Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 2697

World Academy of Science, Engineering and Technology

[Computer and Information Engineering]

Online ISSN : 1307-6892

2697 Application of Signature Verification Models for Document Recognition

Authors: Saule Rakhimova, Boris M. Fedorov, Liudmila P. Goncharenko, Sergey A. Sybachin, Natalia A. Mamedova, Ekaterina V. Makarenkova

Abstract:

In modern economic conditions, the question of the possibility of correct recognition of a signature on digital documents in order to verify the expression of will or confirm a certain operation is relevant. The additional complexity of processing lies in the dynamic variability of the signature for each individual, as well as in the way information is processed because the signature refers to biometric data. The article discusses the issues of using artificial intelligence models in order to improve the quality of signature confirmation in document recognition. The analysis of several possible options for using the model is carried out. The results of the study are given, in which it is possible to correctly determine the authenticity of the signature on small samples.

Keywords: Neural Networks, Artificial Intelligence, Signature recognition, biometric data

Procedia PDF Downloads 1
2696 Modified Model-Based Systems Engineering Driven Approach for Defining Complex Energy Systems

Authors: Hazim El-Mounayri, Akshay S. Dalvi

Abstract:

The internal and the external interactions between the complex structural and behavioral characteristics of the complex energy system result in unpredictable emergent behaviors. These emergent behaviors are not well understood, especially when modeled using the traditional top-down systems engineering approach. The intrinsic nature of current complex energy systems has called for an elegant solution that provides an integrated framework in Model-Based Systems Engineering (MBSE). This paper mainly presents a MBSE driven approach to define and handle the complexity that arises due to emergent behaviors. The approach provides guidelines for developing system architecture that leverages in predicting the complexity index of the system at different levels of abstraction. A framework that integrates indefinite and definite modeling aspects is developed to determine the complexity that arises during the development phase of the system. This framework provides a workflow for modeling complex systems using Systems Modeling Language (SysML) that captures the system’s requirements, behavior, structure, and analytical aspects at both problem definition and solution levels. A system architecture for a district cooling plant is presented, which demonstrates the ability to predict the complexity index. The result suggests that complex energy systems like district cooling plant can be defined in an elegant manner using the unconventional modified MBSE driven approach that helps in estimating development time and cost.

Keywords: Energy Systems, framework, district cooling plant, MBSE

Procedia PDF Downloads 1
2695 Preparation on Sentimental Analysis on Social Media Comments with Bidirectional Long Short-Term Memory Gated Recurrent Unit and Model Glove in Portuguese

Authors: Leonardo Alfredo Mendoza, Cristian Munoz, Marco Aurelio Pacheco, Manoela Kohler, Evelyn Batista, Rodrigo Moura

Abstract:

Natural Language Processing (NLP) techniques are increasingly more powerful to be able to interpret the feelings and reactions of a person to a product or service. Sentiment analysis has become a fundamental tool for this interpretation but has few applications in languages other than English. This paper presents a classification of sentiment analysis in Portuguese with a base of comments from social networks in Portuguese. A word embedding's representation was used with a 50-Dimension GloVe pre-trained model, generated through a corpus completely in Portuguese. To generate this classification, the bidirectional long short-term memory and bidirectional Gated Recurrent Unit (GRU) models are used, reaching results of 99.1%.

Keywords: sentiment analysis, gated recurrent unit, natural processing language, bidirectional long short-term memory, BI-LSTM, GRU

Procedia PDF Downloads 1
2694 Knowledge Integration from Concept to Practice: An Exploratory Study of Designing a Flood Resilient Urban Park in Viet Nam

Authors: Oswald Devisch, To Quyen Le, Tu Anh Trinh, Els Hannes

Abstract:

Urban centres worldwide are affected differently by flooding. In Vietnam this impact is increasingly negative caused by a process of rapid urbanisation. Traditional spatial planning and flood mitigation planning are not able to deal with this growing threat. This article therefore proposes to focus on increasing the participation of local communities in flood control and management. It explores, on the basis of a design studio exercise, how lay knowledge on flooding can be integrated within planning processes. The article presents a theoretical basis for the structured criterion for site selection for a flood resilient urban park from the perspective of science, then discloses the tacit and explicit knowledge of the flood-prone area and finally integrates this knowledge into the design strategies for flood resilient urban park design.

