Search results for: data combining
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 24986

Search results for: data combining

24026 A Formal Approach for Instructional Design Integrated with Data Visualization for Learning Analytics

Authors: Douglas A. Menezes, Isabel D. Nunes, Ulrich Schiel

Abstract:

Most Virtual Learning Environments do not provide support mechanisms for the integrated planning, construction and follow-up of Instructional Design supported by Learning Analytic results. The present work aims to present an authoring tool that will be responsible for constructing the structure of an Instructional Design (ID), without the data being altered during the execution of the course. The visual interface aims to present the critical situations present in this ID, serving as a support tool for the course follow-up and possible improvements, which can be made during its execution or in the planning of a new edition of this course. The model for the ID is based on High-Level Petri Nets and the visualization forms are determined by the specific kind of the data generated by an e-course, a population of students generating sequentially dependent data.

Keywords: educational data visualization, high-level petri nets, instructional design, learning analytics

Procedia PDF Downloads 223
24025 Analysis of Users’ Behavior on Book Loan Log Based on Association Rule Mining

Authors: Kanyarat Bussaban, Kunyanuth Kularbphettong

Abstract:

This research aims to create a model for analysis of student behavior using Library resources based on data mining technique in case of Suan Sunandha Rajabhat University. The model was created under association rules, apriori algorithm. The results were found 14 rules and the rules were tested with testing data set and it showed that the ability of classify data was 79.24 percent and the MSE was 22.91. The results showed that the user’s behavior model by using association rule technique can use to manage the library resources.

Keywords: behavior, data mining technique, a priori algorithm, knowledge discovery

Procedia PDF Downloads 388
24024 Development and Characterization of a Bio-Sourced Composite Material Based on Phase Change Material and Hemp Shives

Authors: Hachmi Toifane, Pierre Tittelein, Anh Dung Tran Le, Laurent Zalewsi

Abstract:

This study introduces a composite material composed of bio-sourced phase-change material (PCM) of plant origin combined with hemp shives, developed in response to environmental challenges in the construction sector. The state of the art emphasizes the low thermal storage capacity of bio-based materials and highlights increasing need for developing sustainable materials that offer optimal thermal, mechanical, and hydric performances. The combining of PCM's thermal properties and hygric properties of hemp shives results in a material that combines lightness, strength, and hygrothermal regulation. Various formulations are being assessed and compared to conventional hemp concrete. Thermal characterization includes the measurements of thermal conductivity and numerical simulations to evaluate the thermal storage capacity. The results indicate that the addition of PCM significantly enhances the material's thermal storage capacity, positioning this one as a promising, eco-friendly solution for sustainable construction and for improving the energy efficiency of buildings.

Keywords: hemp composite, bio-sourced phase change material, thermal storage, hemp shives

Procedia PDF Downloads 22
24023 Exploration of RFID in Healthcare: A Data Mining Approach

Authors: Shilpa Balan

Abstract:

Radio Frequency Identification, also popularly known as RFID is used to automatically identify and track tags attached to items. This study focuses on the application of RFID in healthcare. The adoption of RFID in healthcare is a crucial technology to patient safety and inventory management. Data from RFID tags are used to identify the locations of patients and inventory in real time. Medical errors are thought to be a prominent cause of loss of life and injury. The major advantage of RFID application in healthcare industry is the reduction of medical errors. The healthcare industry has generated huge amounts of data. By discovering patterns and trends within the data, big data analytics can help improve patient care and lower healthcare costs. The number of increasing research publications leading to innovations in RFID applications shows the importance of this technology. This study explores the current state of research of RFID in healthcare using a text mining approach. No study has been performed yet on examining the current state of RFID research in healthcare using a data mining approach. In this study, related articles were collected on RFID from healthcare journal and news articles. Articles collected were from the year 2000 to 2015. Significant keywords on the topic of focus are identified and analyzed using open source data analytics software such as Rapid Miner. These analytical tools help extract pertinent information from massive volumes of data. It is seen that the main benefits of adopting RFID technology in healthcare include tracking medicines and equipment, upholding patient safety, and security improvement. The real-time tracking features of RFID allows for enhanced supply chain management. By productively using big data, healthcare organizations can gain significant benefits. Big data analytics in healthcare enables improved decisions by extracting insights from large volumes of data.

