Search results for: 1) model group

Authors: Ahmed H. Amer, A. Amar, Sh. Hamada, I. I. Bondouk, F. A. El-Hussiny

Abstract:

Elastic scattering of α-particles from 9Be and 11B nuclei at different alpha energies have been analyzed. Optical model parameters (OMPs) of α-particles elastic scattering by these nuclei at different energies have been obtained. In the present calculations, the real part of the optical potential are derived by folding of nucleonnucleon (NN) interaction into nuclear matter density distribution of the projectile and target nuclei using computer code FRESCO. A density-dependent version of the M3Y interaction (CDM3Y6), which is based on the G-matrix elements of the Paris NN potential, has been used. Volumetric integrals of the real and imaginary potential depth (JR, JW) have been calculated and found to be energy dependent. Good agreement between the experimental data and the theoretical predictions in the whole angular range. In double folding (DF) calculations, the obtained normalization coefficient Nr is in the range 0.70–1.32.

Keywords: Elastic scattering of α-particles, optical model parameters, double folding model, nucleon-nucleon interaction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2171

Authors: Taiki Baba, Tomoaki Hashimoto

Abstract:

The random dither quantization method enables us to achieve much better performance than the simple uniform quantization method for the design of quantized control systems. Motivated by this fact, the stochastic model predictive control method in which a performance index is minimized subject to probabilistic constraints imposed on the state variables of systems has been proposed for linear feedback control systems with random dither quantization. In other words, a method for solving optimal control problems subject to probabilistic state constraints for linear discrete-time control systems with random dither quantization has been already established. To our best knowledge, however, the feasibility of such a kind of optimal control problems has not yet been studied. Our objective in this paper is to investigate the feasibility of stochastic model predictive control problems for linear discrete-time control systems with random dither quantization. To this end, we provide the results of numerical simulations that verify the feasibility of stochastic model predictive control problems for linear discrete-time control systems with random dither quantization.

Keywords: Model predictive control, stochastic systems, probabilistic constraints, random dither quantization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 997

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores of text, ranging from positive, neutral and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing, tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process, and substituting the Naive Bayes for a deep learning neural network model.

Keywords: Sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 423

Authors: Tanit P ruktara

Abstract:

This research aims to study the preferable tourism and the elements of choosing tourist destination from domestic tourist in Bangkok and the nearby areas in Thailand.The data were collected by using 1249 set of questionnaires, in mid-August 2012. The result illustrates that religious destinations are the most preferable places for the tourist. The average expense per travel is approximately 47 USD a time. Travellers travel based on the advertisement in the television and internet and their decisions is based on the reputation of the destinations. The result on a place dimension demonstrates the neatness and well managed location play a crucial role on tourist destination. Gender, age, marriage status and their origins are affecting their spending and travelling behaviour. The researcher reckon that providing the area of arcade, selling the souvenir and promoting tourism among a young professional group would be an important key follow the income distribution policy, including managing the destination to welcome the family group, which the result is to identified as the highest spending.

Keywords: Domestic Tourist, Tourism, Tourist Behaviours, Tourism Place.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2165

Authors: Ya-Ting Carolyn Yang, Ping-Han Cheng, Shi-Hui Gilbert Chang, Terry Yuan-Fang Chen, Chih-Chieh Li

Abstract:

Nanotechnology is widely applied in various areas so professionals in the related fields have to know more than nano knowledge. In the study, we focus on adopting ICT-assisted PBL in college general education to foster professionals who possess multiple abilities. The research adopted a pretest and posttest quasi-experimental design. The control group received traditional instruction, and the experimental group received ICT-assisted PBL instruction. Descriptive statistics will be used to describe the means, standard deviations, and adjusted means for the tests between the two groups. Next, analysis of covariance (ANCOVA) will be used to compare the final results of the two research groups after 6 weeks of instruction. Statistics gathered in the end of the research can be used to make contrasts. Therefore, we will see how different teaching strategies can improve students’ understanding about nanotechnology and learning skills.

