Search results for: non-normal data

Authors: Thanh Noi Phan, Martin Kappas, Jan Degener

Abstract:

The currently launched Sentinel 2 (S2) satellite (June, 2015) bring a great potential and opportunities for land use/cover map applications, due to its fine spatial resolution multispectral as well as high temporal resolutions. So far, there are handful studies using S2 real data for land cover classification. Especially in northern Vietnam, to our best knowledge, there exist no studies using S2 data for land cover map application. The aim of this study is to provide the preliminary result of land cover classification using Sentinel -2 data with a rising state – of – art classifier, Random Forest. A case study with heterogeneous land use/cover in the eastern of Hanoi Capital – Vietnam was chosen for this study. All 10 spectral bands of 10 and 20 m pixel size of S2 images were used, the 10 m bands were resampled to 20 m. Among several classified algorithms, supervised Random Forest classifier (RF) was applied because it was reported as one of the most accuracy methods of satellite image classification. The results showed that the red-edge and shortwave infrared (SWIR) bands play an important role in land cover classified results. A very high overall accuracy above 90% of classification results was achieved.

Keywords: classify algorithm, classification, land cover, random forest, sentinel 2, Vietnam

Procedia PDF Downloads 359

Authors: Arman S. Kussainov, Altynbek K. Beisekov

Abstract:

This work focuses on building an efficient universal procedure to construct a single density of states from the multiple pieces of data provided by the parallel implementation of the Wang Landau Monte Carlo based algorithm. The Ising and Pott models were used as the examples of the two-dimensional spin lattices to construct their densities of states. Sampled energy space was distributed between the individual walkers with certain overlaps. This was made to include the latest development of the algorithm as the density of states replica exchange technique. Several factors of immediate importance for the seamless stitching process have being considered. These include but not limited to the speed and universality of the initial parallel algorithm implementation as well as the data post-processing to produce the expected smooth density of states.

Keywords: density of states, Monte Carlo, parallel algorithm, Wang Landau algorithm

Procedia PDF Downloads 384

Authors: Jinan Fiaidhi, Sabah Mohammed

Abstract:

Diagnosing cataract severity is an important factor in deciding to undertake surgery. It is usually conducted by an ophthalmologist or through taking a variety of fundus photography that needs to be examined by the ophthalmologist. This paper carries out an investigation using a Siamese neural net that can be trained with small anchor samples to score cataract severity. The model used in this paper is based on a triplet loss function that takes the ophthalmologist best experience in rating positive and negative anchors to a specific cataract scaling system. This approach that takes the heuristics of the ophthalmologist is generally called the thick data approach, which is a kind of machine learning approach that learn from a few shots. Clinical Relevance: The lens of the eye is mostly made up of water and proteins. A cataract occurs when these proteins at the eye lens start to clump together and block lights causing impair vision. This research aims at employing thick data machine learning techniques to rate the severity of the cataract using Siamese neural network.

Keywords: thick data analytics, siamese neural network, triplet-loss model, few shot learning

Procedia PDF Downloads 92

Authors: Diana Katherine Gonzalez Galindo, David Rolando Suarez Mora

Abstract:

With this study, we used data mining as a new alternative of the solution to evaluate the comments of the customers in order to find a pattern that helps us to determine some behaviors to reduce the deactivation of the partners of the LEVEL app. In one of the greatest business created in the last times, the partners are being affected due to an internal process that compensates the customer for a bad experience, but these comments could be false towards the driver, that’s why we made an investigation to collect information to restructure this process, many partners have been disassociated due to this internal process and many of them refuse the comments given by the customer. The main methodology used in this case study is the observation, we recollect information in real time what gave us the opportunity to see the most common issues to get the most accurate solution. With this new process helped by data mining, we could get a prediction based on the behaviors of the customer and some basic data recollected such as the age, the gender, and others; this could help us in future to improve another process. This investigation gives more opportunities to the partner to keep his account active even if the customer writes a message through the app. The term is trying to avoid a recession of drivers in the future offering improving in the processes, at the same time we are in search of stablishing a strategy which benefits both the app’s managers and the associated driver.

