Search results for: stochastic frontier

Authors: Getaneh Berie Tarekegn, Li-Chia Tai

Abstract:

With the rapid advancement of artificial intelligence, low-power built-in sensors on Internet of Things devices, and communication technologies, location-aware services have become increasingly popular and have permeated every aspect of people’s lives. Global navigation satellite systems (GNSSs) are the default method of providing continuous positioning services for ground and aerial vehicles, as well as consumer devices (smartphones, watches, notepads, etc.). However, the environment affects satellite positioning systems, particularly indoors, in dense urban and suburban cities enclosed by skyscrapers, or when deep shadows obscure satellite signals. This is because (1) indoor environments are more complicated due to the presence of many objects surrounding them; (2) reflection within the building is highly dependent on the surrounding environment, including the positions of objects and human activity; and (3) satellite signals cannot be reached in an indoor environment, and GNSS doesn't have enough power to penetrate building walls. GPS is also highly power-hungry, which poses a severe challenge for battery-powered IoT devices. Due to these challenges, IoT applications are limited. Consequently, precise, seamless, and ubiquitous Positioning, Navigation and Timing (PNT) systems are crucial for many artificial intelligence Internet of Things (AI-IoT) applications in the era of smart cities. Their applications include traffic monitoring, emergency alarming, environmental monitoring, location-based advertising, intelligent transportation, and smart health care. This paper proposes a generative AI-based positioning scheme for large-scale wireless settings using fingerprinting techniques. In this article, we presented a novel semi-supervised deep convolutional generative adversarial network (S-DCGAN)-based radio map construction method for real-time device localization. We also employed a reliable signal fingerprint feature extraction method with t-distributed stochastic neighbor embedding (t-SNE), which extracts dominant features while eliminating noise from hybrid WLAN and long-term evolution (LTE) fingerprints. The proposed scheme reduced the workload of site surveying required to build the fingerprint database by up to 78.5% and significantly improved positioning accuracy. The results show that the average positioning error of GAILoc is less than 0.39 m, and more than 90% of the errors are less than 0.82 m. According to numerical results, SRCLoc improves positioning performance and reduces radio map construction costs significantly compared to traditional methods.

Keywords: location-aware services, feature extraction technique, generative adversarial network, long short-term memory, support vector machine

Procedia PDF Downloads 13

Authors: Francesca Marsili

Abstract:

The reliability assessment of existing structures with probabilistic methods is becoming an increasingly important and frequent engineering task. However probabilistic reliability methods are based on an exhaustive knowledge of the stochastic modeling of the variables involved in the assessment; at the moment standards for the modeling of variables are absent, representing an obstacle to the dissemination of probabilistic methods. The framework according to probability distribution functions (PDFs) are established is represented by the Bayesian statistics, which uses Bayes Theorem: a prior PDF for the considered parameter is established based on information derived from the design stage and qualitative judgments based on the engineer past experience; then, the prior model is updated with the results of investigation carried out on the considered structure, such as material testing, determination of action and structural properties. The application of Bayesian statistics arises two different kind of problems: 1. The results of the updating depend on the engineer previous experience; 2. The updating of the prior PDF can be performed only if the structure has been tested, and quantitative data that can be statistically manipulated have been collected; performing tests is always an expensive and time consuming operation; furthermore, if the considered structure is an ancient building, destructive tests could compromise its cultural value and therefore should be avoided. In order to solve those problems, an interesting research path is represented by investigating Artificial Intelligence (AI) techniques that can be useful for the automation of the modeling of variables and for the updating of material parameters without performing destructive tests. Among the others, one that raises particular attention in relation to the object of this study is constituted by Case-Based Reasoning (CBR). In this application, cases will be represented by existing buildings where material tests have already been carried out and an updated PDFs for the material mechanical parameters has been computed through a Bayesian analysis. Then each case will be composed by a qualitative description of the material under assessment and the posterior PDFs that describe its material properties. The problem that will be solved is the definition of PDFs for material parameters involved in the reliability assessment of the considered structure. A CBR system represent a good candi¬date in automating the modelling of variables because: 1. Engineers already draw an estimation of the material properties based on the experience collected during the assessment of similar structures, or based on similar cases collected in literature or in data-bases; 2. Material tests carried out on structure can be easily collected from laboratory database or from literature; 3. The system will provide the user of a reliable probabilistic description of the variables involved in the assessment that will also serve as a tool in support of the engineer’s qualitative judgments. Automated modeling of variables can help in spreading probabilistic reliability assessment of existing buildings in the common engineering practice, and target at the best intervention and further tests on the structure; CBR represents a technique which may help to achieve this.

