- Zheng Xie;
We conduct a survival analysis for the viewing durations of massive open online courses. The hazard function of the empirical duration data presents as a bathtub curve with the Lindy effect in its tail. To understand the evolutionary mechanisms underlying these features, we categorize learners into two classes based on their different distributions of viewing durations, namely lognormal distribution and power law with exponential cutoff.Two random differential equations are provided to describe the growth patterns of viewing durations for the two classes respectively. The expected duration change rate of the learners featured by lognormal distribution is supposed to be dependent on their past duration, and that of the remainder of learners is supposed to be inversely proportional to time. Solutions to the equations predict the features of viewing duration distributions, and those of the hazard function. The equations also reveal the features of memory and memorylessness for the respective viewing behaviors of the two classes.
2020年03期 v.25 313-324页 [查看摘要][在线阅读][下载 7380K] [下载次数：133 ] |[网刊下载次数：0 ] |[引用频次：11 ] |[阅读次数：0 ] - Zheng Xie;
We conduct a survival analysis for the viewing durations of massive open online courses. The hazard function of the empirical duration data presents as a bathtub curve with the Lindy effect in its tail. To understand the evolutionary mechanisms underlying these features, we categorize learners into two classes based on their different distributions of viewing durations, namely lognormal distribution and power law with exponential cutoff.Two random differential equations are provided to describe the growth patterns of viewing durations for the two classes respectively. The expected duration change rate of the learners featured by lognormal distribution is supposed to be dependent on their past duration, and that of the remainder of learners is supposed to be inversely proportional to time. Solutions to the equations predict the features of viewing duration distributions, and those of the hazard function. The equations also reveal the features of memory and memorylessness for the respective viewing behaviors of the two classes.
2020年03期 v.25 313-324页 [查看摘要][在线阅读][下载 7380K] [下载次数：133 ] |[网刊下载次数：0 ] |[引用频次：11 ] |[阅读次数：0 ] - Zheng Xie;
We conduct a survival analysis for the viewing durations of massive open online courses. The hazard function of the empirical duration data presents as a bathtub curve with the Lindy effect in its tail. To understand the evolutionary mechanisms underlying these features, we categorize learners into two classes based on their different distributions of viewing durations, namely lognormal distribution and power law with exponential cutoff.Two random differential equations are provided to describe the growth patterns of viewing durations for the two classes respectively. The expected duration change rate of the learners featured by lognormal distribution is supposed to be dependent on their past duration, and that of the remainder of learners is supposed to be inversely proportional to time. Solutions to the equations predict the features of viewing duration distributions, and those of the hazard function. The equations also reveal the features of memory and memorylessness for the respective viewing behaviors of the two classes.
2020年03期 v.25 313-324页 [查看摘要][在线阅读][下载 7380K] [下载次数：133 ] |[网刊下载次数：0 ] |[引用频次：11 ] |[阅读次数：0 ] - Tun Li;Wanwei Liu;Juan Chen;Xiaoguang Mao;Xinjun Mao;
To enhance training in software development, we argue that students of software engineering should be exposed to software development activities early in the curriculum. This entails meeting the challenge of engaging students in software development before they take the software engineering course. In this paper, we propose a method to connect courses in the software engineering curriculum by setting comprehensive development projects to students in prerequisite courses for software development. Using the Discrete Mathematics(DM) course as an example, we describe the implementation of the proposed method and teaching practices using several practical and comprehensive projects derived from topics in discrete mathematics. Detailed descriptions of the sample projects, their application, and training results are given. Results and lessons learned from applying these practices show that it is a promising way to connect courses in the software engineering curriculum.
2020年03期 v.25 325-335页 [查看摘要][在线阅读][下载 944K] [下载次数：58 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Tun Li;Wanwei Liu;Juan Chen;Xiaoguang Mao;Xinjun Mao;
To enhance training in software development, we argue that students of software engineering should be exposed to software development activities early in the curriculum. This entails meeting the challenge of engaging students in software development before they take the software engineering course. In this paper, we propose a method to connect courses in the software engineering curriculum by setting comprehensive development projects to students in prerequisite courses for software development. Using the Discrete Mathematics(DM) course as an example, we describe the implementation of the proposed method and teaching practices using several practical and comprehensive projects derived from topics in discrete mathematics. Detailed descriptions of the sample projects, their application, and training results are given. Results and lessons learned from applying these practices show that it is a promising way to connect courses in the software engineering curriculum.
