Search results for: theoretical computer science

Authors: Umair Shoukat Ali, Kamil Zafar, Rashna Hoshang Sukhia, Mubassar Fida, Aqeel Ahmed

Abstract:

Objective: This systematic review and meta-analysis aimed to summarize the effectiveness of bonded and removable retainers (Hawley and Essix retainer) in terms of improvement in occlusal settling (occlusal contact points/areas) after orthodontic treatment. Search Method: We searched the Cochrane Library, CINAHL Plus, PubMed, Web of Science, Orthodontic journals, and Google scholar for eligible studies. We included randomized control trials (RCT) along with Cohort studies. Studies that reported occlusal contacts/areas during retention with fixed bonded and removable retainers were included. To assess the quality of the RCTs Cochrane risk of bias tool was utilized, whereas Newcastle-Ottawa Scale was used for assessing the quality of cohort studies. Data analysis: The data analysis was limited to reporting mean values of occlusal contact points/areas with different retention methods. By utilizing the RevMan software V.5.3, a meta-analysis was performed for all the studies with the quantitative data. For the computation of the summary effect, a random effect model was utilized in case of high heterogeneity. I2 statistics were utilized to assess the heterogeneity among the selected studies. Results: We included 6 articles in our systematic review after scrutinizing 219 articles and eliminating them based on duplication, titles, and objectives. We found significant differences between fixed and removable retainers in terms of occlusal settling within the included studies. Bonded retainer (BR) allowed faster and better posterior tooth settling as compared to Hawley retainer (HR). However, HR showed good occlusal settling in the anterior dental arch. Essix retainer showed a decrease in occlusal contact during the retention phase. Meta-analysis showed no statistically significant difference between BR and removable retainers. Conclusions: HR allowed better overall occlusal settling as compared to other retainers in comparison. However, BR allowed faster settling in the posterior teeth region. Overall, there are insufficient high-quality RCTs to provide additional evidence, and further high-quality RCTs research is needed.

Keywords: orthodontic retainers, occlusal contact, Hawley, fixed, vacuum-formed

Procedia PDF Downloads 104

Authors: Sugandhi, Parteek Kumar, Sanmeet Kaur

Abstract:

Sign Language (SL) is used by deaf and other people who cannot speak but can hear or have a problem with spoken languages due to some disability. It is a visual gesture language that makes use of either one hand or both hands, arms, face, body to convey meanings and thoughts. SL automation system is an effective way which provides an interface to communicate with normal people using a computer. In this paper, an avatar based dictionary has been proposed for text to Indian Sign Language (ISL) generation system. This research work will also depict a literature review on SL corpus available for various SL s over the years. For ISL generation system, a written form of SL is required and there are certain techniques available for writing the SL. The system uses Hamburg sign language Notation System (HamNoSys) and Signing Gesture Mark-up Language (SiGML) for ISL generation. It is developed in PHP using Web Graphics Library (WebGL) technology for 3D avatar animation. A multilingual ISL dictionary is developed using HamNoSys for both English and Hindi Language. This dictionary will be used as a database to associate signs with words or phrases of a spoken language. It provides an interface for admin panel to manage the dictionary, i.e., modification, addition, or deletion of a word. Through this interface, HamNoSys can be developed and stored in a database and these notations can be converted into its corresponding SiGML file manually. The system takes natural language input sentence in English and Hindi language and generate 3D sign animation using an avatar. SL generation systems have potential applications in many domains such as healthcare sector, media, educational institutes, commercial sectors, transportation services etc. This research work will help the researchers to understand various techniques used for writing SL and generation of Sign Language systems.

Keywords: avatar, dictionary, HamNoSys, hearing impaired, Indian sign language (ISL), sign language

Procedia PDF Downloads 205

Authors: M. R. Zaman, M. S. Bari, M. Kajal

Abstract:

A field experiment was conducted at the Agroforestry and Environment Research Field, Hajee Mohammad Danesh Science and Technology University, Dinajpur during 2013 to investigate the potentiality of three napier fodder varieties under Litchi orchard. The experiment was consisted of 2 factors RCBD with 3 replications. Among the two factors, factor A was two production systems; S1= Litchi + fodder and S2 = Fodder (sole crop); another factor B was three napier varieties: V1= BARI Napier -1 (Bazra), V2= BARI Napier - 2 (Arusha) and V3= BARI Napier -3 (Hybrid). The experimental results revealed that there were significant variation among the varieties in terms of leaf growth and yield. The maximum number of leaf plant -1 was recorded in variety Bazra (V1) whereas the minimum number was recorded in hybrid variety (V3).Significantly the highest (13.75, 14.53 and14.84 tha-1 at 1st, 2nd and 3rd harvest respectively) yield was also recorded in variety Bazra whereas the lowest (5.89, 6.36 and 9.11 tha-1 at 1st, 2nd v and 3rd harvest respectively) yield was in hybrid variety. Again, in case of production systems, there were also significant differences between the two production systems were founded. The maximum number of leaf plant -1 was recorded under Litchi based AGF system (T1) whereas the minimum was recorded in open condition (T2). Similarly, significantly the highest (12.00, 12.35 and 13.31 tha-1 at 1st, 2nd and 3rd harvest respectively) yield of napier was recorded under Litchi based AGF system where as the lowest (9.73, 10.47 and 11.66 tha-1 at 1st, 2nd and 3rd harvest respectively) yield was recorded in open condition i.e. napier in sole cropping. Furthermore, the interaction effect of napier variety and production systems were also gave significant deviation result in terms of growth and yield. The maximum number of leaf plant -1 was recorded under Litchi based AGF systems with Bazra variety whereas the minimum was recorded in open condition with hybrid variety. The highest yield (14.42, 16.14 and 16.15 tha-1 at 1st, 2nd and 3rd harvest respectively) of napier was found under Litchi based AGF systems with Bazra variety. Significantly the lowest (5.33, 5.79 and 8.48 tha-1 at 1st, 2nd and 3rd harvest respectively) yield was found in open condition i.e. sole cropping with hybrid variety. In case of the quality perspective, the highest nutritive value (DM, ASH, CP, CF, EE, and NFE) was found in Bazra (V1) and the lowest value was found in hybrid variety (V3). Therefore, the suitability of napier production under Litchi based AGF system may be ranked as Bazra > Arusha > Hybrid variety. Finally, the economic analysis showed that maximum BCR (5.20) was found in the Litchi based AGF systems over sole cropping (BCR=4.38). From the findings of the taken investigation, it may be concluded that the cultivation of Bazra napier varieties in the floor of Litchi orchard ensures higher revenue to the farmers compared to its sole cropping.

