Search results for: information processing model

Authors: Ben Soltane Cheima, Ittansa Yonas Kelbesa

Abstract:

Speaker Identification (SI) is the task of establishing identity of an individual based on his/her voice characteristics. The SI task is typically achieved by two-stage signal processing: training and testing. The training process calculates speaker specific feature parameters from the speech and generates speaker models accordingly. In the testing phase, speech samples from unknown speakers are compared with the models and classified. Even though performance of speaker identification systems has improved due to recent advances in speech processing techniques, there is still need of improvement. In this paper, a Closed-Set Tex-Independent Speaker Identification System (CISI) based on a Multiple Classifier System (MCS) is proposed, using Mel Frequency Cepstrum Coefficient (MFCC) as feature extraction and suitable combination of vector quantization (VQ) and Gaussian Mixture Model (GMM) together with Expectation Maximization algorithm (EM) for speaker modeling. The use of Voice Activity Detector (VAD) with a hybrid approach based on Short Time Energy (STE) and Statistical Modeling of Background Noise in the pre-processing step of the feature extraction yields a better and more robust automatic speaker identification system. Also investigation of Linde-Buzo-Gray (LBG) clustering algorithm for initialization of GMM, for estimating the underlying parameters, in the EM step improved the convergence rate and systems performance. It also uses relative index as confidence measures in case of contradiction in identification process by GMM and VQ as well. Simulation results carried out on voxforge.org speech database using MATLAB highlight the efficacy of the proposed method compared to earlier work.

Keywords: feature extraction, speaker modeling, feature matching, Mel frequency cepstrum coefficient (MFCC), Gaussian mixture model (GMM), vector quantization (VQ), Linde-Buzo-Gray (LBG), expectation maximization (EM), pre-processing, voice activity detection (VAD), short time energy (STE), background noise statistical modeling, closed-set tex-independent speaker identification system (CISI)

Procedia PDF Downloads 309

Authors: Donghee Noh, Seonhyeong Kim, Junhwan Choi, Heegon Kim, Sooho Jung, Keunho Park

Abstract:

In this paper, we describe an image post-processing method to enhance the performance of the parcel segmentation method using deep learning-based aerial images conducted in previous studies. The study results were evaluated using a confusion matrix, IoU, Precision, Recall, and F1-Score. In the case of the confusion matrix, it was observed that the false positive value, which is the result of misclassification, was greatly reduced as a result of image post-processing. The average IoU was 0.9688 in the image post-processing, which is higher than the deep learning result of 0.8362, and the F1-Score was also 0.9822 in the image post-processing, which was higher than the deep learning result of 0.8850. As a result of the experiment, it was found that the proposed technique positively complements the deep learning results in segmenting the parcel of interest.

Keywords: aerial image, image process, machine vision, open field smart farm, segmentation

Procedia PDF Downloads 80

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 67

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 260

Authors: Sheikh Shams Azam, Manoj Raju, Venkatesh Pagidimarri, Vamsi Kasivajjala

Abstract:

Over the past decade, there has been a steep rise in the data-driven analysis in major areas of medicine, such as clinical decision support system, survival analysis, patient similarity analysis, image analytics etc. Most of the data in the field are well-structured and available in numerical or categorical formats which can be used for experiments directly. But on the opposite end of the spectrum, there exists a wide expanse of data that is intractable for direct analysis owing to its unstructured nature which can be found in the form of discharge summaries, clinical notes, procedural notes which are in human written narrative format and neither have any relational model nor any standard grammatical structure. An important step in the utilization of these texts for such studies is to transform and process the data to retrieve structured information from the haystack of irrelevant data using information retrieval and data mining techniques. To address this problem, the authors present Q-Map in this paper, which is a simple yet robust system that can sift through massive datasets with unregulated formats to retrieve structured information aggressively and efficiently. It is backed by an effective mining technique which is based on a string matching algorithm that is indexed on curated knowledge sources, that is both fast and configurable. The authors also briefly examine its comparative performance with MetaMap, one of the most reputed tools for medical concepts retrieval and present the advantages the former displays over the latter.

