Search results for: weather prediction

Authors: Thewodros K. Geberemariam

Abstract:

The rapid physical expansion of urbanization coupled with aging infrastructure presents a unique decision and management challenges for many big city municipalities. Cities must therefore upgrade and maintain the existing aging urban drainage infrastructure systems to keep up with the demands. Given the overall contribution of assets to municipal revenue and the importance of infrastructure to the success of a livable city, many municipalities are currently looking for a robust and smart urban drainage infrastructure asset management solution that combines management, financial, engineering and technical practices. This robust decision-making shall rely on sound, complete, current and relevant data that enables asset valuation, impairment testing, lifecycle modeling, and forecasting across the multiple asset portfolios. On this paper, predictive computational intelligence (CI) and multi-class machine learning (ML) coupled with online, offline, and historical record data that are collected from an array of multi-parameter sensors are used for the extraction of different operational and non-conforming patterns hidden in structured and unstructured data to determine and produce actionable insight on the current and future states of the network. This paper aims to improve the strategic decision-making process by identifying all possible alternatives; evaluate the risk of each alternative, and choose the alternative most likely to attain the required goal in a cost-effective manner using historical and near real-time urban drainage infrastructure data for urban drainage infrastructures assets that have previously not benefited from computational intelligence and machine learning advancements.

Keywords: computational intelligence, machine learning, urban drainage infrastructure, machine learning, classification, prediction, asset management space

Procedia PDF Downloads 124

Authors: Carlos Gonzales, Zaida Quiroz, Marcos Prates

Abstract:

Several spatial variables collected at the same location that share a common spatial distribution can be modeled simultaneously through a multivariate geostatistical model that takes into account the correlation between these variables and the spatial autocorrelation. The main goal of this model is to perform spatial prediction of these variables in the region of study. Here we focus on a geostatistical multivariate formulation that relies on sharing common spatial random effect terms. In particular, the first response variable can be modeled by a mean that incorporates a shared random spatial effect, while the other response variables depend on this shared spatial term, in addition to specific random spatial effects. Each spatial random effect is defined through a Gaussian process with a valid covariance function, but in order to improve the computational efficiency when the data are large, each Gaussian process is approximated to a Gaussian random Markov field (GRMF), specifically to the block nearest neighbor Gaussian process (Block-NNGP). This approach involves dividing the spatial domain into several dependent blocks under certain constraints, where the cross blocks allow capturing the spatial dependence on a large scale, while each individual block captures the spatial dependence on a smaller scale. The multivariate geostatistical model belongs to the class of Latent Gaussian Models; thus, to achieve fast Bayesian inference, it is used the integrated nested Laplace approximation (INLA) method. The good performance of the proposed model is shown through simulations and applications for massive data.

Keywords: Block-NNGP, geostatistics, gaussian process, GRMF, INLA, multivariate models.

Procedia PDF Downloads 68

Authors: Joe Dorbor Wuokolo

Abstract:

Thousands of smallholder farmers in Todee District, Montserrado county, are currently vulnerable to the negative impact of climate change. The district, which is the agricultural hot spot for the county, is faced with unfavorable changes in the daily temperature due to climate change. Farmers in the district have observed a dramatic change in the ratio of rainfall to sunshine, which has caused a chilling effect on their crop yields. However, there is a lack of documentation regarding how farmers perceive and respond to these changes and challenges. A study was conducted in the region to examine the perceptions of smallholder farmers regarding the negative impact of climate change, the adaptation strategies practice, and the barriers that hinder the process of advancing adaptation strategy. On purpose, a sample of 41 respondents from five towns was selected, including five town chiefs, five youth leaders, five women leaders, and sixteen community members. Women and youth leaders were specifically chosen to provide gender balance and enhance the quality of the investigation. Additionally, to validate the barriers farmers face during adaptation to climate change, this study interviewed eight experts from local and international organizations and government ministries and agencies involved in climate change and agricultural programs on what they perceived as the major barrier in both local and national level that impede farmers adaptation to climate change impact. SPSS was used to code the data, and descriptive statistics were used to analyze the data. The weighted average index (WAI) was used to rank adaptation strategies and the perceived importance of adaptation practices among farmers. On a scale from 0 to 3, 0 indicates the least important technique, and 3 indicates the most effective technique. In addition, the Problem Confrontation Index (PCI) was used to rank the barriers that prevented farmers from implementing adaptation measures. According to the findings, approximately 60% of all respondents considered the use of irrigation systems to be the most effective adaptation strategy, with drought-resistant varieties making up 30% of the total. Additionally, 80% of respondents placed a high value on drought-resistant varieties, while 63% percent placed it on irrigation practices. In addition, 78% of farmers ranked and indicated that unpredictability of the weather is the most significant barrier to their adaptation strategies, followed by the high cost of farm inputs and lack of access to financing facilities. 80% of respondents believe that the long-term changes in precipitation (rainfall) and temperature (hotness) are accelerating. This suggests that decision-makers should adopt policies and increase the capacity of smallholder farmers to adapt to the negative impact of climate change in order to ensure sustainable food production.

Keywords: adaptation strategies, climate change, farmers’ perception, smallholder farmers

Procedia PDF Downloads 62

Authors: Mathieu Bourdeau, Philippe Basset, Julien Waeytens, Elyes Nefzaoui

Abstract:

As residential buildings account for a third of the overall energy consumption and greenhouse gas emissions in Europe, building energy modeling is an essential tool to reach energy efficiency goals. In the energy modeling process, calibration is a mandatory step to obtain accurate and reliable energy simulations. Nevertheless, the comparison between simulation results and the actual building energy behavior often highlights a significant performance gap. The literature discusses different origins of energy performance gaps, from building design to building operation. Then, building operation description in energy models, especially energy usages and users’ behavior, plays an important role in the reliability of simulations but is also the most accessible target for post-occupancy energy management and optimization. Therefore, the present study aims to discuss results on the calibration ofresidential building energy models using real operation data. Data are collected through a sensor network of more than 180 sensors and advanced energy meters deployed in three collective residential buildings undergoing major retrofit actions. The sensor network is implemented at building scale and in an eight-apartment sample. Data are collected for over one year and half and coverbuilding energy behavior – thermal and electricity, indoor environment, inhabitants’ comfort, occupancy, occupants behavior and energy uses, and local weather. Building energy simulations are performed using a physics-based building energy modeling software (Pleaides software), where the buildings’features are implemented according to the buildingsthermal regulation code compliance study and the retrofit project technical files. Sensitivity analyses are performed to highlight the most energy-driving building features regarding each end-use. These features are then compared with the collected post-occupancy data. Energy-driving features are progressively replaced with field data for a step-by-step calibration of the energy model. Results of this study provide an analysis of energy performance gap on an existing residential case study under deep retrofit actions. It highlights the impact of the different building features on the energy behavior and the performance gap in this context, such as temperature setpoints, indoor occupancy, the building envelopeproperties but also domestic hot water usage or heat gains from electric appliances. The benefits of inputting field data from an extensive instrumentation campaign instead of standardized scenarios are also described. Finally, the exhaustive instrumentation solution provides useful insights on the needs, advantages, and shortcomings of the implemented sensor network for its replicability on a larger scale and for different use cases.

