Search results for: data loss

Authors: Wen-Yang Hu, Ranli Lu, Mark Maienschein-Cline, Danping Hu, Larisa Nonn, Toshi Shioda, Gail S. Prins

Abstract:

Background: Genetic mutations are highly associated with increased prostate cancer risk. In addition to whole genome sequencing, somatic mutations can be identified by aligning transcriptome sequences to the human genome. Here we analyzed bulk RNAseq and single cell RNAseq data of human prostate cancer cells and their matched non-cancer cells in benign regions from 4 individual patients. Methods: Sequencing raw reads were aligned to the reference genome hg38 using STAR. Variants were annotated using Annovar with respect to overlap gene annotation information, effect on gene and protein sequence, and SIFT annotation of nonsynonymous variant effect. We determined cancer-specific novel alleles by comparing variant calls in cancer cells to matched benign cells from the same individual by selecting unique alleles that were only detected in the cancer samples. Results: In bulk RNAseq data from 3 patients, the most common variants were the noncoding mutations at UTR3/UTR5, and the major variant types were single-nucleotide polymorphisms (SNP) including frameshift mutations. C>T transversion is the most frequently presented substitution of SNP. A total of 222 genes carrying unique exonic or UTR variants were revealed in cancer cells across 3 patients but not in benign cells. Among them, transcriptome levels of 7 genes (CITED2, YOD1, MCM4, HNRNPA2B1, KIF20B, DPYSL2, NR4A1) were significantly up or down regulated in cancer stem cells. Out of the 222 commonly mutated genes in cancer, 19 have nonsynonymous variants and 11 are damaged genes with variants including SIFT, frameshifts, stop gain/loss, and insertions/deletions (indels). Two damaged genes, activating transcription factor 6 (ATF6) and histone demethylase KDM3A are of particular interest; the former is a survival factor for certain cancer cells while the later positively activates androgen receptor target genes in prostate cancer. Further, single cell RNAseq data of cancer cells and their matched non-cancer benign cells from both primary 2D and 3D tumoroid cultures were analyzed. Similar to the bulk RNAseq data, single cell RNAseq in cancer demonstrated that the exonic mutations are less common than noncoding variants, with SNPs including frameshift mutations the most frequently presented types in cancer. Compared to cancer stem cell enriched-3D tumoroids, 2D cancer cells carried 3-times higher variants, 8-times more coding mutations and 10-times more nonsynonymous SNP. Finally, in both 2D primary and 3D tumoroid cultures, cancer stem cells exhibited fewer coding mutations and noncoding SNP or insertions/deletions than non-stem cancer cells. Summary: Our study demonstrates the usefulness of bulk and single cell RNAseaq data in identifying somatic mutations in prostate cancer, providing an alternative method in screening candidate genes for prostate cancer diagnosis and potential therapeutic targets. Cancer stem cells carry fewer somatic mutations than non-stem cancer cells due to their inherited immortal stand DNA from parental stem cells that explains their long-lived characteristics.

Keywords: prostate cancer, stem cell, genomic mutation, RNAseq

Procedia PDF Downloads 32

Authors: Piotr Tylec, Julia Wierzbicka, Natalia Gajewska, Krzysztof Przeczek, Grzegorz Torbicz, Alicja Dudek, Magdalena Pisarska-Adamczyk, Mateusz Wierdak, Michal Pedziwiatr

Abstract:

Introduction: Many patients have described changes in taste perception after weight loss surgery. However, little data is available about short term changes in taste after surgery. Aim: We aimed to evaluate short-term changes in taste preference after bariatric surgeries in comparison to colorectal surgeries. Material and Methods: Between April 2018 and April 2019, a total of 121 bariatric patients and 63 controls participated. Bariatric patients underwent laparoscopic sleeve gastrectomy or Roux-en-Y gastric by-pass. Controls underwent oncological colorectal surgeries. Patients who developed clinical complications requiring restriction of oral intake after surgery or withdraw their consent were excluded from the study. In the end, 85 bariatric patients and 44 controls were included. In all of them, the 16-item ERAS Protocol was applied. Using 10-points Numeric Rating Scale (1-10) patients completed questionnaire and rated their appetite and thirst (1 - no appetite/not thirsty, 10 – normal appetite/very thirsty) and flavoured standardized liquids' taste (1- horrible, 10-very tasty) and food images for the 6 group of taste (sweet, umami, sour, spicy, bitter and salty) (1 - not appetizing, 10 - very appetizing) preoperatively and on the first postoperative day. Data were analysed with Statistica 13.0 PL. Results: Analysed group consist of 129 patients (85 bariatric, 44 controls). Mean age and BMI in a research group was 44.91 years old, 46.22 kg/m² and in control group 62.09 years old, 25.87 kg/m², respectively. Our analysis revealed significant differences in changes of appetite between both groups (research: -4.55 ± 3.76 vs. control: -0.85 ± 4.37; p < 0.05), ratings bitter (research: 0.60 ± 2.98 vs. control: -0.88 ± 2.58; p < 0.05) and salty (research: 1.20 ± 3.50 vs. control: -0.52 ± 2.90; p < 0.05) flavoured liquids and ratings for sweet (research: 1.62 ± 3.31 vs. control: 0.01 ± 2.63; p < 0.05) and bitter (research: 1.21 ± 3.15 vs. control: -0.09 ± 2.25; p < 0.05) food images. There were statistically significant results in the ratings of other images, but in comparison to the control group, they were not statistically significant. Conclusion: The study showed that bariatric surgeries quickly decreases appetite and desire to eat certain types of food, such as salty. Moreover, the bitter taste was more desirable in the research group in comparison to control group. Nevertheless, the sweet taste was more appetible in the bariatric group than in control.

