Search results for: meteorological prediction data

Authors: Panaya Sudta, Wanchalerm Patanacharoenwong, Prachya Bumrungkun

Abstract:

As With the evolution of smart grids, ensuring the reliability and efficiency of electrical systems in smart cities has become crucial. This paper proposes a distinct approach that combines advanced machine learning techniques to accurately predict electrical failures and address voltage reliability issues. This approach aims to improve the accuracy and efficiency of reliability evaluations in smart cities. The aim of this research is to develop a comprehensive predictive model that accurately predicts electrical failures and voltage reliability in smart cities. This model integrates RFM analysis, K-means clustering, and LSTM networks to achieve this objective. The research utilizes RFM analysis, traditionally used in customer value assessment, to categorize and analyze electrical components based on their failure recency, frequency, and monetary impact. K-means clustering is employed to segment electrical components into distinct groups with similar characteristics and failure patterns. LSTM networks are used to capture the temporal dependencies and patterns in customer data. This integration of RFM, K-means, and LSTM results in a robust predictive tool for electrical failures and voltage reliability. The proposed model has been tested and validated on diverse electrical utility datasets. The results show a significant improvement in prediction accuracy and reliability compared to traditional methods, achieving an accuracy of 92.78% and an F1-score of 0.83. This research contributes to the proactive maintenance and optimization of electrical infrastructures in smart cities. It also enhances overall energy management and sustainability. The integration of advanced machine learning techniques in the predictive model demonstrates the potential for transforming the landscape of electrical system management within smart cities. The research utilizes diverse electrical utility datasets to develop and validate the predictive model. RFM analysis, K-means clustering, and LSTM networks are applied to these datasets to analyze and predict electrical failures and voltage reliability. The research addresses the question of how accurately electrical failures and voltage reliability can be predicted in smart cities. It also investigates the effectiveness of integrating RFM analysis, K-means clustering, and LSTM networks in achieving this goal. The proposed approach presents a distinct, efficient, and effective solution for predicting and mitigating electrical failures and voltage issues in smart cities. It significantly improves prediction accuracy and reliability compared to traditional methods. This advancement contributes to the proactive maintenance and optimization of electrical infrastructures, overall energy management, and sustainability in smart cities.

Keywords: electrical state prediction, smart grids, data-driven method, long short-term memory, RFM, k-means, machine learning

Procedia PDF Downloads 42

Authors: Debjit Ray

Abstract:

Horizontal gene transfer (HGT) and recombination leads to the emergence of bacterial antibiotic resistance and pathogenic traits. HGT events can be identified by comparing a large number of fully sequenced genomes across a species or genus, define the phylogenetic range of HGT, and find potential sources of new resistance genes. In-depth comparative phylogenomics can also identify subtle genome or plasmid structural changes or mutations associated with phenotypic changes. Comparative phylogenomics requires that accurately sequenced, complete and properly annotated genomes of the organism. Assembling closed genomes requires additional mate-pair reads or “long read” sequencing data to accompany short-read paired-end data. To bring down the cost and time required of producing assembled genomes and annotating genome features that inform drug resistance and pathogenicity, we are analyzing the performance for genome assembly of data from the Illumina NextSeq, which has faster throughput than the Illumina HiSeq (~1-2 days versus ~1 week), and shorter reads (150bp paired-end versus 300bp paired end) but higher capacity (150-400M reads per run versus ~5-15M) compared to the Illumina MiSeq. Bioinformatics improvements are also needed to make rapid, routine production of complete genomes a reality. Modern assemblers such as SPAdes 3.6.0 running on a standard Linux blade are capable in a few hours of converting mixes of reads from different library preps into high-quality assemblies with only a few gaps. Remaining breaks in scaffolds are generally due to repeats (e.g., rRNA genes) are addressed by our software for gap closure techniques, that avoid custom PCR or targeted sequencing. Our goal is to improve the understanding of emergence of pathogenesis using sequencing, comparative genomics, and machine learning analysis of ~1000 pathogen genomes. Machine learning algorithms will be used to digest the diverse features (change in virulence genes, recombination, horizontal gene transfer, patient diagnostics). Temporal data and evolutionary models can thus determine whether the origin of a particular isolate is likely to have been from the environment (could it have evolved from previous isolates). It can be useful for comparing differences in virulence along or across the tree. More intriguing, it can test whether there is a direction to virulence strength. This would open new avenues in the prediction of uncharacterized clinical bugs and multidrug resistance evolution and pathogen emergence.

