Search results for: feature pyramid networks

Authors: Dumont Maxime, Correia Carlos, Sauvage Jean-François, Schwartz Noah, Gray Morgan

Abstract:

Context: The concept of the segmented telescope is unavoidable to build extremely large telescopes (ELT) in the quest for spatial resolution, but it also allows one to fit a large telescope within a reduced volume of space (JWST) or into an even smaller volume (Standard Cubesat). Cubesats have tight constraints on the computational burden available and the small payload volume allowed. At the same time, they undergo thermal gradients leading to large and evolving optical aberrations. The pupil segmentation comes nevertheless with an obvious difficulty: to co-phase the different segments. The CubeSat constraints prevent the use of a dedicated wavefront sensor (WFS), making the focal-plane images acquired by the science detector the most practical alternative. Yet, one of the challenges for the wavefront sensing is the non-linearity between the image intensity and the phase aberrations. Plus, for Earth observation, the object is unknown and unrepeatable. Recently, several studies have suggested Neural Networks (NN) for wavefront sensing; especially convolutional NN, which are well known for being non-linear and image-friendly problem solvers. Aims: We study in this paper the prospect of using NN to measure the phasing aberrations of a segmented pupil from the focal-plane image directly without a dedicated wavefront sensing. Methods: In our application, we take the case of a deployable telescope fitting in a CubeSat for Earth observations which triples the aperture size (compared to the 10cm CubeSat standard) and therefore triples the angular resolution capacity. In order to reach the diffraction-limited regime in the visible wavelength, typically, a wavefront error below lambda/50 is required. The telescope focal-plane detector, used for imaging, will be used as a wavefront-sensor. In this work, we study a point source, i.e. the Point Spread Function [PSF] of the optical system as an input of a VGG-net neural network, an architecture designed for image regression/classification. Results: This approach shows some promising results (about 2nm RMS, which is sub lambda/50 of residual WFE with 40-100nm RMS of input WFE) using a relatively fast computational time less than 30 ms which translates a small computation burder. These results allow one further study for higher aberrations and noise.

Keywords: wavefront sensing, deep learning, deployable telescope, space telescope

Procedia PDF Downloads 80

Authors: Valentina Marutyan

Abstract:

Healthcare data mining is a rapidly developing field at the intersection of technology and medicine that has the potential to change our understanding and approach to providing healthcare. Healthcare and data mining is the process of examining huge amounts of data to extract useful information that can be applied in order to improve patient care, treatment effectiveness, and overall healthcare delivery. This field looks for patterns, trends, and correlations in a variety of healthcare datasets, such as electronic health records (EHRs), medical imaging, patient demographics, and treatment histories. To accomplish this, it uses advanced analytical approaches. Predictive analysis using historical patient data is a major area of interest in healthcare data mining. This enables doctors to get involved early to prevent problems or improve results for patients. It also assists in early disease detection and customized treatment planning for every person. Doctors can customize a patient's care by looking at their medical history, genetic profile, current and previous therapies. In this way, treatments can be more effective and have fewer negative consequences. Moreover, helping patients, it improves the efficiency of hospitals. It helps them determine the number of beds or doctors they require in regard to the number of patients they expect. In this project are used models like logistic regression, random forests, and neural networks for predicting diseases and analyzing medical images. Patients were helped by algorithms such as k-means, and connections between treatments and patient responses were identified by association rule mining. Time series techniques helped in resource management by predicting patient admissions. These methods improved healthcare decision-making and personalized treatment. Also, healthcare data mining must deal with difficulties such as bad data quality, privacy challenges, managing large and complicated datasets, ensuring the reliability of models, managing biases, limited data sharing, and regulatory compliance. Finally, secret code of data mining in healthcare helps medical professionals and hospitals make better decisions, treat patients more efficiently, and work more efficiently. It ultimately comes down to using data to improve treatment, make better choices, and simplify hospital operations for all patients.

Keywords: data mining, healthcare, big data, large amounts of data

Procedia PDF Downloads 46

Authors: Jana Soler Libran

Abstract:

The primary aim of this paper is to analyze the relationship between power and knowledge suggested in Michel Foucault's theory. Taking into consideration the role of power in knowledge production, the goal is to evaluate to what extent genealogy can be presented as a practical method for epistemic resistance. To do so, the methodology used consists of a revision of Foucault’s literature concerning the topic discussed. In this sense, conceptual analysis is applied in order to understand the effect of the double dimension of power on knowledge production. In its negative dimension, power is conceived as an organ of repression, vetoing certain instances of knowledge considered deceitful. In opposition, in its positive dimension, power works as an organ of the production of truth by means of institutionalized discourses. This double declination of power leads to the first main findings of the present analysis: no truth or knowledge can lie outside power’s action, and power is constituted through accepted forms of knowledge. To second these statements, Foucaultian discourse formations are evaluated, presenting external exclusion procedures as paradigmatic practices to demonstrate how power creates and shapes the validity of certain epistemes. Thus, taking into consideration power’s mechanisms to produce and reproduce institutionalized truths, this paper accounts for the Foucaultian praxis of genealogy as a method to reveal power’s intention, instruments, and effects in the production of knowledge. In this sense, it is suggested to consider genealogy as a practice which, firstly, reveals what instances of knowledge are subjugated to power and, secondly, promotes aforementioned peripherical discourses as a form of epistemic resistance. In order to counterbalance these main theses, objections to Foucault’s work from Nancy Fraser, Linda Nicholson, Charles Taylor, Richard Rorty, Alvin Goldman, or Karen Barad are discussed. In essence, the understanding of the Foucaultian relationship between power and knowledge is essential to analyze how contemporary discourses are produced by both traditional institutions and new forms of institutionalized power, such as mass media or social networks. Therefore, Michel Foucault's practice of genealogy is relevant, not only for its philosophical contribution as a method to uncover the effects of power in knowledge production but also because it constitutes a valuable theoretical framework for political theory and sociological studies concerning the formation of societies and individuals in the contemporary world.

Keywords: epistemic resistance, Foucault’s genealogy, knowledge, power, truth

Procedia PDF Downloads 99

Authors: Kurt Maxwell Kusterer, Sylvain Mignot, Annick Vignes

Abstract:

To our best knowledge YouTube is the largest video hosting platform in the world. A high number of creators, viewers, subscribers and commentators act in this specific eco-system which generates huge sums of money. Views, subscribers, and comments help to increase the popularity of content creators. The most popular creators are sponsored by brands and participate in marketing campaigns. For a few of them, this becomes a financially rewarding profession. This is made possible through the YouTube Partner Program, which shares revenue among creators based on their popularity. We believe that the role of comments in increasing the popularity is to be emphasized. In what follows, YouTube is considered as a bilateral network between the videos and the commentators. Analyzing a detailed data set focused on French YouTubers, we consider each comment as a link between a commentator and a video. Our research question asks what are the predominant features of a video which give it the highest probability to be commented on. Following on from this question, how can we use these features to predict the action of the agent in commenting one video instead of another, considering the characteristics of the commentators, videos, topics, channels, and recommendations. We expect to see that the videos of more popular channels generate higher viewer engagement and thus are more frequently commented. The interest lies in discovering features which have not classically been considered as markers for popularity on the platform. A quick view of our data set shows that 96% of the commentators comment only once on a certain video. Thus, we study a non-weighted bipartite network between commentators and videos built on the sub-sample of 96% of unique comments. A link exists between two nodes when a commentator makes a comment on a video. We run an Exponential Random Graph Model (ERGM) approach to evaluate which characteristics influence the probability of commenting a video. The creation of a link will be explained in terms of common video features, such as duration, quality, number of likes, number of views, etc. Our data is relevant for the period of 2020-2021 and focuses on the French YouTube environment. From this set of 391 588 videos, we extract the channels which can be monetized according to YouTube regulations (channels with at least 1000 subscribers and more than 4000 hours of viewing time during the last twelve months).In the end, we have a data set of 128 462 videos which consist of 4093 channels. Based on these videos, we have a data set of 1 032 771 unique commentators, with a mean of 2 comments per a commentator, a minimum of 1 comment each, and a maximum of 584 comments.

