Javier Rozo Alzate, Marta S. Tabares-Betancur, Paola Vallejo-Correa
Graffiti is an element of graphic expression that manifests different states of the human being. However, for many governments worldwide, it has been an element of discord between them and the communities that express themselves through graffitis. This article proposes identifying graffiti and concentration zones through Computer Vision and object detection and localization to support public policy management in smart cities. ASUM-DM methodology is used to achieve the aim. Initially, the current problems faced by municipal governments in the management of public graffiti policy are identified. Then available datasets of images from Google Street View (GSV) and other acquired datasets are identified for the case study carried out in the city of Medellín (Colombia) and border municipalities. A training dataset of 1,395 images and a production dataset of 71,100 panoramas is placed on strictly using the experimental method of the division of training data, validation, and a production sample, to make a correct estimation of the generalization error. As a result of the training process, we obtained an Average Precision of 69,14%, which presented a high precision Tag of 89.23%, and low precision of 59.13% in Mural. Finally, it is possible to build heat maps of graffiti concentration areas that could guide rulers to create or improve public policies related to graffiti expression.
{"title":"Graffiti and government in smart cities: a Deep Learning approach applied to Medellín City, Colombia","authors":"Javier Rozo Alzate, Marta S. Tabares-Betancur, Paola Vallejo-Correa","doi":"10.1145/3460620.3460749","DOIUrl":"https://doi.org/10.1145/3460620.3460749","url":null,"abstract":"Graffiti is an element of graphic expression that manifests different states of the human being. However, for many governments worldwide, it has been an element of discord between them and the communities that express themselves through graffitis. This article proposes identifying graffiti and concentration zones through Computer Vision and object detection and localization to support public policy management in smart cities. ASUM-DM methodology is used to achieve the aim. Initially, the current problems faced by municipal governments in the management of public graffiti policy are identified. Then available datasets of images from Google Street View (GSV) and other acquired datasets are identified for the case study carried out in the city of Medellín (Colombia) and border municipalities. A training dataset of 1,395 images and a production dataset of 71,100 panoramas is placed on strictly using the experimental method of the division of training data, validation, and a production sample, to make a correct estimation of the generalization error. As a result of the training process, we obtained an Average Precision of 69,14%, which presented a high precision Tag of 89.23%, and low precision of 59.13% in Mural. Finally, it is possible to build heat maps of graffiti concentration areas that could guide rulers to create or improve public policies related to graffiti expression.","PeriodicalId":36824,"journal":{"name":"Data","volume":"14 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88457706","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}
With the alarming global health crisis and pandemic, the entire medical industry and every human in this world are desperately looking for new technologies and solutions to monitor and contain the spread of this COVID-19 virus through early detection of its presence among infected patients. The early diagnosis of COVID-19 is hence critical for prevention and limiting this pandemic before it engulfs the humanity. With early diagnosis, the patient may be suggested for self-isolation (or) quarantine under medical supervision. Early detection of COVID-19 can save the patient and minimize the risk of falling prey to CoviD-19. Machine learning, a subset field of Artificial Intelligence can provide a viable solution for early diagnosis of disease and facilitate continuous monitoring of infected patients. AI based approaches can provide a view of the degree of disease severity. In general, Artificial intelligence (AI) could be a better technique for quantitative evaluation of the disease to obtain fruitful results. This paper throws light on the emerging need for AI powered solutions to foster early diagnosis of COVID-19 and suggest an ML based health monitoring framework for diagnosis of infected patients.
{"title":"MACHINE LEARNING FRAMEWORK FOR COVID-19 DIAGNOSIS","authors":"Sravan kiran Vangipuram, Rajesh Appusamy","doi":"10.1145/3460620.3460624","DOIUrl":"https://doi.org/10.1145/3460620.3460624","url":null,"abstract":"With the alarming global health crisis and pandemic, the entire medical industry and every human in this world are desperately looking for new technologies and solutions to monitor and contain the spread of this COVID-19 virus through early detection of its presence among infected patients. The early diagnosis of COVID-19 is hence critical for prevention and limiting this pandemic before it engulfs the humanity. With early diagnosis, the patient may be suggested for self-isolation (or) quarantine under medical supervision. Early detection of COVID-19 can save the patient and minimize the risk of falling prey to CoviD-19. Machine learning, a subset field of Artificial Intelligence can provide a viable solution for early diagnosis of disease and facilitate continuous monitoring of infected patients. AI based approaches can provide a view of the degree of disease severity. In general, Artificial intelligence (AI) could be a better technique for quantitative evaluation of the disease to obtain fruitful results. This paper throws light on the emerging need for AI powered solutions to foster early diagnosis of COVID-19 and suggest an ML based health monitoring framework for diagnosis of infected patients.","PeriodicalId":36824,"journal":{"name":"Data","volume":"5 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75018615","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}
In this paper, we present the main ideas behind the development of a system that can be used to deal with meteorological big data. In particular, the system captures data online and downloads it locally onto a MongoDB database. After that, the user can create a particular database and corresponding minable views for analysis. The results provided by the systems are predictive models with the ability to predict some weather-related variables, such as temperature and rainfall. The system has been validated from a triple perspective (usability, experts’ validation, and performance assessment), obtaining satisfactory results. This paper aims to be a brief guide for authors who intend to developed similar systems either in the meteorological field or other domains generating big amounts of data.
