Search results for: analytical network design model

Authors: S. P. Sharma, Som Nath Saha

Abstract:

This paper deals with the analytical investigation of thermal and thermohydraulic performance of double flow solar air heaters with corrugated and flat plate absorber. A mathematical model of double flow solar air heater has been presented, and a computer program in C⁺⁺ language is developed to estimate the outlet temperature of air for the evaluation of thermal and thermohydraulic efficiency by solving the governing equations numerically using relevant correlations for heat transfer coefficients. The results obtained from the mathematical model is compared with the available experimental results and it is found to be reasonably good. The results show that the double flow solar air heaters have higher efficiency than conventional solar air heater, although the double flow corrugated absorber is superior to that of flat plate double flow solar air heater. It is also observed that the thermal efficiency increases with increase in mass flow rate; however, thermohydraulic efficiency increases with increase in mass flow rate up to a certain limit, attains the maximum value, then thereafter decreases sharply.

Keywords: corrugated absorber, double flow, solar air heater, thermos-hydraulic efficiency

Procedia PDF Downloads 314

Authors: Pascal Mwenge, Jefrey Pilusa, Tumisang Seodigeng

Abstract:

The current study investigated the effect of catalyst ratio and methanol to oil ratio on biodiesel production by using central composite design. Biodiesel was produced by transesterification using sodium hydroxide as a homogeneous catalyst, a laboratory scale reactor consisting of flat bottom flask mounts with a reflux condenser, and a heating plate was used to produce biodiesel. Key parameters, including time, temperature, and mixing rate was kept constant at 60 minutes, 60 ^oC and 600 RPM, respectively. From the results obtained, it was observed that the biodiesel yield depends on catalyst ratio and methanol to oil ratio. The highest yield of 50.65% was obtained at catalyst ratio of 0.5 wt.% and methanol to oil mole ratio 10.5. The analysis of variances of biodiesel yield showed the R Squared value of 0.8387. A quadratic mathematical model was developed to predict the biodiesel yield in the specified parameters ranges.

Keywords: ANOVA, biodiesel, catalyst, transesterification, central composite design

Procedia PDF Downloads 152

Authors: Bououden Soraya

Abstract:

This paper aims to study the existence of the change of coordinates which permits to transform a class of nonlinear dynamical systems into the so-called nonlinear observer canonical form (NOCF). Moreover, an algorithm to construct such a change of coordinates is given. Based on this form, we can design an observer with a linear error dynamic. This enables us to estimate the state of a nonlinear dynamical system. A concrete example (biological model) is provided to illustrate the feasibility of the proposed results.

Keywords: nonlinear observer canonical form, observer, design, gene regulation, gene expression

Procedia PDF Downloads 432

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 284

Authors: Hassan El Ghazi, Mohammed El Jourmi, Tayeb Sadiki, Esmail Ahouzi

Abstract:

The purpose of this paper is to model and analyze a geostationary satellite communication system based on VSAT network and Multicarrier CDMA system scheme which presents a combination of multicarrier modulation scheme and CDMA concepts. In this study the channel coding strategies (Turbo codes and LDPC codes) are adopted to achieve good performance due to iterative decoding. The envisaged system is examined for a transmission over Multipath channel with use of Ku band in the uplink case. The simulation results are obtained for each different case. The performance of the system is given in terms of Bit Error Rate (BER) and energy per bit to noise power spectral density ratio (Eb/N0). The performance results of designed system shown that the communication system coded with LDPC codes can achieve better error rate performance compared to VSAT MC-CDMA system coded with Turbo codes.

Keywords: satellite communication, VSAT Network, MC-CDMA, LDPC codes, turbo codes, uplink

Procedia PDF Downloads 504

Authors: Lela Mirtskhulava, Mariam Khunjgurua, Nino Lomineishvili, Koba Bakuria

Abstract:

Software reliability prediction gives a great opportunity to measure the software failure rate at any point throughout system test. A software reliability prediction model provides with the technique for improving reliability. Software reliability is very important factor for estimating overall system reliability, which depends on the individual component reliabilities. It differs from hardware reliability in that it reflects the design perfection. Main reason of software reliability problems is high complexity of software. Various approaches can be used to improve the reliability of software. We focus on software reliability model in this article, assuming that there is a time redundancy, the value of which (the number of repeated transmission of basic blocks) can be an optimization parameter. We consider given mathematical model in the assumption that in the system may occur not only irreversible failures, but also a failure that can be taken as self-repairing failures that significantly affect the reliability and accuracy of information transfer. Main task of the given paper is to find a time distribution function (DF) of instructions sequence transmission, which consists of random number of basic blocks. We consider the system software unreliable; the time between adjacent failures has exponential distribution.