Keywords: YouTube, social networks, economics, consumer behaviour

Procedia PDF Downloads 50

Authors: Nadia Belu, Laurenţiu Mihai Ionescu, Agnieszka Misztal

Abstract:

The automotive industry is one of the most important industries in the world that concerns not only the economy, but also the world culture. In the present financial and economic context, this field faces new challenges posed by the current crisis, companies must maintain product quality, deliver on time and at a competitive price in order to achieve customer satisfaction. Two of the most recommended techniques of quality management by specific standards of the automotive industry, in the product development, are Failure Mode and Effects Analysis (FMEA) and Control Plan. FMEA is a methodology for risk management and quality improvement aimed at identifying potential causes of failure of products and processes, their quantification by risk assessment, ranking of the problems identified according to their importance, to the determination and implementation of corrective actions related. The companies use Control Plans realized using the results from FMEA to evaluate a process or product for strengths and weaknesses and to prevent problems before they occur. The Control Plans represent written descriptions of the systems used to control and minimize product and process variation. In addition Control Plans specify the process monitoring and control methods (for example Special Controls) used to control Special Characteristics. In this paper we propose a computer-aided solution with Genetic Algorithms in order to reduce the drafting of reports: FMEA analysis and Control Plan required in the manufacture of the product launch and improved knowledge development teams for future projects. The solution allows to the design team to introduce data entry required to FMEA. The actual analysis is performed using Genetic Algorithms to find optimum between RPN risk factor and cost of production. A feature of Genetic Algorithms is that they are used as a means of finding solutions for multi criteria optimization problems. In our case, along with three specific FMEA risk factors is considered and reduce production cost. Analysis tool will generate final reports for all FMEA processes. The data obtained in FMEA reports are automatically integrated with other entered parameters in Control Plan. Implementation of the solution is in the form of an application running in an intranet on two servers: one containing analysis and plan generation engine and the other containing the database where the initial parameters and results are stored. The results can then be used as starting solutions in the synthesis of other projects. The solution was applied to welding processes, laser cutting and bending to manufacture chassis for buses. Advantages of the solution are efficient elaboration of documents in the current project by automatically generating reports FMEA and Control Plan using multiple criteria optimization of production and build a solid knowledge base for future projects. The solution which we propose is a cheap alternative to other solutions on the market using Open Source tools in implementation.

Keywords: automotive industry, FMEA, control plan, automotive technology

Procedia PDF Downloads 391

Authors: Maryam Fallahpoor, Biswajeet Pradhan

Abstract:

Background: Artificial intelligence (AI) serves as a valuable tool in mitigating the scarcity of human resources required for the evaluation and categorization of vast quantities of medical imaging data. When AI operates with optimal precision, it minimizes the demand for human interpretations and, thereby, reduces the burden on radiologists. Among various AI approaches, deep learning (DL) stands out as it obviates the need for feature extraction, a process that can impede classification, especially with intricate datasets. The advent of DL models has ushered in a new era in medical imaging, particularly in the context of COVID-19 detection. Traditional 2D imaging techniques exhibit limitations when applied to volumetric data, such as Computed Tomography (CT) scans. Medical images predominantly exist in one of two formats: neuroimaging informatics technology initiative (NIfTI) and digital imaging and communications in medicine (DICOM). Purpose: This study aims to employ DL for the classification of COVID-19-infected pulmonary patients and normal cases based on 3D CT scans while investigating the impact of image format. Material and Methods: The dataset used for model training and testing consisted of 1245 patients from IranMehr Hospital. All scans shared a matrix size of 512 × 512, although they exhibited varying slice numbers. Consequently, after loading the DICOM CT scans, image resampling and interpolation were performed to standardize the slice count. All images underwent cropping and resampling, resulting in uniform dimensions of 128 × 128 × 60. Resolution uniformity was achieved through resampling to 1 mm × 1 mm × 1 mm, and image intensities were confined to the range of (−1000, 400) Hounsfield units (HU). For classification purposes, positive pulmonary COVID-19 involvement was designated as 1, while normal images were assigned a value of 0. Subsequently, a U-net-based lung segmentation module was applied to obtain 3D segmented lung regions. The pre-processing stage included normalization, zero-centering, and shuffling. Four distinct 3D CNN models (ResNet152, ResNet50, DensNet169, and DensNet201) were employed in this study. Results: The findings revealed that the segmentation technique yielded superior results for DICOM images, which could be attributed to the potential loss of information during the conversion of original DICOM images to NIFTI format. Notably, ResNet152 and ResNet50 exhibited the highest accuracy at 90.0%, and the same models achieved the best F1 score at 87%. ResNet152 also secured the highest Area under the Curve (AUC) at 0.932. Regarding sensitivity and specificity, DensNet201 achieved the highest values at 93% and 96%, respectively. Conclusion: This study underscores the capacity of deep learning to classify COVID-19 pulmonary involvement using real 3D hospital data. The results underscore the significance of employing DICOM format 3D CT images alongside appropriate pre-processing techniques when training DL models for COVID-19 detection. This approach enhances the accuracy and reliability of diagnostic systems for COVID-19 detection.

Keywords: deep learning, COVID-19 detection, NIFTI format, DICOM format

Procedia PDF Downloads 54

Authors: Binbin Chen, Dennis Y. C. Leung

Abstract:

Aluminium (Al) -air cell holds a high volumetric capacity density of 8.05 Ah cm-3, benefit from the trivalence of Al ions. Additional benefits of Al-air cell are low price and environmental friendliness. Furthermore, the Al energy conversion process is characterized of 100% recyclability in theory. Along with a large base of raw material reserve, Al attracts considerable attentions as a promising material to be integrated within the global energy system. However, despite the early successful applications in military services, several problems exist that prevent the Al-air cells from widely civilian use. The most serious issue is the parasitic corrosion of Al when contacts with electrolyte. To overcome this problem, super-pure Al alloyed with various traces of metal elements are used to increase the corrosion resistance. Nevertheless, high-purity Al alloys are costly and require high energy consumption during production process. An alternative approach is to add inexpensive inhibitors directly into the electrolyte. However, such additives would increase the internal ohmic resistance and hamper the cell performance. So far these methods have not provided satisfactory solutions for the problem within Al-air cells. For the operation of alkaline Al-air cell, there are still other minor problems. One of them is the formation of aluminium hydroxide in the electrolyte. This process decreases ionic conductivity of electrolyte. Another one is the carbonation process within the gas diffusion layer of cathode, blocking the porosity of gas diffusion. Both these would hinder the performance of cells. The present work optimizes the above problems by building an Al-air cell operation system, consisting of four components. A top electrolyte tank containing fresh electrolyte is located at a high level, so that it can drive the electrolyte flow by gravity force. A mechanical rechargeable Al-air cell is fabricated with low-cost materials including low grade Al, carbon paper, and PMMA plates. An electrolyte waste tank with elaborate channel is designed to separate the hydrogen generated from the corrosion, which would be collected by gas collection device. In the first section of the research work, we investigated the performance of the mechanical rechargeable Al-air cell with a constant flow rate of electrolyte, to ensure the repeatability experiments. Then the whole system was assembled together and the feasibility of operating was demonstrated. During experiment, pure hydrogen is collected by collection device, which holds potential for various applications. By collecting this by-product, high utilization efficiency of aluminum is achieved. Considering both electricity and hydrogen generated, an overall utilization efficiency of around 90 % or even higher under different working voltages are achieved. Fluidic electrolyte could remove aluminum hydroxide precipitate and solve the electrolyte deterioration problem. This operation system provides a low-cost strategy for harvesting energy from the abundant secondary Al. The system could also be applied into other metal-air cells and is suitable for emergency power supply, power plant and other applications. The low cost feature implies great potential for commercialization. Further optimization, such as scaling up and optimization of fabrication, will help to refine the technology into practical market offerings.