Keywords: agent, driver, deactivation, rider

Procedia PDF Downloads 261

Authors: El Asnaoui Khalid, Chawki Youness, Aksasse Brahim, Ouanan Mohammed

Abstract:

In these recent decades, the important and fast growth in the development and demand of multimedia products is contributing to an insufficient in the bandwidth of device and network storage memory. Consequently, the theory of data compression becomes more significant for reducing the data redundancy in order to save more transfer and storage of data. In this context, this paper addresses the problem of the lossless and the near-lossless compression of images. This proposed method is based on Block SVD Power Method that overcomes the disadvantages of Matlab's SVD function. The experimental results show that the proposed algorithm has a better compression performance compared with the existing compression algorithms that use the Matlab's SVD function. In addition, the proposed approach is simple and can provide different degrees of error resilience, which gives, in a short execution time, a better image compression.

Keywords: image compression, SVD, block SVD power method, lossless compression, near lossless

Procedia PDF Downloads 364

Authors: Jingting Luo, Yong Wang, Ying Wang

Abstract:

Pedestrian detection in image or video data is a very important and challenging task in security surveillance. The difficulty of this task is to locate and detect pedestrians of different scales in complex scenes accurately. To solve these problems, a deep neural network (RT-YOLOv3) is proposed to realize real-time pedestrian detection at different scales in security monitoring. RT-YOLOv3 improves the traditional YOLOv3 algorithm. Firstly, the deep residual network is added to extract vehicle features. Then six convolutional neural networks with different scales are designed and fused with the corresponding scale feature maps in the residual network to form the final feature pyramid to perform pedestrian detection tasks. This method can better characterize pedestrians. In order to further improve the accuracy and generalization ability of the model, a hybrid pedestrian data set training method is used to extract pedestrian data from the VOC data set and train with the INRIA pedestrian data set. Experiments show that the proposed RT-YOLOv3 method achieves 93.57% accuracy of mAP (mean average precision) and 46.52f/s (number of frames per second). In terms of accuracy, RT-YOLOv3 performs better than Fast R-CNN, Faster R-CNN, YOLO, SSD, YOLOv2, and YOLOv3. This method reduces the missed detection rate and false detection rate, improves the positioning accuracy, and meets the requirements of real-time detection of pedestrian objects.

Keywords: pedestrian detection, feature detection, convolutional neural network, real-time detection, YOLOv3

Procedia PDF Downloads 121

Authors: R. B. Adegbola, K. F. Oyedele, L. Adeoti

Abstract:

We present a method that utilizes Multi-channel Analysis of Surface Waves, which was used to measure shear wave velocities with a view to establishing the probable causes of road failure, subsidence and weakening of structures in some Local Government Area, Lagos, Nigeria. Multi channel Analysis of Surface waves (MASW) data were acquired using 24-channel seismograph. The acquired data were processed and transformed into two-dimensional (2-D) structure reflective of depth and surface wave velocity distribution within a depth of 0–15m beneath the surface using SURFSEIS software. The shear wave velocity data were compared with other geophysical/borehole data that were acquired along the same profile. The comparison and correlation illustrates the accuracy and consistency of MASW derived-shear wave velocity profiles. Rigidity modulus and N-value were also generated. The study showed that the low velocity/very low velocity are reflective of organic clay/peat materials and thus likely responsible for the failed, subsidence/weakening of structures within the study areas.

Keywords: seismograph, road failure, rigidity modulus, N-value, subsidence

Procedia PDF Downloads 343

Authors: Soumia Merat, Lynda Djerbal, Ramdane Bahar, Mohammed Amin Benbouras

Abstract:

Along with shear wave, many soil parameters are associated with the standard penetration test (SPT) as a dynamic in situ experiment. Both SPT-N data and geophysical data do not often exist in the same area. Statistical analysis of correlation between these parameters is an alternate method to estimate Vₛ conveniently and without additional investigations or data acquisition. Shear wave velocity is a basic engineering tool required to define dynamic properties of soils. In many instances, engineers opt for empirical correlations between shear wave velocity (Vₛ) and reliable static field test data like standard penetration test (SPT) N value, CPT (Cone Penetration Test) values, etc., to estimate shear wave velocity or dynamic soil parameters. The relation between Vs and SPT- N values of Algiers area is predicted using the collected data, and it is also compared with the previously suggested formulas of Vₛ determination by measuring Root Mean Square Error (RMSE) of each model. Algiers area is situated in high seismic zone (Zone III [RPA 2003: réglement parasismique algerien]), therefore the study is important for this region. The principal aim of this paper is to compare the field measurements of Down-hole test and the empirical models to show which one of these proposed formulas are applicable to predict and deduce shear wave velocity values.