Keywords: RFID, data mining, data analysis, healthcare

Procedia PDF Downloads 205
24022 The Importance of Knowledge Innovation for External Audit on Anti-Corruption

Authors: Adel M. Qatawneh

Abstract:

This paper aimed to determine the importance of knowledge innovation for external audit on anti-corruption in the entire Jordanian bank companies are listed in Amman Stock Exchange (ASE). The study importance arises from the need to recognize the Knowledge innovation for external audit and anti-corruption as the development in the world of business, the variables that will be affected by external audit innovation are: reliability of financial data, relevantly of financial data, consistency of the financial data, Full disclosure of financial data and protecting the rights of investors to achieve the objectives of the study a questionnaire was designed and distributed to the society of the Jordanian bank are listed in Amman Stock Exchange. The data analysis found out that the banks in Jordan have a positive importance of Knowledge innovation for external audit on anti-corruption. They agree on the benefit of Knowledge innovation for external audit on anti-corruption. The statistical analysis showed that Knowledge innovation for external audit had a positive impact on the anti-corruption and that external audit has a significantly statistical relationship with anti-corruption, reliability of financial data, consistency of the financial data, a full disclosure of financial data and protecting the rights of investors.

Keywords: knowledge innovation, external audit, anti-corruption, Amman Stock Exchange

Procedia PDF Downloads 445
24021 Automated End-to-End Pipeline Processing Solution for Autonomous Driving

Authors: Ashish Kumar, Munesh Raghuraj Varma, Nisarg Joshi, Gujjula Vishwa Teja, Srikanth Sambi, Arpit Awasthi

Abstract:

Autonomous driving vehicles are revolutionizing the transportation system of the 21st century. This has been possible due to intensive research put into making a robust, reliable, and intelligent program that can perceive and understand its environment and make decisions based on the understanding. It is a very data-intensive task with data coming from multiple sensors and the amount of data directly reflects on the performance of the system. Researchers have to design the preprocessing pipeline for different datasets with different sensor orientations and alignments before the dataset can be fed to the model. This paper proposes a solution that provides a method to unify all the data from different sources into a uniform format using the intrinsic and extrinsic parameters of the sensor used to capture the data allowing the same pipeline to use data from multiple sources at a time. This also means easy adoption of new datasets or In-house generated datasets. The solution also automates the complete deep learning pipeline from preprocessing to post-processing for various tasks allowing researchers to design multiple custom end-to-end pipelines. Thus, the solution takes care of the input and output data handling, saving the time and effort spent on it and allowing more time for model improvement.

Keywords: augmentation, autonomous driving, camera, custom end-to-end pipeline, data unification, lidar, post-processing, preprocessing

Procedia PDF Downloads 82
24020 Visual Text Analytics Technologies for Real-Time Big Data: Chronological Evolution and Issues

Authors: Siti Azrina B. A. Aziz, Siti Hafizah A. Hamid

Abstract:

New approaches to analyze and visualize data stream in real-time basis is important in making a prompt decision by the decision maker. Financial market trading and surveillance, large-scale emergency response and crowd control are some example scenarios that require real-time analytic and data visualization. This situation has led to the development of techniques and tools that support humans in analyzing the source data. With the emergence of Big Data and social media, new techniques and tools are required in order to process the streaming data. Today, ranges of tools which implement some of these functionalities are available. In this paper, we present chronological evolution evaluation of technologies for supporting of real-time analytic and visualization of the data stream. Based on the past research papers published from 2002 to 2014, we gathered the general information, main techniques, challenges and open issues. The techniques for streaming text visualization are identified based on Text Visualization Browser in chronological order. This paper aims to review the evolution of streaming text visualization techniques and tools, as well as to discuss the problems and challenges for each of identified tools.

