Search results for: network restructuring

Authors: Akeel A. Shah, Tong Zhang

Abstract:

Computational approaches to learning the properties of materials are commonplace, motivated by the need to screen or design materials for a given application, e.g., semiconductors and energy storage. Experimental approaches can be both time consuming and costly. Unfortunately, computational approaches such as ab-initio electronic structure calculations and classical or ab-initio molecular dynamics are themselves can be too slow for the rapid evaluation of materials, often involving thousands to hundreds of thousands of candidates. Machine learning assisted approaches have been developed to overcome the time limitations of purely physics-based approaches. These approaches, on the other hand, require large volumes of data for training (hundreds of thousands on many standard data sets such as QM7b). This means that they are limited by how quickly such a large data set of physics-based simulations can be established. At high fidelity, such as configuration interaction, composite methods such as G4, and coupled cluster theory, gathering such a large data set can become infeasible, which can compromise the accuracy of the predictions - many applications require high accuracy, for example band structures and energy levels in semiconductor materials and the energetics of charge transfer in energy storage materials. In order to circumvent this problem, multi-fidelity approaches can be adopted, for example the Δ-ML method, which learns a high-fidelity output from a low-fidelity result such as Hartree-Fock or density functional theory (DFT). The general strategy is to learn a map between the low and high fidelity outputs, so that the high-fidelity output is obtained a simple sum of the physics-based low-fidelity and correction, Although this requires a low-fidelity calculation, it typically requires far fewer high-fidelity results to learn the correction map, and furthermore, the low-fidelity result, such as Hartree-Fock or semi-empirical ZINDO, is typically quick to obtain, For high-fidelity outputs the result can be an order of magnitude or more in speed up. In this work, a new multi-fidelity approach is developed, based on a graph convolutional network (GCN) combined with semi-supervised learning. The GCN allows for the material or molecule to be represented as a graph, which is known to improve accuracy, for example SchNet and MEGNET. The graph incorporates information regarding the numbers of, types and properties of atoms; the types of bonds; and bond angles. They key to the accuracy in multi-fidelity methods, however, is the incorporation of low-fidelity output to learn the high-fidelity equivalent, in this case by learning their difference. Semi-supervised learning is employed to allow for different numbers of low and high-fidelity training points, by using an additional GCN-based low-fidelity map to predict high fidelity outputs. It is shown on 4 different data sets that a significant (at least one order of magnitude) increase in accuracy is obtained, using one to two orders of magnitude fewer low and high fidelity training points. One of the data sets is developed in this work, pertaining to 1000 simulations of quinone molecules (up to 24 atoms) at 5 different levels of fidelity, furnishing the energy, dipole moment and HOMO/LUMO.

Keywords: .materials screening, computational materials, machine learning, multi-fidelity, graph convolutional network, semi-supervised learning

Procedia PDF Downloads 41

Authors: Savita Tangwongkit, Chittur S Srinivasan, Philip J. Jones

Abstract:

Thailand has become the world’s fourth largest sugarcane producer and second largest sugar exporter. While there have been a number of drivers of this growth, the primary driver has been wide-ranging government support measures. Recently, the Thai government has emphasized the need for policy reform as part of a broader industry restructuring to bring the sector up-to-date with the current and future developments in the international sugar market. Because of the sectors historical dependence on government support, any such reform is likely to have a very significant impact on the fortunes of Thai cane farmers. This study explores the impact of three policy scenarios, representing a spectrum of policy approaches, on Thai cane producers. These reform scenarios were designed in consultation with policy makers and academics working in the cane sector. Scenario 1 captures the current ‘government proposal’ for policy reform. This scenario removes certain domestic production subsidies but seeks to maintain as much support as is permissible under current WTO rules. The second scenario, ‘protectionism’, maintains the current internal market producer supports, but otherwise complies with international (WTO) commitments. Third, the ‘libertarian scenario’ removes all production support and market interventions, trade and domestic consumption distortions. Most important driver of producer behaviour in all of the scenarios is the producer price of cane. Cane price is obviously highest under the protectionism scenario, followed by government proposal and libertarian scenarios, respectively. Likely producer responses to these three policy scenarios was determined by means of a large-scale survey of cane farmers. The sample was stratified by size group and quotas filled by size group and region. One scenario was presented to each of three sub-samples, consisting of approx.150 farmers. Total sample size was 462 farms. Data was collected by face-to-face interview between June and August 2019. There was a marked difference in farmer response to the three scenarios. Farmers in the ‘Protectionism’ scenario, which maintains the highest cane price and those who farm larger cane areas are more likely to continue cane farming. The libertarian scenario is likely to result in the greatest losses in terms of cane production volume broadly double that of the ‘protectionism’ scenario, primarily due to farmers quitting cane production altogether. Over half of loss cane production volume comes from medium-size farm, i.e. the largest and smallest producers are the most resilient. This result is likely due to the fact that the medium size group are large enough to require hired labour but lack the economies of scale of the largest farms. Over all size groups the farms most heavily specialized in cane production, i.e. those devoting 26-50% of arable land to cane, are also the most vulnerable, with 70% of all farmers quitting cane production coming from this group. This investigation suggests that cane price is the most significant determinant of farmer behaviour. Also, that where scenarios drive significantly lower cane price, policy makers should target support towards mid-sized producers, with policies that encourage efficiency gains and diversification into alternative agricultural crops.