Keywords: Knowledge Integration, AHP, analytic hierarchy process, design resilience, flood resilient urban park

Procedia PDF Downloads 1
2693 A Particle Swarm Optimal Control Method for DC Motor by Considering Energy Consumption

Authors: Ying Zhang, Jing Zhang, Ming Li, Yingjie Zhang, Zuolei Hu

Abstract:

In the actual start-up process of DC motors, the DC drive system often faces a conflict between energy consumption and acceleration performance. To resolve the conflict, this paper proposes a comprehensive performance index that energy consumption index is added on the basis of classical control performance index in the DC motor starting process. Taking the comprehensive performance index as the cost function, particle swarm optimization algorithm is designed to optimize the comprehensive performance. Then it conducts simulations on the optimization of the comprehensive performance of the DC motor on condition that the weight coefficient of the energy consumption index should be properly designed. The simulation results show that as the weight of energy consumption increased, the energy efficiency was significantly improved at the expense of a slight sacrifice of fastness indicators with the comprehensive performance index method. The energy efficiency was increased from 63.18% to 68.48% and the response time reduced from 0.2875s to 0.1736s simultaneously compared with traditional proportion integrals differential controller in energy saving.

Keywords: Energy Consumption, comprehensive performance index, acceleration performance, particle swarm optimal control

Procedia PDF Downloads 1
2692 Deep Neural Network Approach for Navigation of Autonomous Vehicles

Authors: Mayank Raj, V. G. Narendra

Abstract:

Ever since the DARPA challenge on autonomous vehicles in 2005, there has been a lot of buzz about ‘Autonomous Vehicles’ amongst the major tech giants such as Google, Uber, and Tesla. Numerous approaches have been adopted to solve this problem, which can have a long-lasting impact on mankind. In this paper, we have used Deep Learning techniques and TensorFlow framework with the goal of building a neural network model to predict (speed, acceleration, steering angle, and brake) features needed for navigation of autonomous vehicles. The Deep Neural Network has been trained on images and sensor data obtained from the comma.ai dataset. A heatmap was used to check for correlation among the features, and finally, four important features were selected. This was a multivariate regression problem. The final model had five convolutional layers, followed by five dense layers. Finally, the calculated values were tested against the labeled data, where the mean squared error was used as a performance metric.

Keywords: Artificial Intelligence, Computer Vision, Deep learning, autonomous vehicles

Procedia PDF Downloads 1
2691 Spontaneous and Posed Smile Detection: Deep Learning, Traditional Machine Learning, and Human Performance

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: Computer Vision, Machine Learning, Human-Computer Interaction, Deep learning, Affective Computing, affect detection, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 1
2690 Training a Multi-Layered Perceptron Using Moth Swarm Algorithm for Predicting the Energy Demand of a Data Centre

Authors: Oluwafemi P. Ajayi, Reolyn H. Heymann

Abstract:

Multi-Layered Perceptron is a type of artificial neural network and obtaining its optimal weights and biases is critical to achieving good performance of the model. In this study, the Moth Swarm Algorithm has been proposed to train a Multi-Layered Perceptron neural network by finding its optimal weights and biases. The model developed has been used to predict the energy demand of a data centre. The performance of the proposed method has been evaluated based on Mean Squared Error, Root Mean Squared Error, Mean Absolute Error, Mean Absolute Percentage Error, and accuracy values obtained for the training and testing set. By comparing the results obtained from using the proposed model with other models like Moth Flame Optimization, Ant Lion Optimization, and Whale Optimization Algorithm, it was found that the Multi-Layered Perceptron trained using Moth Swarm Algorithm outperformed the other models.

