Search results for: real time prediction

Authors: Housein Deli, Loui Al-Shrouf, Hammoud Al Joumaa, Mohieddine Jelali

Abstract:

When forming metallic materials, fluctuations in material properties, process conditions, and wear lead to deviations in the component geometry. Several hundred features sometimes need to be measured, especially in the case of functional and safety-relevant components. These can only be measured offline due to the large number of features and the accuracy requirements. The risk of producing components outside the tolerances is minimized but not eliminated by the statistical evaluation of process capability and control measurements. The inspection intervals are based on the acceptable risk and are at the expense of productivity but remain reactive and, in some cases, considerably delayed. Due to the considerable progress made in the field of condition monitoring and measurement technology, permanently installed sensor systems in combination with machine learning and artificial intelligence, in particular, offer the potential to independently derive forecasts for component geometry and thus eliminate the risk of defective products - actively and preventively. The reliability of forecasts depends on the quality, completeness, and timeliness of the data. Measuring all geometric characteristics is neither sensible nor technically possible. This paper, therefore, uses the example of car seat rail production to discuss the necessary first step of feature selection and reduction by correlation analysis, as otherwise, it would not be possible to forecast components in real-time and inline. Four different car seat rails with an average of 130 features were selected and measured using a coordinate measuring machine (CMM). The run of such measuring programs alone takes up to 20 minutes. In practice, this results in the risk of faulty production of at least 2000 components that have to be sorted or scrapped if the measurement results are negative. Over a period of 2 months, all measurement data (> 200 measurements/ variant) was collected and evaluated using correlation analysis. As part of this study, the number of characteristics to be measured for all 6 car seat rail variants was reduced by over 80%. Specifically, direct correlations for almost 100 characteristics were proven for an average of 125 characteristics for 4 different products. A further 10 features correlate via indirect relationships so that the number of features required for a prediction could be reduced to less than 20. A correlation factor >0.8 was assumed for all correlations.

Keywords: long-term SHM, condition monitoring, machine learning, correlation analysis, component prediction, wear prediction, regressions analysis

Procedia PDF Downloads 34

Authors: Mohd Sukri Hassan, Ahlam Inayatullah Badrul Munir, M. Husaini A. Rahman

Abstract:

Halal authentication and verification in supplement capsules are highly required as the gelatine available in the market can be from halal or non-halal sources. It is an obligation for Muslim to consume and use the halal consumer goods. At present, real-time polymerase chain reaction (RT-PCR) is the most common technique being used for the detection of porcine and bovine DNA in gelatine due to high sensitivity of the technique and higher stability of DNA compared to protein. In this study, twenty samples of supplements capsules from different products with different Halal logos were analyzed for porcine and bovine DNA using RT-PCR. Standard bovine and porcine gelatine from eurofins at a range of concentration from 10^-1 to 10^-5 ng/µl were used to determine the linearity range, limit of detection and specificity on RT-PCR (SYBR Green method). RT-PCR detected porcine (two samples), bovine (four samples) and mixture of porcine and bovine (six samples). The samples were also tested using FT-IR technique where normalized peak of IR spectra were pre-processed using Savitsky Golay method before Principal Components Analysis (PCA) was performed on the database. Scores plot of PCA shows three clusters of samples; bovine, porcine and mixture (bovine and porcine). The RT-PCR and FT-IR with chemometrics technique were found to give same results for porcine gelatine samples which can be used for Halal authentication.

Keywords: halal, real-time PCR, gelatine, chemometrics

Procedia PDF Downloads 230

Authors: Ulas Vural, M. Ergun Okay, E. Mesut Yildiz

Abstract:

Telecommunication service providers demand accurate and precise prediction of customer churn probabilities to increase the effectiveness of their customer relation services. The large amount of customer data owned by the service providers is suitable for analysis by machine learning methods. In this study, expenditure data of customers are analyzed by using an artificial neural network (ANN). The ANN model is applied to the data of customers with different billing duration. The proposed model successfully predicts the churn probabilities at 83% accuracy for only three months expenditure data and the prediction accuracy increases up to 89% when the nine month data is used. The experiments also show that the accuracy of ANN model increases on an extended feature set with information of the changes on the bill amounts.

