Search results for: automatic censoring

Authors: Rodrigo T. Sepulveda-Hirose, Ana B. Carrera-Aguilar, Francisco Andree Ramirez-Casas, Alondra Orozco-Gomez, Miguel Angel Sanchez-Caro, Carlos Herrera-Ventosa

Abstract:

High concentrations of particulate matter in the atmosphere pose a threat to human health, especially over areas with high concentrations of population; however, field air pollution monitoring is expensive and time-consuming. In order to achieve reduced costs and global coverage of the whole urban area, remote sensing can be used. This study evaluates PM2.5 concentrations, over the Mexico City´s metropolitan area, are estimated using atmospheric reflectance from LANDSAT 8, satellite imagery and historical PM2.5 measurements of the Automatic Environmental Monitoring Network of Mexico City (RAMA). Through the processing of the available satellite images, a preliminary model was generated to evaluate the optimal bands for the generation of the final model for Mexico City. Work on the final model continues with the results of the preliminary model. It was found that infrared bands have helped to model in other cities, but the effectiveness that these bands could provide for the geographic and climatic conditions of Mexico City is still being evaluated.

Keywords: air pollution modeling, Landsat 8, PM2.5, remote sensing

Procedia PDF Downloads 160

Authors: Xulu Yao, Moi Hoon Yap, Yanlong Zhang

Abstract:

As a branch of artificial neural network, deep learning is widely used in the field of image recognition, but the lack of its dataset leads to imperfect model learning. By analysing the data scale requirements of deep learning and aiming at the application in GUI generation, it is found that the collection of GUI dataset is a time-consuming and labor-consuming project, which is difficult to meet the needs of current deep learning network. To solve this problem, this paper proposes a semi-supervised deep learning model that relies on the original small-scale datasets to produce a large number of reliable data sets. By combining the cyclic neural network with the generated countermeasure network, the cyclic neural network can learn the sequence relationship and characteristics of data, make the generated countermeasure network generate reasonable data, and then expand the Rico dataset. Relying on the network structure, the characteristics of collected data can be well analysed, and a large number of reasonable data can be generated according to these characteristics. After data processing, a reliable dataset for model training can be formed, which alleviates the problem of dataset shortage in deep learning.

Keywords: GUI, deep learning, GAN, data augmentation

Procedia PDF Downloads 154

Authors: Daliyah S. Aljutaili, Redna A. Almutlaq, Suha A. Alharbi, Dina M. Ibrahim

Abstract:

All currencies around the world look very different from each other. For instance, the size, color, and pattern of the paper are different. With the development of modern banking services, automatic methods for paper currency recognition become important in many applications like vending machines. One of the currency recognition architecture’s phases is Feature detection and description. There are many algorithms that are used for this phase, but they still have some disadvantages. This paper proposes a feature detection algorithm, which merges the advantages given in the current SIFT and SURF algorithms, which we call, Speeded up Robust Scale-Invariant Feature Transform (SR-SIFT) algorithm. Our proposed SR-SIFT algorithm overcomes the problems of both the SIFT and SURF algorithms. The proposed algorithm aims to speed up the SIFT feature detection algorithm and keep it robust. Simulation results demonstrate that the proposed SR-SIFT algorithm decreases the average response time, especially in small and minimum number of best key points, increases the distribution of the number of best key points on the surface of the currency. Furthermore, the proposed algorithm increases the accuracy of the true best point distribution inside the currency edge than the other two algorithms.

Keywords: currency recognition, feature detection and description, SIFT algorithm, SURF algorithm, speeded up and robust features

Procedia PDF Downloads 215

Authors: Fu-Chien Hung, Chi‐Wen Liang

Abstract:

Background: People who suffer from chronic fatigue syndrome (CFS) frequently complain about continuous tiredness, weakness or lack of strength, but without apparent organic etiology. The prevalence rate of the CFS is nearly from 3% to 20%, yet more than 80% go undiagnosed or misdiagnosed as depression. The biopsychosocial model has suggested the associations among the CFS, depressive syndrome, and stress. This study aimed to investigate the difference between individuals with the CFS and with the depressive syndrome on psychophysiological responses under stress. Method: There were 23 participants in the CFS group, 14 participants in the depression group, and 23 participants in the healthy control group. All of the participants first completed the measures of demographic data, CFS-related symptoms, daily life functioning, and depressive symptoms. The participants were then asked to perform a stressful cognitive task. The participants’ psychophysiological responses including the HR, BVP and SC were measured during the task. These indexes were used to assess the reactivity and recovery rates of the automatic nervous system. Results: The stress reactivity of the CFS and depression groups was not different from that of the healthy control group. However, the stress recovery rate of the CFS group was worse than that of the healthy control group. Conclusion: The results from this study suggest that the CFS is a syndrome which can be independent from the depressive syndrome, although the depressive syndrome may include fatigue syndrome.