Keywords: data centre, energy demand prediction, moth swarm algorithm, multi-layered perceptron optimization

Procedia PDF Downloads 1
2689 FASTNet: Full Attention Stacked Network for Nuclei Segmentation

Authors: Jie Chen, Yalu Cheng, Yongsheng Liang, Yonghong Tian, Luyang Chen

Abstract:

Image segmentation plays an important role in medical image analysis. Meanwhile, the accurate segmentation of nuclei is crucial for clinical diagnosis. Most deep networks are designed for the segmentation of natural images, which do not work well for nuclei segmentation because of the challenges of nuclei clustering and also scale variations. To this end, we propose a network, named Full Attention Stacked Network (FASNet). In particular, we firstly stack nine full attention dilation blocks to enlarge the receptive field of our network. We then bend our network into a U-type form to concatenate both the shallow and deep full attention dilation blocks. In this way, we can obtain more contour information of clustered nuclei and make use of shallow layers’ semantic information to supply deep layers. We conduct experiments on the MoNuSeg dataset and CPM-17 dataset. Experimental results show that our proposed FASNet outperforms the state-of-the-art methods, such as Seg-Net, DIST, Hover-Net, BES￾Net, CIA-Net. For example, We achieve 0.6269 and 0.6392 for Test A and Test B using AJI over MoNuSeg dataset respectively.

Keywords: Attention, Deep learning, nuclei instance segmentation, full-resolution network

Procedia PDF Downloads 1
2688 Optical Character Recognition/Intelligent Character Recognition Text Recognition Using ABBYY FineReader as an Example Text

Authors: Bagirzade A. R., Najafova A. Sh., Yessirkepova S. M., Albert E. S.

Abstract:

Text recognition is based on optical character recognition (OCR) and is an information technology term. It describes automatic recognition of text in images. OCR is necessary because optical input devices (scanners or digital cameras, and fax receivers) can only transmit bitmap graphics as a result. Dots of different colors (pixels) are arranged in rows and columns. Text Recognition describes the task of recognizing letters shown as such, to identify and assign them their assigned numeric value in accordance with the usual text encoding (ASCII, Unicode). Automatic text recognition and OCR are often used interchangeably in the German-speaking world. However, from a technical point of view, OCR refers only to the subarea of comparing patterns of individual parts of an image as candidates for recognition of individual characters. This OCR process is preceded by global structure recognition, in which text blocks are first separated from graphic elements, linear structures are recognized, and finally individual characters are separated. When deciding which symbol is present, the linguistic context can be taken into account using additional algorithms.

Keywords: ABBYY FineReader system, algorithm symbol recognition, OCR/ICR techniques, recognition technologies

Procedia PDF Downloads 1
2687 Improving Cyber Resilience in Mobile Field Hospitals: Towards an Assessment Model

Authors: Nasir B. Ahmed, Nicolas Daclin, Marc Olivaux, Gilles Dusserre

Abstract:

The mobile field hospital is critical in terms of managing emergencies in crisis. It is a sub-section of the main hospitals and the health sector, tasked with delivering responsive, immediate, and efficient medical services during a crisis. With the aim to prevent further crisis, the assessment of the cyber assets which follows different methods, to distinguish its strengths and weaknesses, in order to achieve cyber resiliency. The work focuses on assessments of cyber resilience in field hospitals with trends growing in both the field hospital and the health sector in general. This creates opportunities for the adverse attackers and the response improvement objectives for attaining cyber resilience, as the assessments allow users and stakeholders to know the level of risks with regards to its cyber assets. Thus, the purpose is to show the possible threat vectors which opens up opportunities, with contrast to current trends in the assessment of the mobile field hospitals’ cyber assets.

Keywords: Cyber Security, cyber resilience, assessment framework, mobile field hospital

Procedia PDF Downloads 1
2686 A Survey of Sentiment Analysis Based on Deep Learning

Authors: Pingping Lin, Xudong Luo

Abstract:

Sentiment analysis is a very active research topic. Every day, Facebook, Twitter, Weibo, and other social media, as well as significant e-commerce websites, generate a massive amount of comments, which can be used to analyse people’s opinions or emotions. The existing methods for sentiment analysis are based mainly on sentiment dictionaries, machine learning, and deep learning. The first two kinds of methods rely on heavily sentiment dictionaries or large amounts of labelled data. The third one overcomes these two problems. So, in this paper, we focus on the third one. Specifically, we survey various sentiment analysis methods based on convolutional neural network, recurrent neural network, long short-term memory, deep neural network, deep belief network, and memory network. We compare their futures, advantages, and disadvantages. Also, we point out the main problems of these methods, which may be worthy of careful studies in the future. Finally, we also examine the application of deep learning in multimodal sentiment analysis and aspect-level sentiment analysis.