2020年03期 v.25 325-335页 [查看摘要][在线阅读][下载 944K] [下载次数：58 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Tun Li;Wanwei Liu;Juan Chen;Xiaoguang Mao;Xinjun Mao;
To enhance training in software development, we argue that students of software engineering should be exposed to software development activities early in the curriculum. This entails meeting the challenge of engaging students in software development before they take the software engineering course. In this paper, we propose a method to connect courses in the software engineering curriculum by setting comprehensive development projects to students in prerequisite courses for software development. Using the Discrete Mathematics(DM) course as an example, we describe the implementation of the proposed method and teaching practices using several practical and comprehensive projects derived from topics in discrete mathematics. Detailed descriptions of the sample projects, their application, and training results are given. Results and lessons learned from applying these practices show that it is a promising way to connect courses in the software engineering curriculum.
2020年03期 v.25 325-335页 [查看摘要][在线阅读][下载 944K] [下载次数：58 ] |[网刊下载次数：0 ] |[引用频次：2 ] |[阅读次数：0 ] - Yimin Wen;Ye Tian;Boxi Wen;Qing Zhou;Guoyong Cai;Shaozhong Liu;
Recently, Massive Open Online Courses(MOOCs) have become a major online learning methodology for millions of people worldwide. However, the dropout rates from several current MOOCs are high. Usually, dropout prediction aims to predict whether a learner will exhibit learning behaviors during several consecutive days in the future. Therefore, the information related to the learning behaviors of a learner in several consecutive days should be considered. After in-depth analysis of the learning behavior patterns of the MOOC learners, this study reports that learners often exhibit similar learning behaviors on several consecutive days, i.e., the learning status of a learner for the subsequent day is likely to be similar to that for the previous day. Based on this characteristic of MOOC learning,this study proposes a new simple feature matrix for keeping information related to the local correlation of learning behaviors and a new Convolutional Neural Network(CNN) model for predicting the dropout. Extensive experimental validations illustrate that the local correlation of learning behaviors should not be neglected. The proposed CNN model considers this characteristic and improves the dropout prediction accuracy. Furthermore, the proposed model can be used to predict dropout temporally and early when sufficient data are collected.
2020年03期 v.25 336-347页 [查看摘要][在线阅读][下载 2211K] [下载次数：91 ] |[网刊下载次数：0 ] |[引用频次：18 ] |[阅读次数：0 ] - Yimin Wen;Ye Tian;Boxi Wen;Qing Zhou;Guoyong Cai;Shaozhong Liu;
Recently, Massive Open Online Courses(MOOCs) have become a major online learning methodology for millions of people worldwide. However, the dropout rates from several current MOOCs are high. Usually, dropout prediction aims to predict whether a learner will exhibit learning behaviors during several consecutive days in the future. Therefore, the information related to the learning behaviors of a learner in several consecutive days should be considered. After in-depth analysis of the learning behavior patterns of the MOOC learners, this study reports that learners often exhibit similar learning behaviors on several consecutive days, i.e., the learning status of a learner for the subsequent day is likely to be similar to that for the previous day. Based on this characteristic of MOOC learning,this study proposes a new simple feature matrix for keeping information related to the local correlation of learning behaviors and a new Convolutional Neural Network(CNN) model for predicting the dropout. Extensive experimental validations illustrate that the local correlation of learning behaviors should not be neglected. The proposed CNN model considers this characteristic and improves the dropout prediction accuracy. Furthermore, the proposed model can be used to predict dropout temporally and early when sufficient data are collected.
2020年03期 v.25 336-347页 [查看摘要][在线阅读][下载 2211K] [下载次数：91 ] |[网刊下载次数：0 ] |[引用频次：18 ] |[阅读次数：0 ] - Yimin Wen;Ye Tian;Boxi Wen;Qing Zhou;Guoyong Cai;Shaozhong Liu;
Recently, Massive Open Online Courses(MOOCs) have become a major online learning methodology for millions of people worldwide. However, the dropout rates from several current MOOCs are high. Usually, dropout prediction aims to predict whether a learner will exhibit learning behaviors during several consecutive days in the future. Therefore, the information related to the learning behaviors of a learner in several consecutive days should be considered. After in-depth analysis of the learning behavior patterns of the MOOC learners, this study reports that learners often exhibit similar learning behaviors on several consecutive days, i.e., the learning status of a learner for the subsequent day is likely to be similar to that for the previous day. Based on this characteristic of MOOC learning,this study proposes a new simple feature matrix for keeping information related to the local correlation of learning behaviors and a new Convolutional Neural Network(CNN) model for predicting the dropout. Extensive experimental validations illustrate that the local correlation of learning behaviors should not be neglected. The proposed CNN model considers this characteristic and improves the dropout prediction accuracy. Furthermore, the proposed model can be used to predict dropout temporally and early when sufficient data are collected.