Keywords: calibration, building energy modeling, performance gap, sensor network

Procedia PDF Downloads 132

Authors: Laura Kupers, Julie Piérard, Niki Cauberg

Abstract:

The use of exposed concrete (sometimes referred to as architectural concrete), keeps gaining popularity. Exposed concrete has the advantage to combine the structural properties of concrete with an aesthetic finish. However, for a successful aesthetic finish, much attention needs to be paid to the execution (formwork, release agent, curing, weather conditions…), the concrete composition (choice of the raw materials and mix proportions) as well as to its fresh properties. For the latter, a simple on-site pass/fail test could halt the casting of concrete not suitable for architectural concrete and thus avoid expensive repairs later. When architects opt for an exposed concrete, they usually want a smooth, uniform and nearly blemish-free surface. For this choice, a standard ‘construction’ concrete does not suffice. An aesthetic surface finishing requires the concrete to contain a minimum content of fines to minimize the risk of segregation and to allow complete filling of more complex shaped formworks. The concrete may neither be too viscous as this makes it more difficult to compact and it increases the risk of blow holes blemishing the surface. On the other hand, too much bleeding may cause color differences on the concrete surface. An easy pass/fail test, which can be performed on the site just before the casting, could avoid these problems. In case the fresh concrete fails the test, the concrete can be rejected. Only in case the fresh concrete passes the test, the concrete would be cast. The pass/fail tests are intended for a concrete with a consistency class S4. Five tests were selected as possible onsite pass/fail test. Two of these tests already exist: the K-slump test (ASTM C1362) and the Bauer Filter Press Test. The remaining three tests were developed by the BBRI in order to test the segregation resistance of fresh concrete on site: the ‘dynamic sieve stability test’, the ‘inverted cone test’ and an adapted ‘visual stability index’ (VSI) for the slump and flow test. These tests were inspired by existing tests for self-compacting concrete, for which the segregation resistance is of great importance. The suitability of the fresh concrete mixtures was also tested by means of a laboratory reference test (resistance to segregation) and by visual inspection (blow holes, structure…) of small test walls. More than fifteen concrete mixtures of different quality were tested. The results of the pass/fail tests were compared with the results of this laboratory reference test and the test walls. The preliminary laboratory results indicate that concrete mixtures ‘suitable’ for placing as exposed concrete (containing sufficient fines, a balanced grading curve etc.) can be distinguished from ‘inferior’ concrete mixtures. Additional laboratory tests, as well as tests on site, will be conducted to confirm these preliminary results and to set appropriate pass/fail values.

Keywords: exposed concrete, testing fresh concrete, segregation resistance, bleeding, consistency

Procedia PDF Downloads 403

Authors: Elizabeth Crafton, Donald Ott, Teresa Cutright

Abstract:

Harmful algal blooms (HABs), more notably cyanobacteria-dominated HABs, compromise water quality, jeopardize access to drinking water and are a risk to public health and safety. HABs are representative of ecosystem imbalance largely caused by environmental changes, such as eutrophication, that are associated with the globally expanding human population. Cyanobacteria-dominated HABs are anticipated to increase in frequency, magnitude, and are predicted to plague a larger geographical area as a result of climate change. The weather pattern is important as storm-driven, pulse-input of nutrients have been correlated to cyanobacteria-dominated HABs. The mobilization of aqueous and particulate nutrients and the response of the phytoplankton community is an important relationship in this complex phenomenon. This relationship is most apparent in high-impact areas of adequate sunlight, > 20ᵒC, excessive nutrients and quiescent water that corresponds to ideal growth of HABs. Typically the impact of particulate phosphorus is dismissed as an insignificant contribution; which is true for areas that are not considered high-impact. The objective of this study was to assess the impact of a simulated storm-driven, pulse-input of reactive phosphorus and the response of three different cyanobacteria assemblages (~5,000 cells/mL). The aqueous and particulate sources of phosphorus and changes in HAB were tracked weekly for 4 weeks. The first cyanobacteria composition consisted of Planktothrix sp., Microcystis sp., Aphanizomenon sp., and Anabaena sp., with 70% of the total population being non-diazotrophic and 30% being diazotrophic. The second was comprised of Anabaena sp., Planktothrix sp., and Microcystis sp., with 87% diazotrophic and 13% non-diazotrophic. The third composition has yet to be determined as these experiments are ongoing. Preliminary results suggest that both aqueous and particulate sources are contributors of total reactive phosphorus in high-impact areas. The results further highlight shifts in the cyanobacteria assemblage after the simulated pulse-input. In the controls, the reactors dosed with aqueous reactive phosphorus maintained a constant concentration for the duration of the experiment; whereas, the reactors that were dosed with aqueous reactive phosphorus and contained soil decreased from 1.73 mg/L to 0.25 mg/L of reactive phosphorus from time zero to 7 days; this was higher than the blank (0.11 mg/L). Suggesting a binding of aqueous reactive phosphorus to sediment, which is further supported by the positive correlation observed between total reactive phosphorus concentration and turbidity. The experiments are nearly completed and a full statistical analysis will be completed of the results prior to the conference.

