Pub Date : 2021-09-15DOI: 10.1142/s2196888822500099
P. Savino, A. Tonazzini
Virtual restoration of digital copies of the human documental heritage is crucial for facilitating both the traditional work of philologists and paleographers and the automatic analysis of the contents. Here we propose a practical and fast procedure for the correction of the typically complex background of recto–verso historical manuscripts. The procedure has two main, distinctive features: it does not need for a preliminary registration of the two page sides, and it is non-invasive, as it does not alter the original appearance of the manuscript. This makes it suitable for the routinary use in the archives, and permits an easier fruition of the manuscripts, without any information being lost. In the first stage, the detection of both the primary text and the spurious strokes is performed via soft segmentation, based on the statistical decorrelation of the two recto and verso images. In the second stage, the noisy pattern is substituted with pixels that simulate the texture of the clean surrounding background, through an efficient technique of image inpainting. As shown in the experimental results, evaluated both qualitatively and quantitatively, the proposed procedure is able to perform a fine and selective removal of the degradation, while preserving other informative marks of the manuscript history.
{"title":"A Procedure for the Correction of Back-to-Front Degradations in Archival Manuscripts with Preservation of the Original Appearance","authors":"P. Savino, A. Tonazzini","doi":"10.1142/s2196888822500099","DOIUrl":"https://doi.org/10.1142/s2196888822500099","url":null,"abstract":"Virtual restoration of digital copies of the human documental heritage is crucial for facilitating both the traditional work of philologists and paleographers and the automatic analysis of the contents. Here we propose a practical and fast procedure for the correction of the typically complex background of recto–verso historical manuscripts. The procedure has two main, distinctive features: it does not need for a preliminary registration of the two page sides, and it is non-invasive, as it does not alter the original appearance of the manuscript. This makes it suitable for the routinary use in the archives, and permits an easier fruition of the manuscripts, without any information being lost. In the first stage, the detection of both the primary text and the spurious strokes is performed via soft segmentation, based on the statistical decorrelation of the two recto and verso images. In the second stage, the noisy pattern is substituted with pixels that simulate the texture of the clean surrounding background, through an efficient technique of image inpainting. As shown in the experimental results, evaluated both qualitatively and quantitatively, the proposed procedure is able to perform a fine and selective removal of the degradation, while preserving other informative marks of the manuscript history.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124767294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-02DOI: 10.1142/s2196888822500026
Hanane Lakehal, M. Ghanai, K. Chafaa
In this investigation, state vector estimation of the Permanent Magnet Synchronous machine (PMSM) using the nonlinear Kalman estimator (Extended Kalman Filter) is considered. The considered states are the speed of the rotor, its angular position, the torque of the load and the resistance of the stator. Since the extended Kalman filter contains some free parameters, it will be necessary to optimize them in order to obtain a better efficiency. The free parameters of EKF are the covariance matrices of state noise and measurement noise. These later will be auto adjusted by a new metaheuristic optimization technique called Biogeographical-based optimization (BBO). As far as we know, BBO–EKF optimization for PMSM state was not treated in the literature. The suggested estimation tuning approach is demonstrated using a computer simulation of a PMSM. Simulated experimentations show the robustness and effectiveness of the proposed scheme. In addition, a detailed comparative study with conventional methods like Particle Swarm Optimization and Genetic Algorithms will be given.