Keywords: empirical models, RMSE, shear wave velocity, standard penetration test

Procedia PDF Downloads 319

Authors: Che-Wei Lee, Bay-Erl Lai

Abstract:

A new steganographic method via the use of numeric data on public websites with self-authentication capability is proposed. The proposed technique transforms a secret message into partial shares by Shamir’s (k, n)-threshold secret sharing scheme with n = k + 1. The generated k+1 partial shares then are embedded into the selected numeric items in a website as if they are part of the website’s numeric content. Afterward, a receiver links to the website and extracts every k shares among the k+1 ones from the stego-numeric-content to compute k+1 copies of the secret, and the phenomenon of value consistency of the computed k+1 copies is taken as an evidence to determine whether the extracted message is authentic or not, attaining the goal of self-authentication of the extracted secret message. Experimental results and discussions are provided to show the feasibility and effectiveness of the proposed method.

Keywords: steganography, data hiding, secret authentication, secret sharing

Procedia PDF Downloads 224

Authors: T. Gangadhararao, K. Krishna Kishore

Abstract:

Motion Estimation (ME) plays a critical role in a video coder, testing such a module is of priority concern. While focusing on the testing of ME in a video coding system, this work presents an error detection and data recovery (EDDR) design, based on the residue-and-quotient (RQ) code, to embed into ME for video coding testing applications. An error in processing Elements (PEs), i.e. key components of a ME, can be detected and recovered effectively by using the proposed EDDR design. The proposed EDDR design for ME testing can detect errors and recover data with an acceptable area overhead and timing penalty.

Keywords: area overhead, data recovery, error detection, motion estimation, reliability, residue-and-quotient (RQ) code

Procedia PDF Downloads 411

Authors: Omid Khodabakhshi, Amir Rozdel

Abstract:

The subject of cloud computing security research has allocated a number of challenges and competitions because the data center is comprised of complex private information and are always faced various risks of information disclosure by hacker attacks or internal enemies. Accordingly, the security of virtual machines in the cloud computing infrastructure layer is very important. So far, there are many software solutions to develop security in virtual machines. But using software alone is not enough to solve security problems. The purpose of this article is to examine the challenges and security requirements for accessing and storing data in an insecure cloud environment. In other words, in this article, a structure is proposed for the implementation of highly isolated security-sensitive codes using secure computing hardware in virtual environments. It also allows remote code validation with inputs and outputs. We provide these security features even in situations where the BIOS, the operating system, and even the super-supervisor are infected. To achieve these goals, we will use the hardware support provided by the new Intel and AMD processors, as well as the TPM security chip. In conclusion, the use of these technologies ultimately creates a root of dynamic trust and reduces TCB to security-sensitive codes.

Keywords: code, cloud computing, security, virtual machines

Procedia PDF Downloads 174

Authors: Rojin Bana Derakhshan, Abbas Toloie

Abstract:

For the purpose of optimizing and developing energy efficiency in building, it is required to recognize key elements of success in optimization of energy consumption before performing any actions. Surveying Principal Components is one of the most valuable result of Linear Algebra because the simple and non-parametric methods are become confusing. So that energy management system implemented according to energy management system international standard ISO50001:2011 and all energy parameters in building to be measured through performing energy auditing. In this essay by simulating used of data mining, the key impressive elements on energy saving in buildings to be determined. This approach is based on data mining statistical techniques using feature selection method and fuzzy logic and convert data from massive to compressed type and used to increase the selected feature. On the other side, influence portion and amount of each energy consumption elements in energy dissipation in percent are recognized as separated norm while using obtained results from energy auditing and after measurement of all energy consuming parameters and identified variables. Accordingly, energy saving solution divided into 3 categories, low, medium and high expense solutions.

Keywords: energy saving, key elements of success, optimization of energy consumption, data mining

Procedia PDF Downloads 447

Authors: Kwaku Damoah

Abstract:

This study presents a comprehensive data-driven analysis to understand the evolution of adverse events (AEs) in pharmacovigilance. Utilizing data from the FDA Adverse Event Reporting System (FAERS), we employed three analytical methods: rank-based, frequency-based, and percentage change analyses. These methods assessed temporal trends and patterns in AE reporting, focusing on various drug-active ingredients and patient demographics. Our findings reveal significant trends in AE occurrences, with both increasing and decreasing patterns from 2000 to 2023. This research highlights the importance of continuous monitoring and advanced analysis in pharmacovigilance, offering valuable insights for healthcare professionals and policymakers to enhance drug safety.