Keywords: potentiality, Litchi, fodder, agroforestry

Procedia PDF Downloads 301

Authors: Fu Jia

Abstract:

The effects of soil-structure interaction (SSI) are often studied using axial-symmetric three-dimensional (3D) models to avoid the high computational cost of the more realistic, fully 3D models, which require 2-3 orders of magnitude more computer time and storage. This paper analyzes the error and presents correction factors for system frequency, system damping, and peak amplitude of structural response computed by axisymmetric models, embedded in uniform or layered half-space. The results are compared with those for fully 3D rectangular foundations of different aspect ratios. Correction factors are presented for a range of the model parameters, such as fixed-base frequency, structure mass, height and length-to-width ratio, foundation embedment, soil-layer stiffness and thickness. It is shown that the errors are larger for stiffer, taller and heavier structures, deeper foundations and deeper soil layer. For example, for a stiff structure like Millikan Library (NS response; length-to-width ratio 1), the error is 6.5% in system frequency, 49% in system damping and 180% in peak amplitude. Analysis of a case study shows that the NEHRP-2015 provisions for reduction of base shear force due to SSI effects may be unsafe for some structures and need revision. The presented correction factor diagrams can be used in practical design and other applications.

Keywords: 3D soil-structure interaction, correction factors for axisymmetric models, length-to-width ratio, NEHRP-2015 provisions for reduction of base shear force, rectangular embedded foundations, SSI system frequency, SSI system damping

Procedia PDF Downloads 240

Authors: Raluca-Ioana Antonescu

Abstract:

The paper treats about the Korean public diplomacy and national branding strategies, and how the Korean language textbooks were used in order to construct the Korean national image. The field research of the paper stands at the intersection between Linguistics and Political Science, while the problem of the research is the role of language and culture in national branding process. The research goal is to contribute to the literature situated at the intersection between International Relations and Applied Linguistics, while the objective is to conceptualize the idea of national branding by emphasizing a dimension which is not much discussed, and that would be the education as an instrument of the national branding and public diplomacy strategies. In order to examine the importance of language upon the national branding strategies, the paper will answer one main question, How is the Korean language used in the construction of national branding?, and two secondary questions, How are explored in literature the relations between language and national branding construction? and What kind of image of South Korea the language textbooks for foreigners transmit? In order to answer the research questions, the paper starts from one main hypothesis, that the language is an essential component of the culture, which is used in the construction of the national branding influenced by traditional elements (like Confucianism) but also by modern elements (like Western influence), and from two secondary hypothesis, the first one is that in the International Relations literature there are little explored the connections between language and national branding, while the second hypothesis is that the South Korean image is constructed through the promotion of a traditional society, but also a modern one. In terms of methodology, the paper will analyze the textbooks used in Romania at the universities which provide Korean Language classes during the three years program B.A., following the dialogs, the descriptive texts and the additional text about the Korean culture. The analysis will focus on the rank status difference, the individual in relation to the collectivity, the respect for the harmony, and the image of the foreigner. The results of the research show that the South Korean image projected in the textbooks convey the Confucian values and it does not emphasize the changes suffered by the society due to the modernity and globalization. The Westernized aspect of the Korean society is conveyed more in an informative way about the Korean international companies, Korean internal development (like the transport or other services), but it does not show the cultural changed the society underwent. Even if the paper is using the textbooks which are used in Romania as a teaching material, it could be used and applied at least to other European countries, since the textbooks are the ones issued by the South Korean language schools, which other European countries are using also.

Keywords: confucianism, modernism, national branding, public diplomacy, traditionalism

Procedia PDF Downloads 217

Authors: Juan C. Torrado, Javier Gomez, Guadalupe Montero, German Montoro, M. Dolores Villalba

Abstract:

One of the most challenging aspects of the executive dysfunction of people with Autism Spectrum Disorders is the behavior control. This is related to a deficit in their ability to regulate, recognize and manage their own emotions. Some researchers have developed applications for tablets and smartphones to practice strategies of relaxation and emotion recognition. However, they cannot be applied to the very moment of temper outbursts, anger episodes or anxiety, since they require to carry the device, start the application and be helped by caretakers. Also, some of these systems are developed for either obsolete technologies (old versions of tablet devices, PDAs, outdated operative systems of smartphones) or specific devices (self-developed or proprietary ones) that create differentiation between the users and the rest of the individuals in their context. For this project we selected smartwatches. Focusing on emergent technologies ensures a wide lifespan of the developed products, because the derived products are intended to be available in the same moment the very technology gets popularized, not later. We also focused our research in commercial versions of smartwatches, since this way differentiation is easily avoided, so the users’ abandonment rate lowers. We have developed a smartwatch system along with a smartphone authoring tool to display self-regulation strategies. These micro-prompting strategies are conformed of pictograms, animations and temporizers, and they are designed by means of the authoring tool: When both devices synchronize their data, the smartwatch holds the self-regulation strategies, which are triggered when the smartwatch sensors detect a remarkable rise of heart rate and movement. The system is being currently tested in an educational center of people with ASD of Madrid, Spain.

Keywords: assistive technologies, emotion regulation, human-computer interaction, smartwatches

Procedia PDF Downloads 278

Authors: Thelma Palaoag, Melanie Basa, Jezreel Mark Panilo

Abstract:

Checking short-answer questions and essays, whether it may be paper or electronic in form, is a tiring and tedious task for teachers. Evaluating a student’s output require wide array of domains. Scoring the work is often a critical task. Several attempts in the past few years to create an automated writing assessment software but only have received negative results from teachers and students alike due to unreliability in scoring, does not provide feedback and others. The study aims to create an application that will be able to check short-answer questions which incorporate information extraction. Information extraction is a subfield of Natural Language Processing (NLP) where a chunk of text (technically known as unstructured text) is being broken down to gather necessary bits of data and/or keywords (structured text) to be further analyzed or rather be utilized by query tools. The proposed system shall be able to extract keywords or phrases from the individual’s answers to match it into a corpora of words (as defined by the instructor), which shall be the basis of evaluation of the individual’s answer. The proposed system shall also enable the teacher to provide feedback and re-evaluate the output of the student for some writing elements in which the computer cannot fully evaluate such as creativity and logic. Teachers can formulate, design, and check short answer questions efficiently by defining keywords or phrases as parameters by assigning weights for checking answers. With the proposed system, teacher’s time in checking and evaluating students output shall be lessened, thus, making the teacher more productive and easier.