Keywords: genomics, pathogens, genome assembly, superbugs

Procedia PDF Downloads 190

Authors: Reneiloe Seodigeng, Malwandla Hanabe, Haleden Chiririwa, Hilary Rutto, Tumisang Seodigeng

Abstract:

Neutralisation of acid-mine drainage (AMD) using limestone is cost effective, and good results can be obtained. However, this process has its limitations; it cannot be used for highly acidic water which consists of Fe(III). When Fe(III) reacts with CaCO₃, it results in armoring. Armoring slows the reaction, and additional alkalinity can no longer be generated. Limestone is easily accessible, so this problem can be easily dealt with. Experiments were carried out to evaluate the effect of PVC pipe length on ferric and ferrous ions. It was found that the shorter the pipe length the more these dissolved metals precipitate. The effect of the pipe length on the hydrogen ions was also studied, and it was found that these two have an inverse relationship. Experimental data were further compared with the model prediction data to see if they behave in a similar fashion. The model was able to predict the behaviour of 1.5m and 2 m pipes in ferric and ferrous ion precipitation.

Keywords: acid mine drainage, neutralisation, limestone, mathematical modelling

Procedia PDF Downloads 355

Authors: Milad Abbasi

Abstract:

Carbon fiber-reinforced polymer (CFRP) composite structures are increasingly being utilized in the automotive industry due to their lightweight and specific energy absorption capabilities. Although it is impossible to predict composite mechanical properties directly using theoretical methods, various research has been conducted so far in the literature for accurate simulation of CFRP structures' energy-absorbing behavior. In this research, axial compression experiments were carried out on hand lay-up unidirectional CFRP composite tubes. The fabrication method allowed the authors to extract the material properties of the CFRPs using ASTM D3039, D3410, and D3518 standards. A neural network machine learning algorithm was then utilized to build a robust prediction model to forecast the axial compressive properties of CFRP tubes while reducing high-cost experimental efforts. The predicted results have been compared with the experimental outcomes in terms of load-carrying capacity and energy absorption capability. The results showed high accuracy and precision in the prediction of the energy-absorption capacity of the CFRP tubes. This research also demonstrates the effectiveness and challenges of machine learning techniques in the robust simulation of composites' energy-absorption behavior. Interestingly, the proposed method considerably condensed numerical and experimental efforts in the simulation and calibration of CFRP composite tubes subjected to compressive loading.

Keywords: CFRP composite tubes, energy absorption, crushing behavior, machine learning, neural network

Procedia PDF Downloads 139

Authors: Nishtha Madaan, Prateek Chaudhury, Nishant Kumar, Srikanta Bedathur

Abstract:

In modern NLP applications, word embeddings are a crucial backbone that can be readily shared across a number of tasks. However, as the text distributions change and word semantics evolve over time, the downstream applications using the embeddings can suffer if the word representations do not conform to the data drift. Thus, maintaining word embeddings to be consistent with the underlying data distribution is a key problem. In this work, we tackle this problem and propose TransDrift, a transformer-based prediction model for word embeddings. Leveraging the flexibility of the transformer, our model accurately learns the dynamics of the embedding drift and predicts future embedding. In experiments, we compare with existing methods and show that our model makes significantly more accurate predictions of the word embedding than the baselines. Crucially, by applying the predicted embeddings as a backbone for downstream classification tasks, we show that our embeddings lead to superior performance compared to the previous methods.

Keywords: NLP applications, transformers, Word2vec, drift, word embeddings

Procedia PDF Downloads 79

Authors: Alanoud Moraya Aldalan, Abdulaziz Almaleh

Abstract:

A crucial component of maintaining a customer-oriented business as in the telecom industry is understanding the reasons and factors that lead to customer churn. Competition between telecom companies has greatly increased in recent years. It has become more important to understand customers’ needs in this strong market of telecom industries, especially for those who are looking to turn over their service providers. So, predictive churn is now a mandatory requirement for retaining those customers. Machine learning can be utilized to accomplish this. Churn Prediction has become a very important topic in terms of machine learning classification in the telecommunications industry. Understanding the factors of customer churn and how they behave is very important to building an effective churn prediction model. This paper aims to predict churn and identify factors of customers’ churn based on their past service usage history. Aiming at this objective, the study makes use of feature selection, normalization, and feature engineering. Then, this study compared the performance of four different machine learning algorithms on the Orange dataset: Logistic Regression, Random Forest, Decision Tree, and Gradient Boosting. Evaluation of the performance was conducted by using the F1 score and ROC-AUC. Comparing the results of this study with existing models has proven to produce better results. The results showed the Gradients Boosting with feature selection technique outperformed in this study by achieving a 99% F1-score and 99% AUC, and all other experiments achieved good results as well.

Keywords: machine learning, gradient boosting, logistic regression, churn, random forest, decision tree, ROC, AUC, F1-score

Procedia PDF Downloads 125

Authors: Muhammad Zubair Khan, Yugyung Lee

Abstract:

Deep learning has recently achieved enormous response in semantic image segmentation. The previously developed U-Net inspired architectures operate with continuous stride and pooling operations, leading to spatial data loss. Also, the methods lack establishing long-term pixels connection to preserve context knowledge and reduce spatial loss in prediction. This article developed encoder-decoder architecture with bi-directional LSTM embedded in long skip-connections and densely connected convolution blocks. The network non-linearly combines the feature maps across encoder-decoder paths for finding dependency and correlation between image pixels. Additionally, the densely connected convolutional blocks are kept in the final encoding layer to reuse features and prevent redundant data sharing. The method applied batch-normalization for reducing internal covariate shift in data distributions. The empirical evidence shows a promising response to our method compared with other semantic segmentation techniques.