{"title":"Meteorological forecasting based on big data analysis","authors":"Shadi A. Aljawarneh, J. A. L. Torralbo","doi":"10.1145/3460620.3460622","DOIUrl":"https://doi.org/10.1145/3460620.3460622","url":null,"abstract":"In this paper, we present the main ideas behind the development of a system that can be used to deal with meteorological big data. In particular, the system captures data online and downloads it locally onto a MongoDB database. After that, the user can create a particular database and corresponding minable views for analysis. The results provided by the systems are predictive models with the ability to predict some weather-related variables, such as temperature and rainfall. The system has been validated from a triple perspective (usability, experts’ validation, and performance assessment), obtaining satisfactory results. This paper aims to be a brief guide for authors who intend to developed similar systems either in the meteorological field or other domains generating big amounts of data.","PeriodicalId":36824,"journal":{"name":"Data","volume":"22 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77487687","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}
An important observation which figures out when we look into several applications which are the result of applying data science, machine learning, and deep learning techniques is that most of these techniques are based on the concept of measuring similarity between any two vectors. These vectors may act as representatives for objects being considered. Similarity measurement thus gains a great importance in the design of machine learning or deep learning algorithms and techniques. In similar lines, when we are required to carry a supervised or unsupervised learning task, an algorithm is required to carry the task efficiently. Thus, in this paper, our objective is to outline various similarity measures that have been considered for carrying supervised or unsupervised learning tasks and also to throw light on different machine learning algorithms employed for supervised and unsupervised learning tasks from disease classification and prediction point of view and also interdisciplinary domains such as time series analysis, temporal data mining, medical data mining, and anomaly or intrusion detection.
{"title":"A SURVEY ON SIMILARITY MEASURES AND MACHINE LEARNING ALGORITHMS FOR CLASSIFICATION AND PREDICTION","authors":"Sravan kiran Vangipuram, Rajesh Appusamy","doi":"10.1145/3460620.3460755","DOIUrl":"https://doi.org/10.1145/3460620.3460755","url":null,"abstract":"An important observation which figures out when we look into several applications which are the result of applying data science, machine learning, and deep learning techniques is that most of these techniques are based on the concept of measuring similarity between any two vectors. These vectors may act as representatives for objects being considered. Similarity measurement thus gains a great importance in the design of machine learning or deep learning algorithms and techniques. In similar lines, when we are required to carry a supervised or unsupervised learning task, an algorithm is required to carry the task efficiently. Thus, in this paper, our objective is to outline various similarity measures that have been considered for carrying supervised or unsupervised learning tasks and also to throw light on different machine learning algorithms employed for supervised and unsupervised learning tasks from disease classification and prediction point of view and also interdisciplinary domains such as time series analysis, temporal data mining, medical data mining, and anomaly or intrusion detection.","PeriodicalId":36824,"journal":{"name":"Data","volume":"4 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87266536","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}
Gaziza Yelibayeva, A. Sharipbay, G. Bekmanova, A. Omarbekova
This article provides an ontological model of nominative word combinations in the Kazakh language. It is necessary for creation of the automated templates for search of nominative word combinations of the Kazakh language in text corpora. The presented model expands the theory of applied linguistics in the field of extracting information from the text during corpus studies. The results will be used in semantic searches, Q&A systems and in the development of software applications for obtaining knowledge, as well as for training and evaluation of knowledge on the syntax of the Kazakh language in the system of e-learning.
