Search results for: computing experiment

Authors: Monirah Alkathiry, Hanan Aljarwan

Abstract:

Cloud computing is one of the most significant technologies that the world deals with, in different sectors with different purposes and capabilities. The cloud faces various challenges in securing data from unauthorized access or modification. Consequently, security risks and levels have greatly increased. Therefore, cloud service providers (CSPs) and users need secure mechanisms that ensure that data are kept secret and safe from any disclosures or exploits. For this reason, CSPs need a number of techniques and technologies to manage and secure access to the cloud services to achieve security goals, such as confidentiality, integrity, identity access management (IAM), etc. Therefore, this paper will review and explore various access controls implemented in a cloud environment that achieve different security purposes. The methodology followed in this survey was conducting an assessment, evaluation, and comparison between those access controls mechanisms and technologies based on different factors, such as the security goals it achieves, usability, and cost-effectiveness. This assessment resulted in the fact that the technology used in an access control affects the security goals it achieves as well as there is no one access control method that achieves all security goals. Consequently, such a comparison would help decision-makers to choose properly the access controls that meet their requirements.

Keywords: access controls, cloud computing, confidentiality, identity and access management

Procedia PDF Downloads 113

Authors: Qiuxiao Chen, Yan Hou, Ning Wu

Abstract:

As there are deficiencies of the classic Douglas-Peucker Algorithm (DPA), such as high risks of deleting key nodes by mistake, high complexity, time consumption and relatively slow execution speed, a new Deletion-Cost Based Compression Algorithm (DCA) for linear vector data was proposed. For each curve — the basic element of linear vector data, all the deletion costs of its middle nodes were calculated, and the minimum deletion cost was compared with the pre-defined threshold. If the former was greater than or equal to the latter, all remaining nodes were reserved and the curve’s compression process was finished. Otherwise, the node with the minimal deletion cost was deleted, its two neighbors' deletion costs were updated, and the same loop on the compressed curve was repeated till the termination. By several comparative experiments using different types of linear vector data, the comparison between DPA and DCA was performed from the aspects of compression quality and computing efficiency. Experiment results showed that DCA outperformed DPA in compression accuracy and execution efficiency as well.

Keywords: Douglas-Peucker algorithm, linear vector data, compression, deletion cost

Procedia PDF Downloads 228

Authors: Alexander Denzler, Marcel Wehrle, Andreas Meier

Abstract:

A knowledge base stores facts and rules about the world that applications can use for the purpose of reasoning. By applying the concept of granular computing to a knowledge base, several advantages emerge. These can be harnessed by applications to improve their capabilities and performance. In this paper, the concept behind such a construct, called a granular knowledge cube, is defined, and its intended use as an instrument that manages to cope with different data types and detect knowledge domains is elaborated. Furthermore, the underlying architecture, consisting of the three layers of the storing, representing, and structuring of knowledge, is described. Finally, benefits as well as challenges of deploying it are listed alongside application types that could profit from having such an enhanced knowledge base.

Keywords: granular computing, granular knowledge, hierarchical structuring, knowledge bases

Procedia PDF Downloads 482

Authors: Mokhlisur Rahman

Abstract:

Consumers' understanding of the products depends on what levels of information the advertisement contains. Consumers' attitudes vary widely depending on factors such as their level of environmental awareness, their perception of the company's motives, and the perceived effectiveness of the advertising campaign. Considering the growing eco-consciousness among consumers and their concern for the environment, strategies for green advertising have become equally significant for companies to attract new consumers. It is important to understand consumers' habits of purchasing, knowledge, and attitudes regarding eco-friendly products depending on promotion because of the limitless options of the products in the market. Additionally, encouraging consumers to buy sustainable products requires a platform that can message the world that being a stakeholder in sustainability is possible if consumers show eco-friendly behavior on a larger scale. Social media platforms provide an excellent atmosphere to promote companies' sustainable efforts to be connected engagingly with their potential consumers. The unique strategies of green advertising use techniques to carry information and rewards for the consumers. This study aims to understand the consumer behavior and effectiveness of green advertising by experimenting in collaboration with three companies in promoting their eco-friendly products using green designs on the products. The experiment uses three sustainable personalized offerings, Nike shoes, H&M t-shirts, and Patagonia school bags. The experiment uses a pretest and posttest design. 300 randomly selected participants take part in this experiment and survey through Facebook, Twitter, and Instagram. Nike, H&M, and Patagonia share the post of the experiment on their social media homepages with a video advertisement for the three products. The consumers participate in a pre-experiment online survey before making a purchase decision to assess their attitudes and behavior toward eco-friendly products. The audio-only feature explains the product's information, like their use of recycled materials, their manufacturing methods, sustainable packaging, and their impact on the environment during the purchase while the consumer watches the product video. After making a purchase, consumers take a post-experiment survey to know their perception and behavior toward eco-friendly products. For the data analysis, descriptive statistical tools mean, standard deviation, and frequencies measure the pre- and post-experiment survey data. The inferential statistical tool paired sample t-test measures the difference in consumers' behavior and attitudes between pre-purchase and post-experiment survey results. This experiment provides consumers ample time to consider many aspects rather than impulses. This research provides valuable insights into how companies can adopt sustainable and eco-friendly products. The result set a target for the companies to achieve a sustainable production goal that ultimately supports companies' profit-making and promotes consumers' well-being. This empowers consumers to make informed choices about the products they purchase and support their companies of interest.

Keywords: green-advertising, sustainability, consumer-behavior, social media

Procedia PDF Downloads 68

Authors: Gideon Yaniv, Erez Siniver, Yossef Tobol

Abstract:

The extensive body of economic and psychological research correlating between students' cheating and their grade point average (GPA) consistently finds a significant negative relationship between cheating and the GPA. However, this literature is entirely based on students' responses to direct question surveys that inquire whether they have ever cheated on their academic assignments. The present paper reports the results of a two-round experiment designed to expose student cheating at the individual level and correlate it with their GPAs. The experiment involved two classes of third-year economics students incentivized by a competitive reward to answer a multiple-choice trivia quiz without consulting their electronic devices. While this forbiddance was deliberately overlooked in the first round, providing an opportunity to cheat, it was strictly enforced in the second, conducted two months later in the same classes with the same quiz. A comparison of subjects' performance in the two rounds, self-revealed a considerable extent of cheating in the first one. Regressing the individual cheating levels on subjects' gender and GPA exhibited no significant differences in cheating between males and females. However, cheating of both genders was found to significantly increase with their GPA, implying, in sharp contrast with the direct question surveys, that higher achievers are bigger cheaters. A second experiment, which allowed subjects to answer the quiz in the privacy of their own cars, reveals that when really feeling safe to cheat, many subjects would cheat maximally, challenging the literature's claim that people generally cheat modestly.

Keywords: academic achievement, cheating behavior, experimental data, grade-point average

Procedia PDF Downloads 191

Authors: Ajay Biswas, Swapan Bhaumik, Abhijit Bhowmik

Abstract:

Present experiment has been carried out to study the microstructure of weldment obtained by submerged arc welding on mild steel plate at zero degree Celsius. To study this, bead on plate welding is done by submerged arc welding on the sample plate of heavy duty mild steel of designation IS 2062 grade B, fitted on the special fixture ensuring the plate temperature at zero degree Celsius. Sixteen numbers of such samples are welded by varying the most influencing parameters viz. travel speed, voltage, wire feed rate and electrode stick-out at four different levels. Taguchi’s design of experiment is applied by selecting Taguchi's L16 orthogonal array to restrict the number of experimental runs. Cross sectioned samples are polished and etched to view the weldment. Finally, different zone of the weldment is observed by optical microscope. From the type of microstructure of weldment it is concluded that submerged arc welding is feasible at zero degree Celsius on mild steel plate.