Keywords: Anabaena, cyanobacteria, harmful algal blooms, Microcystis, phosphorous, response surface methodology

Procedia PDF Downloads 139

Authors: Brindha Senthil Kumar, Payel Chakraborty, Senthil Kumar Nachimuthu, Arindam Maitra, Prem Nath

Abstract:

Gastric cancer is predominantly caused by demographic and diet factors as compared to other cancer types. The aim of the study is to predict Early Gastric Cancer (ECG) from diet and lifestyle factors using supervised machine learning algorithms. For this study, 160 healthy individual and 80 cases were selected who had been followed for 3 years (2016-2019), at Civil Hospital, Aizawl, Mizoram. A dataset containing 11 features that are core risk factors for the gastric cancer were extracted. Supervised machine algorithms: Logistic Regression, Naive Bayes, Support Vector Machine (SVM), Multilayer perceptron, and Random Forest were used to analyze the dataset using Python Jupyter Notebook Version 3. The obtained classified results had been evaluated using metrics parameters: minimum_false_positives, brier_score, accuracy, precision, recall, F1_score, and Receiver Operating Characteristics (ROC) curve. Data analysis results showed Naive Bayes - 88, 0.11; Random Forest - 83, 0.16; SVM - 77, 0.22; Logistic Regression - 75, 0.25 and Multilayer perceptron - 72, 0.27 with respect to accuracy and brier_score in percent. Naive Bayes algorithm out performs with very low false positive rates as well as brier_score and good accuracy. Naive Bayes algorithm classification results in predicting ECG showed very satisfactory results using only diet cum lifestyle factors which will be very helpful for the physicians to educate the patients and public, thereby mortality of gastric cancer can be reduced/avoided with this knowledge mining work.

Keywords: Early Gastric cancer, Machine Learning, Diet, Lifestyle Characteristics

Procedia PDF Downloads 130

Authors: Joonas Pääkkönen

Abstract:

In sports, individuals and teams are typically interested in final rankings. Final results, such as times or distances, dictate these rankings, also known as places. Places can be further associated with ordered random variables, commonly referred to as order statistics. In this work, we introduce a simple, yet accurate order statistical ordinal regression function that predicts relay race places with changeover-times. We call this function the Fenton-Wilkinson Order Statistics model. This model is built on the following educated assumption: individual leg-times follow log-normal distributions. Moreover, our key idea is to utilize Fenton-Wilkinson approximations of changeover-times alongside an estimator for the total number of teams as in the notorious German tank problem. This original place regression function is sigmoidal and thus correctly predicts the existence of a small number of elite teams that significantly outperform the rest of the teams. Our model also describes how place increases linearly with changeover-time at the inflection point of the log-normal distribution function. With real-world data from Jukola 2019, a massive orienteering relay race, the model is shown to be highly accurate even when the size of the training set is only 5% of the whole data set. Numerical results also show that our model exhibits smaller place prediction root-mean-square-errors than linear regression, mord regression and Gaussian process regression.

Keywords: Fenton-Wilkinson approximation, German tank problem, log-normal distribution, order statistics, ordinal regression, orienteering, sports analytics, sports modeling

Procedia PDF Downloads 104

Authors: Takuro Kida, Yuichi Kida

Abstract:

In this paper, it is shown a base of the new trend of algorithm mathematically that treats a historical reason of continuous discrimination in the world as well as its solution by introducing new concepts of parallel world that includes an invisible set of errors as its companion. With respect to a matrix operator-filter bank that the matrix operator-analysis-filter bank H and the matrix operator-sampling-filter bank S are given, firstly, we introduce the detail algorithm to derive the optimum matrix operator-synthesis-filter bank Z that minimizes all the worst-case measures of the matrix operator-error-signals E(ω) = F(ω) − Y(ω) between the matrix operator-input-signals F(ω) and the matrix operator-output-signals Y(ω) of the matrix operator-filter bank at the same time. Further, feedback is introduced to the above approximation theory, and it is indicated that introducing conversations with feedback do not superior automatically to the accumulation of existing knowledge of signal prediction. Secondly, the concept of category in the field of mathematics is applied to the above optimum signal approximation and is indicated that the category-based approximation theory is applied to the set-theoretic consideration of the recognition of humans. Based on this discussion, it is shown naturally why the narrow perception that tends to create isolation shows an apparent advantage in the short term and, often, why such narrow thinking becomes intimate with discriminatory action in a human group. Throughout these considerations, it is presented that, in order to abolish easy and intimate discriminatory behavior, it is important to create a parallel world of conception where we share the set of invisible error signals, including the words and the consciousness of both worlds.

Keywords: matrix filterbank, optimum signal approximation, category theory, simultaneous minimization

Procedia PDF Downloads 108

Authors: Bi-Huei Tsai

Abstract:

This work explores the inter-region investment behaviors of integrated circuit (IC) design industry from Taiwan to China using the amount of foreign direct investment (FDI). According to the mutual dependence among different IC design industrial locations, Lotka-Volterra model is utilized to explore the FDI interactions between South and East China. Effects of inter-regional collaborations on FDI flows into China are considered. Evolutions of FDIs into South China for IC design industry significantly inspire the subsequent FDIs into East China, while FDIs into East China for Taiwan’s IC design industry significantly hinder the subsequent FDIs into South China. The supply chain along IC industry includes IC design, manufacturing, packing and testing enterprises. I C manufacturing, packaging and testing industries depend on IC design industry to gain advanced business benefits. The FDI amount from Taiwan’s IC design industry into East China is the greatest among the four regions: North, East, Mid-West and South China. The FDI amount from Taiwan’s IC design industry into South China is the second largest. If IC design houses buy more equipment and bring more capitals in South China, those in East China will have pressure to undertake more FDIs into East China to maintain the leading position advantages of the supply chain in East China. On the other hand, as the FDIs in East China rise, the FDIs in South China will successively decline since capitals have concentrated in East China. Prediction of Lotka-Volterra model in FDI trends is accurate because the industrial interactions between the two regions are included. Finally, this work confirms that the FDI flows cannot reach a stable equilibrium point, so the FDI inflows into East and South China will expand in the future.

Keywords: Lotka-Volterra model, foreign direct investment, competitive, Equilibrium analysis

Procedia PDF Downloads 339

Authors: Theresa Ukamaka Nwagha, Angela Ogechukwu Ugwu, Martins Nweke

Abstract:

Background and Objectives: Blood transfusion is an effective and proven treatment for some severe complications of sickle cell disease. Recurrent transfusions have put patients with sickle cell disease at risk of developing antibodies against the various antigens they were exposed to. This study aims to investigate the frequency of red blood cell alloimmunization in patients with sickle disease in Africa. Materials and Methods: This is a systematic review of peer-reviewed literature published in English. The review was conducted consistent with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist. Data sources for the review include MEDLINE, PubMed, CINAHL, and Academic Search Complete. Included in this review are articles that reported the frequency/prevalence of red blood cell alloimmunization in sickle cell disease patients in Africa. Eligible studies were subjected to independent full-text screening and data extraction. Risk of bias assessment was conducted with the aid of the mixed method appraisal tool. We employed a random-effects model of meta-analysis to estimate the pooled prevalence. We computed Cochrane’s Q statistics and I2 and prediction interval to quantify heterogeneity in effect size. Results: The prevalence estimates range from 2.6% to 29%. Pooled prevalence was estimated to be 10.4% (CI 7.7.–13.8); PI = 3.0 – 34.0%), with significant heterogeneity (I2 = 84.62; PI = 2.0-32.0%) and publication bias (Egger’s t-test = 1.744, p = 0.0965). Conclusion: The frequency of red cell alloantibody varies considerably in Africa. The alloantibodies appeared frequent in this order: the Rhesus, Kell, Lewis, Duffy, MNS, and Lutheran