Keywords: reliability assessment of existing buildings, Bayesian analysis, case-based reasoning, historical structures

Procedia PDF Downloads 317

Authors: Mohammed Makki, Milad Showkatbakhsh, Aiman Tabony

Abstract:

Computational applications of natural evolutionary processes as problem-solving tools have been well established since the mid-20th century. However, their application within architecture and design has only gained ground in recent years, with an increasing number of academics and professionals in the field electing to utilize evolutionary computation to address problems comprised from multiple conflicting objectives with no clear optimal solution. Recent advances in computer science and its consequent constructive influence on the architectural discourse has led to the emergence of multiple algorithmic processes capable of simulating the evolutionary process in nature within an efficient timescale. Many of the developed processes of generating a population of candidate solutions to a design problem through an evolutionary based stochastic search process are often driven through the application of both environmental and architectural parameters. These methods allow for conflicting objectives to be simultaneously, independently, and objectively optimized. This is an essential approach in design problems with a final product that must address the demand of a multitude of individuals with various requirements. However, one of the main challenges encountered through the application of an evolutionary process as a design tool is the ability for the simulation to maintain variation amongst design solutions in the population while simultaneously increasing in fitness. This is most commonly known as the ‘golden rule’ of balancing exploration and exploitation over time; the difficulty of achieving this balance in the simulation is due to the tendency of either variation or optimization being favored as the simulation progresses. In such cases, the generated population of candidate solutions has either optimized very early in the simulation, or has continued to maintain high levels of variation to which an optimal set could not be discerned; thus, providing the user with a solution set that has not evolved efficiently to the objectives outlined in the problem at hand. As such, the experiments presented in this paper seek to achieve the ‘golden rule’ by incorporating a mathematical fitness criterion for the development of an urban tissue comprised from the superblock as its primary architectural element. The mathematical value investigated in the experiments is the standard deviation factor. Traditionally, the standard deviation factor has been used as an analytical value rather than a generative one, conventionally used to measure the distribution of variation within a population by calculating the degree by which the majority of the population deviates from the mean. A higher standard deviation value delineates a higher number of the population is clustered around the mean and thus limited variation within the population, while a lower standard deviation value is due to greater variation within the population and a lack of convergence towards an optimal solution. The results presented will aim to clarify the extent to which the utilization of the standard deviation factor as a fitness criterion can be advantageous to generating fitter individuals in a more efficient timeframe when compared to conventional simulations that only incorporate architectural and environmental parameters.

Keywords: architecture, computation, evolution, standard deviation, urban

Procedia PDF Downloads 111

Authors: Andrew N. Saylor, James R. Peters

Abstract:

Scoliosis is a complex 3D deformity of the thoracic and lumbar spines, clinically diagnosed by measurement of a Cobb angle of 10 degrees or more on a coronal X-ray. The Cobb angle is the angle made by the lines drawn along the proximal and distal endplates of the respective proximal and distal vertebrae comprising the curve. Traditionally, Cobb angles are measured manually using either a marker, straight edge, and protractor or image measurement software. The task of measuring the Cobb angle can also be represented by a function taking the spine geometry rendered using X-ray imaging as input and returning the approximate angle. Although the form of such a function may be unknown, it can be approximated using artificial neural networks (ANNs). The performance of ANNs is affected by many factors, including the choice of activation function and network architecture; however, the effects of these parameters on the accuracy of scoliotic deformity measurements are poorly understood. Therefore, the objective of this study was to systematically investigate the effect of ANN architecture and activation function on Cobb angle measurement from the coronal X-rays of scoliotic subjects. The data set for this study consisted of 609 coronal chest X-rays of scoliotic subjects divided into 481 training images and 128 test images. These data, which included labeled Cobb angle measurements, were obtained from the SpineWeb online database. In order to normalize the input data, each image was resized using bi-linear interpolation to a size of 500 × 187 pixels, and the pixel intensities were scaled to be between 0 and 1. A fully connected (dense) ANN with a fixed cost function (mean squared error), batch size (10), and learning rate (0.01) was developed using Python Version 3.7.3 and TensorFlow 1.13.1. The activation functions (sigmoid, hyperbolic tangent [tanh], or rectified linear units [ReLU]), number of hidden layers (1, 3, 5, or 10), and number of neurons per layer (10, 100, or 1000) were varied systematically to generate a total of 36 network conditions. Stochastic gradient descent with early stopping was used to train each network. Three trials were run per condition, and the final mean squared errors and mean absolute errors were averaged to quantify the network response for each condition. The network that performed the best used ReLU neurons had three hidden layers, and 100 neurons per layer. The average mean squared error of this network was 222.28 ± 30 degrees2, and the average mean absolute error was 11.96 ± 0.64 degrees. It is also notable that while most of the networks performed similarly, the networks using ReLU neurons, 10 hidden layers, and 1000 neurons per layer, and those using Tanh neurons, one hidden layer, and 10 neurons per layer performed markedly worse with average mean squared errors greater than 400 degrees2 and average mean absolute errors greater than 16 degrees. From the results of this study, it can be seen that the choice of ANN architecture and activation function has a clear impact on Cobb angle inference from coronal X-rays of scoliotic subjects.