Keywords: bariatric surgery, general surgery, obesity, taste preference

Procedia PDF Downloads 140

Authors: Kaustav Mukherjee

Abstract:

In this paper we propose a Neural Style Transfer solution whereby we have created a Lightweight Separable Convolution Kernel Based GAN Architecture (SC-GAN) which will very useful for designing filter for Mobile Phone Cameras and also Edge Devices which will convert any image to its 2D ANIMATED COMIC STYLE Movies like HEMAN, SUPERMAN, JUNGLE-BOOK. This will help the 2D animation artist by relieving to create new characters from real life person's images without having to go for endless hours of manual labour drawing each and every pose of a cartoon. It can even be used to create scenes from real life images.This will reduce a huge amount of turn around time to make 2D animated movies and decrease cost in terms of manpower and time. In addition to that being extreme light-weight it can be used as camera filters capable of taking Comic Style Shots using mobile phone camera or edge device cameras like Raspberry Pi 4,NVIDIA Jetson NANO etc. Existing Methods like CartoonGAN with the model size close to 170 MB is too heavy weight for mobile phones and edge devices due to their scarcity in resources. Compared to the current state of the art our proposed method which has a total model size of 31 MB which clearly makes it ideal and ultra-efficient for designing of camera filters on low resource devices like mobile phones, tablets and edge devices running OS or RTOS. .Owing to use of high resolution input and usage of bigger convolution kernel size it produces richer resolution Comic-Style Pictures implementation with 6 times lesser number of parameters and with just 25 extra epoch trained on a dataset of less than 1000 which breaks the myth that all GAN need mammoth amount of data. Our network reduces the density of the Gan architecture by using Depthwise Separable Convolution which does the convolution operation on each of the RGB channels separately then we use a Point-Wise Convolution to bring back the network into required channel number using 1 by 1 kernel.This reduces the number of parameters substantially and makes it extreme light-weight and suitable for mobile phones and edge devices. The architecture mentioned in the present paper make use of Parameterised Batch Normalization Goodfellow etc al. (Deep Learning OPTIMIZATION FOR TRAINING DEEP MODELS page 320) which makes the network to use the advantage of Batch Norm for easier training while maintaining the non-linear feature capture by inducing the learnable parameters

Keywords: comic stylisation from camera image using GAN, creating 2D animated movie style custom stickers from images, depth-wise separable convolutional neural network for light-weight GAN architecture for EDGE devices, GAN architecture for 2D animated cartoonizing neural style, neural style transfer for edge, model distilation, perceptual loss

Procedia PDF Downloads 137

Authors: Jun Hong Lee

Abstract:

Background: Alzheimer`s disease (AD) I: creases with age and is characterized by the premature progressive loss of neuronal cell. In contrast, cancer cells have inappropriate cell proliferation and resistance to cell death. Objective: We evaluated the association between cancer and AD and also examined the specific types of cancer. Patients and Methods/Material and Methods: This retrospective, nationwide, longitudinal study used National Health Insurance Service – Senior cohort (NHIS-Senior) 2002-2013, which was released by the KNHIS in 2016, comprising 550,000 random subjects who were selected from over than 60. The study included a cohort of 4,408 patients who were first diagnoses as AD between 2003 and 2005. To match each dementia patient, 19,150 subjects were selected from the database by Propensity Score Matching. Results: We enrolled 4,790 patients for analysis in this cohort and the prevalence of AD was higher in female (19.29%) than in male (17.71%). A higher prevalence of AD was observed in the 70-84 year age group and in the higher income status group. A total of 540 cancers occurred within the observation interval. Overall cancer was less frequent in those with AD (12.25%) than in the control (18.46%), with HR 0.704 (95% Confidence Intervals (CIs)=0.0.64-0.775, p-Value < 0.0001). Conclusion: Our data showed a decreased incidence of overall cancers in patients with AD similar to previous studies. Patients with AD had a significantly decreased risk of colon & rectum, lung and stomach cancer. This finding lower than but consistent with Western countries. We need further investigation of genetic evidence linking AD to cancer.