Keywords: event analysis, FDA adverse event reporting system, pharmacovigilance, temporal trend analysis

Procedia PDF Downloads 33

Authors: Salima Kouici, Abdelkader Khelladi

Abstract:

In this work, we begin with the presentation of the Tθ family of usual similarity measures concerning multidimensional binary data. Subsequently, some properties of these measures are proposed. Finally, the impact of the use of different inter-elements measures on the results of the Agglomerative Hierarchical Clustering Methods is studied.

Keywords: binary data, similarity measure, Tθ measures, agglomerative hierarchical clustering

Procedia PDF Downloads 464

Authors: Numair Ahmed Siddiqui, Abdul Hadi bin Abd Rahman, Chow Weng Sum, Wan Ismail Wan Yousif, Asif Zameer, Joel Ben-Awal

Abstract:

Advances in data capturing from outcrop studies have made possible the acquisition of high-resolution digital data, offering improved and economical reservoir modelling methods. Terrestrial laser scanning utilizing LiDAR (Light detection and ranging) provides a new method to build outcrop based reservoir models, which provide a crucial piece of information to understand heterogeneities in sandstone facies with high-resolution images and data set. This study presents the detailed application of outcrop based sandstone facies connectivity model by acquiring information gathered from traditional fieldwork and processing detailed digital point-cloud data from LiDAR to develop an intermediate small-scale reservoir sandstone facies model of the Miocene Sandakan Formation, Sabah, East Malaysia. The software RiScan pro (v1.8.0) was used in digital data collection and post-processing with an accuracy of 0.01 m and point acquisition rate of up to 10,000 points per second. We provide an accurate and descriptive workflow to triangulate point-clouds of different sets of sandstone facies with well-marked top and bottom boundaries in conjunction with field sedimentology. This will provide highly accurate qualitative sandstone facies connectivity model which is a challenge to obtain from subsurface datasets (i.e., seismic and well data). Finally, by applying this workflow, we can build an outcrop based static connectivity model, which can be an analogue to subsurface reservoir studies.

Keywords: LiDAR, outcrop, high resolution, sandstone faceis, connectivity model

Procedia PDF Downloads 202

Authors: Sumiko Anno, Keiji Imaoka, Takeo Tadono, Tamotsu Igarashi, Subramaniam Sivaganesh, Selvam Kannathasan, Vaithehi Kumaran, Sinnathamby Noble Surendran

Abstract:

Dengue outbreaks are affected by biological, ecological, socio-economic and demographic factors that vary over time and space. These factors have been examined separately and still require systematic clarification. The present study aimed to investigate the spatial-temporal clustering relationships between these factors and dengue outbreaks in the northern region of Sri Lanka. Remote sensing (RS) data gathered from a plurality of satellites were used to develop an index comprising rainfall, humidity and temperature data. RS data gathered by ALOS/AVNIR-2 were used to detect urbanization, and a digital land cover map was used to extract land cover information. Other data on relevant factors and dengue outbreaks were collected through institutions and extant databases. The analyzed RS data and databases were integrated into geographic information systems, enabling temporal analysis, spatial statistical analysis and space-time clustering analysis. Our present results showed that increases in the number of the combination of ecological factor and socio-economic and demographic factors with above the average or the presence contribute to significantly high rates of space-time dengue clusters.

Keywords: ALOS/AVNIR-2, dengue, space-time clustering analysis, Sri Lanka

Procedia PDF Downloads 461

Authors: Fu Jinyu, Lin Jinguan

Abstract:

This paper introduces a novel approach that unifies two types of models: one is the continuous-time jump-diffusion used to model high-frequency data, and the other is discrete-time GQARCH employed to model low-frequency financial data by embedding the discrete GQARCH structure with jumps in the instantaneous volatility process. This model is named “GQARCH-It\^{o} -Jumps mode.” We adopt the realized range-based threshold estimation for high-frequency financial data rather than the realized return-based volatility estimators, which entail the loss of intra-day information of the price movement. Meanwhile, a quasi-likelihood function for the low-frequency GQARCH structure with jumps is developed for the parametric estimate. The asymptotic theories are mainly established for the proposed estimators in the case of finite activity jumps. Moreover, simulation studies are implemented to check the finite sample performance of the proposed methodology. Specifically, it is demonstrated that how our proposed approaches can be practically used on some financial data.