Keywords: aluminium-air cell, high efficiency, hydrogen, mechanical recharge

Procedia PDF Downloads 261

Authors: L. R. Valencia Pérez, A. Morita Alexander, Peña A. Juan Manuel, A. Lamadrid Álvarez

Abstract:

This research shows the reflection and identification of explanatory variables and their relationships between different variables that are involved with educational technology, all of them encompassed in macro-concepts which are: cognitive inequality, economy, food and language; These will give the guideline to have a more detailed knowledge of educational systems, the communication and equipment, the physical space and the teachers; All of them interacting with each other give rise to what is called educational technology management. These elements contribute to have a very specific knowledge of the equipment of communications, networks and computer equipment, systems and content repositories. This is intended to establish the importance of knowing a global environment in the transfer of knowledge in poor countries, so that it does not diminish the capacity to be authentic and preserve their cultures, their languages or dialects, their hierarchies and real needs; In short, to respect the customs of different towns, villages or cities that are intended to be reached through the use of internationally agreed professional educational technologies. The methodology used in this research is the analytical - descriptive, which allows to explain each of the variables, which in our opinion must be taken into account, in order to achieve an optimal incorporation of the educational technology in a model that gives results in a medium term. The idea is that in an encompassing way the concepts will be integrated to others with greater coverage until reaching macro concepts that are of national coverage in the countries and that are elements of conciliation in the different federal and international reforms. At the center of the model is the educational technology which is directly related to the concepts that are contained in factors such as the educational system, communication and equipment, spaces and teachers, which are globally immersed in macro concepts Cognitive inequality, economics, food and language. One of the major contributions of this article is to leave this idea under an algorithm that allows to be as unbiased as possible when evaluating this indicator, since other indicators that are to be taken from international preference entities like the OECD in the area of education systems studied, so that they are not influenced by particular political or interest pressures. This work opens the way for a relationship between involved entities, both conceptual, procedural and human activity, to clearly identify the convergence of their impact on the problem of education and how the relationship can contribute to an improvement, but also shows possibilities of being able to reach a comprehensive education reform for all.

Keywords: relationships macro-concepts, cognitive inequality, economics, alimentation and language

Procedia PDF Downloads 178

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

Traditional classification Convolutional Neural Networks (CNN) attempt to classify an image in its entirety. This becomes problematic when trying to perform classification with a drone’s camera in real-time due to unpredictable backgrounds. Object detectors with bounding boxes can be used to isolate individuals and other items, but the original backgrounds remain within these boxes. These basic detectors have been regularly used to determine what type of object an item is, such as “person” or “dog.” Recent advancement in computer vision, particularly with human imaging, is keypoint detection. Human keypoint detection goes beyond bounding boxes to fully isolate humans and plot points, or Regions of Interest (ROI), on their bodies within an image. ROIs can include shoulders, elbows, knees, heads, etc. These points can then be related to each other and used in deep learning methods such as pose estimation. For drone control based on human motions, poses, or signals using the onboard camera, it is important to have a simple method for pilot identification among multiple individuals while also giving the pilot fine control options for the drone. To achieve this, the OpenPose keypoint detection network was used with body and hand keypoint detection enabled. OpenPose supports the ability to combine multiple keypoint detection methods in real-time with a single network. Body keypoint detection allows simple poses to act as the pilot identifier. The hand keypoint detection with ROIs for each finger can then offer a greater variety of signal options for the pilot once identified. For this work, the individual must raise their non-control arm to be identified as the operator and send commands with the hand on their other arm. The drone ignores all other individuals in the onboard camera feed until the current operator lowers their non-control arm. When another individual wish to operate the drone, they simply raise their arm once the current operator relinquishes control, and then they can begin controlling the drone with their other hand. This is all performed mid-flight with no landing or script editing required. When using a desktop with a discrete NVIDIA GPU, the drone’s 2.4 GHz Wi-Fi connection combined with OpenPose restrictions to only body and hand allows this control method to perform as intended while maintaining the responsiveness required for practical use.

Keywords: computer vision, drone control, keypoint detection, openpose

Procedia PDF Downloads 162

Authors: M. Moso-Diez, J. L. Moragues-Oregi, K. Simon-Elorz

Abstract:

Innovation procurement is designed to steer the development of solutions towards concrete public sector needs as a driver for innovation from the demand side (in public services as well as in market opportunities for companies), is horizontally emerging as a new policy instrument. In 2014 the new EU public procurement directives 2014/24/EC and 2014/25/EC reinforced the support for Public Procurement for Innovation, dedicating funding instruments that can be used across all areas supported by Horizon 2020, and targeting potential buyers of innovative solutions: groups of public procurers with similar needs. Under this programme, new policy adapters and networks emerge, aiming to embed innovation criteria into new procurement processes. As these initiatives are in process, research related to is scarce. We argue that Innovation Public Procurement can arise as an innovative policy instrument to public procurement in different policy domains, in spite of existing institutional and cultural barriers (legal guarantee versus innovation). The presentation combines insights from public procurement to supply management chain management in a sustainability and innovation policy arena, as a means of providing understanding of: (1) the circumstances that emerge; (2) the relationship between public and private actors; and (3) the emerging capacities in the definition of the agenda. The policy adopters are the contracting authorities that mainly are at municipal level where they interact with the supply management chain, interconnecting sustainability and climate measures with other policy priorities such as innovation and urban planning; and through the Competitive Dialogue procedure. We found that geography and territory affect both the level of municipal budget (due to municipal income per capita) and its institutional competencies (due to demographic reasons). In spite of the relevance of institutional determinants for public procurement, other factors play an important role such as human factors as well as both public policy and private intervention. The experience is a ‘city project’ (Bilbao) in the field of brownfield decontamination. Brownfield sites typically refer to abandoned or underused industrial and commercial properties—such as old process plants, mining sites, and landfills—that are available but contain low levels of environmental contaminants that may complicate reuse or redevelopment of the land. This article concludes that Innovation Public Procurement in sustainability and climate issues should be further developed both as a policy instrument and as a policy research line that could enable further relevant changes in public procurement as well as in climate innovation.

Keywords: innovation, city projects, public policy, public procurement

Procedia PDF Downloads 288

Authors: Francesca Spagnoli, Shenja van der Graaf, Pieter Ballon

Abstract:

Humans do not behave rationally. We are emotional, easily influenced by others, as well as by our context. The study of human behaviour became a supreme endeavour within many academic disciplines, including economics, sociology, and clinical and social psychology. Understanding what motivates humans and triggers them to perform certain activities, and what it takes to change their behaviour, is central both for researchers and companies, as well as policy makers to implement efficient public policies. While numerous theoretical approaches for diverse domains such as health, retail, environment have been developed, the methodological models guiding the evaluation of such research have reached for a long time their limits. Within this context, digitisation, the Information and communication technologies (ICT) and wearable, the Internet of Things (IoT) connecting networks of devices, and new possibilities to collect and analyse massive amounts of data made it possible to study behaviour from a realistic perspective, as never before. Digital technologies make it possible to (1) capture data in real-life settings, (2) regain control over data by capturing the context of behaviour, and (3) analyse huge set of information through continuous measurement. Within this complex context, this paper describes a new framework for initiating behavioural change, capitalising on the digital developments in applied research projects and applicable both to academia, enterprises and policy makers. By applying this model, behavioural research can be conducted to address the issues of different domains, such as mobility, environment, health or media. The Modular Behavioural Analysis Approach (MBAA) is here described and firstly validated through a concrete use case within the domain of health. The results gathered have proven that disclosing information about health in connection with the use of digital apps for health, can be a leverage for changing behaviour, but it is only a first component requiring further follow-up actions. To this end, a clear definition of different 'behavioural profiles', towards which addressing several typologies of interventions, it is essential to effectively enable behavioural change. In the refined version of the MBAA a strong focus will rely on defining a methodology for shaping 'behavioural profiles' and related interventions, as well as the evaluation of side-effects on the creation of new business models and sustainability plans.