Keywords: natural language processing, Deep learning, Document Analysis, multimodal sentiment analysis

Procedia PDF Downloads 1
2685 SISSLE in Consensus-Based Ripple: Some Improvements in Speed, Security, Last Mile Connectivity and Ease of Use

Authors: Mayank Mundhra, Chester Rebeiro

Abstract:

Cryptocurrencies are rapidly finding wide application in areas such as Real Time Gross Settlements and Payments Systems. Ripple is a cryptocurrency that has gained prominence with banks and payment providers. It solves the Byzantine General’s Problem with its Ripple Protocol Consensus Algorithm (RPCA), where each server maintains a list of servers, called Unique Node List (UNL) that represents the network for the server, and will not collectively defraud it. The server believes that the network has come to a consensus when members of the UNL come to a consensus on a transaction. In this paper we improve Ripple to achieve better speed, security, last mile connectivity and ease of use. We implement guidelines and automated systems for building and maintaining UNLs for resilience, robustness, improved security, and efficient information propagation. We enhance the system so as to ensure that each server receives information from across the whole network rather than just from the UNL members. We also introduce the paradigm of UNL overlap as a function of information propagation and the trust a server assigns to its own UNL. Our design not only reduces vulnerabilities such as eclipse attacks, but also makes it easier to identify malicious behaviour and entities attempting to fraudulently Double Spend or stall the system. We provide experimental evidence of the benefits of our approach over the current Ripple scheme. We observe ≥ 4.97x and 98.22x in speedup and success rate for information propagation respectively, and ≥ 3.16x and 51.70x in speedup and success rate in consensus.

Keywords: consensus, information propagation, Ripple, Kelips, unique node list

Procedia PDF Downloads 1
2684 Reed: An Approach Towards Quickly Bootstrapping Multilingual Acoustic Models

Authors: Bipasha Sen, Aditya Agarwal

Abstract:

Multilingual automatic speech recognition (ASR) system is a single entity capable of transcribing multiple languages sharing a common phone space. Performance of such a system is highly dependent on the compatibility of the languages. State of the art speech recognition systems are built using sequential architectures based on recurrent neural networks (RNN) limiting the computational parallelization in training. This poses a significant challenge in terms of time taken to bootstrap and validate the compatibility of multiple languages for building a robust multilingual system. Complex architectural choices based on self-attention networks are made to improve the parallelization thereby reducing the training time. In this work, we propose Reed, a simple system based on 1D convolutions which uses very short context to improve the training time. To improve the performance of our system, we use raw time-domain speech signals directly as input. This enables the convolutional layers to learn feature representations rather than relying on handcrafted features such as MFCC. We report improvement on training and inference times by atleast a factor of 4x and 7.4x respectively with comparable WERs against standard RNN based baseline systems on SpeechOcean's multilingual low resource dataset.

Keywords: Convolutional Neural Networks, language compatibility, low resource languages, multilingual automatic speech recognition

Procedia PDF Downloads 1
2683 The Application of a Hybrid Neural Network for Recognition of a Handwritten Kazakh Text

Authors: Sergey Sybachin, Almagul Assainova, Dariya Abykenova, Liudmila Goncharenko, Saule Rakhimova, Abay Aman

Abstract:

The recognition of a handwritten Kazakh text is a relevant objective today for the digitization of materials. The study presents a model of a hybrid neural network for handwriting recognition, which includes a convolutional neural network and a multi-layer perceptron. Each network includes 1024 input neurons and 42 output neurons. The model is implemented in the program, written in the Python programming language using the EMNIST database, NumPy, Keras, and Tensorflow modules. The neural network training of such specific letters of the Kazakh alphabet as ә, ғ, қ, ң, ө, ұ, ү, h, і was conducted. The neural network model and the program created on its basis can be used in electronic document management systems to digitize the Kazakh text.