Keywords: information visualization, visual analytics, text mining, visual text analytics tools, big data visualization

Procedia PDF Downloads 380
24019 Reliability Factors Based Fuzzy Logic Scheme for Spectrum Sensing

Authors: Tallataf Rasheed, Adnan Rashdi, Ahmad Naeem Akhtar

Abstract:

The accurate spectrum sensing is a fundamental requirement of dynamic spectrum access for deployment of Cognitive Radio Network (CRN). To acheive this requirement a Reliability factors based Fuzzy Logic (RFL) Scheme for Spectrum Sensing has been proposed in this paper. Cognitive Radio User (CRU) predicts the presence or absence of Primary User (PU) using energy detector and calculates the Reliability factors which are SNR of sensing node, threshold of energy detector and decision difference of each node with other nodes in a cooperative spectrum sensing environment. Then the decision of energy detector is combined with Reliability factors of sensing node using Fuzzy Logic. These Reliability Factors used in RFL Scheme describes the reliability of decision made by a CRU to improve the local spectrum sensing. This Fuzzy combining scheme provides the accuracy of decision made by sensornode. The simulation results have shown that the proposed technique provide better PU detection probability than existing Spectrum Sensing Techniques.

Keywords: cognitive radio, spectrum sensing, energy detector, reliability factors, fuzzy logic

Procedia PDF Downloads 459
24018 Churn Prediction for Telecommunication Industry Using Artificial Neural Networks

Authors: Ulas Vural, M. Ergun Okay, E. Mesut Yildiz

Abstract:

Telecommunication service providers demand accurate and precise prediction of customer churn probabilities to increase the effectiveness of their customer relation services. The large amount of customer data owned by the service providers is suitable for analysis by machine learning methods. In this study, expenditure data of customers are analyzed by using an artificial neural network (ANN). The ANN model is applied to the data of customers with different billing duration. The proposed model successfully predicts the churn probabilities at 83% accuracy for only three months expenditure data and the prediction accuracy increases up to 89% when the nine month data is used. The experiments also show that the accuracy of ANN model increases on an extended feature set with information of the changes on the bill amounts.

Keywords: customer relationship management, churn prediction, telecom industry, deep learning, artificial neural networks

Procedia PDF Downloads 124
24017 The Face Sync-Smart Attendance

Authors: Bekkem Chakradhar Reddy, Y. Soni Priya, Mathivanan G., L. K. Joshila Grace, N. Srinivasan, Asha P.

Abstract:

Currently, there are a lot of problems related to marking attendance in schools, offices, or other places. Organizations tasked with collecting daily attendance data have numerous concerns. There are different ways to mark attendance. The most commonly used method is collecting data manually by calling each student. It is a longer process and problematic. Now, there are a lot of new technologies that help to mark attendance automatically. It reduces work and records the data. We have proposed to implement attendance marking using the latest technologies. We have implemented a system based on face identification and analyzing faces. The project is developed by gathering faces and analyzing data, using deep learning algorithms to recognize faces effectively. The data is recorded and forwarded to the host through mail. The project was implemented in Python and Python libraries used are CV2, Face Recognition, and Smtplib.

Keywords: python, deep learning, face recognition, CV2, smtplib, Dlib.

Procedia PDF Downloads 32
24016 Geographical Data Visualization Using Video Games Technologies

Authors: Nizar Karim Uribe-Orihuela, Fernando Brambila-Paz, Ivette Caldelas, Rodrigo Montufar-Chaveznava

Abstract:

In this paper, we present the advances corresponding to the implementation of a strategy to visualize geographical data using a Software Development Kit (SDK) for video games. We use multispectral images from Landsat 7 platform and Laser Imaging Detection and Ranging (LIDAR) data from The National Institute of Geography and Statistics of Mexican (INEGI). We select a place of interest to visualize from Landsat platform and make some processing to the image (rotations, atmospheric correction and enhancement). The resulting image will be our gray scale color-map to fusion with the LIDAR data, which was selected using the same coordinates than in Landsat. The LIDAR data is translated to 8-bit raw data. Both images are fused in a software developed using Unity (an SDK employed for video games). The resulting image is then displayed and can be explored moving around. The idea is the software could be used for students of geology and geophysics at the Engineering School of the National University of Mexico. They will download the software and images corresponding to a geological place of interest to a smartphone and could virtually visit and explore the site with a virtual reality visor such as Google cardboard.