Keywords: chronic fatigue syndrome, depression, stress response, misdiagnosis

Procedia PDF Downloads 431

Authors: Aileen F. Wang

Abstract:

Mammography has been one of the most reliable methods for early detection and diagnosis of breast cancer. However, mammography misses about 17% and up to 30% of breast cancers due to the subtle and unstable appearances of breast cancer in their early stages. Recent computer-aided diagnosis (CADx) technology using Zernike moments has improved detection accuracy. However, it has several drawbacks: it uses manual segmentation, Zernike moments are not robust, and it still has a relatively high false negative rate (FNR)–17.6%. This project will focus on the development of a novel breast cancer detection algorithm to automatically segment the breast mass and further reduce FNR. The algorithm consists of automatic segmentation of a single breast mass using Point Region Growing Segmentation, reconstruction of the segmented breast mass using Pseudo-Zernike moments, and classification of the breast mass using the root mean square (RMS). A comparative study among the various algorithms on the segmentation and reconstruction of breast masses was performed on randomly selected mammographic images. The results demonstrated that the newly developed algorithm is the best in terms of accuracy and cost effectiveness. More importantly, the new classifier RMS has the lowest FNR–6%.

Keywords: computer aided diagnosis, mammography, point region growing segmentation, pseudo-zernike moments, root mean square

Procedia PDF Downloads 427

Authors: Chayanika Hazarika Bordoloi

Abstract:

This paper is an attempt to work on a highly inflectional language called Assamese. This is also one of the national languages of India and very little has been achieved in terms of computational research. Building a language processing tool for a natural language is not very smooth as the standard and language representation change at various levels. This paper presents inflectional suffixes of Assamese verbs and how the statistical tools, along with linguistic features, can improve the tagging accuracy. Conditional random fields (CRF tool) was used to automatically tag and train the text data; however, accuracy was improved after linguistic featured were fed into the training data. Assamese is a highly inflectional language; hence, it is challenging to standardizing its morphology. Inflectional suffixes are used as a feature of the text data. In order to analyze the inflections of Assamese word forms, a list of suffixes is prepared. This list comprises suffixes, comprising of all possible suffixes that various categories can take is prepared. Assamese words can be classified into inflected classes (noun, pronoun, adjective and verb) and un-inflected classes (adverb and particle). The corpus used for this morphological analysis has huge tokens. The corpus is a mixed corpus and it has given satisfactory accuracy. The accuracy rate of the tagger has gradually improved with the modified training data.

Keywords: CRF, morphology, tagging, tagset

Procedia PDF Downloads 174

Authors: P. Abhishesh, B. S. Ryuh, Y. S. Oh, H. J. Moon, R. Akanksha

Abstract:

This paper discusses about the conceptual design and development of the control system software using Programmable logic controller (PLC) for autonomous driving and agricultural operations of Multipurpose Agricultural Robot Platform (MARP). Based on given initial conditions by field analysis and desired agricultural operations, the structural design development of MARP is done using modelling and analysis tool. PLC, being robust and easy to use, has been used to design the autonomous control system of robot platform for desired parameters. The robot is capable of performing autonomous driving and three automatic agricultural operations, viz. hilling, mulching, and sowing of seeds in the respective order. The input received from various sensors on the field is later transmitted to the controller via ZigBee network to make the changes in the control program to get desired field output. The research is conducted to provide assistance to farmers by reducing labor hours for agricultural activities by implementing automation. This study will provide an alternative to the existing systems with machineries attached behind tractors and rigorous manual operations on agricultural field at effective cost.