Keywords: Submerged Arc Welding, zero degree Celsius, Taguchi’s design of experiment, microstructure of weldment

Procedia PDF Downloads 427

Authors: O. A. Anjola, M. A. Adejobi, A. Ogunbameru, F. P. Agbaye, R. O. Odunukan

Abstract:

This experiment was conducted for 8 weeks to evaluate the growth performance and economics of pullets fed on different dietary energy sources. A total of 300 Harco black was used for this experiment. The birds were completely randomized and divided into four diet treatment groups. Each treatment group had three replicates of twenty-five birds per replicate. Four diets containing maize, spaghetti, noodles, and biscuit was formulated to represent diet 1, 2, 3 and 4 respectively. Diet 1 containing maize is the control, while diet 2, 3, and 4 contains spaghetti, noodles, and biscuit waste meal at 100% replacement for maize on weight for weight basis. Performance indices on Feed intake, body weight, weight gain, feed conversion ratio (FCR) and economy of production were measured. Blood samples were also collected for heamatology and serum biochemistry assessment. The result of the experiment indicated that different dietary energy source fed to birds significantly (P < 0.05) affect feed intake, body weight, weight gain, and feed conversion ratio (FCR). The best cost of feed per kilogram of body weight gain was obtained in Spaghetti based diet (₦559.30). However, the best performance were obtained from diet 1(maize), it can be concluded that spaghetti as a replacement for maize in diet of pullet is most economical and profitable for production without any deleterious effects attached. Blood parameters of birds were not significantly (p > 0.05) influenced by the use of the dietary energy sources used in this experiment.

Keywords: growth performance, spaghetti, noodles, biscuit, profit, hematology, serum biochemistry

Procedia PDF Downloads 210

Authors: Jan Barak, Karel Frana, Joerg Stiller

Abstract:

This work presents results of moist air condensation in heat exchanger. It describes theoretical knowledge and definition of moist air. Model with geometry of square canal was created for better understanding and post processing of condensation phenomena. Different approaches were examined on this model to find suitable software and model. Obtained knowledge was applied to geometry of real heat exchanger and results from experiment were compared with numerical results. One of the goals is to solve this issue without creating any user defined function in the applied code. It also contains summary of knowledge and outlook for future work.

Keywords: condensation, exchanger, experiment, validation

Procedia PDF Downloads 385

Authors: Wafa' Slaibi Alsharafat

Abstract:

Cloud computing is a modern approach in network environment. According to increased number of network users and online systems, there is a need to help these systems to be away from unauthorized resource access and detect any attempts for privacy contravention. For that purpose, Intrusion Detection System is an effective security mechanism to detect any attempts of attacks for cloud resources and their information. In this paper, Cloud Intrusion Detection System has been proposed in term of reducing or eliminating any attacks. This model concerns about achieving high detection rate after conducting a set of experiments using benchmarks dataset called KDD'99.

Keywords: IDS, cloud computing, anticipating classifier system, intrusion detection

Procedia PDF Downloads 457

Authors: Ivan Stanev, Maria Koleva

Abstract:

Automated software development issues are addressed in this paper. Layers and packages of a Common Platform for Automated Programming (CPAP) are defined based on Service Oriented Architecture, Cloud computing, Knowledge based automated software engineering (KBASE) and Method of automated programming. Tools of seven leading companies (AWS of Amazon, Azure of Microsoft, App Engine of Google, vCloud of VMWare, Bluemix of IBM, Helion of HP, OCPaaS of Oracle) are analyzed in the context of CPAP. Based on the results of the analysis CPAP requirements are formulated

Keywords: automated programming, cloud computing, knowledge based software engineering, service oriented architecture

Procedia PDF Downloads 283

Authors: Michael Danilov, Sergei Iskakov, Vladimir Mazurenko

Abstract:

The present paper describes a high-performance parallel realization of an exact diagonalization solver for quantum-electron models in a shared memory computing system. The proposed algorithm contains a storage format for efficient computing eigenvalues and eigenvectors of a quantum electron Hamiltonian matrix. The results of the test calculations carried out for 15 sites Hubbard model demonstrate reduction in the required memory and good multiprocessor scalability, while maintaining performance of the same order as compressed row storage.