Keywords: farmer intentions, farm survey, policy reform, Thai cane production

Procedia PDF Downloads 110

Authors: Diego De Almeida Pereira, Diana Borchenko

Abstract:

Artificial neural networks are used for many applications as they are able to learn complex nonlinear relationships between input and output data. As the number of neurons and layers in a neural network increases, it is possible to represent more complex behaviors. The present study proposes that artificial neural networks are a valuable tool for architecture and engineering professionals concerned with understanding how buildings influence human and social well-being based on theories of environmental psychology.

Keywords: environmental psychology, architecture, neural networks, human and social well-being

Procedia PDF Downloads 496

Authors: Sarah Reker, Christiane H. Kellner

Abstract:

From the perspective of people with disabilities, inequalities can also emerge from spatial segregation, the lack of social contacts or limited economic resources. In order to reduce or even eliminate these disadvantages and increase general well-being, community-based participation as well as decentralisation efforts within exclusively residential homes is essential. Therefore, the new research project “Index for participation development and quality of life for persons with disabilities”(TeLe-Index, 2014-2016), which is anchored at the Technische Universität München in Munich and at a large residential complex and service provider for persons with disabilities in the outskirts of Munich aims to assist the development of community-based living environments. People with disabilities should be able to participate in social life beyond the confines of the institution. Since a diverse society is a society in which different individual needs and wishes can emerge and be catered to, the ultimate goal of the project is to create an environment for all citizens–regardless of disability, age or ethnic background–that accommodates their daily activities and requirements. The UN-Convention on the Rights of Persons with Disabilities, which Germany also ratified, postulates the necessity of user-centered design, especially when it comes to evaluating the individual needs and wishes of all citizens. Therefore, a multidimensional approach is required. Based on this insight, the structure of the town-like center will be remodeled to open up the community to all people. This strategy should lead to more equal opportunities and open the way for a much more diverse community. Therefore, macro-level research questions were inspired by quality of life theory and were formulated as follows for different dimensions: •The user dimension: what needs and necessities can we identify? Are needs person-related? Are there any options to choose from? What type of quality of life can we identify? The economic dimension: what resources (both material and staff-related) are available in the region? (How) are they used? What costs (can) arise and what effects do they entail? •The environment dimension: what “environmental factors” such as access (mobility and absence of barriers) prove beneficial or impedimental? In this context, we have provided academic supervision and support for three projects (the construction of a new school, inclusive housing for children and teenagers with disabilities and the professionalization of employees with person-centered thinking). Since we cannot present all the issues of the umbrella-project within the conference framework, we will be focusing on one project more in-depth, namely “Outpatient Housing Options for Children and Teenagers with Disabilities”. The insights we have obtained until now will enable us to present the intermediary results of our evaluation. The most central questions pertaining to this part of the research were the following: •How have the existing network relations been designed? •What meaning (or significance) does the existing service offers and structures have for the everyday life of an external residential group? These issues underpinned the environmental analyses as well as the qualitative guided interviews and qualitative network analyses we carried out.

Keywords: decentralisation, environmental analyses, outpatient housing options for children and teenagers with disabilities, qualitative network analyses

Procedia PDF Downloads 365

Authors: Julius Y Asamoah

Abstract:

Mobile money has seen faster adoption in the decade. Its emergence serves as an essential driver of financial inclusion and an innovative financial service delivery channel, especially to the unbanked population. The rising importance of mobile money services has caught policymakers and regulators' attention, seeking to understand the many issues emerging from this context. At the same time, it is unlocking the potential of knowledge of this new technology. Regulatory responses and support are essential, requiring significant changes to current regulatory practices in Ghana. The article aims to answer the following research questions: "What risk does an unregulated mobile money service pose to consumers and the financial system? "What factors stimulate and hinder the introduction of mobile payments in developing countries? The sample size used was 250 respondents selected from the study area. The study has adopted an analytical approach comprising a combination of qualitative and quantitative data collection methods. Actor-network theory (ANT) is used as an interpretive lens to analyse this process. ANT helps analyse how actors form alliances and enrol other actors, including non-human actors (i.e. technology), to secure their interests. The study revealed that government regulatory policies impact mobile money as critical to mobile money services in developing countries. Regulatory environment should balance the needs of advancing access to finance with the financial system's stability and draw extensively from Kenya's work as the best strategies for the system's players. Thus, regulators need to address issues related to the enhancement of supportive regulatory frameworks. It recommended that the government involve various stakeholders, such as mobile phone operators. Moreover, the national regulatory authority creates a regulatory environment that promotes fair practices and competition to raise revenues to support a business-enabling environment's key pillars as infrastructure.

Keywords: actor-network theory (ANT), cashless future, Developing countries, Ghana, Mobile Money

Procedia PDF Downloads 138

Authors: Enrique Barra, Aldo Gordillo, Juan Quemada

Abstract:

This paper presents the Virtual Science Hub platform. It is an open source platform that combines a social network, an e-learning authoring tool, a video conference service and a learning object repository for science teaching enrichment. These four main functionalities fit very well together. The platform was released in April 2012 and since then it has not stopped growing. Finally we present the results of the surveys conducted and the statistics gathered to validate this approach.