Keywords: frequency, red blood cell, alloimmunization, sickle cell disease, Africa

Procedia PDF Downloads 69

Authors: Xianghe Dai, Dennis Lam, Therese Sheehan, Naveed Rehman, Jie Yang

Abstract:

Concrete is one of the most used construction materials that may be made onsite as fresh concrete and then placed in formwork to produce the desired shapes of structures. It has been recognized that the raw materials and mix proportion of concrete dominate the mechanical characteristics of hardened concrete, and the curing method and environment applied to the concrete in early stages of hardening will significantly influence the concrete properties, such as compressive strength, durability, permeability etc. In construction practice, there are various curing methods to maintain the presence of mixing water throughout the early stages of concrete hardening. They are also beneficial to concrete in hot weather conditions as they provide cooling and prevent the evaporation of water. Such methods include ponding or immersion, spraying or fogging, saturated wet covering etc. Also there are various curing methods that may be implemented to decrease the level of water lost which belongs to the concrete surface, such as putting a layer of impervious paper, plastic sheeting or membrane on the concrete to cover it. In the concrete material laboratory, accelerated strength gain methods supply the concrete with heat and additional moisture by applying live steam, coils that are subject to heating or pads that have been warmed electrically. Currently when determining the mechanical parameters of a concrete, the concrete is usually sampled from fresh concrete on site and then cured and tested in laboratories where standardized curing procedures are adopted. However, in engineering practice, curing procedures in the construction sites after the placing of concrete might be very different from the laboratory criteria, and this includes some standard curing procedures adopted in the laboratory that can’t be applied on site. Sometimes the contractor compromises the curing methods in order to reduce construction costs etc. Obviously the difference between curing procedures adopted in the laboratory and those used on construction sites might over- or under-estimate the real concrete quality. This paper presents the effect of three typical curing methods (air curing, water immersion curing, plastic film curing) and of maintaining concrete in steel moulds on the compressive strength development of normal concrete. In this study, Portland cement with 30% fly ash was used and different curing periods, 7 days, 28 days and 60 days were applied. It was found that the highest compressive strength was observed from concrete samples to which 7-day water immersion curing was applied and from samples maintained in steel moulds up to the testing date. The research results implied that concrete used as infill in steel tubular members might develop a higher strength than predicted by design assumptions based on air curing methods. Wrapping concrete with plastic film as a curing method might delay the concrete strength development in the early stages. Water immersion curing for 7 days might significantly increase the concrete compressive strength.

Keywords: compressive strength, air curing, water immersion curing, plastic film curing, maintaining in steel mould, comparison

Procedia PDF Downloads 269

Authors: Muhammed Ashiq Villanthenkodath, Shreya Pal

Abstract:

Purpose: This study scrutinizes the impact of economic globalization on ecological footprint while endogenizing economic growth and energy consumption from 1990 to 2018 in India. Design/methodology/approach: The standard unit root test has been employed for time series analysis to unveil the integration order. Then, the cointegration was confirmed using autoregressive distributed lag (ARDL) analysis. Further, the study executed the dynamic ARDL simulation model to estimate long-run and short-run results along with simulation and robotic prediction. Findings: The cointegration analysis confirms the existence of a long-run association among variables. Further, economic globalization reduces the ecological footprint in the long run. Similarly, energy consumption decreases the ecological footprint. In contrast, economic growth spurs the ecological footprint in India. Originality/value: This study contributes to the literature in many ways. First, unlike studies that employ CO2 emissions and globalization nexus, this study employs ecological footprint for measuring environmental quality; since it is the broader measure of environmental quality, it can offer a wide range of climate change mitigation policies for India. Second, the study executes a multivariate framework with updated series from 1990 to 2018 in India to explore the link between EF, economic globalization, energy consumption, and economic growth. Third, the dynamic autoregressive distributed lag (ARDL) model has been used to explore the short and long-run association between the series. Finally, to our limited knowledge, this is the first study that uses economic globalization in the EF function of India amid facing a trade-off between sustainable economic growth and the environment in the era of globalization.

Keywords: economic globalization, ecological footprint, India, dynamic ARDL simulation model

Procedia PDF Downloads 98

Authors: Zhongmin Wang, Wudong Fan, Hengshan Zhang, Yimin Zhou

Abstract:

In data-driven prognostic methods, the prediction accuracy of the estimation for remaining useful life of bearings mainly depends on the performance of health indicators, which are usually fused some statistical features extracted from vibrating signals. However, the existing health indicators have the following two drawbacks: (1) The differnet ranges of the statistical features have the different contributions to construct the health indicators, the expert knowledge is required to extract the features. (2) When convolutional neural networks are utilized to tackle time-frequency features of signals, the time-series of signals are not considered. To overcome these drawbacks, in this study, the method combining convolutional neural network with gated recurrent unit is proposed to extract the time-frequency image features. The extracted features are utilized to construct health indicator and predict remaining useful life of bearings. First, original signals are converted into time-frequency images by using continuous wavelet transform so as to form the original feature sets. Second, with convolutional and pooling layers of convolutional neural networks, the most sensitive features of time-frequency images are selected from the original feature sets. Finally, these selected features are fed into the gated recurrent unit to construct the health indicator. The results state that the proposed method shows the enhance performance than the related studies which have used the same bearing dataset provided by PRONOSTIA.