2020年03期 v.25 336-347页 [查看摘要][在线阅读][下载 2211K] [下载次数：91 ] |[网刊下载次数：0 ] |[引用频次：18 ] |[阅读次数：0 ] - Hui Chen;Chuantao Yin;Rumei Li;Wenge Rong;Zhang Xiong;Bertrand David;
Smart learning systems provide relevant learning resources as a personalized bespoke package for learners based on their pedagogical needs and individual preferences. This paper introduces a learning style model to represent features of online learners. It also presents an enhanced recommendation method named Adaptive Recommendation based on Online Learning Style(AROLS), which implements learning resource adaptation by mining learners' behavioral data. First, AROLS creates learner clusters according to their online learning styles.Second, it applies Collaborative Filtering(CF) and association rule mining to extract the preferences and behavioral patterns of each cluster. Finally, it generates a personalized recommendation set of variable size. A real-world dataset is employed for some experiments. Results show that our online learning style model is conducive to the learners' data mining, and AROLS evidently outperforms the traditional CF method.
2020年03期 v.25 348-356页 [查看摘要][在线阅读][下载 1253K] [下载次数：144 ] |[网刊下载次数：0 ] |[引用频次：17 ] |[阅读次数：0 ] - Hui Chen;Chuantao Yin;Rumei Li;Wenge Rong;Zhang Xiong;Bertrand David;
Smart learning systems provide relevant learning resources as a personalized bespoke package for learners based on their pedagogical needs and individual preferences. This paper introduces a learning style model to represent features of online learners. It also presents an enhanced recommendation method named Adaptive Recommendation based on Online Learning Style(AROLS), which implements learning resource adaptation by mining learners' behavioral data. First, AROLS creates learner clusters according to their online learning styles.Second, it applies Collaborative Filtering(CF) and association rule mining to extract the preferences and behavioral patterns of each cluster. Finally, it generates a personalized recommendation set of variable size. A real-world dataset is employed for some experiments. Results show that our online learning style model is conducive to the learners' data mining, and AROLS evidently outperforms the traditional CF method.
2020年03期 v.25 348-356页 [查看摘要][在线阅读][下载 1253K] [下载次数：144 ] |[网刊下载次数：0 ] |[引用频次：17 ] |[阅读次数：0 ] - Hui Chen;Chuantao Yin;Rumei Li;Wenge Rong;Zhang Xiong;Bertrand David;
Smart learning systems provide relevant learning resources as a personalized bespoke package for learners based on their pedagogical needs and individual preferences. This paper introduces a learning style model to represent features of online learners. It also presents an enhanced recommendation method named Adaptive Recommendation based on Online Learning Style(AROLS), which implements learning resource adaptation by mining learners' behavioral data. First, AROLS creates learner clusters according to their online learning styles.Second, it applies Collaborative Filtering(CF) and association rule mining to extract the preferences and behavioral patterns of each cluster. Finally, it generates a personalized recommendation set of variable size. A real-world dataset is employed for some experiments. Results show that our online learning style model is conducive to the learners' data mining, and AROLS evidently outperforms the traditional CF method.
2020年03期 v.25 348-356页 [查看摘要][在线阅读][下载 1253K] [下载次数：144 ] |[网刊下载次数：0 ] |[引用频次：17 ] |[阅读次数：0 ]
- Mengkai Shi;Yaohan Tang;Xiangyun Zhang;Yi Zhang;Jun Xu;
As one of the most promising communication technologies for vehicular networks, LTE-V has the advantages of wide coverage and a high transmission rate. 3 GPP released the technical specification of LTE-V in March 2017, launching a spate of related research and industrialization. In this paper, we propose a communication model based on Markov process to evaluate the reliability of LTE-V. We derived the Packet Delivery Rate(PDR) of LTE-V based on the model. Moreover, we use Poisson process to model the distribution of vehicles on a highway,then combine the communication model with the vehicles' distribution to derive the PDR under this scenario. To verify the correctness of the proposed model, we established a simulation program on the MATLAB platform. By comparing the simulation results and the mathematical results, we found that simulation results are a very good fit for the model.
2020年03期 v.25 357-367页 [查看摘要][在线阅读][下载 1302K] [下载次数：47 ] |[网刊下载次数：0 ] |[引用频次：7 ] |[阅读次数：0 ] - Mengkai Shi;Yaohan Tang;Xiangyun Zhang;Yi Zhang;Jun Xu;
As one of the most promising communication technologies for vehicular networks, LTE-V has the advantages of wide coverage and a high transmission rate. 3 GPP released the technical specification of LTE-V in March 2017, launching a spate of related research and industrialization. In this paper, we propose a communication model based on Markov process to evaluate the reliability of LTE-V. We derived the Packet Delivery Rate(PDR) of LTE-V based on the model. Moreover, we use Poisson process to model the distribution of vehicles on a highway,then combine the communication model with the vehicles' distribution to derive the PDR under this scenario. To verify the correctness of the proposed model, we established a simulation program on the MATLAB platform. By comparing the simulation results and the mathematical results, we found that simulation results are a very good fit for the model.