Keywords: information extraction, short-answer question, natural language processing, application

Procedia PDF Downloads 411

Authors: A. Zuchowska, A. Buta, M. Mazurkiewicz-Pawlicka, A. Malolepszy, L. Stobinski, Z. Brzozka

Abstract:

In recent years, graphene-based materials are finding more and more applications in biological science. As a thin, tough, transparent and chemically resistant materials, they appear to be a very good material for the production of implants and biosensors. Interest in graphene derivatives also resulted at the beginning of research about the possibility of their application in cancer therapy. Currently, the analysis of their potential use in photothermal therapy and as a drug carrier is mostly performed. Moreover, the direct anticancer properties of graphene-based materials are also tested. Nowadays, cytotoxic studies are conducted on in vitro cell culture in standard culture vessels (macroscale). However, in this type of cell culture, the cells grow on the synthetic surface in static conditions. For this reason, cell culture in macroscale does not reflect in vivo environment. The microfluidic systems, called Lab-on-a-chip, are proposed as a solution for improvement of cytotoxicity analysis of new compounds. Here, we present the evaluation of cytotoxic properties of graphene oxide (GO) on breast, liver and colon cancer cell line in a microfluidic system in two spatial models (2D and 3D). Before cell introduction, the microchambers surface was modified by the fibronectin (2D, monolayer) and poly(vinyl alcohol) (3D, spheroids) covering. After spheroid creation (3D) and cell attachment (2D, monolayer) the selected concentration of GO was introduced into microsystems. Then monolayer and spheroids viability/proliferation using alamarBlue® assay and standard microplate reader was checked for three days. Moreover, in every day of the culture, the morphological changes of cells were determined using microscopic analysis. Additionally, on the last day of the culture differential staining using Calcein AM and Propidium iodide were performed. We were able to note that the GO has an influence on all tested cell line viability in both monolayer and spheroid arrangement. We showed that GO caused higher viability/proliferation decrease for spheroids than a monolayer (this was observed for all tested cell lines). Higher cytotoxicity of GO on spheroid culture can be caused by different geometry of the microchambers for 2D and 3D cell cultures. Probably, GO was removed from the flat microchambers for 2D culture. Those results were also confirmed by differential staining. Comparing our results with the studies conducted in the macroscale, we also proved that the cytotoxic properties of GO are changed depending on the cell culture conditions (static/ flow).

Keywords: cytotoxicity, graphene oxide, monolayer, spheroid

Procedia PDF Downloads 107

Authors: Sakshi Dhumale, Madhushree C., Amba Shetty

Abstract:

The effect of station density on the geostatistical prediction of groundwater levels is of critical importance to ensure accurate and reliable predictions. Monitoring station density directly impacts the accuracy and reliability of geostatistical predictions by influencing the model's ability to capture localized variations and small-scale features in groundwater levels. This is particularly crucial in regions with complex hydrogeological conditions and significant spatial heterogeneity. Insufficient station density can result in larger prediction uncertainties, as the model may struggle to adequately represent the spatial variability and correlation patterns of the data. On the other hand, an optimal distribution of monitoring stations enables effective coverage of the study area and captures the spatial variability of groundwater levels more comprehensively. In this study, we investigate the effect of station density on the predictive performance of groundwater levels using the geostatistical technique of Ordinary Kriging. The research utilizes groundwater level data collected from 121 observation wells within the semi-arid Berambadi watershed, gathered over a six-year period (2010-2015) from the Indian Institute of Science (IISc), Bengaluru. The dataset is partitioned into seven subsets representing varying sampling densities, ranging from 15% (12 wells) to 100% (121 wells) of the total well network. The results obtained from different monitoring networks are compared against the existing groundwater monitoring network established by the Central Ground Water Board (CGWB). The findings of this study demonstrate that higher station densities significantly enhance the accuracy of geostatistical predictions for groundwater levels. The increased number of monitoring stations enables improved interpolation accuracy and captures finer-scale variations in groundwater levels. These results shed light on the relationship between station density and the geostatistical prediction of groundwater levels, emphasizing the importance of appropriate station densities to ensure accurate and reliable predictions. The insights gained from this study have practical implications for designing and optimizing monitoring networks, facilitating effective groundwater level assessments, and enabling sustainable management of groundwater resources.

Keywords: station density, geostatistical prediction, groundwater levels, monitoring networks, interpolation accuracy, spatial variability

Procedia PDF Downloads 32

Authors: M. S. Riyazulla

Abstract:

Since the dawn of the 21st century, there has been a perceptible decline in Islamic supremacy in world affairs, apart from the gradual waning of the amiable relations and relevance of Islamic countries in the International political arena. For a long, Islamic countries have been marginalised by the superpowers in the global conflicting issues. This was evident in the context of their recent invasions and interference in Afghanistan, Syria, Iraq, and Libya. The leading International Islamic organizations like the Arab League, Organization of Islamic Cooperation, Gulf Cooperation Council, and Muslim World League did not play any prominent role there in resolving the crisis that ensued due to the exogenous and endogenous causes. Hence, there is a need for Islamic countries to create a credible International Islamic organization that could dictate its terms and shape a new Islamic world order. The prominent Islamic countries are divided on ideological and religious fault lines. Their concord is indispensable to enhance their image and placate the relations with other countries and communities. The massive boon of oil and gas could be synergistically utilised to exhibit their omnipotence and eminence through constructive ways. The prevailing menace of Islamophobia could be abated through syncretic messages, discussions, and deliberations by the sagacious Islamic scholars with the other community leaders. Presently, as Muslims are at a crossroads, a dynamic leadership could navigate the agitated Muslim community on the constructive path and herald political stability around the world. The present political disorder, chaos, and economic challenges necessities a paradigm shift in approach to worldly affairs. This could also be accomplished through the advancement in science and technology, particularly space exploration, for peaceful purposes. The Islamic world, in order to regain its lost preeminence, should rise to the occasion in promoting peace and tranquility in the world and should evolve a rational and human-centric solution to global disputes and concerns. As a splendid contribution to humanity and for amicable international relations, they should devote all their resources and scientific intellect towards space exploration and should safely transport man from the Earth to the nearest and most accessible cosmic body, the Moon, within one hundred years as the mankind is facing the existential threat on the planet.

