel models, increasingly deployed in industries such as insurance, food production, and entertainment within functions such as marketing and supply chain management, need to be transparent and ethical. Applications usually result in binary classification within groups or hierarchies based on a set of input features. Using open-source datasets, we demonstrate that popular explainability methods, such as SHAP and LIME, consistently underperform inaccuracy when interpreting these models. They fail to predict the order of feature importance, the magnitudes, and occasionally even the nature of the feature contribution (negative versus positive contribution to the outcome). Besides accuracy, the computational intractability of SHAP for binomial classification is a cause of concern. For transparent and ethical applications of these hierarchical statistical models, sound audit frameworks need to be developed. In this paper, we propose an audit framework for technical assessment of multilevel regression models focusing on three aspects: (i) model assumptions & statistical properties, (ii) model transparency using different explainability methods, and (iii) discrimination assessment. To this end, we undertake a quantitative approach and compare intrinsic model methods with SHAP and LIME. The framework comprises a shortlist of KPIs, such as PoCE (Percentage of Correct Explanations) and MDG (Mean Discriminatory Gap) per feature, for each of these three aspects. A traffic light risk assessment method is furthermore coupled to these KPIs. The audit framework will assist regulatory bodies in performing conformity assessments of AI systems using multilevel binomial classification models at businesses. It will also benefit businesses deploying multilevel models to be future-proof and aligned with the European Commission’s proposed Regulation on Artificial Intelligence.

Keywords: audit, multilevel model, model transparency, model explainability, discrimination, ethics

Procedia PDF Downloads 94

Authors: Nima Pirhadi, Shao Yong Bo, Xusheng Wan, Jianguo Lu, Jilei Hu

Abstract:

Although gravels and gravelly soils are assumed to be non-liquefiable because of high conductivity and small modulus; however, the occurrence of this phenomenon in some historical earthquakes, especially recently earthquakes during 2008 Wenchuan, Mw= 7.9, 2014 Cephalonia, Greece, Mw= 6.1 and 2016, Kaikoura, New Zealand, Mw = 7.8, has been promoted the essential consideration to evaluate risk assessment and hazard analysis of seismic gravelly soil liquefaction. Due to the limitation in sampling and laboratory testing of this type of soil, in situ tests and site exploration of case histories are the most accepted procedures. Of all in situ tests, dynamic penetration test (DPT), Which is well known as the Chinese dynamic penetration test, and shear wave velocity (Vs) test, have been demonstrated high performance to evaluate seismic gravelly soil liquefaction. However, the lack of a sufficient number of case histories provides an essential limitation for developing new models. This study at first investigates recent earthquakes that caused liquefaction in gravelly soils to collect new data. Then, it adds these data to the available literature’s dataset to extend them and finally develops new models to assess seismic gravelly soil liquefaction. To validate the presented models, their results are compared to extra available models. The results show the reasonable performance of the proposed models and the critical effect of gravel content (GC)% on the assessment.

Keywords: liquefaction, gravel, dynamic penetration test, shear wave velocity

Procedia PDF Downloads 201

Authors: Qing Wu, Fei-Yan Li, Heng-Chang Zhang

Abstract:

Multitask learning support vector machines (SVMs) have recently attracted increasing research attention. Given several related tasks, the single-task learning methods trains each task separately and ignore the inner cross-relationship among tasks. However, multitask learning can capture the correlation information among tasks and achieve better performance by training all tasks simultaneously. In addition, the asymmetric squared loss function can better improve the generalization ability of the models on the most asymmetric distributed data. In this paper, we first make two assumptions on the relatedness among tasks and propose two multitask learning proximal support vector machine algorithms, named MTL-a-PSVM and EMTL-a-PSVM, respectively. MTL-a-PSVM seeks a trade-off between the maximum expectile distance for each task model and the closeness of each task model to the general model. As an extension of the MTL-a-PSVM, EMTL-a-PSVM can select appropriate kernel functions for shared information and private information. Besides, two corresponding special cases named MTL-PSVM and EMTLPSVM are proposed by analyzing the asymmetric squared loss function, which can be easily implemented by solving linear systems. Experimental analysis of three classification datasets demonstrates the effectiveness and superiority of our proposed multitask learning algorithms.