Keywords: continuous wavelet transform, convolution neural net-work, gated recurrent unit, health indicators, remaining useful life

Procedia PDF Downloads 106

Authors: Tugba Bayoglu

Abstract:

Aerodynamic parameter estimation is very crucial in missile design phase, since accurate high fidelity aerodynamic model is required for designing high performance and robust control system, developing high fidelity flight simulations and verification of computational and wind tunnel test results. However, in literature, there is not enough missile aerodynamic parameter identification study for three main reasons: (1) most air to air missiles cannot fly with constant speed, (2) missile flight test number and flight duration are much less than that of fixed wing aircraft, (3) variation of the missile aerodynamic parameters with respect to Mach number is higher than that of fixed wing aircraft. In addition to these challenges, identification of aerodynamic parameters for high wind angles by using classical estimation techniques brings another difficulty in the estimation process. The reason for this, most of the estimation techniques require employing polynomials or splines to model the behavior of the aerodynamics. However, for the missiles with a large variation of aerodynamic parameters with respect to flight variables, the order of the proposed model increases, which brings computational burden and complexity. Therefore, in this study, it is aimed to solve nonlinear aerodynamic parameter identification problem for a supersonic air to air missile by using Artificial Neural Networks. The method proposed will be tested by using simulated data which will be generated with a six degree of freedom missile model, involving a nonlinear aerodynamic database. The data will be corrupted by adding noise to the measurement model. Then, by using the flight variables and measurements, the parameters will be estimated. Finally, the prediction accuracy will be investigated.

Keywords: air to air missile, artificial neural networks, open loop simulation, parameter identification

Procedia PDF Downloads 250

Authors: Mohammed Saleh Rezk, Reza Kashani

Abstract:

Auxiliary damping has gained popularity in recent years, especially in structures such as mid- and high-rise buildings. Distributed damping systems (typically viscous and viscoelastic) or reactive damping systems (such as tuned mass dampers) are the two types of damping choices for such structures. Distributed VE dampers are normally configured as braces or damping panels, which are engaged through relatively small movements between the structural members when the structure sways under wind or earthquake loading. In addition to being used as stand-alone dampers in distributed damping applications, VE dampers can also be incorporated into the suspension element of tuned mass dampers (TMDs). In this study, analytical and numerical tools for modeling and design of multilayer viscoelastic damping devices to be used in dampening the vibration of large structures are developed. Considering the limitations of analytical models for the synthesis and analysis of realistic, large, multilayer VE dampers, the emphasis of the study has been on numerical modeling using the finite element method. To verify the finite element models, a two-layer VE damper using ½ inch synthetic viscoelastic urethane polymer was built, tested, and the measured parameters were compared with the numerically predicted ones. The numerical model prediction and experimentally evaluated damping and stiffness of the test VE damper were in very good agreement. The effectiveness of VE dampers in adding auxiliary damping to larger structures is numerically demonstrated by chevron bracing one such damper numerically into the model of a massive frame subject to an abrupt lateral load. A comparison of the responses of the frame to the aforementioned load, without and with the VE damper, clearly shows the efficacy of the damper in lowering the extent of frame vibration.

Keywords: viscoelastic, damper, distributed damping, tuned mass damper

Procedia PDF Downloads 80

Authors: Ashirgul Kozhagulova, Ainash Shabdirova, Galym Tokazhanov, Minh Nguyen

Abstract:

The synthetic rocks have been advantageous over the natural rocks in terms of availability and the consistent studying the impact of a particular parameter. The artificial rocks can be fabricated using variety of techniques such as mixing sand and Portland cement or gypsum, firing the mixture of sand and fine powder of borosilicate glass or by in-situ precipitation of calcite solution. In this study, sodium silicate solution has been used as the cementing agent for the quartz sand. The molded soft cylindrical sandstone samples are placed in the gas-tight pressure vessel, where the hardening of the material takes place as the chemical reaction between carbon dioxide and the silicate solution progresses. The vessel allows uniform disperse of carbon dioxide and control over the ambient gas pressure. Current paper shows how the bonding material is initially distributed in the intergranular space and the surface of the sand particles by the usage of Electron Microscopy and the Energy Dispersive Spectroscopy. During the study, the strength of the cement bond as a function of temperature is observed. The impact of cementing agent dosage on the micro and macro characteristics of the sandstone is investigated. The analysis of the cement bond at micro level helps to trace the changes to particles bonding damage after a potential yielding. Shearing behavior and compressional response have been examined resulting in the estimation of the shearing resistance and cohesion force of the sandstone. These are considered to be main input values to the mathematical prediction models of sand production from weak clastic oil reservoir formations.

Keywords: artificial sanstone, cement bond, microstructure, SEM, triaxial shearing

Procedia PDF Downloads 143

Authors: Ashis Mallick, Rajeev Ranjan

Abstract:

The closed form solution for thermal stresses in an annular fin with hyperbolic profile is derived using Adomian decomposition method (ADM). The conductive-convective fin with variable thermal conductivity is considered in the analysis. The nonlinear heat transfer equation is efficiently solved by ADM considering insulated convective boundary conditions at the tip of fin. The constant of integration in the solution is to be estimated using minimum decomposition error method. The solution of temperature field is represented in a polynomial form for convenience to use in thermo-elasticity equation. The non-dimensional thermal stress fields are obtained using the ADM solution of temperature field coupled with the thermo-elasticity solution. The influence of the various thermal parameters in temperature field and stress fields are presented. In order to show the accuracy of the ADM solution, the present results are compared with the results available in literature. The stress fields in fin with hyperbolic profile are compared with those of uniform thickness profile. Result shows that hyperbolic fin profile is better choice for enhancing heat transfer. Moreover, less thermal stresses are developed in hyperbolic profile as compared to rectangular profile. Next, Nelder-Mead based simplex search method is employed for the inverse estimation of unknown non-dimensional thermal parameters in a given stress fields. Owing to the correlated nature of the unknowns, the best combinations of the model parameters which are satisfying the predefined stress field are to be estimated. The stress fields calculated using the inverse parameters give a very good agreement with the stress fields obtained from the forward solution. The estimated parameters are suitable to use for efficient and cost effective fin designing.

Keywords: Adomian decomposition, inverse analysis, hyperbolic fin, variable thermal conductivity

Procedia PDF Downloads 304

Authors: Omar Bouledroua, Djamel Zelmati, Zahreddine Hafsi, Milos B. Djukic

Abstract:

Transporting hydrogen gas through the existing natural gas pipeline network offers an efficient solution for energy storage and conveyance. Hydrogen generated from excess renewable electricity can be conveyed through the API 5L steel-made pipelines that already exist. In recent years, there has been a growing demand for the transportation of hydrogen through existing gas pipelines. Therefore, numerical and experimental tests are required to verify and ensure the mechanical integrity of the API 5L steel pipelines that will be used for pressurized hydrogen transportation. Internal pressure loading is likely to accelerate hydrogen diffusion through the internal pipe wall and consequently accentuate the hydrogen embrittlement of steel pipelines. Furthermore, pre-cracked pipelines are susceptible to quick failure, mainly under a time-dependent cyclic pressure loading that drives fatigue crack propagation. Meanwhile, after several loading cycles, the initial cracks will propagate to a critical size. At this point, the remaining service life of the pipeline can be estimated, and inspection intervals can be determined. This paper focuses on the hydrogen embrittlement of API 5L steel-made pipeline under cyclic pressure loading. Pressurized hydrogen gas is transported through a network of pipelines where demands at consumption nodes vary periodically. The resulting pressure profile over time is considered a cyclic loading on the internal wall of a pre-cracked pipeline made of API 5L steel-grade material. Numerical modeling has allowed the prediction of fatigue crack evolution and estimation of the remaining service life of the pipeline. The developed methodology in this paper is based on the ASME B31.12 standard, which outlines the guidelines for hydrogen pipelines.