Keywords: information retrieval, unified medical language system, syntax based analysis, natural language processing, medical informatics

Procedia PDF Downloads 133

Authors: O. Mauroner, L. Le, S. Best

Abstract:

Digital technologies offer many opportunities in the design and implementation of brand communication and advertising. Augmented reality (AR) is an innovative technology in marketing communication that focuses on the fact that virtual interaction with a product ad offers additional value to consumers. AR enables consumers to obtain (almost) real product experiences by the way of virtual information even before the purchase of a certain product. Aim of AR applications in relation with advertising is in-depth examination of product characteristics to enhance product knowledge as well as brand knowledge. Interactive design of advertising provides observers with an intense examination of a specific advertising message and therefore leads to better brand knowledge. The elaboration likelihood model and the central route to persuasion strongly support this argumentation. Nevertheless, AR in brand communication is still in an initial stage and therefore scientific findings about the impact of AR on information processing and brand attitude are rare. The aim of this paper is to empirically investigate the potential of AR applications in combination with traditional print advertising. To that effect an experimental design with different levels of interactivity is built to measure the impact of interactivity of an ad on different variables o advertising effectiveness.

Keywords: advertising effectiveness, augmented reality, brand communication, brand recall

Procedia PDF Downloads 302

Authors: Yasser F. Hassan

Abstract:

In this paper, a proposed model of cellular automata is studied by means of fractional integral function. A cellular automaton is a decentralized computing model providing an excellent platform for performing complex computation with the help of only local information. The paper discusses how using fractional integral function for representing cellular automata memory or state. The architecture of computing and learning model will be given and the results of calibrating of approach are also given.

Keywords: fractional integral, cellular automata, memory, learning

Procedia PDF Downloads 412

Authors: Srinidhi. A, Naveed Ahmed, Twinkle Hareendran, Vriksha Prakash

Abstract:

This work reviews some of the advanced image processing techniques for deep learning applications. Object detection by template matching, image denoising, edge detection, and super-resolution modelling are but a few of the tasks. The paper looks in into great detail, given that such tasks are crucial preprocessing steps that increase the quality and usability of image datasets in subsequent deep learning tasks. We review some of the methods for the assessment of image quality, more specifically sharpness, which is crucial to ensure a robust performance of models. Further, we will discuss the development of deep learning models specific to facial emotion detection, age classification, and gender classification, which essentially includes the preprocessing techniques interrelated with model performance. Conclusions from this study pinpoint the best practices in the preparation of image datasets, targeting the best trade-off between computational efficiency and retaining important image features critical for effective training of deep learning models.

Keywords: image processing, machine learning applications, template matching, emotion detection

Procedia PDF Downloads 13

Authors: L. Kučerová, M. Bystrianský, V. Kotěšovec

Abstract:

Thermo-mechanical processing with various processing parameters was applied to 0.2%C-0.6%Mn-2S%i-0.8%Cr low alloyed high strength steel. The aim of the processing was to achieve the microstructures typical for transformation induced plasticity (TRIP) steels. Thermo-mechanical processing used in this work incorporated two or three deformation steps. The deformations were in all the cases carried out during the cooling from soaking temperatures to various bainite hold temperatures. In this way, 4-10% of retained austenite were retained in the final microstructures, consisting further of ferrite, bainite, martensite and pearlite. The complex character of TRIP steel microstructure is responsible for its good strength and ductility. The strengths achieved in this work were in the range of 740 MPa – 836 MPa with ductility A_5mm of 31-41%.

Keywords: pearlite, retained austenite, thermo-mechanical treatment, TRIP steel

Procedia PDF Downloads 293

Authors: Reham K. El Sawah, N. S. M. El-Tayeb

Abstract:

This study aims to produce a polymer matrix composite reinforced with Al₂O₃ nanoparticles in order to enhance the mechanical properties of PMMA. The composite was fabricated via Friction stir processing to ensure homogenous dispersion of Al₂O₃ nanoparticles in the polymer, and the processing was submerged to prevent the sputtering of nanoparticles. The surface quality, microstructure, impact energy and hardness of the prepared samples were investigated. Good surface quality and dispersion of nanoparticles were attained through employing sufficient processing conditions. The experimental results indicated that as the percentage of nanoparticles increased, the impact energy and hardness increased, reaching 2 kJ/m2 and 14.7 HV at a nanoparticle concentration of 25%, which means that the toughness and the hardness of the polymer-ceramic produced composite is higher than unprocessed PMMA by 66% and 33% respectively.