Keywords: deep learning, semantic segmentation, image analysis, pixels connection, convolution neural network

Procedia PDF Downloads 90

Authors: Thidathit Prachanukool, Chaiyaporn Yuksen, Welawat Tienpratarn, Sorravit Savatmongkorngul, Panvilai Tangkulpanich, Chetsadakon Jenpanitpong, Yuranan Phootothum, Malivan Phontabtim, Promphet Nuanprom

Abstract:

Background: Ruptured appendicitis has a high morbidity and mortality and requires immediate surgery. The Alvarado Score is used as a tool to predict the risk of acute appendicitis, but there is no such score for predicting rupture. This study aimed to developed the prediction score to determine the likelihood of ruptured appendicitis in an Asian population. Methods: This study was diagnostic, retrospectively cross-sectional and exploratory model at the Emergency Medicine Department in Ramathibodi Hospital between March 2016 and March 2018. The inclusion criteria were age >15 years and an available pathology report after appendectomy. Clinical factors included gender, age>60 years, right lower quadrant pain, migratory pain, nausea and/or vomiting, diarrhea, anorexia, fever>37.3°C, rebound tenderness, guarding, white blood cell count, polymorphonuclear white blood cells (PMN)>75%, and the pain duration before presentation. The predictive model and prediction score for ruptured appendicitis was developed by multivariable logistic regression analysis. Result: During the study period, 480 patients met the inclusion criteria; of these, 77 (16%) had ruptured appendicitis. Five independent factors were predictive of rupture, age>60 years, fever>37.3°C, guarding, PMN>75%, and duration of pain>24 hours to presentation. A score > 6 increased the likelihood ratio of ruptured appendicitis by 3.88 times. Conclusion: Using the Ramathibodi Welawat Ruptured Appendicitis Score. (RAMA WeRA Score) developed in this study, a score of > 6 was associated with ruptured appendicitis.

Keywords: predictive model, risk score, ruptured appendicitis, emergency room

Procedia PDF Downloads 156

Authors: Fuad M. Alkoot

Abstract:

We aim at highlighting the benefits of classifier systems especially in supporting educational management decisions. The paper aims at using classifiers in an educational application where an outcome is predicted based on given input parameters that represent various conditions at the institute. We present a classifier system that is designed using a limited training set with data for only one semester. The achieved system is able to reach at previously known outcomes accurately. It is also tested on new input parameters representing variations of input conditions to see its prediction on the possible outcome value. Given the supervised expectation of the outcome for the new input we find the system is able to predict the correct outcome. Experiments were conducted on one semester data from two departments only, Switching and Mathematics. Future work on other departments with larger training sets and wider input variations will show additional benefits of classifier systems in supporting the management decisions at an educational institute.

Keywords: machine learning, pattern recognition, classifier design, educational management, outcome estimation

Procedia PDF Downloads 268

Authors: Farzad Hosseini Hossein Abadi, Cristina Prieto Sierra, Cesar Álvarez Díaz

Abstract:

Predicting streamflow accurately in flashy catchments prone to floods is a major research and operational challenge in hydrological modeling. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have shown to be promising in achieving accurate hydrological predictions at daily and hourly time scales. In this work, a multi-timescale LSTM (MTS-LSTM) network was applied to the context of regional hydrological predictions at an hourly time scale in flashy catchments. The case study includes 40 catchments allocated in the Basque Country, north of Spain. We explore the impact of hyperparameters on the performance of streamflow predictions given by regional deep learning models through systematic hyperparameter tuning - where optimal regional values for different catchments are identified. The results show that predictions are highly accurate, with Nash-Sutcliffe (NSE) and Kling-Gupta (KGE) metrics values as high as 0.98 and 0.97, respectively. A principal component analysis reveals that a hyperparameter related to the length of the input sequence contributes most significantly to the prediction performance. The findings suggest that input sequence lengths have a crucial impact on the model prediction performance. Moreover, employing catchment-scale analysis reveals distinct sequence lengths for individual basins, highlighting the necessity of customizing this hyperparameter based on each catchment’s characteristics. This aligns with well known “uniqueness of the place” paradigm. In prior research, tuning the length of the input sequence of LSTMs has received limited focus in the field of streamflow prediction. Initially it was set to 365 days to capture a full annual water cycle. Later, performing limited systematic hyper-tuning using grid search, revealed a modification to 270 days. However, despite the significance of this hyperparameter in hydrological predictions, usually studies have overlooked its tuning and fixed it to 365 days. This study, employing a simultaneous systematic hyperparameter tuning approach, emphasizes the critical role of input sequence length as an influential hyperparameter in configuring LSTMs for regional streamflow prediction. Proper tuning of this hyperparameter is essential for achieving accurate hourly predictions using deep learning models.