Keywords: agricultural operations, autonomous driving, MARP, PLC

Procedia PDF Downloads 337

Authors: L. Krpalkova, N. O' Mahony, A. Carvalho, S. Campbell, S. Harapanahalli, J. Walsh

Abstract:

The objective of this study was to determine the effects of environmental stressors on the performance of lactating dairy cows and discuss some future trends. There exists a relationship between the meteorological data and milk yield prediction accuracy in pasture-based dairy systems. New precision technologies are available and are being developed to improve the sustainability of the dairy industry. Some of these technologies focus on welfare of individual animals on dairy farms. These technologies allow the automatic identification of animal behaviour and health events, greatly increasing overall herd health and yield while reducing animal health inspection demands and long-term animal healthcare costs. The data set consisted of records from 489 dairy cows at two dairy farms and temperature measured from the nearest meteorological weather station in 2018. The effects of temperature on milk production and behaviour of animals were analyzed. The statistical results indicate different effects of temperature on milk yield and behaviour. The “comfort zone” for animals is in the range 10 °C to 20 °C. Dairy cows out of this zone had to decrease or increase their metabolic heat production, and it affected their milk production and behaviour.

Keywords: behavior, milk yield, temperature, precision technologies

Procedia PDF Downloads 84

Authors: M. Mohemmed Sha Mohamed Kunju, Abdalla A. Al-Ameen Abdurahman, T. Manesh Thankappan, A. Mohamed Mustaq Ahmed Hameed

Abstract:

Web service composition is an effective approach to complete the web based tasks with desired quality. A single web service with limited functionality is inadequate to execute a specific task with series of action. So, it is very much required to combine multiple web services with different functionalities to reach the target. Also, it will become more and more challenging, when these services are from different providers with identical functionalities and varying QoS, so while composing the web services, the overall QoS is considered to be the major factor. Also, it is not true that the expected QoS is always attained when the task is completed. A single web service in the composed chain may affect the overall performance of the task. So care should be taken in different aspects such as functionality of the service, while composition. Dynamic and automatic service composition is one of the main option available. But to achieve the actual functionality of the task, quality of the individual web services are also important. Normally the QoS of the individual service can be evaluated by using the non-functional parameters such as response time, throughput, reliability, availability, etc. At the same time, the QoS is not needed to be at the same level for all the composed services. So this paper proposes a framework that allows composing the services in terms of QoS by setting the appropriate weight to the non-functional parameters of each individual web service involved in the task. Experimental results show that the importance given to the non-functional parameter while composition will definitely improve the performance of the web services.

Keywords: composition, non-functional parameters, quality of service, web service

Procedia PDF Downloads 306

Authors: Mortez Alijani, Anas Osman

Abstract:

Recently, the popularity of Unmanned aerial vehicles (UAVs) has skyrocketed amidst the unprecedented events and the global pandemic, as they play a key role in both the security and health sectors, through surveillance, taking test samples, transportation of crucial goods and spreading awareness among civilians. However, the process of designing and producing such aerial robots is suppressed by the internal and external constraints that pose serious challenges. Landing is one of the key operations during flight, especially, the autonomous landing of UAVs on a moving platform is a scientifically complex engineering problem. Typically having a successful automatic landing of UAV on a moving platform requires accurate localization of landing, fast trajectory planning, and robust control planning. To achieve these goals, the information about the autonomous landing process such as the intersection point, the position of platform/UAV and inclination angle are more necessary. In this study, the mathematical approach to this problem in the X-Y axis based on the inclination angle and position of UAV in the landing process have been presented. The experimental results depict the accurate position of the UAV, intersection between UAV and moving platform and inclination angle in the landing process, allowing prediction of the intersection point.

Keywords: autonomous landing, inclination angle, unmanned aerial vehicles, moving platform, X-Y axis, intersection point

Procedia PDF Downloads 137

Authors: Sidi Ahmed Maouloud, Cheikh Ba

Abstract:

Much of West Africa’s cultural heritage is written in the Al-Soudani Arabic script, which was widely used in West Africa before the time of European colonization. This Al-Soudani Arabic script is an African version of the Maghrebi script, in particular, the Al-Mebssout script. However, the local African qualities were incorporated into the Al-Soudani script in a way that gave it a unique African diversity and character. Despite the existence of several Arabic datasets in Oriental script, allowing for the analysis, layout, and recognition of texts written in these calligraphies, many Arabic scripts and written traditions remain understudied. In this paper, we present a dataset of words from Al-Soudani calligraphy scripts. This dataset consists of 100 images selected from three different manuscripts written in Al-Soudani Arabic script by different copyists. The primary source for this database was the libraries of Boston University and Cambridge University. This dataset highlights the unique characteristics of the Al-Soudani Arabic script as well as the new challenges it presents in terms of automatic word recognition of Arabic manuscripts. An HTR system based on a hybrid ANN (CRNN-CTC) is also proposed to test this dataset. SAMRA is a dataset of annotated Arabic manuscript words in the Al-Soudani script that can help researchers automatically recognize and analyze manuscript words written in this script.