Keywords: Alzheimer, cancer, nationwide, longitudinal study

Procedia PDF Downloads 184

Authors: Francky Fouedjio

Abstract:

Multivariate geostatistical data have become omnipresent in the geosciences and pose substantial analysis challenges. One of them is the grouping of data locations into spatially contiguous clusters so that data locations within the same cluster are more similar while clusters are different from each other, in some sense. Spatially contiguous clusters can significantly improve the interpretation that turns the resulting clusters into meaningful geographical subregions. In this paper, we develop an agglomerative hierarchical clustering approach that takes into account the spatial dependency between observations. It relies on a dissimilarity matrix built from a non-parametric kernel estimator of the spatial dependence structure of data. It integrates existing methods to find the optimal cluster number and to evaluate the contribution of variables to the clustering. The capability of the proposed approach to provide spatially compact, connected and meaningful clusters is assessed using bivariate synthetic dataset and multivariate geochemical dataset. The proposed clustering method gives satisfactory results compared to other similar geostatistical clustering methods.

Keywords: clustering, geostatistics, multivariate data, non-parametric

Procedia PDF Downloads 481

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 143

Authors: Nidhin Dani Abraham, T. K. Sri Shilpa

Abstract:

Asset liability management is an important aspect in banking business. Moreover, the today’s banking is based on BASEL III which strictly regulates on the counterparty default. This paper focuses on prediction and analysis of counter party default risk, which is a type of risk occurs when the customers fail to repay the amount back to the lender (bank or any financial institutions). This paper proposes an approach to reduce the counterparty risk occurring in the financial institutions using an appropriate data mining technique and thus predicts the occurrence of NPA. It also helps in asset building and restructuring quality. Liability management is very important to carry out banking business. To know and analyze the depth of liability of bank, a suitable technique is required. For that a data mining technique is being used to predict the dormant behaviour of various deposit bank customers. Various models are implemented and the results are analyzed of saving bank deposit customers. All these data are cleaned using data cleansing approach from the bank data warehouse.

Keywords: data mining, asset liability management, BASEL III, banking

Procedia PDF Downloads 562

Authors: Chris Suma, Yingcai Xiao

Abstract:

This paper presents Parallel Coordinates on a Spiral Surface (PCoSS), a parallel coordinate based interactive visualization method for high-dimensional data, and a test implementation of the method. Plots generated by the test system are compared with those generated by XDAT, a software implementing traditional parallel coordinates. Traditional parallel coordinate plots can be cluttered when the number of data points is large or when the dimensionality of the data is high. PCoSS plots display multivariate data on a 3D spiral surface and allow users to see the whole picture of high-dimensional data with less cluttering. Taking advantage of the 3D display environment in PCoSS, users can further reduce cluttering by zooming into an axis of interest for a closer view or by moving vantage points and by reorienting the viewing angle to obtain a desired view of the plots.

Keywords: human computer interaction, parallel coordinates, spiral surface, visualization

Procedia PDF Downloads 22

Authors: Wanyi Zhu, Xia Ming, Huafeng Wang, Junda Chen, Lu Liu, Jiangwei Jiang, Guohua Liu

Abstract:

Anomaly detection is a first and imperative step needed to respond to unexpected problems and to assure high performance and security in large data center management. This paper presents an online anomaly detection system through an innovative approach of ensemble machine learning and adaptive differentiation algorithms, and applies them to performance data collected from a continuous monitoring system for multi-tier web applications running in Alibaba data centers. We evaluate the effectiveness and efficiency of this algorithm with production traffic data and compare with the traditional anomaly detection approaches such as a static threshold and other deviation-based detection techniques. The experiment results show that our algorithm correctly identifies the unexpected performance variances of any running application, with an acceptable false positive rate. This proposed approach has already been deployed in real-time production environments to enhance the efficiency and stability in daily data center operations.

Keywords: Alibaba data centers, anomaly detection, big data computation, dynamic ensemble learning

Procedia PDF Downloads 205

Authors: Elkington Sibusiso Mnguni

Abstract:

In South Africa, mining has been a key economic sector since the discovery of gold in 1886 in the Witwatersrand region, where the city of Johannesburg is located. However, some mines have since been decommissioned, and the continuous pumping of acid mine drainage (AMD) also stopped causing the AMD to rise towards the ground surface. This posed a serious environmental risk to the groundwater resources and river systems in the region. This paper documents the development and extent of the environmental damage as well as the measures implemented by the government to alleviate such damage. The study will add to the body of knowledge on the subject of AMD treatment to prevent environmental degradation. The method used to gather and collate relevant data and information was the desktop study. The key findings include the social and environmental impact of the AMD, which include the pollution of water sources for domestic use leading to skin and other health problems and the loss of biodiversity in some areas. It was also found that the technical intervention of constructing a plant to pump and treat the AMD using the high-density sludge technology was the most effective short-term solution available while a long-term solution was being explored. Some successes and challenges experienced during the implementation of the project are also highlighted. The study will be a useful record of the current status of the AMD treatment interventions in the region.