Keywords: LSTMs, streamflow, hyperparameters, hydrology

Procedia PDF Downloads 44

Authors: Messay Mulugeta, Degefa Tolossa

Abstract:

The purpose of this paper is to scrutinize trends of climate risks in eastern and southeastern parts of Ethiopia. This part of the country appears severely affected by recurrent droughts, erratic rainfall, and increasing temperature condition. Particularly, erratic rains and moisture stresses have been forcibly threatening and shoving the people over many decades coupled with unproductive policy frameworks and weak institutional setups. These menaces have been more severe in dry lowlands where rainfall is more erratic and scarce. Long-term climate data of nine weather stations in eastern and southeastern parts of Ethiopia were obtained from National Meteorological Agency of Ethiopia (NMA). As issues related to climate risks are very intricate, different techniques and indices were applied to deal with the objectives of the study. It is concluded that erratic rainfall, moisture scarcity, and increasing temperature conditions have been the main challenges in eastern and southeastern Ethiopia. In fact, these risks can be eased by putting in place efficient and integrated rural development strategies, environmental rehabilitation plans of action in overworked areas, proper irrigation and water harvesting practices and well thought-out and genuine resettlement schemes.

Keywords: rainfall variability, erratic rains, precipitation concentration index (PCI), climatic pattern, Ethiopia

Procedia PDF Downloads 223

Authors: Kanika Taneja, V. K. Soni, S. D. Attri, Kafeel Ahmad, Shamshad Ahmad

Abstract:

Aerosols represent an important component of earth-atmosphere system and have a profound impact on the global and regional climate. With the growing population and urbanization, the aerosol load in the atmosphere over the Indian region is found to be increasing. Several studies have reported that the aerosol optical depth over the northern part of India is higher as compared to the southern part. The northern India along the Indo-Gangetic plain is often influenced with dust transported from the Thar Desert in northwestern India and from Arabian Peninsula during the pre-monsoon season. Seasonal variations in aerosol optical and radiative properties were examined using data retrieved from ground based multi-wavelength Prede Sun/sky radiometer (POM-02) over Delhi, Rohtak, Jodhpur and Varanasi for the period April 2011-April 2013. These stations are part of the Skynet-India network of India Meteorological Department. The Sun/sky radiometer (POM-02) has advantage over other instruments that it can be calibrated on-site. These aerosol optical properties retrieved from skyradiometer observations are further used to analyze the Direct Aerosol Radiative Forcing (DARF) over the study locations.

Keywords: aerosol optical properties, indo- gangetic plain, radiative forcing, sky radiometer

Procedia PDF Downloads 534

Authors: M. Heydari Vini

Abstract:

There is a complicated relation between effective input parameters of cold rolling and output rolling force and exit thickness of strips.in many mathematical models, the effect of some rolling parameters have been ignored and the outputs have not a desirable accuracy. In the other hand, there is a special relation among input thickness of strips,the width of the strips,rolling speeds,mandrill tensions and the required exit thickness of strips with rolling force and the real exit thickness of the rolled strip. First of all, in this paper the effective parameters of cold rolling process modeled using an artificial neural network according to the optimum network achieved by using a written program in MATLAB,it has been shown that the prediction of rolling stand parameters with different properties and new dimensions attained from prior rolled strips by an artificial neural network is applicable.

Keywords: cold rolling, artificial neural networks, rolling force, real rolled thickness of strips

Procedia PDF Downloads 492

Authors: Biruhi Tesfaye, Avinash M. Potdar

Abstract:

The laboratory test process to determine the California bearing ratio (CBR) of black cotton soils is not only overpriced but also time-consuming as well. Hence advanced prediction of CBR plays a significant role as it is applicable In pavement design. The prediction of CBR of treated soil was executed by Artificial Neural Networks (ANNs) which is a Computational tool based on the properties of the biological neural system. To observe CBR values, combined eggshell and waste glass was added to soil as 4, 8, 12, and 16 % of the weights of the soil samples. Accordingly, the laboratory related tests were conducted to get the required best model. The maximum CBR value found at 5.8 at 8 % of eggshell waste glass powder addition. The model was developed using CBR as an output layer variable. CBR was considered as a function of the joint effect of liquid limit, plastic limit, and plastic index, optimum moisture content and maximum dry density. The best model that has been found was ANN with 5, 6 and 1 neurons in the input, hidden and output layer correspondingly. The performance of selected ANN has been 0.99996, 4.44E-05, 0.00353 and 0.0067 which are correlation coefficient (R), mean square error (MSE), mean absolute error (MAE) and root mean square error (RMSE) respectively. The research presented or summarized above throws light on future scope on stabilization with waste glass combined with different percentages of eggshell that leads to the economical design of CBR acceptable to pavement sub-base or base, as desired.