Keywords: behavioural change, framework, health, nudging, sustainability

Procedia PDF Downloads 201

Authors: Kaustav Mukherjee

Abstract:

In this paper we propose a Neural Style Transfer solution whereby we have created a Lightweight Separable Convolution Kernel Based GAN Architecture (SC-GAN) which will very useful for designing filter for Mobile Phone Cameras and also Edge Devices which will convert any image to its 2D ANIMATED COMIC STYLE Movies like HEMAN, SUPERMAN, JUNGLE-BOOK. This will help the 2D animation artist by relieving to create new characters from real life person's images without having to go for endless hours of manual labour drawing each and every pose of a cartoon. It can even be used to create scenes from real life images.This will reduce a huge amount of turn around time to make 2D animated movies and decrease cost in terms of manpower and time. In addition to that being extreme light-weight it can be used as camera filters capable of taking Comic Style Shots using mobile phone camera or edge device cameras like Raspberry Pi 4,NVIDIA Jetson NANO etc. Existing Methods like CartoonGAN with the model size close to 170 MB is too heavy weight for mobile phones and edge devices due to their scarcity in resources. Compared to the current state of the art our proposed method which has a total model size of 31 MB which clearly makes it ideal and ultra-efficient for designing of camera filters on low resource devices like mobile phones, tablets and edge devices running OS or RTOS. .Owing to use of high resolution input and usage of bigger convolution kernel size it produces richer resolution Comic-Style Pictures implementation with 6 times lesser number of parameters and with just 25 extra epoch trained on a dataset of less than 1000 which breaks the myth that all GAN need mammoth amount of data. Our network reduces the density of the Gan architecture by using Depthwise Separable Convolution which does the convolution operation on each of the RGB channels separately then we use a Point-Wise Convolution to bring back the network into required channel number using 1 by 1 kernel.This reduces the number of parameters substantially and makes it extreme light-weight and suitable for mobile phones and edge devices. The architecture mentioned in the present paper make use of Parameterised Batch Normalization Goodfellow etc al. (Deep Learning OPTIMIZATION FOR TRAINING DEEP MODELS page 320) which makes the network to use the advantage of Batch Norm for easier training while maintaining the non-linear feature capture by inducing the learnable parameters

Keywords: comic stylisation from camera image using GAN, creating 2D animated movie style custom stickers from images, depth-wise separable convolutional neural network for light-weight GAN architecture for EDGE devices, GAN architecture for 2D animated cartoonizing neural style, neural style transfer for edge, model distilation, perceptual loss

Procedia PDF Downloads 113

Authors: O. O. Sufyani, M. E. Oraiby, S. A. Qumaiy, A. I. Alaamri, Z. M. Eisa, A. M. Hakami, M. A. Attafi, O. M. Alhassan, W. M. Elsideeg, E. M. Noureldin, Y. A. Hobani, Y. Q. Majrabi, I. A. Khardali, A. B. Maashi, A. A. Al Mane, A. H. Hakami, I. M. Alkhyat, A. A. Sahly, I. M. Attafi

Abstract:

According to the Food and Agriculture Organization (FAO) Pesticides Use Database, pesticide use in agriculture in Saudi Arabia has more than doubled from 4539 tons in 2009 to 10496 tons in 2019. Among pesticides, pyrethroids is commonly used in Saudi Arabia. Pesticides may increase susceptibility to a variety of diseases, particularly among pesticide workers, due to their extensive use, indiscriminate use, and long-term exposure. Therefore, analyzing blood chemo-profiles and evaluating the detected substances as biomarkers for pyrethroid pesticide exposure may assist to identify and predicting adverse effects of exposure, which may be used for both preventative and risk assessment purposes. The purpose of this study was to (a) analyze chemo-profiling by Gas Chromatography-Mass Spectrometry (GC-MS) analysis, (b) identify the most commonly detected chemicals in a time-exposure-dependent manner using a Venn diagram, and (c) identify their associated disease among pesticide workers using analyzer tools on the Comparative Toxicogenomics Database (CTD) website, (250 healthy male volunteers (20-60 years old) who deal with pesticides in the Jazan region of Saudi Arabia (exposure intervals: 1-2, 4-6, 6-8, more than 8 years) were included in the study. A questionnaire was used to collect demographic information, the duration of pesticide exposure, and the existence of chronic conditions. Blood samples were collected for biochemistry analysis and extracted by solid-phase extraction for gas chromatography-mass spectrometry (GC-MS) analysis. Biochemistry analysis reveals no significant changes in response to the exposure period; however, an inverse association between the albumin level and the exposure interval was observed. The blood chemo-profiling was differentially expressed in an exposure time-dependent manner. This analysis identified the common chemical set associated with each group and their associated significant occupational diseases. While some of these chemicals are associated with a variety of diseases, the distinguishing feature of these chemically associated disorders is their applicability for prevention measures. The most interesting finding was the identification of several chemicals; erucic acid, pelargonic acid, alpha-linolenic acid, dibutyl phthalate, diisobutyl phthalate, dodecanol, myristic Acid, pyrene, and 8,11,14-eicosatrienoic acid, associated with pneumoconiosis, asbestosis, asthma, silicosis and berylliosis. Chemical-disease association study also found that cancer, digestive system disease, nervous system disease, and metabolic disease were the most often recognized disease categories in the common chemical set. The hierarchical clustering approach was used to compare the expression patterns and exposure intervals of the chemicals found commonly. More study is needed to validate these chemicals as early markers of pyrethroid insecticide-related occupational disease, which might assist evaluate and reducing risk. The current study contributes valuable data and recommendations to public health.

Keywords: occupational, toxicology, chemo-profiling, pesticide, pyrethroid, GC-MS

Procedia PDF Downloads 76

Authors: Ipek Kivanc, Demet Ozgur-Unluakin

Abstract:

Over the past years, technological innovations and advancements have played an important role in the industrial world. Due to technological improvements, the degree of complexity of the systems has increased. Hence, all systems are getting more uncertain that emerges from increased complexity, resulting in more cost. It is challenging to cope with this situation. So, implementing efficient planning of maintenance activities in such systems are getting more essential. Partially Observable Markov Decision Processes (POMDPs) are powerful tools for stochastic sequential decision problems under uncertainty. Although maintenance optimization in a dynamic environment can be modeled as such a sequential decision problem, POMDPs are not widely used for tackling maintenance problems. However, they can be well-suited frameworks for obtaining optimal maintenance policies. In the classical representation of the POMDP framework, the system is denoted by a single node which has multiple states. The main drawback of this classical approach is that the state space grows exponentially with the number of state variables. On the other side, factored representation of POMDPs enables to simplify the complexity of the states by taking advantage of the factored structure already available in the nature of the problem. The main idea of factored POMDPs is that they can be compactly modeled through dynamic Bayesian networks (DBNs), which are graphical representations for stochastic processes, by exploiting the structure of this representation. This study aims to demonstrate how maintenance planning of dynamic systems can be modeled with factored POMDPs. An empirical maintenance planning problem of a dynamic system consisting of four partially observable components deteriorating in time is designed. To solve the empirical model, we resort to Symbolic Perseus solver which is one of the state-of-the-art factored POMDP solvers enabling approximate solutions. We generate some more predefined policies based on corrective or proactive maintenance strategies. We execute the policies on the empirical problem for many replications and compare their performances under various scenarios. The results show that the computed policies from the POMDP model are superior to the others. Acknowledgment: This work is supported by the Scientific and Technological Research Council of Turkey (TÜBİTAK) under grant no: 117M587.

