Search results for: neural machine translation (NMT)

Authors: Abdelkrim Belhaoua, Jean-Pierre Radoux

Abstract:

In France, the railway network is one of the main transport infrastructures and is the second largest European network. Therefore, railway inspection is an important task in railway maintenance to ensure safety for passengers using significant means in personal and technical facilities. Artificial vision has recently been applied to several railway applications due to its potential to improve the efficiency and accuracy when analyzing large databases of acquired images. In this paper, we present a vision system able to detect fastening elements based on artificial vision approach. This system acquires railway images using a CCD camera installed under a control carriage. These images are stitched together before having processed. Experimental results are presented to show that the proposed method is robust for detection fasteners in a complex environment.

Keywords: computer vision, image processing, railway inspection, image stitching, fastener recognition, neural network

Procedia PDF Downloads 427

Authors: Yahoel Van Essen, Gordon Ho, Brett Russell, Hans-Georg Worms, Xiao Lin Long, Edward David Cooper, Avner Bachar

Abstract:

Weeds reduce farm and forest productivity, invade crops, smother pastures and some can harm livestock. Farmers need to spend a significant amount of money to control weeds by means of biological, chemical, cultural, and physical methods. To solve the global agricultural labor shortage and remove poisonous chemicals, a fully autonomous, eco-friendly, and sustainable weeding technology is developed. This takes the form of a weeding robot, ‘Roboweeder’. Roboweeder includes a four-wheel-drive self-driving vehicle, a 4-DOF robotic arm which is mounted on top of the vehicle, an electromagnetic wave generator (magnetron) which is mounted on the “wrist” of the robotic arm, 48V battery packs, and a control/communication system. Cameras are mounted on the front and two sides of the vehicle. Using image processing and recognition, distinguish types of weeds are detected before being eliminated. The electromagnetic wave technology is applied to heat the individual weeds and clusters dielectrically causing them to wilt and die. The 4-DOF robotic arm was modeled mathematically based on its structure/mechanics, each joint’s load, brushless DC motor and worm gear’ characteristics, forward kinematics, and inverse kinematics. The Proportional-Integral-Differential control algorithm is used to control the robotic arm’s motion to ensure the waveguide aperture pointing to the detected weeds. GPS and machine vision are used to traverse the farm and avoid obstacles without the need of supervision. A Roboweeder prototype has been built. Multiple test trials show that Roboweeder is able to detect, point, and kill the pre-defined weeds successfully although further improvements are needed, such as reducing the “weeds killing” time and developing a new waveguide with a smaller waveguide aperture to avoid killing crops surrounded. This technology changes the tedious, time consuming and expensive weeding processes, and allows farmers to grow more, go organic, and eliminate operational headaches. A patent of this technology is pending.

Keywords: autonomous navigation, machine vision, precision heating, sustainable and eco-friendly

Procedia PDF Downloads 208

Authors: Samir Lecheb, Ahmed Chellil, Hamza Mechakra, Brahim Safi, Houcine Kebir

Abstract:

In this paper we studied fracture and dynamic behavior of vertical axis wind turbine blade, the VAWT is a historical machine, it has many properties, structure, advantage, component to be able to produce the electricity. We modeled the blade design then imported to Abaqus software for analysis the modes shapes, frequencies, stress, strain, displacement and stress intensity factor SIF, after comparison we chose the idol material. Finally, the CTS test of glass epoxy reinforced polymer plates to obtain the material fracture toughness Kc.

Keywords: blade, crack, frequency, material, SIF

Procedia PDF Downloads 527

Authors: Fouad Berrabah, Saad Salah, Zaamouche Fares

Abstract:

In this paper, the Direct Torque Control (DTC) Control and the Sliding Mode Control for induction motor are presented and compared. The performance of the two control schemes is evaluated in terms of torque and current ripple, and transient response to variations of the torque , speed and robustness, trajectory tracking. In order to identify the more suitable solution for any application, both techniques are analyzed mathematically and simulation results are compared which advantages and drawbacks are discussed.

Keywords: induction motor, DTC- MRAS control, sliding mode control, robustness, trajectory tracking

Procedia PDF Downloads 565

Authors: Molakala Mourya Vardhan Reddy, Kandimala Revanth, Koduru Sumanth, Beena B. M.