{"title":"BBO-Based State Optimization for PMSM Machines","authors":"Hanane Lakehal, M. Ghanai, K. Chafaa","doi":"10.1142/s2196888822500026","DOIUrl":"https://doi.org/10.1142/s2196888822500026","url":null,"abstract":"In this investigation, state vector estimation of the Permanent Magnet Synchronous machine (PMSM) using the nonlinear Kalman estimator (Extended Kalman Filter) is considered. The considered states are the speed of the rotor, its angular position, the torque of the load and the resistance of the stator. Since the extended Kalman filter contains some free parameters, it will be necessary to optimize them in order to obtain a better efficiency. The free parameters of EKF are the covariance matrices of state noise and measurement noise. These later will be auto adjusted by a new metaheuristic optimization technique called Biogeographical-based optimization (BBO). As far as we know, BBO–EKF optimization for PMSM state was not treated in the literature. The suggested estimation tuning approach is demonstrated using a computer simulation of a PMSM. Simulated experimentations show the robustness and effectiveness of the proposed scheme. In addition, a detailed comparative study with conventional methods like Particle Swarm Optimization and Genetic Algorithms will be given.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122411943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-05DOI: 10.1142/S2196888822500051
F. A. Şenel
The COVID-19 is a global disease that occurred at the end of 2019 and it has shown its effects all over the world in a very short time. World Health Organization has mobilized all the countries of the world to survive with minimal damage from this outbreak. The situation in some countries was under control as their health infrastructure is robust enough. On the other hand, many countries suffered significant damage from the outbreak. The countries that have already taken their precautions have suffered less, Turkey is one of the leading countries. Besides taking precautions in advance, countries are guiding each other throughout the outbreak. Therefore, the countries leading the fight against the outbreak should be analyzed and each country should update its precautions to fight the outbreak. In this study, COVID-19 deaths are taken into account and similar countries to Turkey are identified by K-means clustering. Later, by comparing the various characteristics of Turkey with these similar countries, Turkey’s status in fighting the outbreak is revealed. The precautions Turkey took before the outbreak showed that Turkey can fight the COVID-19 outbreak successfully.
{"title":"The Analysis of Turkey's Fight Against the COVID-19 Outbreak Using K-Means Clustering and Curve Fitting","authors":"F. A. Şenel","doi":"10.1142/S2196888822500051","DOIUrl":"https://doi.org/10.1142/S2196888822500051","url":null,"abstract":"The COVID-19 is a global disease that occurred at the end of 2019 and it has shown its effects all over the world in a very short time. World Health Organization has mobilized all the countries of the world to survive with minimal damage from this outbreak. The situation in some countries was under control as their health infrastructure is robust enough. On the other hand, many countries suffered significant damage from the outbreak. The countries that have already taken their precautions have suffered less, Turkey is one of the leading countries. Besides taking precautions in advance, countries are guiding each other throughout the outbreak. Therefore, the countries leading the fight against the outbreak should be analyzed and each country should update its precautions to fight the outbreak. In this study, COVID-19 deaths are taken into account and similar countries to Turkey are identified by K-means clustering. Later, by comparing the various characteristics of Turkey with these similar countries, Turkey’s status in fighting the outbreak is revealed. The precautions Turkey took before the outbreak showed that Turkey can fight the COVID-19 outbreak successfully.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134318317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-05DOI: 10.1142/S2196888822500063
Helena Dudycz, P. Stefaniak, Pawel Pyda
The new generation of industry, i.e. Industry 4.0, pertains to the processing of immense amounts of data, resulting, among other things, from the large-scale use of microcontrollers to control machines, an increase in the scale of automation, the use of the Internet of Things technology — e.g. in sensors installed at different stages of the production process, the implementation of the digital twin concept, and many other technologies designed to collect data (e.g. GPS or RFID). These data are collected in the enterprise’s variety of resources and databases. These data can be a valuable source of information and knowledge if the right approach to advanced data analysis is adopted, which depends, among other things, on the enterprise’s existing IT infrastructure. This paper sets out to present conclusions formulated on the basis of research consisting in the analysis of multinational manufacturing companies’ existing IT infrastructures. Three basic model solutions of IT architecture occurring in multi-site enterprises were identified, which made it possible to identify the main problems stemming from the IT architecture in place and concerning the analysis of data for the needs of company management. Additionally, this paper discusses the challenges faced by multi-site manufacturing companies. One such activity is the modification and expansion of the company’s IT infrastructure, including the implementation of Big Data and Master Data Management (MDM) solutions. The contribution provided by this paper consists in the analysis of the IT infrastructure in large, multi-site enterprises, which enabled the identification of problems and challenges related to advanced data analysis in this type of companies.