Keywords: scoliosis, artificial neural networks, cobb angle, medical imaging

Procedia PDF Downloads 102

Authors: Mathuravech Thanaphon, Thephasit Nat

Abstract:

The Electricity Generating Authority of Thailand (EGAT) is focusing on expanding its pumped storage hydropower (PSH) capacity to increase the reliability of the system during peak demand and allow for greater integration of renewables. To achieve this requirement, Thailand will have to double its current renewable electricity production. To address the challenges of balancing supply and demand in the grid with increasing levels of RE penetration, as well as rising peak demand, EGAT has already been studying the potential for additional PSH capacity for several years to enable an increased share of RE and replace existing fossil fuel-fired generation. In addition, the role that pumped-storage hydropower would play in fulfilling multiple grid functions and renewable integration. The proposed sites for new PSH would help increase the reliability of power generation in Thailand. However, most of the electricity generation will come from RE, chiefly wind and photovoltaic, and significant additional Energy Storage capacity will be needed. In this paper, the impact of integrating the PSH system on the adequacy of renewable rich power generating systems to reduce the thermal power generating units is investigated. The variations of system adequacy indices are analyzed for different PSH-renewables capacities and storage levels. Power Development Plan 2018 rev.1 (PDP2018 rev.1), which is modified by integrating a six-new PSH system and RE planning and development aftermath in 2030, is the very challenge. The system adequacy indices through power generation are obtained using Multi-Objective Genetic Algorithm (MOGA) Optimization. MOGA is a probabilistic heuristic and stochastic algorithm that is able to find the global minima, which have the advantage that the fitness function does not necessarily require the gradient. In this sense, the method is more flexible in solving reliability optimization problems for a composite power system. The optimization with hourly time step takes years of planning horizon much larger than the weekly horizon that usually sets the scheduling studies. The objective function is to be optimized to maximize RE energy generation, minimize energy imbalances, and minimize thermal power generation using MATLAB. The PDP2018 rev.1 was set to be simulated based on its planned capacity stepping into 2030 and 2050. Therefore, the four main scenario analyses are conducted as the target of renewables share: 1) Business-As-Usual (BAU), 2) National Targets (30% RE in 2030), 3) Carbon Neutrality Targets (50% RE in 2050), and 5) 100% RE or full-decarbonization. According to the results, the generating system adequacy is significantly affected by both PSH-RE and Thermal units. When a PSH is integrated, it can provide hourly capacity to the power system as well as better allocate renewable energy generation to reduce thermal generations and improve system reliability. These results show that a significant level of reliability improvement can be obtained by PSH, especially in renewable-rich power systems.