Keywords: dataset, CRNN-CTC, handwritten words recognition, Al-Soudani Arabic script, HTR, manuscripts

Procedia PDF Downloads 83

Authors: Wassana Naiyapo, Atichat Sangtong

Abstract:

The processes in software development by Object Oriented methodology have many stages those take time and high cost. The inconceivable error in system analysis process will affect to the design and the implementation process. The unexpected output causes the reason why we need to revise the previous process. The more rollback of each process takes more expense and delayed time. Therefore, the good test process from the early phase, the implemented software is efficient, reliable and also meet the user’s requirement. Unified Modelling Language (UML) is the tool which uses symbols to describe the work process in Object Oriented Analysis (OOA). This paper presents the approach for automatically generated UML use case diagram and test cases. UML use case diagram is generated from the event table and test cases are generated from use case specifications and Graphic User Interfaces (GUI). Test cases are derived from the Classification Tree Method (CTM) that classify data to a node present in the hierarchy structure. Moreover, this paper refers to the program that generates use case diagram and test cases. As the result, it can reduce work time and increase efficiency work.

Keywords: classification tree method, test case, UML use case diagram, use case specification

Procedia PDF Downloads 135

Authors: Aleksander Nawrat, Karol Jędrasiak, Artur Ryt, Dawid Sobel

Abstract:

The goal of the article is to present a novel Multimedia Firearms Training System. The system was developed in order to compensate for major problems of existing shooting training systems. The designed and implemented solution can be characterized by five major advantages: algorithm for automatic geometric calibration, algorithm of photometric recalibration, firearms hit point detection using thermal imaging camera, IR laser spot tracking algorithm for after action review analysis, and implementation of ballistics equations. The combination of the abovementioned advantages in a single multimedia firearms training system creates a comprehensive solution for detecting and tracking of the target point usable for shooting training systems and improving intervention tactics of uniformed services. The introduced algorithms of geometric and photometric recalibration allow the use of economically viable commercially available projectors for systems that require long and intensive use without most of the negative impacts on color mapping of existing multi-projector multimedia shooting range systems. The article presents the results of the developed algorithms and their application in real training systems.

Keywords: firearms shot detection, geometric recalibration, photometric recalibration, IR tracking algorithm, thermography, ballistics

Procedia PDF Downloads 197

Authors: Deawan Rakin Ahamed Remal, Sinthia Chowdhury, Sharun Akter Khushbu, Sheak Rashed Haider Noori

Abstract:

Native Speech to text synthesis has its own leverage for the purpose of mankind. The extensive nature of art to speaking different accents is common but the purpose of communication between two different accent types of people is quite difficult. This problem will be motivated by the extraction of the wrong perception of language meaning. Thus, many existing automatic speech recognition has been placed to detect text. Overall study of this paper mentions a review of NSTTR (Native Speech Text to Text Recognition) synthesis compared with Text to Text recognition. Review has exposed many text to text recognition systems that are at a very early stage to comply with the system by native speech recognition. Many discussions started about the progression of chatbots, linguistic theory another is rule based approach. In the Recent years Deep learning is an overwhelming chapter for text to text learning to detect language nature. To the best of our knowledge, In the sub continent a huge number of people speak in Bangla language but they have different accents in different regions therefore study has been elaborate contradictory discussion achievement of existing works and findings of future needs in Bangla language acoustic accent.

Keywords: TTR, NSTTR, text to text recognition, deep learning, natural language processing

Procedia PDF Downloads 105

Authors: Belgherbi Aicha, Hadjidj Ismahen, Bessaid Abdelhafid

Abstract:

Accurate Liver, spleen and kidneys segmentation in abdominal CT images is one of the most important steps for computer aided abdominal organs pathology diagnosis. In this paper, we have proposed a new semi-automatic algorithm for Liver, spleen and kidneys area extraction in abdominal CT images. Our proposed method is based on hierarchical segmentation and watershed algorithm. In our approach, a powerful technique has been designed to suppress over-segmentation based on mosaic image and on the computation of the watershed transform. The algorithm is currency in two parts. In the first, we seek to improve the quality of the gradient-mosaic image. In this step, we propose a method for improving the gradient-mosaic image by applying the anisotropic diffusion filter followed by the morphological filters. Thereafter we proceed to the hierarchical segmentation of the liver, spleen and kidney. To validate the segmentation technique proposed, we have tested it on several images. Our segmentation approach is evaluated by comparing our results with the manual segmentation performed by an expert. The experimental results are described in the last part of this work.