2020年03期 v.25 357-367页 [查看摘要][在线阅读][下载 1302K] [下载次数：47 ] |[网刊下载次数：0 ] |[引用频次：7 ] |[阅读次数：0 ] - Mengkai Shi;Yaohan Tang;Xiangyun Zhang;Yi Zhang;Jun Xu;
As one of the most promising communication technologies for vehicular networks, LTE-V has the advantages of wide coverage and a high transmission rate. 3 GPP released the technical specification of LTE-V in March 2017, launching a spate of related research and industrialization. In this paper, we propose a communication model based on Markov process to evaluate the reliability of LTE-V. We derived the Packet Delivery Rate(PDR) of LTE-V based on the model. Moreover, we use Poisson process to model the distribution of vehicles on a highway,then combine the communication model with the vehicles' distribution to derive the PDR under this scenario. To verify the correctness of the proposed model, we established a simulation program on the MATLAB platform. By comparing the simulation results and the mathematical results, we found that simulation results are a very good fit for the model.
2020年03期 v.25 357-367页 [查看摘要][在线阅读][下载 1302K] [下载次数：47 ] |[网刊下载次数：0 ] |[引用频次：7 ] |[阅读次数：0 ] - Guangyuan Zheng;Guanghui Han;Nouman Qadeer Soomro;
A "sign" on a lung CT image refers to a radiologic finding that suggests a pathological progression of some specific disease. Analysis of CT signs is helpful to understand the pathological origin of the lesion. In-depth study of lung nodules classification with different CT signs will help to distinguish benign and malignant nodules more clearly and accurately. To this end, we propose an Inception module-based ensemble classification method for pulmonary nodule diagnosis with different nodule signs. We first construct a Convolutional Neural Network(CNN) classifier adopting Inception modules and pre-train it on ImageNet. We then fine-tune this pre-trained classifier on 10 different lung nodule sign sample sets, and fuse these 10 classifiers with an artificial immune ensemble algorithm. The overall sensitivity, specificity, and accuracy of our proposed Artificial Immune Algorithm-based Inception Networks Fusion(AIA-INF) algorithm are 82.22%, 93.17%, and 88.67%, respectively, which are significantly higher than those of the alternative Bagging and Boosting methods. The experimental results show that our Inception-based ensemble classifier offers promising performance, and compared with other CADx systems, this scheme can offer a more detailed reference for diagnosis, and can be valuable for junior radiologist training.
2020年03期 v.25 368-383页 [查看摘要][在线阅读][下载 2396K] [下载次数：89 ] |[网刊下载次数：0 ] |[引用频次：16 ] |[阅读次数：0 ] - Guangyuan Zheng;Guanghui Han;Nouman Qadeer Soomro;
A "sign" on a lung CT image refers to a radiologic finding that suggests a pathological progression of some specific disease. Analysis of CT signs is helpful to understand the pathological origin of the lesion. In-depth study of lung nodules classification with different CT signs will help to distinguish benign and malignant nodules more clearly and accurately. To this end, we propose an Inception module-based ensemble classification method for pulmonary nodule diagnosis with different nodule signs. We first construct a Convolutional Neural Network(CNN) classifier adopting Inception modules and pre-train it on ImageNet. We then fine-tune this pre-trained classifier on 10 different lung nodule sign sample sets, and fuse these 10 classifiers with an artificial immune ensemble algorithm. The overall sensitivity, specificity, and accuracy of our proposed Artificial Immune Algorithm-based Inception Networks Fusion(AIA-INF) algorithm are 82.22%, 93.17%, and 88.67%, respectively, which are significantly higher than those of the alternative Bagging and Boosting methods. The experimental results show that our Inception-based ensemble classifier offers promising performance, and compared with other CADx systems, this scheme can offer a more detailed reference for diagnosis, and can be valuable for junior radiologist training.