Keywords: customer relationship management, churn prediction, telecom industry, deep learning, artificial neural networks

Procedia PDF Downloads 140

Authors: Gayathri Nagarajan, L. D. Dhinesh Babu

Abstract:

Health care is one of the prominent industries that generate voluminous data thereby finding the need of machine learning techniques with big data solutions for efficient processing and prediction. Missing data, incomplete data, real time streaming data, sensitive data, privacy, heterogeneity are few of the common challenges to be addressed for efficient processing and mining of health care data. In comparison with other applications, accuracy and fast processing are of higher importance for health care applications as they are related to the human life directly. Though there are many machine learning techniques and big data solutions used for efficient processing and prediction in health care data, different techniques and different frameworks are proved to be effective for different applications largely depending on the characteristics of the datasets. In this paper, we present a framework that uses ensemble machine learning technique gradient boosted trees for data classification in health care big data. The framework is built on Spark platform which is fast in comparison with other traditional frameworks. Unlike other works that focus on a single technique, our work presents a comparison of six different machine learning techniques along with gradient boosted trees on datasets of different characteristics. Five benchmark health care datasets are considered for experimentation, and the results of different machine learning techniques are discussed in comparison with gradient boosted trees. The metric chosen for comparison is misclassification error rate and the run time of the algorithms. The goal of this paper is to i) Compare the performance of gradient boosted trees with other machine learning techniques in Spark platform specifically for health care big data and ii) Discuss the results from the experiments conducted on datasets of different characteristics thereby drawing inference and conclusion. The experimental results show that the accuracy is largely dependent on the characteristics of the datasets for other machine learning techniques whereas gradient boosting trees yields reasonably stable results in terms of accuracy without largely depending on the dataset characteristics.

Keywords: big data analytics, ensemble machine learning, gradient boosted trees, Spark platform

Procedia PDF Downloads 234

Authors: Marian Sorin Ionescu, Olivia Negoita, Cosmin Dobrin

Abstract:

This scientific communication reports and discusses learning models adaptable to modern business problems and models specific to digital concepts and paradigms. In the PAC (probably approximately correct) learning model approach, in which the learning process begins by receiving a batch of learning examples, the set of learning processes is used to acquire a hypothesis, and when the learning process is fully used, this hypothesis is used in the prediction of new operational examples. For complex business models, a lot of models should be introduced and evaluated to estimate the induced results so that the totality of the results are used to develop a predictive rule, which anticipates the choice of new models. In opposition, for online learning-type processes, there is no separation between the learning (training) and predictive phase. Every time a business model is approached, a test example is considered from the beginning until the prediction of the appearance of a model considered correct from the point of view of the business decision. After choosing choice a part of the business model, the label with the logical value "true" is known. Some of the business models are used as examples of learning (training), which helps to improve the prediction mechanisms for future business models.

Keywords: machine learning, business models, convex analysis, online learning

Procedia PDF Downloads 136

Authors: Romain Ben Taleb, Aurélie Montarnal, Matthieu Lauras, Mathieu Dahan, Romain Miclo

Abstract:

To be competitive and sustainable, any company has to maximize its value. However, unlike listed companies that can assess their values based on market shares, most Small and Medium Enterprises (SMEs) which are non-listed cannot have direct and live access to this critical information. Traditional accounting reports only give limited insights to SME decision-makers about the real impact of their day-to-day decisions on the company’s performance and value. Most of the time, an SME’s financial valuation is made one time a year as the associated process is time and resource-consuming, requiring several months and external expertise to be completed. To solve this issue, we propose in this paper a value-oriented metamodel that enables real-time and dynamic assessment of the SME’s value based on the large definition of their assets. These assets cover a wider scope of resources of the company and better account for immaterial assets. The proposal, which is illustrated in a case study, discusses the benefits of incorporating assets in the SME valuation.

Keywords: SME, metamodel, decision support system, financial valuation, assets

Procedia PDF Downloads 88

Authors: Abdul Ghani Rajput

Abstract:

Although monitoring and evaluation concept adopted by Technical Vocational Education and Training (TVET) organization to track the progress over the continuous interval of time based on planned interventions and subsequently, evaluating it for the impact, quality assurance and sustainability. In digital world, TVET providers are giving preference to have real time information to do monitoring of training activities. Identifying the benefits and challenges of digitized monitoring & evaluation real time information system has not been sufficiently tackled in this date. This research paper looks at the impact of digitized M&E in TVET sector by analyzing two case studies and describe the benefits and challenges of using digitized M&E system. Finally, digitized M&E have been identified as carriers for high potential of TVET sector.