Keywords: Neural Networks, Machine Learning, Image Recognition, handwriting recognition system, Kazakh font

Procedia PDF Downloads 1
2682 Towards Resilient Cloud Computing through Cyber Risk Assessment

Authors: Fatiha Djebbar, Hilalah Alturkistani, Alaa AlFaadhel, Nora AlJahani

Abstract:

Cloud computing is one of the most widely used technology which provides opportunities and services to government entities, large companies, and standard users. However, cybersecurity risk management studies of cloud computing and resiliency approaches are lacking. This paper proposes resilient cloud cybersecurity risk assessment and management tailored specifically, to Dropbox with two approaches:1) technical-based solution motivated by a cybersecurity risk assessment of cloud services, and 2)a target personnel-based solution guided by cybersecurity-related survey among employees to identify their knowledge that qualifies them withstand to any cyberattack. The proposed work attempts to identify cloud vulnerabilities, assess threats and detect high risk components, to finally propose appropriate safeguards such as failure predicting and removing, redundancy or load balancing techniques for quick recovery and return to pre-attack state if failure happens.

Keywords: Cyberattacks, cybersecurity risk management plan, resilient cloud computing, cybersecurity risk assessment

Procedia PDF Downloads 1
2681 Enhancing Cultural Heritage Data Retrieval by Mapping COURAGE to CIDOC Conceptual Reference Model

Authors: Ghazal Faraj, Andras Micsik

Abstract:

The CIDOC Conceptual Reference Model (CRM) is an extensible ontology that provides integrated access to heterogeneous and digital datasets. The CIDOC-CRM offers a “semantic glue” intended to promote accessibility to several diverse and dispersed sources of cultural heritage data. That is achieved by providing a formal structure for the implicit and explicit concepts and their relationships in the cultural heritage field. The COURAGE (“Cultural Opposition – Understanding the CultuRal HeritAGE of Dissent in the Former Socialist Countries”) project aimed to explore methods about socialist-era cultural resistance during 1950-1990 and planned to serve as a basis for further narratives and digital humanities (DH) research. This project highlights the diversity of flourished alternative cultural scenes in Eastern Europe before 1989. Moreover, the dataset of COURAGE is an online RDF-based registry that consists of historical people, organizations, collections, and featured items. For increasing the inter-links between different datasets and retrieving more relevant data from various data silos, a shared federated ontology for reconciled data is needed. As a first step towards these goals, a full understanding of the CIDOC CRM ontology (target ontology), as well as the COURAGE dataset, was required to start the work. Subsequently, the queries toward the ontology were determined, and a table of equivalent properties from COURAGE and CIDOC CRM was created. The structural diagrams that clarify the mapping process and construct queries are on progress to map person, organization, and collection entities to the ontology. Through mapping the COURAGE dataset to CIDOC-CRM ontology, the dataset will have a common ontological foundation with several other datasets. Therefore, the expected results are: 1) retrieving more detailed data about existing entities, 2) retrieving new entities’ data, 3) aligning COURAGE dataset to a standard vocabulary, 4) running distributed SPARQL queries over several CIDOC-CRM datasets and testing the potentials of distributed query answering using SPARQL. The next plan is to map CIDOC-CRM to other upper-level ontologies or large datasets (e.g., DBpedia, Wikidata), and address similar questions on a wide variety of knowledge bases.

Keywords: Ontology alignment, CIDOC CRM, cultural heritage data, COURAGE dataset

Procedia PDF Downloads 1
2680 Personal Information Classification Based on Deep Learning in Automatic Form Filling System

Authors: Xudong Luo, Shunzuo Wu, Yuanxiu Liao

Abstract:

Recently, the rapid development of deep learning makes artificial intelligence (AI) penetrate into many fields, replacing manual work there. In particular, AI systems also become a research focus in the field of automatic office. To meet real needs in automatic officiating, in this paper we develop an automatic form filling system. Specifically, it uses two classical neural network models and several word embedding models to classify various relevant information elicited from the Internet. When training the neural network models, we use less noisy and balanced data for training. We conduct a series of experiments to test my systems and the results show that our system can achieve better classification results.