Keywords: virtual reality, interactive technologies, geographical data visualization, video games technologies, educational material

Procedia PDF Downloads 223
24015 Life Cycle Cost Evaluation of Structures with Hysteretic Dampers

Authors: Jinkoo Kim, Hyungoo Kang, Hyungjun Shin

Abstract:

In this study, a hybrid energy dissipation device is developed by combining a steel slit plate and friction pads to be used for seismic retrofit of structures, and its effectiveness is investigated by comparing the life cycle costs of the structure before and after the retrofit. The seismic energy dissipation capability of the dampers is confirmed by cyclic loading tests. The probabilities of reaching various damage states are obtained by fragility analysis, and the life cycle costs of the model structures are computed using the PACT (Performance Assessment Calculation Tool) program based on FEMA P-58 methodology. The fragility analysis shows that the probabilities of reaching limit states are minimized by the seismic retrofit with hybrid dampers and increasing column size. The seismic retrofit with increasing column size and hybrid dampers results in the lowest repair cost and shortest repair time.

Keywords: slit dampers, friction dampers, seismic retrofit, life cycle cost, FEMA P-58, PACT

Procedia PDF Downloads 307
24014 Nonparametric Sieve Estimation with Dependent Data: Application to Deep Neural Networks

Authors: Chad Brown

Abstract:

This paper establishes general conditions for the convergence rates of nonparametric sieve estimators with dependent data. We present two key results: one for nonstationary data and another for stationary mixing data. Previous theoretical results often lack practical applicability to deep neural networks (DNNs). Using these conditions, we derive convergence rates for DNN sieve estimators in nonparametric regression settings with both nonstationary and stationary mixing data. The DNN architectures considered adhere to current industry standards, featuring fully connected feedforward networks with rectified linear unit activation functions, unbounded weights, and a width and depth that grows with sample size.

Keywords: sieve extremum estimates, nonparametric estimation, deep learning, neural networks, rectified linear unit, nonstationary processes

Procedia PDF Downloads 11
24013 Molecular and Phytochemical Fingerprinting of Anti-Cancer Drug Yielding Plants in South India

Authors: Alexis John de Britto

Abstract:

Studies were performed to select the superior genotypes based on intra-specific variations, caused by phytogeographical, climatic and edaphic parameters of three anti cancer drug yielding mangrove plants such as Acanthus ilicifolius L., Calophyllum inophyllum L. and Excoecaria agallocha L. using ISSR (Inter Simple Sequence Repeats) markers and phytochemical analysis such as preliminary phytochemical tests, TLC, HPTLC, HPLC and antioxidant tests. The plants were collected from five different geographical locations of the East Coast of south India. Genetic heterozygosity, Nei’s gene diversity, Shannon’s information index and Percentage of polymorphism between the populations were calculated using POPGENE software. Cluster analysis was performed using UPGMA algorithm. AMOVA and correlations between genetic diversity and soil factors were analyzed. Combining the molecular and phytochemical variations superior genotypes were selected. Conservation constraints and methods of efficient exploitation of the species are discussed.

Keywords: anti-cancer drug yielding plants, DNA fingerprinting, phytochemical analysis, selection of superior genotypes

Procedia PDF Downloads 314
24012 Development of Risk Management System for Urban Railroad Underground Structures and Surrounding Ground

Authors: Y. K. Park, B. K. Kim, J. W. Lee, S. J. Lee

Abstract:

To assess the risk of the underground structures and surrounding ground, we collect basic data by the engineering method of measurement, exploration and surveys and, derive the risk through proper analysis and each assessment for urban railroad underground structures and surrounding ground including station inflow. Basic data are obtained by the fiber-optic sensors, MEMS sensors, water quantity/quality sensors, tunnel scanner, ground penetrating radar, light weight deflectometer, and are evaluated if they are more than the proper value or not. Based on these data, we analyze the risk level of urban railroad underground structures and surrounding ground. And we develop the risk management system to manage efficiently these data and to support a convenient interface environment at input/output of data.