Keywords: digitized M&E, innovation, quality assurance, TVET

Procedia PDF Downloads 222

Authors: Ionel Zagan, Vasile Gheorghita Gaitan

Abstract:

The development of CPUs and of real-time systems based on them made it possible to use time at increasingly low resolutions. Together with the scheduling methods and algorithms, time organizing has been improved so as to respond positively to the need for optimization and to the way in which the CPU is used. This presentation contains both a detailed theoretical description and the results obtained from research on improving the performances of the nMPRA (Multi Pipeline Register Architecture) processor by implementing specific functions in hardware. The proposed CPU architecture has been developed, simulated and validated by using the FPGA Virtex-7 circuit, via a SoC project. Although the nMPRA processor hardware structure with five pipeline stages is very complex, the present paper presents and analyzes the tests dedicated to the implementation of the CPU and of the memory on-chip for instructions and data. In order to practically implement and test the entire SoC project, various tests have been performed. These tests have been performed in order to verify the drivers for peripherals and the boot module named Bootloader.

Keywords: hardware scheduler, nMPRA processor, real-time systems, scheduling methods

Procedia PDF Downloads 264

Authors: Mehrzad Mohabbi Yadollahi, Ramazan Demirboğa, Majid Atashafrazeh

Abstract:

Geopolymers are highly complex materials which involve many variables which makes modeling its properties very difficult. There is no systematic approach in mix design for Geopolymers. Since the amounts of silica modulus, Na2O content, w/b ratios and curing time have a great influence on the compressive strength an ANFIS (Adaptive neuro fuzzy inference system) method has been established for predicting compressive strength of ground pumice based Geopolymers and the possibilities of ANFIS for predicting the compressive strength has been studied. Consequently, ANFIS can be used for geopolymer compressive strength prediction with acceptable accuracy.

Keywords: geopolymer, ANFIS, compressive strength, mix design

Procedia PDF Downloads 844

Authors: Cyrus Addy, Venkata Sriram Siddhardh Nadendla, Kwame Awuah-Offei

Abstract:

Surface robots in modern underground mine rescue operations suffer from several limitations in enabling a prompt self-rescue. Therefore, the possibility of designing and deploying in-mine robots to expedite miner self-rescue can have a transformative impact on miner safety. These in-mine robots for miner self-rescue can be envisioned to carry out diverse tasks such as object detection, autonomous navigation, and payload delivery. Specifically, this paper investigates the challenges in the design of object detection algorithms for in-mine robots using thermal images, especially to detect people in real-time. A total of 125 thermal images were collected in the Missouri S&T Experimental Mine with the help of student volunteers using the FLIR TG 297 infrared camera, which were pre-processed into training and validation datasets with 100 and 25 images, respectively. Three state-of-the-art, pre-trained real-time object detection models, namely YOLOv5, YOLO-FIRI, and YOLOv8, were considered and re-trained using transfer learning techniques on the training dataset. On the validation dataset, the re-trained YOLOv8 outperforms the re-trained versions of both YOLOv5, and YOLO-FIRI.

Keywords: miner self-rescue, object detection, underground mine, YOLO

Procedia PDF Downloads 74

Authors: Surangrat Srisurapanon, Chatchawal Wongjitrat, Navin Horthongkham, Ruengpung Sutthent

Abstract:

HBV infection causes a potential serious public health problem. The ability to detect the HBV DNA concentration is of the importance and improved continuously. By using quantitative Polymerase Chain Reaction (qPCR), several factors in standardized; source of material, calibration standard curve and PCR efficiency are inconsistent. Digital PCR (dPCR) is an alternative PCR-based technique for absolute quantification using Poisson's statistics without requiring a standard curve. Therefore, the aim of this study is to compare the data set of HBV DNA generated between dPCR and qPCR methods. All samples were quantified by Abbott’s real time PCR and 54 samples with 2 -6 log10 HBV DNA were selected for comparison with dPCR. Of these 54 samples, there were two outlier samples defined as negative by dPCR. Of these two, samples were defined as negative by dPCR, whereas 52 samples were positive by both the tests. The difference between the two assays was less than 0.25 log IU/mL in 24/52 samples (46%) of paired samples; less than 0.5 log IU/mL in 46/52 samples (88%) and less than 1 log in 50/52 samples (96%). The correlation coefficient was r=0.788 and P-value <0.0001. Comparison to qPCR, data generated by dPCR tend to be the overestimation in the sample with low HBV DNA concentration and underestimated in the sample with high viral load. The variation in DNA by dPCR measurement might be due to the pre-amplification bias, template. Moreover, a minor drawback of dPCR is the large quantity of DNA had to be used when compare to the qPCR. Since the technology is relatively new, the limitations of this assay will be improved.