Keywords: carboniferous period, Earth, extinction, fossil fuels, global leaders, Islamic glory, international order, life, marginalization, Moon, natural catastrophes

Procedia PDF Downloads 52

Authors: Areti Angeliki Veroniki, Sofia Tsokani, Evangelos Paraskevaidis, Dimitris Mavridis

Abstract:

The plethora of diagnostic test accuracy (DTA) studies has led to the increased use of systematic reviews and meta-analysis of DTA studies. Clinicians and healthcare professionals often consult DTA meta-analyses to make informed decisions regarding the optimum test to choose and use for a given setting. For example, the human papilloma virus (HPV) DNA, mRNA, and cytology can be used for the cervical intraepithelial neoplasia grade 2+ (CIN2+) diagnosis. But which test is the most accurate? Studies directly comparing test accuracy are not always available, and comparisons between multiple tests create a network of DTA studies that can be synthesized through a network meta-analysis of diagnostic tests (DTA-NMA). The aim is to summarize the DTA-NMA methods for at least three index tests presented in the methodological literature. We illustrate the application of the methods using a real data set for the comparative accuracy of HPV DNA, HPV mRNA, and cytology tests for cervical cancer. A search was conducted in PubMed, Web of Science, and Scopus from inception until the end of July 2019 to identify full-text research articles that describe a DTA-NMA method for three or more index tests. Since the joint classification of the results from one index against the results of another index test amongst those with the target condition and amongst those without the target condition are rarely reported in DTA studies, only methods requiring the 2x2 tables of the results of each index test against the reference standard were included. Studies of any design published in English were eligible for inclusion. Relevant unpublished material was also included. Ten relevant studies were finally included to evaluate their methodology. DTA-NMA methods that have been presented in the literature together with their advantages and disadvantages are described. In addition, using 37 studies for cervical cancer obtained from a published Cochrane review as a case study, an application of the identified DTA-NMA methods to determine the most promising test (in terms of sensitivity and specificity) for use as the best screening test to detect CIN2+ is presented. As a conclusion, different approaches for the comparative DTA meta-analysis of multiple tests may conclude to different results and hence may influence decision-making. Acknowledgment: This research is co-financed by Greece and the European Union (European Social Fund- ESF) through the Operational Programme «Human Resources Development, Education and Lifelong Learning 2014-2020» in the context of the project “Extension of Network Meta-Analysis for the Comparison of Diagnostic Tests ” (MIS 5047640).

Keywords: colposcopy, diagnostic test, HPV, network meta-analysis

Procedia PDF Downloads 121

Authors: Stephanie Chen, Mitja Echim, Christof Büskens

Abstract:

To describe and propagate the behavior of a system mathematical models are formulated. Parameter identification is used to adapt the coefficients of the underlying laws of science. For complex systems this approach can be incomplete and hence imprecise and moreover too slow to be computed efficiently. Therefore, these models might be not applicable for the numerical optimization of real systems, since these techniques require numerous evaluations of the models. Moreover not all quantities necessary for the identification might be available and hence the system must be adapted manually. Therefore, an approach is described that generates models that overcome the before mentioned limitations by not focusing on physical laws, but on measured (sensor) data of real systems. The approach is more general since it generates models for every system detached from the scientific background. Additionally, this approach can be used in a more general sense, since it is able to automatically identify correlations in the data. The method can be classified as a multivariate data regression analysis. In contrast to many other data regression methods this variant is also able to identify correlations of products of variables and not only of single variables. This enables a far more precise and better representation of causal correlations. The basis and the explanation of this method come from an analytical background: the series expansion. Another advantage of this technique is the possibility of real-time adaptation of the generated models during operation. Herewith system changes due to aging, wear or perturbations from the environment can be taken into account, which is indispensable for realistic scenarios. Since these data driven models can be evaluated very efficiently and with high precision, they can be used in mathematical optimization algorithms that minimize a cost function, e.g. time, energy consumption, operational costs or a mixture of them, subject to additional constraints. The proposed method has successfully been tested in several complex applications and with strong industrial requirements. The generated models were able to simulate the given systems with an error in precision less than one percent. Moreover the automatic identification of the correlations was able to discover so far unknown relationships. To summarize the above mentioned approach is able to efficiently compute high precise and real-time-adaptive data-based models in different fields of industry. Combined with an effective mathematical optimization algorithm like WORHP (We Optimize Really Huge Problems) several complex systems can now be represented by a high precision model to be optimized within the user wishes. The proposed methods will be illustrated with different examples.

Keywords: adaptive modeling, automatic identification of correlations, data based modeling, optimization

Procedia PDF Downloads 383

Authors: Yi-Guang Li, Suresh Sampath

Abstract:

Gas turbine performance degrades over time, and the degradation is greatly affected by environmental, ambient, and operating conditions. The engines may degrade slowly under favorable conditions and result in a waste of engine life if a scheduled maintenance scheme is followed. They may also degrade fast and fail before a scheduled overhaul if the conditions are unfavorable, resulting in serious secondary damage, loss of engine availability, and increased maintenance costs. To overcome these problems, gas turbine owners are gradually moving from scheduled maintenance to condition-based maintenance, where condition monitoring is one of the key supporting technologies. This paper presents an integrated adaptive GPA diagnostics and performance monitoring system developed at Cranfield University for gas turbine gas path condition monitoring. It has the capability to predict the performance degradation of major gas path components of gas turbine engines, such as compressors, combustors, and turbines, using gas path measurement data. It is also able to predict engine key performance parameters for condition monitoring, such as turbine entry temperature that cannot be directly measured. The developed technology has been implemented into digital twin computer Software, Pythia, to support the condition monitoring of gas turbine engines. The capabilities of the integrated GPA condition monitoring system are demonstrated in three test cases using a model gas turbine engine similar to the GE aero-derivative LM2500 engine widely used in power generation and marine propulsion. It shows that when the compressor of the model engine degrades, the Adaptive GPA is able to predict the degradation and the changing engine performance accurately using gas path measurements. Such a presented technology and software are generic, can be applied to different types of gas turbine engines, and provide crucial engine health and performance parameters to support condition monitoring and condition-based maintenance.

Keywords: gas turbine, adaptive GPA, performance, diagnostics, condition monitoring

Procedia PDF Downloads 61

Authors: Jinsiang Shaw, Sheng-Xiang Xu

Abstract:

This paper presents the development of an autonomous automated guided vehicle (AGV) with a robot arm attached on top of it within the framework of robot operation system (ROS). ROS can provide libraries and tools, including hardware abstraction, device drivers, libraries, visualizers, message-passing, package management, etc. For this reason, this AGV can provide automatic navigation and parts transportation and pick-and-place task using robot arm for typical industrial production line use. More specifically, this AGV will be controlled by an on-board host computer running ROS software. Command signals for vehicle and robot arm control and measurement signals from various sensors are transferred to respective microcontrollers. Users can operate the AGV remotely through the TCP / IP protocol and perform SLAM (Simultaneous Localization and Mapping). An RGBD camera and LIDAR sensors are installed on the AGV, using these data to perceive the environment. For SLAM, Gmapping is used to construct the environment map by Rao-Blackwellized particle filter; and AMCL method (Adaptive Monte Carlo localization) is employed for mobile robot localization. In addition, current AGV position and orientation can be visualized by ROS toolkit. As for robot navigation and obstacle avoidance, A* for global path planning and dynamic window approach for local planning are implemented. The developed ROS AGV with a robot arm on it has been experimented in the university factory. A 2-D and 3-D map of the factory were successfully constructed by the SLAM method. Base on this map, robot navigation through the factory with and without dynamic obstacles are shown to perform well. Finally, pick-and-place of parts using robot arm and ensuing delivery in the factory by the mobile robot are also accomplished.