Keywords: Nanotechnology, science education, project-based learning, information and communication technology.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2054

Authors: Tessy Badriyah, Jim S. Briggs, Dave R. Prytherch

Abstract:

It is well known that Logistic Regression is the gold standard method for predicting clinical outcome, especially predicting risk of mortality. In this paper, the Decision Tree method has been proposed to solve specific problems that commonly use Logistic Regression as a solution. The Biochemistry and Haematology Outcome Model (BHOM) dataset obtained from Portsmouth NHS Hospital from 1 January to 31 December 2001 was divided into four subsets. One subset of training data was used to generate a model, and the model obtained was then applied to three testing datasets. The performance of each model from both methods was then compared using calibration (the χ2 test or chi-test) and discrimination (area under ROC curve or c-index). The experiment presented that both methods have reasonable results in the case of the c-index. However, in some cases the calibration value (χ2) obtained quite a high result. After conducting experiments and investigating the advantages and disadvantages of each method, we can conclude that Decision Trees can be seen as a worthy alternative to Logistic Regression in the area of Data Mining.

Keywords: Decision Trees, Logistic Regression, clinical outcome, risk of mortality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2498

Authors: Alexander Efremov

Abstract:

A system for market identification (SMI) is presented. The resulting representations are multivariable dynamic demand models. The market specifics are analyzed. Appropriate models and identification techniques are chosen. Multivariate static and dynamic models are used to represent the market behavior. The steps of the first stage of SMI, named data preprocessing, are mentioned. Next, the second stage, which is the model estimation, is considered in more details. Stepwise linear regression (SWR) is used to determine the significant cross-effects and the orders of the model polynomials. The estimates of the model parameters are obtained by a numerically stable estimator. Real market data is used to analyze SMI performance. The main conclusion is related to the applicability of multivariate dynamic models for representation of market systems.

Keywords: market identification, dynamic models, stepwise regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1598

Authors: I. Sonia d’Apolito, Bianca Sisinni, Mirko Grimaldi, Barbara Gili Fivela

Abstract:

The American English contrast /ɑ-ʌ/ (cop-cup) is difficult to be produced by Italian learners since they realize L2-/ɑ-ʌ/ as L1-/ɔ-a/ respectively, due to differences in phonetic-phonological systems and also in grapheme-to-phoneme conversion rules. In this paper, we try to answer the following research questions: Can a short training improve the production of English /ɑ-ʌ/ by Italian learners? Is a perceptual training better than an articulatory (ultrasound - US) training? Thus, we compare a perceptual training with an US articulatory one to observe: 1) the effects of short trainings on L2-/ɑ-ʌ/ productions; 2) if the US articulatory training improves the pronunciation better than the perceptual training. In this pilot study, 9 Salento-Italian monolingual adults participated: 3 subjects performed a 1-hour perceptual training (ES-P); 3 subjects performed a 1-hour US training (ES-US); and 3 control subjects did not receive any training (CS). Verbal instructions about the phonetic properties of L2-/ɑ-ʌ/ and L1-/ɔ-a/ and their differences (representation on F1-F2 plane) were provided during both trainings. After these instructions, the ES-P group performed an identification training based on the High Variability Phonetic Training procedure, while the ES-US group performed the articulatory training, by means of US video of tongue gestures in L2-/ɑ-ʌ/ production and dynamic view of their own tongue movements and position using a probe under their chin. The acoustic data were analyzed and the first three formants were calculated. Independent t-tests were run to compare: 1) /ɑ-ʌ/ in pre- vs. post-test respectively; /ɑ-ʌ/ in pre- and post-test vs. L1-/a-ɔ/ respectively. Results show that in the pre-test all speakers realize L2-/ɑ-ʌ/ as L1-/ɔ-a/ respectively. Contrary to CS and ES-P groups, the ES-US group in the post-test differentiates the L2 vowels from those produced in the pre-test as well as from the L1 vowels, although only one ES-US subject produces both L2 vowels accurately. The articulatory training seems more effective than the perceptual one since it favors the production of vowels in the correct direction of L2 vowels and differently from the similar L1 vowels.

Keywords: L2 vowel production, perceptual training, articulatory training, ultrasound.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 996

Authors: Farag Azzedin, Ahmad Ridha, Ali Rizvi

Abstract:

Trust management is one of the drawbacks in Peer-to-Peer (P2P) system. Lack of centralized control makes it difficult to control the behavior of the peers. Reputation system is one approach to provide trust assessment in P2P system. In this paper, we use fuzzy logic to model trust in a P2P environment. Our trust model combines first-hand (direct experience) and second-hand (reputation)information to allow peers to represent and reason with uncertainty regarding other peers' trustworthiness. Fuzzy logic can help in handling the imprecise nature and uncertainty of trust. Linguistic labels are used to enable peers assign a trust level intuitively. Our fuzzy trust model is flexible such that inference rules are used to weight first-hand and second-hand accordingly.