Keywords: sparse matrix, compressed format, Hubbard model, Anderson model

Procedia PDF Downloads 383

Authors: Kweon Oh-Sang, Kim Heung-Youl

Abstract:

Estimating the engineering properties of fires is important to be prepared for the complex and various fire risks of large-scale structures such as super-tall buildings, large stadiums, and multi-purpose structures. In this study, a mock-up of a compartment which was 2.4(L) x 3.6 (W) x 2.4 (H) meter in dimensions was fabricated at the 10MW LSC (Large Scale Calorimeter) and combustible office supplies were placed in the compartment for a real-scale fire test. Maximum heat release rate was 4.1 MW and total energy release obtained through the application of t2 fire growth rate was 6705.9 MJ.

Keywords: fire growth, fire experiment, t2 curve, large scale calorimeter

Procedia PDF Downloads 322

Authors: Rahma Souli-Jbali, Minyar Sassi Hidri, Rahma Ben Ayed

Abstract:

Grid of computing nodes has emerged as a representative means of connecting distributed computers or resources scattered all over the world for the purpose of computing and distributed storage. Since fault tolerance becomes complex due to the availability of resources in decentralized grid environment, it can be used in connection with replication in data grids. The objective of our work is to present fault tolerance in data grids with data replication-driven model based on clustering. The performance of the protocol is evaluated with Omnet++ simulator. The computational results show the efficiency of our protocol in terms of recovery time and the number of process in rollbacks.

Keywords: data grids, fault tolerance, clustering, chandy-lamport

Procedia PDF Downloads 315

Authors: Manuela Nayantara Jeyaraj

Abstract:

Green IT is a term that refers to the collective strategic and tactical practices that unswervingly condense the carbon footprint to a diminished proportion in an establishment’s computing procedures. This concept has been tightly knit with IT related organizations; hence it has been precluded to be applied within non-IT organizations in Sri Lanka. With the turn of the century, computing technologies have taken over commonplace activities in every nook and corner in Sri Lanka, which is still on the verge of moving forth in its march towards being a developed country. Hence, it needs to be recursively proven that non-IT industries are well-bound to adhere to ‘Green IT’ practices as well, in order to reduce their carbon footprint and move towards considering the practicality of implementing Green-IT practices within their work-arounds. There are several spheres that need to be taken into account in creating awareness of ‘Green IT’, such as the economic breach, technologies available, legislative bounds, community mind-set and many more. This paper tends to reconnoiter causes that currently restrain non-IT organizations from considering Green IT concepts. By doing so, it is expected to prove the beneficial providence gained by implementing this concept within the organization. The ultimate goal is to propose feasible ‘Green IT’ practices that could be implemented within the context of Sri Lankan non-IT sectors in order to ensure that organization’s sustainable growth towards a long term existence.

Keywords: computing practices, Green IT, non-IT industries, Sri Lanka, sustainability

Procedia PDF Downloads 231

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 154

Authors: Maggie Hui

Abstract:

Risk management is not a new concept; however, it is an uncharted area as applied to the translation process and translator training. Serving as one of the self-discovery activities in their practicum course, a two-cycle experiment was carried out with a class of 13 MA translation students with an attempt to explore their risk management while translating in a simulated setting that involves translator-client relations. To test the effects of the main variable of translators’ interaction with the simulated clients, the researcher employed control-group translators and two experiment groups (with Group A being the translator in Cycle 1 and the client in Cycle 2, and Group B on the client position in Cycle 1 and the translator position in Cycle 2). Experiment cycle 1 aims to explore if there would be any behavioral difference in risk management between translators with interaction with the simulated clients, i.e. experiment group A, and their counterparts without such interaction, i.e. control group. Design of Cycle 2 concerns the order of playing different roles of the translator and client in the experiment, and provides information to compare behavior of translators of the two experiment groups. Since this is process-oriented research, it is necessary to hypothesize what was happening in the translators’ minds. The researcher made use of a user-friendly screen-voice recording freeware to record subjects’ screen activities, including every word the translator typed and every change they made to the rendition, the websites they browsed and the reference tools they used, in addition to the verbalization of their thoughts throughout the process. The research observes the translation procedures subjects considered and finally adopted, and looks into the justifications for their procedures, in order to interpret their risk management. The qualitative and quantitative results of this study have some implications for translator training: (a) the experience of being a client seems to reinforce the translator’s risk aversion; (b) the use of role-playing simulation can empower students’ learning by enhancing their attitudinal or psycho-physiological competence, interpersonal competence and strategic competence; and (c) the screen-voice recordings serve as a helpful tool for learners to reflect on their rendition processes, i.e. what they performed satisfactorily and unsatisfactorily while translating and what they could do for improvement in future translation tasks.