{"title":"Problems and Challenges Related to Advanced Data Analysis in Multi-Site Enterprises","authors":"Helena Dudycz, P. Stefaniak, Pawel Pyda","doi":"10.1142/S2196888822500063","DOIUrl":"https://doi.org/10.1142/S2196888822500063","url":null,"abstract":"The new generation of industry, i.e. Industry 4.0, pertains to the processing of immense amounts of data, resulting, among other things, from the large-scale use of microcontrollers to control machines, an increase in the scale of automation, the use of the Internet of Things technology — e.g. in sensors installed at different stages of the production process, the implementation of the digital twin concept, and many other technologies designed to collect data (e.g. GPS or RFID). These data are collected in the enterprise’s variety of resources and databases. These data can be a valuable source of information and knowledge if the right approach to advanced data analysis is adopted, which depends, among other things, on the enterprise’s existing IT infrastructure. This paper sets out to present conclusions formulated on the basis of research consisting in the analysis of multinational manufacturing companies’ existing IT infrastructures. Three basic model solutions of IT architecture occurring in multi-site enterprises were identified, which made it possible to identify the main problems stemming from the IT architecture in place and concerning the analysis of data for the needs of company management. Additionally, this paper discusses the challenges faced by multi-site manufacturing companies. One such activity is the modification and expansion of the company’s IT infrastructure, including the implementation of Big Data and Master Data Management (MDM) solutions. The contribution provided by this paper consists in the analysis of the IT infrastructure in large, multi-site enterprises, which enabled the identification of problems and challenges related to advanced data analysis in this type of companies.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128205470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-25DOI: 10.1142/S2196888821500226
B. Amarasekara, A. Mathrani, C. Scogings
Online user activities are tracked for many purposes. In e-commerce, cross-domain tracking is used to quantify and pay for web-traffic generation. Our previous research studies have shown that HTTP cookie-based tracking process, though reliable, can fail due to technical reasons, as well as through fraudulent manipulation by traffic generators. In this research study, we evaluate which of the previously published tracking mechanisms are still functional. We assess the efficacy and utility of those methods to create a robust tracking mechanism for e-commerce. A failsafe and robust tracking mechanism does not need to translate into further privacy intrusions. Many countries are rushing to introduce new regulations, which can have a negative impact on the development of robust technologies in an inherently stateless eco-system. We used a multi-domain, purpose-built simulation environment to experiment common tracking scenarios, and to describe the parameters that define the minimum tracking requirement use-cases, and practices that result in invading privacy of users. This study will help practitioners in their implementations, and policy developers and regulators to draw up policies that would not curtail the development of robust tracking technologies that are needed in e-commerce activities, while safeguarding the privacy of internet users.