Keywords: automated guided vehicle, navigation, robot operation system, Simultaneous Localization and Mapping

Procedia PDF Downloads 129

Authors: Arash Parehkar, S. Jamshid Mousavi, Shoubo Bayazidi, Vahid Karami, Laleh Shahidi, Arash Azaranfar, Ali Moridi, M. Shabakhti, Tayebeh Ariyan, Mitra Tofigh, Kaveh Masoumi, Alireza Motahari

Abstract:

Water resource systems modelling have constantly been a challenge through history for human being. As the innovative methodological development is evolving alongside computer sciences on one hand, researches are likely to confront more complex and larger water resources systems due to new challenges regarding increased water demands, climate change and human interventions, socio-economic concerns, and environment protection and sustainability. In this research, an automatic calibration scheme has been applied on the Gilan’s large-scale water resource model using mathematical programming. The water resource model’s calibration is developed in order to attune unknown water return flows from demand sites in the complex Sefidroud irrigation network and other related areas. The calibration procedure is validated by comparing several gauged river outflows from the system in the past with model results. The calibration results are pleasantly reasonable presenting a rational insight of the system. Subsequently, the unknown optimized parameters were used in a basin-scale linear optimization model with the ability to evaluate the system’s performance against a reduced inflow scenario in future. Results showed an acceptable match between predicted and observed outflows from the system at selected hydrometric stations. Moreover, an efficient operating policy was determined for Sefidroud dam leading to a minimum water shortage in the reduced inflow scenario.

Keywords: auto-calibration, Gilan, large-scale water resources, simulation

Procedia PDF Downloads 319

Authors: Anthony D. Rhodes, Manan Goel

Abstract:

We provide a high fidelity deep learning algorithm (HyperSeg) for interactive video segmentation tasks using a dense convolutional network with context-aware skip connections and compressed, 'hypercolumn' image features combined with a convolutional tessellation procedure. In order to maintain high output fidelity, our model crucially processes and renders all image features in high resolution, without utilizing downsampling or pooling procedures. We maintain this consistent, high grade fidelity efficiently in our model chiefly through two means: (1) we use a statistically-principled, tensor decomposition procedure to modulate the number of hypercolumn features and (2) we render these features in their native resolution using a convolutional tessellation technique. For improved pixel-level segmentation results, we introduce a boundary loss function; for improved temporal coherence in video data, we include temporal image information in our model. Through experiments, we demonstrate the improved accuracy of our model against baseline models for interactive segmentation tasks using high resolution video data. We also introduce a benchmark video segmentation dataset, the VFX Segmentation Dataset, which contains over 27,046 high resolution video frames, including green screen and various composited scenes with corresponding, hand-crafted, pixel-level segmentations. Our work presents a improves state of the art segmentation fidelity with high resolution data and can be used across a broad range of application domains, including VFX pipelines and medical imaging disciplines.

Keywords: computer vision, object segmentation, interactive segmentation, model compression

Procedia PDF Downloads 102

Authors: Abigail Vallance

Abstract:

Current research shows a correlation between declining mental health in the United States and the effect of COVID-19 on young adults and adolescents. Anxiety and depression are the two most common psychiatric illnesses, which are also the leading impediments to academic success. Spending six hours a day or more using computers is associated with higher risks of depression, with this time constraint pervasive even in present-day academia. Along with many hours on the computer, common issues COVID-19 had on students’ academic performance during online school included technical difficulties, poor support services, and difficulty adapting to online learning. Given the volume of requirements with unrealistic deadlines, and despite experiencing COVID-19, students showed an increase in their levels of anxiety. Besides the prevalent effect of COVID-19 on mental health, many studies show a correlation between mental health, COVID-19, academia, and sports performance. Academic research showed that negative self-talk, in relation to one’s self-efficacy, correlated with negative academic performance. Research showed that students who reported negative self-efficacy when test-taking led to negative test results. Furthermore, in sports performance, negative effects were found when athletes engage in negative self-talk. Overall, motivational self-talk, by oneself and through teammates and coaches, correlated with better performance than regular self-talk in sports. In relation to sports performance, the COVID-19 pandemic canceled complete sports seasons for millions of adolescents across the country. Many student-athletes use their sport to release emotions and escape from their mental health, but this was taken away. The purpose of this study is to address the current increase in mental health diagnoses in adolescents, including suicide rates after the COVID-19 pandemic began in 2020.This literature analysis is actively being studied.

Keywords: self-talk, COVID-19, mental health, adolescents

Procedia PDF Downloads 37

Authors: Biki Sarmah, Priyanko Raj Mudiar

Abstract:

In the modern world of remotely interactive virtual reality-based learning and teaching, including professional skill-building training and acquisition practices, as well as data acquisition and robotic systems, the revolutionary application or implementation of field-programmable neurostimulator aids and first-hand interactive sensitisation techniques into 3D holographic audio-visual platforms have been a coveted dream of many scholars, professionals, scientists, and students. Integration of 'kinaesthetic vibrotactile haptic perception' along with an actuated step magnitude contact profiloscopy in augmented reality-based learning platforms and professional training can be implemented by using an extremely calculated and well-coordinated image telemetry including remote data mining and control technique. A real-time, computer-aided (PLC-SCADA) field calibration based algorithm must be designed for the purpose. But most importantly, in order to actually realise, as well as to 'interact' with some 3D holographic models displayed over a remote screen using remote laser image telemetry and control, all spatio-physical parameters like cardinal alignment, gyroscopic compensation, as well as surface profile and thermal compositions, must be implemented using zero-order type 1 actuators (or transducers) because they provide zero hystereses, zero backlashes, low deadtime as well as providing a linear, absolutely controllable, intrinsically observable and smooth performance with the least amount of error compensation while ensuring the best ergonomic comfort ever possible for the users.