Keywords: It\^{o} process, GQARCH, leverage effects, threshold, realized range-based volatility estimator, quasi-maximum likelihood estimate

Procedia PDF Downloads 138

Authors: Azadeh Bashiri

Abstract:

Introduction: In order to better designing of electronic health record system in Iran, integration of health information systems based on a common language must be done to interpret and exchange this information with this system is required. Background: This study, provides a conceptual model of radiology reporting system using unified modeling language. The proposed model can solve the problem of integration this information system with electronic health record system. By using this model and design its service based, easily connect to electronic health record in Iran and facilitate transfer radiology report data. Methods: This is a cross-sectional study that was conducted in 2013. The student community was 22 experts that working at the Imaging Center in Imam Khomeini Hospital in Tehran and the sample was accorded with the community. Research tool was a questionnaire that prepared by the researcher to determine the information requirements. Content validity and test-retest method was used to measure validity and reliability of questioner respectively. Data analyzed with average index, using SPSS. Also, Visual Paradigm software was used to design a conceptual model. Result: Based on the requirements assessment of experts and related texts, administrative, demographic and clinical data and radiological examination results and if the anesthesia procedure performed, anesthesia data suggested as minimum data set for radiology report and based it class diagram designed. Also by identifying radiology reporting system process, use case was drawn. Conclusion: According to the application of radiology reports in electronic health record system for diagnosing and managing of clinical problem of the patient, provide the conceptual Model for radiology reporting system; in order to systematically design it, the problem of data sharing between these systems and electronic health records system would eliminate.

Keywords: structured radiology report, information needs, minimum data set, electronic health record system in Iran

Procedia PDF Downloads 235

Authors: Praniil Nagaraj

Abstract:

This paper proposes a method to collect homeless data using crowdsourcing and presents an approach to analyze the data, demonstrating its potential to strengthen existing and future policies aimed at promoting socio-economic equilibrium. The 2022 Annual Homeless Assessment Report (AHAR) to Congress highlighted alarming statistics, emphasizing the need for effective decision-making and budget allocation within local planning bodies known as Continuums of Care (CoC). This paper's contributions can be categorized into three main areas. Firstly, a unique method for collecting homeless data is introduced, utilizing a user-friendly smartphone app (currently available for Android). The app enables the general public to quickly record information about homeless individuals, including the number of people and details about their living conditions. The collected data, including date, time, and location, is anonymized and securely transmitted to the cloud. It is anticipated that an increasing number of users motivated to contribute to society will adopt the app, thus expanding the data collection efforts. Duplicate data is addressed through simple classification methods, and historical data is utilized to fill in missing information. The second contribution of this paper is the description of data analysis techniques applied to the collected data. By combining this new data with existing information, statistical regression analysis is employed to gain insights into various aspects, such as distinguishing between unsheltered and sheltered homeless populations, as well as examining their correlation with factors like unemployment rates, housing affordability, and labor demand. Initial data is collected in San Francisco, while pre-existing information is drawn from three cities: San Francisco, New York City, and Washington D.C., facilitating the conduction of simulations. The third contribution focuses on demonstrating the practical implications of the data processing results. The challenges faced by key stakeholders, including charitable organizations and local city governments, are taken into consideration. Two case studies are presented as examples. The first case study explores improving the efficiency of food and necessities distribution, as well as medical assistance, driven by charitable organizations. The second case study examines the correlation between micro-geographic budget expenditure by local city governments and homeless information to justify budget allocation and expenditures. The ultimate objective of this endeavor is to enable the continuous enhancement of the quality of life for the underprivileged. It is hoped that through increased crowdsourcing of data from the public, the Generosity Curve and the Need Curve will intersect, leading to a better world for all.

Keywords: crowdsourcing, homelessness, socio-economic policies, statistical regression

Procedia PDF Downloads 69

Authors: Jisun Lee, Jay Hyoun Kwon

Abstract:

As an alternative way to compensate the INS (inertial navigation system) error in non-GNSS (Global Navigation Satellite System) environment, geophysical database referenced navigation is being studied. In this study, both gravity gradient and terrain data were combined to complement the weakness of sole geophysical data as well as to improve the stability of the positioning. The main process to compensate the INS error using geophysical database was constructed on the basis of the EKF (Extended Kalman Filter). In detail, two type of combination method, centralized and decentralized filter, were applied to check the pros and cons of its algorithm and to find more robust results. The performance of each navigation algorithm was evaluated based on the simulation by supposing that the aircraft flies with precise geophysical DB and sensors above nine different trajectories. Especially, the results were compared to the ones from sole geophysical database referenced navigation to check the improvement due to a combination of the heterogeneous geophysical database. It was found that the overall navigation performance was improved, but not all trajectories generated better navigation result by the combination of gravity gradient with terrain data. Also, it was found that the centralized filter generally showed more stable results. It is because that the way to allocate the weight for the decentralized filter could not be optimized due to the local inconsistency of geophysical data. In the future, switching of geophysical data or combining different navigation algorithm are necessary to obtain more robust navigation results.