Keywords: friction stir processing, polymer matrix nanocomposite, mechanical properties, microstructure

Procedia PDF Downloads 177

Authors: Seigo Matsuno, Yasuo Uchida, Shozo Tokinaga

Abstract:

This paper proposes and empirically tests a model of the relationships between green supply chain management (GSCM) activities and corporate performance. From the literature review, we identified five constructs, namely, environmental commitment, supplier collaboration, supplier assessment, information sharing among suppliers, and business process improvement. These explanatory variables are used to form a structural model explaining the environmental and economic performance. The model was analyzed using the data from a survey of a sample of manufacturing firms in Japan. The results suggest that the degree of supplier collaboration has an influence on the environmental performance directly. While, the impact of supplier assessment on the environmental performance is mediated by the information sharing and/or business process improvement. And the environmental performance has a positive relationship on the economic performance. Academic and managerial implications of our findings are discussed.

Keywords: corporate performance, empirical study, green supply chain management, path modeling

Procedia PDF Downloads 392

Authors: S. V. Ncube, A. I. O. Jideani, E. T. Gwata

Abstract:

The plight of food insecurity in developing countries has led to renewed interest in underutilized legumes. Their nutritional versatility, desirable functionality, pharmaceutical value and inherent bioactive compounds have drawn the attention of researchers. This has provoked the development of value added products with the aim of commercially exploiting their full potential. However processing of these legumes leads to changes in nutritional composition as affected by processing variables like pH, temperature and pressure. There is therefore a need for process control and quality assurance during production of the value added products. However, conventional methods for microbiological and biochemical identification are labour intensive and time-consuming. Biosensors offer rapid and affordable methods to assure the quality of the products. They may be used to quantify nutrients and anti-nutrients in the products while manipulating and monitoring variables such as pH, temperature, pressure and oxygen that affect the quality of the final product. This review gives an overview of the types of biosensors used in the food industry, their advantages and disadvantages and their possible application in processing of legumes.

Keywords: legume processing, biosensors, quality control, nutritional versatility

Procedia PDF Downloads 492

Authors: Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Abstract:

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.

Keywords: fake news detection, natural language processing, machine learning, classification techniques.

Procedia PDF Downloads 167

Authors: Janusz Bobulski, Mariusz Kubanek

Abstract:

The main goal of the research is to develop a multimedia container structure containing three types of images: RGB, lidar and infrared, properly calibrated to each other. An additional goal is to develop program libraries for creating and saving this type of file and for restoring it. It will also be necessary to develop a method of data synchronization from lidar and RGB cameras as well as infrared. This type of file could be used in autonomous vehicles, which would certainly facilitate data processing by the intelligent autonomous vehicle management system. Autonomous cars are increasingly breaking into our consciousness. No one seems to have any doubts that self-driving cars are the future of motoring. Manufacturers promise that moving the first of them to showrooms is the prospect of the next few years. Many experts believe that creating a network of communicating autonomous cars will be able to completely eliminate accidents. However, to make this possible, it is necessary to develop effective methods of detection of objects around the moving vehicle. In bad weather conditions, this task is difficult on the basis of the RGB(red, green, blue) image. Therefore, in such situations, you should be supported by information from other sources, such as lidar or infrared cameras. The problem is the different data formats that individual types of devices return. In addition to these differences, there is a problem with the synchronization of these data and the formatting of this data. The goal of the project is to develop a file structure that could be containing a different type of data. This type of file is calling a multimedia container. A multimedia container is a container that contains many data streams, which allows you to store complete multimedia material in one file. Among the data streams located in such a container should be indicated streams of images, films, sounds, subtitles, as well as additional information, i.e., metadata. This type of file could be used in autonomous vehicles, which would certainly facilitate data processing by the intelligent autonomous vehicle management system. As shown by preliminary studies, the use of combining RGB and InfraRed images with Lidar data allows for easier data analysis. Thanks to this application, it will be possible to display the distance to the object in a color photo. Such information can be very useful for drivers and for systems in autonomous cars.

Keywords: an autonomous car, image processing, lidar, obstacle detection

Procedia PDF Downloads 225

Authors: Hooman Torabifard

Abstract:

In the last few years, with the progress of technology and computers and artificial intelligence entry into all kinds of scientific and industrial fields, the lifestyles of human life have changed and in general, the way of humans live on earth has many changes and development. Until now, some of the changes has occurred in the context of digital images and image processing and still continues. However, besides all the benefits, there have been disadvantages. One of these disadvantages is the multiplicity of images with high volume and data; the focus of this paper is on improving and developing a method for summarizing and enhancing the productivity of these images. The general method used for this purpose in this paper consists of a set of methods based on data obtained from image processing and using the PSO (Particle swarm optimization) algorithm. In the remainder of this paper, the method used is elaborated in detail.

