Mohammad Kchouri, Norharyati Harum, Hussein Hazimeh, Ali Obeid
Falling is a critical issue for disabled people, and it leads to potentially serious injuries and death. Smart fall detection is a technology that depends on sensors and auxiliary devices that seek to improve the quality of life and enhance the lifestyle of disabled people. So far, the most widely used fall prediction methods collect data from inertial measurement unit (IMU) sensors. In addition, they use thresholds to identify falls based on artificial experiences or machine learning (ML) algorithms. Nonetheless, these approaches still require extensive classification and calibration. In this paper, we suggest a new technique to detect falls by combining Fuzzy Logic (FL) and Support Vector Machine (SVM). The FL model is built by using a fuzzy membership function along with the input dataset to obtain the intermediate output. Because combining these two algorithms is not an easy task, we leverage SVM with a kernel comprised of a fuzzy membership function and thus build a new model known as FSVM. Besides, the hyperplane of the SVM is used as the separating plane to replace the traditional threshold method for detecting falling Activities of Daily Living (ADLs) on a comprehensive dataset containing simulated falling ADLs, non-falling ADLs, and scripted ADLs, including falling ADLs and unscripted ADLs performed by volunteers with our designed device. The results show that no false-positive rate had been triggered, and 100% specificity was achieved for ADL. An overall accuracy of about 99.87% in detecting the fall function was obtained. Furthermore, the overall sensitivity of 100% with no false negative rate obtained was achieved by implementing the proposed method. The attained results validate that our introduced method can effectively learn from features extracted from a multiphase fall model.
{"title":"Smart Fall Detection by Enhanced SVM with Fuzzy Logic Membership Function","authors":"Mohammad Kchouri, Norharyati Harum, Hussein Hazimeh, Ali Obeid","doi":"10.3897/jucs.91399","DOIUrl":"https://doi.org/10.3897/jucs.91399","url":null,"abstract":"Falling is a critical issue for disabled people, and it leads to potentially serious injuries and death. Smart fall detection is a technology that depends on sensors and auxiliary devices that seek to improve the quality of life and enhance the lifestyle of disabled people. So far, the most widely used fall prediction methods collect data from inertial measurement unit (IMU) sensors. In addition, they use thresholds to identify falls based on artificial experiences or machine learning (ML) algorithms. Nonetheless, these approaches still require extensive classification and calibration. In this paper, we suggest a new technique to detect falls by combining Fuzzy Logic (FL) and Support Vector Machine (SVM). The FL model is built by using a fuzzy membership function along with the input dataset to obtain the intermediate output. Because combining these two algorithms is not an easy task, we leverage SVM with a kernel comprised of a fuzzy membership function and thus build a new model known as FSVM. Besides, the hyperplane of the SVM is used as the separating plane to replace the traditional threshold method for detecting falling Activities of Daily Living (ADLs) on a comprehensive dataset containing simulated falling ADLs, non-falling ADLs, and scripted ADLs, including falling ADLs and unscripted ADLs performed by volunteers with our designed device. The results show that no false-positive rate had been triggered, and 100% specificity was achieved for ADL. An overall accuracy of about 99.87% in detecting the fall function was obtained. Furthermore, the overall sensitivity of 100% with no false negative rate obtained was achieved by implementing the proposed method. The attained results validate that our introduced method can effectively learn from features extracted from a multiphase fall model. ","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135343724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
César Domínguez, Jónathan Heras, Eloy Mata, Vico Pascual, Lucas Fernández-Cedrón, Marcos Martínez-Lanchares, Jon Pellejero-Espinosa, Antonio Rubio-Loscertales, Carlos Tarragona-Pérez
In waste recycling plants, measuring the waste volume and weight at the beginning of the treatment process is key for a better management of resources. This task can be conducted by using orthophoto images, but it is necessary to remove from those images the objects, such as containers or trucks, that are not involved in the measurement process. This work proposes the application of deep learning for the semantic segmentation of those irrelevant objects. Several deep architectures are trained and compared, while three semi-supervised learning methods (PseudoLabeling, Distillation and Model Distillation) are proposed to take advantage of non-annotated images. In these experiments, the U-net++ architecture with an EfficientNetB3 backbone, trained with the set of labelled images, achieves the best overall multi Dice score of 91.23%. The application of semi-supervised learning methods further boosts the segmentation accuracy in a range between 1.31% and 2.59%, on average.