Keywords: hydrogen embrittlement, pipelines, transient flow, cyclic pressure, fatigue crack growth

Procedia PDF Downloads 55

Authors: Mauro Iannazzone, Carmine D'Agostino

Abstract:

Off-shore wind turbines are currently considered as a reliable source of renewable energy Worldwide and especially in the UK. Most of the operational off-shore wind turbines located in shallow waters (i.e. < 30 m) are supported on monopiles. Monopiles are open-ended steel tubes with diameter ranging between 4 to 6 m. It is expected that future off-shore wind farms will be located in water depths as high as 70 m. Therefore, alternative foundation arrangements are needed. Foundations for off-shore structures normally consist of open-ended piles driven into the soil by means of impact hammers. During pile installation, the soil inside the pile may be mobilized by the increasing shear strength such as to prevent more soil from entering the pile. This phenomenon is known as soil plugging, and represents an important issue as it may change significantly the driving resistance of open-ended piles. In fact, if the plugging formation is unexpected, the installation may require more powerful and more expensive hammers. Engineers need to estimate whether the driven pile will be installed in a plugged or unplugged mode. As a consequence, a prediction of the degree of soil plugging is required in order to correctly predict the drivability of the pile. This work presents a brief review of the state-of-the-art of pile driving and approaches used to predict formation of soil plugs. In addition, a novel analytical approach is proposed, which is based on the vertical equilibrium of a plugged pile. Differently from previous studies, this research takes into account the enhancement of the stress within the soil plug. Finally, the work presents and discusses a series of experimental tests, which are carried out on small-scale models piles to validate the analytical solution.

Keywords: off-shore wind turbines, pile installation, soil plugging, wind energy

Procedia PDF Downloads 293

Authors: Domingos Viegas, Miguel Almeida, Carmen Rocha, Ilda Novo, Yolanda Luna

Abstract:

Forest fires along the more than 1200km of the Spanish-Portuguese border are more and more frequent, currently achieving around 2000 fire events per year. Some of these events develop to large international wildfire requiring concerted operations based on shared information between the two countries. The fire event of Valencia de Alcantara (2003) causing several fatalities and more than 13000ha burnt, is a reference example of these international events. Currently, Portugal and Spain have a specific cross-border cooperation protocol on wildfires response for a strip of about 30km (15 km for each side). It is recognized by public authorities the successfulness of this collaboration however it is also assumed that this cooperation should include more functionalities such as the development of a common risk information system for transboundary fire events. Since Portuguese and Spanish authorities use different approaches to determine the fire risk indexes inputs and different methodologies to assess the fire risk, sometimes the conjoint firefighting operations are jeopardized since the information is not harmonized and the understanding of the situation by the civil protection agents from both countries is not unique. Thus, a methodology aiming the harmonization of the fire risk calculation and perception by Portuguese and Spanish Civil protection authorities is hereby presented. The final results are presented as well. The fire risk index used in this work is the Canadian Fire Weather Index (FWI), which is based on meteorological data. The FWI is limited on its application as it does not take into account other important factors with great effect on the fire appearance and development. The combination of these factors is very complex since, besides the meteorology, it addresses several parameters of different topics, namely: sociology, topography, vegetation and soil cover. Therefore, the meaning of FWI values is different from region to region, according the specific characteristics of each region. In this work, a methodology for FWI calibration based on the number of fire occurrences and on the burnt area in the transboundary regions of Portugal and Spain, in order to assess the fire risk based on calibrated FWI values, is proposed. As previously mentioned, the cooperative firefighting operations require a common perception of the information shared. Therefore, a common classification of the fire risk for the fire events occurred in the transboundary strip is proposed with the objective of harmonizing this type of information. This work is integrated in the ECHO project SpitFire - Spanish-Portuguese Meteorological Information System for Transboundary Operations in Forest Fires, which aims the development of a web platform for the sharing of information and supporting decision tools to be used in international fire events involving Portugal and Spain.

Keywords: data harmonization, FWI, international collaboration, transboundary wildfires

Procedia PDF Downloads 227

Authors: Levente Kovács, Fruzsina Luca Kézér, Ottó Szenci

Abstract:

Prediction of the onset of calving and recognizing difficulties at calving has great importance in decreasing neonatal losses and reducing the risk of health problems in the early postpartum period. In this study, changes of rumination time, reticuloruminal pH and temperature were investigated in eutocic (EUT, n = 10) and dystocic (DYS, n = 8) dairy cows around parturition. Rumination time was continuously recorded using an acoustic biotelemetry system, whereas reticuloruminal pH and temperature were recorded using an indwelling and wireless data transmitting system. The recording period lasted from 3 d before calving until 7 days in milk. For the comparison of rumination time and reticuloruminal characteristics between groups, time to return to baseline (the time interval required to return to baseline from the delivery of the calf) and area under the curve (AUC, both for prepartum and postpartum periods) were calculated for each parameter. Rumination time decreased from baseline 28 h before calving both for EUT and DYS cows (P = 0.023 and P = 0.017, respectively). After 20 h before calving, it decreased onwards to reach 32.4 ± 2.3 and 13.2 ± 2.0 min/4 h between 8 and 4 h before delivery in EUT and DYS cows, respectively, and then it decreased below 10 and 5 min during the last 4 h before calving (P = 0.003 and P = 0.008, respectively). Until 12 h after delivery rumination time reached 42.6 ± 2.7 and 51.0 ± 3.1 min/4 h in DYS and EUT dams, respectively, however, AUC and time to return to baseline suggested lower rumination activity in DYS cows than in EUT dams for the 168-h postpartum observational period (P = 0.012 and P = 0.002, respectively). Reticuloruminal pH decreased from baseline 56 h before calving both for EUT and DYS cows (P = 0.012 and P = 0.016, respectively), but did not differ between groups before delivery. In DYS cows, reticuloruminal temperature decreased from baseline 32 h before calving by 0.23 ± 0.02 °C (P = 0.012), whereas in EUT cows such a decrease was found only 20 h before delivery (0.48 ± 0.05 °C, P < 0.01). AUC of reticuloruminal temperature calculated for the prepartum period was greater in EUT cows than in DYS cows (P = 0.042). During the first 4 h after calving, it decreased from 39.7 ± 0.1 to 39.00 ± 0.1 °C and from 39.8 ± 0.1 to 38.8 ± 0.1 °C in EUT and DYS cows, respectively (P < 0.01 for both groups) and reached baseline levels after 35.4 ± 3.4 and 37.8 ± 4.2 h after calving in EUT and DYS cows, respectively. Based on our results, continuous monitoring of changes in rumination time and reticuloruminal temperature seems to be promising in the early detection of cows with a higher risk of dystocia. Depressed postpartum rumination time of DYS cows highlights the importance of the monitoring of cows experiencing difficulties at calving.