Keywords: anisotropic diffusion filter, CT images, morphological filter, mosaic image, multi-abdominal organ segmentation, mosaic image, the watershed algorithm

Procedia PDF Downloads 468

Authors: Khaled Nagaty, Heba Nagaty, Gerard McKee

Abstract:

A signature is a behavioral biometric that is used for authenticating users in most financial and legal transactions. Signatures can be easily forged by skilled forgers. Therefore, it is essential to verify whether a signature is genuine or forged. The aim of any signature verification algorithm is to accommodate the differences between signatures of the same person and increase the ability to discriminate between signatures of different persons. This work presented in this paper proposes an automatic signature verification system to indicate whether a signature is genuine or not. The system comprises four phases: (1) The pre-processing phase in which image scaling, binarization, image rotation, dilation, thinning, and connecting ridge breaks are applied. (2) The feature extraction phase in which global and local features are extracted. The local features are minutiae points, curvature orientation, and curve plateau. The global features are signature area, signature aspect ratio, and Hu moments. (3) The post-processing phase, in which false minutiae are removed. (4) The classification phase in which features are enhanced before feeding it into the classifier. k-nearest neighbors and support vector machines are used. The classifier was trained on a benchmark dataset to compare the performance of the proposed offline signature verification system against the state-of-the-art. The accuracy of the proposed system is 92.3%.

Keywords: signature, ridge breaks, minutiae, orientation

Procedia PDF Downloads 124

Authors: J. Belovickis, V. Samulionis, J. Banys, M. V. Silibin, A. V. Solnyshkin, A. V. Sysa

Abstract:

Ferroelectric polymers exhibit good flexibility, processability and low cost of production. Doping of ferroelectric polymers with nanofillers may modify its dielectric, elastic or piezoelectric properties. Carbon nanotubes are one of the ingredients that can improve the mechanical properties of polymer based composites. In this work, we report on both the ultrasonic and the dielectric properties of the copolymer polyvinylidene fluoride/tetrafluoroethylene (P(VDF-TrFE)) of the composition 70/30 mol% with various concentrations of carbon nanotubes (CNT). Experimental study of ultrasonic wave attenuation and velocity in these composites has been performed over wide temperature range (100 K – 410 K) using an ultrasonic automatic pulse-echo tecnique. The temperature dependences of ultrasonic velocity and attenuation showed anomalies attributed to the glass transition and paraelectric-ferroelectric phase transition. Our investigations showed mechanical losses to be dependent on the volume fraction of the CNTs within the composites. The existence of broad hysteresis of the ultrasonic wave attenuation and velocity within the nanocomposites is presented between cooling and heating cycles. By the means of dielectric spectroscopy, it is shown that the dielectric properties may be tuned by varying the volume fraction of the CNT fillers.

Keywords: carbon nanotubes, polymer composites, PVDF-TrFE, ultrasonic spectroscopy

Procedia PDF Downloads 317

Authors: Ahmad K. Jassim, Raheem Kh. Al-Subar

Abstract:

Friction stir welding is a modern and an environmentally friendly solid state joining process used to joint relatively lighter family of materials. Recently, friction stir spot welding has been used instead of resistance spot welding which has received considerable attention from the automotive industry. It is environmentally friendly process that eliminated heat and pollution. In this research, friction stir spot welding has been used to study the possibility to weld AA1100 aluminum alloy sheet with 3 mm thickness by overlapping the edges of sheet as lap joint. The process was done using a drilling machine instead of milling machine. Different tool rotational speeds of 760, 1065, 1445, and 2000 RPM have been applied with manual and automatic compression to study their effect on the quality of welded joints. Heat generation, pressure applied, and depth of tool penetration have been measured during the welding process. The result shows that there is a possibility to weld AA1100 sheets; however, there is some surface defect that happened due to insufficient condition of welding. Moreover, the relationship between rotational speed, pressure, heat generation and tool depth penetration was created.