Keywords: factored representation, maintenance, multi-component system, partially observable Markov decision processes

Procedia PDF Downloads 117

Authors: Samantha A. Cintron, Janet Pierce, Mihaela E. Sardiu, Diane Mahoney, Jill Peltzer, Bhanu Gupta, Qiuhua Shen

Abstract:

High output heart failure (HOHF) is characterized a high output state resulting from an underlying disease process and is commonly caused by obesity. As obesity levels increase, more individuals will be at risk for obesity-related HOHF. However, the underlying pathophysiologic mechanisms of obesity-related HOHF are not well understood and need further research. The aim of the study was to describe the differences in leukocyte transcriptomes of morbidly obese patients with HOHF and those with non-HOHF. In this cross-sectional study, the study team collected blood samples, demographics, and clinical data of six patients with morbid obesity and HOHF and six patients with morbid obesity and non-HOHF. The study team isolated the peripheral blood leukocyte RNA and applied stranded total RNA sequencing. Differential gene expression was calculated, and Ingenuity Pathway Analysis software was used to interpret the canonical pathways, functional changes, upstream regulators, and mechanistic and causal networks that were associated with the significantly different leukocyte transcriptomes. The study team identified 116 differentially expressed genes; 114 were upregulated, and 2 were downregulated in the HOHF group (Benjamini-Hochberg adjusted p-value ≤ 0.05 and log2(fold-change) of ±1). The differentially expressed genes were involved with cell proliferation, mitochondrial function, erythropoiesis, erythrocyte stability, and apoptosis. The top upregulated canonical pathways associated with differentially expressed genes were autophagy, adenosine monophosphate-activated protein kinase signaling, and senescence pathways. Upstream regulator GATA Binding Protein 1 (GATA1) and a network associated with nuclear factor kappa-light chain-enhancer of activated B cells (NF-kB) were also identified based on the different leukocyte transcriptomes of morbidly obese patients with HOHF and non-HOHF. To the author’s best knowledge, this is the first study that reported the differential gene expression in patients with obesity-related HOHF and demonstrated the unique pathophysiologic mechanisms underlying the disease. Further research is needed to determine the role of cellular function and maintenance, inflammation, and iron homeostasis in obesity-related HOHF.

Keywords: cardiac output, heart failure, obesity, transcriptomics

Procedia PDF Downloads 23

Authors: D. M. Rey, V. Delgado, J. Zambrano Nájera

Abstract:

Increases in urbanization during XX century, has produced changes in natural dynamics of the basins, which has resulted in increases in runoff volumes, peak flows and flow velocities, that in turn increases flood risk. Higher runoff volumes decrease sewerage networks hydraulic capacity and can cause its failure. This in turn generates increasingly recurrent floods causing mobility problems and general economic detriment in the cities. In Latin America, especially Colombia, this is a major problem because urban population at late XX century was more than 70% is in urban areas increasing approximately in 790% in 1940-1990 period. Besides, high slopes product of Andean topography and high precipitation typical of tropical climates increases velocities and volumes even more, causing stopping of cities during storms. Thus, it becomes very important to know hydrological behavior of Andean Urban Watersheds. This research aims to determine the impact of urbanization in high sloped urban watersheds in its hydrology. To this end, it will be used as study area experimental urban watershed named Palogrande-San Luis watershed, located in the city of Manizales, Colombia. Manizales is a city in central western Colombia, located in Colombian Central Mountain Range (part of Los Andes Mountains) with an abrupt topography (average altitude is 2.153 m). The climate in Manizales is quite uniform, but due to its high altitude it presents high precipitations (1.545 mm/year average) with high humidity (83% average). It was applied HEC-HMS Hydrologic model on the watershed. The inputs to the model were derived from Geographic Information Systems (GIS) theme layers of the Instituto de Estudios Ambientales –IDEA of Universidad Nacional de Colombia, Manizales (Institute of Environmental Studies) and aerial photography taken for the research in conjunction with available literature and look up tables. Rainfall data from a network of 4 rain gages and historical stream flow data were used to calibrate and validate runoff depth using the hydrologic model. Manual calibration was made, and the simulation results show that the model selected is able to characterize the runoff response of the watershed due to land use for urbanization in high mountain watersheds.

Keywords: Andean watersheds modelling, high mountain urban hydrology, urban planning, hydrologic modelling

Procedia PDF Downloads 212

Authors: Javier Alfonso Bonilla-Chávez, Angélica Lozano

Abstract:

In North America, more than 2,000 people annually die in accidents related to railroad tracks. In 2020, collisions at grade crossings were the main cause of deaths related to railway accidents in Mexico. Railway networks have constant interaction with motor transport users, cyclists, and pedestrians, mainly in grade crossings, where is the greatest vulnerability and risk of accidents. Usually, accidents at grade crossings are directly related to risky behavior and non-compliance with regulations by motorists, cyclists, and pedestrians, especially in developing countries. Around the world, countries classify these crossings in different ways. In Mexico, according to their dangerousness (high, medium, or low), types A, B and C have been established, recommending for each one different type of auditive and visual signaling and gates, as well as horizontal and vertical signaling. This classification is based in a weighting, but regrettably, it is not explained how the weight values were obtained. A review of the variables and the current approach for the grade crossing classification is required, since it is inadequate for some crossings. In contrast, North America (USA and Canada) and European countries consider a broader classification so that attention to each crossing is addressed more precisely and equipment costs are adjusted. Lack of a proper classification, could lead to cost overruns in the equipment and a deficient operation. To exemplify the lack of a good classification, six crossings are studied, three located in the rural area of Mexico and three in Mexico City. These cases show the need of: improving the current regulations, improving the existing infrastructure, and implementing technological systems, including informative signals with nomenclature of the involved crossing and direct telephone line for reporting emergencies. This implementation is unaffordable for most municipal governments. Also, an inventory of the most dangerous grade crossings in urban and rural areas must be obtained. Then, an approach for improving the classification of grade crossings is suggested. This approach must be based on criteria design, characteristics of adjacent roads or intersections which can influence traffic flow through the crossing, accidents related to motorized and non-motorized vehicles, land use and land management, type of area, and services and economic activities in the zone where the grade crossings is located. An expanded classification of grade crossing in Mexico could reduce accidents and improve the efficiency of the railroad.

Keywords: accidents, grade crossing, railroad, traffic safety

Procedia PDF Downloads 88

Authors: Edwin Calderon-Mendoza, Patrick Schweitzer, Serge Weber

Abstract:

Series arc faults appear frequently and unpredictably in low voltage distribution systems. Many methods have been developed to detect this type of faults and commercial protection systems such AFCI (arc fault circuit interrupter) have been used successfully in electrical networks to prevent damage and catastrophic incidents like fires. However, these devices do not allow series arc faults to be located on the line in operating mode. This paper presents a location algorithm for series arc fault in a low-voltage indoor power line in an AC 230 V-50Hz home network. The method is validated through simulations using the MATLAB software. The fault location method uses electrical parameters (resistance, inductance, capacitance, and conductance) of a 49 m indoor power line. The mathematical model of a series arc fault is based on the analysis of the V-I characteristics of the arc and consists basically of two antiparallel diodes and DC voltage sources. In a first step, the arc fault model is inserted at some different positions across the line which is modeled using lumped parameters. At both ends of the line, currents and voltages are recorded for each arc fault generation at different distances. In the second step, a fault map trace is created by using signature coefficients obtained from Kirchhoff equations which allow a virtual decoupling of the line’s mutual capacitance. Each signature coefficient obtained from the subtraction of estimated currents is calculated taking into account the Discrete Fast Fourier Transform of currents and voltages and also the fault distance value. These parameters are then substituted into Kirchhoff equations. In a third step, the same procedure described previously to calculate signature coefficients is employed but this time by considering hypothetical fault distances where the fault can appear. In this step the fault distance is unknown. The iterative calculus from Kirchhoff equations considering stepped variations of the fault distance entails the obtaining of a curve with a linear trend. Finally, the fault distance location is estimated at the intersection of two curves obtained in steps 2 and 3. The series arc fault model is validated by comparing current registered from simulation with real recorded currents. The model of the complete circuit is obtained for a 49m line with a resistive load. Also, 11 different arc fault positions are considered for the map trace generation. By carrying out the complete simulation, the performance of the method and the perspectives of the work will be presented.