Keywords: e-learning, platform, authoring tool, science teaching, educational sciences

Procedia PDF Downloads 397

Authors: Ademola Ibukunolu Atanda

Abstract:

Research undertakings are meant to proffer solutions to issues and challenges in society. This justifies the need for research in ivory towers. Multinational and non-governmental organisations, as well as foundations, commit financial resources to support research endeavours. In recent times, the direction and dimension of research undertaking encourage collaborations, whereby experts from different disciplines or specializations would bring their expertise in addressing any identified problem, whether in humanities or sciences. However, the extent to which collaborative research undertakings are perceived and embraced by academic staff would determine the impact collaborative research would have on society. To this end, this study investigated academic staff’s perception and willingness to be involved in collaborative research for the purpose of proffering solutions to societal problems. The study adopted a descriptive research design. The population comprised academic staff in southern Nigeria. The sample was drawn through a convenient sampling technique. The data were collected using a questionnaire titled “Perception and Willingness to Participate in Collaborative Research Questionnaire (PWPCRQ)’ using Google Forms. Data collected were analyzed using descriptive statistics of simple percentages, mean and charts. The findings showed that Academic Staff’s readiness to participate in collaborative research is to a great extent (89%) and they participate in collaborative research very often (51%). The Academic Staff was involved more in collaboration research among their colleagues within their universities (1.98) than participation in inter-disciplines collaboration (1.47) with their colleagues outside Nigeria. Collaborative research was perceived to impact on development (2.5). Collaborative research offers the following benefits to members’ aggregation of views, the building of an extensive network of contacts, enhancement of sharing of skills, facilitation of tackling complex problems, increased visibility of research network and citations and promotion of funding opportunities. The study concluded that Academic staff in universities in the South-West of Nigeria participate in collaborative research but with their colleagues within Nigeria rather than outside the country. Based on the findings, it was recommended that the management of universities in South-West Nigeria should encourage collaborative research with some incentives.

Keywords: collaboration, research, development, participation

Procedia PDF Downloads 63

Authors: Chao Wang

Abstract:

Under rapid innovation of information technology, the media plays a very important role in the dissemination of information, and it has a totally different analogy generations face. However, the involvement of narrative images provides more possibilities of narrative text. "Images" through the process of aperture, a camera shutter and developable photosensitive processes are manufactured, recorded and stamped on paper, displayed on a computer screen-concretely saved. They exist in different forms of files, data, or evidence as the ultimate looks of events. By the interface of media and network platforms and special visual field of the viewer, class body space exists and extends out as thin as sebum layer, extremely soft and delicate with real full tension. The physical space of sebum layer of confuses the fact that physical objects exist, needs to be established under a perceived consensus. As at the scene, the existing concepts and boundaries of physical perceptions are blurred. Sebum layer physical simulation shapes the “Topical-Similarity" immersing, leading the contemporary social practice communities, groups, network users with a kind of illusion without the presence, i.e. a non-real illusion. From the investigation and discussion of literatures, digital movies editing manufacture and produce the variability characteristics of time (for example, slices, rupture, set, and reset) are analyzed. Interactive eBook has an unique interaction in "Waiting-Greeting" and "Expectation-Response" that makes the operation of image narrative structure more interpretations functionally. The works of digital editing and interactive technology are combined and further analyze concept and results. After digitization of Interventional Imaging and interactive technology, real events exist linked and the media handing cannot be cut relationship through movies, interactive art, practical case discussion and analysis. Audience needs more rational thinking about images carried by the authenticity of the text.

Keywords: sebum layer, topical and similarity, interactive technology, image narrative

Procedia PDF Downloads 389

Authors: Zhao Gao, Eran Edirisinghe

Abstract:

The production of an accurate sketch of a suspect based on a verbal description obtained from a witness is an essential task for most criminal investigations. The criminal investigation system employs specifically trained professional artists to manually draw a facial image of the suspect according to the descriptions of an eyewitness for subsequent identification. Within the advancement of Deep Learning, Recurrent Neural Networks (RNN) have shown great promise in Natural Language Processing (NLP) tasks. Additionally, Generative Adversarial Networks (GAN) have also proven to be very effective in image generation. In this study, a trained GAN conditioned on textual features such as keywords automatically encoded from a verbal description of a human face using an RNN is used to generate photo-realistic facial images for criminal investigations. The intention of the proposed system is to map corresponding features into text generated from verbal descriptions. With this, it becomes possible to generate many reasonably accurate alternatives to which the witness can use to hopefully identify a suspect from. This reduces subjectivity in decision making both by the eyewitness and the artist while giving an opportunity for the witness to evaluate and reconsider decisions. Furthermore, the proposed approach benefits law enforcement agencies by reducing the time taken to physically draw each potential sketch, thus increasing response times and mitigating potentially malicious human intervention. With publically available 'CelebFaces Attributes Dataset' (CelebA) and additionally providing verbal description as training data, the proposed architecture is able to effectively produce facial structures from given text. Word Embeddings are learnt by applying the RNN architecture in order to perform semantic parsing, the output of which is fed into the GAN for synthesizing photo-realistic images. Rather than the grid search method, a metaheuristic search based on genetic algorithms is applied to evolve the network with the intent of achieving optimal hyperparameters in a fraction the time of a typical brute force approach. With the exception of the ‘CelebA’ training database, further novel test cases are supplied to the network for evaluation. Witness reports detailing criminals from Interpol or other law enforcement agencies are sampled on the network. Using the descriptions provided, samples are generated and compared with the ground truth images of a criminal in order to calculate the similarities. Two factors are used for performance evaluation: The Structural Similarity Index (SSIM) and the Peak Signal-to-Noise Ratio (PSNR). A high percentile output from this performance matrix should attribute to demonstrating the accuracy, in hope of proving that the proposed approach can be an effective tool for law enforcement agencies. The proposed approach to criminal facial image generation has potential to increase the ratio of criminal cases that can be ultimately resolved using eyewitness information gathering.