Abstract:

Emergency response and recovery operations are severely hampered by natural catastrophes, especially floods. Understanding post-flood scenarios is essential to disaster management because it facilitates quick evaluation and decision-making. To this end, we introduce FloodNet, a brand-new high-resolution aerial picture collection created especially for comprehending post-flood scenes. A varied collection of excellent aerial photos taken during and after flood occurrences make up FloodNet, which offers comprehensive representations of flooded landscapes, damaged infrastructure, and changed topographies. The dataset provides a thorough resource for training and assessing computer vision models designed to handle the complexity of post-flood scenarios, including a variety of environmental conditions and geographic regions. Pixel-level semantic segmentation masks are used to label the pictures in FloodNet, allowing for a more detailed examination of flood-related characteristics, including debris, water bodies, and damaged structures. Furthermore, temporal and positional metadata improve the dataset's usefulness for longitudinal research and spatiotemporal analysis. For activities like flood extent mapping, damage assessment, and infrastructure recovery projection, we provide baseline standards and evaluation metrics to promote research and development in the field of post-flood scene comprehension. By integrating FloodNet into machine learning pipelines, it will be easier to create reliable algorithms that will help politicians, urban planners, and first responders make choices both before and after floods. The goal of the FloodNet dataset is to support advances in computer vision, remote sensing, and disaster response technologies by providing a useful resource for researchers. FloodNet helps to create creative solutions for boosting communities' resilience in the face of natural catastrophes by tackling the particular problems presented by post-flood situations.

Keywords: image classification, segmentation, computer vision, nature disaster, unmanned arial vehicle(UAV), machine learning.

Procedia PDF Downloads 37

Authors: Adel H. Hejaaji

Abstract:

The need for organisations to be flexible to meet the rapidly changing requirements of their customers is now well appreciated and can be witnessed within companies with their use of techniques such as single-minute exchange of die (SMED) for machine change-over or Kanban as the visual production and inventory control for Just-in-time manufacture and delivery. What is not so well appreciated by companies is the need for agility. Put simply it is the need to be alert for a new and unexpected opportunity and quick to respond with the changes necessary in order to profit from it. This paper aims to study the literature of agility in manufacturing to understand the concept of agility and how it is important and critical for the small and medium size manufacturing organisations (SMEs), and to defined the specific benefits of moving towards agility, and thus what benefit it can bring to an organisation.

Keywords: SMEs, agile manufacturing, manufacturing, industrial engineering

Procedia PDF Downloads 583

Authors: F. Saptouw

Abstract:

This paper will examine the digitization process of the |Xam and !Kun notebooks, authored by Lucy Lloyd, Dorothea Bleek and Wilhelm Bleek, and their collaborators |a!kunta, ||kabbo, ≠kasin, Dia!kwain, !kweiten ta ||ken, |han≠kass'o, !nanni, Tamme, |uma, and Da during the 19th century. Detail will be provided about the status of the archive, the creation of the digital archive and selected research projects linked to the archive. The Digital Bleek and Lloyd project is an example of institutional collaboration by the University of Cape Town, University of South Africa, Iziko South African Museum, the National Library of South Africa and the Western Cape Provincial Archives and Records Service. The contemporary value of the archive will be discussed in relation to its current manifestation as a collection of archival and digital objects, each with its own set of properties and archival risk factors. This tension between the two ways to access the archive will be interrogated to shed light on the slippages between the digital object and the archival object. The primary argument is that the process of digitization generates an ontological shift in the status of the archival object. The secondary argument is an engagement with practices to curate the encounters with these ontologically shifted objects and how to relate to each as a contemporary viewer. In conclusion this paper will argue for regarding these archival objects according to the interpretive framework utilized to engage secular relics.

Keywords: archive, curatorship, digitization, museum practice

Procedia PDF Downloads 123

Authors: P. Sankar, P. James Daniel Paul, Siddhant Sahu

Abstract:

A brief review of the empirical studies on the methodology of the stock market decision support would indicate that they are at a threshold of validating the accuracy of the traditional and the fuzzy, artificial neural network and the decision trees. Many researchers have been attempting to compare these models using various data sets worldwide. However, the research community is on the way to the conclusive confidence in the emerged models. This paper attempts to use the automotive sector stock prices from National Stock Exchange (NSE), India and analyze them for the intra-sectorial support for stock market decisions. The study identifies the significant variables and their lags which affect the price of the stocks using OLS analysis and decision tree classifiers.

Keywords: Indian automotive sector, stock market decisions, equity portfolio analysis, decision tree classifiers, statistical data analysis

Procedia PDF Downloads 457

Authors: Hoda A. Abdel Hafez

Abstract:

Mining big data represents a big challenge nowadays. Many types of research are concerned with mining massive amounts of data and big data streams. Mining big data faces a lot of challenges including scalability, speed, heterogeneity, accuracy, provenance and privacy. In telecommunication industry, mining big data is like a mining for gold; it represents a big opportunity and maximizing the revenue streams in this industry. This paper discusses the characteristics of big data (volume, variety, velocity and veracity), data mining techniques and tools for handling very large data sets, mining big data in telecommunication and the benefits and opportunities gained from them.