{"title":"Ontology-Based Extraction of Kazakh Language Word Combinations in Natural Language Processing","authors":"Gaziza Yelibayeva, A. Sharipbay, G. Bekmanova, A. Omarbekova","doi":"10.1145/3460620.3460631","DOIUrl":"https://doi.org/10.1145/3460620.3460631","url":null,"abstract":"This article provides an ontological model of nominative word combinations in the Kazakh language. It is necessary for creation of the automated templates for search of nominative word combinations of the Kazakh language in text corpora. The presented model expands the theory of applied linguistics in the field of extracting information from the text during corpus studies. The results will be used in semantic searches, Q&A systems and in the development of software applications for obtaining knowledge, as well as for training and evaluation of knowledge on the syntax of the Kazakh language in the system of e-learning.","PeriodicalId":36824,"journal":{"name":"Data","volume":"9 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89373942","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}
In this paper, we describe the steps we took to access and use one of the data sets available via Amazon Web Services (AWS).
在本文中，我们描述了通过Amazon Web Services (AWS)访问和使用其中一个数据集所采取的步骤。
{"title":"Public Datasets: Access, Download and Cleaning (AWS)","authors":"Mary E. Koone, R. Elmasri","doi":"10.1145/3460620.3460633","DOIUrl":"https://doi.org/10.1145/3460620.3460633","url":null,"abstract":"In this paper, we describe the steps we took to access and use one of the data sets available via Amazon Web Services (AWS).","PeriodicalId":36824,"journal":{"name":"Data","volume":"27 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78355225","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}
Over the last few years, the amount of information that resides on the internet is quickly increasing especially due to the digital transformation era. Social media platforms, moving to the cloud, using the internet of things (IoT) are reasons for this transformation. However, taking advantage of publically available information related to companies and individuals can be useful in many ways. In this paper, an integration process between selected OSINT (Open source intelligence) techniques and ISO 27001 standard under some relevant domains for additional security, is proposed.
{"title":"OSINT Techniques Integration with Risk Assessment ISO/IEC 27001","authors":"Hamzeh Al-Kilani, A. Qusef","doi":"10.1145/3460620.3460736","DOIUrl":"https://doi.org/10.1145/3460620.3460736","url":null,"abstract":"Over the last few years, the amount of information that resides on the internet is quickly increasing especially due to the digital transformation era. Social media platforms, moving to the cloud, using the internet of things (IoT) are reasons for this transformation. However, taking advantage of publically available information related to companies and individuals can be useful in many ways. In this paper, an integration process between selected OSINT (Open source intelligence) techniques and ISO 27001 standard under some relevant domains for additional security, is proposed.","PeriodicalId":36824,"journal":{"name":"Data","volume":"90 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85650725","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}
Challenging annotated video datasets are in huge demand for the researchers and embedded industrials to learn and build an artificial intelligence for detecting, localizing and classifying the objects of interest aimed at various applications under pattern recognition and computer vision domain. It is very significant to produce those annotated sets to the respective communal. This paper focuses on text as annotated data in video for detection, localization, tracking and classification to solve several optical character recognition (OCR) based problems. Text is very essential in understanding the nature of the video because of diverse applications which are in renowned today like video retrieval and searching, driverless cars, industrial goods automation, geocoding and many more. Hence, it is important to understand how to create, prepare and load datasets to make ready for the machine to learn and understand. First, we have applied bilateral filter to preserve the edge information. Then, rotational gradient approach is proposed to detect the text in variable viewpoints. Later, the combination of morphology and contours has applied to generate blobs with bounding box around the detected regions by eradicating quasi text areas. The simulation results have shown better performance than traditional techniques with better detection rate on ICDAR Robust Reading Competition on Text in Video 2013-15 datasets.