Keywords: P2P Systems; Trust, Reputation, Fuzzy Logic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2131

Authors: Selvam M, Natarajan. A M, Thangarajan R

Abstract:

Parsing is important in Linguistics and Natural Language Processing to understand the syntax and semantics of a natural language grammar. Parsing natural language text is challenging because of the problems like ambiguity and inefficiency. Also the interpretation of natural language text depends on context based techniques. A probabilistic component is essential to resolve ambiguity in both syntax and semantics thereby increasing accuracy and efficiency of the parser. Tamil language has some inherent features which are more challenging. In order to obtain the solutions, lexicalized and statistical approach is to be applied in the parsing with the aid of a language model. Statistical models mainly focus on semantics of the language which are suitable for large vocabulary tasks where as structural methods focus on syntax which models small vocabulary tasks. A statistical language model based on Trigram for Tamil language with medium vocabulary of 5000 words has been built. Though statistical parsing gives better performance through tri-gram probabilities and large vocabulary size, it has some disadvantages like focus on semantics rather than syntax, lack of support in free ordering of words and long term relationship. To overcome the disadvantages a structural component is to be incorporated in statistical language models which leads to the implementation of hybrid language models. This paper has attempted to build phrase structured hybrid language model which resolves above mentioned disadvantages. In the development of hybrid language model, new part of speech tag set for Tamil language has been developed with more than 500 tags which have the wider coverage. A phrase structured Treebank has been developed with 326 Tamil sentences which covers more than 5000 words. A hybrid language model has been trained with the phrase structured Treebank using immediate head parsing technique. Lexicalized and statistical parser which employs this hybrid language model and immediate head parsing technique gives better results than pure grammar and trigram based model.

Keywords: Hybrid Language Model, Immediate Head Parsing, Lexicalized and Statistical Parsing, Natural Language Processing, Parts of Speech, Probabilistic Context Free Grammar, Tamil Language, Tree Bank.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3622

Authors: Mahdi Sadeghian, Mahmoud Hassanlourad, Alireza Ardakani, Reza Dinarvand

Abstract:

In this research, the behavior of monopiles, under lateral loads, was investigated with vertical and oblique piles by Finite Element Method. In engineering practice when soil-pile interaction comes to the picture some simplifications are applied to reduce the design time. As a simplified replacement of soil and pile interaction analysis, pile could be replaced by a column. The height of the column would be equal to the free length of the pile plus a portion of the embedded length of it. One of the important factors studied in this study was that columns with an equivalent length (free length plus a part of buried depth) could be used instead of soil and pile modeling. The results of the analysis show that the more internal friction angle of the soil increases, the more the bearing capacity of the soil is achieved. This additional length is 6 to 11 times of the pile diameter in dense soil although in loose sandy soil this range might increase.

Keywords: Lateral bearing capacity, pile group, oblique pile, soil-structure interaction, depth of fixity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1010

Authors: Syhalath Xaphakdy, Toshio Nagata, Saykham Phommathat, Pavy Souwannavong, Vilayvanh Srithilat, Phoxay Sengdala, Bounaom Phetarnousone, Boualay Siharath, Xaya Chemcheng

Abstract:

The National University of Laos (NUOL) invited a group of volunteers from the Japan International Cooperation Agency (JICA) to revise the physics experiments to utilize the materials that were already available to students. The intension was to review and revise the materials regularly utilized in physics class. The project had access to limited materials and a small budget for the class in the unit; however, by developing experimental textbooks related to mechanics, electricity, and wave and vibration, the group found a way to apply them in the classroom and enhance the students teaching activities. The aim was to introduce a way to incorporate the materials and practices in the classroom to enhance the students learning and teaching skills, particularly when they graduate and begin working as high school teachers.