Keywords: RNN, GAN, NLP, facial composition, criminal investigation

Procedia PDF Downloads 162

Authors: Mehmet Karaata

Abstract:

Given two distinct vertices (nodes) source s and target t of a graph G = (V, E), the two node-disjoint paths problem is to identify two node-disjoint paths between s ∈ V and t ∈ V . Two paths are node-disjoint if they have no common intermediate vertices. In this paper, we present an algorithm with O(m)-time complexity for finding two node-disjoint paths between s and t in arbitrary graphs where m is the number of edges. The proposed algorithm has a wide range of applications in ensuring reliability and security of sensor, mobile and fixed communication networks.

Keywords: disjoint paths, distributed systems, fault-tolerance, network routing, security

Procedia PDF Downloads 442

Authors: Shankaran Sitarama

Abstract:

Teamwork is an extremely effective pedagogical tool in engineering education. New Product Development (NPD) has been an effective strategy of companies to streamline and bring innovative products and solutions to customers. Thus, Engineering curriculum in many schools, some collaboratively with business schools, have brought NPD into the curriculum at the graduate level. Teamwork is invariably used during instruction, where students work in teams to come up with new products and solutions. There is a significant emphasis of grade on the semester long teamwork for it to be taken seriously by students. As the students work in teams and go through this process to develop the new product prototypes, their effectiveness and learning to a great extent depends on how they function as a team and go through the creative process, come together, and work towards the common goal. A core attribute of a successful NPD team is their creativity and innovation. The team needs to be creative as a group, generating a breadth of ideas and innovative solutions that solve or address the problem they are targeting and meet the user’s needs. They also need to be very efficient in their teamwork as they work through the various stages of the development of these ideas resulting in a POC (proof-of-concept) implementation or a prototype of the product. The simultaneous requirement of teams to be creative and at the same time also converge and work together imposes different types of tensions in their team interactions. These ideational tensions / conflicts and sometimes relational tensions / conflicts are inevitable. Effective teams will have to deal with the Team dynamics and manage it to be resilient enough and yet be creative. This research paper provides a computational analysis of the teams’ communication that is reflective of the team dynamics, and through a superimposition of latent semantic analysis with social network analysis, provides a computational methodology of arriving at patterns of visual interaction. These team interaction patterns have clear correlations to the team dynamics and provide insights into the functioning and thus the effectiveness of the teams. 23 student NPD teams over 2 years of a course on Managing NPD that has a blend of engineering and business school students is considered, and the results are presented. It is also correlated with the teams’ detailed and tailored individual and group feedback and self-reflection and evaluation questionnaire.

Keywords: team dynamics, social network analysis, team interaction patterns, new product development teamwork, NPD teams

Procedia PDF Downloads 116

Authors: Doaa El-Shereef

Abstract:

The Canaanite civilization was one of the early great civilizations of the Near East, they influenced and been influenced from the civilizations of the ancient world especially the Egyptian and Mesopotamia civilizations. The development of the Canaanite trade started from the Chalcolithic Age to the Iron Age through the oldest trade route in the Middle East. This paper will focus on defining the Canaanites and from where did they come from and the meaning of the term Canaan and how the Ancient Manuscripts define the borders of the land of Canaan and this essay will describe the Canaanite trade route and their exported goods such as cedar wood, and pottery.

Keywords: archaeology, bronze age, Canaanite, colonies, Massilia, pottery, shipwreck, vineyards

Procedia PDF Downloads 201

Authors: Suraj Mehrotra

Abstract:

The stock market is a volatile, bustling marketplace that is a cornerstone of economics. It defines whether companies are successful or in spiral. A thorough understanding of it is important - many companies have whole divisions dedicated to analysis of both their stock and of rivaling companies. Linking the world of finance and artificial intelligence (AI), especially the stock market, has been a relatively recent development. Predicting how stocks will do considering all external factors and previous data has always been a human task. With the help of AI, however, machine learning models can help us make more complete predictions in financial trends. Taking a look at the stock market specifically, predicting the open, closing, high, and low prices for the next day is very hard to do. Machine learning makes this task a lot easier. A model that builds upon itself that takes in external factors as weights can predict trends far into the future. When used effectively, new doors can be opened up in the business and finance world, and companies can make better and more complete decisions. This paper explores the various techniques used in the prediction of stock prices, from traditional statistical methods to deep learning and neural networks based approaches, among other methods. It provides a detailed analysis of the techniques and also explores the challenges in predictive analysis. For the accuracy of the testing set, taking a look at four different models - linear regression, neural network, decision tree, and naïve Bayes - on the different stocks, Apple, Google, Tesla, Amazon, United Healthcare, Exxon Mobil, J.P. Morgan & Chase, and Johnson & Johnson, the naïve Bayes model and linear regression models worked best. For the testing set, the naïve Bayes model had the highest accuracy along with the linear regression model, followed by the neural network model and then the decision tree model. The training set had similar results except for the fact that the decision tree model was perfect with complete accuracy in its predictions, which makes sense. This means that the decision tree model likely overfitted the training set when used for the testing set.