Keywords: mining big data, big data, machine learning, telecommunication

Procedia PDF Downloads 374

Authors: Qianwei Cheng, A. K. M. Mahbubur Rahman, Anis Sarker, Abu Bakar Siddik Nayem, Ovi Paul, Amin Ahsan Ali, M. Ashraful Amin, Ryosuke Shibasaki, Moinul Zaber

Abstract:

Thomas Friedman, in his famous book, argued that the world in this 21st century is flat and will continue to be flatter. This is attributed to rapid globalization and the interdependence of humanity that engendered tremendous in-flow of human migration towards the urban spaces. In order to keep the urban environment sustainable, policy makers need to plan based on extensive analysis of the urban environment. With the advent of high definition satellite images, high resolution data, computational methods such as deep neural network analysis, and hardware capable of high-speed analysis; urban planning is seeing a paradigm shift. Legacy data on urban environments are now being complemented with high-volume, high-frequency data. However, the first step of understanding urban space lies in useful categorization of the space that is usable for data collection, analysis, and visualization. In this paper, we propose a pragmatic categorization method that is readily usable for machine analysis and show applicability of the methodology on a developing world setting. Categorization to plan sustainable urban spaces should encompass the buildings and their surroundings. However, the state-of-the-art is mostly dominated by classification of building structures, building types, etc. and largely represents the developed world. Hence, these methods and models are not sufficient for developing countries such as Bangladesh, where the surrounding environment is crucial for the categorization. Moreover, these categorizations propose small-scale classifications, which give limited information, have poor scalability and are slow to compute in real time. Our proposed method is divided into two steps-categorization and automation. We categorize the urban area in terms of informal and formal spaces and take the surrounding environment into account. 50 km × 50 km Google Earth image of Dhaka, Bangladesh was visually annotated and categorized by an expert and consequently a map was drawn. The categorization is based broadly on two dimensions-the state of urbanization and the architectural form of urban environment. Consequently, the urban space is divided into four categories: 1) highly informal area; 2) moderately informal area; 3) moderately formal area; and 4) highly formal area. In total, sixteen sub-categories were identified. For semantic segmentation and automatic categorization, Google’s DeeplabV3+ model was used. The model uses Atrous convolution operation to analyze different layers of texture and shape. This allows us to enlarge the field of view of the filters to incorporate larger context. Image encompassing 70% of the urban space was used to train the model, and the remaining 30% was used for testing and validation. The model is able to segment with 75% accuracy and 60% Mean Intersection over Union (mIoU). In this paper, we propose a pragmatic categorization method that is readily applicable for automatic use in both developing and developed world context. The method can be augmented for real-time socio-economic comparative analysis among cities. It can be an essential tool for the policy makers to plan future sustainable urban spaces.

Keywords: semantic segmentation, urban environment, deep learning, urban building, classification

Procedia PDF Downloads 154

Authors: Mehdi Damaliamiri, Firouzeh Akbari

Abstract:

Teaching literature to children at an early age is of great importance, and there have been different methods to facilitate learning literature. Based on the law, all children going to school in Iran should learn the Persian language and literature. This has been concomitant with two different levels of learning related to urban or rural bilingualism. For bilingual children living in the villages, learning literature and a new language (Persian) turns into a big challenge as it is done based on the translation the teacher does while in the city, it is easier as the confrontation of children with the Persian language is more. Over recent years, to change the trend of learning Persian by children speaking another language, the TV and radio programs have been considered to be effective, but the scores of the students in Persian language national exams show that these programs have not been so effective for the bilingual students living in the villages. To identify the determinants of weak learning of Persian by bilingual children, two different regions were chosen, Turkish-speaking and Kurdish-speaking communities, to compare their learning of Persian at the first and second levels of elementary school. The criteria of learning was based on the syllabification of Persian words, word order in the sentence, and compound sentences. Students were taught in Persian how to recognize syllabification without letting them translate the words in their own languages and were asked to produce simple sentences in Persian in response to situational questions. Teaching methods, language relatedness with Persian, and exposure to social media programs, especially TV and radio, were the factors that were considered to affect the potential of children in learning Persian.

