Digital images often contain “noise” which takes away their clarity and sharpness. Most of the existing denoising algorithms do not offer the best solution because there are difficulties such as removing strong noise while leaving the features and other details of the image intact. Faced with the problem of denoising, we tried solving it with a Convolutional Neural Network architecture called the “U-Net”. This paper deals with the training of a U-Net to remove 3 different kinds of noise: Gaussian, Blockiness, and Camera shake. Our results indicate the effectiveness of U-Net in denoising images while leaving their features and other details intact
{"title":"EFFECTIVENESS OF U-NET IN DENOISING RGB IMAGES","authors":"Rina Komatsu, T. Gonsalves","doi":"10.5121/CSIT.2019.90201","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90201","url":null,"abstract":"Digital images often contain “noise” which takes away their clarity and sharpness. Most of the\u0000existing denoising algorithms do not offer the best solution because there are difficulties such as removing strong noise while leaving the features and other details of the image intact. Faced with the problem of denoising, we tried solving it with a Convolutional Neural Network\u0000architecture called the “U-Net”. This paper deals with the training of a U-Net to remove 3 different kinds of noise: Gaussian, Blockiness, and Camera shake. Our results indicate the effectiveness of U-Net in denoising images while leaving their features and other details intact","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123498126","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}
Moving object detection is one of the fundamental technologies necessary to realize autonomous driving. In this study, we propose the prediction of an in-vehicle camera image by Generative Adversarial Network (GAN). From the past images input to the system, it predicts the future images at the output. By predicting the motion of a moving object, it can predict the destination of the moving object. The proposed model can predict the motion of moving objects such as cars, bicycles, and pedestrians.
{"title":"IN-VEHICLE CAMERA IMAGES PREDICTION BY GENERATIVE ADVERSARIAL NETWORK","authors":"J. Watanabe, T. Gonsalves","doi":"10.5121/CSIT.2019.90205","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90205","url":null,"abstract":"Moving object detection is one of the fundamental technologies necessary to realize autonomous driving. In this study, we propose the prediction of an in-vehicle camera image by Generative Adversarial Network (GAN). From the past images input to the system, it predicts the future images at the output. By predicting the motion of a moving object, it can predict the destination of the moving object. The proposed model can predict the motion of moving objects such as cars, bicycles, and pedestrians.","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124344450","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 social media platforms, hate speech can be a reason of “cyber conflict” which can affect social life in both of individual-level and country-level. Hateful and antagonistic content propagated via social networks has the potential to cause harm and suffering on an individual basis and lead to social tension and disorder beyond cyber space. However, social networks cannot control all the content that users post. For this reason, there is a demand for automatic detection of hate speech. This demand particularly raises when the content is written in complex languages (e.g. Arabic). Arabic text is known with its challenges, complexity and scarcity of its resources. This paper will present a background on hate speech and its related detection approaches. In addition, the recent contributions on hate speech and its related anti-social behaviour topics will be reviewed. Finally, challenges and recommendations for the Arabic hate speech detection problem will be presented.
{"title":"DETECTION OF HATE SPEECH IN SOCIAL NETWORKS: A SURVEY ON MULTILINGUAL CORPUS","authors":"A. Al-Hassan, Hmood Al-Dossari","doi":"10.5121/CSIT.2019.90208","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90208","url":null,"abstract":"In social media platforms, hate speech can be a reason of “cyber conflict” which can affect social life in both of individual-level and country-level. Hateful and antagonistic content propagated via social networks has the potential to cause harm and suffering on an individual basis and lead to social tension and disorder beyond cyber space. However, social networks cannot control all the content that users post. For this reason, there is a demand for automatic detection of hate speech. This demand particularly raises when the content is written in complex languages (e.g. Arabic). Arabic text is known with its challenges, complexity and scarcity of its resources. This paper will present a background on hate speech and its related detection approaches. In addition, the recent contributions on hate speech and its related anti-social behaviour topics will be reviewed. Finally, challenges and recommendations for the Arabic hate speech detection problem will be presented.","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122489986","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}
Soft-as-a-Service (SaaS) is a software delivery model that contains composition, development and execution on cloud platforms. And massive SaaS applications need verifying before deployed. To get the verify results of a large quantity of applications in a tolerate time, verify algebra (VA) is used to cut down the number of combinations to be verified. VA is an effective way to acquire the verify statue by using previous results. In VA, the verify result is calculated without knowing the process of verification. In this way, the verification task can be distributed to servers and executed in any order. This paper proposes method called component disassembly tree to decompose a complex SaaS application. And designs a parallel verification framework in cloud environment. The Optimization of execution is discussed. The proposed parallel schema is simulated in MapReduce.