Keywords: reticuloruminal pH, reticuloruminal temperature, rumination time, dairy cows, dystocia

Procedia PDF Downloads 296

Authors: N. D. Iswarya, M. A. Maluk Mohamed, N. Vijaya

Abstract:

Grid is infrastructure that allows the deployment of distributed data in large size from multiple locations to reach a common goal. Scheduling data intensive applications becomes challenging as the size of data sets are very huge in size. Only two solutions exist in order to tackle this challenging issue. First, computation which requires huge data sets to be processed can be transferred to the data site. Second, the required data sets can be transferred to the computation site. In the former scenario, the computation cannot be transferred since the servers are storage/data servers with little or no computational capability. Hence, the second scenario can be considered for further exploration. During scheduling, transferring huge data sets from one site to another site requires more network bandwidth. In order to mitigate this issue, this work focuses on incorporating cognitive science in scheduling. Cognitive Science is the study of human brain and its related activities. Current researches are mainly focused on to incorporate cognitive science in various computational modeling techniques. In this work, the problem solving approach of human brain is studied and incorporated during the data intensive scheduling in grid environments. Here, a cognitive engine is designed and deployed in various grid sites. The intelligent agents present in CE will help in analyzing the request and creating the knowledge base. Depending upon the link capacity, decision will be taken whether to transfer data sets or to partition the data sets. Prediction of next request is made by the agents to serve the requesting site with data sets in advance. This will reduce the data availability time and data transfer time. Replica catalog and Meta data catalog created by the agents assist in decision making process.

Keywords: data grid, grid workflow scheduling, cognitive artificial intelligence

Procedia PDF Downloads 370

Authors: Didier Auroux, Vladimir Groza

Abstract:

This work is part of STEEP Marie-Curie ITN project, and it focuses on the identification of unknown parameters of the proposed generic Abrasive WaterJet Milling (AWJM) PDE model, that appears as an ill-posed inverse problem. The necessity of studying this problem comes from the industrial milling applications where the possibility to predict and model the final surface with high accuracy is one of the primary tasks in the absence of any knowledge of the model parameters that should be used. In this framework, we propose the identification of model parameters by minimizing a cost function, measuring the difference between experimental and numerical solutions. The adjoint approach based on corresponding Lagrangian gives the opportunity to find out the unknowns of the AWJM model and their optimal values that could be used to reproduce the required trench profile. Due to the complexity of the nonlinear problem and a large number of model parameters, we use an automatic differentiation software tool (TAPENADE) for the adjoint computations. By adding noise to the artificial data, we show that in fact the parameter identification problem is highly unstable and strictly depends on input measurements. Regularization terms could be effectively used to deal with the presence of data noise and to improve the identification correctness. Based on this approach we present results in 2D and 3D of the identification of the model parameters and of the surface prediction both with self-generated data and measurements obtained from the real production. Considering different types of model and measurement errors allows us to obtain acceptable results for manufacturing and to expect the proper identification of unknowns. This approach also gives us the ability to distribute the research on more complex cases and consider different types of model and measurement errors as well as 3D time-dependent model with variations of the jet feed speed.

Keywords: Abrasive Waterjet Milling, inverse problem, model parameters identification, regularization

Procedia PDF Downloads 291

Authors: Anwesha Pathak

Abstract:

With the increasing number of satellites and space debris, space traffic management (STM) becomes crucial. AI can aid in STM by predicting and preventing potential collisions, optimizing satellite trajectories, and managing orbital slots. Governance frameworks need to address the integration of AI algorithms in STM to ensure safe and sustainable satellite activities. AI and governance play significant roles in the context of satellite activities in space. Artificial intelligence (AI) technologies, such as machine learning and computer vision, can be utilized to process vast amounts of data received from satellites. AI algorithms can analyse satellite imagery, detect patterns, and extract valuable information for applications like weather forecasting, urban planning, agriculture, disaster management, and environmental monitoring. AI can assist in automating and optimizing satellite operations. Autonomous decision-making systems can be developed using AI to handle routine tasks like orbit control, collision avoidance, and antenna pointing. These systems can improve efficiency, reduce human error, and enable real-time responsiveness in satellite operations. AI technologies can be leveraged to enhance the security of satellite systems. AI algorithms can analyze satellite telemetry data to detect anomalies, identify potential cyber threats, and mitigate vulnerabilities. Governance frameworks should encompass regulations and standards for securing satellite systems against cyberattacks and ensuring data privacy. AI can optimize resource allocation and utilization in satellite constellations. By analyzing user demands, traffic patterns, and satellite performance data, AI algorithms can dynamically adjust the deployment and routing of satellites to maximize coverage and minimize latency. Governance frameworks need to address fair and efficient resource allocation among satellite operators to avoid monopolistic practices. Satellite activities involve multiple countries and organizations. Governance frameworks should encourage international cooperation, information sharing, and standardization to address common challenges, ensure interoperability, and prevent conflicts. AI can facilitate cross-border collaborations by providing data analytics and decision support tools for shared satellite missions and data sharing initiatives. AI and governance are critical aspects of satellite activities in space. They enable efficient and secure operations, ensure responsible and ethical use of AI technologies, and promote international cooperation for the benefit of all stakeholders involved in the satellite industry.

Keywords: satellite, space debris, traffic, threats, cyber security.

Procedia PDF Downloads 43

Authors: Idris M. Olatunde, Kareem B.