Keywords: exponential distribution, conditional mean time to failure, distribution function, mathematical model, software reliability

Procedia PDF Downloads 464

Authors: Olivia Borgue, Massimo Panarotto, Ola Isaksson

Abstract:

This article presents a neural networks-based strategy for reducing the need for support structures when designing for additive manufacturing (AM). Additive manufacturing is a relatively new and immature industrial technology, and the information to make confident decisions when designing for AM is limited. This lack of information impacts especially the early stages of engineering design, for instance, it is difficult to actively consider the support structures needed for manufacturing a part. This difficulty is related to the challenge of designing a product geometry accounting for customer requirements, manufacturing constraints and minimization of support structure. The approach presented in this article proposes an automatized geometry modification technique for reducing the use of the support structures while designing for AM. This strategy starts with a neural network-based strategy for shape recognition to achieve product classification, using an STL file of the product as input. Based on the classification, an automatic part geometry modification based on MATLAB© is implemented. At the end of the process, the strategy presents different geometry modification alternatives depending on the type of product to be designed. The geometry alternatives are then evaluated adopting a QFD-like decision support tool.

Keywords: additive manufacturing, engineering design, geometry modification optimization, neural networks

Procedia PDF Downloads 253

Authors: Vassilis C. Moulianitis, Evgenios Scourboutis, Ilias Katsanis, Paraskevas Papanikos, Nikolas Zacharopoulos

Abstract:

This paper presents the conceptual design of an automated biomethane potential measurement system. First, the design specifications for the BMP system and the basic components of the system will be presented. Three concepts that meet the design specifications will be presented. The basic characteristics of each concept will be analyzed in detail. The concepts will be evaluated using a set of design criteria that includes flexibility, cost, size, complexity, aesthetics, and accessibility in order to determine the best solution. The evaluation will be based on the discrete Choquet integral.

Keywords: automated biomethane test, conceptual mechatronics design, concept evaluation, Choquet integral

Procedia PDF Downloads 94

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

Neural network approaches are machine learning methods used in many domains, such as healthcare and cyber security. Neural networks are mostly known for dealing with image datasets. While training with the images, several fundamental mathematical operations are carried out in the Neural Network. The operation includes a number of algebraic and mathematical functions, including derivative, convolution, and matrix inversion and transposition. Such operations require higher processing power than is typically needed for computer usage. Central Processing Unit (CPU) is not appropriate for a large image size of the dataset as it is built with serial processing. While Graphics Processing Unit (GPU) has parallel processing capabilities and, therefore, has higher speed. This paper uses advanced Neural Network techniques such as VGG16, Resnet50, Densenet, Inceptionv3, Xception, Mobilenet, XGBOOST-VGG16, and our proposed models to compare CPU and GPU resources. A system for classifying autism disease using face images of an autistic and non-autistic child was used to compare performance during testing. We used evaluation matrices such as Accuracy, F1 score, Precision, Recall, and Execution time. It has been observed that GPU runs faster than the CPU in all tests performed. Moreover, the performance of the Neural Network models in terms of accuracy increases on GPU compared to CPU.

Keywords: autism disease, neural network, CPU, GPU, transfer learning

Procedia PDF Downloads 118

Authors: Yasser F. Hassan

Abstract:

The reduction or removal of noise in a color image is an essential part of image processing, whether the final information is used for human perception or for an automatic inspection and analysis. This paper describes the modeling system based on the rough neural network model to adaptive cellular automata for various image processing tasks and noise remover. In this paper, we consider the problem of object processing in colored image using rough neural networks to help deriving the rules which will be used in cellular automata for noise image. The proposed method is compared with some classical and recent methods. The results demonstrate that the new model is capable of being trained to perform many different tasks, and that the quality of these results is comparable or better than established specialized algorithms.

Keywords: rough sets, rough neural networks, cellular automata, image processing

Procedia PDF Downloads 439

Authors: Leah Ning

Abstract:

This paper discusses the development of a machine learning algorithm that accurately detects metastatic breast cancer (cancer has spread elsewhere from its origin part) in selected images that come from pathology scans of lymph node sections. Being able to develop an accurate artificial intelligence (AI) algorithm would help significantly in breast cancer diagnosis since manual examination of lymph node scans is both tedious and oftentimes highly subjective. The usage of AI in the diagnosis process provides a much more straightforward, reliable, and efficient method for medical professionals and would enable faster diagnosis and, therefore, more immediate treatment. The overall approach used was to train a convolution neural network (CNN) based on a set of pathology scan data and use the trained model to binarily classify if a new scan were benign or malignant, outputting a 0 or a 1, respectively. The final model’s prediction accuracy is very high, with 100% for the train set and over 70% for the test set. Being able to have such high accuracy using an AI model is monumental in regard to medical pathology and cancer detection. Having AI as a new tool capable of quick detection will significantly help medical professionals and patients suffering from cancer.