Keywords: hepatitis B virus, real time PCR, digital PCR, DNA quantification

Procedia PDF Downloads 477

Authors: Vitalijs Lusis, Andrejs Krasnikovs

Abstract:

Fiber reinforced concrete is important material for load bearing structural elements. Usually fibers are homogeneously distributed in a concrete body having arbitrary spatial orientations. At the same time, in many situations, fiber concrete with oriented fibers is more optimal. Is obvious, that is possible to create constructions with oriented short fibers in them, in different ways. Present research is devoted to one of such approaches- fiber reinforced concrete prisms having dimensions 100 mm×100 mm×400 mm with layers of non-homogeneously distributed fibers inside them were fabricated. Simultaneously prisms with homogeneously dispersed fibers were produced for reference as well. Prisms were tested under four point bending conditions. During the tests vertical deflection at the center of every prism and crack opening were measured (using linear displacements transducers in real timescale). Prediction results were discussed.

Keywords: fiber reinforced concrete, 4-point bending, steel fiber, construction engineering

Procedia PDF Downloads 363

Authors: Femi Elegbeleye, Omobayo Esan, Muienge Mbodila, Patrick Bowe

Abstract:

This paper focused on cost effective storage architecture using fog and cloud data storage gateway and presented the design of the framework for the data privacy model and data analytics framework on a real-time analysis when using machine learning method. The paper began with the system analysis, system architecture and its component design, as well as the overall system operations. The several results obtained from this study on data privacy model shows that when two or more data privacy model is combined we tend to have a more stronger privacy to our data, and when fog storage gateway have several advantages over using the traditional cloud storage, from our result shows fog has reduced latency/delay, low bandwidth consumption, and energy usage when been compare with cloud storage, therefore, fog storage will help to lessen excessive cost. This paper dwelt more on the system descriptions, the researchers focused on the research design and framework design for the data privacy model, data storage, and real-time analytics. This paper also shows the major system components and their framework specification. And lastly, the overall research system architecture was shown, its structure, and its interrelationships.

Keywords: IoT, fog, cloud, data analysis, data privacy

Procedia PDF Downloads 92

Authors: Yalçın Bozkurt

Abstract:

Prediction models were developed for accurate prediction of bodyweight (BW) by using Digital Images of beef cattle body dimensions by Artificial Neural Networks (ANN). For this purpose, the animal data were collected at a private slaughter house and the digital images and the weights of each live animal were taken just before they were slaughtered and the body dimensions such as digital wither height (DJWH), digital body length (DJBL), digital body depth (DJBD), digital hip width (DJHW), digital hip height (DJHH) and digital pin bone length (DJPL) were determined from the images, using the data with 1069 observations for each traits. Then, prediction models were developed by ANN. Digital body measurements were analysed by ANN for body prediction and R2 values of DJBL, DJWH, DJHW, DJBD, DJHH and DJPL were approximately 94.32, 91.31, 80.70, 83.61, 89.45 and 70.56 % respectively. It can be concluded that in management situations where BW cannot be measured it can be predicted accurately by measuring DJBL and DJWH alone or both DJBD and even DJHH and different models may be needed to predict BW in different feeding and environmental conditions and breeds

Keywords: artificial neural networks, bodyweight, cattle, digital body measurements

Procedia PDF Downloads 363

Authors: Ankur Jain, W. Wilfred Godfrey

Abstract:

Embedded systems are usually microcontroller-based systems that represent a class of reliable and dependable dedicated computer systems designed for specific purposes. Micro-controllers are used in most electronic devices in an endless variety of ways. Some micro-controller-based embedded systems are required to respond to external events in the shortest possible time and such systems are known as real-time embedded systems. So in multitasking system there is a need of task Scheduling,there are various scheduling algorithms like Fixed priority Scheduling(FPS),Earliest deadline first(EDF), Rate Monotonic(RM), Deadline Monotonic(DM),etc have been researched. In this Report various conventional algorithms have been reviewed and analyzed, these algorithms consists of single shape task, A new Multishape scheduling algorithms has been proposed and implemented and analyzed.