Keywords: friction, spot, stir, environmental, sustainable, AA1100 aluminum alloy

Procedia PDF Downloads 176

Authors: R. N. Begum, Ambalika Sharma, G. K. Singh

Abstract:

Identity theft has serious ramifications beyond data and personal information loss. This necessitates the implementation of robust and efficient user identification systems. Therefore, automatic biometric recognition systems are the need of the hour, and ECG-based systems are unquestionably the best choice due to their appealing inherent characteristics. The CNNs are the recent state-of-the-art techniques for ECG-based user identification systems. However, the results obtained are significantly below standards, and the situation worsens as the number of users and types of heartbeats in the dataset grows. As a result, this study proposes a highly accurate and resilient ECG-based person identification system using CNN's dense learning framework. The proposed research explores explicitly the calibre of dense CNNs in the field of ECG-based human recognition. The study tests four different configurations of dense CNN which are trained on a dataset of recordings collected from eight popular ECG databases. With the highest FAR of 0.04 percent and the highest FRR of 5%, the best performing network achieved an identification accuracy of 99.94 percent. The best network is also tested with various train/test split ratios. The findings show that DenseNets are not only extremely reliable but also highly efficient. Thus, they might also be implemented in real-time ECG-based human recognition systems.

Keywords: Biometrics, Dense Networks, Identification Rate, Train/Test split ratio

Procedia PDF Downloads 139

Authors: Malarvizhi Selvaraj, Paul Fergus, Andy Shaw

Abstract:

Uterine contractions produced during labour have the potential to damage the foetus by diminishing the maternal blood flow to the placenta. In order to observe this phenomenon labour and delivery are routinely monitored using cardiotocography monitors. An obstetrician usually makes the diagnosis of foetus hypoxia by interpreting cardiotocography recordings. However, cardiotocography capture and interpretation is time-consuming and subjective, often lead to misclassification that causes damage to the foetus and unnecessary caesarean section. Both of these have a high impact on the foetus and the cost to the national healthcare services. Automatic detection of foetal heart rate may be an objective solution to help to reduce unnecessary medical interventions, as reported in several studies. This paper aim is to provide a system for better identification and interpretation of abnormalities of the fetal heart rate using RStudio. An open dataset of 552 Intrapartum recordings has been filtered with 0.034 Hz filters in an attempt to remove noise while keeping as much of the discriminative data as possible. Features were chosen following an extensive literature review, which concluded with FIGO features such as acceleration, deceleration, mean, variance and standard derivation. The five features were extracted from 552 recordings. Using these features, recordings will be classified either normal or abnormal. If the recording is abnormal, it has got more chances of hypoxia.

Keywords: cardiotocography, foetus, intrapartum, hypoxia

Procedia PDF Downloads 192

Authors: Olivia Borgue, Massimo Panarotto, Ola Isaksson

Abstract:

This article presents a neural networks-based strategy for reducing the need for support structures when designing for additive manufacturing (AM). Additive manufacturing is a relatively new and immature industrial technology, and the information to make confident decisions when designing for AM is limited. This lack of information impacts especially the early stages of engineering design, for instance, it is difficult to actively consider the support structures needed for manufacturing a part. This difficulty is related to the challenge of designing a product geometry accounting for customer requirements, manufacturing constraints and minimization of support structure. The approach presented in this article proposes an automatized geometry modification technique for reducing the use of the support structures while designing for AM. This strategy starts with a neural network-based strategy for shape recognition to achieve product classification, using an STL file of the product as input. Based on the classification, an automatic part geometry modification based on MATLAB© is implemented. At the end of the process, the strategy presents different geometry modification alternatives depending on the type of product to be designed. The geometry alternatives are then evaluated adopting a QFD-like decision support tool.

Keywords: additive manufacturing, engineering design, geometry modification optimization, neural networks

Procedia PDF Downloads 227

Authors: A. Elsehemy, M. Abdeen , T. Nazmy

Abstract:

Since the appearance of the Semantic web, many semantic search techniques and models were proposed to exploit the information in ontology to enhance the traditional keyword-based search. Many advances were made in languages such as English, German, French and Spanish. However, other languages such as Arabic are not fully supported yet. In this paper we present a framework for ontology based information retrieval for Arabic language. Our system consists of four main modules, namely query parser, indexer, search and a ranking module. Our approach includes building a semantic index by linking ontology concepts to documents, including an annotation weight for each link, to be used in ranking the results. We also augmented the framework with an automatic document categorizer, which enhances the overall document ranking. We have built three Arabic domain ontologies: Sports, Economic and Politics as example for the Arabic language. We built a knowledge base that consists of 79 classes and more than 1456 instances. The system is evaluated using the precision and recall metrics. We have done many retrieval operations on a sample of 40,316 documents with a size 320 MB of pure text. The results show that the semantic search enhanced with text classification gives better performance results than the system without classification.