Keywords: image summarization, particle swarm optimization, image threshold, image processing

Procedia PDF Downloads 133

Authors: İmren Öztürk Yılmaz, Abdullah Yasin Bilici, Yasin Atalay Candemir

Abstract:

The system consists of 4 main elements: motion system, image acquisition system, image processing software, and control interface. The parts coming out of the production line to enter the image processing system with the conveyor belt at the end of the line. The 3D scanning of the produced part is performed with the laser scanning system integrated into the system entry side. With the 3D scanning method, it is determined at what position and angle the parts enter the system, and according to the data obtained, parameters such as part origin and conveyor speed are calculated with the designed software, and the robot is informed about the position where it will take part. The robot, which receives the information, takes the produced part on the belt conveyor and shows it to high-resolution cameras for quality control. Measurement processes are carried out with a maximum error of 20 microns determined by the experiments.

Keywords: quality control, industry 4.0, image processing, automated fault detection, digital visual inspection

Procedia PDF Downloads 113

Authors: Eda Kocakaya, Sebahat Seker, Dogan Argun

Abstract:

The aim of this study is to determine the process of information technologies and the connections between concepts in accounting management services in Turkey. The objective of this study is to determine the adaptation and evaluation process of information technologies and the connections between concepts and differences in accounting management services in Turkey. The situation and determination of the IT applications of Accounting Management were studied. The applications of • Billing • Order Processing • Accounts Receivable/Payable Management • Contract Management • Bank Account Management Were discussed in this study. The IT applications were demonstrated and realized in actual accounting services. The sectoral representative's companies were selected, and the IT application was searched by bibliometric analysis.

Keywords: management, accounting, information technologies, adaptation

Procedia PDF Downloads 309

Authors: Fuyuan Ma, Yuhan Wang, Junhe Zhang, Ying Wang

Abstract:

Identifying the sources of information dissemination is a pivotal task in the study of collective behaviors in networks, enabling us to discern and intercept the critical pathways through which information propagates from its origins. This allows for the control of the information’s dissemination impact in its early stages. Numerous methods for source detection rely on pre-existing, underlying propagation models as prior knowledge. Current models that eschew prior knowledge attempt to harness label propagation algorithms to model the statistical characteristics of propagation states or employ Graph Neural Networks (GNNs) for deep reverse modeling of the diffusion process. These approaches are either deficient in modeling the propagation patterns of information or are constrained by the over-smoothing problem inherent in GNNs, which limits the stacking of sufficient model depth to excavate global propagation patterns. Consequently, we introduce the ODESI model. Initially, the model employs a label propagation algorithm to delineate the distribution density of infected states within a graph structure and extends the representation of infected states from integers to state vectors, which serve as the initial states of nodes. Subsequently, the model constructs a deep architecture based on GNNs-coupled Ordinary Differential Equations (ODEs) to model the global propagation patterns of continuous propagation processes. Addressing the challenges associated with solving ODEs on graphs, we approximate the analytical solutions to reduce computational costs. Finally, we conduct simulation experiments on two real-world social network datasets, and the results affirm the efficacy of our proposed ODESI model in source identification tasks.

Keywords: source identification, ordinary differential equations, label propagation, complex networks

Procedia PDF Downloads 20

Authors: M. Chumburidze, N. Salia, T. Namchevadze

Abstract:

This work deal with case processing problems in business. The task of strategic credit requirements management of cases portfolio is discussed. The information model of credit requirements in a binary tree diagram is considered. The algorithms to solve issues of prioritizing clusters of cases in business have been investigated. An implementation of priority queues to support case management operations has been presented. The corresponding pseudo codes for the programming application have been constructed. The tools applied in this development are based on binary tree ordering algorithms, optimization theory, and business management methods.