{"title":"Semi-Supervised Semantic Segmentation for Identification of Irrelevant Objects in a Waste Recycling Plant","authors":"César Domínguez, Jónathan Heras, Eloy Mata, Vico Pascual, Lucas Fernández-Cedrón, Marcos Martínez-Lanchares, Jon Pellejero-Espinosa, Antonio Rubio-Loscertales, Carlos Tarragona-Pérez","doi":"10.3897/jucs.87643","DOIUrl":"https://doi.org/10.3897/jucs.87643","url":null,"abstract":"In waste recycling plants, measuring the waste volume and weight at the beginning of the treatment process is key for a better management of resources. This task can be conducted by using orthophoto images, but it is necessary to remove from those images the objects, such as containers or trucks, that are not involved in the measurement process. This work proposes the application of deep learning for the semantic segmentation of those irrelevant objects. Several deep architectures are trained and compared, while three semi-supervised learning methods (PseudoLabeling, Distillation and Model Distillation) are proposed to take advantage of non-annotated images. In these experiments, the U-net++ architecture with an EfficientNetB3 backbone, trained with the set of labelled images, achieves the best overall multi Dice score of 91.23%. The application of semi-supervised learning methods further boosts the segmentation accuracy in a range between 1.31% and 2.59%, on average.","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135831710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-01-01DOI: 10.3217/jucs-022-05-0709
E. Kalampokis, Areti Karamanou, E. Tambouris, K. Tarabanis
{"title":"Applying Brand Equity Theory to Understand the Opinion of Consumers in Social Media","authors":"E. Kalampokis, Areti Karamanou, E. Tambouris, K. Tarabanis","doi":"10.3217/jucs-022-05-0709","DOIUrl":"https://doi.org/10.3217/jucs-022-05-0709","url":null,"abstract":"","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"122 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87635564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2010-09-01DOI: 10.3217/JUCS-016-17-2475
José Alfonso Aguilar Calderón, Irene Garrigós Fernández, José Norberto Mazón López, Juan Carlos Trujillo Mondéjar
Web designers usually ignore how to model real user expectations and goals, mainly due to the large and heterogeneous audience of the Web. This fact leads to websites which are difficult to comprehend by visitors and complex to maintain by designers. In order to ameliorate this scenario, an approach for using the i* modeling framework in Web engineering has been developed in this paper. Furthermore, due to the fact that most of the existing Web engineering approaches do not consider how to derive conceptual models of the Web application from requirements analysis we also propose the use of MDA (Model Driven Architecture) in Web engineering for: (i) the definition of the requirements of a Web application in a Computational Independent Model (CIM), (ii) the description of Platform Independent Models (PIMs), and (iii) the definition of a set of QVT (Query/View/Transformation) transformations for the derivation of PIMs from requirements specification (CIM), thus to enable the automatic generation of Web applications. Finally, we include a sample of our approach in order to show its applicability and we describe a prototype tool as a proof of concept of our research.
{"title":"An MDA approach for goal-oriented requirement analysis in Web engineering","authors":"José Alfonso Aguilar Calderón, Irene Garrigós Fernández, José Norberto Mazón López, Juan Carlos Trujillo Mondéjar","doi":"10.3217/JUCS-016-17-2475","DOIUrl":"https://doi.org/10.3217/JUCS-016-17-2475","url":null,"abstract":"Web designers usually ignore how to model real user expectations and goals, mainly due to the large and heterogeneous audience of the Web. This fact leads to websites which are difficult to comprehend by visitors and complex to maintain by designers. In order to ameliorate this scenario, an approach for using the i* modeling framework in Web engineering has been developed in this paper. Furthermore, due to the fact that most of the existing Web engineering approaches do not consider how to derive conceptual models of the Web application from requirements analysis we also propose the use of MDA (Model Driven Architecture) in Web engineering for: (i) the definition of the requirements of a Web application in a Computational Independent Model (CIM), (ii) the description of Platform Independent Models (PIMs), and (iii) the definition of a set of QVT (Query/View/Transformation) transformations for the derivation of PIMs from requirements specification (CIM), thus to enable the automatic generation of Web applications. Finally, we include a sample of our approach in order to show its applicability and we describe a prototype tool as a proof of concept of our research.","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"57 1","pages":"2475-2494"},"PeriodicalIF":1.0,"publicationDate":"2010-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78634712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2009-01-01DOI: 10.4230/OASICS.CCA.2009.2276
K. Weihrauch
This article continues the study of computable elementary topology started in (Weihrauch, Grubba 2009). We introduce a number of computable versions of the topological $T_0$ to $T_3$ separation axioms and solve their logical relation completely. In particular, it turns out that computable $T_1$ is equivalent to computable $T_2$. The strongest axiom $SCT_3$ is used in (Grubba, Schroeder, Weihrauch 2007) to construct a computable metric.