Keywords: acid mine drainage, groundwater resources, pollution, river systems, technical intervention, high density sludge

Procedia PDF Downloads 189

Authors: Ichihan Tai, Bill Olson, Paul Blessner

Abstract:

Traditional early warning systems that alarm against crisis are generally based on structured or numerical data; therefore, a system that can make predictions based on unstructured textual data, an uncorrelated data source, is a great complement to the traditional early warning systems. The Chicago Board Options Exchange (CBOE) Volatility Index (VIX), commonly referred to as the fear index, measures the cost of insurance against market crash, and spikes in the event of crisis. In this study, news data is consumed for prediction of whether there will be a market-wide crisis by predicting the movement of the fear index, and the historical references to similar events are presented in an unsupervised manner. Topic modeling-based prediction and representation are made based on daily news data between 1990 and 2015 from The Wall Street Journal against VIX index data from CBOE.

Keywords: early warning system, knowledge management, market prediction, topic modeling.

Procedia PDF Downloads 343

Authors: Ava Dodd, Jonathan Adams

Abstract:

The purpose of this study is to explore the characteristics of developing a machine learning application using synthetic data. The study is structured to develop the application for the purpose of deploying the computer vision model. The findings discuss the realities of attempting to develop a computer vision model for practical purpose, and detail the processes, tools, and techniques that were used to meet accuracy requirements. The research reveals that synthetic data represents another variable that can be adjusted to improve the performance of a computer vision model. Further, a suite of tools and tuning recommendations are provided.

Keywords: computer vision, machine learning, synthetic data, YOLOv4

Procedia PDF Downloads 229

Authors: Mohammad Motiee

Abstract:

From Kierkegaard to Sartre, the concept of 'being' was debated over various angles in the philosophy of being. Then, the futility, nothingness and absurdity of human condition in the world were all justified and led to a kind of solution by different approaches like Christianity, loss of faith, authentic existence and responsibility. In an extreme concern, the human condition in the world was pondered in different ways and the philosophy of thought tried to render an awareness of such condition for human beings. The present study aims at illustration of some approaches presented by prominent existentialists to justify the controversies in the concept of existence in human life.

Keywords: existence, existentialism, alienation, being

Procedia PDF Downloads 564

Authors: K. Indra Gandhi

Abstract:

Wireless Sensor Networks (WSNs) have always been characterized for application-specific sensing, relaying and collection of information for further analysis. However, software development was not considered as a separate entity in this process of data collection which has posed severe limitations on the software development for WSN. Software development for WSN is a complex process since the components involved are data-driven, network-driven and application-driven in nature. This implies that there is a tremendous need for the separation of concern from the software development perspective. A layered approach for developing data acquisition design based on Model Driven Development (MDD) has been proposed as the sensed data collection process itself varies depending upon the application taken into consideration. This work focuses on the layered view of the data acquisition process so as to ease the software point of development. A metamodel has been proposed that enables reusability and realization of the software development as an adaptable component for WSN systems. Further, observing users perception indicates that proposed model helps in improving the programmer's productivity by realizing the collaborative system involved.

Keywords: data acquisition, model-driven development, separation of concern, wireless sensor networks

Procedia PDF Downloads 439

Authors: Bhat Geetalaxmi Jairam, D. V. Ashoka

Abstract:

Wireless Sensor Networks are used in many applications to collect sensed data from different sources. Sensed data has to be delivered through sensors wireless interface using multi-hop communication towards the sink. The data collection in wireless sensor networks consumes energy. Energy consumption is the major constraints in WSN .Reducing the energy consumption while increasing the amount of generated data is a great challenge. In this paper, we have implemented two data gathering protocols with multiple mobile sinks/elements to collect data from sensor nodes. First, is Energy-Efficient Data Gathering with Tour Length-Constrained Mobile Elements in Wireless Sensor Networks (EEDG), in which mobile sinks uses vehicle routing protocol to collect data. Second is An Intelligent Agent-based Routing Structure for Mobile Sinks in WSNs (IAR), in which mobile sinks uses prim’s algorithm to collect data. Authors have implemented concepts which are common to both protocols like deployment of mobile sinks, generating visiting schedule, collecting data from the cluster member. Authors have compared the performance of both protocols by taking statistics based on performance parameters like Delay, Packet Drop, Packet Delivery Ratio, Energy Available, Control Overhead. Authors have concluded this paper by proving EEDG is more efficient than IAR protocol but with few limitations which include unaddressed issues likes Redundancy removal, Idle listening, Mobile Sink’s pause/wait state at the node. In future work, we plan to concentrate more on these limitations to avail a new energy efficient protocol which will help in improving the life time of the WSN.