{"title":"PARALLEL VERIFICATION EXECUTION WITH VERIFY ALGEBRA IN A CLOUD ENVIRONMENT","authors":"Kan Luo, Siyuan Wang, An Wei, Wei Yu, Kai Hu","doi":"10.5121/CSIT.2019.90209","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90209","url":null,"abstract":"Soft-as-a-Service (SaaS) is a software delivery model that contains composition, development and execution on cloud platforms. And massive SaaS applications need verifying before deployed. To get the verify results of a large quantity of applications in a tolerate time, verify algebra (VA) is used to cut down the number of combinations to be verified. VA is an effective way to acquire the verify statue by using previous results. In VA, the verify result is calculated without knowing the process of verification. In this way, the verification task can be distributed to servers and executed in any order. This paper proposes method called component disassembly tree to decompose a complex SaaS application. And designs a parallel verification framework in cloud environment. The Optimization of execution is discussed. The proposed parallel schema is simulated in MapReduce.","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116599207","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 demonstrate how regression curves can be used to recognize 2D non-rigid handwritten shapes. Each shape is represented by a set of non-overlapping uniformly distributed landmarks. The underlying models utilize 2nd order of polynomials to model shapes within a training set. To estimate the regression models, we need to extract the required coefficients which describe the variations for a set of shape class. Hence, a least square method is used to estimate such modes. We proceed then, by training these coefficients using the apparatus Expectation Maximization algorithm. Recognition is carried out by finding the least error landmarks displacement with respect to the model curves. Handwritten isolated Arabic characters are used to evaluate our approach.
{"title":"MIXTURES OF REGRESSION CURVE MODELS FOR ARABIC CHARACTER RECOGNITION","authors":"Abdullah A. Al-Shaher","doi":"10.5121/CSIT.2019.90207","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90207","url":null,"abstract":"In this paper, we demonstrate how regression curves can be used to recognize 2D non-rigid handwritten shapes. Each shape is represented by a set of non-overlapping uniformly distributed landmarks. The underlying models utilize 2nd order of polynomials to model shapes within a training set. To estimate the regression models, we need to extract the required coefficients which describe the variations for a set of shape class. Hence, a least square method is used to estimate such modes. We proceed then, by training these coefficients using the apparatus Expectation Maximization algorithm. Recognition is carried out by finding the least error landmarks displacement with respect to the model curves. Handwritten isolated Arabic characters are used to evaluate our approach.","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125900274","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}
The role of any variable is interpreted as the required task or performance of it in any part of a program. This role contributes to the easy understanding of the program and thus formulates it clearly and unambiguously. Many novice programmers face various difficulties in understanding programming, especially Object Oriented Programming. This research adopts the design of a visualization tool which includes visual model that shows the role of the reference variable (an object) within a Java program to enhance comprehension understanding for novice programmers. The model enables them to interact and thus formulate an objectoriented program in an intuitive and clear way. Based on the actual experimentation, the effectiveness of this model is improved and the importance of this research in the field of object programming is demonstrated.
{"title":"THE EFFECT OF VISUALIZING ROLE OF VARIABLE IN OBJECT ORIENTED PROGRAMMING UNDERSTANDING","authors":"Mabroukah Amarif, Sakeenah Ahmed","doi":"10.5121/CSIT.2019.90202","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90202","url":null,"abstract":"The role of any variable is interpreted as the required task or performance of it in any part of a program. This role contributes to the easy understanding of the program and thus formulates it clearly and unambiguously. Many novice programmers face various difficulties in understanding programming, especially Object Oriented Programming. This research adopts the design of a visualization tool which includes visual model that shows the role of the reference variable (an object) within a Java program to enhance comprehension understanding for novice programmers. The model enables them to interact and thus formulate an objectoriented program in an intuitive and clear way. Based on the actual experimentation, the effectiveness of this model is improved and the importance of this research in the field of object programming is demonstrated.","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121015103","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}
The shortest path between two points is one of the greatest challenges facing the researchers nowadays. There are many algorithms and mechanisms that are designed and still all according to the certain approach and adopted structural. The most famous and widely used algorithm is Dijkstra algorithm, which is characterized by finding the shortest path between two points through graph data structure. It’s obvious to find the implicit path from the solution path; but the searching time varies according to the type of data structure used to store the solution path. This paper improves the development of Dijkstra algorithm using linked hash map data structure for storing the produced solution shortest path, and then investigates the subsequent implicit paths within this data structure. The result show that the searching time through the given data structure is much better than restart the algorithm again to search for the same path.