Keywords: machine learning, testing set, artificial intelligence, stock analysis

Procedia PDF Downloads 95

Authors: S. Adjiri-Bailiche, S. M. Boudia, H. Daaou, S. Hadouche, A. Benzaoui

Abstract:

In this work the study of changes in the wind speed depending on the altitude is calculated and described by the model of the neural networks, the use of measured data, the speed and direction of wind, temperature and the humidity at 10 m are used as input data and as data targets at 50m above sea level. Comparing predict wind speeds and extrapolated at 50 m above sea level is performed. The results show that the prediction by the method of artificial neural networks is very accurate.

Keywords: MATLAB, neural network, power low, vertical extrapolation, wind energy, wind speed

Procedia PDF Downloads 693

Authors: Duncan Wallace, M-Tahar Kechadi

Abstract:

In recent years, Machine Learning (ML) approaches have been successfully applied to an analysis of patient symptom data in the context of disease diagnosis, at least where such data is well codified. However, much of the data present in Electronic Health Records (EHR) are unlikely to prove suitable for classic ML approaches. Furthermore, as scores of data are widely spread across both hospitals and individuals, a decentralized, computationally scalable methodology is a priority. The focus of this paper is to develop a method to predict outliers in an out-of-hours healthcare provision center (OOHC). In particular, our research is based upon the early identification of patients who have underlying conditions which will cause them to repeatedly require medical attention. OOHC act as an ad-hoc delivery of triage and treatment, where interactions occur without recourse to a full medical history of the patient in question. Medical histories, relating to patients contacting an OOHC, may reside in several distinct EHR systems in multiple hospitals or surgeries, which are unavailable to the OOHC in question. As such, although a local solution is optimal for this problem, it follows that the data under investigation is incomplete, heterogeneous, and comprised mostly of noisy textual notes compiled during routine OOHC activities. Through the use of Deep Learning methodologies, the aim of this paper is to provide the means to identify patient cases, upon initial contact, which are likely to relate to such outliers. To this end, we compare the performance of Long Short-Term Memory, Gated Recurrent Units, and combinations of both with Convolutional Neural Networks. A further aim of this paper is to elucidate the discovery of such outliers by examining the exact terms which provide a strong indication of positive and negative case entries. While free-text is the principal data extracted from EHRs for classification, EHRs also contain normalized features. Although the specific demographical features treated within our corpus are relatively limited in scope, we examine whether it is beneficial to include such features among the inputs to our neural network, or whether these features are more successfully exploited in conjunction with a different form of a classifier. In this section, we compare the performance of randomly generated regression trees and support vector machines and determine the extent to which our classification program can be improved upon by using either of these machine learning approaches in conjunction with the output of our Recurrent Neural Network application. The output of our neural network is also used to help determine the most significant lexemes present within the corpus for determining high-risk patients. By combining the confidence of our classification program in relation to lexemes within true positive and true negative cases, with an inverse document frequency of the lexemes related to these cases, we can determine what features act as the primary indicators of frequent-attender and non-frequent-attender cases, providing a human interpretable appreciation of how our program classifies cases.

Keywords: artificial neural networks, data-mining, machine learning, medical informatics

Procedia PDF Downloads 131

Authors: Sandeep Mehmi, Harsh Verma, A. L. Sangal

Abstract:

Ever since the idea of using computing services as commodity that can be delivered like other utilities e.g. electric and telephone has been floated, the scientific fraternity has diverted their research towards a new area called utility computing. New paradigms like cluster computing and grid computing came into existence while edging closer to utility computing. With the advent of internet the demand of anytime, anywhere access of the resources that could be provisioned dynamically as a service, gave rise to the next generation computing paradigm known as cloud computing. Today, cloud computing has become one of the most aggressively growing computer paradigm, resulting in growing rate of applications in area of IT outsourcing. Besides catering the computational and storage demands, cloud computing has economically benefitted almost all the fields, education, research, entertainment, medical, banking, military operations, weather forecasting, business and finance to name a few. Smart grid is another discipline that direly needs to be benefitted from the cloud computing advantages. Smart grid system is a new technology that has revolutionized the power sector by automating the transmission and distribution system and integration of smart devices. Cloud based smart grid can fulfill the storage requirement of unstructured and uncorrelated data generated by smart sensors as well as computational needs for self-healing, load balancing and demand response features. But, security issues such as confidentiality, integrity, availability, accountability and privacy need to be resolved for the development of smart grid cloud. In recent years, a number of intrusion prevention techniques have been proposed in the cloud, but hackers/intruders still manage to bypass the security of the cloud. Therefore, precise intrusion detection systems need to be developed in order to secure the critical information infrastructure like smart grid cloud. Considering the success of artificial neural networks in building robust intrusion detection, this research proposes an artificial neural network based model for detecting attacks in smart grid cloud.