Keywords: dm, edf, embedded systems, fixed priority, microcontroller, rtos, rm, scheduling algorithms

Procedia PDF Downloads 398

Authors: Naman Solanki, Souraj Mondal

Abstract:

With the world moving towards online communication, the video datastore has exploded in the past few years. Consequently, it has become crucial to analyse participant’s engagement levels in online communication videos. Engagement prediction of people in videos can be useful in many domains, like education, client meetings, dating, etc. Video-level or frame-level prediction of engagement for a user involves the development of robust models that can capture facial micro-emotions efficiently. For the development of an engagement prediction model, it is necessary to have a widely-accepted standard dataset for engagement analysis. DAiSEE is one of the datasets which consist of in-the-wild data and has a gold standard annotation for engagement prediction. Earlier research done using the DAiSEE dataset involved training and testing standard models like CNN-based models, but the results were not satisfactory according to industry standards. In this paper, a multi-level classification approach has been introduced to create a more robust model for engagement analysis using the DAiSEE dataset. This approach has recorded testing accuracies of 0.638, 0.7728, 0.8195, and 0.866 for predicting boredom level, engagement level, confusion level, and frustration level, respectively.

Keywords: computer vision, engagement prediction, deep learning, multi-level classification

Procedia PDF Downloads 109

Authors: Elona Saliaj

Abstract:

The registration of real estate in Albania after the 90's has been a long process in time and with high cost for the country. Passing the registration system from a centralized system to a free market private system, it’s accompanied by legal uncertainties that have led to economic instability. The reforms that have been undertaken in terms of property rights have been numerous and continuous throughout the years. But despite the reforms, the system of registration of real estate, has failed to be standards requirements established by the European Union. The completion of initial registration of real estate, legal treatment of previous owners or legalization of illegal constructions remain among the main problems that prevent the development of the country in its economic sector. The performance of the registration of real estate system and dealing with issues that have appeared in the Court of First Instance, the civil section of the Albanian constitute the core of handling this analysis. This paper presents a detailed analysis on the registration system that is chosen to be applied in our country for real estate. In its content it is also determined the institution that administrates these properties, the management technique and the law that determinate its functionality. The strategy is determined for creating a modern and functional registration system and for the country remains a challenge to achieve. Identifying practical problems and providing their solutions are also the focus of reference in order to improve and modernize this important system to a state law that aims to become a member of the European Union.

Keywords: real estates registration system, comparative aspects, cadastral area, property certificate, legal reform

Procedia PDF Downloads 487

Authors: Sohyoung Won, Heebal Kim, Dajeong Lim

Abstract:

Genomic prediction is an effective way to measure the abilities of livestock for breeding based on genomic estimated breeding values, statistically predicted values from genotype data using best linear unbiased prediction (BLUP). Using haplotypes, clusters of linked single nucleotide polymorphisms (SNPs), as markers instead of individual SNPs can improve the reliability of genomic prediction since the probability of a quantitative trait loci to be in strong linkage disequilibrium (LD) with markers is higher. To efficiently use haplotypes in genomic prediction, finding optimal ways to define haplotypes is needed. In this study, 770K SNP chip data was collected from Hanwoo (Korean cattle) population consisted of 2506 cattle. Haplotypes were first defined in three different ways using 770K SNP chip data: haplotypes were defined based on 1) length of haplotypes (bp), 2) the number of SNPs, and 3) k-medoids clustering by LD. To compare the methods in parallel, haplotypes defined by all methods were set to have comparable sizes; in each method, haplotypes defined to have an average number of 5, 10, 20 or 50 SNPs were tested respectively. A modified GBLUP method using haplotype alleles as predictor variables was implemented for testing the prediction reliability of each haplotype set. Also, conventional genomic BLUP (GBLUP) method, which uses individual SNPs were tested to evaluate the performance of the haplotype sets on genomic prediction. Carcass weight was used as the phenotype for testing. As a result, using haplotypes defined by all three methods showed increased reliability compared to conventional GBLUP. There were not many differences in the reliability between different haplotype defining methods. The reliability of genomic prediction was highest when the average number of SNPs per haplotype was 20 in all three methods, implying that haplotypes including around 20 SNPs can be optimal to use as markers for genomic prediction. When the number of alleles generated by each haplotype defining methods was compared, clustering by LD generated the least number of alleles. Using haplotype alleles for genomic prediction showed better performance, suggesting improved accuracy in genomic selection. The number of predictor variables was decreased when the LD-based method was used while all three haplotype defining methods showed similar performances. This suggests that defining haplotypes based on LD can reduce computational costs and allows efficient prediction. Finding optimal ways to define haplotypes and using the haplotype alleles as markers can provide improved performance and efficiency in genomic prediction.