Keywords: haptic feedback, kinaesthetic vibrotactile 3D design, medical simulation training, piezo diaphragm based actuator

Procedia PDF Downloads 138

Authors: Zhao Yu, Zhi-Nan Zhang

Abstract:

More and more interactive devices are used in the transportation service system. Our mobile phones, on-board computers, and Head-Up Displays (HUDs) can all be used as the tools of the in-car service system. People can access smart systems with different terminals such as mobile phones, computers, pads and even their cars and watches. Different forms of terminals bring the different quality of interaction by the various human-computer Interaction modes. The new interactive devices require good ergonomics design at each stage of the whole design process. According to the theory of human factors and ergonomics, this paper compared three types of interactive devices by four driving tasks. Forty-eight drivers were chosen to experience these three interactive devices (mobile phones, on-board computers, and HUDs) by a simulate driving process. The subjects evaluated ergonomics performance and subjective workload after the process. And subjects were encouraged to support suggestions for improving the interactive device. The result shows that different interactive devices have different advantages in driving tasks, especially in non-driving tasks such as information and entertainment fields. Compared with mobile phones and onboard groups, the HUD groups had shorter response times in most tasks. The tasks of slow-up and the emergency braking are less accurate than the performance of a control group, which may because the haptic feedback of these two tasks is harder to distinguish than the visual information. Simulated driving is also helpful in improving the design of in-vehicle interactive devices. The paper summarizes the ergonomics characteristics of three in-vehicle interactive devices. And the research provides a reference for the future design of in-vehicle interactive devices through an ergonomic approach to ensure a good interaction relationship between the driver and the in-vehicle service system.

Keywords: human factors, industrial ergonomics, transportation system, usability, vehicle user interface

Procedia PDF Downloads 115

Authors: Maria Klitgaard Christensen, Carmen Lim, Sukanta Saha, Danielle Cannon, Finley Prentis, Oleguer Plana-Ripoll, Natalie Momen, Kim Moesgaard Iburg, John J. McGrath

Abstract:

Introduction: About a third of the world’s population will develop a mental disorder over their lifetime. Having a mental disorder is a huge burden in health loss and cost for the individual, but also for society because of treatment cost, production loss and caregivers’ cost. The objective of this study is to synthesize the international published literature on the economic burden of mental disorders. Methods: Systematic literature searches were conducted in the databases PubMed, Embase, Web of Science, EconLit, NHS York Database and PsychInfo using key terms for cost and mental disorders. Searches were restricted to 1980 until May 2019. The inclusion criteria were: (1) cost-of-illness studies or cost-analyses, (2) diagnosis of at least one mental disorder, (3) samples based on the general population, and (4) outcome in monetary units. 13,640 publications were screened by their title/abstract and 439 articles were full-text screened by at least two independent reviewers. 112 articles were included from the systematic searches and 31 articles from snowball searching, giving a total of 143 included articles. Results: Information about diagnosis, diagnostic criteria, sample size, age, sex, data sources, study perspective, study period, costing approach, cost categories, discount rate and production loss method and cost unit was extracted. The vast majority of the included studies were from Western countries and only a few from Africa and South America. The disorder group most often investigated was mood disorders, followed by schizophrenia and neurotic disorders. The disorder group least examined was intellectual disabilities, followed by eating disorders. The preliminary results show a substantial variety in the used perspective, methodology, costs components and outcomes in the included studies. An online tool is under development enabling the reader to explore the published information on costs by type of mental disorder, subgroups, country, methodology, and study quality. Discussion: This is the first systematic review synthesizing the economic cost of mental disorders worldwide. The paper will provide an important and comprehensive overview over the economic burden of mental disorders, and the output from this review will inform policymaking.

Keywords: cost-of-illness, health economics, mental disorders, systematic review

Procedia PDF Downloads 110

Authors: O. B. Iskender, K. V. Ling, V. Dubanchet, L. Simonini

Abstract:

This paper presents a Guidance and Control (G&C) strategy to address spacecraft maneuvering problem for future Rendezvous and Docking (RVD) missions. The proposed strategy allows safe and propellant efficient trajectories for space servicing missions including tasks such as approaching, inspecting and capturing. This work provides the validation test results of the G&C laws using a Hardware-In-the-Loop (HIL) setup with two robotic mockups representing the chaser and the target spacecraft. Through this paper, the challenges of the relative motion control in space are first summarized, and in particular, the constraints imposed by the mission, spacecraft and, onboard processing capabilities. Second, the proposed algorithm is introduced by presenting the formulation of constrained Model Predictive Control (MPC) to optimize the fuel consumption and explicitly handle the physical and geometric constraints in the system, e.g. thruster or Line-Of-Sight (LOS) constraints. Additionally, the coupling between translational motion and rotational motion is addressed via dual quaternion based kinematic description and accordingly explained. The resulting convex optimization problem allows real-time implementation capability based on a detailed discussion on the computational time requirements and the obtained results with respect to the onboard computer and future trends of space processors capabilities. Finally, the performance of the algorithm is presented in the scope of a potential future mission and of the available equipment. The results also cover a comparison between the proposed algorithms with Linear–quadratic regulator (LQR) based control law to highlight the clear advantages of the MPC formulation.

Keywords: autonomous vehicles, embedded optimization, real-time experiment, rendezvous and docking, space robotics

Procedia PDF Downloads 105

Authors: Halimatu S. Abdullahi, Ray E. Sheriff, Fatima Mahieddine

Abstract:

Agriculture is essential to the continuous existence of human life as they directly depend on it for the production of food. The exponential rise in population calls for a rapid increase in food with the application of technology to reduce the laborious work and maximize production. Technology can aid/improve agriculture in several ways through pre-planning and post-harvest by the use of computer vision technology through image processing to determine the soil nutrient composition, right amount, right time, right place application of farm input resources like fertilizers, herbicides, water, weed detection, early detection of pest and diseases etc. This is precision agriculture which is thought to be solution required to achieve our goals. There has been significant improvement in the area of image processing and data processing which has being a major challenge. A database of images is collected through remote sensing, analyzed and a model is developed to determine the right treatment plans for different crop types and different regions. Features of images from vegetations need to be extracted, classified, segmented and finally fed into the model. Different techniques have been applied to the processes from the use of neural network, support vector machine, fuzzy logic approach and recently, the most effective approach generating excellent results using the deep learning approach of convolution neural network for image classifications. Deep Convolution neural network is used to determine soil nutrients required in a plantation for maximum production. The experimental results on the developed model yielded results with an average accuracy of 99.58%.