Abstract:

In manufacturing systems, especially job shops, service performance is a key factor that determines customer satisfaction. Service performance depends not only on the quality of the output but on the delivery lead times as well. Besides product quality enhancement, delivery lead time must be minimized for optimal patronage. Quoting accurate due dates is sine quo non for job shop operational survival in a global competitive environment. Quoting accurate due dates in job shops has been a herculean task that nearly defiled solutions from many methods employed due to complex jobs routing nature of the system. This class of NP-hard problems possessed no rigid algorithms that can give an optimal solution. Jobshop operational problem is more complex in developing nations due to some peculiar factors. Operational complexity in job shops emanated from political instability, poor economy, technological know-how, and the non-promising socio-political environment. The mentioned exogenous factors were hardly considered in the previous studies on scheduling problem related to due date determination in job shops. This study has filled the gap created in the past studies by developing a dynamic model that incorporated the exogenous factors for accurate determination of due dates for varying jobs complexity. Real data from six job shops selected from the different part of Nigeria, were used to test the efficacy of the model, and the outcomes were analyzed statistically. The results of the analyzes showed that the model is more promising in determining accurate due dates than the traditional models deployed by many job shops in terms of patronage and lead times minimization.

Keywords: due dates prediction, improved performance, customer satisfaction, dynamic model, exogenous factors, job shops

Procedia PDF Downloads 387

Authors: Gajanan M. Sonwane

Abstract:

Nowadays, the entire pharmaceutical industry is facing the challenge of increasing efficiency and innovation. The major hurdles are the growing cost of research and development and a concurrent stagnating number of new chemical entities (NCEs). Hence, the challenge is to select the most druggable targets and to search the equivalent drug-like compounds, which also possess specific pharmacokinetic and toxicological properties that allow them to be developed as drugs. The present research work includes the studies of developing new anticancer heterocycles by using molecular modeling techniques. The heterocycles synthesized through such methodology are much effective as various physicochemical parameters have been already studied and the structure has been optimized for its best fit in the receptor. Hence, on the basis of the literature survey and considering the need to develop newer anticancer agents, new phenazinamine derivatives were designed by subjecting the nucleus to molecular modeling, viz., GQSAR analysis and docking studies. Simultaneously, these designed derivatives were subjected to in silico prediction of biological activity through PASS studies and then in silico toxicity risk assessment studies. In PASS studies, it was found that all the derivatives exhibited a good spectrum of biological activities confirming its anticancer potential. The toxicity risk assessment studies revealed that all the derivatives obey Lipinski’s rule. Amongst these series, compounds 4c, 5b and 6c were found to possess logP and drug-likeness values comparable with the standard Imatinib (used for anticancer activity studies) and also with the standard drug methotrexate (used for antimitotic activity studies). One of the most notable mutations is the threonine to isoleucine mutation at codon 315 (T315I), which is known to be resistant to all currently available TKI. Enzyme assay planned for confirmation of target selective activity.

Keywords: drug design, tyrosine kinases, anticancer, Phenazinamine

Procedia PDF Downloads 90

Authors: Maryam Zarabian, Hector Guzman, Pedro Pereira-Almao, Abraham Fapojuwo

Abstract:

Dry reforming of methane (DRM) has sparked significant industrial and scientific interest not only as a viable alternative for addressing the environmental concerns of two main contributors of the greenhouse effect, i.e., carbon dioxide (CO₂) and methane (CH₄), but also produces syngas, i.e., a mixture of hydrogen (H₂) and carbon monoxide (CO) utilized by a wide range of downstream processes as a feedstock for other chemical productions. In this study, we develop an AI-enable syngas production model to tackle the problem of achieving an equivalent H₂/CO ratio [1:1] with respect to the most efficient conversion. Firstly, the unsupervised density-based spatial clustering of applications with noise (DBSAN) algorithm removes outlier data points from the original experimental dataset. Then, random forest (RF) and deep neural network (DNN) models employ the error-free dataset to predict the DRM results. DNN models inherently would not be able to obtain accurate predictions without a huge dataset. To cope with this limitation, we employ reusing pre-trained layers’ approaches such as transfer learning and greedy layer-wise pretraining. Compared to the other deep models (i.e., pure deep model and transferred deep model), the greedy layer-wise pre-trained deep model provides the most accurate prediction as well as similar accuracy to the RF model with R² values 1.00, 0.999, 0.999, 0.999, 0.999, and 0.999 for the total outlet flow, H₂/CO ratio, H₂ yield, CO yield, CH₄ conversion, and CO₂ conversion outputs, respectively.

Keywords: artificial intelligence, dry reforming of methane, artificial neural network, deep learning, machine learning, transfer learning, greedy layer-wise pretraining

Procedia PDF Downloads 63

Authors: K. Geetha Ramesh, A. Ramachandraiah

Abstract:

In an internal building space, daylight becomes a powerful source of illumination. The challenge therefore, is to develop means of utilizing both direct and diffuse natural light in buildings while maintaining and improving occupant's visual comfort, particularly at greater distances from the windows throwing daylight. The geometrical features of windows in a building have significant effect in providing daylight. The main goal of this research is to develop an innovative window geometry, which will effectively provide the daylight component adequately together with internal reflected component(IRC) and also the external reflected component(ERC), if any. This involves exploration of a light redirecting system using fractal geometry for windows, in order to penetrate and distribute daylight more uniformly to greater depths, minimizing heat gain and glare, and also to reduce building energy use substantially. Of late the creation of fractal geometrical window and the occurrence of daylight illuminance due to such windows is becoming an interesting study. The amount of daylight can change significantly based on the window geometry and sky conditions. This leads to the (i) exploration of various fractal patterns suitable for window designs, and (ii) quantification of the effect of chosen fractal window based on the relationship between the fractal pattern, size, orientation and glazing properties for optimizing daylighting. There are a lot of natural lighting applications able to predict the behaviour of a light in a room through a traditional opening - a regular window. The conventional prediction methodology involves the evaluation of the daylight factor, the internal reflected component and the external reflected component. Having evaluated the daylight illuminance level for a conventional window, the technical performance of a fractal window for an optimal daylighting is to be studied and compared with that of a regular window. The methodologies involved are highlighted in this paper.

Keywords: daylighting, fractal geometry, fractal window, optimization

Procedia PDF Downloads 281

Authors: Pius Marthin, Nihal Ata Tutkun

Abstract:

Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional and machine learning models and our model demonstrates better performance across all datasets.

Keywords: cumulative incidence function (CIF), risk information weight (RIW), autoencoders (AE), survival analysis, recurrent events with competing risks, recurrent neural networks (RNN), long short-term memory (LSTM), self-attention, multilayers perceptrons (MLPs)

Procedia PDF Downloads 59