Keywords: credit network, case portfolio, binary tree, priority queue, stack

Procedia PDF Downloads 150

Authors: Ismail Bile Hassan, Masrah Azrifah Azmi Murad

Abstract:

This study discovers a novel framework of individual level technology adoption known as I-P (Individual- Privacy) towards Smart National Identity Card health information application. Many countries introduced smart national identity card (SNIC) with various applications such as health information application embedded inside it. However, the degree to which citizens accept and use some of the embedded applications in smart national identity remains unknown to many governments and application providers as well. Moreover, the previous studies revealed that the factors of trust, perceived risk, privacy concern and perceived credibility need to be incorporated into more comprehensive models such as extended Unified Theory of Acceptance and Use of Technology known as UTAUT2. UTAUT2 is a mainly widespread and leading theory existing in the information system literature up to now. This research identifies factors affecting the citizens’ behavioural intention to use health information application embedded in SNIC and extends better understanding on the relevant factors that the government and the application providers would need to consider in predicting citizens’ new technology acceptance in the future. We propose a conceptual framework by combining the UTAUT2 and Privacy Calculus Model constructs and also adding perceived credibility as a new variable. The proposed framework may provide assistance to any government planning, decision, and policy makers involving e-government projects. The empirical study may be conducted in the future to provide proof and empirically validate this I-P framework.

Keywords: unified theory of acceptance and use of technology (UTAUT) model, UTAUT2 model, smart national identity card (SNIC), health information application, privacy calculus model (PCM)

Procedia PDF Downloads 467

Authors: M. Z. Raqab, Debasis Kundu, M. A. Meraou

Abstract:

In this paper, we have analyzed maximum precipitation data during a particular period of time obtained from different stations in the Global Historical Climatological Network of the USA. One important point to mention is that some stations are shut down on certain days for some reason or the other. Hence, the maximum values are recorded by excluding those readings. It is assumed that the number of stations that operate follows zero-truncated Poisson random variables, and the daily precipitation follows a lognormal random variable. We call this model a compound truncated Poisson lognormal model. The proposed model has three unknown parameters, and it can take a variety of shapes. The maximum likelihood estimators can be obtained quite conveniently using Expectation-Maximization (EM) algorithm. Approximate maximum likelihood estimators are also derived. The associated confidence intervals also can be obtained from the observed Fisher information matrix. Simulation results have been performed to check the performance of the EM algorithm, and it is observed that the EM algorithm works quite well in this case. When we analyze the precipitation data set using the proposed model, it is observed that the proposed model provides a better fit than some of the existing models.

Keywords: compound Poisson lognormal distribution, EM algorithm, maximum likelihood estimation, approximate maximum likelihood estimation, Fisher information, skew distribution

Procedia PDF Downloads 108

Authors: Mohd Asrul Affendi Bi Abdullah, Nyi Nyi Naing

Abstract:

The purpose of this study was to identify comparable manner between negative binomial death rate (NBDR) and zero inflated negative binomial death rate (ZINBDR) with died patients with (HIV + T B+) and (HIV + T B−). HIV and TB is a serious world wide problem in the developing country. Data were analyzed with applying NBDR and ZINBDR to make comparison which a favorable model is better to used. The ZINBDR model is able to account for the disproportionately large number of zero within the data and is shown to be a consistently better fit than the NBDR model. Hence, as a results ZINBDR model is a superior fit to the data than the NBDR model and provides additional information regarding the died mechanisms HIV+TB. The ZINBDR model is shown to be a use tool for analysis death rate according age categorical.

Keywords: zero inflated negative binomial death rate, HIV and TB, AIC and BIC, death rate

Procedia PDF Downloads 432

Authors: Cau Tran, Tu Nguyen, Tien Pham

Abstract:

Model-based design (MBD) is a mathematical and visual technique for addressing design issues in the fields of communications, signal processing, and complicated control systems. It is utilized in several automotive, aerospace, industrial, and motion control applications. Virtual models are at the center of the software development process with model based design. A method used in the creation of embedded software is model-based design. In this study, the LAT motor is modeled in a simulation environment, and the LAT motor control is designed with a cascade structure, a speed and current control loop, and a controller that is used in the next part. A PID structure serves as this controller. Based on techniques and motor parameters that match the design goals, the PID controller is created for the model using traditional design principles. The MBD approach will be used to build embedded software for motor control. The paper will be divided into three distinct sections. The first section will introduce the design process and the benefits and drawbacks of the MBD technique. The design of control software for LAT motors will be the main topic of the next section. The experiment's results are the subject of the last section.