Keywords: risk management, screen-voice recordings, simulated translator-client relations, translation pedagogy, translation process-oriented research

Procedia PDF Downloads 252

Authors: S. H. Nguyen, L. Li, R. S. Hegarty

Abstract:

Two experiments were conducted assessing the effects of presence or absence of rumen protozoa and dietary nitrate addition on rumen fermentation characteristics and methane production in Brahman heifers. The first experiment assessed changes in rumen fermentation pattern and in-vitro methane production post-refaunation and the second experiment investigated whether addition of nitrate to the incubation would give rise to methane mitigation additional to that contributed by defaunation. Ten Brahman heifers were progressively adapted to a diet containing coconut oil distillate 4.5% (COD) for 18 d and then all heifers were defaunated using sodium 1-(2-sulfonatooxyethoxy) dodecane (Empicol). After 15 d, the heifers were given a second dose of Empicol. Fifteen days after the second dosing, all heifers were allocated to defaunated or refaunated groups by stratified randomisation. On d 48, an oral dose of rumen fluid collected from unrelated faunated cattle was used to inoculate 5 heifers and form a refaunated group so that the effects of re-establishment of protozoa on fermentation characteristics could be investigated. Samples of rumen fluid collected from each animal using oesophageal intubation before feeding on d 48, 55, 62 and 69 were incubated for 23h in-vitro (experiment 1). On day 82, 2% of NO3 (as NaNO3) was included in in-vitro incubations (experiment 2) to test for additivity of NO3 and absence of protozoa effects on fermentation and methane production. It was concluded that increasing protozoal numbers were associated with increased methane production, with methane production rate significantly higher from refaunated heifers than from defaunated heifers 7, 14 and 21 d after refaunation. Concentration and proportions of major VFA, however, were not affected by protozoal treatments. There is scope for further reducing methane output through combining defaunation and dietary nitrate as the addition of nitrate in the defaunated heifers resulted in 86% reduction in methane production in-vitro.

Keywords: defaunation, nitrate, fermentation, methane production

Procedia PDF Downloads 538

Authors: D. K. Sreekantha, T. M. Girish, R. H. Fattepur

Abstract:

In this article, we have given an overview of medical expert systems, which can be used for the developed of physicians in making decisions such as appropriate, prognostic, and therapeutic decisions which help to organize, store, and gives appropriate medical knowledge needed by physicians and practitioners during medical operations or further treatment. If they support the studies by using these systems, advanced tools in medicine will be developed in the future. New trends in the methodology of development of medical expert systems have also been discussed in this paper. So Authors would like to develop an innovative IT based solution to help doctors in rural areas to gain expertise in Medical Science for treating patients. This paper aims to survey the Soft Computing techniques in treating patient’s problems used throughout the world.

Keywords: expert system, fuzzy logic, knowledge base, soft computing, epilepsy

Procedia PDF Downloads 241

Authors: Shraddha Jain Sharma, Ratnalata Gupta

Abstract:

Predicting stock movements in the financial market is both difficult and rewarding. Analysts and academics are increasingly using advanced approaches such as machine learning techniques to anticipate stock price patterns, thanks to the expanding capacity of computing and the recent advent of graphics processing units and tensor processing units. Stock market prediction is a type of time series prediction that is incredibly difficult to do since stock prices are influenced by a variety of financial, socioeconomic, and political factors. Furthermore, even minor mistakes in stock market price forecasts can result in significant losses for companies that employ the findings of stock market price prediction for financial analysis and investment. Soft computing techniques are increasingly being employed for stock market prediction due to their better accuracy than traditional statistical methodologies. The proposed research looks at the need for soft computing techniques in stock market prediction, the numerous soft computing approaches that are important to the field, past work in the area with their prominent features, and the significant problems or issue domain that the area involves. For constructing a predictive model, the major focus is on neural networks and fuzzy logic. The stock market is extremely unpredictable, and it is unquestionably tough to correctly predict based on certain characteristics. This study provides a complete overview of the numerous strategies investigated for high accuracy prediction, with a focus on the most important characteristics.