Keywords: CBR, artificial neural network, liquid limit, plastic limit, maximum dry density, OMC

Procedia PDF Downloads 176

Authors: Benjamin Leiby, Darryl Ahner

Abstract:

This study demonstrates an alternative stochastic imputation approach for large datasets when preferred commercial packages struggle to iterate due to numerical problems. A large country conflict dataset motivates the search to impute missing values well over a common threshold of 20% missingness. The methodology capitalizes on correlation while using model residuals to provide the uncertainty in estimating unknown values. Examination of the methodology provides insight toward choosing linear or nonlinear modeling terms. Static tolerances common in most packages are replaced with tailorable tolerances that exploit residuals to fit each data element. The methodology evaluation includes observing computation time, model fit, and the comparison of known values to replaced values created through imputation. Overall, the country conflict dataset illustrates promise with modeling first-order interactions while presenting a need for further refinement that mimics predictive mean matching.

Keywords: correlation, country conflict, imputation, stochastic regression

Procedia PDF Downloads 110

Authors: Hoda A. Abdel Hafez

Abstract:

Mining big data represents a big challenge nowadays. Many types of research are concerned with mining massive amounts of data and big data streams. Mining big data faces a lot of challenges including scalability, speed, heterogeneity, accuracy, provenance and privacy. In telecommunication industry, mining big data is like a mining for gold; it represents a big opportunity and maximizing the revenue streams in this industry. This paper discusses the characteristics of big data (volume, variety, velocity and veracity), data mining techniques and tools for handling very large data sets, mining big data in telecommunication and the benefits and opportunities gained from them.

Keywords: mining big data, big data, machine learning, telecommunication

Procedia PDF Downloads 390

Authors: D. Serero, L. Couton, J. D. Parisse, R. Leroy

Abstract:

In urban planning, an increasing number of cities require wind analysis to verify comfort of public spaces and around buildings. These studies are made using computer fluid dynamic simulation (CFD). However, this technique is often based on wind information taken from meteorological stations located at several kilometers of the spot of analysis. The approximated input data on project surroundings produces unprecise results for this type of analysis. They can only be used to get general behavior of wind in a zone but not to evaluate precise wind speed. This paper presents another approach to this problem, based on collecting wind data and generating an urban wind cartography using connected ultrasound anemometers. They are wireless devices that send immediate data on wind to a remote server. Assembled in array, these devices generate geo-localized data on wind such as speed, temperature, pressure and allow us to compare wind behavior on a specific site or building. These Netatmo-type anemometers communicate by wifi with central equipment, which shares data acquired by a wide variety of devices such as wind speed, indoor and outdoor temperature, rainfall, and sunshine. Beside its precision, this method extracts geo-localized data on any type of site that can be feedback looped in the architectural design of a building or a public place. Furthermore, this method allows a precise calibration of a virtual wind tunnel using numerical aeraulic simulations (like STAR CCM + software) and then to develop the complete volumetric model of wind behavior over a roof area or an entire city block. The paper showcases connected ultrasonic anemometers, which were implanted for an 18 months survey on four study sites in the Grand Paris region. This case study focuses on Paris as an urban environment with multiple historical layers whose diversity of typology and buildings allows considering different ways of capturing wind energy. The objective of this approach is to categorize the different types of wind in urban areas. This, particularly the identification of the minimum and maximum wind spectrum, helps define the choice and performance of wind energy capturing devices that could be implanted there. The localization on the roof of a building, the type of wind, the altimetry of the device in relation to the levels of the roofs, the potential nuisances generated. The method allows identifying the characteristics of wind turbines in order to maximize their performance in an urban site with turbulent wind.

Keywords: computer fluid dynamic simulation in urban environment, wind energy harvesting devices, net-zero energy building, urban wind behavior simulation, advanced building skin design methodology

Procedia PDF Downloads 92

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 95

Authors: Belkacem Laimouche

Abstract:

With the field of artificial intelligence (AI) experiencing exponential growth, fueled by technological advancements that pave the way for increasingly innovative and promising applications, there is an escalating need to develop rigorous methods for assessing their performance in pursuit of transparency and equity. This article proposes a metrology-inspired statistical framework for evaluating bias and explainability in AI systems. Drawing from the principles of metrology, we propose a pioneering approach, using a concrete example, to evaluate the accuracy and precision of AI models, as well as to quantify the sources of measurement uncertainty that can lead to bias in their predictions. Furthermore, we explore a statistical approach for evaluating the explainability of AI systems based on their ability to provide interpretable and transparent explanations of their predictions.