Keywords: Extended Kalman Filter, geophysical database referenced navigation, gravity gradient, terrain

Procedia PDF Downloads 327

Authors: Khan R. Rahaman, Quazi K. Hassan

Abstract:

Global changes in climate, environment, economies, populations, governments, institutions, and cultures converge in localities. Changes at a local scale, in turn, contribute to global changes as well as being affected by them. Our hypothesis is built on a consideration that temperature does vary at local level (i.e., termed as local warming) in comparison to the predicted models at the regional and/or global scale. To date, the bulk of the research relating local places to global climate change has been top-down, from the global toward the local, concentrating on methods of impact analysis that use as a starting point climate change scenarios derived from global models, even though these have little regional or local specificity. Thus, our focus is to understand such trends over the southern Alberta, which will enable decision makers, scientists, researcher community, and local people to adapt their policies based on local level temperature variations and to act accordingly. Specific objectives in this study are: (i) to understand the local warming (temperature in particular) trend in context of temperature normal during the period 1961-2010 at point locations using meteorological data; (ii) to validate the data by using specific yearly data, and (iii) to delineate the spatial extent of the local warming trends and understanding influential factors to adopt situation by local governments. Existing data has brought the evidence of such changes and future research emphasis will be given to validate this hypothesis based on remotely sensed data (i.e. MODIS product by NASA).

Keywords: local warming, climate change, urban area, Alberta, Canada

Procedia PDF Downloads 315

Authors: Stephanie Boue, Nicolas Sierro, Julia Hoeng, Manuel C. Peitsch

Abstract:

Systems biology relies on large numbers of data points and sophisticated methods to extract biologically meaningful signal and mechanistic understanding. For example, analyses of transcriptomics and proteomics data enable to gain insights into the molecular differences in tissues exposed to diverse stimuli or test items. Whereas the interpretation of endpoints specifically measuring a mechanism is relatively straightforward, the interpretation of big data is more complex and would benefit from comparing results obtained with diverse analysis methods. The sbv IMPROVER project was created to implement solutions to verify systems biology data, methods, and conclusions. Computational challenges leveraging the wisdom of the crowd allow benchmarking methods for specific tasks, such as signature extraction and/or samples classification. Four challenges have already been successfully conducted and confirmed that the aggregation of predictions often leads to better results than individual predictions and that methods perform best in specific contexts. Whenever the scientific question of interest does not have a gold standard, but may greatly benefit from the scientific community to come together and discuss their approaches and results, datathons are set up. The inaugural sbv IMPROVER datathon was held in Singapore on 23-24 September 2016. It allowed bioinformaticians and data scientists to consolidate their ideas and work on the most promising methods as teams, after having initially reflected on the problem on their own. The outcome is a set of visualization and analysis methods that will be shared with the scientific community via the Garuda platform, an open connectivity platform that provides a framework to navigate through different applications, databases and services in biology and medicine. We will present the results we obtained when analyzing data with our network-based method, and introduce a datathon that will take place in Japan to encourage the analysis of the same datasets with other methods to allow for the consolidation of conclusions.

Keywords: big data interpretation, datathon, systems toxicology, verification

Procedia PDF Downloads 265

Authors: Fares Hedayatit, Arnauld Joly, Panagiotis Papadimitriou

Abstract:

Many machine learning tasks such as text annotation usually require training over very big datasets, e.g., millions of web documents, that can be represented in a sparse input space. State-of the-art tree-based ensemble algorithms cannot scale to such datasets, since they include operations whose running time is a function of the input space size rather than a function of the non-zero input elements. In this paper, we propose an efficient splitting algorithm to leverage input sparsity within decision tree methods. Our algorithm improves training time over sparse datasets by more than two orders of magnitude and it has been incorporated in the current version of scikit-learn.org, the most popular open source Python machine learning library.