Keywords: artificial neural networks, cloud computing, intrusion detection systems, security issues, smart grid

Procedia PDF Downloads 318

Authors: Thulane Paepae, Tumisang Seodigeng

Abstract:

This paper demonstrates the use of a method of synthesizing process flowsheets using a graphical tool called the GH-plot and in particular, to look at how it can be used to compare the reactions of a combined simultaneous process with regard to their thermodynamics. The technique uses fundamental thermodynamic principles to allow the mass, energy and work balances locate the attainable region for chemical processes in a reactor. This provides guidance on what design decisions would be best suited to developing new processes that are more effective and make lower demands on raw material and energy usage.

Keywords: attainable regions, dimethyl ether, optimal reaction network, GH Space

Procedia PDF Downloads 240

Authors: Lawrence Williams

Abstract:

As the mechanism which converts domains to internet protocol (IP) addresses, Domain Name System (DNS) is an essential part of internet usage. It was not designed securely and can be subject to attacks. DNS attacks have become more frequent and sophisticated and the need for detecting and preventing them becomes more important for the modern network. DNS tunnelling attacks are one type of attack that are primarily used for distributed denial-of-service (DDoS) attacks and data exfiltration. Discussion of different techniques to detect and prevent DNS tunneling attacks is done. The methods, models, experiments, and data for each technique are discussed. A proposal about feasibility is made. Future research on these topics is proposed.

Keywords: DNS, tunneling, exfiltration, botnet

Procedia PDF Downloads 75

Authors: Ankit Shah, R. K. Shrivastava

Abstract:

Flood and drought are two main features of hydrology which affect the human life. Floods are natural disasters which cause millions of rupees’ worth of damage each year in India and the whole world. Flood causes destruction in form of life and property. An accurate estimate of the flood damage potential is a key element to an effective, nationwide flood damage abatement program. Also, the increase in demand of water due to increase in population, industrial and agricultural growth, has let us know that though being a renewable resource it cannot be taken for granted. We have to optimize the use of water according to circumstances and conditions and need to harness it which can be done by construction of hydraulic structures. For their safe and proper functioning of hydraulic structures, we need to predict the flood magnitude and its impact. Hydraulic structures play a key role in harnessing and optimization of flood water which in turn results in safe and maximum use of water available. Mainly hydraulic structures are constructed on ungauged sites. There are two methods by which we can estimate flood viz. generation of Unit Hydrographs and Flood Frequency Analysis. In this study, Regional Flood Frequency Analysis has been employed. There are many methods for estimating the ‘Regional Flood Frequency Analysis’ viz. Index Flood Method. National Environmental and Research Council (NERC Methods), Multiple Regression Method, etc. However, none of the methods can be considered universal for every situation and location. The Narmada basin is located in Central India. It is drained by most of the tributaries, most of which are ungauged. Therefore it is very difficult to estimate flood on these tributaries and in the main river. As mentioned above Artificial Neural Network (ANN)s and Multiple Regression Method is used for determination of Regional flood Frequency. The annual peak flood data of 20 sites gauging sites of Narmada Basin is used in the present study to determine the Regional Flood relationships. Homogeneity of the considered sites is determined by using the Index Flood Method. Flood relationships obtained by both the methods are compared with each other, and it is found that ANN is more reliable than Multiple Regression Method for the present study area.

Keywords: artificial neural network, index flood method, multi layer perceptrons, multiple regression, Narmada basin, regional flood frequency

Procedia PDF Downloads 419

Authors: Beatriz Cortés, Andrés Boza, David Pérez, Llanos Cuenca

Abstract:

The Internet of Things (IoT) field is been applied in industries with different purposes. Sensing Enterprise (SE) is an attribute of an enterprise or a network that allows it to react to business stimuli originating on the internet. These fields have come into focus recently on the enterprises and there is some evidence of the use and implications in supply chain management while finding it as an interesting aspect to work on. This paper presents a revision and proposals of IoT applications in supply chain management.

Keywords: industrial, internet of things, production systems, sensing enterprises, sensor, supply chain management

Procedia PDF Downloads 423

Authors: Santos Andressa M. N.

Abstract:

The research brings reflections on the importance of Instagram for the clothing trade, aiming to analyze the use of this social network as a sales tool by small companies in the fashion/clothing sector in Boqueirão-PI. Thus, field research was carried out, with the application of questionnaires, to raise and analyze data related to the topic. Thus, it is believed that Instagram positively influences the dissemination, visibility, reach and profitability of companies in Boqueirão do Piauí. The survey had a low number of companies due to the lack of availability of the owners during the COVID-19 pandemic.

Keywords: Instagram, sales, fashion, marketing

Procedia PDF Downloads 57

Authors: H. Kiani, S. Moradi, B. Soltani Soulgani, S. Mousavian

Abstract:

Desalting/dehydration plants (DDP) are often installed in crude oil production units in order to remove water-soluble salts from an oil stream. In order to optimize this process, desalting unit should be modeled. In this research, artificial neural network is used to model efficiency of desalting unit as a function of input parameter. The result of this research shows that the mentioned model has good agreement with experimental data.

Keywords: desalting unit, crude oil, neural networks, simulation, recovery, separation

Procedia PDF Downloads 450

Authors: Linda Smail, Zineb Azouz

Abstract:

Given a Bayesian network relative to a set I of discrete random variables, we are interested in computing the probability distribution P(S) where S is a subset of I. The general idea is to write the expression of P(S) in the form of a product of factors where each factor is easy to compute. More importantly, it will be very useful to give an interpretation of each of the factors in terms of conditional probabilities. This paper considers a semantic interpretation of the factors involved in computing marginal probabilities in Bayesian networks. Establishing such a semantic interpretations is indeed interesting and relevant in the case of large Bayesian networks.