Keywords: aggregation, consumption, data gathering, efficiency

Procedia PDF Downloads 502

Authors: Ryan Maclellan

Abstract:

EXO-200 has provided one of the most sensitive searches for neutrinoless double-beta decay utilizing 175 kg of enriched liquid xenon in an ultra-low background time projection chamber. This detector has demonstrated excellent energy resolution and background rejection capabilities. Using the first two years of data, EXO-200 has set a limit of 1.1x10^25 years at 90% C.L. on the neutrinoless double-beta decay half-life of Xe-136. The experiment has experienced a brief hiatus in data taking during a temporary shutdown of its host facility: the Waste Isolation Pilot Plant. EXO-200 expects to resume data taking in earnest this fall with upgraded detector electronics. Results from the analysis of EXO-200 data and an update on the current status of EXO-200 will be presented.

Keywords: double-beta, Majorana, neutrino, neutrinoless

Procedia PDF Downloads 417

Authors: Akbar Darouie, Mamak Joulaie

Abstract:

In regard of phonological skills development importance and its influence on other aspects of language, this study has been performed. Determination of some phonological indexes in children with hearing impairment and comparison with hearing children was the objective. A sample of convenience was selected from a rehabilitation center and a kindergarten in Karaj, Iran. Participants consisted of 12 hearing impaired and 12 hearing children (age range: 5 years and 6 months to 6 years and 6 months old). Hearing impaired children suffered from severe to profound hearing loss while three of them were cochlear implanted and the others were wearing hearing aids. Conversational speech of these children was recorded and 50 first utterances were selected to analyze. Percentage of consonant correct (PCC) and vowel correct (PVC), initial and final consonant omission error, cluster consonant omission error and syllabic structure variety were compared in two groups. Data were analyzed with t test (version 16th SPSS). Comparison between PCC and PVC averages in two groups showed a significant difference (P< 0/01). There was a significant difference about final consonant emission error (P<0/001) and initial consonant emission error (P<0/01) too. Also, the differences between two groups on cluster consonant omission were significant (P<0/001). Therefore, some changes were seen in syllabic structures in children with hearing impairment compared to typical group. This study demonstrates some phonological differences in Farsi language between two groups of children. Therefore, it seems, in clinical practices we must notice this issue.

Keywords: hearing impairment, phonology, vowel, consonant

Procedia PDF Downloads 246

Authors: A. Sivakumar, S. S. Darun Prakash, P. Navaneethakrishnan

Abstract:

In and around Erode District, it is estimated that more than 1250 chemical and allied textile processing fabric industries are affected, partially closed and shut off for various reasons such as poor management, poor supplier performance, lack of planning for productivity, fluctuation of output, poor investment, waste analysis, labor problems, capital/labor ratio, accumulation of stocks, poor maintenance of resources, deficiencies in the quality of fabric, low capacity utilization, age of plant and equipment, high investment and input but low throughput, poor research and development, lack of energy, workers’ fear of loss of jobs, work force mix and work ethic. The main objective of this work is to analyze the existing conditions in textile fabric sector, validate the break even of Total Productivity (TP), analyze, design and implement fuzzy sets and mathematical programming for improvement of productivity and quality dimensions in the fabric processing industry. It needs to be compatible with the reality of textile and fabric processing industries. The highly risk events from productivity and quality dimension were found by fuzzy systems and results are wrapped up among the textile fabric processing industry.

Keywords: break even point, fuzzy crisp data, fuzzy sets, productivity, productivity cycle, total productive maintenance

Procedia PDF Downloads 343

Authors: Nadia Jurkovic, Sarven McLinton, Alyson Crozier, Amber Mosewich, Ed O'Connor

Abstract:

Retiring from elite sport can have detrimental effects on the mental health and life satisfaction of retired elite athletes. To aid in this transition, sporting organisations use retirement interventions. The aim of this study is to understand the experience of elite sport retirement from a holistic perspective, exploring the experiences of retiring athletes, retired athletes, and sport support staff. A secondary aim is used to uncover any recommendations both retiring/retired athletes and sport support staff suggest towards improving retirement programs or interventions. A total of N=15 participants took part in semi-structured interviews to explore their experiences with sport retirement. Retiring and retired elite athletes were asked about how they felt during their transition into retirement, and sport support staff were asked about their experience working with retiring athletes. Data collection and iterative qualitative analysis are still ongoing; however, it is anticipated that the final key themes to emerge will include isolation, identity loss, and lack of support, with varying sub-themes such as organisational support and family support. Relationships across and within themes will be explored within the study. The anticipated findings present retiring from elite sports as a challenging life and career transition; however, current support and resources for elite athletes are not addressing the core difficulties experienced by retiring elite athletes. The findings of this study will inform future development of new co-designed elite sport retirement interventions.