Keywords: breast cancer detection, AI, machine learning, algorithm

Procedia PDF Downloads 91

Authors: Ariba Siddiqui, Amber Khan

Abstract:

The need for bio-implantable devices in the field of medical sciences has been increasing day by day; however, the charging of these devices is a major issue. Batteries, a very common method of powering the implants, have a limited lifetime and bulky nature. Therefore, as a replacement of batteries, acoustic power transfer (APT) technology is being accepted as the most suitable technique to wirelessly power the medical implants in the present scenario. The basic model of APT consists of piezoelectric transducers that work on the principle of converse piezoelectric effect at the transmitting end and direct piezoelectric effect at the receiving end. This paper provides mechanistic insight into the parameters affecting the design and efficient working of acoustic power transfer systems. The optimum design considerations have been presented that will help to compress the size of the device and augment the intensity of the pressure wave. A COMSOL model of the PZT (Lead Zirconate Titanate) transducer was developed. The model was simulated and analyzed on a frequency spectrum. The simulation results displayed that the efficiency of these devices is strongly dependent on the frequency of operation, and a wrong choice of the operating frequency leads to the high absorption of acoustic field inside the tissue (medium), poor power strength, and heavy transducers, which in effect influence the overall configuration of the acoustic systems. Considering all the tradeoffs, the simulations were performed again by determining an optimum frequency (900 kHz) that resulted in the reduction of the transducer's thickness to 1.96 mm and augmented the power strength with an intensity of 432 W/m². Thus, the results obtained after the second simulation contribute to lesser attenuation, lightweight systems, high power intensity, and also comply with safety limits provided by the U.S Food and Drug Administration (FDA). It was also found that the chosen operating frequency enhances the directivity of the acoustic wave at the receiver side.

Keywords: acoustic power, bio-implantable, COMSOL, Lead Zirconate Titanate, piezoelectric, transducer

Procedia PDF Downloads 174

Authors: Alisher Ibragimov, Sofya Senotrusova, Aleksandra Beliaeva, Egor Ushakov, Yuri Markin

Abstract:

Mammography plays a critical role in screening for breast cancer in women, and artificial intelligence has enabled the automatic detection of diseases in medical images. Many of the current techniques used for mammogram analysis focus on a single view (mediolateral or craniocaudal view), while in clinical practice, radiologists consider multiple views of mammograms from both breasts to make a correct decision. Consequently, computer-aided diagnosis (CAD) systems could benefit from incorporating information gathered from multiple views. In this study, the introduce a method based on a Siamese neural network (SNN) model that simultaneously analyzes mammographic images from tri-view: bilateral and ipsilateral. In this way, when a decision is made on a single image of one breast, attention is also paid to two other images – a view of the same breast in a different projection and an image of the other breast as well. Consequently, the algorithm closely mimics the radiologist's practice of paying attention to the entire examination of a patient rather than to a single image. Additionally, to the best of our knowledge, this research represents the first experiments conducted using the recently released Vietnamese dataset of digital mammography (VinDr-Mammo). On an independent test set of images from this dataset, the best model achieved an AUC of 0.87 per image. Therefore, this suggests that there is a valuable automated second opinion in the interpretation of mammograms and breast cancer diagnosis, which in the future may help to alleviate the burden on radiologists and serve as an additional layer of verification.

Keywords: breast cancer, computer-aided diagnosis, deep learning, multi-view mammogram, siamese neural network

Procedia PDF Downloads 138

Authors: W. Assaad, D. Wilmink, H. R. Pasaribu, H. J. M. Geijselaers

Abstract:

Shell has developed a mono-diameter well concept for oil and gas wells as opposed to the traditional telescopic well design. A Mono-diameter well design allows well to have a single inner diameter from the surface all the way down to reservoir to increase production capacity, reduce material cost and reduce environmental footprint. This is achieved by expansion of liners (casing string) concerned using an expansion tool (e.g. a cone). Since the well is drilled in stages and liners are inserted to support the borehole, overlap sections between consecutive liners exist which should be expanded. At overlap, the previously inserted casing which can be expanded or unexpanded is called the host casing and the newly inserted casing is called the expandable casing. When the cone enters the overlap section, an expandable casing is expanded against a host casing, a cured cement layer and formation. In overlap expansion, ironing or lengthening may appear instead of shortening in the expandable casing when the pressure exerted by the host casing, cured cement layer and formation exceeds a certain limit. This pressure is related to cement strength, thickness of cement layer, host casing material mechanical properties, host casing thickness, formation type and formation strength. Ironing can cause implications that hinder the deployment of the technology. Therefore, the understanding of ironing becomes essential. A physical model is built in-house to calculate expansion forces, stresses, strains and post expansion casing dimensions under different conditions. In this study, only free casing and overlap expansion of two casings are addressed while the cement and formation will be incorporated in future study. Since the axial strain can be predicted by the physical model, the onset of ironing can be confirmed. In addition, this model helps in understanding ironing and the parameters influencing it. Finally, the physical model is validated with Finite Element (FE) simulations and small-scale experiments. The results of the study confirm that high pressure leads to ironing when the casing is expanded in tension mode.

Keywords: casing expansion, cement, formation, metal forming, plasticity, well design

Procedia PDF Downloads 180

Authors: Apidet Booranawong, Wiklom Teerapabkajorndet

Abstract:

An enhanced ad-hoc on-demand distance vector routing (E-AODV) protocol for control system applications in wireless sensor and actuator networks (WSANs) is proposed. Our routing algorithm is designed by considering both wireless network communication and the control system aspects. Control system error and network delay are the main selection criteria in our routing protocol. The control and communication performance is evaluated on multi-hop IEEE 802.15.4 networks for building-temperature control systems. The Gilbert-Elliott error model is employed to simulate packet loss in wireless networks. The simulation results demonstrate that the E-AODV routing approach can significantly improve the communication performance better than an original AODV routing under various packet loss rates. However, the control performance result by our approach is not much improved compared with the AODV routing solution.

Keywords: WSANs, building temperature control, AODV routing protocol, control system error, settling time, delay, delivery ratio

Procedia PDF Downloads 339

Authors: Despoina Mouratidis, Katia Lida Kermanidis

Abstract:

Machine translation (MT) is a very important task in Natural Language Processing (NLP). MT evaluation is crucial in MT development, as it constitutes the means to assess the success of an MT system, and also helps improve its performance. Several methods have been proposed for the evaluation of (MT) systems. Some of the most popular ones in automatic MT evaluation are score-based, such as the BLEU score, and others are based on lexical similarity or syntactic similarity between the MT outputs and the reference involving higher-level information like part of speech tagging (POS). This paper presents a language-independent machine learning framework for classifying pairwise translations. This framework uses vector representations of two machine-produced translations, one from a statistical machine translation model (SMT) and one from a neural machine translation model (NMT). The vector representations consist of automatically extracted word embeddings and string-like language-independent features. These vector representations used as an input to a multi-layer neural network (NN) that models the similarity between each MT output and the reference, as well as between the two MT outputs. To evaluate the proposed approach, a professional translation and a "ground-truth" annotation are used. The parallel corpora used are English-Greek (EN-GR) and English-Italian (EN-IT), in the educational domain and of informal genres (video lecture subtitles, course forum text, etc.) that are difficult to be reliably translated. They have tested three basic deep learning (DL) architectures to this schema: (i) fully-connected dense, (ii) Convolutional Neural Network (CNN), and (iii) Long Short-Term Memory (LSTM). Experiments show that all tested architectures achieved better results when compared against those of some of the well-known basic approaches, such as Random Forest (RF) and Support Vector Machine (SVM). Better accuracy results are obtained when LSTM layers are used in our schema. In terms of a balance between the results, better accuracy results are obtained when dense layers are used. The reason for this is that the model correctly classifies more sentences of the minority class (SMT). For a more integrated analysis of the accuracy results, a qualitative linguistic analysis is carried out. In this context, problems have been identified about some figures of speech, as the metaphors, or about certain linguistic phenomena, such as per etymology: paronyms. It is quite interesting to find out why all the classifiers led to worse accuracy results in Italian as compared to Greek, taking into account that the linguistic features employed are language independent.

Keywords: machine learning, machine translation evaluation, neural network architecture, pairwise classification

Procedia PDF Downloads 132

Authors: Ikra Khan, Reenu Singh

Abstract:

Composition is essential when designing the interiors of residential spaces. The ability to adopt a unique style of using design principles and design elements is another. This research report explores how the visual aesthetic within a space is achieved through the use of design principles and design elements while maintaining a signature style. It also observes the relationship between design styles and compositions that are achieved as a result of the implementation of the principles. Information collected from books and the internet helped to understand how a composition can be achieved in residential interiors by resorting to design principles and design elements as tools for achieving an aesthetic composition. It also helped determine the results of authentic representation of design ideas and how they make one’s work exceptional. A questionnaire survey was also conducted to understand the impact of a visually aesthetic residential interior of a signature style on the lifestyle of individuals residing in them. The findings denote a pattern in the application of design principles and design elements. Individual principles and elements or a combination of the same are used to achieve an aesthetically pleasing composition. This was supported by creating CAD illustrations of two different residential projects with varying approaches and design styles. These illustrations include mood boards, 3D models, and sectional elevations as rendered views to understand the concept design and its translation via these mediums. A direct relation is observed between the application of design principles and design elements to achieve visually aesthetic residential interiors that suit an individual’s taste. These practices can be applied when designing bespoke commercial as well as industrial interiors that are suited to specific aesthetic and functional needs.

Keywords: composition, design principles, elements, interiors, residential spaces

Procedia PDF Downloads 103

Authors: Aarthi Sridhar, Henri Gavin, Karah Kelly

Abstract:

Rolling Isolation Systems (RISs) are simple and effective means to mitigate earthquake hazards to equipment in critical and precious facilities, such as hospitals, network collocation facilities, supercomputer centers, and museums. The RIS works by isolating components acceleration the inertial forces felt by the subsystem. The RIS consists of two platforms with counter-facing concave surfaces (dishes) in each corner. Steel balls lie inside the dishes and allow the relative motion between the top and bottom platform. Formerly, a mathematical model for the dynamics of RISs was developed using Lagrange’s equations (LE) and experimentally validated. A new mathematical model was developed using Gauss’s Principle of Least Constraint (GPLC) and verified by comparing impulse response trajectories of the GPLC model and the LE model in terms of the peak displacements and accelerations of the top platform. Mathematical models for the RIS are tedious to derive because of the non-holonomic rolling constraints imposed on the system. However, using Gauss’s Principle of Least constraint to find the equations of motion removes some of the obscurity and yields a system that can be easily extended. Though the GPLC model requires more state variables, the equations of motion are far simpler. The non-holonomic constraint is enforced in terms of accelerations and therefore requires additional constraint stabilization methods in order to avoid the possibility that numerical integration methods can cause the system to go unstable. The GPLC model allows the incorporation of more physical aspects related to the RIS, such as contribution of the vertical velocity of the platform to the kinetic energy and the mass of the balls. This mathematical model for the RIS is a tool to predict the motion of the isolation platform. The ability to statistically quantify the expected responses of the RIS is critical in the implementation of earthquake hazard mitigation.

Keywords: earthquake hazard mitigation, earthquake isolation, Gauss’s Principle of Least Constraint, nonlinear dynamics, rolling isolation system

Procedia PDF Downloads 250

Authors: Aishwarya Shekhar, Devesh Kumar Srivastava

Abstract:

Cloud computing has emerged as a promising direction for cost efficient and reliable service delivery across data communication networks. The dynamic location of service facilities and the virtualization of hardware and software elements are stressing the communication networks and protocols, especially when data centres are interconnected through the internet. Although the computing aspects of cloud technologies have been largely investigated, lower attention has been devoted to the networking services without involving IT operating overhead. Cloud computing has enabled elastic and transparent access to infrastructure services without involving IT operating overhead. Virtualization has been a key enabler for cloud computing. While resource virtualization and service abstraction have been widely investigated, networking in cloud remains a difficult puzzle. Even though network has significant role in facilitating hybrid cloud scenarios, it hasn't received much attention in research community until recently. We propose Network as a Service (NaaS), which forms the basis of unifying public and private clouds. In this paper, we identify various challenges in adoption of hybrid cloud. We discuss the design and implementation of a cloud platform.

Keywords: cloud computing, networking, infrastructure, hybrid cloud, open stack, naas

Procedia PDF Downloads 427

Authors: Chi Wu, Dean Wu, Wen-Te Liu, Cheng-Yu Tsai, Shin-Mei Hsu, Yin-Tzu Lin, Ru-Yin Yang

Abstract:

Background: The results of previous studies compared the benefits and risks of receiving insomnia medication. However, the effects between hypnotic drugs used and enhancement of sleep quality were still unclear. Objective: The aim of this study is to establish a prediction model for hypnotic drugs' dosage used for insomnia subjects and associated the relationship between sleep stage ratio change and drug types. Methodologies: According to American Academy of Sleep Medicine (AASM) guideline, sleep stages were classified and transformed to hypnogram via the polysomnography (PSG) in a hospital in New Taipei City (Taiwan). The subjects with diagnosis for insomnia without receiving hypnotic drugs treatment were be set as the comparison group. Conversely, hypnotic drugs dosage within the past three months was obtained from the clinical registration for each subject. Furthermore, the collecting subjects were divided into two groups for training and testing. After training convolution neuron network (CNN) to predict types of hypnotics used and dosages are taken, the test group was used to evaluate the accuracy of classification. Results: We recruited 76 subjects in this study, who had been done PSG for transforming hypnogram from their sleep stages. The accuracy of dosages obtained from confusion matrix on the test group by CNN is 81.94%, and accuracy of hypnotic drug types used is 74.22%. Moreover, the subjects with high ratio of wake stage were correctly classified as requiring medical treatment. Conclusion: CNN with hypnogram was potentially used for adjusting the dosage of hypnotic drugs and providing subjects to pre-screening the types of hypnotic drugs taken.