{"title":"Data Preprocessing for Learning, Analyzing and Detecting Scene Text Video based on Rotational Gradient","authors":"Manasa Devi Mortha, S. Maddala, V. Raju","doi":"10.1145/3460620.3460621","DOIUrl":"https://doi.org/10.1145/3460620.3460621","url":null,"abstract":"Challenging annotated video datasets are in huge demand for the researchers and embedded industrials to learn and build an artificial intelligence for detecting, localizing and classifying the objects of interest aimed at various applications under pattern recognition and computer vision domain. It is very significant to produce those annotated sets to the respective communal. This paper focuses on text as annotated data in video for detection, localization, tracking and classification to solve several optical character recognition (OCR) based problems. Text is very essential in understanding the nature of the video because of diverse applications which are in renowned today like video retrieval and searching, driverless cars, industrial goods automation, geocoding and many more. Hence, it is important to understand how to create, prepare and load datasets to make ready for the machine to learn and understand. First, we have applied bilateral filter to preserve the edge information. Then, rotational gradient approach is proposed to detect the text in variable viewpoints. Later, the combination of morphology and contours has applied to generate blobs with bounding box around the detected regions by eradicating quasi text areas. The simulation results have shown better performance than traditional techniques with better detection rate on ICDAR Robust Reading Competition on Text in Video 2013-15 datasets.","PeriodicalId":36824,"journal":{"name":"Data","volume":"89 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85963099","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}
Wireless Sensor Network (WSN) enables the digital world to hear, see, and smell the physical world without the interaction of human beings. It is an essential enabler of the Internet of Things (IoT) in many domains. A WSN is a group of a large number of sensor nodes and a base station. The sensor nodes are characterized by their limited processing, storage, and communication capabilities. In addition, they might get deployed in harsh physical environments where reliability is not guaranteed. Because of that, the IoT-enabled WSNs are challenged by the need to determine the trust of the sensor nodes. Thus, many research studies considered the trust of the sensor nodes in all the IoT layers. This paper overviewed the well-known attacks in the field of IoT-enabled WSN. In addition, it reviewed the trust models in the perception and the network layers of IoT. Also, it discussed the limitations and the challenges of the existing trust models to be considered by the researchers.
{"title":"Trust Models in IoT-enabled WSN: A review","authors":"Safaa Hriez, Sufyan Almajali, M. Ayyash","doi":"10.1145/3460620.3460748","DOIUrl":"https://doi.org/10.1145/3460620.3460748","url":null,"abstract":"Wireless Sensor Network (WSN) enables the digital world to hear, see, and smell the physical world without the interaction of human beings. It is an essential enabler of the Internet of Things (IoT) in many domains. A WSN is a group of a large number of sensor nodes and a base station. The sensor nodes are characterized by their limited processing, storage, and communication capabilities. In addition, they might get deployed in harsh physical environments where reliability is not guaranteed. Because of that, the IoT-enabled WSNs are challenged by the need to determine the trust of the sensor nodes. Thus, many research studies considered the trust of the sensor nodes in all the IoT layers. This paper overviewed the well-known attacks in the field of IoT-enabled WSN. In addition, it reviewed the trust models in the perception and the network layers of IoT. Also, it discussed the limitations and the challenges of the existing trust models to be considered by the researchers.","PeriodicalId":36824,"journal":{"name":"Data","volume":"21 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86455099","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}
Medical simulations in virtual reality (VR) offer a personalized learning environment that can be structured and adapted to various modes of learning in ways that conventional teaching can not offer. There is an increasing interest in using VR for training and learning. The use of VR in medical training, without requiring a real human being, will promote an effective medical learning process. The software helps learners to adapt to various types of learning in ways that are not suitable in conventional teaching. This paper presents VR and its important usages in education and healthcare and the development of our prototype 3D First Aid VR. Two teaching modules are presented in this prototype: a tutorial which explains the cause and symptoms of a seizure, and training which is used to train first aid in a 3D environment. The two modules were presented in the form of a 3D model kitchen, with a character having a seizure in the immersive environment, and viewed with Oculus Quest. This paper will be useful for researchers and developers in the field of VR.
{"title":"Healthcare Training Application: 3D First Aid Virtual Reality","authors":"Narmeen Al-Hiyari, S. Jusoh","doi":"10.1145/3460620.3460741","DOIUrl":"https://doi.org/10.1145/3460620.3460741","url":null,"abstract":"Medical simulations in virtual reality (VR) offer a personalized learning environment that can be structured and adapted to various modes of learning in ways that conventional teaching can not offer. There is an increasing interest in using VR for training and learning. The use of VR in medical training, without requiring a real human being, will promote an effective medical learning process. The software helps learners to adapt to various types of learning in ways that are not suitable in conventional teaching. This paper presents VR and its important usages in education and healthcare and the development of our prototype 3D First Aid VR. Two teaching modules are presented in this prototype: a tutorial which explains the cause and symptoms of a seizure, and training which is used to train first aid in a 3D environment. The two modules were presented in the form of a 3D model kitchen, with a character having a seizure in the immersive environment, and viewed with Oculus Quest. This paper will be useful for researchers and developers in the field of VR.","PeriodicalId":36824,"journal":{"name":"Data","volume":"62 1","pages":""},"PeriodicalIF":2.6,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87050009","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：