Keywords: best linear unbiased predictor, genomic prediction, haplotype, linkage disequilibrium

Procedia PDF Downloads 138

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 274

Authors: Mohammad A. Obeidat, Ayman M. Mansour

Abstract:

Capturing the dynamic behavior of the heart to improve control performance, enhance robustness, and support diagnosis is very important in establishing real time models for the heart. Control Techniques and strategies have been utilized to improve system costs, reliability, and estimation accuracy for different types of systems such as biomedical, industrial, and other systems that required tuning input/output relation and/or monitoring. Simulations are performed to illustrate potential applications of the technology. In this research, a new control technology scheme is used to enhance the performance of the Af system and meet the design specifications.

Keywords: atrial fibrillation, dynamic behavior, closed loop, signal, filter

Procedia PDF Downloads 409

Authors: Mohammad Zavid Parvez, Manoranjan Paul

Abstract:

Epilepsy is a common neurological disorders characterized by sudden recurrent seizures. Electroencephalogram (EEG) is widely used to diagnose possible epileptic seizure. Many research works have been devoted to predict epileptic seizure by analyzing EEG signal. Seizure prediction by analyzing EEG signals are challenging task due to variations of brain signals of different patients. In this paper, we propose a new approach for feature extraction based on phase correlation in EEG signals. In phase correlation, we calculate relative change between two consecutive segments of an EEG signal and then combine the changes with neighboring signals to extract features. These features are then used to classify preictal/ictal and interictal EEG signals for seizure prediction. Experiment results show that the proposed method carries good prediction rate with greater consistence for the benchmark data set in different brain locations compared to the existing state-of-the-art methods.

Keywords: EEG, epilepsy, phase correlation, seizure

Procedia PDF Downloads 303

Authors: Hiroki Takiguchi, Masahiro Furuya, Takahiro Arai

Abstract:

In order to quantitatively comprehend thermal flow for some industrial applications such as nuclear and chemical reactors, detailed measurements for temperature and abundance (concentration) of materials at high temporal and spatial resolution are required. Additionally, rigorous evaluation of the size effect is also important for practical realization. This paper introduces a real-time spectroscopic imaging method in micro scale field, which visualizes temperature and concentration distribution of a liquid or mix liquids with near-infrared (NIR) wavelength region. This imaging principle is based on absorption of pre-selected narrow band from absorption spectrum peak or its dependence property of target liquid in NIR region. For example, water has a positive temperature sensitivity in the wavelength at 1905 nm, therefore the temperature of water can be measured using the wavelength band. In the experiment, the real-time imaging observation of concentration distribution in micro channel was demonstrated to investigate the applicability of micro-scale diffusion coefficient and temperature measurement technique using this proposed method. The effect of thermal diffusion and binary mutual diffusion was evaluated with the time-series visualizations of concentration distribution.

Keywords: near-infrared spectroscopic imaging, micro fluid channel, concentration distribution, diffusion phenomenon

Procedia PDF Downloads 155

Authors: Kanae Suzuki

Abstract:

Handheld video games are popular communication tools among Japanese elementary school students today. This study aims to examine the effects of the use of handheld video games on interpersonal relationships of the students in real and virtual worlds. A two-wave panel survey was conducted for students of ten elementary schools at an interval of approximately six months. The survey questionnaire included questions about the average amount of time spent playing a handheld video game during the past one month, the frequency of communication with players during game play, and the interpersonal relationships, such as the number of real and virtual friends the students have. A multiple regression model was constructed for 324 students to examine causal relationships. The results indicated that the more frequently the students communicated with other players while playing games, the number of the real friends tended to increase. In contrast, no significant effect of the total time spent playing games was found on interpersonal relationships. The findings suggested that communication during game play is an important factor for improving interpersonal relationships of this age group.

Keywords: communication, real friend, social adjustment, virtual friend

Procedia PDF Downloads 487

Authors: Alan Wan

Abstract:

In recent years, the body of literature on frequentist model averaging in statistics has grown significantly. Most of this work focuses on models with different mean structures but leaves out the variance consideration. In this paper, we consider a regression model with multiplicative heteroscedasticity and develop a model averaging method that combines maximum likelihood estimators of unknown parameters in both the mean and variance functions of the model. Our weight choice criterion is based on a minimisation of a plug-in estimator of the model average estimator's squared prediction risk. We prove that the new estimator possesses an asymptotic optimality property. Our investigation of finite-sample performance by simulations demonstrates that the new estimator frequently exhibits very favourable properties compared to some existing heteroscedasticity-robust model average estimators. The model averaging method hedges against the selection of very bad models and serves as a remedy to variance function misspecification, which often discourages practitioners from modeling heteroscedasticity altogether. The proposed model average estimator is applied to the analysis of two real data sets.