Keywords: convolution neuron network, hypnotic drugs, insomnia, polysomnography

Procedia PDF Downloads 195

Authors: Avi Harel

Abstract:

Most accidents are commonly attributed in hindsight to human errors, yet most methodologies for safety focus on technical issues. According to the Black Swan theory, this paradox is due to insufficient data about the ways systems fail. The article presents a study of the sources of errors, and proposes a methodology for utility-oriented design, comprising methods for coping with each of the sources identified. Accident analysis indicates that errors typically result from difficulties of operating in exceptional conditions. Therefore, following STAMP, the focus should be on preventing exceptions. Exception analysis indicates that typically they involve an improper account of the operational scenario, due to deficiencies in the system integration. The methodology proposes a model, which is a formal definition of the system operation, as well as principles and guidelines for safety-oriented system integration. The article calls to develop and integrate tools for recording and analysis of the system activity during the operation, required to implement validate the model.

Keywords: accidents, complexity, errors, exceptions, interaction, modeling, resilience, risks

Procedia PDF Downloads 196

Authors: Ruvaitha Banu, Amaladhithyan Krishnamoorthy

Abstract:

IoT networks today solve various consumer problems, from home automation systems to aiding in driving autonomous vehicles with the exploration of multiple devices. For example, in an autonomous vehicle environment, multiple sensors are available on roads to monitor weather and road conditions and interact with each other to aid the vehicle in reaching its destination safely and timely. IoT systems are predominantly dependent on the cloud environment for data storage, and computing needs that result in latency problems. With the advent of Fog networks, some of this storage and computing is pushed to the edge/fog nodes, saving the network bandwidth and reducing the latency proportionally. Managing the data stored in these fog nodes becomes crucial as it might also store sensitive information required for a certain application. Data management in fog nodes is strenuous because Fog networks are dynamic in terms of their availability and hardware capability. It becomes more challenging when the nodes in the network also live a short span, detaching and joining frequently. When an end-user or Fog Node wants to access, read, or write data stored in another Fog Node, then a new protocol becomes necessary to access/manage the data stored in the fog devices as a conventional static way of managing the data doesn’t work in Fog Networks. The proposed solution discusses a protocol that acts by defining sensitivity levels for the data being written and read. Additionally, a distinct data distribution and replication model among the Fog nodes is established to decentralize the access mechanism. In this paper, the proposed model implements stewardship towards the data stored in the Fog node using the application of Reinforcement Learning so that access to the data is determined dynamically based on the requests.

Keywords: IoT, fog networks, data stewardship, dynamic access policy

Procedia PDF Downloads 59

Authors: Kyu Jin Kim, Byung Kwan Oh, Hyo Seon Park

Abstract:

The seismic responses-based structural health monitoring system has been performed to reduce seismic damage. The inter-story drift ratio which is the major index of the seismic capacity assessment is employed for estimating the seismic damage of buildings. Meanwhile, seismic response analysis to estimate the structural responses of building demands significantly high computational cost due to increasing number of high-rise and large buildings. To estimate the inter-story drift ratio of buildings from the earthquake efficiently, this paper suggests the estimation method of inter-story drift for buildings using an artificial neural network (ANN). In the method, the radial basis function neural network (RBFNN) is integrated with optimization algorithm to optimize the variable through evolutionary learning that refers to evolutionary radial basis function neural network (ERBFNN). The estimation method estimates the inter-story drift without seismic response analysis when the new earthquakes are subjected to buildings. The effectiveness of the estimation method is verified through a simulation using multi-degree of freedom system.

Keywords: structural health monitoring, inter-story drift ratio, artificial neural network, radial basis function neural network, genetic algorithm

Procedia PDF Downloads 327

Authors: Dana Alghool, Tarek ElMekkawy, Mohamed Haouari, Adel Elomari

Abstract:

District cooling systems have captured the attentions of many researchers recently due to the enormous benefits offered by such system in comparison with traditional cooling technologies. It is considered a major component of urban cities due to the significant reduction of energy consumption. This paper aims to find the optimal design and operation of district cooling systems by developing a mixed integer linear programming model to minimize the annual total system cost and satisfy the end-user cooling demand. The proposed model is experimented with different cooling demand scenarios. The results of the very high cooling demand scenario are only presented in this paper. A sensitivity analysis on different parameters of the model was performed.