Keywords: Deep learning, NLP, text classification, artificial intelligence and office

Procedia PDF Downloads 1
2679 Analysis and Identification of Different Factors Affecting Students' Performance Using a Correlation-Based Network Approach

Authors: Jeff Chak Fu Wong, Tony Chun Yin Yip

Abstract:

The transition from secondary school to university seems exciting for many first-year students but can be more challenging than expected. Enabling instructors to know students' learning habits and styles enhances their understanding of the students' learning backgrounds, allows teachers to provide better support for their students, and has therefore high potential to improve teaching quality and learning, especially in any mathematics-related courses. The aim of this research is to collect students' data using online surveys, to analyze students' factors using learning analytics and educational data mining and to discover the characteristics of the students at risk of falling behind in their studies based on students' previous academic backgrounds and collected data. In this paper, we use correlation-based distance methods and mutual information for measuring student factor relationships. We then develop a factor network using the Minimum Spanning Tree method and consider further study for analyzing the topological properties of these networks using social network analysis tools. Under the framework of mutual information, two graph-based feature filtering methods, i.e., unsupervised and supervised infinite feature selection algorithms, are used to analyze the results for students' data to rank and select the appropriate subsets of features and yield effective results in identifying the factors affecting students at risk of failing. This discovered knowledge may help students as well as instructors enhance educational quality by finding out possible under-performers at the beginning of the first semester and applying more special attention to them in order to help in their learning process and improve their learning outcomes.

Keywords: Social Network Analysis, Feature selection, Students' academic performance, correlation-based distance method, graph-based feature filtering method

Procedia PDF Downloads 1
2678 Analysis and Detection of Facial Expressions in Autism Spectrum Disorder People Using Machine Learning

Authors: Muhammad Maisam Abbas, Salman Tariq, Usama Riaz, Muhammad Tanveer, Humaira Abdul Ghafoor

Abstract:

Autism Spectrum Disorder (ASD) refers to a developmental disorder that impairs an individual's communication and interaction ability. Individuals feel difficult to read facial expressions while communicating or interacting. Facial Expression Recognition (FER) is a unique method of classifying basic human expressions, i.e., happiness, fear, surprise, sadness, disgust, neutral, and anger through static and dynamic sources. This paper conducts a comprehensive comparison and proposed optimal method for a continued research project—a system that can assist people who have Autism Spectrum Disorder (ASD) in recognizing facial expressions. Comparison has been conducted on three supervised learning algorithms EigenFace, FisherFace, and LBPH. The JAFFE, CK+, and TFEID (I&II) datasets have been used to train and test the algorithms. The results were then evaluated based on variance, standard deviation, and accuracy. The experiments showed that FisherFace has the highest accuracy for all datasets and is considered the best algorithm to be implemented in our system.

Keywords: ASD, Autism spectrum disorder, Local Binary Pattern Histogram, facial expression recognition, Eigenface, Fisherface, LBPH

Procedia PDF Downloads 1
2677 Programming with Grammars

Authors: Peter M. Maurer Maurer

Abstract:

DGL is a context free grammar-based tool for generating random data. Many types of simulator input data require some computation to be placed in the proper format. For example, it might be necessary to generate ordered triples in which the third element is the sum of the first two elements, or it might be necessary to generate random numbers in some sorted order. Although DGL is universal in computational power, generating these types of data is extremely difficult. To overcome this problem, we have enhanced DGL to include features that permit direct computation within the structure of a context free grammar. The features have been implemented as special types of productions, preserving the context free flavor of DGL specifications.

Keywords: DGL, Enhanced Context Free Grammars, Programming Constructs, Random Data Generation

Procedia PDF Downloads 1
2676 Clothes Identification Using Inception ResNet V2 and MobileNet V2

Authors: Ashutosh Chauhan, Badal Shrestha, Subodh Chandra Shakya, Saugat Adhikari, Suni Thapa

Abstract:

To tackle our problem of clothes identification, we used different architectures of Convolutional Neural Networks. Among different architectures, the outcome from Inception ResNet V2 and MobileNet V2 seemed promising. On comparison of the metrices, we observed that the Inception ResNet V2 slightly outperforms MobileNet V2 for this purpose. So this paper of ours proposes the cloth identifier using Inception ResNet V2 and also contains the comparison between the outcome of ResNet V2 and MobileNet V2. The document here contains the results and findings of the research that we performed on the DeepFashion Dataset. To improve the dataset, we used different image preprocessing techniques like image shearing, image rotation, and denoising. The whole experiment was conducted with the intention of testing the efficiency of convolutional neural networks on cloth identification so that we could develop a reliable system that is good enough in identifying the clothes worn by the users. The whole system can be integrated with some kind of recommendation system.