Keywords: pumped storage hydropower, renewable energy integration, system adequacy, power development planning, RE100, multi-objective genetic algorithm

Procedia PDF Downloads 32

Authors: Zhenyu Zhang, Hsi-Hsien Wei

Abstract:

Highway network systems play a vital role in disaster response for disaster-damaged areas. Damaged bridges in such network systems can impede disaster response by disrupting transportation of rescue teams or humanitarian supplies. Therefore, emergency inspection and repair of bridges to quickly collect damage information of bridges and recover the functionality of highway networks is of paramount importance to disaster response. A widely used measure of a network’s capability to recover from disasters is resilience. To enhance highway network resilience, plenty of studies have developed various repair scheduling methods for the prioritization of bridge-repair tasks. These methods assume that repair activities are performed after the damage to a highway network is fully understood via inspection, although inspecting all bridges in a regional highway network may take days, leading to the significant delay in repairing bridges. In reality, emergency repair activities can be commenced as soon as the damage data of some bridges that are crucial to emergency response are obtained. Given that emergency bridge inspection and repair (EBIR) activities are executed simultaneously in the response phase, the real-time interactions between these activities can occur – the blockage of highways due to repair activities can affect inspection routes which in turn have an impact on emergency repair scheduling by providing real-time information on bridge damages. However, the impact of such interactions on the optimal emergency inspection routes (EIR) and emergency repair schedules (ERS) has not been discussed in prior studies. To overcome the aforementioned deficiencies, this study develops a routing and scheduling model for EBIR while accounting for real-time inspection-repair interactions to maximize highway network resilience. A stochastic, time-dependent integer program is proposed for the complex and real-time interacting EBIR problem given multiple inspection and repair teams at locations as set post-disaster. A hybrid genetic algorithm that integrates a heuristic approach into a traditional genetic algorithm to accelerate the evolution process is developed. Computational tests are performed using data from the 2008 Wenchuan earthquake, based on a regional highway network in Sichuan, China, consisting of 168 highway bridges on 36 highways connecting 25 cities/towns. The results show that the simultaneous implementation of bridge inspection and repair activities can significantly improve the highway network resilience. Moreover, the deployment of inspection and repair teams should match each other, and the network resilience will not be improved once the unilateral increase in inspection teams or repair teams exceeds a certain level. This study contributes to both knowledge and practice. First, the developed mathematical model makes it possible for capturing the impact of real-time inspection-repair interactions on inspection routing and repair scheduling and efficiently deriving optimal EIR and ERS on a large and complex highway network. Moreover, this study contributes to the organizational dimension of highway network resilience by providing optimal strategies for highway bridge management. With the decision support tool, disaster managers are able to identify the most critical bridges for disaster management and make decisions on proper inspection and repair strategies to improve highway network resilience.

Keywords: disaster management, emergency bridge inspection and repair, highway network, resilience, uncertainty

Procedia PDF Downloads 90

Authors: Kamyar Tolouei, Ehsan Moosavi

Abstract:

In open-pit mines, the long-term production scheduling optimization problem (LTPSOP) is a complicated problem that contains constraints, large datasets, and uncertainties. Uncertainty in the output is caused by several geological, economic, or technical factors. Due to its dimensions and NP-hard nature, it is usually difficult to find an ideal solution to the LTPSOP. The optimal schedule generally restricts the ore, metal, and waste tonnages, average grades, and cash flows of each period. Past decades have witnessed important measurements of long-term production scheduling and optimal algorithms since researchers have become highly cognizant of the issue. In fact, it is not possible to consider LTPSOP as a well-solved problem. Traditional production scheduling methods in open-pit mines apply an estimated orebody model to produce optimal schedules. The smoothing result of some geostatistical estimation procedures causes most of the mine schedules and production predictions to be unrealistic and imperfect. With the expansion of simulation procedures, the risks from grade uncertainty in ore reserves can be evaluated and organized through a set of equally probable orebody realizations. In this paper, to synthesize grade uncertainty into the strategic mine schedule, a stochastic integer programming framework is presented to LTPSOP. The objective function of the model is to maximize the net present value and minimize the risk of deviation from the production targets considering grade uncertainty simultaneously while satisfying all technical constraints and operational requirements. Instead of applying one estimated orebody model as input to optimize the production schedule, a set of equally probable orebody realizations are applied to synthesize grade uncertainty in the strategic mine schedule and to produce a more profitable and risk-based production schedule. A mixture of metaheuristic procedures and mathematical methods paves the way to achieve an appropriate solution. This paper introduced a hybrid model between the augmented Lagrangian relaxation (ALR) method and the metaheuristic algorithm, the Harris Hawks optimization (HHO), to solve the LTPSOP under grade uncertainty conditions. In this study, the HHO is experienced to update Lagrange coefficients. Besides, a machine learning method called Random Forest is applied to estimate gold grade in a mineral deposit. The Monte Carlo method is used as the simulation method with 20 realizations. The results specify that the progressive versions have been considerably developed in comparison with the traditional methods. The outcomes were also compared with the ALR-genetic algorithm and ALR-sub-gradient. To indicate the applicability of the model, a case study on an open-pit gold mining operation is implemented. The framework displays the capability to minimize risk and improvement in the expected net present value and financial profitability for LTPSOP. The framework could control geological risk more effectively than the traditional procedure considering grade uncertainty in the hybrid model framework.