Keywords: NUOL, JICA, physics experiment materials, small budget, mechanics, electricity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1217

Authors: Ekaterina Artiukhina, Panagiotis Grammelis

Abstract:

Torrefaction of biomass pellets is considered as a useful pretreatment technology in order to convert them into a high quality solid biofuel that is more suitable for pyrolysis, gasification, combustion, and co-firing applications. In the course of torrefaction, the temperature varies across the pellet, and therefore chemical reactions proceed unevenly within the pellet. However, the uniformity of the thermal distribution along the pellet is generally assumed. The torrefaction process of a single cylindrical pellet is modeled here, accounting for heat transfer coupled with chemical kinetics. The drying sub-model was also introduced. The nonstationary process of wood pellet decomposition is described by the system of non-linear partial differential equations over the temperature and mass. The model captures well the main features of the experimental data.

Keywords: Torrefaction, biomass pellets, model, heat and mass transfer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1784

Authors: Firas Gerges, Frank Y. Shih

Abstract:

Malignant Melanoma, known simply as Melanoma, is a type of skin cancer that appears as a mole on the skin. It is critical to detect this cancer at an early stage because it can spread across the body and may lead to the patient death. When detected early, Melanoma is curable. In this paper we propose a deep learning model (Convolutional Neural Networks) in order to automatically classify skin lesion images as Malignant or Benign. Images underwent certain pre-processing steps to diminish the effect of the normal skin region on the model. The result of the proposed model showed a significant improvement over previous work, achieving an accuracy of 97%.

Keywords: Deep learning, skin cancer, image processing, melanoma.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1496

Authors: Sanjeeva Balasuriya

Abstract:

A phenomenological model for species spreading which incorporates the Allee effect, a species- maximum attainable growth rate, collective dispersal rate and dispersal adaptability is presented. This builds on a well-established reaction-diffusion model for spatial spreading of invading organisms. The model is phrased in terms of the “hostility" (which quantifies the Allee threshold in relation to environmental sustainability) and dispersal adaptability (which measures how a species is able to adapt its migratory response to environmental conditions). The species- invading/retreating speed and the sharpness of the invading boundary are explicitly characterised in terms of the fundamental parameters, and analysed in detail.

Keywords: Allee effect, dispersal, migration speed, diffusion, invasion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1247

Authors: Y. Q. Chen, P. K. Wong, Z. C. Xie, H. W. Wu, K. U. Chan, J., L. Huang

Abstract:

It is believed that continuously variable transmission (CVT) will dominate the automotive transmissions in the future. The most popular design is Van Doorne-s CVT with single metal pushing V-belt. However, it is only applicable to low power passenger cars because its major limitation is low torque capacity. Therefore, this research studies a novel dual-belt CVT system to overcome the limitation of traditional single-belt CVT, such that it can be applicable to the heavy-duty vehicles. This paper presents the mathematical model of the design and its experimental verification. Experimental and simulated results show that the model developed is valid and the proposed dual-belt CVT can really overcome the traditional limitation of single-belt Van Doorne-s CVT.

Keywords: Analytical model, CVT, Dual belts, Torque capacity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2125

Authors: Mária Stachová, Lukáš Sobíšek

Abstract:

Data mining incorporates a group of statistical methods used to analyze a set of information, or a data set. It operates with models and algorithms, which are powerful tools with the great potential. They can help people to understand the patterns in certain chunk of information so it is obvious that the data mining tools have a wide area of applications. For example in the theoretical chemistry data mining tools can be used to predict moleculeproperties or improve computer-assisted drug design. Classification analysis is one of the major data mining methodologies. The aim of thecontribution is to create a classification model, which would be able to deal with a huge data set with high accuracy. For this purpose logistic regression, Bayesian logistic regression and random forest models were built using R software. TheBayesian logistic regression in Latent GOLD software was created as well. These classification methods belong to supervised learning methods. It was necessary to reduce data matrix dimension before construct models and thus the factor analysis (FA) was used. Those models were applied to predict the biological activity of molecules, potential new drug candidates.