{"title":"Computable Separation in Topology, from T_0 to T_3","authors":"K. Weihrauch","doi":"10.4230/OASICS.CCA.2009.2276","DOIUrl":"https://doi.org/10.4230/OASICS.CCA.2009.2276","url":null,"abstract":"This article continues the study of computable elementary topology started in (Weihrauch, Grubba 2009). We introduce a number of computable versions of the topological $T_0$ to $T_3$ separation axioms and solve their logical relation completely. In particular, it turns out that computable $T_1$ is equivalent to computable $T_2$. The strongest axiom $SCT_3$ is used in (Grubba, Schroeder, Weihrauch 2007) to construct a computable metric.","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"142 1","pages":"2733-2753"},"PeriodicalIF":1.0,"publicationDate":"2009-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78528185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2008-01-01DOI: 10.6084/M9.FIGSHARE.96670.V1
K. Brito, V. Garcia, E. Almeida, S. Meira
Nowadays software systems are essential to the environment of most organizations, and their maintenance is a key point to support business dynamics. Thus, reverse engineering legacy systems for knowledge reuse has become a major concern in software industry. This article, based on a survey about reverse engineering tools, discusses a set of functional and non- functional requirements for an effective tool for reverse engineering, and observes that current tools only partly support these requirements. In addition, we define new requirements, based on our group's experience and industry feedback, and present the architecture and implementation of LIFT: a Legacy InFormation retrieval Tool, developed based on these demands. Furthermore, we discuss the compliance of LIFT with the defined requirements. Finally, we applied the LIFT in a reverse engineering project of a 210KLOC NATURAL/ADABAS system of a financial institution and analyzed its effectiveness and scalability, comparing data with previous similar projects performed by the same institution.
{"title":"LIFT – A Legacy InFormation Retrieval Tool","authors":"K. Brito, V. Garcia, E. Almeida, S. Meira","doi":"10.6084/M9.FIGSHARE.96670.V1","DOIUrl":"https://doi.org/10.6084/M9.FIGSHARE.96670.V1","url":null,"abstract":"Nowadays software systems are essential to the environment of most organizations, and their maintenance is a key point to support business dynamics. Thus, reverse engineering legacy systems for knowledge reuse has become a major concern in software industry. This article, based on a survey about reverse engineering tools, discusses a set of functional and non- functional requirements for an effective tool for reverse engineering, and observes that current tools only partly support these requirements. In addition, we define new requirements, based on our group's experience and industry feedback, and present the architecture and implementation of LIFT: a Legacy InFormation retrieval Tool, developed based on these demands. Furthermore, we discuss the compliance of LIFT with the defined requirements. Finally, we applied the LIFT in a reverse engineering project of a 210KLOC NATURAL/ADABAS system of a financial institution and analyzed its effectiveness and scalability, comparing data with previous similar projects performed by the same institution.","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"12 1","pages":"1256-1284"},"PeriodicalIF":1.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87160181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2008-01-01DOI: 10.3217/JUCS-014-05-0653
Laura Rodríguez de Lope López, Klaus Dietrich Hackbarth Planeta
The European Regulator Group (ERG) defines Bitstream Access Service as a wholesale service offered by a broadband network operator with significant market power to an Internet Service Provider, and identifies it as a market subject to regulation. This paper develops a cost model for the Bitstream Access Service under xDSL technology, following the recommendations of the ERG, considering different user classes with differentiated QoS requirements. For this purpose, three traffic engineering methods are analysed: separate virtual tunnels, over-engineering and priority queuing techniques.