Keywords: indoor power line, fault location, fault map trace, series arc fault

Procedia PDF Downloads 115

Authors: William Luke Hamel

Abstract:

Existing conceptions of urban flooding caused by tidal fluctuations and sea-level rise have been inadequately conceptualized by metrics of resilience and methods of flow modeling. While a great deal of research has been devoted to the effects of urbanization on pluvial flooding, the kind of tidal flooding experienced by locations like Hampton Roads, Virginia, has not been adequately conceptualized as being a result of human factors such as urbanization and gray infrastructure. Resilience from sea level rise and its associated flooding has been pioneered in the region with the 2015 Norfolk Resilience Plan from 100 Resilient Cities as well as the 2016 Norfolk Vision 2100 plan, which envisions different patterns of land use for the city. Urban resilience still conceptualizes the city as having the ability to maintain an equilibrium in the face of disruptions. This economic and social equilibrium relies on the Elizabeth River, narrowly conceptualized. Intentionally or accidentally, the river was made to be a piece of infrastructure. Its development was meant to serve the docks, shipyards, naval yards, and port infrastructure that gives the region so much of its economic life. Inasmuch as it functions to permit the movement of cargo; the raising and lowering of ships to be repaired, commissioned, or decommissioned; or the provisioning of military vessels, the river as infrastructure is functioning properly. The idea that the infrastructure is malfunctioning when high tides and sea-level rise create flooding is predicated on the idea that the infrastructure is truly a human creation and can be controlled. The natural flooding cycles of an urban river, combined with the action of climate change and sea-level rise, are only abnormal so much as they encroach on the development that first encroached on the river. The urban political ecology of water provides the ability to view the river as an infrastructural extension of urban networks while also calling for its emancipation from stationarity and human control. Understanding the river and city as a hydrosocial territory or as a socio-natural system liberates both actors from the duality of the natural and the social while repositioning river flooding as a normal part of coexistence on a floodplain. This paper argues for the adoption of an urban political ecology lens in the analysis and governance of urban rivers like the Elizabeth River as a departure from the equilibrium-seeking and stability metrics of urban resilience.

Keywords: urban flooding, political ecology, Elizabeth river, Hampton roads

Procedia PDF Downloads 142

Authors: Mirain Rhys, Kevin Smith

Abstract:

In 2017, the Welsh Government introduced an ambitious, new strategy to increase the number of Welsh speakers in Wales to 1 million by 2050. The Welsh education system is a vitally important feature of this strategy. All children attending state schools in Wales learn Welsh as a second language until the age of 16 and are assessed at General Certificate of Secondary Education (GCSE) level. In 2013, a review of Welsh second language instruction in Key Stages 3 and 4 was completed. The report identified considerable gaps in teachers’ preparation and training for teaching Welsh; poor Welsh language ethos at many schools; and a general lack of resources to support the instruction of Welsh. Recommendations were made across a number of dimensions including curriculum content, pedagogical practice, and teacher assessment, training, and resources. With a new national curriculum currently in development, this study builds on this review and provides unprecedented detail into pupils’ and teachers’ perceptions of Welsh language instruction. The current research built on data taken from an existing capacity building research project on Welsh education, the Wales multi-cohort study (WMS). Quantitative data taken from WMS surveys with over 1200 pupils in schools in Wales indicated that Welsh language lessons were the least enjoyable subject among pupils. The current research aimed to unpick pupil experiences in order to add to the policy development context. To achieve this, forty-four pupils and four teachers in three schools from the larger WMS sample participated in focus groups. Participants from years 9, 11 and 13 who had indicated positive, negative and neutral attitudes towards the Welsh language in a previous WMS survey were selected. Questions were based on previous research exploring issues including, but not limited to pedagogy, policy, assessment, engagement and (teacher) training. A thematic analysis of the focus group recordings revealed that the majority of participants held positive views around keeping the language alive but did not want to take on responsibility for its maintenance. These views were almost entirely based on their experiences of learning Welsh at school, especially in relation to their perceived lack of choice and opinions around particular lesson strategies and assessment. Analysis of teacher interviews highlighted a distinct lack of resources (materials and staff alike) compared to modern foreign languages, which had a negative impact on student motivation and attitudes. Both staff and students indicated a need for more practical, oral language instruction which could lead to Welsh being used outside the classroom. The data corroborate many of the review’s previous findings, but what makes this research distinctive is the way in which pupils poignantly address generally misguided aims for Welsh language instruction, poor pedagogical practice and a general disconnect between Welsh instruction and its daily use in their lives. These findings emphasize the complexity of incorporating the educational sector in strategies for Welsh language maintenance and the complications arising from pedagogical training, support, and resources, as well as teacher and pupil perceptions of, and attitudes towards, teaching and learning Welsh.

Keywords: bilingual education, language maintenance, language revitalisation, minority languages, Wales

Procedia PDF Downloads 95

Authors: Muhammad Arif Khan, Haroon Idrees, Imran Aziz, Sidra Mushtaq

Abstract:

The purpose of this study is to investigate the current level of knowledge mapping skills of the public sector employees in Pakistan. National Institute of Management is one of the premiere public sector training organization for mid-career public sector employees in Pakistan. This study is conducted on participants of fourteen weeks long training course called Mid-Career Management Course (MCMC) which is mandatory for public sector employees in order to ascertain how to enhance their knowledge mapping skills. Methodology: Researcher used both qualitative and quantitative approach to conduct this study. Primary data about current level of participants’ understanding of knowledge mapping was collected through structured questionnaire. Later on, Participant Observation method was used where researchers acted as part of the group to gathered data from the trainees during their performance in training activities and tasks. Findings: Respondents of the study were examined for skills and abilities to organizing ideas, helping groups to develop conceptual framework, identifying critical knowledge areas of an organization, study large networks and identifying the knowledge flow using nodes and vertices, visualizing information, represent organizational structure etc. Overall, the responses varied in different skills depending on the performance and presentations. However, generally all participants have demonstrated average level of using both the IT and Non-IT K-mapping tools and techniques during simulation exercises, analysis paper de-briefing, case study reports, post visit presentation, course review, current issue presentation, syndicate meetings, and daily synopsis. Research Limitations: This study is conducted on a small-scale population of 67 public sector employees nominated by federal government to undergo 14 weeks extensive training program called MCMC (Mid-Career Management Course) at National Institute of Management, Peshawar, Pakistan. Results, however, reflects only a specific class of public sector employees i.e. working in grade 18 and having more than 5 years of work. Practical Implications: Research findings are useful for trainers, training agencies, government functionaries, and organizations working for capacity building of public sector employees.

Keywords: knowledge management, km in public sector, knowledge management and professional development, knowledge management in training, knowledge mapping

Procedia PDF Downloads 235

Authors: Michelle Mansfield

Abstract:

Introduction: This paper uses the work of Deleuze and Guattari to consider the street art practice of youth in the Indonesian city of Yogyakarta, a hub of arts and culture in Central Java. Around the world young people have taken to city streets to populate the new informal exhibition spaces outside the galleries of official art institutions. However, rarely is the focus outside the urban metropolis of the ‘Global North.' This paper looks at these practices in a ‘Global South’ Asian context. Space and place are concepts central to understanding youth cultural expression as it emerges on the streets. Deleuze and Guattari’s notion of assemblage enriches understanding of this complex spatial and creative relationship. Yogyakarta street art combines global patterns and motifs with local meanings, symbolism, and language to express local youth voices that convey a unique sense of place on the world stage. Street art has developed as a global urban youth art movement and is theorised as a way in which marginalised young people reclaim urban space for themselves. Methodologies: This study utilised a variety of qualitative methodologies to collect and analyse data. This project took a multi-method approach to data collection, incorporating the qualitative social research methods of ethnography, nongkrong (deep hanging out), participatory action research, online research, in-depth interviews and focus group discussions. Both interviews and focus groups employed photo-elicitation methodology to stimulate rich data gathering. To analyse collected data, rhizoanalytic approaches incorporating discourse analysis and visual analysis were utilised. Street art practice is a fluid and shifting phenomenon, adding to the complexity of inquiry sites. A qualitative approach to data collection and analysis was the most appropriate way to map the components of the street art assemblage and to draw out complexities of this youth cultural practice in Yogyakarta. Major Findings: The rhizoanalytic approach devised for this study proved a useful way of examining in the street art assemblage. It illustrated the ways in which the street art assemblage is constructed. Especially the interaction of inspiration, materials, creative techniques, audiences, and spaces operate in the creations of artworks. The study also exposed the generational tensions between the senior arts practitioners, the established art world, and the young artists. Conclusion: In summary, within the spatial processes of the city, street art is inextricably linked with its audience, its striving artistic community and everyday life in the smooth rather than the striated worlds of the state and the official art world. In this way, the anarchic rhizomatic art practice of nomadic urban street crews can be described not only as ‘becoming-artist’ but as constituting ‘nomos’, a way of arranging elements which are not dependent on a structured, hierarchical organisation practice. The site, streets, crews, neighbourhood and the passers by can all be examined with the concept of assemblage. The assemblage effectively brings into focus the complexity, dynamism, and flows of desire that is a feature of street art practice by young people in Yogyakarta.