Keywords: data mining, classification, drug design, QSAR

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2826

Authors: Chien-Jen Liu, Shu Ching Yang

Abstract:

Using the technology acceptance model (TAM), this study examined the external variables of technological complexity (TC) to acquire a better understanding of the factors that influence the acceptance of computer application courses by learners at Active Aging Universities. After the learners in this study had completed a 27-hour Facebook course, 44 learners responded to a modified TAM survey. Data were collected to examine the path relationships among the variables that influence the acceptance of Facebook-mediated community learning. The partial least squares (PLS) method was used to test the measurement and the structural model. The study results demonstrated that attitudes toward Facebook use directly influence behavioral intentions (BI) with respect to Facebook use, evincing a high prediction rate of 58.3%. In addition to the perceived usefulness (PU) and perceived ease of use (PEOU) measures that are proposed in the TAM, other external variables, such as TC, also indirectly influence BI. These four variables can explain 88% of the variance in BI and demonstrate a high level of predictive ability. Finally, limitations of this investigation and implications for further research are discussed.

Keywords: Technology acceptance model (TAM), technological complexity, partial least squares (PLS), perceived usefulness.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3163

Authors: Leonardo Juan Ramírez López, Javier Oswaldo Rodriguez Velasquez

Abstract:

We have designed a Holter that measures the heart´s activity for over 24 hours, implemented a prediction methodology, and generate alarms as well as indicators to patients and treating physicians. Various diagnostic advances have been developed in clinical cardiology thanks to Holter implementation; however, their interpretation has largely been conditioned to clinical analysis and measurements adjusted to diverse population characteristics, thus turning it into a subjective examination. This, however, requires vast population studies to be validated that, in turn, have not achieved the ultimate goal: mortality prediction. Given this context, our Insight Research Group developed a mathematical methodology that assesses cardiac dynamics through entropy and probability, creating a numerical and geometrical attractor which allows quantifying the normalcy of chronic and acute disease as well as the evolution between such states, and our Tigum Research Group developed a holter device with 12 channels and advanced computer software. This has been shown in different contexts with 100% sensitivity and specificity results.

Keywords: Entropy, mathematical, prediction, cardiac, holter, attractor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 679

Authors: Lambros V. Skarlas, Grigorios N. Beligiannis, Efstratios F. Georgopoulos, Adam V. Adamopoulos

Abstract:

The aim of this contribution is to present a new approach in modeling the electrical activity of the human heart. A recurrent artificial neural network is being used in order to exhibit a subset of the dynamics of the electrical behavior of the human heart. The proposed model can also be used, when integrated, as a diagnostic tool of the human heart system. What makes this approach unique is the fact that every model is being developed from physiological measurements of an individual. This kind of approach is very difficult to apply successfully in many modeling problems, because of the complexity and entropy of the free variables describing the complex system. Differences between the modeled variables and the variables of an individual, measured at specific moments, can be used for diagnostic purposes. The sensor fusion used in order to optimize the utilization of biomedical sensors is another point that this paper focuses on. Sensor fusion has been known for its advantages in applications such as control and diagnostics of mechanical and chemical processes.

Keywords: Artificial Neural Networks, Diagnostic System, Health Condition Modeling Tool, Heart Diagnostics Model, Heart Electricity Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1809

Authors: Ahmed Zaafouri, Mounir Sayadi, Farhat Fnaiech

Abstract:

In this paper, we present a method for edge segmentation of satellite images based on 2-D Phase Congruency (PC) model. The proposed approach is composed by two steps: The contextual non linear smoothing algorithm (CNLS) is used to smooth the input images. Then, the 2D stretched Gabor filter (S-G filter) based on proposed angular variation is developed in order to avoid the multiple responses in the previous work. An assessment of our proposed method performance is provided in terms of accuracy of satellite image edge segmentation. The proposed method is compared with others known approaches.

Keywords: Edge segmentation, Phase congruency model, Satellite images, Stretched Gabor filter

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2645

Authors: J. Geiser, R. Röhle

Abstract:

In this paper we present discretization and decomposition methods for a multi-component transport model of a chemical vapor deposition (CVD) process. CVD processes are used to manufacture deposition layers or bulk materials. In our transport model we simulate the deposition of thin layers. The microscopic model is based on the heavy particles, which are derived by approximately solving a linearized multicomponent Boltzmann equation. For the drift-process of the particles we propose diffusionreaction equations as well as for the effects of heat conduction. We concentrate on solving the diffusion-reaction equation with analytical and numerical methods. For the chemical processes, modelled with reaction equations, we propose decomposition methods and decouple the multi-component models to simpler systems of differential equations. In the numerical experiments we present the computational results of our proposed models.