{"title":"Online Tracking: When Does it Become Stalking?","authors":"B. Amarasekara, A. Mathrani, C. Scogings","doi":"10.1142/S2196888821500226","DOIUrl":"https://doi.org/10.1142/S2196888821500226","url":null,"abstract":"Online user activities are tracked for many purposes. In e-commerce, cross-domain tracking is used to quantify and pay for web-traffic generation. Our previous research studies have shown that HTTP cookie-based tracking process, though reliable, can fail due to technical reasons, as well as through fraudulent manipulation by traffic generators. In this research study, we evaluate which of the previously published tracking mechanisms are still functional. We assess the efficacy and utility of those methods to create a robust tracking mechanism for e-commerce. A failsafe and robust tracking mechanism does not need to translate into further privacy intrusions. Many countries are rushing to introduce new regulations, which can have a negative impact on the development of robust technologies in an inherently stateless eco-system. We used a multi-domain, purpose-built simulation environment to experiment common tracking scenarios, and to describe the parameters that define the minimum tracking requirement use-cases, and practices that result in invading privacy of users. This study will help practitioners in their implementations, and policy developers and regulators to draw up policies that would not curtail the development of robust tracking technologies that are needed in e-commerce activities, while safeguarding the privacy of internet users.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123189682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-01DOI: 10.1142/s2196888821500093
Tomasz Zlamaniec, K. Chao, Nick Godwin
It is a trend for the public organizations to digitalize and publish their large dataset as open linked data to the public users for queries and other applications for further utilizations. Different users’ queries with various frequencies over time create different workload patterns to the servers which cannot guarantee the QoS during peak usages. Materialization is a well-known effective method to reduce peaks, but it is not used by semantic webs, due to frequently evolving schema. This research is able to estimate workloads based on previous queries, analyze and normalize their structures to materialize views, and map the queries to the views with populated data. By analyzing how access patterns of individual views contribute to the overall system workload, the proposed model aims at selection of candidates offering the highest reduction of the peak workload. Consequently, rather than optimizing all queries equally, a system using the new selection method can offer higher query throughput when it is the most needed, allowing for a higher number of concurrent users without compromising QoS during the peak usage. Finally, two case studies were used to evaluate the proposed method.
{"title":"Workload-Aware Views Materialization for Big Open Linked Data","authors":"Tomasz Zlamaniec, K. Chao, Nick Godwin","doi":"10.1142/s2196888821500093","DOIUrl":"https://doi.org/10.1142/s2196888821500093","url":null,"abstract":"It is a trend for the public organizations to digitalize and publish their large dataset as open linked data to the public users for queries and other applications for further utilizations. Different users’ queries with various frequencies over time create different workload patterns to the servers which cannot guarantee the QoS during peak usages. Materialization is a well-known effective method to reduce peaks, but it is not used by semantic webs, due to frequently evolving schema. This research is able to estimate workloads based on previous queries, analyze and normalize their structures to materialize views, and map the queries to the views with populated data. By analyzing how access patterns of individual views contribute to the overall system workload, the proposed model aims at selection of candidates offering the highest reduction of the peak workload. Consequently, rather than optimizing all queries equally, a system using the new selection method can offer higher query throughput when it is the most needed, allowing for a higher number of concurrent users without compromising QoS during the peak usage. Finally, two case studies were used to evaluate the proposed method.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134030106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-03-30DOI: 10.1142/S2196888822500038
Manish Kumar, B. Poornima, H. S. Nagendraswamy, C. Manjunath, B. E. Rangaswamy
This work identifies the strong dominant features by its location and extracts the image features for the purpose of automatic desire focusing on prominent structure and artistic stylization of images. At the pre-processing level, dataset image is treated using refined structure preserving image abstraction framework which can deliver the best effectual structure preserved abstracted results by utilizing visual attributes from 2D color image. The presented framework efficiently conserves the structural characteristics in the foreground of an input image by exhaustively amalgamate the series of non-photorealistic rendering image filters over meticulous investigational work and it also reduces the background substance of an image. The framework assesses image and object space details to generate structure preserved image abstraction thus distinguishing the accentuated elements of an enhanced structures using Harris key-point feature detector and chooses the 100 major unique dominant feature locations among available features. This work automatically selects the unique location from the extracted features using polynomial region of interest and unselected image regions and its background are blurred using Gaussian motion blurring with point spread function. Deblurring the selected region using wiener filtering to get the desire focusing on prominent structure followed by color quantization and flow-based bilateral filtering is applied over focused structural region to achieve artistic stylization. Efficiency of the framework has been validated by carrying out the trials on the selected Flickr repository, David Mould and Ruixing Wang dataset. In addition, user’s visual opinion and the image quality estimation methods were also utilized to appraise the proposed pre-processing framework. This work lists the structure preserving image abstraction framework applications, limitation, execution difficulties and future work in the field of Non-photorealistic rendering domain.