Keywords: Arabic text classification, ontology based retrieval, Arabic semantic web, information retrieval, Arabic ontology

Procedia PDF Downloads 501

Authors: Bel G Raggad

Abstract:

An e-Learning setting is a distributed computing environment where information resources can be connected to any public network. Public networks are very unsecure which can compromise the reliability of an e-Learning environment. This study is only concerned with the intrusion detection aspect of e-Learning security and how incident responses are planned. The literature reported great advances in intrusion detection system (ids) but neglected to study an important ids weakness: suspected events are detected but an intrusion is not determined because it is not defined in ids databases. We propose an incident response generator (DIRG) that produces incident responses when the working ids system suspects an event that does not correspond to a known intrusion. Data involved in intrusion detection when ample uncertainty is present is often not suitable to formal statistical models including Bayesian. We instead adopt Dempster and Shafer theory to process intrusion data for the unknown event. The DIRG engine transforms data into a belief structure using incident scenarios deduced by the security administrator. Belief values associated with various incident scenarios are then derived and evaluated to choose the most appropriate scenario for which an automatic incident response is generated. This article provides a numerical example demonstrating the working of the DIRG system.

Keywords: decision support system, distributed computing, e-Learning security, incident response, intrusion detection, security risk, statefull inspection

Procedia PDF Downloads 403

Authors: R. Tlili Yaakoubi, H.Nakouri, O. Blanpain, S. Lallahem

Abstract:

The current tools for real time management of sewer systems are based on two software tools: the software of weather forecast and the software of hydraulic simulation. The use of the first ones is an important cause of imprecision and uncertainty, the use of the second requires temporal important steps of decision because of their need in times of calculation. This way of proceeding fact that the obtained results are generally different from those waited. The major idea of this project is to change the basic paradigm by approaching the problem by the "automatic" face rather than by that "hydrology". The objective is to make possible the realization of a large number of simulations at very short times (a few seconds) allowing to take place weather forecasts by using directly the real time meditative pluviometric data. The aim is to reach a system where the decision-making is realized from reliable data and where the correction of the error is permanent. A first model of control laws was realized and tested with different return-period rainfalls. The gains obtained in rejecting volume vary from 19 to 100 %. The development of a new algorithm was then used to optimize calculation time and thus to overcome the subsequent combinatorial problem in our first approach. Finally, this new algorithm was tested with 16- year-rainfall series. The obtained gains are 40 % of total volume rejected to the natural environment and of 65 % in the number of discharges.

Keywords: automation, optimization, paradigm, RTC

Procedia PDF Downloads 280

Authors: Zhdanova A. O., Volkov R. S., Kuznetsov G. V., Strizhak P. A.

Abstract:

Fires in different types of facilities are a serious problem worldwide.It is still an unaccomplished science and technology objective to establish the minimum number and type of sensors in automatic systems of compartment fire suppression which would turn the fire-extinguishing agent spraying on and off in real time depending on the state of the fire, minimize the amount of agent applied, delay time in fire suppression and system response, as well as the time of combustion suppression. Based on the results of experimental studies, the conclusion was made that it is reasonable to use a gas analysis system and heat sensors (in the event of their prior activation) to determine the effectiveness of fire suppression (fire-extinguishing composition interacts with the fire). Thus, the concentration of CO in the interaction of the firefighting liquid with the fire increases to 0.7–1.2%, which indicates a slowdown in the flame combustion, and heat sensors stop responding at a gas medium temperature below 80 ºC, which shows a gradual decrease in the heat release from the fire. The evidence from this study suggests that the information received from the video recording equipment (video camera) should be used in real time as an additional parameter confirming fire suppression. Research was supported by Russian Science Foundation (project No 21-19-00009, https://rscf.ru/en/project/21-19-00009/).

Keywords: compartment fires, fire suppression, continuous control of fire behavior, feedback systems

Procedia PDF Downloads 106

Authors: Bing Li, Zhi Li, Yilong Yang

Abstract:

Web classification can promote the quality of service discovery and management in the service repository. It is widely used to locate developers desired services. Although traditional classification methods based on supervised learning models can achieve classification tasks, developers need to manually mark web services, and the quality of these tags may not be enough to establish an accurate classifier for service classification. With the doubling of the number of web services, the manual tagging method has become unrealistic. In recent years, the attention mechanism has made remarkable progress in the field of deep learning, and its huge potential has been fully demonstrated in various fields. This paper designs a multi-head attention graph convolutional network (MHAGCN) service classification method, which can assign different weights to the neighborhood nodes without complicated matrix operations or relying on understanding the entire graph structure. The framework combines the advantages of the attention mechanism and graph convolutional neural network. It can classify web services through automatic feature extraction. The comprehensive experimental results on a real dataset not only show the superior performance of the proposed model over the existing models but also demonstrate its potentially good interpretability for graph analysis.