Keywords: assemblage, Indonesia, street art, youth

Procedia PDF Downloads 161

Authors: Yan Zhang

Abstract:

Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. Analytics-driven predictive maintenance is gaining increasing attention in many industries such as manufacturing, utilities, aerospace, etc., along with the emerging demand of Internet of Things (IoT) applications and the maturity of technologies that support Big Data storage and processing. This study aims to build an end-to-end analytics solution that includes both real-time machine condition monitoring and machine learning based predictive analytics capabilities. The goal is to showcase a general predictive maintenance solution architecture, which suggests how the data generated from field machines can be collected, transmitted, stored, and analyzed. We use a publicly available aircraft engine run-to-failure dataset to illustrate the streaming analytics component and the batch failure prediction component. We outline the contributions of this study from four aspects. First, we compare the predictive maintenance problems from the view of the traditional reliability centered maintenance field, and from the view of the IoT applications. When evolving to the IoT era, predictive maintenance has shifted its focus from ensuring reliable machine operations to improve production/maintenance efficiency via any maintenance related tasks. It covers a variety of topics, including but not limited to: failure prediction, fault forecasting, failure detection and diagnosis, and recommendation of maintenance actions after failure. Second, we review the state-of-art technologies that enable a machine/device to transmit data all the way through the Cloud for storage and advanced analytics. These technologies vary drastically mainly based on the power source and functionality of the devices. For example, a consumer machine such as an elevator uses completely different data transmission protocols comparing to the sensor units in an environmental sensor network. The former may transfer data into the Cloud via WiFi directly. The latter usually uses radio communication inherent the network, and the data is stored in a staging data node before it can be transmitted into the Cloud when necessary. Third, we illustrate show to formulate a machine learning problem to predict machine fault/failures. By showing a step-by-step process of data labeling, feature engineering, model construction and evaluation, we share following experiences: (1) what are the specific data quality issues that have crucial impact on predictive maintenance use cases; (2) how to train and evaluate a model when training data contains inter-dependent records. Four, we review the tools available to build such a data pipeline that digests the data and produce insights. We show the tools we use including data injection, streaming data processing, machine learning model training, and the tool that coordinates/schedules different jobs. In addition, we show the visualization tool that creates rich data visualizations for both real-time insights and prediction results. To conclude, there are two key takeaways from this study. (1) It summarizes the landscape and challenges of predictive maintenance applications. (2) It takes an example in aerospace with publicly available data to illustrate each component in the proposed data pipeline and showcases how the solution can be deployed as a live demo.

Keywords: Internet of Things, machine learning, predictive maintenance, streaming data

Procedia PDF Downloads 364

Authors: A. Caicedo Padilla, J. Zambrano Nájera

Abstract:

Cali, the capital of Valle del Cauca and the second city of Colombia, is located in the Cauca River Valley between the Western and Central Cordillera that is South West of the country. The topography of the city is mainly flat, but it is possibly to find mountains in the west. The city has increased urbanization during XX century, especially since 1958 when started a rapid growth due to migration of people from other parts of the region. Much of that population has settled in eastern of Cali, an area originally intended for cane cultivation and a zone of flood from Cauca River and its tributaries. Due to the unplanned migration, settling was inadequate and produced changes in natural dynamics of the basins, which has resulted in increases in runoff volumes, peak flows and flow velocities, that in turn increases flood risk. Sewerage networks capacity were not enough for this higher runoff volume, because in first term they were not adequately designed and built, causing its failure. This in turn generates increasingly recurrent floods generating considerable effects on the economy and development of normal activities in Cali. Thus, it becomes very important to know hydrological behavior of Urban Watersheds. This research aims to determine the impact of urbanization on hydrology of watersheds with very low slopes. The project aims to identify changes in natural drainage patterns caused by the changes made on landscape. From the identification of such modifications it will be defined the most critical areas due to recurring flood events in the city of Cali. Critical areas are defined as areas where the sewerage system does not work properly as surface runoff increases considerable with storm events, and floods are recurrent. The assessment will be done from the analysis of Geographic Information Systems (GIS) theme layers from CVC Environmental Institution of Regional Control in Valle del Cauca, hydrological data and disaster database developed by OSSO Corporation. Rainfall data from a network and historical stream flow data will be used for analysis of historical behavior and change of precipitation and hydrological response according to homogeneous zones characterized by EMCALI S.A. public utility enterprise of Cali in 1999.

Keywords: drainage systems, land cover changes, urban hydrology, urban planning

Procedia PDF Downloads 240

Authors: Pin Xiu Chen, Shang Liang Chen

Abstract:

A virtualized software controller is developed in this research to replace traditional hardware control units. This virtualized software controller transfers motion interpolation calculations from the motion control units of end devices to edge computing platforms, thereby reducing the end devices' computational load and hardware requirements and making maintenance and updates easier. The study also applies the concept of microservices, dividing the control system into several small functional modules and then deploy into a cloud data server. This reduces the interdependency among modules and enhances the overall system's flexibility and scalability. Finally, with containerization technology, the system can be deployed and started in a matter of seconds, which is more efficient than traditional virtual machine deployment methods. Furthermore, this virtualized software controller communicates with end control devices via wireless networks, making the placement of production equipment or the redesign of processes more flexible and no longer limited by physical wiring. To handle the large data flow and maintain low-latency transmission, this study integrates 5G technology, fully utilizing its high speed, wide bandwidth, and low latency features to achieve rapid and stable remote machine control. An experimental setup is designed to verify the feasibility and test the performance of this framework. This study designs a smart manufacturing site with a 5G communication architecture, serving as a field for experimental data collection and performance testing. The smart manufacturing site includes one robotic arm, three Computer Numerical Control machine tools, several Input/Output ports, and an edge computing architecture. All machinery information is uploaded to edge computing servers and cloud servers via 5G communication and the Internet of Things framework. After analysis and computation, this information is converted into motion control commands, which are transmitted back to the relevant machinery for motion control through 5G communication. The communication time intervals at each stage are calculated using the C++ chrono library to measure the time difference for each command transmission. The relevant test results will be organized and displayed in the full-text.