Keywords: Annual Cooling Demand, Compression Chiller, Mathematical Modeling, District Cooling Systems, Optimization

Procedia PDF Downloads 202

Authors: K. C. Tanuja, Mamatha P. Raj

Abstract:

Urbanisation is happening rapidly all over the world. As population increasing in the urban settlements, its required to provide quality of life to all the inhabitants who live in. Urban design is a place making strategic planning. Urban design principles promote visualising any place environmentally, socially and economically viable. Urban design strategies include building mass, transit development, economic viability and sustenance and social aspects.

Keywords: livable streets, social interaction, pedestrian use, urban design

Procedia PDF Downloads 234

Authors: Petra Gergelova, Sofia Ioannidou, Davide Arcella, Alexandra Tard, Polly E. Boon, Oliver Lindtner, Christina Tlustos, Jean-Charles Leblanc

Abstract:

Objectives: To assess chronic dietary exposure to food additives in different European countries and population groups. Method and Design: The European Food Safety Authority’s (EFSA) Panel on Food Additives and Nutrient Sources added to Food (ANS) estimates chronic dietary exposure to food additives with the purpose of re-evaluating food additives that were previously authorized in Europe. For this, EFSA uses concentration values (usage and/or analytical occurrence data) reported through regular public calls for data by food industry and European countries. These are combined, at individual level, with national food consumption data from the EFSA Comprehensive European Food Consumption Database including data from 33 dietary surveys from 19 European countries and considering six different population groups (infants, toddlers, children, adolescents, adults and the elderly). EFSA ANS Panel estimates dietary exposure for each individual in the EFSA Comprehensive Database by combining the occurrence levels per food group with their corresponding consumption amount per kg body weight. An individual average exposure per day is calculated, resulting in distributions of individual exposures per survey and population group. Based on these distributions, the average and 95th percentile of exposure is calculated per survey and per population group. Dietary exposure is assessed based on two different sets of data: (a) Maximum permitted levels (MPLs) of use set down in the EU legislation (defined as regulatory maximum level exposure assessment scenario) and (b) usage levels and/or analytical occurrence data (defined as refined exposure assessment scenario). The refined exposure assessment scenario is sub-divided into the brand-loyal consumer scenario and the non-brand-loyal consumer scenario. For the brand-loyal consumer scenario, the consumer is considered to be exposed on long-term basis to the highest reported usage/analytical level for one food group, and at the mean level for the remaining food groups. For the non-brand-loyal consumer scenario, the consumer is considered to be exposed on long-term basis to the mean reported usage/analytical level for all food groups. An additional exposure from sources other than direct addition of food additives (i.e. natural presence, contaminants, and carriers of food additives) is also estimated, as appropriate. Results: Since 2014, this methodology has been applied in about 30 food additive exposure assessments conducted as part of scientific opinions of the EFSA ANS Panel. For example, under the non-brand-loyal scenario, the highest 95th percentile of exposure to α-tocopherol (E 307) and ammonium phosphatides (E 442) was estimated in toddlers up to 5.9 and 8.7 mg/kg body weight/day, respectively. The same estimates under the brand-loyal scenario in toddlers resulted in exposures of 8.1 and 20.7 mg/kg body weight/day, respectively. For the regulatory maximum level exposure assessment scenario, the highest 95th percentile of exposure to α-tocopherol (E 307) and ammonium phosphatides (E 442) was estimated in toddlers up to 11.9 and 30.3 mg/kg body weight/day, respectively. Conclusions: Detailed and up-to-date information on food additive concentration values (usage and/or analytical occurrence data) and food consumption data enable the assessment of chronic dietary exposure to food additives to more realistic levels.