Keywords: grade uncertainty, metaheuristic algorithms, open-pit mine, production scheduling optimization

Procedia PDF Downloads 75

Authors: Rauan Sakenov, Peter Bukovics, Peter Gaszler, Veronika Tokacs-Kollar, Beata Bugyi

Abstract:

FH2 (formin homology-2) domains of several proteins, collectively known as formins, including DAAM, DAAM1 and mDia1, promote G-actin nucleation and elongation. FH2 domains of these formins exist as oligomers. Chain dimerization by ring structure formation serves as a structural basis for actin polymerization function of FH2 domain. Proper single chain configuration and specific interactions between its various regions are necessary for individual chains to form a dimer functional in G-actin nucleation and elongation. FH1 and WH2 domain-containing formins were shown to behave as intrinsically disordered proteins. Thus, the aim of this research was to study structural dynamics of FH2 domain of DAAM. To investigate structural features of FH2 domain of DAAM, molecular dynamics simulation of chain A of FH2 domain of DAAM solvated in water box in 50 mM NaCl was conducted at temperatures from 293.15 to 353.15K, with VMD 1.9.2, NAMD 2.14 and Amber Tools 21 using 2z6e and 1v9d PDB structures of DAAM was obtained on I-TASSER webserver. Calcium and ATP bound G-actin 3hbt PDB structure was used as a reference protein with well-described structural dynamics of denaturation. Topology and parameter information of CHARMM 2012 additive all-atom force fields for proteins, carbohydrate derivatives, water and ions were used in NAMD 2.14 and ff19SB force field for proteins in Amber Tools 21. The systems were energy minimized for the first 1000 steps, equilibrated and produced in NPT ensemble for 1ns using stochastic Langevin dynamics and the particle mesh Ewald method. Our root-mean square deviation (RMSD) analysis of molecular dynamics of chain A of FH2 domains of DAAM revealed similar insignificant changes of total molecular average RMSD values of FH2 domain of these formins at temperatures from 293.15 to 353.15K. In contrast, total molecular average RMSD values of G-actin showed considerable increase at 328K, which corresponds to the denaturation of G-actin molecule at this temperature and its transition from native, ordered, to denatured, disordered, state which is well-described in the literature. RMSD values of lasso and tail regions of chain A of FH2 domain of DAAM exhibited higher than total molecular average RMSD at temperatures from 293.15 to 353.15K. These regions are functional in intra- and interchain interactions and contain highly conserved tryptophan residues of lasso region, highly conserved GNYMN sequence of post region and amino acids of the shell of hydrophobic pocket of the salt bridge between Arg171 and Asp321, which are important for structural stability and ordered state of FH2 domain of DAAM and its functions in FH2 domain dimerization. In conclusion, higher than total molecular average RMSD values of lasso and post regions of chain A of FH2 domain of DAAM may explain disordered state of FH2 domain of DAAM at temperatures from 293.15 to 353.15K. Finally, absence of marked transition, in terms of significant changes in average molecular RMSD values between native and denatured states of FH2 domain of DAAM at temperatures from 293.15 to 353.15K, can make it possible to attribute these formins to the group of intrinsically disordered proteins rather than to the group of intrinsically ordered proteins such as G-actin.