2020年03期 v.25 368-383页 [查看摘要][在线阅读][下载 2396K] [下载次数：89 ] |[网刊下载次数：0 ] |[引用频次：16 ] |[阅读次数：0 ] - Guangyuan Zheng;Guanghui Han;Nouman Qadeer Soomro;
A "sign" on a lung CT image refers to a radiologic finding that suggests a pathological progression of some specific disease. Analysis of CT signs is helpful to understand the pathological origin of the lesion. In-depth study of lung nodules classification with different CT signs will help to distinguish benign and malignant nodules more clearly and accurately. To this end, we propose an Inception module-based ensemble classification method for pulmonary nodule diagnosis with different nodule signs. We first construct a Convolutional Neural Network(CNN) classifier adopting Inception modules and pre-train it on ImageNet. We then fine-tune this pre-trained classifier on 10 different lung nodule sign sample sets, and fuse these 10 classifiers with an artificial immune ensemble algorithm. The overall sensitivity, specificity, and accuracy of our proposed Artificial Immune Algorithm-based Inception Networks Fusion(AIA-INF) algorithm are 82.22%, 93.17%, and 88.67%, respectively, which are significantly higher than those of the alternative Bagging and Boosting methods. The experimental results show that our Inception-based ensemble classifier offers promising performance, and compared with other CADx systems, this scheme can offer a more detailed reference for diagnosis, and can be valuable for junior radiologist training.
2020年03期 v.25 368-383页 [查看摘要][在线阅读][下载 2396K] [下载次数：89 ] |[网刊下载次数：0 ] |[引用频次：16 ] |[阅读次数：0 ] - Xu Wang;Zuowei Cui;Lei Jiang;Wenhuan Lu;Jie Li;
Document collections do not only contain rich semantic content but also a diverse range of relationships.We propose WordleNet, an approach to supporting effective relationship exploration in document collections.Existing approaches mainly focus on semantic similarity or a single category of relationships. By constructing a general definition of document relationships, our approach enables the flexible and real-time generation of document relationships that may not otherwise occur to human researchers and may give rise to interesting patterns among documents. Multiple novel visual components are integrated in our approach, the effectiveness of which has been verified through a case study, a comparative study, and an eye-tracking experiment.
2020年03期 v.25 384-400页 [查看摘要][在线阅读][下载 4298K] [下载次数：33 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Xu Wang;Zuowei Cui;Lei Jiang;Wenhuan Lu;Jie Li;
Document collections do not only contain rich semantic content but also a diverse range of relationships.We propose WordleNet, an approach to supporting effective relationship exploration in document collections.Existing approaches mainly focus on semantic similarity or a single category of relationships. By constructing a general definition of document relationships, our approach enables the flexible and real-time generation of document relationships that may not otherwise occur to human researchers and may give rise to interesting patterns among documents. Multiple novel visual components are integrated in our approach, the effectiveness of which has been verified through a case study, a comparative study, and an eye-tracking experiment.
2020年03期 v.25 384-400页 [查看摘要][在线阅读][下载 4298K] [下载次数：33 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Xu Wang;Zuowei Cui;Lei Jiang;Wenhuan Lu;Jie Li;
Document collections do not only contain rich semantic content but also a diverse range of relationships.We propose WordleNet, an approach to supporting effective relationship exploration in document collections.Existing approaches mainly focus on semantic similarity or a single category of relationships. By constructing a general definition of document relationships, our approach enables the flexible and real-time generation of document relationships that may not otherwise occur to human researchers and may give rise to interesting patterns among documents. Multiple novel visual components are integrated in our approach, the effectiveness of which has been verified through a case study, a comparative study, and an eye-tracking experiment.
2020年03期 v.25 384-400页 [查看摘要][在线阅读][下载 4298K] [下载次数：33 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Coral Calero;Javier Mancebo;Félix García;María ángeles Moraga;José Alberto García Berná;José Luis Fern ández-Alemán;Ambrosio Toval;
Green and Sustainable Software has emerged as a new and highly active area in the software community.After several years of research and work, we believe that it is now necessary to obtain a general snapshot of how the research in this area is evolving. To do so, we have applied the 5 Ws(why, when, who, where, and what), a formula for getting the complete story on a subject. We have therefore carried out a study, using 542 publications related to Green and Sustainable Software research; these were recovered using SCOPUS. The results obtained allow us to conclude that it is important to identify key elements of the research to allow researchers be fully aware of the state of the research on Green and Sustainable Software(why); the study uses papers published between 2000 and the beginning of November 2018(when); the most prolific authors are mainly from Europe, although the USA is the most active country, Green and Sustainable Software being a very interactive area with a good number of multinational publications(who); the top five keywords related to sustainable aspects are Green Software, Green IT,Software Sustainability, Energy Consumption, and Energy Efficiency(what); finally, as regards the places authors prefer to publish in, there is almost a complete balance between conferences and journals, with a trend towards an increase in the number of publications(where).