Keywords: Chemical reactions, chemical vapor deposition, convection-diffusion-reaction equations, decomposition methods, multi-component transport.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1386

Authors: Victor Breux, Jérôme Boutet, Alain Goret, Viviane Cattin

Abstract:

Early detection of anomalies in data centers is important to reduce downtimes and the costs of periodic maintenance. However, there is little research on this topic and even fewer on the fusion of sensor data for the detection of abnormal events. The goal of this paper is to propose a method for anomaly detection in data centers by combining sensor data (temperature, humidity, power) and deep learning models. The model described in the paper uses one autoencoder per sensor to reconstruct the inputs. The auto-encoders contain Long-Short Term Memory (LSTM) layers and are trained using the normal samples of the relevant sensors selected by correlation analysis. The difference signal between the input and its reconstruction is then used to classify the samples using feature extraction and a random forest classifier. The data measured by the sensors of a data center between January 2019 and May 2020 are used to train the model, while the data between June 2020 and May 2021 are used to assess it. Performances of the model are assessed a posteriori through F1-score by comparing detected anomalies with the data center’s history. The proposed model outperforms the state-of-the-art reconstruction method, which uses only one autoencoder taking multivariate sequences and detects an anomaly with a threshold on the reconstruction error, with an F1-score of 83.60% compared to 24.16%.

Keywords: Anomaly detection, autoencoder, data centers, deep learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 703

Authors: Samuel A. Phillips, Emmanuel A. Ayanlowo, Rasaki O. Olanrewaju, Olayode Fatoki

Abstract:

This paper employs the Jeffrey's prior technique in the process of estimating the periodograms and frequency of sinusoidal model for unknown noisy time variants or oscillating events (data) in a Bayesian setting. The non-informative Jeffrey's prior was adopted for the posterior trigonometric function of the sinusoidal model such that Cramer-Rao Lower Bound (CRLB) inference was used in carving-out the minimum variance needed to curb the invariance structure effect for unknown noisy time observational and repeated circular patterns. An average monthly oscillating temperature series measured in degree Celsius (0C) from 1901 to 2014 was subjected to the posterior solution of the unknown noisy events of the sinusoidal model via Markov Chain Monte Carlo (MCMC). It was not only deduced that two minutes period is required before completing a cycle of changing temperature from one particular degree Celsius to another but also that the sinusoidal model via the CRLB-Jeffrey's prior for unknown noisy events produced a miniature posterior Maximum A Posteriori (MAP) compare to a known noisy events.

Keywords: Cramer-Rao Lower Bound (CRLB), Jeffrey's prior, Sinusoidal, Maximum A Posteriori (MAP), Markov Chain Monte Carlo (MCMC), Periodograms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 635

Authors: Changjin Xu

Abstract:

In this paper, applying frequency domain approach, a delayed predator-prey fishery model with prey reserve is investigated. By choosing the delay τ as a bifurcation parameter, It is found that Hopf bifurcation occurs as the bifurcation parameter τ passes a sequence of critical values. That is, a family of periodic solutions bifurcate from the equilibrium when the bifurcation parameter exceeds a critical value. The length of delay which preserves the stability of the positive equilibrium is calculated. Some numerical simulations are included to justify the theoretical analysis results. Finally, main conclusions are given.

Keywords: Predator-prey model, stability, Hopf bifurcation, frequency domain, Nyquist criterion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1388

Authors: M. H. Kargarnovin, A. Mamandi

Abstract:

This paper presents investigation effects of a sharp edged gust on aeroelastic behavior and time-domain response of a typical section model using Jones approximate aerodynamics for pure plunging motion. Flutter analysis has been done by using p and p-k methods developed for presented finite-state aerodynamic model for a typical section model (airfoil). Introduction of gust analysis as a linear set of ordinary differential equations in a simplified procedure has been carried out by using transformation into an eigenvalue problem.