Keywords: multitask learning, asymmetric squared loss, EMTL-a-PSVM, classification

Procedia PDF Downloads 134

Authors: S. M. Gupta, Vanita Aggarwal, Som Nath Sachdeva

Abstract:

The work reported through this paper is an experimental work conducted on High Performance Concrete (HPC) with super plasticizer with the aim to develop some models suitable for prediction of compressive strength of HPC mixes. In this study, the effect of varying proportions of fly ash (0% to 50% at 10% increment) on compressive strength of high performance concrete has been evaluated. The mix designs studied were M30, M40 and M50 to compare the effect of fly ash addition on the properties of these concrete mixes. In all eighteen concrete mixes have been designed, three as conventional concretes for three grades under discussion and fifteen as HPC with fly ash with varying percentages of fly ash. The concrete mix designing has been done in accordance with Indian standard recommended guidelines i.e. IS: 10262. All the concrete mixes have been studied in terms of compressive strength at 7 days, 28 days, 90 days and 365 days. All the materials used have been kept same throughout the study to get a perfect comparison of values of results. The models for compressive strength prediction have been developed using Linear Regression method (LR), Artificial Neural Network (ANN) and Leave One Out Validation (LOOV) methods.

Keywords: high performance concrete, fly ash, concrete mixes, compressive strength, strength prediction models, linear regression, ANN

Procedia PDF Downloads 444

Authors: Duncan Oteki, Andebut Yeneneh, Daba Gedafa, Nabil Suleiman

Abstract:

Most agencies lack the equipment required to measure the dynamic modulus (|E*|) of asphalt mixtures, necessitating the need to use predictive models. This study compared measured |E*| values for nine North Dakota asphalt mixes using the original Witczak, modified Witczak, and Hirsch models. The influence of temperature on the |E*| models was investigated, and Pavement ME simulations were conducted using measured |E*| and predictions from the most accurate |E*| model. The results revealed that the original Witczak model yielded the lowest Se/Sy and highest R² values, indicating the lowest bias and highest accuracy, while the poorest overall performance was exhibited by the Hirsch model. Using predicted |E*| as inputs in the Pavement ME generated conservative distress predictions compared to using measured |E*|. The original Witczak model was recommended for predicting |E*| for low-reliability pavements in North Dakota.

Keywords: asphalt mixture, binder, dynamic modulus, MEPDG, pavement ME, performance, prediction

Procedia PDF Downloads 47

Authors: Andrey Khalov

Abstract:

The rapid proliferation of unstructured data in IT infrastructure management demands innovative approaches for extracting actionable knowledge. This paper presents a framework for ontology-based knowledge extraction that combines relational graph neural networks (R-GNN) with large language models (LLMs). The proposed method leverages the DOLCE framework as the foundational ontology, extending it with concepts from ITSMO for domain-specific applications in IT service management and outsourcing. A key component of this research is the use of transformer-based models, such as DeBERTa-v3-large, for automatic entity and relationship extraction from unstructured texts. Furthermore, the paper explores how transfer learning techniques can be applied to fine-tune large language models (LLaMA) for using to generate synthetic datasets to improve precision in BERT-based entity recognition and ontology alignment. The resulting IT Ontology (ITO) serves as a comprehensive knowledge base that integrates domain-specific insights from ITIL processes, enabling more efficient decision-making. Experimental results demonstrate significant improvements in knowledge extraction and relationship mapping, offering a cutting-edge solution for enhancing cognitive computing in IT service environments.

Keywords: ontology mapping, R-GNN, knowledge extraction, large language models, NER, knowlege graph

Procedia PDF Downloads 16

Authors: Dennis Kreutzer, Sarah Müller-Abdelrazeq, Ingrid Isenhardt

Abstract:

Resource scarcity, energy transition and the planned climate neutrality pose enormous challenges for manufacturing companies. In order to achieve these goals and a holistic sustainable development, the European Union has listed the circular economy as part of the Circular Economy Action Plan. In addition to a reduction in resource consumption, reduced emissions of greenhouse gases and a reduced volume of waste, the principles of the circular economy also offer enormous economic potential for companies, such as the generation of new circular business models. However, many manufacturing companies, especially small and medium-sized enterprises, do not have the necessary capacity to plan their transformation. They need support and strategies on the path to circular transformation, because this change affects not only production but also the entire company. Maturity models offer an approach, as they enable companies to determine the current status of their transformation processes. In addition, companies can use the models to identify transformation strategies and thus promote the transformation process. While maturity models are established in other areas, e.g. IT or project management, only a few circular economy maturity models can be found in the scientific literature. The aim of this paper is to analyse the identified maturity models of the circular economy through a systematic literature review (SLR) and, besides other aspects, to check their completeness as well as their quality. Since the terms "maturity model" and "readiness model" are often used to assess the transformation process, this paper considers both types of models to provide a more comprehensive result. For this purpose, circular economy maturity models at the company (micro) level were identified from the literature, compared, and analysed with regard to their theoretical and methodological structure. A specific focus was placed, on the one hand, on the analysis of the business units considered in the respective models and, on the other hand, on the underlying metrics and indicators in order to determine the individual maturity level of the entire company. The results of the literature review show, for instance, a significant difference in the holism of their assessment framework. Only a few models include the entire company with supporting areas outside the value-creating core process, e.g. strategy and vision. Additionally, there are large differences in the number and type of indicators as well as their metrics. For example, most models often use subjective indicators and very few objective indicators in their surveys. It was also found that there are rarely well-founded thresholds between the levels. Based on the generated results, concrete ideas and proposals for a research agenda in the field of circular economy maturity models are made.

Keywords: maturity model, circular economy, transformation, metric, assessment

Procedia PDF Downloads 114

Authors: Ayodele James Akinola

Abstract:

This study investigated the use of English in doctor-patient interaction in a university teaching hospital from a southwestern state in Nigeria with the aim of identifying the role of communication in an L2, patterns of communication, discourse strategies, pragmatic acts, and contexts that shape the interaction. Jacob Mey’s Pragmatic Acts notion complemented with Emanuel and Emanuel’s model of doctor-patient relationship provided the theoretical standpoint. Data comprising 7 audio-recorded doctors-patient interactions were collected from a University Hospital in Oyo state, Nigeria. Interactions involving the use of English language were purposefully selected. These were supplemented with patients’ case notes and interviews conducted with doctors. Transcription was patterned alongside modified Arminen’s notations of conversation analysis. In the study, interaction in English between doctor and patients has the preponderance of direct-translation, code-mixing and switching, Nigerianism and use of cultural worldviews to express medical experience. Irrespective of these, three patterns communication, namely the paternalistic, interpretive, and deliberative were identified. These were exhibited through varying discourse strategies. The paternalistic model reflected slightly casual conversational conventions and registers. These were achieved through the pragmemic activities of situated speech acts, psychological and physical acts, via patients’ quarrel-induced acts, controlled and managed through doctors’ shared situation knowledge. All these produced empathising, pacifying, promising and instructing practs. The patients’ practs were explaining, provoking, associating and greeting in the paternalistic model. The informative model reveals the use of adjacency pairs, formal turn-taking, precise detailing, institutional talks and dialogic strategies. Through the activities of the speech, prosody and physical acts, the practs of declaring, alerting and informing were utilised by doctors, while the patients exploited adapting, requesting and selecting practs. The negotiating conversational strategy of the deliberative model featured in the speech, prosody and physical acts. In this model, practs of suggesting, teaching, persuading and convincing were utilised by the doctors. The patients deployed the practs of questioning, demanding, considering and deciding. The contextual variables revealed that other patterns (such as phatic and informative) are also used and they coalesced in the hospital within the situational and psychological contexts. However, the paternalistic model was predominantly employed by doctors with over six years in practice, while the interpretive, informative and deliberative models were found among registrar and others below six years of medical practice. Doctors’ experience, patients’ peculiarities and shared cultural knowledge influenced doctor-patient communication in the study.