{"title":"A Refined Structure Preserving Image Abstraction Framework as a Pre-Processing Technique for Desire Focusing on Prominent Structure and Artistic Stylization","authors":"Manish Kumar, B. Poornima, H. S. Nagendraswamy, C. Manjunath, B. E. Rangaswamy","doi":"10.1142/S2196888822500038","DOIUrl":"https://doi.org/10.1142/S2196888822500038","url":null,"abstract":"This work identifies the strong dominant features by its location and extracts the image features for the purpose of automatic desire focusing on prominent structure and artistic stylization of images. At the pre-processing level, dataset image is treated using refined structure preserving image abstraction framework which can deliver the best effectual structure preserved abstracted results by utilizing visual attributes from 2D color image. The presented framework efficiently conserves the structural characteristics in the foreground of an input image by exhaustively amalgamate the series of non-photorealistic rendering image filters over meticulous investigational work and it also reduces the background substance of an image. The framework assesses image and object space details to generate structure preserved image abstraction thus distinguishing the accentuated elements of an enhanced structures using Harris key-point feature detector and chooses the 100 major unique dominant feature locations among available features. This work automatically selects the unique location from the extracted features using polynomial region of interest and unselected image regions and its background are blurred using Gaussian motion blurring with point spread function. Deblurring the selected region using wiener filtering to get the desire focusing on prominent structure followed by color quantization and flow-based bilateral filtering is applied over focused structural region to achieve artistic stylization. Efficiency of the framework has been validated by carrying out the trials on the selected Flickr repository, David Mould and Ruixing Wang dataset. In addition, user’s visual opinion and the image quality estimation methods were also utilized to appraise the proposed pre-processing framework. This work lists the structure preserving image abstraction framework applications, limitation, execution difficulties and future work in the field of Non-photorealistic rendering domain.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131469388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-17DOI: 10.1142/S2196888822500014
Syeda Sumbul Hossain, Y. Arafat, Md. Ekram Hossain
Online news blogs and websites are becoming influential to any society as they accumulate the world in one place. Aside from that, online news blogs and websites have efficient strategies in grabbing readers’ attention by the headlines, that being so to recognize the sentiment orientation or polarity of the news headlines for avoiding misinterpretation against any fact. In this study, we have examined 3383 news headlines created by five different global newspapers. In the interest of distinguishing the sentiment polarity (or sentiment orientation) of news headlines, we have trained our model by seven machine learning and two deep learning algorithms. Finally, their performance was compared. Among them, Bernoulli naïve Bayes and Convolutional Neural Network (CNN) achieved higher accuracy than other machine learning and deep learning algorithms, respectively. Such a study will help the audience in determining their impression against or for any leader or governance; and will provide assistance to recognize the most indifferent newspaper or news blogs.
{"title":"Context-Based News Headlines Analysis: A Comparative Study of Machine Learning and Deep Learning Algorithms","authors":"Syeda Sumbul Hossain, Y. Arafat, Md. Ekram Hossain","doi":"10.1142/S2196888822500014","DOIUrl":"https://doi.org/10.1142/S2196888822500014","url":null,"abstract":"Online news blogs and websites are becoming influential to any society as they accumulate the world in one place. Aside from that, online news blogs and websites have efficient strategies in grabbing readers’ attention by the headlines, that being so to recognize the sentiment orientation or polarity of the news headlines for avoiding misinterpretation against any fact. In this study, we have examined 3383 news headlines created by five different global newspapers. In the interest of distinguishing the sentiment polarity (or sentiment orientation) of news headlines, we have trained our model by seven machine learning and two deep learning algorithms. Finally, their performance was compared. Among them, Bernoulli naïve Bayes and Convolutional Neural Network (CNN) achieved higher accuracy than other machine learning and deep learning algorithms, respectively. Such a study will help the audience in determining their impression against or for any leader or governance; and will provide assistance to recognize the most indifferent newspaper or news blogs.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116522387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-06DOI: 10.1142/S2196888821500238
A. Netšunajev, S. Nõmm, A. Toomela, Kadri Medijainen, P. Taba
Analysis of the sentence writing test is conducted in this paper to support diagnostics of the Parkinsons disease. Drawing and writing tests digitization has become a trend where synergy of machine learning techniques on the one side and knowledge base of the neurology and psychiatry on the other side leading sophisticated result in computer aided diagnostics. Such rapid progress has a drawback. In many cases, decisions made by machine learning algorithm are difficult to explain in a language human practitioner familiar with. The method proposed in this paper employs unsupervised learning techniques to segment the sentence into the individual characters. Then, feature engineering process is applied to describe writing of each letter using a set of kinematic and pressure parameters. Following feature selection process applicability of different machine learning classifiers is evaluated. To guarantee that achieved results may be interpreted by human, two major guidelines are established. The first one is to keep dimensionality of the feature set low. The second one is clear physical meaning of the features describing the writing process. Features describing amount and smoothness of the motion observed during the writing alongside with letter size are considered. Resulting algorithm does not take into account any semantic information or language particularities and therefore may be easily adopted to any language based on Latin or Cyrillic alphabets.