Keywords: α-tocopherol, ammonium phosphatides, dietary exposure assessment, European Food Safety Authority, food additives, food consumption data

Procedia PDF Downloads 325

Authors: Amani Tahat, Serdal Kirmizialtin

Abstract:

Trajectory fragment methods such as Markov State Models (MSM), Milestoning (MS) and Transition Path sampling are the prime choice of extending the timescale of all atom Molecular Dynamics simulations. In these approaches, a set of structures that covers the accessible phase space has to be chosen a priori using cluster analysis. Structural clustering serves to partition the conformational state into natural subgroups based on their similarity, an essential statistical methodology that is used for analyzing numerous sets of empirical data produced by Molecular Dynamics (MD) simulations. Local transition kernel among these clusters later used to connect the metastable states using a Markovian kinetic model in MSM and a non-Markovian model in MS. The choice of clustering approach in constructing such kernel is crucial since the high dimensionality of the biomolecular structures might easily confuse the identification of clusters when using the traditional hierarchical clustering methodology. Of particular interest, in the case of MS where the milestones are very close to each other, accurate determination of the milestone identity of the trajectory becomes a challenging issue. Throughout this work we present two cluster analysis methods applied to the cis–trans isomerism of dinucleotide AA. The choice of nucleic acids to commonly used proteins to study the cluster analysis is two fold: i) the energy landscape is rugged; hence transitions are more complex, enabling a more realistic model to study conformational transitions, ii) Nucleic acids conformational space is high dimensional. A diverse set of internal coordinates is necessary to describe the metastable states in nucleic acids, posing a challenge in studying the conformational transitions. Herein, we need improved clustering methods that accurately identify the AA structure in its metastable states in a robust way for a wide range of confused data conditions. The single linkage approach of the hierarchical clustering available in GROMACS MD-package is the first clustering methodology applied to our data. Self Organizing Map (SOM) neural network, that also known as a Kohonen network, is the second data clustering methodology. The performance comparison of the neural network as well as hierarchical clustering method is studied by means of computing the mean first passage times for the cis-trans conformational rates. Our hope is that this study provides insight into the complexities and need in determining the appropriate clustering algorithm for kinetic analysis. Our results can improve the effectiveness of decisions based on clustering confused empirical data in studying conformational transitions in biomolecules.

Keywords: milestoning, self organizing map, single linkage, structure clustering

Procedia PDF Downloads 224

Authors: Javier Fernandez De Canete, Alvaro Fernandez-Quintero

Abstract:

Nowadays, adaptive control schemes are being used when model based control schemes are applied in presence of uncertainty and model mismatches. Artificial neural networks have been employed both in modelling and control of non-linear dynamic systems with unknown dynamics. In fact, these are powerful tools to solve this control problem when only input-output operational data are available. A neural network controller under SIMULINK together with the ARDUINO hardware platform has been used to perform real-time speed control of a computer case fan. Comparison of performance with a PID controller has also been presented in order to show the efficacy of neural control under different command signals tracking and also when disturbance signals are present in the speed control loops.

Keywords: neural networks, ARDUINO platform, SIMULINK, adaptive speed control

Procedia PDF Downloads 363

Authors: Zhiguo Shi, Cheng Ning Loong, Jiazeng Shan, Weichao Wu

Abstract:

This study proposes an equivalent circuit model to simulate the eddy current damping force with shaking table tests and finite element modeling. The model is firstly proposed and applied to a simple eddy current damper, which is modelled in ANSYS, indicating that the proposed model can simulate the eddy current damping force under different types of excitations. Then, a non-contact and friction-free eddy current damper is designed and tested, and the proposed model can reproduce the experimental observations. The excellent agreement between the simulated results and the experimental data validates the accuracy and reliability of the equivalent circuit model. Furthermore, a more complicated model is performed in ANSYS to verify the feasibility of the equivalent circuit model in complex eddy current damper, and the higher-order fractional model and viscous model are adopted for comparison.

Keywords: equivalent circuit model, eddy current damping, finite element model, shake table test

Procedia PDF Downloads 191

Authors: Chung-Ming Lo, Kevin Li-Chun Hsieh

Abstract:

The central nervous system in the World Health Organization defines grade 2, 3, 4 gliomas according to the aggressiveness. For brain tumors, using image examination would have a lower risk than biopsy. Besides, it is a challenge to extract relevant tissues from biopsy operation. Observing the whole tumor structure and composition can provide a more objective assessment. This study further proposed a computer-aided diagnosis (CAD) system based on a convolutional neural network to quantitatively evaluate a tumor's malignancy from brain magnetic resonance imaging. A total of 30 grade 2, 43 grade 3, and 57 grade 4 gliomas were collected in the experiment. Transferred parameters from AlexNet were fine-tuned to classify the target brain tumors and achieved an accuracy of 98% and an area under the receiver operating characteristics curve (Az) of 0.99. Without pre-trained features, only 61% of accuracy was obtained. The proposed convolutional neural network can accurately and efficiently classify grade 2, 3, and 4 gliomas. The promising accuracy can provide diagnostic suggestions to radiologists in the clinic.

Keywords: convolutional neural network, computer-aided diagnosis, glioblastoma, magnetic resonance imaging

Procedia PDF Downloads 147