Keywords: pragmatics, communication pattern, doctor-patient interaction, Nigerian hospital situation

Procedia PDF Downloads 178

Authors: Sruti Akula

Abstract:

Assessment criteria are mostly used for assessing skills like writing and speaking. However, they could be used as a pedagogic tool to develop writing skills. A study was conducted with higher secondary learners (Class XII Kendriya Vidyalaya) to investigate the effectiveness of assessment criteria to develop argumentative essay writing. In order to raise awareness about the features of argumentative essay, assessment criteria were shared with the learners. Along with that, self-evaluation checklists were given to the learners to guide them through the writing process. During the study learners wrote multiple drafts with the help of assessment criteria, self-evaluation checklists and teacher feedback at different stages of their writing. It was observed that learners became more aware of the features of argumentative essay which in turn improved their argumentative essay writing. In addition the self evaluation checklists imporved their ability to reflect on their work there by increasing learner autonomy in the class. Hence, it can be claimed that both assessment criteria and self evaluation checklists are effective pedagogic tools to develop argumentative essay writing. Thus, teachers can be trained to create and use tools like assessment criteria and self-evaluation checklists to develop learners’ writing skills in an effective way. The presentation would discuss the approach adopted in the study to teach argumentative essay writing along with the rationale. The tools used in the study would be shared and the data collected in the form of written scripts, self-evaluation checklists and student interviews will be analyzed to validate the claims. Finally, the practical implication of the study like the ways of using assessment criteria and checklists to raise learner awareness and autonomy, using such tools to keep the learners informed about the task requirements and genre features, and the like will be put forward.

Keywords: argumentative essay writing, assessment criteria, self evaluation checklists, pedagogic

Procedia PDF Downloads 510

Authors: Snezhana G. Gocheva-Ilieva, Maya P. Stoimenova

Abstract:

Ambient air pollution with fine particulate matter (PM10) is a systematic permanent problem in many countries around the world. The accumulation of a large number of measurements of both the PM10 concentrations and the accompanying atmospheric factors allow for their statistical modeling to detect dependencies and forecast future pollution. This study applies the classification and regression trees (CART) method for building and analyzing PM10 models. In the empirical study, average daily air data for the city of Pleven, Bulgaria for a period of 5 years are used. Predictors in the models are seven meteorological variables, time variables, as well as lagged PM10 variables and some lagged meteorological variables, delayed by 1 or 2 days with respect to the initial time series, respectively. The degree of influence of the predictors in the models is determined. The selected best CART models are used to forecast future PM10 concentrations for two days ahead after the last date in the modeling procedure and show very accurate results.

Keywords: cross-validation, decision tree, lagged variables, short-term forecasting

Procedia PDF Downloads 194

Authors: Mohammad Tipu Sultan, Farzana Sharmin, Ke Xue

Abstract:

Social media create a better opportunity for travelers to search for travel information, select destination and share their personal experiences of the travel. This study proposes a framework which describes the relationships between social media, and positive or negative tourism experience sharing impact on destination choice. To find out new trends of travelers behavioral intention, we propose an extended theoretical model, the Theory of Reasoned Action (TRA). We conducted a survey to analyze three external factors, subjective norms, and positive and negative experience influence on travel destination choice. Structural questionnaire analysis was employed to confirm the proposed research hypothesis within the relationship between consumer influences on the shared experience of social media. The results of the study confirm that sharing positive experiences influence the positive effect of destination choice, while negative experiences decrease the destination selection option. The results indicate that attitudes, subjective norms are passively influenced by shared experience. Moreover, we find that sharing live pictures of travel experiences through social media helps to reduce negative perceptions of the destination brand. This research contribution is useable to the research field as a new determination factor and the findings could be used by destination organization management (DMO) to enhancing their tourism promotion through social media.

Keywords: destination choice, tourism experience sharing, Theory of Reasoned Action, TRA, social media

Procedia PDF Downloads 153

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 284

Authors: Zachary Huffman, Joana Rocha

Abstract:

Wall-pressure fluctuations induced by the turbulent boundary layer (TBL) developed over aircraft are a significant source of aircraft cabin noise. Since the power spectral density (PSD) of these pressure fluctuations is directly correlated with the amount of sound radiated into the cabin, the development of accurate empirical models that predict the PSD has been an important ongoing research topic. The sound emitted can be represented from the pressure fluctuations term in the Reynoldsaveraged Navier-Stokes equations (RANS). Therefore, early TBL empirical models (including those from Lowson, Robertson, Chase, and Howe) were primarily derived by simplifying and solving the RANS for pressure fluctuation and adding appropriate scales. Most subsequent models (including Goody, Efimtsov, Laganelli, Smol’yakov, and Rackl and Weston models) were derived by making modifications to these early models or by physical principles. Overall, these models have had varying levels of accuracy, but, in general, they are most accurate under the specific Reynolds and Mach numbers they were developed for, while being less accurate under other flow conditions. Despite this, recent research into the possibility of using alternative methods for deriving the models has been rather limited. More recent studies have demonstrated that an artificial neural network model was more accurate than traditional models and could be applied more generally, but the accuracy of other machine learning techniques has not been explored. In the current study, an original model is derived using a stepwise regression algorithm in the statistical programming language R, and TBL wall-pressure fluctuations PSD data gathered at the Carleton University wind tunnel. The theoretical advantage of a stepwise regression approach is that it will automatically filter out redundant or uncorrelated input variables (through the process of feature selection), and it is computationally faster than machine learning. The main disadvantage is the potential risk of overfitting. The accuracy of the developed model is assessed by comparing it to independently sourced datasets.