Keywords: elite athlete, retired elite athlete, retirement interventions, transition into retirement, interviews

Procedia PDF Downloads 25

Authors: Amit R. Bhende, G. K. Awari

Abstract:

Remaining useful life (RUL) prediction is one of key technologies to realize prognostics and health management that is being widely applied in many industrial systems to ensure high system availability over their life cycles. The present work proposes a data-driven method of RUL prediction based on multiple health state assessment for rolling element bearings. Bearing degradation data at three different conditions from run to failure is used. A RUL prediction model is separately built in each condition. Feed forward back propagation neural network models are developed for prediction modeling.

Keywords: bearing degradation data, remaining useful life (RUL), back propagation, prognosis

Procedia PDF Downloads 442

Authors: Tolga Aydin, M. Fatih Alaeddinoğlu

Abstract:

People, throughout the history, have made estimates and inferences about the future by using their past experiences. Developing information technologies and the improvements in the database management systems make it possible to extract useful information from knowledge in hand for the strategic decisions. Therefore, different methods have been developed. Data mining by association rules learning is one of such methods. Apriori algorithm, one of the well-known association rules learning algorithms, is not commonly used in spatio-temporal data sets. However, it is possible to embed time and space features into the data sets and make Apriori algorithm a suitable data mining technique for learning spatio-temporal association rules. Lake Van, the largest lake of Turkey, is a closed basin. This feature causes the volume of the lake to increase or decrease as a result of change in water amount it holds. In this study, evaporation, humidity, lake altitude, amount of rainfall and temperature parameters recorded in Lake Van region throughout the years are used by the Apriori algorithm and a spatio-temporal data mining application is developed to identify overflows and newly-formed soil regions (underflows) occurring in the coastal parts of Lake Van. Identifying possible reasons of overflows and underflows may be used to alert the experts to take precautions and make the necessary investments.

Keywords: apriori algorithm, association rules, data mining, spatio-temporal data

Procedia PDF Downloads 377

Authors: Busayo Fashoto, Abdulhakeem Shaibu, Justice Agbadu, Samuel Aiyeoribe

Abstract:

Data has gone from just rows and columns to being an infrastructure itself. The traditional medium of data infrastructure has been managed by individuals in different industries and saved on personal work tools; one of such is the laptop. This hinders data sharing and Sustainable Development Goal (SDG) 9 for infrastructure sustainability across all countries and regions. However, there has been a constant demand for data across different agencies and ministries by investors and decision-makers. The rapid development and adoption of open-source technologies that promote the collection and processing of data in new ways and in ever-increasing volumes are creating new data infrastructure in sectors such as lands and health, among others. This paper examines the process of developing data infrastructure and, by extension, a data portal to provide baseline data for sustainable development and decision making in Nigeria. This paper employs the FAIR principle (Findable, Accessible, Interoperable, and Reusable) of data management using open-source technology tools to develop data portals for public use. eHealth Africa, an organization that uses technology to drive public health interventions in Nigeria, developed a data portal which is a typical data infrastructure that serves as a repository for various datasets on administrative boundaries, points of interest, settlements, social infrastructure, amenities, and others. This portal makes it possible for users to have access to datasets of interest at any point in time at no cost. A skeletal infrastructure of this data portal encompasses the use of open-source technology such as Postgres database, GeoServer, GeoNetwork, and CKan. These tools made the infrastructure sustainable, thus promoting the achievement of SDG 9 (Industries, Innovation, and Infrastructure). As of 6th August 2021, a wider cross-section of 8192 users had been created, 2262 datasets had been downloaded, and 817 maps had been created from the platform. This paper shows the use of rapid development and adoption of technologies that facilitates data collection, processing, and publishing in new ways and in ever-increasing volumes. In addition, the paper is explicit on new data infrastructure in sectors such as health, social amenities, and agriculture. Furthermore, this paper reveals the importance of cross-sectional data infrastructures for planning and decision making, which in turn can form a central data repository for sustainable development across developing countries.

Keywords: data portal, data infrastructure, open source, sustainability

Procedia PDF Downloads 103

Authors: Hyun-Woo Cho

Abstract:

Unexpected operational events or abnormalities of industrial processes have a serious impact on the quality of final product of interest. In terms of statistical process control, fault detection and diagnosis of processes is one of the essential tasks needed to run the process safely. In this work, nonlinear representation of process measurement data is presented and evaluated using a simulation process. The effect of using different representation methods on the diagnosis performance is tested in terms of computational efficiency and data handling. The results have shown that the nonlinear representation technique produced more reliable diagnosis results and outperforms linear methods. The use of data filtering step improved computational speed and diagnosis performance for test data sets. The presented scheme is different from existing ones in that it attempts to extract the fault pattern in the reduced space, not in the original process variable space. Thus this scheme helps to reduce the sensitivity of empirical models to noise.