Keywords: artificial intelligence, metrology, measurement uncertainty, prediction error, bias, machine learning algorithms, probabilistic models, interlaboratory comparison, data analysis, data reliability, measurement of bias impact on predictions, improvement of model accuracy and reliability

Procedia PDF Downloads 96

Authors: Sang Heon Han, Daejun Chang, Won Yang

Abstract:

NOx reduction characteristics of syngas fuel were numerically investigated for the 2MW pilot scale heavy oil furnace of KITECH (Korea Institute of Industrial Technology). The secondary fuel and syngas was fed into the furnace with two purposes- partial replacement of main fuel and reburning of NOx. Some portion of syngas was fed into the flame zone to partially replace the heavy oil, while the other portion was fed into the furnace downstream to reduce NOx generation. The numerical prediction was verified by comparing it with the experimental results. Syngas of KITECH’s experiment, assumed to be produced from biomass, had very low calorific value and contained 3% hydrocarbon. This study investigated the precise behavior of NOx generation and NOx reduction as well as thermo-fluidic characteristics inside the furnace, which was unavailable with experiment. In addition to 3% hydrocarbon syngas, 5%, and 7% hydrocarbon syngas were numerically tested as reburning fuels to analyze the effect of hydrocarbon proportion to NOx reduction. The prediction showed that the 3% hydrocarbon syngas is as much effective as 7% hydrocarbon syngas in reducing NOx.

Keywords: syngas, reburning, heavy oil, furnace

Procedia PDF Downloads 429

Authors: Nguyen Tien Thanh, Günter Meon

Abstract:

Precipitation plays a key role in water cycle, defining the local climatic conditions and in ecosystem. It is also an important input parameter for water resources management and hydrologic models. With spatial continuous data, a certainty of discharge predictions or other environmental factors is unquestionably better than without. This is, however, not always willingly available to acquire for a small basin, especially for coastal region in Vietnam due to a low network of meteorological stations (30 stations) on long coast of 3260 km2. Furthermore, available gridded precipitation datasets are not fine enough when applying to hydrologic models. Under conditions of global warming, an application of spatial interpolation methods is a crucial for the climate change impact studies to obtain the spatial continuous data. In recent research projects, although some methods can perform better than others do, no methods draw the best results for all cases. The objective of this paper therefore, is to investigate different spatial interpolation methods for daily precipitation over a small basin (approximately 400 km2) located in coastal region, Southern Vietnam and find out the most efficient interpolation method on this catchment. The five different interpolation methods consisting of cressman, ordinary kriging, regression kriging, dual kriging and inverse distance weighting have been applied to identify the best method for the area of study on the spatio-temporal scale (daily, 10 km x 10 km). A 30-year precipitation database was created and merged into available gridded datasets. Finally, observed changes in constructed precipitation were performed. The results demonstrate that the method of ordinary kriging interpolation is an effective approach to analyze the daily precipitation. The mixed trends of increasing and decreasing monthly, seasonal and annual precipitation have documented at significant levels.

Keywords: interpolation, precipitation, trend, vietnam

Procedia PDF Downloads 270

Authors: B. Selma

Abstract:

The aim of this study is to test the feasibility of SIPINA method to predict the harmfulness parameters controlling the seismic response. The approach developed takes into consideration both the focal depth and the peak ground acceleration. The parameter to determine is displacement. The data used for the learning of this method and analysis nonlinear seismic are described and applied to a class of models damaged to some typical structures of the existing urban infrastructure of Jassy, Romania. The results obtained indicate an influence of the focal depth and the peak ground acceleration on the displacement.

Keywords: SIPINA algorithm, seism, focal depth, peak ground acceleration, displacement

Procedia PDF Downloads 300

Authors: Jacob Green, Cecilia Cabrera, Maximilian Jakobs, Andrea Dimitracopoulos, Mark van der Wilk, Ryan Greenhalgh

Abstract:

Predicting drug properties is key in drug discovery to enable de-risking of assets before expensive clinical trials and to find highly active compounds faster. Interest from the machine learning community has led to the release of a variety of benchmark datasets and proposed methods. However, it remains unclear for practitioners which method or approach is most suitable, as different papers benchmark on different datasets and methods, leading to varying conclusions that are not easily compared. Our large-scale empirical study links together numerous earlier works on different datasets and methods, thus offering a comprehensive overview of the existing property classes, datasets, and their interactions with different methods. We emphasise the importance of uncertainty quantification and the time and, therefore, cost of applying these methods in the drug development decision-making cycle. To the best of the author's knowledge, it has been observed that the optimal approach varies depending on the dataset and that engineered features with classical machine learning methods often outperform deep learning. Specifically, QSAR datasets are typically best analysed with classical methods such as Gaussian Processes, while ADMET datasets are sometimes better described by Trees or deep learning methods such as Graph Neural Networks or language models. Our work highlights that practitioners do not yet have a straightforward, black-box procedure to rely on and sets a precedent for creating practitioner-relevant benchmarks. Deep learning approaches must be proven on these benchmarks to become the practical method of choice in drug property prediction.