2020年03期 v.25 401-414页 [查看摘要][在线阅读][下载 1652K] [下载次数：39 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Coral Calero;Javier Mancebo;Félix García;María ángeles Moraga;José Alberto García Berná;José Luis Fern ández-Alemán;Ambrosio Toval;
Green and Sustainable Software has emerged as a new and highly active area in the software community.After several years of research and work, we believe that it is now necessary to obtain a general snapshot of how the research in this area is evolving. To do so, we have applied the 5 Ws(why, when, who, where, and what), a formula for getting the complete story on a subject. We have therefore carried out a study, using 542 publications related to Green and Sustainable Software research; these were recovered using SCOPUS. The results obtained allow us to conclude that it is important to identify key elements of the research to allow researchers be fully aware of the state of the research on Green and Sustainable Software(why); the study uses papers published between 2000 and the beginning of November 2018(when); the most prolific authors are mainly from Europe, although the USA is the most active country, Green and Sustainable Software being a very interactive area with a good number of multinational publications(who); the top five keywords related to sustainable aspects are Green Software, Green IT,Software Sustainability, Energy Consumption, and Energy Efficiency(what); finally, as regards the places authors prefer to publish in, there is almost a complete balance between conferences and journals, with a trend towards an increase in the number of publications(where).
2020年03期 v.25 401-414页 [查看摘要][在线阅读][下载 1652K] [下载次数：39 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Coral Calero;Javier Mancebo;Félix García;María ángeles Moraga;José Alberto García Berná;José Luis Fern ández-Alemán;Ambrosio Toval;
Green and Sustainable Software has emerged as a new and highly active area in the software community.After several years of research and work, we believe that it is now necessary to obtain a general snapshot of how the research in this area is evolving. To do so, we have applied the 5 Ws(why, when, who, where, and what), a formula for getting the complete story on a subject. We have therefore carried out a study, using 542 publications related to Green and Sustainable Software research; these were recovered using SCOPUS. The results obtained allow us to conclude that it is important to identify key elements of the research to allow researchers be fully aware of the state of the research on Green and Sustainable Software(why); the study uses papers published between 2000 and the beginning of November 2018(when); the most prolific authors are mainly from Europe, although the USA is the most active country, Green and Sustainable Software being a very interactive area with a good number of multinational publications(who); the top five keywords related to sustainable aspects are Green Software, Green IT,Software Sustainability, Energy Consumption, and Energy Efficiency(what); finally, as regards the places authors prefer to publish in, there is almost a complete balance between conferences and journals, with a trend towards an increase in the number of publications(where).
2020年03期 v.25 401-414页 [查看摘要][在线阅读][下载 1652K] [下载次数：39 ] |[网刊下载次数：0 ] |[引用频次：1 ] |[阅读次数：0 ] - Yali Zhao;Yali Li;Shengjin Wang;
Person re-IDentification(re-ID) is an important research topic in the computer vision community, with significance for a range of applications. Pedestrians are well-structured objects that can be partitioned, although detection errors cause slightly misaligned bounding boxes, which lead to mismatches. In this paper, we study the person re-identification performance of using variously designed pedestrian parts instead of the horizontal partitioning routine typically applied in previous hand-crafted part works, and thereby obtain more effective feature descriptors. Specifically, we benchmark the accuracy of individual part matching with discriminatively trained Convolutional Neural Network(CNN) descriptors on the Market-1501 dataset. We also investigate the complementarity among different parts using combination and ablation studies, and provide novel insights into this issue. Compared with the state-of-the-art, our method yields a competitive accuracy rate when the best part combination is used on two large-scale datasets(Market-1501 and CUHK03) and one small-scale dataset(VIPeR).
2020年03期 v.25 415-424页 [查看摘要][在线阅读][下载 3346K] [下载次数：33 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Yali Zhao;Yali Li;Shengjin Wang;
Person re-IDentification(re-ID) is an important research topic in the computer vision community, with significance for a range of applications. Pedestrians are well-structured objects that can be partitioned, although detection errors cause slightly misaligned bounding boxes, which lead to mismatches. In this paper, we study the person re-identification performance of using variously designed pedestrian parts instead of the horizontal partitioning routine typically applied in previous hand-crafted part works, and thereby obtain more effective feature descriptors. Specifically, we benchmark the accuracy of individual part matching with discriminatively trained Convolutional Neural Network(CNN) descriptors on the Market-1501 dataset. We also investigate the complementarity among different parts using combination and ablation studies, and provide novel insights into this issue. Compared with the state-of-the-art, our method yields a competitive accuracy rate when the best part combination is used on two large-scale datasets(Market-1501 and CUHK03) and one small-scale dataset(VIPeR).