Keywords: aircraft noise, machine learning, power spectral density models, regression models, turbulent boundary layer wall-pressure fluctuations

Procedia PDF Downloads 135

Authors: Vidya Nimkar Tayade

Abstract:

Introduction: Intellectual capital of an organization is a key factor to success. Many companies invest a huge amount in their Research and development activities. Any innovation is helpful not only to that particular company but also to many other companies, industry and mankind as a whole. Companies undertake innovative changes for increasing their capital profitability and indirectly increase in pay packages of their employees. The quality of human capital can also improve due to such positive changes. Employees become more skilled and experienced due to such innovations and inventions. For increasing intangible capital, the author has referred to a couple of books and referred case studies to come to a conclusion. Different charts and tables are also referred to by the author. Case studies are more important because they are proven and established techniques. They enable students to apply theoretical concepts in real-world situations. It gives solutions to an open-ended problem with multiple potential solutions. There are three different strategies for undertaking intellectual capital increase. They are: Research push strategy/ Technology pushed approach, Market pull strategy/ approach and Open innovation strategy/approach. Research push strategy, In this strategy, research is undertaken and innovation is achieved on its own. After invention inventor company protects such invention and finds buyers for such invention. In this way, the invention is pushed into the market. In this method, research and development are undertaken first and the outcome of this research is commercialized. Market pull strategy, In this strategy, commercial opportunities are identified first and our research is concentrated in that particular area. For solving a particular problem, research is undertaken. It becomes easier to commercialize this type of invention. Because what is the problem is identified first and in that direction, research and development activities are carried on. Open invention strategy, In this type of research, more than one company enters into an agreement of research. The benefits of the outcome of this research will be shared by both companies. Internal and external ideas and technologies are involved. These ideas are coordinated and then they are commercialized. Due to globalization, people from the outside company are also invited to undertake research and development activities. Remuneration of employees of both the companies can increase and the benefit of commercialization of such invention is also shared by both the companies. Conclusion: In modern days, not only can tangible assets be commercialized, but also intangible assets can also be commercialized. The benefits of such an invention can be shared by more than one company. Competition can become more meaningful. Pay packages of employees can improve. It Is a need for time to adopt such strategies to benefit employees, competitors, stakeholders.

Keywords: innovation, protection, management, commercialization

Procedia PDF Downloads 168

Authors: Chuang-Chun Chiou

Abstract:

In this study, a systematic framework of graceful ageing has been used to explore the possible human resource utilization models for graceful ageing purpose. This framework is based on the Chinese culture. We call ‘Nine-old’ target. They are ageing gracefully with feeding, accomplishment, usefulness, learning, entertainment, care, protection, dignity, and termination. This study is focused on two areas: accomplishment and usefulness. We exam the current practices of initiatives and laws of promoting labor participation. That is to focus on how to increase Labor Force Participation Rate of the middle aged as well as the elderly and try to promote the elderly to achieve graceful ageing. Then we present the possible models that support graceful ageing.

Keywords: human resource utilization model, labor participation, graceful ageing, employment

Procedia PDF Downloads 390

Authors: Abdulrahman Sumayli, Saad M. AlShahrani

Abstract:

For the hydrogenation process, knowing the solubility of hydrogen (H2) in hydrocarbons is critical to improve the efficiency of the process. We investigated the H2 solubility computation in four heavy crude oil feedstocks using machine learning techniques. Temperature, pressure, and feedstock type were considered as the inputs to the models, while the hydrogen solubility was the sole response. Specifically, we employed three different models: Support Vector Regression (SVR), Gaussian process regression (GPR), and Bayesian ridge regression (BRR). To achieve the best performance, the hyper-parameters of these models are optimized using the whale optimization algorithm (WOA). We evaluated the models using a dataset of solubility measurements in various feedstocks, and we compared their performance based on several metrics. Our results show that the WOA-SVR model tuned with WOA achieves the best performance overall, with an RMSE of 1.38 × 10− 2 and an R-squared of 0.991. These findings suggest that machine learning techniques can provide accurate predictions of hydrogen solubility in different feedstocks, which could be useful in the development of hydrogen-related technologies. Besides, the solubility of hydrogen in the four heavy oil fractions is estimated in different ranges of temperatures and pressures of 150 ◦C–350 ◦C and 1.2 MPa–10.8 MPa, respectively

Keywords: temperature, pressure variations, machine learning, oil treatment

Procedia PDF Downloads 69

Authors: L. Grinis

Abstract:

Turbulent flow in complex geometries receives considerable attention due to its importance in many engineering applications. It has been the subject of interest for many researchers. Some of these interests include the design of storm water channels. The design of these channels requires testing through physical models. The main practical limitation of physical models is the so called “scale effect”, that is, the fact that in many cases only primary physical mechanisms can be correctly represented, while secondary mechanisms are often distorted. These observations form the basis of our study, which centered on problems associated with the design of storm water channels near the Dead Sea, in Israel. To help reach a final design decision we used different physical models. Our research showed good coincidence with the results of laboratory tests and theoretical calculations, and allowed us to study different effects of fluid flow in an open channel. We determined that problems of this nature cannot be solved only by means of theoretical calculation and computer simulation. This study demonstrates the use of physical models to help resolve very complicated problems of fluid flow through baffles and similar structures. The study applies these models and observations to different construction and multiphase water flows, among them, those that include sand and stone particles, a significant attempt to bring to the testing laboratory a closer association with reality.

Keywords: open channel, physical modeling, baffles, turbulent flow

Procedia PDF Downloads 284

Authors: L. J. de Bessa Neto, V. S. Filho, J. V. Ferreira Nunes, G. C. Bergamo

Abstract:

There are many situations in which human activities have significant effects on the environment. Damage to the ozone layer is one of them. The objective of this work is to use the Least Squares Method, considering the linear, exponential, logarithmic, power and polynomial models of the second degree, to analyze through the coefficient of determination (R²), which model best fits the behavior of the chlorodifluoromethane (HCFC-142b) in parts per trillion between 1992 and 2018, as well as estimates of future concentrations between 5 and 10 periods, i.e. the concentration of this pollutant in the years 2023 and 2028 in each of the adjustments. A total of 809 observations of the concentration of HCFC-142b in one of the monitoring stations of gases precursors of the deterioration of the ozone layer during the period of time studied were selected and, using these data, the statistical software Excel was used for make the scatter plots of each of the adjustment models. With the development of the present study, it was observed that the logarithmic fit was the model that best fit the data set, since besides having a significant R² its adjusted curve was compatible with the natural trend curve of the phenomenon.

Keywords: chlorodifluoromethane (HCFC-142b), ozone, least squares method, regression models

Procedia PDF Downloads 124

Authors: Besma Khalfoun

Abstract:

In many current Human Activity Recognition (HAR) applications, users' data is frequently shared and centrally stored by third parties, posing a significant privacy risk. This practice makes these entities attractive targets for extracting sensitive information about users, including their identity, health status, and location, thereby directly violating users' privacy. To tackle the issue of centralized data storage, a relatively recent paradigm known as federated learning has emerged. In this approach, users' raw data remains on their smartphones, where they train the HAR model locally. However, users still share updates of their local models originating from raw data. These updates are vulnerable to several attacks designed to extract sensitive information, such as determining whether a data sample is used in the training process, recovering the training data with inversion attacks, or inferring a specific attribute or property from the training data. In this paper, we first introduce PUR-Attack, a parameter-based user re-identification attack developed for HAR applications within a federated learning setting. It involves associating anonymous model updates (i.e., local models' weights or parameters) with the originating user's identity using background knowledge. PUR-Attack relies on a simple yet effective machine learning classifier and produces promising results. Specifically, we have found that by considering the weights of a given layer in a HAR model, we can uniquely re-identify users with an attack success rate of almost 100%. This result holds when considering a small attack training set and various data splitting strategies in the HAR model training. Thus, it is crucial to investigate protection methods to mitigate this privacy threat. Along this path, we propose SAFER, a privacy-preserving mechanism based on adaptive local differential privacy. Before sharing the model updates with the FL server, SAFER adds the optimal noise based on the re-identification risk assessment. Our approach can achieve a promising tradeoff between privacy, in terms of reducing re-identification risk, and utility, in terms of maintaining acceptable accuracy for the HAR model.