Keywords: bilingualism, persian, education, Literature

Procedia PDF Downloads 52

Authors: Magdalena Igras, Joanna Grzybowska, Mariusz Ziółko

Abstract:

The study of emotions expressed in emergency phone call is presented, covering both statistical analysis of emotions configurations and an attempt to automatically classify emotions. An emergency call is a situation usually accompanied by intense, authentic emotions. They influence (and may inhibit) the communication between caller and responder. In order to support responders in their responsible and psychically exhaustive work, we studied when and in which combinations emotions appeared in calls. A corpus of 45 hours of conversations (about 3300 calls) from emergency call center was collected. Each recording was manually tagged with labels of emotions valence (positive, negative or neutral), type (sadness, tiredness, anxiety, surprise, stress, anger, fury, calm, relief, compassion, satisfaction, amusement, joy) and arousal (weak, typical, varying, high) on the basis of perceptual judgment of two annotators. As we concluded, basic emotions tend to appear in specific configurations depending on the overall situational context and attitude of speaker. After performing statistical analysis we distinguished four main types of emotional behavior of callers: worry/helplessness (sadness, tiredness, compassion), alarm (anxiety, intense stress), mistake or neutral request for information (calm, surprise, sometimes with amusement) and pretension/insisting (anger, fury). The frequency of profiles was respectively: 51%, 21%, 18% and 8% of recordings. A model of presenting the complex emotional profiles on the two-dimensional (tension-insecurity) plane was introduced. In the stage of acoustic analysis, a set of prosodic parameters, as well as Mel-Frequency Cepstral Coefficients (MFCC) were used. Using these parameters, complex emotional states were modeled with machine learning techniques including Gaussian mixture models, decision trees and discriminant analysis. Results of classification with several methods will be presented and compared with the state of the art results obtained for classification of basic emotions. Future work will include optimization of the algorithm to perform in real time in order to track changes of emotions during a conversation.

Keywords: acoustic analysis, complex emotions, emotion recognition, machine learning

Procedia PDF Downloads 371

Authors: Reema Alghamdi, Rasees Aleisa, Layan Sukkar

Abstract:

The primary objective of this research is to conduct an examination of the Flo menstrual cycle application. We do that by evaluating the user experience and their satisfaction with integrated AI features. The study seeks to gather data from primary resources, primarily through surveys, to gather different insights about the application, like its usability functionality in addition to the overall user satisfaction. The focus of our project will be particularly directed towards the impact and user perspectives regarding the integration of artificial intelligence features within the application, contributing to an understanding of the holistic user experience.

Keywords: period, women health, machine learning, AI features, menstrual cycle

Procedia PDF Downloads 40

Authors: Anders Troedsson

Abstract:

For us humans, risk and insecurity are intimately linked to vulnerabilities - where there is vulnerability, there is potentially risk and insecurity. Reducing vulnerability through compensatory measures means decreasing the likelihood of a certain external event be qualified as a risk/threat/assault, and thus also means increasing the individual’s sense of security. The paper suggests that a meaningful way to approach the study of risk/ insecurity is to organize thinking about the vulnerabilities that external phenomena evoke in humans as perceived by them. Such phenomena are, through a set of given vulnerabilities, potentially translated into perceptions of "insecurity." An ontological discussion about salient timespace characteristics of external phenomena as perceived by humans, including such which potentially can be qualified as risk/threat/assault, leads to the positing of two dimensions which are central for describing what in the paper is called the essence of risk/threat/assault. As is argued, such modeling helps analysis steer free of the subjective factor which is intimately connected to human perception and which mediates between phenomena “out there” potentially identified as risk/threat/assault, and their translation into an experience of security or insecurity. A proposed set of universally given vulnerabilities are scrutinized with the help of the two dimensions, resulting in a modeling effort featuring four realms of vulnerabilities which together represent a dynamic whole. This model in turn informs modeling on human security.

Keywords: human vulnerabilities, human security, immediate-inert, material-immaterial, timespace

Procedia PDF Downloads 268

Authors: T. Damak, O. Kriaa, A. Baccar, M. A. Ben Ayed, N. Masmoudi

Abstract:

In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used in the safety, the security, and the commercial aspects. Forethought, several methods and techniques are computing to achieve the better levels in terms of accuracy and real time execution. This paper proposed a computer vision algorithm of Number Plate Localization (NPL) and Characters Segmentation (CS). In addition, it proposed an improved method in Optical Character Recognition (OCR) based on Deep Learning (DL) techniques. In order to identify the number of detected plate after NPL and CS steps, the Convolutional Neural Network (CNN) algorithm is proposed. A DL model is developed using four convolution layers, two layers of Maxpooling, and six layers of fully connected. The model was trained by number image database on the Jetson TX2 NVIDIA target. The accuracy result has achieved 95.84%.