{"title":"THE IMPLICIT PATH COST OPTIMIZATION IN DIJKSTRA ALGORITHM USING HASH MAP DATA STRUCTURE","authors":"Mabroukah Amarif, Ibtusam Alashoury","doi":"10.5121/CSIT.2019.90204","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90204","url":null,"abstract":"The shortest path between two points is one of the greatest challenges facing the researchers nowadays. There are many algorithms and mechanisms that are designed and still all according to the certain approach and adopted structural. The most famous and widely used algorithm is Dijkstra algorithm, which is characterized by finding the shortest path between two points through graph data structure. It’s obvious to find the implicit path from the solution path; but the searching time varies according to the type of data structure used to store the solution path. This paper improves the development of Dijkstra algorithm using linked hash map data structure for storing the produced solution shortest path, and then investigates the subsequent implicit paths within this data structure. The result show that the searching time through the given data structure is much better than restart the algorithm again to search for the same path.","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126051503","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}
Ahmad A. Al-Hajji, Fatimah M. AlSuhaibani, N. Alharbi
Artificial Intelligence (AI) is one of computer science branches and is used to solve problems with symbolic reasoning. Expert systems (ESs) are one of the prominent research domains of AI. We developed declarative, online procedural rule-based expert system models for psychological diseases diagnosis and classification. The constructed system exploited computer as an intelligent and deductive tool. This system diagnoses and treats more than four types of psychiatric diseases, i.e., depression, anxiety disorder, obsessive-compulsive disorder, and hysteria. The system helps psychology practitioner and doctors to diagnose the condition of a patient efficiently and in short time. It is also very useful for the patients who cannot go to a doctor because they cannot afford the cast, or they do not have a psychological clinic in their area, or they are ashamed of discussing their situation with a doctor. The system consists of program codes that make a logic decision to classify the problem of the patient. The methodology for developing the declarative model was based on the backward chaining, also called goal-driven reasoning, where knowledge is represented by a set of IF-THEN production rules. The declarative programs were written in the PROLOG. While the design of the procedural model was based on using common languages like PHP, JavaScript, CSS, and HTML. The user of the system will enter the symptoms of the patients through the user interface and the program executes. Then the program links the symptoms to the pre-programmed psychological diseases, and will classify the disease and recommend treatment.
{"title":"ONLINE KNOWLEDGE-BASED EXPERT SYSTEM (KBES) FOR PSYCHOLOGICAL DISEASES DIAGNOSIS","authors":"Ahmad A. Al-Hajji, Fatimah M. AlSuhaibani, N. Alharbi","doi":"10.5121/CSIT.2019.90206","DOIUrl":"https://doi.org/10.5121/CSIT.2019.90206","url":null,"abstract":"Artificial Intelligence (AI) is one of computer science branches and is used to solve problems with symbolic reasoning. Expert systems (ESs) are one of the prominent research domains of AI. We developed declarative, online procedural rule-based expert system models for psychological diseases diagnosis and classification. The constructed system exploited computer as an intelligent and deductive tool. This system diagnoses and treats more than four types of psychiatric diseases, i.e., depression, anxiety disorder, obsessive-compulsive disorder, and hysteria. The system helps psychology practitioner and doctors to diagnose the condition of a patient efficiently and in short time. It is also very useful for the patients who cannot go to a doctor because they cannot afford the cast, or they do not have a psychological clinic in their area, or they are ashamed of discussing their situation with a doctor. The system consists of program codes that make a logic decision to classify the problem of the patient. The methodology for developing the declarative model was based on the backward chaining, also called goal-driven reasoning, where knowledge is represented by a set of IF-THEN production rules. The declarative programs were written in the PROLOG. While the design of the procedural model was based on using common languages like PHP, JavaScript, CSS, and HTML. The user of the system will enter the symptoms of the patients through the user interface and the program executes. Then the program links the symptoms to the pre-programmed psychological diseases, and will classify the disease and recommend treatment.","PeriodicalId":251548,"journal":{"name":"Computer Science & Information Technology(CS & IT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130986132","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：