Keywords: heteroscedasticity-robust, model averaging, multiplicative heteroscedasticity, plug-in, squared prediction risk

Procedia PDF Downloads 373

Authors: Kanchan Mondal, Dasharath Koulage, Dattatray Manerikar, Asmita Ghate

Abstract:

This paper presents an additive reliability model using warranty data and Finite Element Analysis (FEA) data. Warranty data for any product gives insight to its underlying issues. This is often used by Reliability Engineers to build prediction model to forecast failure rate of parts. But there is one major limitation in using warranty data for prediction. Warranty periods constitute only a small fraction of total lifetime of a product, most of the time it covers only the infant mortality and useful life zone of a bathtub curve. Predicting with warranty data alone in these cases is not generally provide results with desired accuracy. Failure rate of a mechanical part is driven by random issues initially and wear-out or usage related issues at later stages of the lifetime. For better predictability of failure rate, one need to explore the failure rate behavior at wear out zone of a bathtub curve. Due to cost and time constraints, it is not always possible to test samples till failure, but FEA-Fatigue analysis can provide the failure rate behavior of a part much beyond warranty period in a quicker time and at lesser cost. In this work, the authors proposed an Additive Weibull Model, which make use of both warranty and FEA fatigue analysis data for predicting failure rates. It involves modeling of two data sets of a part, one with existing warranty claims and other with fatigue life data. Hazard rate base Weibull estimation has been used for the modeling the warranty data whereas S-N curved based Weibull parameter estimation is used for FEA data. Two separate Weibull models’ parameters are estimated and combined to form the proposed Additive Weibull Model for prediction.

Keywords: bathtub curve, fatigue, FEA, reliability, warranty, Weibull

Procedia PDF Downloads 66

Authors: Theoktisti Makridou, Konstantinos Tsaprailis, George Arvanitakis, Charalampos Kontoes

Abstract:

In the literature, the data-driven approaches for mosquito abundance prediction relaying on supervised machine learning models that get trained with historical in-situ measurements. The counterpart of this approach is once the model gets trained on pointlevel (specific x,y coordinates) measurements, the predictions of the model refer again to point-level. These point-level predictions reduce the applicability of those solutions once a lot of early warning and mitigation actions applications need predictions for an area level, such as a municipality, village, etc... In this study, we apply a data-driven predictive model, which relies on public-open satellite Earth Observation and geospatial data and gets trained with historical point-level in-Situ measurements of mosquito abundance. Then we propose a methodology to extract information from a point-level predictive model to a broader area-level prediction. Our methodology relies on the randomly spatial sampling of the area of interest (similar to the Poisson hardcore process), obtaining the EO and geomorphological information for each sample, doing the point-wise prediction for each sample, and aggregating the predictions to represent the average mosquito abundance of the area. We quantify the performance of the transformation from the pointlevel to the area-level predictions, and we analyze it in order to understand which parameters have a positive or negative impact on it. The goal of this study is to propose a methodology that predicts the mosquito abundance of a given area by relying on point-level prediction and to provide qualitative insights regarding the expected performance of the area-level prediction. We applied our methodology to historical data (of Culex pipiens) of two areas of interest (Veneto region of Italy and Central Macedonia of Greece). In both cases, the results were consistent. The mean mosquito abundance of a given area can be estimated with similar accuracy to the point-level predictor, sometimes even better. The density of the samples that we use to represent one area has a positive effect on the performance in contrast to the actual number of sampling points which is not informative at all regarding the performance without the size of the area. Additionally, we saw that the distance between the sampling points and the real in-situ measurements that were used for training did not strongly affect the performance.

Keywords: mosquito abundance, supervised machine learning, culex pipiens, spatial sampling, west nile virus, earth observation data

Procedia PDF Downloads 142

Authors: C. J. Rossouw, T. I. van Niekerk

Abstract:

The global manufacturing industry is utilizing the internet and cloud-based services to further explore the anatomy and optimize manufacturing processes in support of the movement into the Fourth Industrial Revolution (4IR). The 4IR from a third world and African perspective is hindered by the fact that many manufacturing systems that were developed in the third industrial revolution are not inherently equipped to utilize the internet and services of the 4IR, hindering the progression of third world manufacturing industries into the 4IR. This research focuses on the development of a non-invasive and cost-effective cyber-physical IoT system that will exploit a machine’s vibration to expose semantic characteristics in the manufacturing process and utilize these results through a real-time cloud-based machine condition monitoring system with the intention to optimize the system. A microcontroller-based IoT sensor was designed to acquire a machine’s mechanical vibration data, process it in real-time, and transmit it to a cloud-based platform via Wi-Fi and the internet. Time-frequency Fourier analysis was applied to the vibration data to form an image representation of the machine’s behaviour. This data was used to train a Convolutional Neural Network (CNN) to learn semantic characteristics in the machine’s behaviour and relate them to a state of operation. The same data was also used to train a Convolutional Autoencoder (CAE) to detect anomalies in the data. Real-time edge-based artificial intelligence was achieved by deploying the CNN and CAE on the sensor to analyse the vibration. A cloud platform was deployed to visualize the vibration data and the results of the CNN and CAE in real-time. The cyber-physical IoT system was deployed on a semi-automated metal granulation machine with a set of trained machine learning models. Using a single sensor, the system was able to accurately visualize three states of the machine’s operation in real-time. The system was also able to detect a variance in the material being granulated. The research demonstrates how non-IoT manufacturing systems can be equipped with edge-based artificial intelligence to establish a remote machine condition monitoring system.

Keywords: IoT, cyber-physical systems, artificial intelligence, manufacturing, vibration analytics, continuous machine condition monitoring

Procedia PDF Downloads 84

Authors: Larissa Bolliger, Junoš Lukan, Mitja Lustrek, Dirk De Bacquer, Els Clays

Abstract:

Introduction and Aim: Chronic workplace stress and its health-related consequences like mental and cardiovascular diseases have been widely investigated. This project focuses on the sources and context of psychosocial daily workplace stress in a real-world setting. The main objective is to analyze and model real-time relationships between (1) psychosocial stress experiences within the natural work environment, (2) micro-level work activities and events, and (3) physiological signals and behaviors in office workers. Methods: An Ecological Momentary Assessment (EMA) protocol has been developed, partly building on machine learning techniques. Empatica® wristbands will be used for real-life detection of stress from physiological signals; micro-level activities and events at work will be based on smartphone registrations, further processed according to an automated computer algorithm. A field study including 100 office-based workers with high-level problem-solving tasks like managers and researchers will be implemented in Slovenia and Belgium (50 in each country). Data mining and state-of-the-art statistical methods – mainly multilevel statistical modelling for repeated data – will be used. Expected Results and Impact: The project findings will provide novel contributions to the field of occupational health research. While traditional assessments provide information about global perceived state of chronic stress exposure, the EMA approach is expected to bring new insights about daily fluctuating work stress experiences, especially micro-level events and activities at work that induce acute physiological stress responses. The project is therefore likely to generate further evidence on relevant stressors in a real-time working environment and hence make it possible to advise on workplace procedures and policies for reducing stress.

Keywords: ecological momentary assessment, real-time, stress, work

Procedia PDF Downloads 154

Authors: Pallavi Mane, Nikita Mankar, Shraddha Mazire, Rasika Pashankar

Abstract:

Content sharing sites are very useful in sharing information and images. However, with the increasing demand of content sharing sites privacy and security concern have also increased. There is need to develop a tool for controlling user access to their shared content. Therefore, we are developing an Adaptive Privacy Policy Prediction (A3P) system which is helpful for users to create privacy settings for their images. We propose the two-level framework which assigns the best available privacy policy for the users images according to users available histories on the site.

Keywords: online information services, prediction, security and protection, web based services

Procedia PDF Downloads 353

Authors: Sam Khozama, Ali M. Mayya

Abstract:

Breast cancer is one of the most common types in women. Early prediction of breast cancer helps physicians detect cancer in its early stages. Big cancer data needs a very powerful tool to analyze and extract predictions. Machine learning and deep learning are two of the most efficient tools for predicting cancer based on textual data. In this study, we developed a fusion model of two machine learning and deep learning models. To obtain the final prediction, Long-Short Term Memory (LSTM) and ensemble learning with hyper parameters optimization are used, and score-level fusion is used. Experiments are done on the Breast Cancer Surveillance Consortium (BCSC) dataset after balancing and grouping the class categories. Five different training scenarios are used, and the tests show that the designed fusion model improved the performance by 3.3% compared to the individual models.

Keywords: machine learning, deep learning, cancer prediction, breast cancer, LSTM, fusion

Procedia PDF Downloads 157