Keywords: Bayesian networks, D-Separation, level two Bayesian networks, factorization of computation

Procedia PDF Downloads 530

Authors: Carolina Zambrana, Grover Zurita

Abstract:

The food loss production that occurs in deficient agricultural production is one of the major problems worldwide. This puts the population's food security and the efficiency of farming investments at risk. It is to be expected that this food security will be achieved with the own and efficient production of each country. It will have an impact on the well-being of its population and, thus, also on food sovereignty. The production losses in quantity and quality occur due to the lack of efficient detection of diseases at an early stage. It is very difficult to solve the agriculture efficiency using traditional methods since it takes a long time to be carried out due to detection imprecision of the main diseases, especially when the production areas are extensive. Therefore, the main objective of this research study is to perform a systematic literature review, of the latest five years, of Precision Agriculture (PA) to be able to understand the state of the art of the set of new technologies, procedures, and optimization processes with Artificial Intelligence (AI). This study will focus on Corns, Potatoes, and Rice diagnostic diseases. The extensive literature review will be performed on Elsevier, Scopus, and IEEE databases. In addition, this research will focus on advanced digital imaging processing and the development of software and hardware for PA. The convolution neural network will be handling special attention due to its outstanding diagnostic results. Moreover, the studied data will be incorporated with artificial intelligence algorithms for the automatic diagnosis of crop quality. Finally, precision agriculture with technology applied to the agricultural sector allows the land to be exploited efficiently. This system requires sensors, drones, data acquisition cards, and global positioning systems. This research seeks to merge different areas of science, control engineering, electronics, digital image processing, and artificial intelligence for the development, in the near future, of a low-cost image measurement system that allows the optimization of crops with AI.

Keywords: precision agriculture, convolutional neural network, deep learning, artificial intelligence

Procedia PDF Downloads 79

Authors: R. Loukil, M. Chtourou, T. Damak

Abstract:

This paper investigates the training of multilayer neural network using the classic approach. Then, for estimation purposes, we suggest the use of a specific neural observer that we study its training algorithm which is the back-propagation one in the case of the disponibility of the state and in the case of an unmeasurable state. A MATLAB simulation example will be studied to highlight the usefulness of this kind of observer.

Keywords: training, estimation purposes, neural observer, back-propagation, unmeasurable state

Procedia PDF Downloads 574

Authors: Desmond Young

Abstract:

In building services electrical design, a key element of any project will be assessing the electrical load requirements. This needs to be done early in the design process to allow the selection of infrastructure that would be required to meet the electrical needs of the type of building. The type of building will define the type of assessment made, and the values applied in defining the maximum demand for the building, and ultimately the size of supply or infrastructure required, and the application that needs to be made to the distribution network operator, or alternatively to an independent network operator. The fact that this assessment needs to be undertaken early in the design process provides limits on the type of assessment that can be used, as different methods require different types of information, and sometimes this information is not available until the latter stages of a project. A common method applied in the earlier design stages of a project, typically during stages 1,2 & 3, is the use of benchmarks. It is a possibility that some of the benchmarks applied are excessive in relation to the current loads that exist in a modern installation. This lack of accuracy is based on information which does not correspond to the actual equipment loads that are used. This includes lighting and small power loads, where the use of more efficient equipment and lighting has reduced the maximum demand required. The electrical load can be used as part of the process to assess the heat generated from the equipment, with the heat gains from other sources, this feeds into the sizing of the infrastructure required to cool the building. Any overestimation of the loads would contribute to the increase in the design load for the heating and ventilation systems. Finally, with the new policies driving the industry to decarbonise buildings, a prime example being the recently introduced London Plan, loads are potentially going to increase. In addition, with the advent of the pandemic and changes to working practices, and the adoption of electric heating and vehicles, a better understanding of the loads that should be applied will aid in ensuring that infrastructure is not oversized, as a cost to the client, or undersized to the detriment of the building. In addition, more accurate benchmarks and methods will allow assessments to be made for the incorporation of energy storage and renewable technologies as these technologies become more common in buildings new or refurbished.

Keywords: energy, ADMD, electrical load assessment, energy benchmarks

Procedia PDF Downloads 113

Authors: R. M. López-Gutiérrez, L. Cardoza-Avendaño, H. Cervantes-de Ávila, J. A. Michel-Macarty, C. Cruz-Hernández, A. Arellano-Delgado, R. Carmona-Rodríguez

Abstract:

In this paper, synchronization of multiple chaotic semiconductor lasers is achieved by appealing to complex system theory. In particular, we consider dynamical networks composed by semiconductor laser, as interconnected nodes, where the interaction in the networks are defined by coupling the first state of each node. An interesting case is synchronized with master-slave configuration in star topology. Nodes of these networks are modeled for the laser and simulated by Matlab. These results are applicable to private communication.