Keywords: Aeroelastic response, jones approximation, pure plunging motion, sharp edged gust.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1865

Authors: Kari Björn, Mikael Soini

Abstract:

Higher Education system reforms, especially Finnish system of Universities of Applied Sciences in 2014 are discussed. The new steering model is based on major legislative changes, output-oriented funding and open information. The governmental steering reform, especially the financial model and the resulting institutional level responses, such as a curriculum reforms are discussed, focusing especially in engineering programs. The paper is motivated by management need to establish objective steering-related performance indicators and to apply them consistently across all educational programs. The close relationship to governmental steering and funding model imply that internally derived indicators can be directly applied. Metropolia University of Applied Sciences (MUAS) as a case institution is briefly introduced, focusing on engineering education in Information and Communications Technology (ICT), and its related programs. The reform forced consolidation of previously separate smaller programs into fewer units of student application. New curriculum ICT students have a common first year before they apply for a Major. A framework of parallel and longitudinal comparisons is introduced and used across Majors in two campuses. The new externally introduced performance criteria are applied internally on ICT Majors using data ex-ante and ex-post of program merger.  A comparative performance of the Majors after completion of joint first year is established, focusing on previously omitted Majors for completeness of analysis. Some new research questions resulting from transfer of Majors between campuses and quota setting are discussed. Practical orientation identifies best practices to share or targets needing most attention for improvement. This level of analysis is directly applicable at student group and teaching team level, where corrective actions are possible, when identified. The analysis is quantitative and the nature of the corrective actions are not discussed. Causal relationships and factor analysis are omitted, because campuses, their staff and various pedagogical implementation details contain still too many undetermined factors for our limited data. Such qualitative analysis is left for further research. Further study must, however, be guided by the relevance of the observations.

Keywords: Engineering education, integrated curriculum, learning outcomes, performance measurement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 866

Authors: Wimalin S. Laosiritaworn, Pongsak Holimchayachotikul

Abstract:

this article proposed a methodology for computer numerical control (CNC) machine scoring. The case study company is a manufacturer of hard disk drive parts in Thailand. In this company, sample of parts manufactured from CNC machine are usually taken randomly for quality inspection. These inspection data were used to make a decision to shut down the machine if it has tendency to produce parts that are out of specification. Large amount of data are produced in this process and data mining could be very useful technique in analyzing them. In this research, data mining techniques were used to construct a machine scoring model called 'machine priority assessment model (MPAM)'. This model helps to ensure that the machine with higher risk of producing defective parts be inspected before those with lower risk. If the defective prone machine is identified sooner, defective part and rework could be reduced hence improving the overall productivity. The results showed that the proposed method can be successfully implemented and approximately 351,000 baht of opportunity cost could have saved in the case study company.

Keywords: Computer Numerical Control, Data Mining, HardDisk Drive.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1377

Authors: R. Rajabpour, N. Talebbeydokhti, M. H. Ahmadi

Abstract:

Carefully scheduling the operations of pumps can be resulted to significant energy savings. Schedules can be defined either implicit, in terms of other elements of the network such as tank levels, or explicit by specifying the time during which each pump is on/off. In this study, two new explicit representations based on timecontrolled triggers were analyzed, where the maximum number of pump switches was established beforehand, and the schedule may contain fewer switches than the maximum. The optimal operation of pumping stations was determined using a Jumping Particle Swarm Optimization (JPSO) algorithm to achieve the minimum energy cost. The model integrates JPSO optimizer and EPANET hydraulic network solver. The optimal pump operation schedule of VanZyl water distribution system was determined using the proposed model and compared with those from Genetic and Ant Colony algorithms. The results indicate that the proposed model utilizing the JPSO algorithm is a versatile management model for the operation of realworld water distribution system.

Keywords: JPSO, operation, optimization, water distribution system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2024

Authors: F. Alborzi, H. Vafaei, M.H. Gholami, M.M. S. Esfahani

Abstract:

In this article, the design of a Supply Chain Network (SCN) consisting of several suppliers, production plants, distribution centers and retailers, is considered. Demands of retailers are considered stochastic parameters, so we generate amounts of data via simulation to extract a few demand scenarios. Then a mixed integer two-stage programming model is developed to optimize simultaneously two objectives: (1) minimization the fixed and variable cost, (2) maximization the service level. A weighting method is utilized to solve this two objective problem and a numerical example is made to show the performance of the model.

Keywords: Mixed Integer Programming, Multi-objective Optimization, Stochastic Demand, Supply Chain Design, Two Stage Programming

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2304