Keywords: convolution, feature extraction, image analysis, validation, precision agriculture

Procedia PDF Downloads 295

Authors: Matthew J. Emes, Azadeh Jafari, Maziar Arjomandi

Abstract:

Velocity fluctuations of shear-generated turbulence are largest in the atmospheric surface layer (ASL) of nominal 100 m depth, which can lead to dynamic effects such as galloping and flutter on small physical structures on the ground when the turbulence length scales and characteristic length of the physical structure are the same order of magnitude. Turbulence length scales are a measure of the average sizes of the energy-containing eddies that are widely estimated using two-point cross-correlation analysis to convert the temporal lag to a separation distance using Taylor’s hypothesis that the convection velocity is equal to the mean velocity at the corresponding height. Profiles of turbulence length scales in the neutrally-stratified ASL, as predicted by Monin-Obukhov similarity theory in Engineering Sciences Data Unit (ESDU) 85020 for single-point data and ESDU 86010 for two-point correlations, are largely dependent on the aerodynamic roughness length. Field measurements have shown that longitudinal turbulence length scales show significant regional variation, whereas length scales of the vertical component show consistent Obukhov scaling from site to site because of the absence of low-frequency components. Hence, the objective of this experimental study is to compare the similarity theory relationships between the turbulence length scales and aerodynamic roughness length with those calculated using the autocorrelations and cross-correlations of field measurement velocity data at two sites: the Surface Layer Turbulence and Environmental Science Test (SLTEST) facility in a desert ASL in Dugway, Utah, USA and the Commonwealth Scientific and Industrial Research Organisation (CSIRO) wind tower in a rural ASL in Jemalong, NSW, Australia. The results indicate that the longitudinal turbulence length scales increase with increasing aerodynamic roughness length, as opposed to the relationships derived by similarity theory correlations in ESDU models. However, the ratio of the turbulence length scales in the lateral and vertical directions to the longitudinal length scales is relatively independent of surface roughness, showing consistent inner-scaling between the two sites and the ESDU correlations. Further, the diurnal variation of wind velocity due to changes in atmospheric stability conditions has a significant effect on the turbulence structure of the energy-containing eddies in the lower ASL.

Keywords: aerodynamic roughness length, atmospheric surface layer, similarity theory, turbulence length scales

Procedia PDF Downloads 114

Authors: Foad Hassaninejadafarahani, Scott Ormiston

Abstract:

Reflux condensation occurs in a vertical channels and tubes when there is an upward core flow of vapor (or gas-vapor mixture) and a downward flow of the liquid film. The understanding of this condensation configuration is crucial in the design of reflux condensers, distillation columns, and in loss-of-coolant safety analyses in nuclear power plant steam generators. The unique feature of this flow is the upward flow of the vapor-gas mixture (or pure vapor) that retards the liquid flow via shear at the liquid-mixture interface. The present model solves the full, elliptic governing equations in both the film and the gas-vapor core flow. The computational mesh is non-orthogonal and adapts dynamically the phase interface, thus produces sharp and accurate interface. Shear forces and heat and mass transfer at the interface are accounted for fundamentally. This modeling is a big step ahead of current capabilities by removing the limitations of previous reflux condensation models which inherently cannot account for the detailed local balances of shear, mass, and heat transfer at the interface. Discretisation has been done based on a finite volume method and a co-located variable storage scheme. An in-house computer code was developed to implement the numerical solution scheme. Detailed results are presented for laminar reflux condensation from steam-air mixtures flowing in vertical parallel plate channels. The results include velocity and pressure profiles, as well as axial variations of film thickness, Nusselt number and interface gas mass fraction.

Keywords: Reflux, Condensation, CFD-Two Phase, Nusselt number

Procedia PDF Downloads 349

Authors: Yuekun Chen, Yousef Sardahi, Salam Hajjar, Christopher Greer

Abstract:

This paper presents a multi-objective optimal design of a cascade control system for an underactuated mechanical system. Cascade control structures usually include two control algorithms (inner and outer). To design such a control system properly, the following conflicting objectives should be considered at the same time: 1) the inner closed-loop control must be faster than the outer one, 2) the inner loop should fast reject any disturbance and prevent it from propagating to the outer loop, 3) the controlled system should be insensitive to measurement noise, and 4) the controlled system should be driven by optimal energy. Such a control problem can be formulated as a multi-objective optimization problem such that the optimal trade-offs among these design goals are found. To authors best knowledge, such a problem has not been studied in multi-objective settings so far. In this work, an underactuated mechanical system consisting of a rotary servo motor and a ball and beam is used for the computer simulations, the setup parameters of the inner and outer control systems are tuned by NSGA-II (Non-dominated Sorting Genetic Algorithm), and the dominancy concept is used to find the optimal design points. The solution of this problem is not a single optimal cascade control, but rather a set of optimal cascade controllers (called Pareto set) which represent the optimal trade-offs among the selected design criteria. The function evaluation of the Pareto set is called the Pareto front. The solution set is introduced to the decision-maker who can choose any point to implement. The simulation results in terms of Pareto front and time responses to external signals show the competing nature among the design objectives. The presented study may become the basis for multi-objective optimal design of multi-loop control systems.

Keywords: cascade control, multi-Loop control systems, multiobjective optimization, optimal control

Procedia PDF Downloads 135

Authors: Dija Sulekha

Abstract:

Nowadays, a good percentage of reported cybercrimes involve the usage of the Internet, directly or indirectly for committing the crime. Usually, Web Browsers leave traces of browsing activities on the host computer’s hard disk, which can be used by investigators to identify internet-based activities of the suspect. But criminals, who involve in some organized crimes, disable browser file generation feature to hide the evidence while doing illegal activities through the Internet. In such cases, even though browser files were not generated in the storage media of the system, traces of recent and ongoing activities were generated in the Physical Memory of the system. As a result, the analysis of Physical Memory Dump collected from the suspect's machine retrieves lots of forensically crucial information related to the browsing history of the Suspect. This information enables the cyber forensic investigators to concentrate on a few highly relevant selected artefacts while doing the Offline Forensics analysis of storage media. This paper addresses the reconstruction of web browsing activities by conducting live forensics to identify searched terms, downloaded files, visited sites, email headers, email ids, etc. from the physical memory dump collected from Windows 10 Systems. Well-known entry points are available for retrieving all the above artefacts except searched terms. The paper describes a novel methodology to retrieve the searched terms from Windows 10 Physical Memory. The searched terms retrieved in this way can be used for doing advanced file and keyword search in the storage media files reconstructed from the file system recovery in offline forensics.

Keywords: browser forensics, digital forensics, live Forensics, physical memory forensics

Procedia PDF Downloads 99

Authors: Artur Tyliszczak, Ewa Szymanek, Maciej Marek

Abstract:

Flow through granular materials is important to a vast array of industries, for instance in construction industry where granular layers are used for bulkheads and isolators, in chemical engineering and catalytic reactors where large surfaces of packed granular beds intensify chemical reactions, or in energy production systems, where granulates are promising materials for heat storage and heat transfer media. Despite the common usage of granulates and extensive research performed in this field, phenomena occurring between granular solid elements or between solids and fluid are still not fully understood. In the present work we analyze the heat exchange process between the flowing medium (gas, liquid) and solid material inside the granular layers. We consider them as a composite of isolated solid elements and inter-granular spaces in which a gas or liquid can flow. The structure of the layer is controlled by shapes of particular granular elements (e.g., spheres, cylinders, cubes, Raschig rings), its spatial distribution or effective characteristic dimension (total volume or surface area). We will analyze to what extent alteration of these parameters influences on flow characteristics (turbulent intensity, mixing efficiency, heat transfer) inside the layer and behind it. Analysis of flow inside granular layers is very complicated because the use of classical experimental techniques (LDA, PIV, fibber probes) inside the layers is practically impossible, whereas the use of probes (e.g. thermocouples, Pitot tubes) requires drilling of holes inside the solid material. Hence, measurements of the flow inside granular layers are usually performed using for instance advanced X-ray tomography. In this respect, theoretical or numerical analyses of flow inside granulates seem crucial. Application of discrete element methods in combination with the classical finite volume/finite difference approaches is problematic as a mesh generation process for complex granular material can be very arduous. A good alternative for simulation of flow in complex domains is an immersed boundary-volume penalization (IB-VP) in which the computational meshes have simple Cartesian structure and impact of solid objects on the fluid is mimicked by source terms added to the Navier-Stokes and energy equations. The present paper focuses on application of the IB-VP method combined with large eddy simulation (LES). The flow solver used in this work is a high-order code (SAILOR), which was used previously in various studies, including laminar/turbulent transition in free flows and also for flows in wavy channels, wavy pipes and over various shape obstacles. In these cases a formal order of approximation turned out to be in between 1 and 2, depending on the test case. The current research concentrates on analyses of the flows in dense granular layers with elements distributed in a deterministic regular manner and validation of the results obtained using LES-IB method and body-fitted approach. The comparisons are very promising and show very good agreement. It is found that the size, number of elements and their distribution have huge impact on the obtained results. Ordering of the granular elements (or lack of it) affects both the pressure drop and efficiency of the heat transfer as it significantly changes mixing process.

Keywords: granular layers, heat transfer, immersed boundary method, numerical simulations

Procedia PDF Downloads 114

Authors: Behrooz Daneshmand

Abstract:

Software Defined Networking (SDN) is designed to meet the future needs of 5G mobile networks. The SDN architecture offers a new solution that involves separating the control plane from the data plane, which is usually paired together. Network functions traditionally performed on specific hardware can now be abstracted and virtualized on any device, and a centralized software-based administration approach is based on a central controller, facilitating the development of modern applications and services. These plan standards clear the way for a more adaptable, speedier, and more energetic network beneath computer program control compared with a conventional network. We accept SDN gives modern inquire about openings to security, and it can significantly affect network security research in numerous diverse ways. Subsequently, the SDN architecture engages systems to effectively screen activity and analyze threats to facilitate security approach modification and security benefit insertion. The segregation of the data planes and control and, be that as it may, opens security challenges, such as man-in-the-middle attacks (MIMA), denial of service (DoS) attacks, and immersion attacks. In this paper, we analyze security threats to each layer of SDN - application layer - southbound interfaces/northbound interfaces - controller layer and data layer. From a security point of see, the components that make up the SDN architecture have a few vulnerabilities, which may be abused by aggressors to perform noxious activities and hence influence the network and its administrations. Software-defined network assaults are shockingly a reality these days. In a nutshell, this paper highlights architectural weaknesses and develops attack vectors at each layer, which leads to conclusions about further progress in identifying the consequences of attacks and proposing mitigation strategies.

Keywords: software-defined networking, security, SDN, 5G/IMT-2020

Procedia PDF Downloads 79

Authors: Hussain Sajid, Jung-Hun Shin, Kum-Won Cho

Abstract:

Image super-resolution is the most common computer vision problem with many important applications. Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory requirements of GAN-based SR (mainly generators) lead to performance degradation and increased energy consumption, making it difficult to implement it onto resource-constricted devices. To relieve such a problem, In this paper, we introduce an optimized and highly efficient architecture for SR-GAN (generator) model by utilizing model compression techniques such as Knowledge Distillation and pruning, which work together to reduce the storage requirement of the model also increase in their performance. Our method begins with distilling the knowledge from a large pre-trained model to a lightweight model using different loss functions. Then, iterative weight pruning is applied to the distilled model to remove less significant weights based on their magnitude, resulting in a sparser network. Knowledge Distillation reduces the model size by 40%; pruning then reduces it further by 18%. To accelerate the learning process, we employ the Horovod framework for distributed training on a cluster of 2 nodes, each with 8 GPUs, resulting in improved training performance and faster convergence. Experimental results on various benchmarks demonstrate that the proposed compressed model significantly outperforms state-of-the-art methods in terms of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and image quality for x4 super-resolution tasks.

Keywords: single-image super-resolution, generative adversarial networks, knowledge distillation, pruning

Procedia PDF Downloads 63

Authors: R. Clancy, M. Ahern, D. O’Sullivan, K. Bruton

Abstract:

The manufacturing industry is currently undergoing a digital transformation as part of the mega-trend Industry 4.0. As part of this phase of the industrial revolution, traditional manufacturing processes are being combined with digital technologies to achieve smarter and more efficient production. To successfully digitally transform a manufacturing facility, the processes must first be digitized. This is the conversion of information from an analogue format to a digital format. The objective of this study was to explore the research area of digitizing manufacturing data as part of the worldwide paradigm, Industry 4.0. The formal methodology of a systematic mapping study was utilized to capture a representative sample of the research area and assess its current state. Specific research questions were defined to assess the key benefits and limitations associated with the digitization of manufacturing data. Research papers were classified according to the type of research and type of contribution to the research area. Upon analyzing 54 papers identified in this area, it was noted that 23 of the papers originated in Germany. This is an unsurprising finding as Industry 4.0 is originally a German strategy with supporting strong policy instruments being utilized in Germany to support its implementation. It was also found that the Fraunhofer Institute for Mechatronic Systems Design, in collaboration with the University of Paderborn in Germany, was the most frequent contributing Institution of the research papers with three papers published. The literature suggested future research directions and highlighted one specific gap in the area. There exists an unresolved gap between the data science experts and the manufacturing process experts in the industry. The data analytics expertise is not useful unless the manufacturing process information is utilized. A legitimate understanding of the data is crucial to perform accurate analytics and gain true, valuable insights into the manufacturing process. There lies a gap between the manufacturing operations and the information technology/data analytics departments within enterprises, which was borne out by the results of many of the case studies reviewed as part of this work. To test the concept of this gap existing, the researcher initiated an industrial case study in which they embedded themselves between the subject matter expert of the manufacturing process and the data scientist. Of the papers resulting from the systematic mapping study, 12 of the papers contributed a framework, another 12 of the papers were based on a case study, and 11 of the papers focused on theory. However, there were only three papers that contributed a methodology. This provides further evidence for the need for an industry-focused methodology for digitizing and analyzing manufacturing data, which will be developed in future research.

Keywords: analytics, digitization, industry 4.0, manufacturing

Procedia PDF Downloads 90