Keywords: chaotic laser, network, star topology, synchronization

Procedia PDF Downloads 566

Authors: Sonia Boscenco, Zihan Wang, Euclides José de Mendoça Filho, João Paulo Hoppe, Irina Pokhvisneva, Geoffrey B.C. Hall, Michael J. Meaney, Patricia Pelufo Silveira

Abstract:

Entropy can be described as a measure of the number of states of a system, and when used in the context of physiological time-based signals, it serves as a measure of complexity. In functional connectivity data, entropy can account for the moment-to-moment variability that is neglected in traditional functional magnetic resonance imaging (fMRI) analyses. While brain fMRI resting state entropy has been associated with some pathological conditions like schizophrenia, no investigations have explored the association between brain entropy measures and individual differences in child behavior in healthy children. We describe a novel exploratory approach to evaluate brain fMRI resting state data in two child cohorts, and MAVAN (N=54, 4.5 years, 48% males) and GUSTO (N = 206, 4.5 years, 48% males) and its associations to child behavior, that can be used in future research in the context of child exposures and long-term health. Following rs-fMRI data pre-processing and Shannon entropy calculation across 32 network regions of interest to acquire 496 unique functional connections, partial correlation coefficient analysis adjusted for sex was performed to identify associations between entropy data and Strengths and Difficulties questionnaire in MAVAN and Child Behavior Checklist domains in GUSTO. Significance was set at p < 0.01, and we found eight significant associations in GUSTO. Negative associations were found between two frontoparietal regions and cerebellar posterior and oppositional defiant problems, (r = -0.212, p = 0.006) and (r = -0.200, p = 0.009). Positive associations were identified between somatic complaints and four default mode connections: salience insula (r = 0.202, p < 0.01), dorsal attention intraparietal sulcus (r = 0.231, p = 0.003), language inferior frontal gyrus (r = 0.207, p = 0.008) and language posterior superior temporal gyrus (r = 0.210, p = 0.008). Positive associations were also found between insula and frontoparietal connection and attention deficit / hyperactivity problems (r = 0.200, p < 0.01), and insula – default mode connection and pervasive developmental problems (r = 0.210, p = 0.007). In MAVAN, ten significant associations were identified. Two positive associations were found = with prosocial scores: the salience prefrontal cortex and dorsal attention connection (r = 0.474, p = 0.005) and the salience supramarginal gyrus and dorsal attention intraparietal sulcus (r = 0.447, p = 0.008). The insula and prefrontal connection were negatively associated with peer problems (r = -0.437, p < 0.01). Conduct problems were negatively associated with six separate connections, the left salience insula and right salience insula (r = -0.449, p = 0.008), left salience insula and right salience supramarginal gyrus (r = -0.512, p = 0.002), the default mode and visual network (r = -0.444, p = 0.009), dorsal attention and language network (r = -0.490, p = 0.003), and default mode and posterior parietal cortex (r = -0.546, p = 0.001). Entropy measures of resting state functional connectivity can be used to identify individual differences in brain function that are correlated with variation in behavioral problems in healthy children. Further studies applying this marker into the context of environmental exposures are warranted.

Keywords: child behaviour, functional connectivity, imaging, Shannon entropy

Procedia PDF Downloads 202

Authors: Marina Vicario, Amadeo Argüelles, Pilar Gómez, Carlos Hernández

Abstract:

In this paper, the Computer Research Network of the National Polytechnic Institute of Mexico proposes a paradigmatic model for the inference of cognitive patterns in digital learning systems. This model leads to metadata architecture useful for analysis and prediction in online learning systems; especially on MOOc's architectures. The model is in the design phase and expects to be tested through an institutional of courses project which is going to develop for the MOOc.

Keywords: cognitive footprints, learning analytics, predictive learning, digital learning, educational computing, educational informatics

Procedia PDF Downloads 477

Authors: Wen-Bin Chiou, Hsiao-Chiao Weng

Abstract:

Social networking sites (SNS) such as Facebook and Twitter are low-cost tools that can promote the creation of social connections by providing a convenient platform that can be accessed at any time. In the current research, a laboratory experiment was conducted test the hypothesis that reminders of losing SNS would alter the impact of social events, especially those involving social exclusion. Specifically, this study explored whether losing SNS would intensify perceived social distress induced by exclusionary bogus feedback. Eighty-eight Facebook users (46 females, 42 males; mean age = 22.6 years, SD = 3.1 years) were recruited via campus posters and flyers at a national university in southern Taiwan. After participants provided consent, they were randomly assigned to a 2 (SNS non-use vs. neutral) between-subjects experiment. Participants completed an ostensible survey about online social networking in which we included an item about the time spent on SNS per day. The last question was used to manipulate thoughts about losing SNS access. Participants under the non-use condition were asked to record three conditions that would render them unable to use SNS (e.g., a network adaptor problem, malfunctioning cable modem, or problems with Internet service providers); participants under the neutral condition recorded three conditions that would render them unable to log onto the college website (e.g., server maintenance, local network or firewall problems). Later, this experiment employed a bogus-feedback paradigm to induce social exclusion. Participants then rated their social distress on a four-item scale, identical to that of Experiment 1 (α = .84). The results showed that thoughts of losing SNS intensified distress caused by social exclusion, suggesting that the loss of SNS has a similar effect to the loss of a primary source for social reconnections. Moreover, the priming effects of SNS on perceived distress were more prominent for heavy users. The demonstrated link between the idea of losing SNS use and increased pain of social exclusion manifests the importance of SNS as a crucial gateway for acquiring and rebuilding social connections. Use of online social networking appears to be a two-edged sword for coping with social exclusion in human lives in the e-society.

Keywords: online social networking, perceived distress, social exclusion, SNS

Procedia PDF Downloads 420