Keywords: Deep learning, Data Preprocessing, confusion matrix, data augmentation, Convolutional neural net, inception ResNet

Procedia PDF Downloads 1
2675 Resume Ranking Using Custom Word2vec and Rule-Based Natural Language Processing Techniques

Authors: Rajendra Sapkota, Aakash Tamang, Shushant Pudasaini, Sujan Adhikari, Sajjan Adhikari, Subodh Chandra Shakya

Abstract:

Lots of efforts have been made in order to measure the semantic similarity between the text corpora in the documents. Techniques have been evolved to measure the similarity of two documents. One such state-of-art technique in the field of Natural Language Processing (NLP) is word to vector models, which converts the words into their word-embedding and measures the similarity between the vectors. We found this to be quite useful for the task of resume ranking. So, this research paper is the implementation of the word2vec model along with other Natural Language Processing techniques in order to rank the resumes for the particular job description so as to automate the process of hiring. The research paper proposes the system and the findings that were made during the process of building the system.

Keywords: natural language processing, information extraction, word2vec, word embedding, chunking, Document similarity

Procedia PDF Downloads 1
2674 Post-Quantum Resistant Edge Authentication in Large Scale Industrial Internet of Things Environments Using Aggregated Local Knowledge and Consistent Triangulation

Authors: C. P. Autry, A. W. Roscoe, Mykhailo Magal

Abstract:

We discuss the theoretical model underlying 2BPA (two-band peer authentication), a practical alternative to conventional authentication of entities and data in IoT. In essence, this involves assembling a virtual map of authentication assets in the network, typically leading to many paths of confirmation between any pair of entities. This map is continuously updated, confirmed, and evaluated. The value of authentication along multiple disjoint paths becomes very clear, and we require analogues of triangulation to extend authentication along extended paths and deliver it along all possible paths. We discover that if an attacker wants to make an honest node falsely believe she has authenticated another, then the length of the authentication paths is of little importance. This is because optimal attack strategies correspond to minimal cuts in the authentication graph and do not contain multiple edges on the same path. The authentication provided by disjoint paths normally is additive (in entropy).

Keywords: Authentication, Edge Computing, Industrial Iot, post-quantum resistance

Procedia PDF Downloads 1
2673 Antenna for Energy Harvesting in Wireless Connected Objects

Authors: Chokri Baccouch, Hedi Sakli, Nizar Sakli, Chayma Bahar

Abstract:

If connected objects multiply, they are becoming a challenge, in more than one way. In particular by their consumption and their supply of electricity. A large part of the new generations of connected objects will only be able to develop if it is possible to make them entirely autonomous in terms of energy. Some manufacturers are therefore developing products capable of recovering energy from their environment. Vital solutions in certain contexts, such as the medical industry. Energy recovery from the environment is a reliable solution to solve the problem of powering wireless connected objects. This paper presents and study a optically transparent solar patch antenna in frequency band of 2.4 GHz for connected objects in the future standard 5G for energy harvesting and RF transmission.

Keywords: Wireless Communications, Antenna, IoT, Solar Cell

Procedia PDF Downloads 1
2672 Connected Objects with Optical Rectenna for Wireless Information Systems

Authors: Chayma Bahar

Abstract:

The harvesting and transport of optical and radiofrequency signals is a topical subject with multiple challenges. In this paper, we present a Optical RECTENNA system. We propose here a hybrid system solar cell antenna for 5G mobile communications networks.Thus, we propose rectifying circuit . A parametric study is done to follow the influence of load resistance and input power on Optical RECTENNA system performance. Thus, we propose a solar cell antenna structure in the frequency band of future 5G standard in 2.45 GHz bands.