2020年03期 v.25 415-424页 [查看摘要][在线阅读][下载 3346K] [下载次数：33 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Yali Zhao;Yali Li;Shengjin Wang;
Person re-IDentification(re-ID) is an important research topic in the computer vision community, with significance for a range of applications. Pedestrians are well-structured objects that can be partitioned, although detection errors cause slightly misaligned bounding boxes, which lead to mismatches. In this paper, we study the person re-identification performance of using variously designed pedestrian parts instead of the horizontal partitioning routine typically applied in previous hand-crafted part works, and thereby obtain more effective feature descriptors. Specifically, we benchmark the accuracy of individual part matching with discriminatively trained Convolutional Neural Network(CNN) descriptors on the Market-1501 dataset. We also investigate the complementarity among different parts using combination and ablation studies, and provide novel insights into this issue. Compared with the state-of-the-art, our method yields a competitive accuracy rate when the best part combination is used on two large-scale datasets(Market-1501 and CUHK03) and one small-scale dataset(VIPeR).
2020年03期 v.25 415-424页 [查看摘要][在线阅读][下载 3346K] [下载次数：33 ] |[网刊下载次数：0 ] |[引用频次：3 ] |[阅读次数：0 ] - Xiaoyu Fan;Muzhi Dai;Chenxi Liu;Fan Wu;Xiangda Yan;Ye Feng;Yongqiang Feng;Baiquan Su;
Skin lesions are in a category of disease that is both common in humans and a major cause of death. The classification accuracy of skin lesions is a crucial determinant of the success rate of curing lethal diseases. Deep Convolutional Neural Networks(CNNs) are now the most prevalent computer algorithms for the purpose of disease classification. As with all algorithms, CNNs are sensitive to noise from imaging devices, which often contaminates the quality of the images that are fed into them. In this paper, a deep CNN(Inception-v3) is used to study the effect of image noise on the classification of skin lesions. Gaussian noise, impulse noise, and noise made up of a compound of the two are added to an image dataset, namely the Dermofit Image Library from the University of Edinburgh. Evaluations, based on t-distributed Stochastic Neighbor Embedding(t-SNE) visualization, Receiver Operating Characteristic(ROC) analysis, and saliency maps, demonstrate the reliability of the Inception-v3 deep CNN in classifying noisy skin lesion images.
2020年03期 v.25 425-434页 [查看摘要][在线阅读][下载 4841K] [下载次数：39 ] |[网刊下载次数：0 ] |[引用频次：8 ] |[阅读次数：0 ] - Xiaoyu Fan;Muzhi Dai;Chenxi Liu;Fan Wu;Xiangda Yan;Ye Feng;Yongqiang Feng;Baiquan Su;
Skin lesions are in a category of disease that is both common in humans and a major cause of death. The classification accuracy of skin lesions is a crucial determinant of the success rate of curing lethal diseases. Deep Convolutional Neural Networks(CNNs) are now the most prevalent computer algorithms for the purpose of disease classification. As with all algorithms, CNNs are sensitive to noise from imaging devices, which often contaminates the quality of the images that are fed into them. In this paper, a deep CNN(Inception-v3) is used to study the effect of image noise on the classification of skin lesions. Gaussian noise, impulse noise, and noise made up of a compound of the two are added to an image dataset, namely the Dermofit Image Library from the University of Edinburgh. Evaluations, based on t-distributed Stochastic Neighbor Embedding(t-SNE) visualization, Receiver Operating Characteristic(ROC) analysis, and saliency maps, demonstrate the reliability of the Inception-v3 deep CNN in classifying noisy skin lesion images.
2020年03期 v.25 425-434页 [查看摘要][在线阅读][下载 4841K] [下载次数：39 ] |[网刊下载次数：0 ] |[引用频次：8 ] |[阅读次数：0 ] - Xiaoyu Fan;Muzhi Dai;Chenxi Liu;Fan Wu;Xiangda Yan;Ye Feng;Yongqiang Feng;Baiquan Su;
Skin lesions are in a category of disease that is both common in humans and a major cause of death. The classification accuracy of skin lesions is a crucial determinant of the success rate of curing lethal diseases. Deep Convolutional Neural Networks(CNNs) are now the most prevalent computer algorithms for the purpose of disease classification. As with all algorithms, CNNs are sensitive to noise from imaging devices, which often contaminates the quality of the images that are fed into them. In this paper, a deep CNN(Inception-v3) is used to study the effect of image noise on the classification of skin lesions. Gaussian noise, impulse noise, and noise made up of a compound of the two are added to an image dataset, namely the Dermofit Image Library from the University of Edinburgh. Evaluations, based on t-distributed Stochastic Neighbor Embedding(t-SNE) visualization, Receiver Operating Characteristic(ROC) analysis, and saliency maps, demonstrate the reliability of the Inception-v3 deep CNN in classifying noisy skin lesion images.