Keywords: big data, sparsely representable data, tree-based models, scalable learning

Procedia PDF Downloads 244

Authors: Juan F. Muñoz-Rosas, Rosa M. García-Fernández, Encarnación Álvarez-Verdejo, Pablo J. Moya-Fernández

Abstract:

Poverty measurement is a very important topic in many studies in social sciences. One of the most important indicators when measuring poverty is the low income proportion. This indicator gives the proportion of people of a population classified as poor. This indicator is generally unknown, and for this reason, it is estimated by using survey data, which are obtained by official surveys carried out by many statistical agencies such as Eurostat. The main feature of the mentioned survey data is the fact that they contain several variables. The variable used to estimate the low income proportion is called as the variable of interest. The survey data may contain several additional variables, also named as the auxiliary variables, related to the variable of interest, and if this is the situation, they could be used to improve the estimation of the low income proportion. In this paper, we use Monte Carlo simulation studies to analyze numerically the performance of estimators based on several auxiliary variables. In this simulation study, we considered real data sets obtained from the 2011 European Union Survey on Income and Living Condition. Results derived from this study indicate that the estimators based on auxiliary variables are more accurate than the naive estimator.

Keywords: inclusion probability, poverty, poverty line, survey sampling

Procedia PDF Downloads 433

Authors: Jonas Hamann, Siavash Saki, Tobias Hagen

Abstract:

Discretization of urban areas is a crucial aspect in many spatial analyses. The process of discretization of space into subspaces without overlaps and gaps is called tessellation. It helps understanding spatial space and provides a framework for analyzing geospatial data. Tessellation methods can be divided into two groups: regular tessellations and irregular tessellations. While regular tessellation methods, like squares-grids or hexagons-grids, are suitable for addressing pure geometry problems, they cannot take the unique characteristics of different subareas into account. However, irregular tessellation methods allow the border between the subareas to be defined more realistically based on urban features like a road network or Points of Interest (POI). Even though Python is one of the most used programming languages when it comes to spatial analysis, there is currently no library that combines different tessellation methods to enable users and researchers to compare different techniques. To close this gap, we are proposing TessPy, an open-source Python package, which combines all above-mentioned tessellation methods and makes them easily accessible to everyone. The core functions of TessPy represent the five different tessellation methods: squares, hexagons, adaptive squares, Voronoi polygons, and city blocks. By using regular methods, users can set the resolution of the tessellation which defines the finesse of the discretization and the desired number of tiles. Irregular tessellation methods allow users to define which spatial data to consider (e.g., amenity, building, office) and how fine the tessellation should be. The spatial data used is open-source and provided by OpenStreetMap. This data can be easily extracted and used for further analyses. Besides the methodology of the different techniques, the state-of-the-art, including examples and future work, will be discussed. All dependencies can be installed using conda or pip; however, the former is more recommended.

Keywords: geospatial data science, geospatial data analysis, tessellations, urban studies

Procedia PDF Downloads 109

Authors: Dmitry V. Fomichev, Vladimir V. Solonin

Abstract:

This paper presents the findings from a numerical simulation of the flow in 37-rod fuel assembly models spaced by a double-wire trapezoidal wrapping as applied to the BREST-OD-300 experimental nuclear reactor. Data on a high static pressure distribution within the models, and equations for determining the fuel bundle flow friction factors have been obtained. Recommendations are provided on using the closing turbulence models available in the ANSYS Fluent. A comparative analysis has been performed against the existing empirical equations for determining the flow friction factors. The calculated and experimental data fit has been shown. An analysis into the experimental data and results of the numerical simulation of the BREST-OD-300 fuel rod assembly hydrodynamic performance are presented.

Keywords: BREST-OD-300, ware-spaces, fuel assembly, computation fluid dynamics

Procedia PDF Downloads 362

Authors: Abdel-Aziz M. Mohamed, Nermeen Coutry

Abstract:

Lead time is an important measure of supply chain performance. It impacts both customer satisfactions as well as the total cost of inventory. This paper presents the result of a study on the analysis of the customer order lead-time for a multinational company. In the study, the lead time was divided into three stages: order entry, order fulfillment, and order delivery. A sample of size 2,425 order lines from the company records were considered for this study. The sample data includes information regarding customer orders from the time of order entry until order delivery. Data regarding the lead time of each sage for different orders were also provided. Summary statistics on lead time data reveals that about 30% of the orders were delivered after the scheduled due date. The result of the multiple linear regression analysis technique revealed that component type, logistics parameter, order size and the customer type have significant impact on lead time. Data analysis on the stages of lead time indicates that stage 2 consumes over 50% of the lead time. Pareto analysis was made to study the reasons for the customer order delay in each of the 3 stages. Recommendation was given to resolve the problem.