Keywords: ANPR, CS, CNN, deep learning, NPL

Procedia PDF Downloads 283

Authors: Vasile Simulescu, Jakub Mondek, Miloslav Pekař

Abstract:

Hyaluronic acid (HA) is an anionic glycosaminoglycan distributed throughout connective, epithelial and neural tissues. The importance of hyaluronic acid increased in the last decades. It has many applications in medicine and cosmetics. Hyaluronic acid has been used in attempts to treat osteoarthritis of the knee via injecting it into the joint. Bovine serum albumin (also known as BSA) is a protein derived from cows, which has many biochemical applications. The aim of our research work was to compare the thermal degradation of hyaluronic acid and BSA in powder and in solution, by determining changes in molar mass and conformation, by using SEC-MALLS (size exclusion chromatography -multi angle laser light scattering). The aim of our research work was to observe the degradation in powder and in solution of different molar mass hyaluronic acid samples, at different temperatures for certain periods. The degradation of the analyzed samples was mainly observed by modifications in molar mass.

Keywords: thermal degradation, hyaluronic acid, BSA, SEC-MALLS

Procedia PDF Downloads 479

Authors: Aurelien Boutin

Abstract:

In optical systems such as Variable Optical Delay Lines, where a collimated beam has to go back and forth, corner cubes are used in order to keep the reflected beam parallel to the incoming beam. However, the reflected beam can be laterally shifted, which will lead to losses. In this paper, we report on a patented optical design that allows keeping the reflected beam with the exact same position and direction whatever the displacement of the corner cube leading to zero losses. After explaining how the optical design works and theoretically allows to compensate for any defects in the translation of the corner cube, we will present the results of experimental comparisons between a standard layout (i.e., only corner cubes) and our optical layout. To compare both optical layouts, we used a fiber-to-fiber coupling setup. It consists of a couple of lights from one fiber to the other, thanks to two lenses. The ensemble [fiber+lense] is fixed and called a collimator so that the light is coupled from one collimator to another. Each collimator was precisely made in order to have a precise working distance. In the experiment, we measured and compared the Insertion Losses (IL) variations between both collimators with the distance between them (i.e., natural Gaussian beam coupling losses) and between both collimators in the different optical layouts tested, with the same optical length propagation. We will show that the IL variations of our setup are less than 0.05dB with respect to the IL variations of collimators alone.

Keywords: free-space optics, variable optical delay lines, optical cavity, auto-alignment

Procedia PDF Downloads 74

Authors: Catherine Vasnetsov, Victor Vasnetsov

Abstract:

Context: Thermo-responsive polymers are materials that undergo significant changes in their physical properties in response to temperature changes. These polymers have gained significant attention in research due to their potential applications in various industries and medicine. However, the molecular mechanisms underlying their behavior are not well understood, particularly in relation to cosolvency, which is crucial for practical applications. Research Aim: This study aimed to theoretically investigate the phenomenon of cosolvency in long-chain polymers using the Flory-Huggins statistical-mechanical framework. The main objective was to understand the interactions between the polymer, solvent, and cosolvent under different conditions. Methodology: The research employed a combination of Monte Carlo computer simulations and advanced machine-learning methods. The Flory-Huggins mean field theory was used as the basis for the simulations. Spinodal graphs and ternary plots were utilized to develop an initial computer model for predicting polymer behavior. Molecular dynamic simulations were conducted to mimic real-life polymer systems. Machine learning techniques were incorporated to enhance the accuracy and reliability of the simulations. Findings: The simulations revealed that the addition of very low or very high volumes of cosolvent molecules resulted in smaller radii of gyration for the polymer, indicating poor miscibility. However, intermediate volume fractions of cosolvent led to higher radii of gyration, suggesting improved miscibility. These findings provide a possible microscopic explanation for the cosolvency phenomenon in polymer systems. Theoretical Importance: This research contributes to a better understanding of the behavior of thermo-responsive polymers and the role of cosolvency. The findings provide insights into the molecular mechanisms underlying cosolvency and offer specific predictions for future experimental investigations. The study also presents a more rigorous analysis of the Flory-Huggins free energy theory in the context of polymer systems. Data Collection and Analysis Procedures: The data for this study was collected through Monte Carlo computer simulations and molecular dynamic simulations. The interactions between the polymer, solvent, and cosolvent were analyzed using the Flory-Huggins mean field theory. Machine learning techniques were employed to enhance the accuracy of the simulations. The collected data was then analyzed to determine the impact of cosolvent volume fractions on the radii of gyration of the polymer. Question Addressed: The research addressed the question of how cosolvency affects the behavior of long-chain polymers. Specifically, the study aimed to investigate the interactions between the polymer, solvent, and cosolvent under different volume fractions and understand the resulting changes in the radii of gyration. Conclusion: In conclusion, this study utilized theoretical modeling and computer simulations to investigate the phenomenon of cosolvency in long-chain polymers. The findings suggest that moderate cosolvent volume fractions can lead to improved miscibility, as indicated by higher radii of gyration. These insights contribute to a better understanding of the molecular mechanisms underlying cosolvency in polymer systems and provide predictions for future experimental studies. The research also enhances the theoretical analysis of the Flory-Huggins free energy theory.