Keywords: urban railroad, underground structures, ground subsidence, station inflow, risk

Procedia PDF Downloads 315
24011 Study on Measuring Method and Experiment of Arc Fault Detection Device

Authors: Yang Jian-Hong, Zhang Ren-Cheng, Huang Li

Abstract:

Arc fault is one of the main inducements of electric fires. Arc Fault Detection Device (AFDD) can detect arc fault effectively. Arc fault detections and unhooking standards are the keys to AFDD practical application. First, an arc fault continuous production system was developed, which could count the arc half wave number. Then, Combining with the UL1699 standard, ignition probability curve of cotton and unhooking time of various currents intensity were obtained by experiments. The combustion degree of arc fault could be expressed effectively by arc area. Experiments proved that electric fires would be misjudged or missed only using arc half wave number as AFDD unhooking basis. At last, Practical tests were carried out on the self-developed AFDD system. The result showed that actual AFDD unhooking time was the sum of arc half wave cycling number, Arc wave identification time and unhooking mechanical operation time And the first two shared shorter time. Unhooking time standard depended on the shortest mechanical operation time.

Keywords: arc fault detection device, arc area, arc half wave, unhooking time, arc fault

Procedia PDF Downloads 482
24010 Integration of Big Data to Predict Transportation for Smart Cities

Authors: Sun-Young Jang, Sung-Ah Kim, Dongyoun Shin

Abstract:

The Intelligent transportation system is essential to build smarter cities. Machine learning based transportation prediction could be highly promising approach by delivering invisible aspect visible. In this context, this research aims to make a prototype model that predicts transportation network by using big data and machine learning technology. In detail, among urban transportation systems this research chooses bus system.  The research problem that existing headway model cannot response dynamic transportation conditions. Thus, bus delay problem is often occurred. To overcome this problem, a prediction model is presented to fine patterns of bus delay by using a machine learning implementing the following data sets; traffics, weathers, and bus statues. This research presents a flexible headway model to predict bus delay and analyze the result. The prototyping model is composed by real-time data of buses. The data are gathered through public data portals and real time Application Program Interface (API) by the government. These data are fundamental resources to organize interval pattern models of bus operations as traffic environment factors (road speeds, station conditions, weathers, and bus information of operating in real-time). The prototyping model is designed by the machine learning tool (RapidMiner Studio) and conducted tests for bus delays prediction. This research presents experiments to increase prediction accuracy for bus headway by analyzing the urban big data. The big data analysis is important to predict the future and to find correlations by processing huge amount of data. Therefore, based on the analysis method, this research represents an effective use of the machine learning and urban big data to understand urban dynamics.

Keywords: big data, machine learning, smart city, social cost, transportation network

Procedia PDF Downloads 236
24009 Integrated Model for Enhancing Data Security Performance in Cloud Computing

Authors: Amani A. Saad, Ahmed A. El-Farag, El-Sayed A. Helali

Abstract:

Cloud computing is an important and promising field in the recent decade. Cloud computing allows sharing resources, services and information among the people of the whole world. Although the advantages of using clouds are great, but there are many risks in a cloud. The data security is the most important and critical problem of cloud computing. In this research a new security model for cloud computing is proposed for ensuring secure communication system, hiding information from other users and saving the user's times. In this proposed model Blowfish encryption algorithm is used for exchanging information or data, and SHA-2 cryptographic hash algorithm is used for data integrity. For user authentication process a user-name and password is used, the password uses SHA-2 for one way encryption. The proposed system shows an improvement of the processing time of uploading and downloading files on the cloud in secure form.

Keywords: cloud Ccomputing, data security, SAAS, PAAS, IAAS, Blowfish

Procedia PDF Downloads 453
24008 Lineup Optimization Model of Basketball Players Based on the Prediction of Recursive Neural Networks

Authors: Wang Yichen, Haruka Yamashita

Abstract:

In recent years, in the field of sports, decision making such as member in the game and strategy of the game based on then analysis of the accumulated sports data are widely attempted. In fact, in the NBA basketball league where the world's highest level players gather, to win the games, teams analyze the data using various statistical techniques. However, it is difficult to analyze the game data for each play such as the ball tracking or motion of the players in the game, because the situation of the game changes rapidly, and the structure of the data should be complicated. Therefore, it is considered that the analysis method for real time game play data is proposed. In this research, we propose an analytical model for "determining the optimal lineup composition" using the real time play data, which is considered to be difficult for all coaches. In this study, because replacing the entire lineup is too complicated, and the actual question for the replacement of players is "whether or not the lineup should be changed", and “whether or not Small Ball lineup is adopted”. Therefore, we propose an analytical model for the optimal player selection problem based on Small Ball lineups. In basketball, we can accumulate scoring data for each play, which indicates a player's contribution to the game, and the scoring data can be considered as a time series data. In order to compare the importance of players in different situations and lineups, we combine RNN (Recurrent Neural Network) model, which can analyze time series data, and NN (Neural Network) model, which can analyze the situation on the field, to build the prediction model of score. This model is capable to identify the current optimal lineup for different situations. In this research, we collected all the data of accumulated data of NBA from 2019-2020. Then we apply the method to the actual basketball play data to verify the reliability of the proposed model.

Keywords: recurrent neural network, players lineup, basketball data, decision making model

Procedia PDF Downloads 109
24007 Challenges in Multi-Cloud Storage Systems for Mobile Devices

Authors: Rajeev Kumar Bedi, Jaswinder Singh, Sunil Kumar Gupta

Abstract:

The demand for cloud storage is increasing because users want continuous access their data. Cloud Storage revolutionized the way how users access their data. A lot of cloud storage service providers are available as DropBox, G Drive, and providing limited free storage and for extra storage; users have to pay money, which will act as a burden on users. To avoid the issue of limited free storage, the concept of Multi Cloud Storage introduced. In this paper, we will discuss the limitations of existing Multi Cloud Storage systems for mobile devices.

Keywords: cloud storage, data privacy, data security, multi cloud storage, mobile devices

Procedia PDF Downloads 673
24006 Talent Management through Integration of Talent Value Chain and Human Capital Analytics Approaches

Authors: Wuttigrai Ngamsirijit

Abstract:

Talent management in today’s modern organizations has become data-driven due to a demand for objective human resource decision making and development of analytics technologies. HR managers have been faced with some obstacles in exploiting data and information to obtain their effective talent management decisions. These include process-based data and records; insufficient human capital-related measures and metrics; lack of capabilities in data modeling in strategic manners; and, time consuming to add up numbers and make decisions. This paper proposes a framework of talent management through integration of talent value chain and human capital analytics approaches. It encompasses key data, measures, and metrics regarding strategic talent management decisions along the organizational and talent value chain. Moreover, specific predictive and prescriptive models incorporating these data and information are recommended to help managers in understanding the state of talent, gaps in managing talent and the organization, and the ways to develop optimized talent strategies.    

Keywords: decision making, human capital analytics, talent management, talent value chain

Procedia PDF Downloads 152
24005 A Relative Entropy Regularization Approach for Fuzzy C-Means Clustering Problem

Authors: Ouafa Amira, Jiangshe Zhang

Abstract:

Clustering is an unsupervised machine learning technique; its aim is to extract the data structures, in which similar data objects are grouped in the same cluster, whereas dissimilar objects are grouped in different clusters. Clustering methods are widely utilized in different fields, such as: image processing, computer vision , and pattern recognition, etc. Fuzzy c-means clustering (fcm) is one of the most well known fuzzy clustering methods. It is based on solving an optimization problem, in which a minimization of a given cost function has been studied. This minimization aims to decrease the dissimilarity inside clusters, where the dissimilarity here is measured by the distances between data objects and cluster centers. The degree of belonging of a data point in a cluster is measured by a membership function which is included in the interval [0, 1]. In fcm clustering, the membership degree is constrained with the condition that the sum of a data object’s memberships in all clusters must be equal to one. This constraint can cause several problems, specially when our data objects are included in a noisy space. Regularization approach took a part in fuzzy c-means clustering technique. This process introduces an additional information in order to solve an ill-posed optimization problem. In this study, we focus on regularization by relative entropy approach, where in our optimization problem we aim to minimize the dissimilarity inside clusters. Finding an appropriate membership degree to each data object is our objective, because an appropriate membership degree leads to an accurate clustering result. Our clustering results in synthetic data sets, gaussian based data sets, and real world data sets show that our proposed model achieves a good accuracy.