Keywords: fault diagnosis, nonlinear technique, process data, reduced spaces

Procedia PDF Downloads 254

Authors: Harald Lang, Michael Bader, A. Buchroithner

Abstract:

Holistic methods covering the development process as a whole – e.g. systems engineering – have established themselves in product design. However, technical product optimization, representing improvements in efficiency and/or minimization of loss, usually applies to single components of a system. A holistic approach is being defined based on a hierarchical point of view of systems engineering. This is subsequently presented using the example of an electromechanical flywheel energy storage system for automotive applications.

Keywords: design, product development, product optimization, systems engineering

Procedia PDF Downloads 627

Authors: Dzhavidan Zeinalov, Bugra Sen, Firangiz Aslanova

Abstract:

Most text-to-speech models cannot operate well in low-resource languages and require a great amount of high-quality training data to be considered good enough. Yet, with the improvements made in ASR systems, it is now much easier than ever to collect data for the design of custom text-to-speech models. In this work, our work on using the ASR model to collect data to build a viable text-to-speech system for one of the leading financial institutions of Azerbaijan will be outlined. NVIDIA’s implementation of the Tacotron 2 model was utilized along with the HiFiGAN vocoder. As for the training, the model was first trained with high-quality audio data collected from the Internet, then fine-tuned on the bank’s single speaker call center data. The results were then evaluated by 50 different listeners and got a mean opinion score of 4.17, displaying that our method is indeed viable. With this, we have successfully designed the first text-to-speech model in Azerbaijani and publicly shared 12 hours of audiobook data for everyone to use.

Keywords: Azerbaijani language, HiFiGAN, Tacotron 2, text-to-speech, transfer learning, whisper

Procedia PDF Downloads 51

Authors: Ruchika Malhotra, Megha Khanna

Abstract:

The development of change prediction models can help the software practitioners in planning testing and inspection resources at early phases of software development. However, a major challenge faced during the training process of any classification model is the imbalanced nature of the software quality data. A data with very few minority outcome categories leads to inefficient learning process and a classification model developed from the imbalanced data generally does not predict these minority categories correctly. Thus, for a given dataset, a minority of classes may be change prone whereas a majority of classes may be non-change prone. This study explores various alternatives for adeptly handling the imbalanced software quality data using different sampling methods and effective MetaCost learners. The study also analyzes and justifies the use of different performance metrics while dealing with the imbalanced data. In order to empirically validate different alternatives, the study uses change data from three application packages of open-source Android data set and evaluates the performance of six different machine learning techniques. The results of the study indicate extensive improvement in the performance of the classification models when using resampling method and robust performance measures.

Keywords: change proneness, empirical validation, imbalanced learning, machine learning techniques, object-oriented metrics

Procedia PDF Downloads 421

Authors: Jasaswini Mishra, Ashim K. Dey

Abstract:

This paper aims to investigate the group interaction effects of laterally loaded pile groups driven into a medium dense sand layer in submerged state. Static lateral load tests were carried out on pile groups consisting of varying number of piles and at different spacings. The test setup consists of a load cell (500 kg capacity) and an LVDT (50 mm) to measure the load and pile head deflection respectively. The piles were extensively instrumented with strain gauges so as to study the variation of soil resistance within the group. The bending moments at various depths were calculated from strain gauge data and these curves were fitted using a higher order polynomial in order to get 'p-y' curves. A comparative study between a single pile and a pile under a group has also been done for a better understanding of the group effect. It is observed that average load per pile is significantly reduced relative to single pile and it decreases with increase in the number of piles in a pile group. The loss of efficiency of the piles in the group, commonly referred to as "shadowing" effect, has been expressed by the use of a 'p-multiplier'. Leading rows carries greater amount of load when compared with the trailing rows. The variations of bending moment with depth for different rows of pile within a group and different spacing have been analyzed and compared with that of a single pile. p multipliers within different rows in a pile group were evaluated from the experimental study.

Keywords: group action, laterally loaded piles, p-multiplier, strain gauge

Procedia PDF Downloads 243

Authors: Farnoush Haghanipour

Abstract:

Objective: Father loss as one of the major stress factor, can causethe mental imbalances in children. It's clear that children's family condition of lacking a father is very clearly different from the condition of having a father. The goal of this research is to examine mental imbalances comparative checking in complete form and in five subsidiary categories as aggression, stress and depression, social incompatibility, anti-social behavior, and attention deficit imbalances (wackiness) do between children without father and normal ones. Method: This research is in descriptive and analytical method that reimburse to checking mental imbalances from 50 children that are student in one zone of Rasht’s education and nurture office. Material of this research is RATER behavior questionnaire (teacher form) and data analyses were did by SPSS software. Results: The results showed that there are clear different in relation with behavior imbalances between have father children and children without father and in children without a father behavior imbalance is more. Also showed that there is clearly a difference in aggression, stress, and depression and social incompatibility between children without and without fathers, and in children without a father the proportion increases. However, in antisocial behaviours and attention deficit imbalances there are not a clear difference between them. Conclusion: With upper amount of imbalance behaviour detection in children without fathers compared with children with fathers, it is essential that practitioners of society hygienic and remedy put efforts in order to primary and secondary prevention, for mental health of this group of society.