Keywords: lead time reduction, customer satisfaction, service quality, statistical analysis

Procedia PDF Downloads 707

Authors: Ali Alshumrani, Nathan Clarke, Bogdan Ghite, Stavros Shiaeles

Abstract:

Digital forensics has become an essential tool in the investigation of cyber and computer-assisted crime. Arguably, given the prevalence of technology and the subsequent digital footprints that exist, it could have a significant role across almost all crimes. However, the variety of technology platforms (such as computers, mobiles, Closed-Circuit Television (CCTV), Internet of Things (IoT), databases, drones, cloud computing services), heterogeneity and volume of data, forensic tool capability, and the investigative cost make investigations both technically challenging and prohibitively expensive. Forensic tools also tend to be siloed into specific technologies, e.g., File System Forensic Analysis Tools (FS-FAT) and Network Forensic Analysis Tools (N-FAT), and a good deal of data sources has little to no specialist forensic tools. Increasingly it also becomes essential to compare and correlate evidence across data sources and to do so in an efficient and effective manner enabling an investigator to answer high-level questions of the data in a timely manner without having to trawl through data and perform the correlation manually. This paper proposes a Unified Forensic Analysis Tool (U-FAT), which aims to establish a common language for electronic information and permit multi-source forensic analysis. Core to this approach is the identification and development of forensic analyses that automate complex data correlations, enabling investigators to investigate cases more efficiently. The paper presents a systematic analysis of major crime categories and identifies what forensic analyses could be used. For example, in a child abduction, an investigation team might have evidence from a range of sources including computing devices (mobile phone, PC), CCTV (potentially a large number), ISP records, and mobile network cell tower data, in addition to third party databases such as the National Sex Offender registry and tax records, with the desire to auto-correlate and across sources and visualize in a cognitively effective manner. U-FAT provides a holistic, flexible, and extensible approach to providing digital forensics in technology, application, and data-agnostic manner, providing powerful and automated forensic analysis.

Keywords: digital forensics, evidence correlation, heterogeneous data, forensics tool

Procedia PDF Downloads 175

Authors: Mohit Kumar, Mayur Betharia

Abstract:

Healthcare domain, with the emergence of Electronic Medical Record (EMR), collects a lot of data which have been attracting Data Mining expert’s interest. In the past, doctors have relied on their intuition while making critical clinical decisions. This paper presents the means to analyze the Medical workflows to get business insights out of huge dumped medical databases. Market Basket Analysis (MBA) which is a special data mining technique, has been widely used in marketing and e-commerce field to discover the association between products bought together by customers. It helps businesses in increasing their sales by analyzing the purchasing behavior of customers and pitching the right customer with the right product. This paper is an attempt to demonstrate Market Basket Analysis applications in healthcare. In particular, it discusses the Market Basket Analysis Algorithm ‘Apriori’ applications within healthcare in major areas such as analyzing the workflow of diagnostic procedures, Up-selling and Cross-selling of Healthcare Systems, designing healthcare systems more user-friendly. In the paper, we have demonstrated the MBA applications using Angiography Systems, but can be extrapolated to other modalities as well.

Keywords: data mining, market basket analysis, healthcare applications, knowledge discovery in healthcare databases, customer relationship management, healthcare systems

Procedia PDF Downloads 145

Authors: Jonardan Koner, Basabi Bhattacharya, Avinash Purandare

Abstract:

The study is focused to find out the impact of infrastructural investment on economic development in Indian states. The study uses panel data analysis to measure the impact of infrastructural investment on Real Gross Domestic Product in Indian States. Panel data analysis incorporates Unit Root Test, Cointegration Teat, Pooled Ordinary Least Squares, Fixed Effect Approach, Random Effect Approach, Hausman Test. The study analyzes panel data (annual in frequency) ranging from 1991 to 2012 and concludes that infrastructural investment has a desirable impact on economic development in Indian. Finally, the study reveals that the infrastructural investment significantly explains the variation of economic indicator.

Keywords: infrastructural investment, real GDP, unit root test, cointegration teat, pooled ordinary least squares, fixed effect approach, random effect approach, Hausman test

Procedia PDF Downloads 388