Keywords: clustering, fuzzy c-means, regularization, relative entropy

Procedia PDF Downloads 243
24004 Sampled-Data Model Predictive Tracking Control for Mobile Robot

Authors: Wookyong Kwon, Sangmoon Lee

Abstract:

In this paper, a sampled-data model predictive tracking control method is presented for mobile robots which is modeled as constrained continuous-time linear parameter varying (LPV) systems. The presented sampled-data predictive controller is designed by linear matrix inequality approach. Based on the input delay approach, a controller design condition is derived by constructing a new Lyapunov function. Finally, a numerical example is given to demonstrate the effectiveness of the presented method.

Keywords: model predictive control, sampled-data control, linear parameter varying systems, LPV

Procedia PDF Downloads 286
24003 Deep-Learning to Generation of Weights for Image Captioning Using Part-of-Speech Approach

Authors: Tiago do Carmo Nogueira, Cássio Dener Noronha Vinhal, Gélson da Cruz Júnior, Matheus Rudolfo Diedrich Ullmann

Abstract:

Generating automatic image descriptions through natural language is a challenging task. Image captioning is a task that consistently describes an image by combining computer vision and natural language processing techniques. To accomplish this task, cutting-edge models use encoder-decoder structures. Thus, Convolutional Neural Networks (CNN) are used to extract the characteristics of the images, and Recurrent Neural Networks (RNN) generate the descriptive sentences of the images. However, cutting-edge approaches still suffer from problems of generating incorrect captions and accumulating errors in the decoders. To solve this problem, we propose a model based on the encoder-decoder structure, introducing a module that generates the weights according to the importance of the word to form the sentence, using the part-of-speech (PoS). Thus, the results demonstrate that our model surpasses state-of-the-art models.

Keywords: gated recurrent units, caption generation, convolutional neural network, part-of-speech

Procedia PDF Downloads 75
24002 Development of Typical Meteorological Year for Passive Cooling Applications Using World Weather Data

Authors: Nasser A. Al-Azri

Abstract:

The effectiveness of passive cooling techniques is assessed based on bioclimatic charts that require the typical meteorological year (TMY) for a specified location for their development. However, TMYs are not always available; mainly due to the scarcity of records of solar radiation which is an essential component used in developing common TMYs intended for general uses. Since solar radiation is not required in the development of the bioclimatic chart, this work suggests developing TMYs based solely on the relevant parameters. This approach improves the accuracy of the developed TMY since only the relevant parameters are considered and it also makes the development of the TMY more accessible since solar radiation data are not used. The presented paper will also discuss the development of the TMY from the raw data available at the NOAA-NCDC archive of world weather data and the construction of the bioclimatic charts for some randomly selected locations around the world.

Keywords: bioclimatic charts, passive cooling, TMY, weather data

Procedia PDF Downloads 220
24001 A Deep Learning-Based Pedestrian Trajectory Prediction Algorithm

Authors: Haozhe Xiang

Abstract:

With the rise of the Internet of Things era, intelligent products are gradually integrating into people's lives. Pedestrian trajectory prediction has become a key issue, which is crucial for the motion path planning of intelligent agents such as autonomous vehicles, robots, and drones. In the current technological context, deep learning technology is becoming increasingly sophisticated and gradually replacing traditional models. The pedestrian trajectory prediction algorithm combining neural networks and attention mechanisms has significantly improved prediction accuracy. Based on in-depth research on deep learning and pedestrian trajectory prediction algorithms, this article focuses on physical environment modeling and learning of historical trajectory time dependence. At the same time, social interaction between pedestrians and scene interaction between pedestrians and the environment were handled. An improved pedestrian trajectory prediction algorithm is proposed by analyzing the existing model architecture. With the help of these improvements, acceptable predicted trajectories were successfully obtained. Experiments on public datasets have demonstrated the algorithm's effectiveness and achieved acceptable results.