Keywords: stock market prediction, artificial intelligence, artificial neural networks, fuzzy logic, accuracy, deep learning, machine learning, stock price, trading volume

Procedia PDF Downloads 71

Authors: Yan Yu, Wang Yu, Chen Xintong, Liu Yi, Zhang Yanzhong, Wang Yanji, Chen Xingyu, Zhang Miaocheng, Tong Yi

Abstract:

Neuromorphic computing based on spiking neural networks (SNNs) has emerged as a promising avenue for building the next generation of intelligent computing systems. Owing to its high-density integration, low power, and outstanding nonlinearity, memristors have attracted emerging attention on achieving SNNs. However, fabricating a low-power and robust memristor-based spiking neuron without extra electrical components is still a challenge for brain-inspired systems. In this work, we demonstrate a TiO₂-based threshold switching (TS) memristor to emulate a leaky integrate-and-fire (LIF) neuron without auxiliary circuits, used to realize single layer fully connected (FC) SNNs. Moreover, our TiO₂-based resistive switching (RS) memristors realize spiking-time-dependent-plasticity (STDP), originating from the Ag diffusion-based filamentary mechanism. This work demonstrates that TiO2-based memristors may provide an efficient method to construct hardware neuromorphic computing systems.

Keywords: leaky integrate-and-fire, memristor, spiking neural networks, spiking-time-dependent-plasticity

Procedia PDF Downloads 116

Authors: Mintu Philip, Renumol V. G.

Abstract:

An introductory programming course is a major challenge faced in Computing Education. Many of the introductory programming courses fail because student concentrate mainly on writing programs using a programming language rather than involving in problem solving. Computational thinking is a general approach to solve problems. This paper proposes a new preliminary course that aims to develop computational thinking skills in students, which may help them to become good programmers. The proposed course is designed based on the four basic components of computational thinking - abstract thinking, logical thinking, modeling thinking and constructive thinking. In this course, students are engaged in hands-on problem solving activities using a new problem solving model proposed in this paper.

Keywords: computational thinking, computing education, abstraction, constructive thinking, modelling thinking

Procedia PDF Downloads 437

Authors: Ale M. O., Manuwa S. I., Olukunle O. J., Ewetumo T.

Abstract:

Five varying speeds of 1.5, 1.8, 2.1, 2.3, and 2.6 km/h were used at a constant soil depth of 100 mm to determine the effects of forward speed on the draught requirement of a semi-automatic cassava planter under the pneumatic wheel and rigid wheel usage on a well prepared sandy clay loam soil. The soil draught was electronically measured using an on-the-go soil draught measuring instrumentation system developed for the purpose of this research. The results showed an exponential relationship between forward speed and draught, in which draught ranging between 24.91 and 744.44N increased with an increase in forward speed in the rigid wheel experiment. This is contrary to the polynomial relationship observed in the pneumatic wheel experiment in which the draught varied between 96.09 and 343.53 N. It was observed in the experiments that the optimum speed of 1.5 km/h had the least values of draught in both the pneumatic wheel and rigid wheel experiments, with higher values in the pneumatic experiment. It was generally noted that the rigid wheel planter with less value of draught requires less energy required for operation. It is therefore concluded that operating the semi-automatic cassava planter with rigid wheels will be more economical for cassava farmers than operating the planter with pneumatic wheels.

Keywords: Cassava planter, planting, forward speed, draught, wheel type

Procedia PDF Downloads 78

Authors: Yizhen Zhao, Adam S. Z. Belloum, Goncalo Maia Da Costa, Zhiming Zhao

Abstract:

Machine learning has evolved from an area of academic research to a real-word applied field. This change comes with challenges, gaps and differences exist between common practices in academic environments and the ones in production environments. Following continuous integration, development and delivery practices in software engineering, similar trends have happened in machine learning (ML) systems, called MLOps. In this paper we propose a framework that helps to streamline and introduce best practices that facilitate the ML lifecycle in an industrial setting. This framework can be used as a template that can be customized to implement various machine learning experiment. The proposed framework is modular and can be recomposed to be adapted to various use cases (e.g. data versioning, remote training on cloud). The framework inherits practices from DevOps and introduces other practices that are unique to the machine learning system (e.g.data versioning). Our MLOps practices automate the entire machine learning lifecycle, bridge the gap between development and operation.