Keywords: attention mechanism, graph convolutional network, interpretability, service classification, service discovery

Procedia PDF Downloads 112

Authors: M. Moslehpour, S. Khorsandi

Abstract:

Due to shortage in IPv4 addresses, transition to IPv6 has gained significant momentum in recent years. Like Address Resolution Protocol (ARP) in IPv4, Neighbor Discovery Protocol (NDP) provides some functions like address resolution in IPv6. Besides functionality of NDP, it is vulnerable to some attacks. To mitigate these attacks, Internet Protocol Security (IPsec) was introduced, but it was not efficient due to its limitation. Therefore, SEND protocol is proposed to automatic protection of auto-configuration process. It is secure neighbor discovery and address resolution process. To defend against threats on NDP’s integrity and identity, Cryptographically Generated Address (CGA) and asymmetric cryptography are used by SEND. Besides advantages of SEND, its disadvantages like the computation process of CGA algorithm and sequentially of CGA generation algorithm are considerable. In this paper, we parallel this process between network resources in order to improve it. In addition, we compare the CGA generation time in self-computing and distributed-computing process. We focus on the impact of the malicious nodes on the CGA generation time in the network. According to the result, although malicious nodes participate in the generation process, CGA generation time is less than when it is computed in a one-way. By Trust Management System, detecting and insulating malicious nodes is easier.

Keywords: NDP, IPsec, SEND, CGA, modifier, malicious node, self-computing, distributed-computing

Procedia PDF Downloads 261

Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu

Abstract:

Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.

Keywords: GPT, phantom-less QCT, large language model, osteoporosis

Procedia PDF Downloads 43

Authors: Chia-Hui Chen, Chien-Kuo Wang

Abstract:

Background: Full field digital mammography (FFDM) is widely used in diagnosis of breast cancer. Digital breast tomosynthesis (DBT) has recently been introduced into the clinic and is being used for screening for breast cancer in the general population. Hence, the radiation dose delivered to the patients involved in an imaging protocol is of utmost concern. Aim: To compare the surface radiation dose (ESD) of digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) by using breast phantoms. Method: We analyzed the average entrance surface dose (ESD) of FFDM and DBT by using breast phantoms. Optically Stimulated luminescent Dosimeters (OSLD) were placed in a tissue-equivalent Breast phantom at difference sites of interest. Absorbed dose measurements were obtained after digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) exposures. Results: An automatic exposure control (AEC) is proposed for surface dose measurement during DBT and FFDM. The mean ESD values for DBT and FFDM were 6.37 mGy and 3.51mGy, respectively. Using of OSLD measured for surface dose during DBT and FFDM. There were 19.87 mGy and 11.36 mGy, respectively. The surface exposure dose of DBT could possibly be increased by two times with FFDM. Conclusion: The radiation dose from DBT was higher than that of FFDM and the difference in dose between AEC and OSLD measurements at phantom surface.

Keywords: full-field digital mammography, digital breast tomosynthesis, optically stimulated luminescent dosimeters, surface dose

Procedia PDF Downloads 396

Authors: Diana Pombo, Maria Loaiza, Mauricio Quijano, Alberto Cadena, Juan Pablo Tello

Abstract:

In this paper, we present a semi-automatic tool for calculating ejection fraction from an echocardiographic video signal which is derived from a database in DICOM format, of Clinica de la Costa - Barranquilla. Described in this paper are each of the steps and methods used to find the respective calculation that includes acquisition and formation of the test samples, processing and finally the calculation of the parameters to obtain the ejection fraction. Two imaging segmentation methods were compared following a methodological framework that is similar only in the initial stages of processing (process of filtering and image enhancement) and differ in the end when algorithms are implemented (Active Contour and Region Growing Algorithms). The results were compared with the measurements obtained by two different medical specialists in cardiology who calculated the ejection fraction of the study samples using the traditional method, which consists of drawing the region of interest directly from the computer using echocardiography equipment and a simple equation to calculate the desired value. The results showed that if the quality of video samples are good (i.e., after the pre-processing there is evidence of an improvement in the contrast), the values provided by the tool are substantially close to those reported by physicians; also the correlation between physicians does not vary significantly.

Keywords: echocardiography, DICOM, processing, segmentation, EDV, ESV, ejection fraction

Procedia PDF Downloads 405