Keywords: deep learning, graph convolutional network, attention mechanism, LSTM

Procedia PDF Downloads 42
24000 Development of Management System of the Experience of Defensive Modeling and Simulation by Data Mining Approach

Authors: D. Nam Kim, D. Jin Kim, Jeonghwan Jeon

Abstract:

Defense Defensive Modeling and Simulation (M&S) is a system which enables impracticable training for reducing constraints of time, space and financial resources. The necessity of defensive M&S has been increasing not only for education and training but also virtual fight. Soldiers who are using defensive M&S for education and training will obtain empirical knowledge and know-how. However, the obtained knowledge of individual soldiers have not been managed and utilized yet since the nature of military organizations: confidentiality and frequent change of members. Therefore, this study aims to develop a management system for the experience of defensive M&S based on data mining approach. Since individual empirical knowledge gained through using the defensive M&S is both quantitative and qualitative data, data mining approach is appropriate for dealing with individual empirical knowledge. This research is expected to be helpful for soldiers and military policy makers.

Keywords: data mining, defensive m&s, management system, knowledge management

Procedia PDF Downloads 230
23999 Timely Detection and Identification of Abnormalities for Process Monitoring

Authors: Hyun-Woo Cho

Abstract:

The detection and identification of multivariate manufacturing processes are quite important in order to maintain good product quality. Unusual behaviors or events encountered during its operation can have a serious impact on the process and product quality. Thus they should be detected and identified as soon as possible. This paper focused on the efficient representation of process measurement data in detecting and identifying abnormalities. This qualitative method is effective in representing fault patterns of process data. In addition, it is quite sensitive to measurement noise so that reliable outcomes can be obtained. To evaluate its performance a simulation process was utilized, and the effect of adopting linear and nonlinear methods in the detection and identification was tested with different simulation data. It has shown that the use of a nonlinear technique produced more satisfactory and more robust results for the simulation data sets. This monitoring framework can help operating personnel to detect the occurrence of process abnormalities and identify their assignable causes in an on-line or real-time basis.

Keywords: detection, monitoring, identification, measurement data, multivariate techniques

Procedia PDF Downloads 212
23998 Imputation of Urban Movement Patterns Using Big Data

Authors: Eusebio Odiari, Mark Birkin, Susan Grant-Muller, Nicolas Malleson

Abstract:

Big data typically refers to consumer datasets revealing some detailed heterogeneity in human behavior, which if harnessed appropriately, could potentially revolutionize our understanding of the collective phenomena of the physical world. Inadvertent missing values skew these datasets and compromise the validity of the thesis. Here we discuss a conceptually consistent strategy for identifying other relevant datasets to combine with available big data, to plug the gaps and to create a rich requisite comprehensive dataset for subsequent analysis. Specifically, emphasis is on how these methodologies can for the first time enable the construction of more detailed pictures of passenger demand and drivers of mobility on the railways. These methodologies can predict the influence of changes within the network (like a change in time-table or impact of a new station), explain local phenomena outside the network (like rail-heading) and the other impacts of urban morphology. Our analysis also reveals that our new imputation data model provides for more equitable revenue sharing amongst network operators who manage different parts of the integrated UK railways.

Keywords: big-data, micro-simulation, mobility, ticketing-data, commuters, transport, synthetic, population

Procedia PDF Downloads 205
23997 Improvement of Buckling Behavior of Cold Formed Steel Uprights with Open Cross Section Used in Storage Rack Systems

Authors: Yasar Pala, Safa Senaysoy, Emre Calis

Abstract:

In this paper, structural behavior and improvement of buckling behavior of cold formed steel uprights with open cross-section used storage rack system are studied. As a first step, in the case of a stiffener having an inclined part on the flange, experimental and nonlinear finite element analysis are carried out for three different upright lengths. In the uprights with long length, global buckling is observed while distortional buckling and local buckling are observed in the uprights with medium length and those with short length, respectively. After this point, the study is divided into two groups. One of these groups is the case where the stiffener on the flange is folded at 90°. For this case, four different distances of the stiffener from the web are taken into account. In the other group, the case where different depth of stiffener on the web is considered. Combining experimental and finite element results, the cross-section giving the ultimate critical buckling load is selected.

Keywords: steel, upright, buckling, modes, nonlinear finite element analysis, optimization

Procedia PDF Downloads 241