Keywords: cloud computing, continuous development, data versioning, DevOps, industrial setting, MLOps

Procedia PDF Downloads 249

Authors: Seun Mayowa Sunday

Abstract:

Loan prediction is one of the most significant and recognised fields of research in the banking, insurance, and the financial security industries. Some prediction systems on the market include the construction of static software. However, due to the fact that static software only operates with strictly regulated rules, they cannot aid customers beyond these limitations. Application of many machine learning (ML) techniques are required for loan prediction. Four separate machine learning models, random forest (RF), decision tree (DT), k-nearest neighbour (KNN), and logistic regression, are used to create the loan prediction model. Using the anaconda navigator and the required machine learning (ML) libraries, models are created and evaluated using the appropriate measuring metrics. From the finding, the random forest performs with the highest accuracy of 80.17% which was later implemented into the Django framework. For real-time testing, the web application is deployed on the Alibabacloud which is among the top 4 biggest cloud computing provider. Hence, to the best of our knowledge, this research will serve as the first academic paper which combines the model development and the Django framework, with the deployment into the Alibaba cloud computing application.

Keywords: k-nearest neighbor, random forest, logistic regression, decision tree, django, cloud computing, alibaba cloud

Procedia PDF Downloads 113

Authors: Mohammed Nadir Djedid, Abdallah Chouarfia

Abstract:

Transparency of the system and its integration into the natural environment of the user are some of the important features of pervasive computing. But these characteristics that are considered as the strongest points of pervasive systems are also their weak points in terms of the user’s privacy. The privacy in pervasive systems involves more than the confidentiality of communications and concealing the identity of virtual users. The physical presence and behavior of the user in the pervasive space cannot be completely hidden and can reveal the secret of his/her identity and affect his/her privacy. This paper shows that the application of major techniques for protecting the user’s privacy still insufficient. A new solution named Shadow Protocol is proposed, which allows the users to authenticate and interact with the surrounding devices within an ubiquitous computing environment while preserving their privacy.

Keywords: pervasive systems, identification, authentication, privacy

Procedia PDF Downloads 458

Authors: Ian A. McCulloh, Madelaine Zinser, Jesse Patsolic, Michael Ramos

Abstract:

Recommender systems are a common artificial intelligence (AI) application. For any given input, a search system will return a rank-ordered list of similar items. As users review returned items, they must decide when to halt the search and either revise search terms or conclude their requirement is novel with no similar items in the database. We present a statistically designed experiment that investigates the impact of similarity ratings on human judgement to conclude a search item is novel and halt the search. 450 participants were recruited from Amazon Mechanical Turk to render judgement across 12 decision tasks. We find the inclusion of ratings increases the human perception that items are novel. Percent similarity increases novelty discernment when compared with star-rated similarity or the absence of a rating. Ratings reduce the time to decide and improve decision confidence. This suggests the inclusion of similarity ratings can aid human decision-makers in knowledge search tasks.

Keywords: ratings, rankings, crowdsourcing, empirical studies, user studies, similarity measures, human-centered computing, novelty in information retrieval

Procedia PDF Downloads 106

Authors: Hatim Elhag

Abstract:

Banking and Financial Service Institutions are possibly the most advanced in terms of technology adoption and use it as a key differentiator. With high levels of business process automation, maturity in the functional portfolio, straight through processing and proven technology outsourcing benefits, Banking sector stand to benefit significantly from Cloud computing capabilities. Additionally, with complex Compliance and Regulatory policies, combined with expansive products and geography coverage, the business impact is even greater. While the benefits are exponential, there are also significant challenges in adopting this model– including Legal, Security, Performance, Reliability, Transformation complexity, Operating control and Governance and most importantly proof for the promised cost benefits. However, new architecture designed should be implemented to align this approach.