Keywords: FH2 domain, DAAM, formins, molecular modelling, computational biophysics

Procedia PDF Downloads 108

Authors: Hadush Kidane Meresa

Abstract:

The hydrological extremes frequency analysis is the foundation for the hydraulic engineering design, flood protection, drought management and water resources management and planning to utilize the available water resource to meet the desired objectives of different organizations and sectors in a country. This spatial variation of the statistical characteristics of the extreme flood and drought events are key practice for regional flood and drought analysis and mitigation management. For different hydro-climate of the regions, where the data set is short, scarcity, poor quality and insufficient, the regionalization methods are applied to transfer at-site data to a region. This study aims in regional high and low flow frequency analysis for Poland River Basins. Due to high frequent occurring of hydrological extremes in the region and rapid water resources development in this basin have caused serious concerns over the flood and drought magnitude and frequencies of the river in Poland. The magnitude and frequency result of high and low flows in the basin is needed for flood and drought planning, management and protection at present and future. Hydrological homogeneous high and low flow regions are formed by the cluster analysis of site characteristics, using the hierarchical and C- mean clustering and PCA method. Statistical tests for regional homogeneity are utilized, by Discordancy and Heterogeneity measure tests. In compliance with results of the tests, the region river basin has been divided into ten homogeneous regions. In this study, frequency analysis of high and low flows using AM for high flow and 7-day minimum low flow series is conducted using six statistical distributions. The use of L-moment and LL-moment method showed a homogeneous region over entire province with Generalized logistic (GLOG), Generalized extreme value (GEV), Pearson type III (P-III), Generalized Pareto (GPAR), Weibull (WEI) and Power (PR) distributions as the regional drought and flood frequency distributions. The 95% percentile and Flow duration curves of 1, 7, 10, 30 days have been plotted for 10 stations. However, the cluster analysis performed two regions in west and east of the province where L-moment and LL-moment method demonstrated the homogeneity of the regions and GLOG and Pearson Type III (PIII) distributions as regional frequency distributions for each region, respectively. The spatial variation and regional frequency distribution of flood and drought characteristics for 10 best catchment from the whole region was selected and beside the main variable (streamflow: high and low) we used variables which are more related to physiographic and drainage characteristics for identify and delineate homogeneous pools and to derive best regression models for ungauged sites. Those are mean annual rainfall, seasonal flow, average slope, NDVI, aspect, flow length, flow direction, maximum soil moisture, elevation, and drainage order. The regional high-flow or low-flow relationship among one streamflow characteristics with (AM or 7-day mean annual low flows) some basin characteristics is developed using Generalized Linear Mixed Model (GLMM) and Generalized Least Square (GLS) regression model, providing a simple and effective method for estimation of flood and drought of desired return periods for ungauged catchments.

Keywords: flood , drought, frequency, magnitude, regionalization, stochastic, ungauged, Poland

Procedia PDF Downloads 571

Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez

Abstract:

Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.

Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning

Procedia PDF Downloads 320

Authors: Vijaya Dixit Aasheesh Dixit

Abstract:

Shipbuilding industry operates in Engineer Procure Construct (EPC) context. Product mix of a shipyard comprises of various types of ships like bulk carriers, tankers, barges, coast guard vessels, sub-marines etc. Each order is unique based on the type of ship and customized requirements, which are engineered into the product right from design stage. Thus, to execute every new project, a shipyard needs to upgrade its production expertise. As a result, over the long run, holistic learning occurs across different types of projects which contributes to the knowledge base of the shipyard. Simultaneously, in the short term, during execution of a project comprising of multiple sister ships, repetition of similar tasks leads to learning at activity level. This research aims to capture above learnings of a shipyard and incorporate learning curve effect in project scheduling and materials procurement to improve project performance. Extant literature provides support for the existence of such learnings in an organization. In shipbuilding, there are sequences of similar activities which are expected to exhibit learning curve behavior. For example, the nearly identical structural sub-blocks which are successively fabricated, erected, and outfitted with piping and electrical systems. Learning curve representation can model not only a decrease in mean completion time of an activity, but also a decrease in uncertainty of activity duration. Sister ships have similar material requirements. The same supplier base supplies materials for all the sister ships within a project. On one hand, this provides an opportunity to reduce transportation cost by batching the order quantities of multiple ships. On the other hand, it increases the inventory holding cost at shipyard and the risk of obsolescence. Further, due to learning curve effect the production scheduled of each consequent ship gets compressed. Thus, the material requirement schedule of every next ship differs from its previous ship. As more and more ships get constructed, compressed production schedules increase the possibility of batching the orders of sister ships. This work aims at integrating materials management with project scheduling of long duration projects for manufacturing of multiple sister ships. It incorporates the learning curve effect on progressively compressing material requirement schedules and addresses the above trade-off of transportation cost and inventory holding and shortage costs while satisfying budget constraints of various stages of the project. The activity durations and lead time of items are not crisp and are available in the form of probabilistic distribution. A Stochastic Mixed Integer Programming (SMIP) model is formulated which is solved using evolutionary algorithm. Its output provides ordering dates of items and degree of order batching for all types of items. Sensitivity analysis determines the threshold number of sister ships required in a project to leverage the advantage of learning curve effect in materials management decisions. This analysis will help materials managers to gain insights about the scenarios: when and to what degree is it beneficial to treat a multiple ship project as an integrated one by batching the order quantities and when and to what degree to practice distinctive procurement for individual ship.