Keywords: molecular modelling, flory-huggins, cosolvency, stimuli-responsive polymers

Procedia PDF Downloads 48

Authors: Olatunbosun Samuel Adekogbe

Abstract:

This paper addresses the question of musical signification, revolving around nature and its natural divides; the paper tends to examine the roles of the dispositional apparatus of listeners to react to sounding environments through music as coordinated sound that focuses on the powerful strain between vibrational occurrences of sound and potentials of being structured. This paper sets out to examine music as a simple conventional design that does not allude to something beyond music and sound as a vehicle to communicate through production, perception, translation, and reaction with regard to melodic and semiotic functions of sounds. This paper adopts the application of questionnaire and evolutionary approach methods to probe musical adaptation, reproduction, and natural selection as the basis for explaining specific human behavioural responses to musical sense-making beyond the above-sketched dichotomies, with a major focus on the transition from acoustic-emotional sensibilities to musical meaning in the selected soundscapes. It was observed that music has emancipated itself from the level of mere acoustic processing of sounds to a functional description in terms of allowing music users to share experiences and interact with the soundscaping environment. The paper, therefore, concludes that the audience as music participants and listeners in the selected soundscapes have been conceived as adaptive devices in the paradigm shift, which can build up new semiotic linkages with the sounding environments in southwestern Nigeria.

Keywords: semiotics, sound, music, soundscape, environment

Procedia PDF Downloads 38

Authors: Sanjay Rathee, Arti Kashyap

Abstract:

Extraction of useful information from large datasets is one of the most important research problems. Association rule mining is one of the best methods for this purpose. Finding possible associations between items in large transaction based datasets (finding frequent patterns) is most important part of the association rule mining. There exist many algorithms to find frequent patterns but Apriori algorithm always remains a preferred choice due to its ease of implementation and natural tendency to be parallelized. Many single-machine based Apriori variants exist but massive amount of data available these days is above capacity of a single machine. Therefore, to meet the demands of this ever-growing huge data, there is a need of multiple machines based Apriori algorithm. For these types of distributed applications, MapReduce is a popular fault-tolerant framework. Hadoop is one of the best open-source software frameworks with MapReduce approach for distributed storage and distributed processing of huge datasets using clusters built from commodity hardware. However, heavy disk I/O operation at each iteration of a highly iterative algorithm like Apriori makes Hadoop inefficient. A number of MapReduce-based platforms are being developed for parallel computing in recent years. Among them, two platforms, namely, Spark and Flink have attracted a lot of attention because of their inbuilt support to distributed computations. Earlier we proposed a reduced- Apriori algorithm on Spark platform which outperforms parallel Apriori, one because of use of Spark and secondly because of the improvement we proposed in standard Apriori. Therefore, this work is a natural sequel of our work and targets on implementing, testing and benchmarking Apriori and Reduced-Apriori and our new algorithm ReducedAll-Apriori on Apache Flink and compares it with Spark implementation. Flink, a streaming dataflow engine, overcomes disk I/O bottlenecks in MapReduce, providing an ideal platform for distributed Apriori. Flink's pipelining based structure allows starting a next iteration as soon as partial results of earlier iteration are available. Therefore, there is no need to wait for all reducers result to start a next iteration. We conduct in-depth experiments to gain insight into the effectiveness, efficiency and scalability of the Apriori and RA-Apriori algorithm on Flink.

Keywords: apriori, apache flink, Mapreduce, spark, Hadoop, R-Apriori, frequent itemset mining

Procedia PDF Downloads 261

Authors: Jamison Duckworth, Shankarachary Ragi

Abstract:

Detection and segmentation of wildfire smoke plumes from remote sensing imagery are being pursued as a solution for early fire detection and response. Smoke plume detection can be automated and made robust by the application of artificial intelligence methods. Specifically, in this study, the deep learning approach Mask Region-based Convolutional Neural Network (RCNN) is being proposed to learn smoke patterns across different spectral bands. This method is proposed to separate the smoke regions from the background and return masks placed over the smoke plumes. Multispectral data was acquired using NASA’s Earthdata and WorldView and services and satellite imagery. Due to the use of multispectral bands along with the three visual bands, we show that Mask R-CNN can be applied to distinguish smoke plumes from clouds and other landscape features that resemble smoke.