Keywords: child, behave imbalances, children without father, mental imbalances

Procedia PDF Downloads 260

Authors: Sung-Won Seo, Jang-Young Choi

Abstract:

The rare earth magnets used in synchronous generators offer many advantages, including high efficiency, greatly reduced the size, and weight. The permanent magnet linear synchronous generator (PMLSG) allows for direct drive without the need for a mechanical device. Therefore, the PMLSG is well suited to translational applications, such as wave energy converters and free piston energy converters. This manuscript compares the effects of different magnetization patterns on the characteristics of double-sided PMLSGs in slotless stator structures. The Halbach array has a higher flux density in air-gap than the Vertical array, and the advantages of its performance and efficiency are widely known. To verify the advantage of Halbach array, we apply a finite element method (FEM) and analytical method. In general, a FEM and an analytical method are used in the electromagnetic analysis for determining model characteristics, and the FEM is preferable to magnetic field analysis. However, the FEM is often slow and inflexible. On the other hand, the analytical method requires little time and produces accurate analysis of the magnetic field. Therefore, the flux density in air-gap and the Back-EMF can be obtained by FEM. In addition, the results from the analytical method correspond well with the FEM results. The model of the Halbach array reveals less copper loss than the model of the Vertical array, because of the Halbach array’s high output power density. The model of the Vertical array is lower core loss than the model of Halbach array, because of the lower flux density in air-gap. Therefore, the current density in the Vertical model is higher for identical power output. The completed manuscript will include the magnetic field characteristics and structural features of both models, comparing various results, and specific comparative analysis will be presented for the determination of the best model for application in a wave energy converting system.

Keywords: wave energy converter, permanent magnet linear synchronous generator, finite element method, analytical method

Procedia PDF Downloads 305

Authors: Francesco Pandolfi, Georgios Baltzopoulos, Iunio Iervolino

Abstract:

The impact of extreme winds on industrial assets and the built environment is gaining increasing attention from stakeholders, including the corporate insurance industry. This has led to a progressively more in-depth study of building vulnerability and fragility to wind. Wind vulnerability models are used in probabilistic risk assessment to relate a loss metric to an intensity measure of the natural event, usually a gust or a mean wind speed. In fact, vulnerability models can be integrated with the wind hazard, which consists of associating a probability to each intensity level in a time interval (e.g., by means of return periods) to provide an assessment of future losses due to extreme wind. This has also given impulse to the world- and regional-scale wind hazard studies.Another approach often adopted for the probabilistic description of building vulnerability to the wind is the use of fragility functions, which provide the conditional probability that selected building components will exceed certain damage states, given wind intensity. In fact, in wind engineering literature, it is more common to find structural system- or component-level fragility functions rather than wind vulnerability models for an entire building. Loss assessment based on component fragilities requires some logical combination rules that define the building’s damage state given the damage state of each component and the availability of a consequence model that provides the losses associated with each damage state. When risk calculations are based on numerical simulation of a structure’s behavior during extreme wind scenarios, the interaction of component fragilities is intertwined with the computational procedure. However, simulation-based approaches are usually computationally demanding and case-specific. In this context, the present work introduces the ExtReMe wind risk assESsment prototype Software, ERMESS, which is being developed at the University of Naples Federico II. ERMESS is a wind risk assessment tool for insurance applications to industrial facilities, collecting a wide assortment of available wind vulnerability models and fragility functions to facilitate their incorporation into risk calculations based on in-built or user-defined wind hazard data. This software implements an alternative method for building-specific risk assessment based on existing component-level fragility functions and on a number of simplifying assumptions for their interactions. The applicability of this alternative procedure is explored by means of an illustrative proof-of-concept example, which considers four main building components, namely: the roof covering, roof structure, envelope wall and envelope openings. The application shows that, despite the simplifying assumptions, the procedure can yield risk evaluations that are comparable to those obtained via more rigorous building-level simulation-based methods, at least in the considered example. The advantage of this approach is shown to lie in the fact that a database of building component fragility curves can be put to use for the development of new wind vulnerability models to cover building typologies not yet adequately covered by existing works and whose rigorous development is usually beyond the budget of portfolio-related industrial applications.

Keywords: component wind fragility, probabilistic risk assessment, vulnerability model, wind-induced losses

Procedia PDF Downloads 183