Keywords: model based design, limited angle torque, intellectual property core, hardware description language, controller area network, user datagram protocol

Procedia PDF Downloads 94

Authors: Zhen Cheng, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract:

Recently, explanatory natural language inference has attracted much attention for the interpretability of logic relationship prediction, which is also known as explanation generation for Natural Language Inference (NLI). Existing explanation generators based on discriminative Encoder-Decoder architecture have achieved noticeable results. However, we find that these discriminative generators usually generate explanations with correct evidence but incorrect logic semantic. It is due to that logic information is implicitly encoded in the premise-hypothesis pairs and difficult to model. Actually, logic information identically exists between premise-hypothesis pair and explanation. And it is easy to extract logic information that is explicitly contained in the target explanation. Hence we assume that there exists a latent space of logic information while generating explanations. Specifically, we propose a generative model called Variational Explanation Generator (VariationalEG) with a latent variable to model this space. Training with the guide of explicit logic information in target explanations, latent variable in VariationalEG could capture the implicit logic information in premise-hypothesis pairs effectively. Additionally, to tackle the problem of posterior collapse while training VariaztionalEG, we propose a simple yet effective approach called Logic Supervision on the latent variable to force it to encode logic information. Experiments on explanation generation benchmark—explanation-Stanford Natural Language Inference (e-SNLI) demonstrate that the proposed VariationalEG achieves significant improvement compared to previous studies and yields a state-of-the-art result. Furthermore, we perform the analysis of generated explanations to demonstrate the effect of the latent variable.

Keywords: natural language inference, explanation generation, variational auto-encoder, generative model

Procedia PDF Downloads 151

Authors: A. Porshnev, A. Zaporozhtchuk

Abstract:

Motivation regarded as a key factor of labor turnover, is especially important for volunteers working on an altruistic basis in NGO. Despite the motivational letter, candidate selection depends on the impression of the selection committee, which can be subject to human bias. We expect that structured and unstructured information provided in motivation letters could be used to improve candidate selection procedures. In our paper, we perform qualitative and quantitative analysis of 2280 motivation letters, create logistic regression, and build a decision tree to improve selection procedures. Our analysis showed that motivation factors are significant and enable human resources department to forecast labor turnover and provide extra information to demographic, professional and timing questions. In spite of the average level of accuracy the model demonstrates the selection procedures of company of under consideration can be improved. We also discuss interrelation between answers to open and closed motivation questions, recommend changes in motivational letter templates to ensure more relevant information about applicants and further steps to create more accurate model.

Keywords: decision trees, logistic regression, model, motivational letter, non-governmental organization, retention, turnover

Procedia PDF Downloads 177

Authors: M. Bruzza, M. Tupia, F. Rodríguez

Abstract:

As part of the regulatory compliance process and the streamlining of public administration, the Peruvian government has implemented the National E-Government Plan in all state institutions with the aim of providing citizens with solid services based on the use of Information and Communications Technologies (ICT). As part of the regulations, the requisites to be met by public institutions have been submitted. However, the lack of an implementation model was detected, one that can serve as a guide to such institutions in order to materialize the organizational and technological structures needed, which allow them to provide the required digital services. This paper develops an implementation model of electronic government (e-government) for Peru’s state institutions, in compliance with current regulations based on a COBIT 5.0 framework. Furthermore, the paper introduces phase 1 of this model: business and IT goals, the goals cascade and the future model of processes.

Keywords: e-government, u-government, COBIT, implementation model

Procedia PDF Downloads 324

Authors: Burak Oksuzoglu, Savas Yildirim, Ferhat Kutlu

Abstract:

Opinion mining (OM) is one of the natural language processing (NLP) problems to determine the polarity of opinions, mostly represented on a positive-neutral-negative axis. The data for OM is usually collected from various social media platforms. In an era where social media has considerable control over companies’ futures, it’s worth understanding social media and taking actions accordingly. OM comes to the fore here as the scale of the discussion about companies increases, and it becomes unfeasible to gauge opinion on individual levels. Thus, the companies opt to automize this process by applying machine learning (ML) approaches to their data. For the last two decades, OM or sentiment analysis (SA) has been mainly performed by applying ML classification algorithms such as support vector machines (SVM) and Naïve Bayes to a bag of n-gram representations of textual data. With the advent of deep learning and its apparent success in NLP, traditional methods have become obsolete. Transfer learning paradigm that has been commonly used in computer vision (CV) problems started to shape NLP approaches and language models (LM) lately. This gave a sudden rise to the usage of the pretrained language model (PTM), which contains language representations that are obtained by training it on the large datasets using self-supervised learning objectives. The PTMs are further fine-tuned by a specialized downstream task dataset to produce efficient models for various NLP tasks such as OM, NER (Named-Entity Recognition), Question Answering (QA), and so forth. In this study, the traditional and modern NLP approaches have been evaluated for OM by using a sizable corpus belonging to a large private company containing about 76,000 comments in Turkish: SVM with a bag of n-grams, and two chosen pre-trained models, multilingual universal sentence encoder (MUSE) and bidirectional encoder representations from transformers (BERT). The MUSE model is a multilingual model that supports 16 languages, including Turkish, and it is based on convolutional neural networks. The BERT is a monolingual model in our case and transformers-based neural networks. It uses a masked language model and next sentence prediction tasks that allow the bidirectional training of the transformers. During the training phase of the architecture, pre-processing operations such as morphological parsing, stemming, and spelling correction was not used since the experiments showed that their contribution to the model performance was found insignificant even though Turkish is a highly agglutinative and inflective language. The results show that usage of deep learning methods with pre-trained models and fine-tuning achieve about 11% improvement over SVM for OM. The BERT model achieved around 94% prediction accuracy while the MUSE model achieved around 88% and SVM did around 83%. The MUSE multilingual model shows better results than SVM, but it still performs worse than the monolingual BERT model.

Keywords: BERT, MUSE, opinion mining, pretrained language model, SVM, Turkish

Procedia PDF Downloads 146

Authors: Yadpiroon Onmek, Jean Triboulet, Sebastien Druon, Bruno Jouvencel

Abstract:

The objective of this paper is to develop the 3D underwater reconstruction of archaeology object, which is based on the fusion between a sonar system and stereo camera system. The underwater images are obtained from a calibrated camera system. The multiples image pairs are input, and we first solve the problem of image processing by applying the well-known filter, therefore to improve the quality of underwater images. The features of interest between image pairs are selected by well-known methods: a FAST detector and FLANN descriptor. Subsequently, the RANSAC method is applied to reject outlier points. The putative inliers are matched by triangulation to produce the local sparse point clouds in 3D space, using a pinhole camera model and Euclidean distance estimation. The SFM technique is used to carry out the global sparse point clouds. Finally, the ICP method is used to fusion the sonar information with the stereo model. The final 3D models have a précised by measurement comparing with the real object.

Keywords: 3D reconstruction, archaeology, fusion, stereo system, sonar system, underwater

Procedia PDF Downloads 299

Authors: Abhishek Saha, Serene Tay, Gerard Pijcke

Abstract:

The availability of high-resolution topography and rainfall information in urban areas has made it necessary to revise modeling approaches used for simulating flood risk assessments. Lidar derived elevation models that have 1m or lower resolutions are becoming widely accessible. The classical approaches of 1D-2D flow models where channel flow is simulated and coupled with a coarse resolution 2D overland flow models may not fully utilize the information provided by high-resolution data. In this context, a study was undertaken to compare three different modeling approaches to simulate flooding in an urban area. The first model used is the base model used is Sobek, which uses 1D model formulation together with hydrologic boundary conditions and couples with an overland flow model in 2D. The second model uses a full 2D model for the entire area with shallow water equations at the resolution of the digital elevation model (DEM). These models are compared against another shallow water equation solver in 2D, which uses a subgrid method for grid refinement. These models are simulated for different horizontal resolutions of DEM varying between 1m to 5m. The results show a significant difference in inundation extents and water levels for different DEMs. They are also sensitive to the different numerical models with the same physical parameters, such as friction. The study shows the importance of having reliable field observations of inundation extents and levels before a choice of model and data can be made for spatial flood risk assessments.

Keywords: flooding, DEM, shallow water equations, subgrid

Procedia PDF Downloads 141

Authors: Sameut Bouhaik Mostafa

Abstract:

Information Act is the Canadian law gives the right of access to information for the institution of government. It declares the availability of government information to the public, but that exceptions should be limited and the necessary right of access to be specific, and also states the need to constantly re-examine the decisions on the disclosure of any government information independently from the government. By 1982, it enacted a dozen countries, including France, Denmark, Finland, Sweden, the Netherlands and the United States (1966) newly legally to access the information. It entered access to Canadian information into force of the Act of 1983, under the government of Pierre Trudeau, allowing Canadians to recover information from government files, and the development of what can be accessed from the information, and the imposition of timetables to respond. It has been applied by the Information Commissioner in Canada.

Keywords: law, information, management, legal

Procedia PDF Downloads 415