Keywords: federated learning, privacy risk assessment, re-identification risk, privacy preserving mechanisms, local differential privacy, human activity recognition

Procedia PDF Downloads 11

Authors: Mohammad B. HabibiNajafi, Saeideh Sadat Fatemizadeh, Maryam Tavakoli

Abstract:

In recent years, the consumption of functional foods, including foods containing probiotic bacteria, has come to notice. Milk proteins have been identified as a source of angiotensin-I-converting enzyme )ACE( inhibitory peptides and are currently the best-known class of bioactive peptides. In this study, the effects of adding prebiotic ingredients (inulin and wheat fiber) and fat percentage (0%, 2% and 3.5%) in yogurt containing probiotic Lactobacillus casei on physicochemical properties, degree of proteolysis, antioxidant and ACE-inhibitory activity within 21 days of storage at 5 ± 1 °C were evaluated. The results of statistical analysis showed that the application of prebiotic compounds led to a significant increase in water holding capacity, proteolysis and ACE-inhibitory of samples. The degree of proteolysis in yogurt increases as storage time elapses (P < 0.05) but when proteolysis exceeds a certain threshold, this trend begins to decline. Also, during storage time, water holding capacity reduced initially but increased thereafter. Moreover, based on our findings, the survival of Lactobacillus casei in samples treated with inulin and wheat fiber increased significantly in comparison to the control sample (P < 0.05) whereas the effect of fat percentage on the survival of probiotic bacteria was not significant (P = 0.095). Furthermore, the effect of prebiotic ingredients and the presence of probiotic cultures on the antioxidant activity of samples was significant (P < 0.05).

Keywords: probiotic yogurt, proteolysis, ACE-inhibitory, antioxidant activity

Procedia PDF Downloads 252

Authors: Byeongcheol Kang, Junyi Kim, Hyungsik Jung, Hyungjun Yang, Jaewoo An, Jonggeun Choe

Abstract:

It is important to figure out reservoir properties for better production management. Due to the limited information, there are geological uncertainties on very heterogeneous or channel reservoir. One of the solutions is to generate multiple equi-probable realizations using geostatistical methods. However, some models have wrong properties, which need to be excluded for simulation efficiency and reliability. We propose a novel method of model selection scheme, based on distance-based clustering for reliable application of production optimization algorithm. Distance is defined as a degree of dissimilarity between the data. We calculate Hausdorff distance to classify the models based on their similarity. Hausdorff distance is useful for shape matching of the reservoir models. We use multi-dimensional scaling (MDS) to describe the models on two dimensional space and group them by K-means clustering. Rather than simulating all models, we choose one representative model from each cluster and find out the best model, which has the similar production rates with the true values. From the process, we can select good reservoir models near the best model with high confidence. We make 100 channel reservoir models using single normal equation simulation (SNESIM). Since oil and gas prefer to flow through the sand facies, it is critical to characterize pattern and connectivity of the channels in the reservoir. After calculating Hausdorff distances and projecting the models by MDS, we can see that the models assemble depending on their channel patterns. These channel distributions affect operation controls of each production well so that the model selection scheme improves management optimization process. We use one of useful global search algorithms, particle swarm optimization (PSO), for our production optimization. PSO is good to find global optimum of objective function, but it takes too much time due to its usage of many particles and iterations. In addition, if we use multiple reservoir models, the simulation time for PSO will be soared. By using the proposed method, we can select good and reliable models that already matches production data. Considering geological uncertainty of the reservoir, we can get well-optimized production controls for maximum net present value. The proposed method shows one of novel solutions to select good cases among the various probabilities. The model selection schemes can be applied to not only production optimization but also history matching or other ensemble-based methods for efficient simulations.

Keywords: distance-based clustering, geological uncertainty, particle swarm optimization (PSO), production optimization

Procedia PDF Downloads 143