Keywords: security, cloud, banking sector, cloud computing

Procedia PDF Downloads 484

Authors: Chane-Yu Lai, Xiang-Yu Huang

Abstract:

This study conducted an assessment of sampling result by using the new development rotation filtration device (RFD) filled with porous media filters integrating the method of cyclone centrifugal spins. The testing system established for the experiment used corn oil and potassium sodium tartrate tetrahydrate (PST) as challenge aerosols and were produced by using an Ultrasonic Atomizing Nozzle, a Syringe Pump, and a Collison nebulizer. The collection efficiency of RFD for oil aerosol was assessed by using an Aerodynamic Particle Sizer (APS) and a Fidas® Frog. The results of RFD for the liquid particles condition indicated the cutoff size was 1.65 µm and 1.02 µm for rotation of 0 rpm and 9000 rpm, respectively, under an 80 PPI (pores per inch）foam with a thickness of 80 mm, and sampling velocity of 13.5 cm/s. As the experiment increased the foam thickness of RFD, the cutoff size reduced from 1.62 µm to 1.02 µm. However, when increased the foam porosity of RFD, the cutoff size reduced from 1.26 µm to 0.96 µm. Moreover, as increased the sampling velocity of RFD, the cutoff size reduced from 1.02 µm to 0.76 µm. These discrepancies of above cutoff sizes of RFD all had statistical significance (P < 0.05). The cutoff size of RFD for three experimental conditions of generated liquid oil particles, solid PST particles or both liquid oil and solid PST particles was 1.03 µm, 1.02 µm, or 0.99 µm, respectively, under a 80 PPI foam with thickness of 80 mm, rotation of 9000 rpm, and sampling velocity of 13.5 cm/s. In addition, under the best condition of the experiment, two hours of sampling loading, the RFD had better collection efficiency for particle diameter greater than 0.45 µm, under a 94 PPI nickel mesh with a thickness of 68 mm, rotation of 9000 rpm, and sampling velocity of 108.3 cm/s. The experiment concluded that increased the thickness of porous media, face velocity, and porosity of porous media of RFD could increase the collection efficiency of porous media for sampling oil particles. Moreover, increased the rotation speed of RFD also increased the collection efficiency for sampling oil particles. Further investigation is required for those above operation parameters for RFD in this study in the future.

Keywords: oil aerosol, porous media filter, rotation, filtration

Procedia PDF Downloads 384

Authors: Tamara Trček Pečak, Andrej Mohar, Denis Trček

Abstract:

This article investigates the latest technological means, which deploy smart structures that are based on (advanced) wireless sensors technologies and ubiquitous computing in general in order to support the above mentioned decision making. Based on two years of in-field research experiences it gives their analysis for these kinds of purposes and provides appropriate architectures and architectural solutions. Moreover, the directions for future research are stated, because these technologies are currently the most promising ones to enable cost-effective preservation of cultural heritage not only in uncontrolled places, but also in general.

Keywords: smart structures, wireless sensors, sensors networks, green computing, cultural heritage preservation, monitoring, cost effectiveness

Procedia PDF Downloads 429

Authors: Elias Nemer, Greg Vines

Abstract:

Time-frequency transformation and spectral representations of audio signals are commonly used in various machine learning applications. Training networks on frequency features such as the Mel-Spectrogram or Cochleogram have been proven more effective and convenient than training on-time samples. In practical realizations, these features are created on a different processor and/or pre-computed and stored on disk, requiring additional efforts and making it difficult to experiment with different features. In this paper, we provide a PyTorch framework for creating various spectral features as well as time-frequency transformation and time-domain filter-banks using the built-in trainable conv1d() layer. This allows computing these features on the fly as part of a larger network and enabling easier experimentation with various combinations and parameters. Our work extends the work in the literature developed for that end: First, by adding more of these features and also by allowing the possibility of either starting from initialized kernels or training them from random values. The code is written as a template of classes and scripts that users may integrate into their own PyTorch classes or simply use as is and add more layers for various applications.

Keywords: neural networks Mel-Spectrogram, chromagram, cochleogram, discrete Fourrier transform, PyTorch conv1d()

Procedia PDF Downloads 215