Keywords: learning curve, materials management, shipbuilding, sister ships

Procedia PDF Downloads 475

Authors: Parag Katira, Frederika Rentzeperis, Zuzanna Nowicka, Giada Fiandaca, Thomas Veith, Jack Farinhas, Noemi Andor

Abstract:

Resource limitations shape the outcome of competitions between genetically heterogeneous pre-malignant cells. One example of such heterogeneity is in the ploidy (DNA content) of pre-malignant cells. A whole-genome duplication (WGD) transforms a diploid cell into a tetraploid one and has been detected in 28-56% of human cancers. If a tetraploid subclone expands, it consistently does so early in tumor evolution, when cell density is still low, and competition for nutrients is comparatively weak – an observation confirmed for several tumor types. WGD+ cells need more resources to synthesize increasing amounts of DNA, RNA, and proteins. To quantify resource limitations and how they relate to ploidy, we performed a PAN cancer analysis of WGD, PET/CT, and MRI scans. Segmentation of >20 different organs from >900 PET/CT scans were performed with MOOSE. We observed a strong correlation between organ-wide population-average estimates of Oxygen and the average ploidy of cancers growing in the respective organ (Pearson R = 0.66; P= 0.001). In-vitro experiments using near-diploid and near-tetraploid lineages derived from a breast cancer cell line supported the hypothesis that DNA content influences Glucose- and Oxygen-dependent proliferation-, death- and migration rates. To model how subpopulations with variable DNA content compete in the resource-limited environment of the human brain, we developed a stochastic state-space model of the brain (S3MB). The model discretizes the brain into voxels, whereby the state of each voxel is defined by 8+ variables that are updated over time: stiffness, Oxygen, phosphate, glucose, vasculature, dead cells, migrating cells and proliferating cells of various DNA content, and treat conditions such as radiotherapy and chemotherapy. Well-established Fokker-Planck partial differential equations govern the distribution of resources and cells across voxels. We applied S3MB on sequencing and imaging data obtained from a primary GBM patient. We performed whole genome sequencing (WGS) of four surgical specimens collected during the 1ˢᵗ and 2ⁿᵈ surgeries of the GBM and used HATCHET to quantify its clonal composition and how it changes between the two surgeries. HATCHET identified two aneuploid subpopulations of ploidy 1.98 and 2.29, respectively. The low-ploidy clone was dominant at the time of the first surgery and became even more dominant upon recurrence. MRI images were available before and after each surgery and registered to MNI space. The S3MB domain was initiated from 4mm³ voxels of the MNI space. T1 post and T2 flair scan acquired after the 1ˢᵗ surgery informed tumor cell densities per voxel. Magnetic Resonance Elastography scans and PET/CT scans informed stiffness and Glucose access per voxel. We performed a parameter search to recapitulate the GBM’s tumor cell density and ploidy composition before the 2ⁿᵈ surgery. Results suggest that the high-ploidy subpopulation had a higher Glucose-dependent proliferation rate (0.70 vs. 0.49), but a lower Glucose-dependent death rate (0.47 vs. 1.42). These differences resulted in spatial differences in the distribution of the two subpopulations. Our results contribute to a better understanding of how genomics and microenvironments interact to shape cell fate decisions and could help pave the way to therapeutic strategies that mimic prognostically favorable environments.

Keywords: tumor evolution, intra-tumor heterogeneity, whole-genome doubling, mathematical modeling

Procedia PDF Downloads 48

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 169