2020年03期 v.25 425-434页 [查看摘要][在线阅读][下载 4841K] [下载次数：39 ] |[网刊下载次数：0 ] |[引用频次：8 ] |[阅读次数：0 ] - Shangen Zhang;Xu Han;Xiaorong Gao;
This study explored methods for improving the performance of Steady-State Visual Evoked Potential(SSVEP)-based Brain-Computer Interfaces(BCI), and introduced a new analytical method to quantitatively analyze and reflect the characteristics of SSVEP. We focused on the effect of the pre-stimulation paradigm on the SSVEP dynamic models and the dynamic response process of SSVEP, and performed a comparative analysis of three pre-stimulus paradigms(black, gray, and white). Four dynamic models with different orders(second-and third-order)and with and without a zero point were used to fit the SSVEP envelope. The zero-pole analytical method was adopted to conduct quantitative analysis on the dynamic models, and the response characteristics of SSVEP were represented by zero-pole distribution characteristics. The results of this study indicated that the pre-stimulation paradigm affects the characteristics of SSVEP, and the dynamic models had good fitting abilities with SSVEPs under various types of pre-stimulation. Furthermore, the zero-pole characteristics of the models effectively characterize the damping coefficient, oscillation period, and other SSVEP characteristics. The comparison of zeros and poles indicated that the gray pre-stimulation condition corresponds to a lower damping coefficient, thus showing its potential to improve the performance of SSVEP-BCIs.
2020年03期 v.25 435-446页 [查看摘要][在线阅读][下载 1395K] [下载次数：42 ] |[网刊下载次数：0 ] |[引用频次：4 ] |[阅读次数：0 ] - Shangen Zhang;Xu Han;Xiaorong Gao;
This study explored methods for improving the performance of Steady-State Visual Evoked Potential(SSVEP)-based Brain-Computer Interfaces(BCI), and introduced a new analytical method to quantitatively analyze and reflect the characteristics of SSVEP. We focused on the effect of the pre-stimulation paradigm on the SSVEP dynamic models and the dynamic response process of SSVEP, and performed a comparative analysis of three pre-stimulus paradigms(black, gray, and white). Four dynamic models with different orders(second-and third-order)and with and without a zero point were used to fit the SSVEP envelope. The zero-pole analytical method was adopted to conduct quantitative analysis on the dynamic models, and the response characteristics of SSVEP were represented by zero-pole distribution characteristics. The results of this study indicated that the pre-stimulation paradigm affects the characteristics of SSVEP, and the dynamic models had good fitting abilities with SSVEPs under various types of pre-stimulation. Furthermore, the zero-pole characteristics of the models effectively characterize the damping coefficient, oscillation period, and other SSVEP characteristics. The comparison of zeros and poles indicated that the gray pre-stimulation condition corresponds to a lower damping coefficient, thus showing its potential to improve the performance of SSVEP-BCIs.
2020年03期 v.25 435-446页 [查看摘要][在线阅读][下载 1395K] [下载次数：42 ] |[网刊下载次数：0 ] |[引用频次：4 ] |[阅读次数：0 ] - Shangen Zhang;Xu Han;Xiaorong Gao;
This study explored methods for improving the performance of Steady-State Visual Evoked Potential(SSVEP)-based Brain-Computer Interfaces(BCI), and introduced a new analytical method to quantitatively analyze and reflect the characteristics of SSVEP. We focused on the effect of the pre-stimulation paradigm on the SSVEP dynamic models and the dynamic response process of SSVEP, and performed a comparative analysis of three pre-stimulus paradigms(black, gray, and white). Four dynamic models with different orders(second-and third-order)and with and without a zero point were used to fit the SSVEP envelope. The zero-pole analytical method was adopted to conduct quantitative analysis on the dynamic models, and the response characteristics of SSVEP were represented by zero-pole distribution characteristics. The results of this study indicated that the pre-stimulation paradigm affects the characteristics of SSVEP, and the dynamic models had good fitting abilities with SSVEPs under various types of pre-stimulation. Furthermore, the zero-pole characteristics of the models effectively characterize the damping coefficient, oscillation period, and other SSVEP characteristics. The comparison of zeros and poles indicated that the gray pre-stimulation condition corresponds to a lower damping coefficient, thus showing its potential to improve the performance of SSVEP-BCIs.
2020年03期 v.25 435-446页 [查看摘要][在线阅读][下载 1395K] [下载次数：42 ] |[网刊下载次数：0 ] |[引用频次：4 ] |[阅读次数：0 ] 下载本期数据