Keywords: activity (QSAR), ADMET, classical methods, drug property prediction, empirical study, machine learning

Procedia PDF Downloads 64

Authors: Marc Solé, Francesc Giné, Magda Valls, Nina Bijedic

Abstract:

What people say on social media has turned into a rich source of information to understand social behavior. Specifically, the growing use of Twitter social media for political communication has arisen high opportunities to know the opinion of large numbers of politically active individuals in real time and predict the global political tendencies of a specific country. It has led to an increasing body of research on this topic. The majority of these studies have been focused on polarized political contexts characterized by only two alternatives. Unlike them, this paper tackles the challenge of forecasting Spanish political trends, characterized by multiple political parties, by means of analyzing the Twitters Users political tendency. According to this, a new strategy, named Tweets Analysis Strategy (TAS), is proposed. This is based on analyzing the users tweets by means of discovering its sentiment (positive, negative or neutral) and classifying them according to the political party they support. From this individual political tendency, the global political prediction for each political party is calculated. In order to do this, two different strategies for analyzing the sentiment analysis are proposed: one is based on Positive and Negative words Matching (PNM) and the second one is based on a Neural Networks Strategy (NNS). The complete TAS strategy has been performed in a Big-Data environment. The experimental results presented in this paper reveal that NNS strategy performs much better than PNM strategy to analyze the tweet sentiment. In addition, this research analyzes the viability of the TAS strategy to obtain the global trend in a political context make up by multiple parties with an error lower than 23%.

Keywords: political tendency, prediction, sentiment analysis, Twitter

Procedia PDF Downloads 225

Authors: Fameli Kyriaki-Maria, Assimakopoulos D. Vasiliki, Kotroni Vassiliki

Abstract:

The Greater Athens Area (GAA) faces photochemical and particulate pollution episodes as a result of the combined effects of local pollutant emissions, regional pollution transport, synoptic circulation and topographic characteristics. The area has undergone significant changes since the Athens 2004 Olympic Games because of large scale infrastructure works that lead to the shift of population to areas previously characterized as rural, the increase of the traffic fleet and the operation of highways. However, no recent modelling studies have been performed due to the lack of an accurate, updated emission inventory. The photochemical modelling system MM5/CAMx was applied in order to study the photochemical and particulate pollution characteristics above the GAA for two distinct ten-day periods in the summer of 2006 and 2010, where air pollution episodes occurred. A new updated emission inventory was used based on official data. Comparison of modeled results with measurements revealed the importance and accuracy of the new Athens emission inventory as compared to previous modeling studies. The model managed to reproduce the local meteorological conditions, the daily ozone and particulates fluctuations at different locations across the GAA. Higher ozone levels were found at suburban and rural areas as well as over the sea at the south of the basin. Concerning PM10, high concentrations were computed at the city centre and the southeastern suburbs in agreement with measured data. Source apportionment analysis showed that different sources contribute to the ozone levels, the local sources (traffic, port activities) affecting its formation.

Keywords: photochemical modelling, urban pollution, greater Athens area, MM5/CAMx

Procedia PDF Downloads 270

Authors: Omar Hussein El Ayadi, EmadY. El-Mansouri, Mohamed B. Dozan

Abstract:

Production oil process require specific details i.e. oil composition. Generally, types of oil or differentiation between reservoir fluids depend specifically on composition. The main purpose of this study is to correlate and predict the Libyan oil (reservoir fluid and residual) composition utilizing tri-angle-coordinate plots discovered and tasked with Excel. The reservoir fluid data (61 old + 47 new), the residual oil data (33 new) collected from most of Libyan reservoirs were correlated with each others. Moreover, find a relation between stock tank molecular weight and stock tank oil gravity (oAPI), the molecular weight oh (C7+) versus residual oil gravity (oAPI). The average value of every oil composition was estimated including non-hydrocarbon (H2S, CO2, and N2). Nevertheless, the isomers (i-…) and normal (n-…) structure of (C4) and (C5) were also obtained. The summary of the conclusion is; utilizing excel Microsoft office to draw triangle coordinates to find two unknown component if only one is known. However, it is recommended to use the obtained oil composition plots and equations for any oil composition dependents i.e. optimum separator pressure.

Keywords: PVT, phase behavior, petroleum, chemical engineering

Procedia PDF Downloads 502

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: deep learning, data mining, gender predication, MOOCs

Procedia PDF Downloads 129

Authors: Zachary Blanks, Solomon Sonya

Abstract:

Poaching presents a serious threat to endangered animal species, environment conservations, and human life. Additionally, some poaching activity has even been linked to supplying funds to support terrorist networks elsewhere around the world. Consequently, agencies dedicated to protecting wildlife habitats have a near intractable task of adequately patrolling an entire area (spanning several thousand kilometers) given limited resources, funds, and personnel at their disposal. Thus, agencies need predictive tools that are both high-performing and easily implementable by the user to help in learning how the significant features (e.g. animal population densities, topography, behavior patterns of the criminals within the area, etc) interact with each other in hopes of abating poaching. This research develops a classification model using machine learning algorithms to aid in forecasting future attacks that is both easy to train and performs well when compared to other models. In this research, we demonstrate how data imputation methods (specifically predictive mean matching, gradient boosting, and random forest multiple imputation) can be applied to analyze data and create significant predictions across a varied data set. Specifically, we apply these methods to improve the accuracy of adopted prediction models (Logistic Regression, Support Vector Machine, etc). Finally, we assess the performance of the model and the accuracy of our data imputation methods by learning on a real-world data set constituting four years of imputed data and testing on one year of non-imputed data. This paper provides three main contributions. First, we extend work done by the Teamcore and CREATE (Center for Risk and Economic Analysis of Terrorism Events) research group at the University of Southern California (USC) working in conjunction with the Department of Homeland Security to apply game theory and machine learning algorithms to develop more efficient ways of reducing poaching. This research introduces ensemble methods (Random Forests and Stochastic Gradient Boosting) and applies it to real-world poaching data gathered from the Ugandan rain forest park rangers. Next, we consider the effect of data imputation on both the performance of various algorithms and the general accuracy of the method itself when applied to a dependent variable where a large number of observations are missing. Third, we provide an alternate approach to predict the probability of observing poaching both by season and by month. The results from this research are very promising. We conclude that by using Stochastic Gradient Boosting to predict observations for non-commercial poaching by season, we are able to produce statistically equivalent results while being orders of magnitude faster in computation time and complexity. Additionally, when predicting potential poaching incidents by individual month vice entire seasons, boosting techniques produce a mean area under the curve increase of approximately 3% relative to previous prediction schedules by entire seasons.

Keywords: ensemble methods, imputation, machine learning, random forests, statistical analysis, stochastic gradient boosting, wildlife protection

Procedia PDF Downloads 277

Authors: Meera Tandan, Mohan Timilsina, Martin Cormican, Akke Vellinga

Abstract:

Background: In general practice, many infections are treated empirically without microbiological confirmation. Understanding susceptibility of antimicrobials during empirical prescribing can be helpful to reduce inappropriate prescribing. This study aims to apply a prediction model using a decision tree approach to predict the antimicrobial resistance (AMR) of urinary tract infections (UTI) based on non-clinical features of patients over 65 years. Decision tree models are a novel idea to predict the outcome of AMR at an initial stage. Method: Data was extracted from the database of the microbiological laboratory of the University Hospitals Galway on all antimicrobial susceptibility testing (AST) of urine specimens from patients over the age of 65 from January 2011 to December 2014. The primary endpoint was resistance to common antimicrobials (Nitrofurantoin, trimethoprim, ciprofloxacin, co-amoxiclav and amoxicillin) used to treat UTI. A classification and regression tree (CART) model was generated with the outcome ‘resistant infection’. The importance of each predictor (the number of previous samples, age, gender, location (nursing home, hospital, community) and causative agent) on antimicrobial resistance was estimated. Sensitivity, specificity, negative predictive (NPV) and positive predictive (PPV) values were used to evaluate the performance of the model. Seventy-five percent (75%) of the data were used as a training set and validation of the model was performed with the remaining 25% of the dataset. Results: A total of 9805 UTI patients over 65 years had their urine sample submitted for AST at least once over the four years. E.coli, Klebsiella, Proteus species were the most commonly identified pathogens among the UTI patients without catheter whereas Sertia, Staphylococcus aureus; Enterobacter was common with the catheter. The validated CART model shows slight differences in the sensitivity, specificity, PPV and NPV in between the models with and without the causative organisms. The sensitivity, specificity, PPV and NPV for the model with non-clinical predictors was between 74% and 88% depending on the antimicrobial. Conclusion: The CART models developed using non-clinical predictors have good performance when predicting antimicrobial resistance. These models predict which antimicrobial may be the most appropriate based on non-clinical factors. Other CART models, prospective data collection and validation and an increasing number of non-clinical factors will improve model performance. The presented model provides an alternative approach to decision making on antimicrobial prescribing for UTIs in older patients.

Keywords: antimicrobial resistance, urinary tract infection, prediction, decision tree

Procedia PDF Downloads 245

Authors: Kuo-C. Lo, Chung-H. Hung

Abstract:

Invasion of foreign air pollutants to deteriorate local air quality has become an emerging international issue of concern. This study aimed to apply meteorological and air quality model, WRF-Chem (V3.1), for simulating and analyzing the phenomenon of forming of high-concentrated particulate matters, PM10 and PM2.5, in ambient air of Taiwan during January 17th to 19th, 2014. The foreign air pollutants were mainly from long-distance transport of air pollutants of China being transported with a strong continental cold high. It was observed that PM10 and PM2.5 peaked as high as 182~588 μg/m3 and 95~165 μg/m3, respectively, in the ambient air of west side of Taiwan. They were about 2~3 folds higher than the usual concentrations of particulate matters in these seasons.

Keywords: WRF-Chem, air pollution, PM2.5, ambient air quality

Procedia PDF Downloads 443