{"title":"Parkinson's Disease Diagnostics Based on the Analysis of Digital Sentence Writing Test","authors":"A. Netšunajev, S. Nõmm, A. Toomela, Kadri Medijainen, P. Taba","doi":"10.1142/S2196888821500238","DOIUrl":"https://doi.org/10.1142/S2196888821500238","url":null,"abstract":"Analysis of the sentence writing test is conducted in this paper to support diagnostics of the Parkinsons disease. Drawing and writing tests digitization has become a trend where synergy of machine learning techniques on the one side and knowledge base of the neurology and psychiatry on the other side leading sophisticated result in computer aided diagnostics. Such rapid progress has a drawback. In many cases, decisions made by machine learning algorithm are difficult to explain in a language human practitioner familiar with. The method proposed in this paper employs unsupervised learning techniques to segment the sentence into the individual characters. Then, feature engineering process is applied to describe writing of each letter using a set of kinematic and pressure parameters. Following feature selection process applicability of different machine learning classifiers is evaluated. To guarantee that achieved results may be interpreted by human, two major guidelines are established. The first one is to keep dimensionality of the feature set low. The second one is clear physical meaning of the features describing the writing process. Features describing amount and smoothness of the motion observed during the writing alongside with letter size are considered. Resulting algorithm does not take into account any semantic information or language particularities and therefore may be easily adopted to any language based on Latin or Cyrillic alphabets.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121308644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-01DOI: 10.1142/s2196888821500019
N. Nguyen, M. Bui
We introduce a computational framework, namely, a pretopological construct, for mining stock prices’ time series in order to expand a set of stocks by adding other stocks whose average correlations with the set are above a threshold. We increase the threshold with the set’s size to verify group impact in financial crises. This approach is tested by a consecutive expansion process started from a stock of Merrill Lynch & Co., and a consecutive contraction process of the rest. The test’s results and the comparison to graph theory show that our model and pretopology theory are helpful to study stock markets.
{"title":"Modeling Cascading Failures in Stock Markets by a Pretopological Framework","authors":"N. Nguyen, M. Bui","doi":"10.1142/s2196888821500019","DOIUrl":"https://doi.org/10.1142/s2196888821500019","url":null,"abstract":"We introduce a computational framework, namely, a pretopological construct, for mining stock prices’ time series in order to expand a set of stocks by adding other stocks whose average correlations with the set are above a threshold. We increase the threshold with the set’s size to verify group impact in financial crises. This approach is tested by a consecutive expansion process started from a stock of Merrill Lynch & Co., and a consecutive contraction process of the rest. The test’s results and the comparison to graph theory show that our model and pretopology theory are helpful to study stock markets.","PeriodicalId":256649,"journal":{"name":"Vietnam. J. Comput. Sci.","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133951731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：