Keywords: deep learning, mask-RCNN, smoke plumes, spectral bands

Procedia PDF Downloads 97

Authors: Maulik Parmar, Sumeet Sandhu

Abstract:

The online fashion industry experiences high product return rates. Many returns are because of size/fit mismatches -the size scale on labels can vary across brands, the size parameters may not capture all fit measurements, or the product may have manufacturing defects. Warehouse quality check of garment sizes can be semi-automated to improve speed and accuracy. This paper presents an approach for automatically measuring garment sizes from a single image of the garment -using Deep Learning to learn garment keypoints. The paper focuses on the waist size measurement of jeans and can be easily extended to other garment types and measurements. Experimental results show that this approach can greatly improve the speed and accuracy of today’s manual measurement process.

Keywords: convolutional neural networks, deep learning, distortion, garment measurements, image warping, keypoints

Procedia PDF Downloads 274

Authors: Mania Nosratinia, Zahra Deris

Abstract:

The purpose of the present study was to investigate the relationship between EFL learners' self-regulation (SR) and willingness to communicate (WTC). To this end, 520 male and female EFL learners, ranging between 19 and 34 years old (Mage = 26), majoring in English Translation, English Language Teaching and English Literature at Islamic Azad University, Fars Province, were randomly selected. They were given two questionnaires: Self-Regulation Questionnaire devised by Brown, Miller, and Lawendowski (1999) and Willingness to Communicate Scale devised by McCroskey and Baer (1985). Preliminarily, pertinent analyses were performed on the data to check the assumptions of normality, linearity, and homoscedasticity. Since the assumption of normality was violated, Spearman's rank-order correlation was employed to probe the relationships between SR and WTC. The results indicated a significant and positive correlation between the two variables, ρ = .56, n = 520, p < .05, which signified a large effect size supplemented by a very small confidence interval (0.503 – 0.619). The results of the Kruskal-Wallis tests indicated that there is a statistically significant difference in WTC score between the different levels of SR, χ2(2) = 157.843, p = 0.000 with a mean rank SR score of 128.13 for low-SR level, 286.64 for mid-SR level, and 341.12 for high-SR level. Also, a post-hoc comparison through running a Dwass-Steel-Critchlow-Fligner indicated significant differences among the SR level groups on WTC scores. Given the findings of the study, the obtained results may help EFL teachers, teacher trainers, and material developers to possess a broader perspective towards the TEFL practice and to take practical steps towards the attainments of the desired objectives and effective instruction.

Keywords: EFL learner, self-regulation, willingness to communicate, relationship

Procedia PDF Downloads 290

Authors: Danilo López, Edwin Rivas, Fernando Pedraza

Abstract:

Currently, one of the major challenges in wireless networks is the optimal use of radio spectrum, which is managed inefficiently. One of the solutions to existing problem converges in the use of Cognitive Radio (CR), as an essential parameter so that the use of the available licensed spectrum is possible (by secondary users), well above the usage values that are currently detected; thus allowing the opportunistic use of the channel in the absence of primary users (PU). This article presents the results found when estimating or predicting the future use of a spectral transmission band (from the perspective of the PU) for a chaotic type channel arrival behavior. The time series prediction method (which the PU represents) used is ANFIS (Adaptive Neuro Fuzzy Inference System). The results obtained were compared to those delivered by the RNA (Artificial Neural Network) algorithm. The results show better performance in the characterization (modeling and prediction) with the ANFIS methodology.

Keywords: ANFIS, cognitive radio, prediction primary user, RNA

Procedia PDF Downloads 395

Authors: Zelal Çınar

Abstract:

This paper aims to expose the effects of the ideological program of Turkish Republic on city planning, through the first plan of Ankara. As the new capital, Ankara was planned to be the ‘showcase’ of modern Turkey. It was to represent all new ideologies and the country’s cultural similarities with the west. At the same time it was to underline the national identity and independence of Turkish republic. To this end, a new plan for the capital was designed by German city planner Carl Christopher Lörcher. Diametrically opposed with the existing fabric of the city, this plan was built on the basis of papers and plans, on ideological aims. On the contrary, this paper argues that the city is a machine of possibilities, rather than a clear, materialized system.

Keywords: architecture, ideology, modernization, urban planning

Procedia PDF Downloads 248

Authors: Carlos Arias-Alcaide, Cristina Soguero-Ruiz, Paloma Santos-Álvarez, Adrián García-Romero, Inmaculada Mora-Jiménez

Abstract:

Analysing clinical data with computers in such a way that have an impact on the practitioners’ workflow is a challenge nowadays. This paper provides a first approach for monitoring the health status of COVID-19 patients through the use of some biomarkers (blood tests) and the simplest Naïve Bayes classifier. Data of two Spanish hospitals were considered, showing the potential of our approach to estimate reasonable posterior probabilities even some days before the event.