Keywords: Antenna, IoT, Solar Cell, optical rectenna

Procedia PDF Downloads 1
2671 Comparing Image Processing and AI Techniques for Disease Detection in Plants

Authors: Luiz Daniel Garay Trindade, Antonio De Freitas Valle Neto, Fabio Paulo Basso, Elder De Macedo Rodrigues, Maicon Bernardino, Daniel Welfer, Daniel Muller

Abstract:

Agriculture plays an important role in society since it is one of the main sources of food in the world. To help the production and yield of crops, precision agriculture makes use of technologies aiming at improving productivity and quality of agricultural commodities. One of the problems hampering quality of agricultural production is the disease affecting crops. Failure in detecting diseases in a short period of time can result in small or big damages to production, causing financial losses to farmers. In order to provide a map of the contributions destined to the early detection of plant diseases and a comparison of the accuracy of the selected studies, a systematic literature review of the literature was performed, showing techniques for digital image processing and neural networks. We found 35 interesting tool support alternatives to detect disease in 19 plants. Our comparison of these studies resulted in an overall average accuracy of 87.45%, with two studies very closer to obtain 100%.

Keywords: Image Processing, Pattern Recognition, Precision Agriculture, Deep learning, Smart Farming, Agricultural Automation

Procedia PDF Downloads 1
2670 Hybrid Fuzzy Weighted K-Nearest Neighbor to Predict Hospital Readmission for Diabetic Patients

Authors: Soha A. Bahanshal, Byung G. Kim

Abstract:

Identification of patients at high risk for hospital readmission is of crucial importance for quality health care and cost reduction. Predicting hospital readmissions among diabetic patients has been of great interest to many researchers and health decision makers. We build a prediction model to predict hospital readmission for diabetic patients within 30 days of discharge. The core of the prediction model is a modified k Nearest Neighbor called Hybrid Fuzzy Weighted k Nearest Neighbor algorithm. The prediction is performed on a patient dataset which consists of more than 70,000 patients with 50 attributes. We applied data preprocessing using different techniques in order to handle data imbalance and to fuzzify the data to suit the prediction algorithm. The model so far achieved classification accuracy of 80% compared to other models that only use k Nearest Neighbor.

Keywords: Machine Learning, classification, prediction, hybrid fuzzy weighted k-nearest neighbor, diabetic hospital readmission

Procedia PDF Downloads 1
2669 On Dialogue Systems Based on Deep Learning

Authors: Xudong Luo, Yifan Fan

Abstract:

Nowadays, dialogue systems increasingly become the way for humans to access many computer systems. So, humans can interact with computers in natural language. A dialogue system consists of three parts: understanding what humans say in natural language, managing dialogue, and generating responses in natural language. In this paper, we survey deep learning based methods for dialogue management, response generation and dialogue evaluation. Specifically, these methods are based on neural network, long shortterm memory network, deep reinforcement learning, pre-training and generative adversarial network. We compare these methods and point out the further research directions.

Keywords: Evaluation, Deep learning, Dialogue Management, response generation

Procedia PDF Downloads 1
2668 Project Management Process Implementation in Data Centers

Authors: Fariborz Haghighat, Fuzhan Nasiri, Mostafa Fadaeefath Abadi

Abstract:

Data Centers (DCs) are one of the most critical infrastructures because of their complexity, having important components and providing essential online services to the world. Many Information Technology (IT) companies, governmental departments, and agencies around the world must have reliable DCs to protect and maintain significant amounts of data for their users and customers. Recently, due to the worldwide COVID-19 outbreak, the demand for online services has been extremely increased and thus, the crisis has brought high attention to DCs and their systems more than ever. Project Management, which manages every process in a system is also highly involved in a DC design project and should be addressed and considered. DC Project Management's main elements are planning, scheduling and providing safety and security for the DC infrastructure. It is also responsible for managing various operations and assets such as telecommunications networks, data storage, and processing systems and available equipment, which are servers, network switches, etc. In this paper, the application of Project Management in DCs has been evaluated considering important quality standards. The main parameters and facts based on recent research works and advancements have been presented and discussed to identify issues, problems, and challenges in terms of applying Project Management standards in DCs. This study will also allow better clarification and understanding of DC Project Management metrics to assist DC project managers and practitioners in performance monitoring.

Keywords: Project Management, Infrastructure Management, information technology (IT), data center (DC)

Procedia PDF Downloads 1