Keywords: 5G, MEC, microservices, virtualized software controller, smart manufacturing

Procedia PDF Downloads 51

Authors: B. S Kaith, K. Sharma, V. Kumar, S. Kalia

Abstract:

Superabsorbent are three-dimensional networks of linear or branched polymeric chains which can uptake large volume of biological fluids. The ability is due to the presence of functional groups like –NH2, -COOH and –OH. Such cross-linked products based on natural materials, such as cellulose, starch, dextran, gum and chitosan, because of their easy availability, low production cost, non-toxicity and biodegradability have attracted the attention of Scientists and Technologists all over the world. Since natural polymers have better biocompatibility and are non-toxic than most synthetic one, therefore, such materials can be applied in the preparation of controlled drug delivery devices, biosensors, tissue engineering, contact lenses, soil conditioning, removal of heavy metal ions and dyes. Gums are natural potential antioxidants and are used as food additives. They have excellent properties like high solubility, pH stability, non-toxicity and gelling characteristics. Till date lot of methods have been applied for the synthesis and modifications of cross-linked materials with improved properties suitable for different applications. It is well known that ion beam irradiation can play a crucial role to synthesize, modify, crosslink or degrade polymeric materials. High energetic heavy ions irradiation on polymer film induces significant changes like chain scission, cross-linking, structural changes, amorphization and degradation in bulk. Various researchers reported the effects of low and heavy ion irradiation on the properties of polymeric materials and observed significant improvement in optical, electrical, chemical, thermal and dielectric properties. Moreover, modifications induced in the materials mainly depend on the structure, the ion beam parameters like energy, linear energy transfer, fluence, mass, charge and the nature of the target material. Ion-beam irradiation is a useful technique for improving the surface properties of biodegradable polymers without missing the bulk properties. Therefore, a considerable interest has been grown to study the effects of SHIs irradiation on the properties of synthesized semi-IPNs and IPNs. The present work deals with the preparation of semi-IPNs and IPNs and impact of SHI like O7+ and Ni9+ irradiation on optical, chemical, structural, morphological and thermal properties along with impact on different applications. The results have been discussed on the basis of Linear Energy Transfer (LET) of the ions.

Keywords: adsorbent, gel, IPNs, semi-IPNs

Procedia PDF Downloads 352

Authors: Peter C. St. John, Michael F. Crowley, Yannick J. Bomble

Abstract:

Production of chemicals from engineered organisms in a batch culture typically involves a trade-off between productivity, yield, and titer. However, strategies for strain design typically involve designing mutations to achieve the highest yield possible while maintaining growth viability. Such approaches tend to follow the principle of designing static networks with minimum metabolic functionality to achieve desired yields. While these methods are computationally tractable, optimum productivity is likely achieved by a dynamic strategy, in which intracellular fluxes change their distribution over time. One can use multi-stage fermentations to increase either productivity or yield. Such strategies would range from simple manipulations (aerobic growth phase, anaerobic production phase), to more complex genetic toggle switches. Additionally, some computational methods can also be developed to aid in optimizing two-stage fermentation systems. One can assume an initial control strategy (i.e., a single reaction target) in maximizing productivity - but it is unclear how close this productivity would come to a global optimum. The calculation of maximum theoretical yield in metabolic engineering can help guide strain and pathway selection for static strain design efforts. Here, we present a method for the calculation of a maximum theoretical productivity of a batch culture system. This method follows the traditional assumptions of dynamic flux balance analysis: that internal metabolite fluxes are governed by a pseudo-steady state and external metabolite fluxes are represented by dynamic system including Michealis-Menten or hill-type regulation. The productivity optimization is achieved via dynamic programming, and accounts explicitly for an arbitrary number of fermentation stages and flux variable changes. We have applied our method to succinate production in two common microbial hosts: E. coli and A. succinogenes. The method can be further extended to calculate the complete productivity versus yield Pareto surface. Our results demonstrate that nearly optimal yields and productivities can indeed be achieved with only two discrete flux stages.

Keywords: A. succinogenes, E. coli, metabolic engineering, metabolite fluxes, multi-stage fermentations, succinate

Procedia PDF Downloads 192

Authors: Darren J. Ellis

Abstract:

This paper investigates the key industry-level consequences and future prospects for the global airline industry of the requirement for airlines to have a home base. This industry context results in geographical location playing a central role in determining how and where international airlines can operate, and the extent to which their international networks can develop. Data from a five stage mixed-methods Delphi study into the global airline industry’s likely future trajectory conducted in 2013 and 2014 are utilized to better understand the likelihood and consequences of home base requirements changing in future. Expert views and forecasts were collected to gauge core industry trends over a ten year timeframe. Attempts to change or bypass this industry requirement have not been successful to date outside of the European single air market. Europe remains the only prominent exception to the general rule in this regard. Most of the industry is founded on air space sovereignty, the nationality rule, and the bilateral system of traffic rights. Europe’s exceptionalism has seen it evolve into a single air market with characteristics similar to a nation-state, rather than to become a force for wider industry change and regional multilateralism. Europe has indeed become a key actor in global aviation, but Europe seems to now be part of the industry’s status quo, not a vehicle for substantially wider multilateralism around the world. The findings from this research indicate that the bilateral system is not viewed by most study experts as disappearing or substantially weakening in the foreseeable future. However, regional multilateralism was also viewed as progressively taking hold in the industry in future, demonstrating that for most industry experts the two are not seen as mutually exclusive but rather as being able to co-exist with each other. This reality ensures that geographical location will continue to play an important role in the global airline industry in future and that, home base requirements will not disappear any time soon either. Even moves in some aviation jurisdictions to dilute nationality requirements for airlines, and instead replace ownership and control restrictions with principal place of business tests, do not ultimately free airlines from their home base. Likewise, an expansion of what constitutes home base to include a regional grouping of countries – again, a currently uncommon reality in global aviation – does not fundamentally weaken the continued relevance of geographical location to the global industry’s future growth and development realities and prospects.

Keywords: airline industry, air space sovereignty, geographical location, home base

Procedia PDF Downloads 111

Authors: B. S. Premalatha, Kausalya Sahani

Abstract:

Background: Glomus jugulare tumors arise within the jugular foramen and are commonly seen in females particularly on the left side. Surgical excision of the tumor may cause lower cranial nerve deficits. Cranial nerve involvement produces hoarseness of voice, slurred speech, and dysphagia along with other physical symptoms, thereby affecting the quality of life of individuals. Though oncological clearance is mainly emphasized on while treating these individuals, little importance is given to their communication, voice and swallowing problems, which play a crucial part in daily functioning. Objective: To examine the functions of voice, speech and swallowing outcomes of the subjects, following excision of glomus jugulare tumor. Methods: Two female subjects aged 56 and 62 years had come with a complaint of change in voice, inability to swallow and reduced clarity of speech following surgery for left glomus jugulare tumor were participants of the study. Their surgical information revealed multiple cranial nerve palsies involving the left facial, left superior and recurrent branches of the vagus nerve, left pharyngeal, left soft palate, left hypoglossal and vestibular nerves. Functional outcomes of voice, speech and swallowing were evaluated by perceptual and objective assessment procedures. Assessment included the examination of oral structures and functions, dysarthria by Frenchey dysarthria assessment, cranial nerve functions and swallowing functions. MDVP and Dr. Speech software were used to evaluate acoustic parameters of voice and quality of voice respectively. Results: The study revealed that both the subjects, subsequent to excision of glomus jugulare tumor, showed a varied picture of affected oral structure and functions, articulation, voice and swallowing functions. The cranial nerve assessment showed impairment of the vagus, hypoglossal, facial and glossopharyngeal nerves. Voice examination indicated vocal cord paralysis associated with breathy quality of voice, weak voluntary cough, reduced pitch and loudness range, and poor respiratory support. Perturbation parameters as jitter, shimmer were affected along with s/z ratio indicative of voice fold pathology. Reduced MPD(Maximum Phonation Duration) of vowels indicated that disturbed coordination between respiratory and laryngeal systems. Hypernasality was found to be a prominent feature which reduced speech intelligibility. Imprecise articulation was seen in both the subjects as the hypoglossal nerve was affected following surgery. Injury to vagus, hypoglossal, gloss pharyngeal and facial nerves disturbed the function of swallowing. All the phases of swallow were affected. Aspiration was observed before and during the swallow, confirming the oropharyngeal dysphagia. All the subsystems were affected as per Frenchey Dysarthria Assessment signifying the diagnosis of flaccid dysarthria. Conclusion: There is an observable communication and swallowing difficulty seen following excision of glomus jugulare tumor. Even with complete resection, extensive rehabilitation may be necessary due to significant lower cranial nerve dysfunction. The finding of the present study stresses the need for involvement of as speech and swallowing therapist for pre-operative counseling and assessment of functional outcomes.

Keywords: functional outcome, glomus jugulare tumor excision, multiple cranial nerve impairment, speech and swallowing

Procedia PDF Downloads 230

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 83