{"title":"Cost model for bitstream access services with QoS parameters","authors":"Laura Rodríguez de Lope López, Klaus Dietrich Hackbarth Planeta","doi":"10.3217/JUCS-014-05-0653","DOIUrl":"https://doi.org/10.3217/JUCS-014-05-0653","url":null,"abstract":"The European Regulator Group (ERG) defines Bitstream Access Service as a wholesale service offered by a broadband network operator with significant market power to an Internet Service Provider, and identifies it as a market subject to regulation. This paper develops a cost model for the Bitstream Access Service under xDSL technology, following the recommendations of the ERG, considering different user classes with differentiated QoS requirements. For this purpose, three traffic engineering methods are analysed: separate virtual tunnels, over-engineering and priority queuing techniques.","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"102 1","pages":"653-672"},"PeriodicalIF":1.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82131563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1998-11-01DOI: 10.1080/10157891.1998.10462570
D. Ferens, D. Christensen
Abstract There are many sophisticated parametric models for estimating the size, cost, and schedule of software projects. In general, the predictive accuracy of these models is no better than within 25 percent of actual cost or schedule, about one half of the time (Thibodeau, 1981; IIT Research Institute, 1988). Several authors assert that a model's predictive accuracy can be improved by calibrating (adjusting) its default parameters to a specific environment (Kemerer, 1987; Van Genuchten and Koolen, 1991; Andolfi et al. 1996). This paper reports the results of a long-term project that tests this assertion.
有许多复杂的参数模型用于估算软件项目的规模、成本和进度。一般来说，这些模型的预测精度不超过实际成本或进度的25%，约占时间的一半(Thibodeau, 1981;印度理工学院研究所，1988年)。一些作者断言，模型的预测精度可以通过校准(调整)其默认参数来提高特定环境(Kemerer, 1987;Van Genuchten and Koolen, 1991;Andolfi et al. 1996)。本文报告了对这一断言进行检验的一个长期项目的结果。
{"title":"Calibrating Software Cost Models to Department of Defense DatabasesA Review of Ten Studies","authors":"D. Ferens, D. Christensen","doi":"10.1080/10157891.1998.10462570","DOIUrl":"https://doi.org/10.1080/10157891.1998.10462570","url":null,"abstract":"Abstract There are many sophisticated parametric models for estimating the size, cost, and schedule of software projects. In general, the predictive accuracy of these models is no better than within 25 percent of actual cost or schedule, about one half of the time (Thibodeau, 1981; IIT Research Institute, 1988). Several authors assert that a model's predictive accuracy can be improved by calibrating (adjusting) its default parameters to a specific environment (Kemerer, 1987; Van Genuchten and Koolen, 1991; Andolfi et al. 1996). This paper reports the results of a long-term project that tests this assertion.","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"29 1","pages":""},"PeriodicalIF":1.0,"publicationDate":"1998-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79102197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-01-01DOI: 10.1007/978-3-642-80350-5_5
Cristian S. Calude
{"title":"What is a Random String","authors":"Cristian S. Calude","doi":"10.1007/978-3-642-80350-5_5","DOIUrl":"https://doi.org/10.1007/978-3-642-80350-5_5","url":null,"abstract":"","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"18 1","pages":"48-66"},"PeriodicalIF":1.0,"publicationDate":"1996-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81333190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1996-01-01DOI: 10.1007/978-3-642-80350-5_53
Rohan F. M. Aranha, C. Rangan
{"title":"An Efficient Distributed Algorithm For st-numbering The Vertices Of A Biconnected Graph","authors":"Rohan F. M. Aranha, C. Rangan","doi":"10.1007/978-3-642-80350-5_53","DOIUrl":"https://doi.org/10.1007/978-3-642-80350-5_53","url":null,"abstract":"","PeriodicalId":54757,"journal":{"name":"Journal of Universal Computer Science","volume":"54 1","pages":"633-651"},"PeriodicalIF":1.0,"publicationDate":"1996-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73506053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：