Keywords: Bayesian model, blood biomarkers, classification, health tracing, machine learning, posterior probability

Procedia PDF Downloads 191

Authors: Minjuan Sun

Abstract:

Ever since the late 1990s, China has experienced explosive growth in consumer lending, especially in short-term consumer loans, among which, the growth rate of non-bank lending has surpassed bank lending due to the development in financial technology. On the other hand, China does not have a universal credit scoring and registration system that can guide lenders during the processes of credit evaluation and risk control, for example, an individual’s bank credit records are not available for online lenders to see and vice versa. Given this context, the purpose of this paper is three-fold. First, we explore if and how alternative digital footprint data can be utilized to assess borrower’s creditworthiness. Then, we perform a comparative analysis of machine learning methods for the canonical problem of credit default prediction. Finally, we analyze, from an institutional point of view, the necessity of establishing a viable and nationally universal credit registration and scoring system utilizing online digital footprints, so that more people in China can have better access to the consumption loan market. Two different types of digital footprint data are utilized to match with bank’s loan default records. Each separately captures distinct dimensions of a person’s characteristics, such as his shopping patterns and certain aspects of his personality or inferred demographics revealed by social media features like profile image and nickname. We find both datasets can generate either acceptable or excellent prediction results, and different types of data tend to complement each other to get better performances. Typically, the traditional types of data banks normally use like income, occupation, and credit history, update over longer cycles, hence they can’t reflect more immediate changes, like the financial status changes caused by the business crisis; whereas digital footprints can update daily, weekly, or monthly, thus capable of providing a more comprehensive profile of the borrower’s credit capabilities and risks. From the empirical and quantitative examination, we believe digital footprints can become an alternative information source for creditworthiness assessment, because of their near-universal data coverage, and because they can by and large resolve the "thin-file" issue, due to the fact that digital footprints come in much larger volume and higher frequency.

Keywords: credit score, digital footprint, Fintech, machine learning

Procedia PDF Downloads 134

Authors: Noora Al Muftah, Reda Rawi, Richard Thompson, Halima Bensmail

Abstract:

Clinical responses to anticancer therapies are often restricted to a subset of patients. In some cases, mutated cancer genes are potent biomarkers of response to targeted agents. There is an urgent need to identify biomarkers that predict which patients with are most likely to respond to treatment. Systematic efforts to correlate tumor mutational data with biologic dependencies may facilitate the translation of somatic mutation catalogs into meaningful biomarkers for patient stratification. To identify genomic features associated with drug sensitivity and uncover new biomarkers of sensitivity and resistance to cancer therapeutics, we have screened and integrated a panel of several hundred cancer cell lines from different databases, mutation, DNA copy number, and gene expression data for hundreds of cell lines with their responses to targeted and cytotoxic therapies with drugs under clinical and preclinical investigation. We found mutated cancer genes were associated with cellular response to most currently available Glioma cancer drugs and some frequently mutated genes were associated with sensitivity to a broad range of therapeutic agents. By linking drug activity to the functional complexity of cancer genomes, systematic pharmacogenomic profiling in cancer cell lines provides a powerful biomarker discovery platform to guide rational cancer therapeutic strategies.

Keywords: cancer, gene network, Lasso, penalized regression, P-values, unbiased estimator

Procedia PDF Downloads 384

Authors: Diego Aguirre, Olac Fuentes

Abstract:

In this paper, we present a taxonomy of weight initialization schemes used in deep learning. We survey the most representative techniques in each class and compare them in terms of overhead cost, convergence rate, and applicability. We also introduce a new weight initialization scheme. In this technique, we perform an initial feedforward pass through the network using an initialization mini-batch. Using statistics obtained from this pass, we initialize the weights of the network, so the following properties are met: 1) weight matrices are orthogonal; 2) ReLU layers produce a predetermined number of non-zero activations; 3) the output produced by each internal layer has a unit variance; 4) weights in the last layer are chosen to minimize the error in the initial mini-batch. We evaluate our method on three popular architectures, and a faster converge rates are achieved on the MNIST, CIFAR-10/100, and ImageNet datasets when compared to state-of-the-art initialization techniques.

Keywords: deep learning, image classification, supervised learning, weight initialization

Procedia PDF Downloads 110

Authors: Ravneil Nand

Abstract:

Cooperative coevolution uses problem decomposition methods to solve a larger problem. The problem decomposition deals with breaking down the larger problem into a number of smaller sub-problems depending on their method. Different problem decomposition methods have their own strengths and limitations depending on the neural network used and application problem. In this paper we are introducing a new problem decomposition method known as Hidden-Neuron Level Decomposition (HNL). The HNL method is competing with established problem decomposition method in time series prediction. The results show that the proposed approach has improved the results in some benchmark data sets when compared to the standalone method and has competitive results when compared to methods from literature.

Keywords: cooperative coevaluation, feed forward network, problem decomposition, neuron, synapse

Procedia PDF Downloads 305