In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring...In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.展开更多
Learning a mapping between an input space and an output.space from training data canbe viewed as a problem of function approximation,which means that different criteria result in learningapproaches of different abilit...Learning a mapping between an input space and an output.space from training data canbe viewed as a problem of function approximation,which means that different criteria result in learningapproaches of different abilities.Among them,projection criterion proposed by one of the authors aimsdirectly at optimal generalization.The projection idea leads to three specific learning approaches,projection learning,partial projection learning,and averaged projection learning,and a framework of afamily of projection learning called S-L projection learning is established to discuss infinite kinds oflearning.S-L projection learning has a different form from the three methods,and it is not easy to analyzetheir relationship.This paper focuses on an equivalent form of S-L projection learning,which shows thatit is a transformed version of partial projection learning.展开更多
The Wavelet-Domain Projection Pursuit Learning Network (WDPPLN) is proposedfor restoring degraded image. The new network combines the advantages of both projectionpursuit and wavelet shrinkage. Restoring image is very...The Wavelet-Domain Projection Pursuit Learning Network (WDPPLN) is proposedfor restoring degraded image. The new network combines the advantages of both projectionpursuit and wavelet shrinkage. Restoring image is very difficult when little is known about apriori knowledge for multisource degraded factors. WDPPLN successfully resolves this problemby separately processing wavelet coefficients and scale coefficients. Parameters in WDPPLN,which are used to simulate degraded factors, are estimated via WDPPLN training, using scalecoefficients. Also, WDPPLN uses soft-threshold of wavelet shrinkage technique to suppress noisein three high frequency subbands. The new method is compared with the traditional methodsand the Projection Pursuit Learning Network (PPLN) method. Experimental results demonstratethat it is an effective method for unsupervised restoring degraded image.展开更多
All engineering students need to develop their important skills of leadership in project management. Many students have never been leaders in their social and school lives. A leading role is unimaginable to them and h...All engineering students need to develop their important skills of leadership in project management. Many students have never been leaders in their social and school lives. A leading role is unimaginable to them and hence they cannot imagine how to achieve it. The purpose of this paper is to report a result of a new leadership education program which links a variety of simulated experiences with real actions of students in project based learning （PBL） to develop their leadership ability. The first step is for graduate students to gain knowledge in the leadership arena. Then, they utilize simulation to experience leadership actions many times. Simulation provides a safe environment in which they can try out many different approaches in taking leadership in various situations. In the next step, students as a team utilize PBL, so that the above simulated experiences can help them to actually take leadership. Students can apply trained leadership to actual projects. It is highly effective to apply conscious leadership to a project aimed at a specific goal in limited circumstances. This education repeats both of the steps above, raising leadership abilities in an upward spiral. In terms of students＇ evaluation of leadership education in project management, 360-degree assessments were carried out by teachers, senior, and junior students before and after the course, and authors compare their assessments thoroughly. As a result, authors are assured that students not only gained knowledge but also raised leadership abilities in their actions after this education. Six months after the time of leadership education employing simulated experiences and PBL, follow-up interviews were conducted on its effects. Authors recognized the cyclic period that students apply simulated experiences to PBL and that they seek different approaches in simulation for solving problems found in reality. This research concludes that this cycle of simulator and PBL can produce effective leadership actions.展开更多
The peculiar nature of control theory as a course that cut across a lot of major engineering disciplines calls for a look into how its learning can best be done without students feeling like they are wasting their tim...The peculiar nature of control theory as a course that cut across a lot of major engineering disciplines calls for a look into how its learning can best be done without students feeling like they are wasting their time.This paper takes a look at control theory as subject cut across various engineering field and has a wide background that students must really be comfortable with.Its wide application and background pose a huge challenge to the teaching of control.It goes further to look into traditional method of teaching,Project-Based Learning Blooms Taxonomy.It then proposes applying Flipped Bloom Taxonomy to Project-based learning for a deep understanding of control systems.展开更多
In practice, it is necessary to implement an incremental and active learning for a learning method. In terms of such implementation, this paper shows that the previously discussed S-L projection learning is inappropri...In practice, it is necessary to implement an incremental and active learning for a learning method. In terms of such implementation, this paper shows that the previously discussed S-L projection learning is inappropriate to constructing a family of projection learning, and proposes a new version called partial oblique projection (POP) learning. In POP learning, a function space is decomposed into two complementary subspaces, so that functions belonging to one of the subspaces can be completely estimated in noiseless case; while in noisy case, the dispersions are set to be the smallest. In addition, a general form of POP learning is presented and the results of a simulation are given.展开更多
Project-based learning （PBL） as an instructional approach focuses on student-centeredness through contextualizing learning by presenting students with real world issues and practices that aim at achieving enduring l...Project-based learning （PBL） as an instructional approach focuses on student-centeredness through contextualizing learning by presenting students with real world issues and practices that aim at achieving enduring learning effects. As a challenge to traditional lecture-based instruction, PBL may generate positive backwash assessment effects via documenting the process of developing authentic language skills. These skills-oriented outcomes are achieved through proper curricula in appropriate learning situations via various dimensions. However, problems may occur such as management, pressure from administration, evaluation doing their selected projects. teacher/student attitude, class size and proper group process and criteria, and students＇ likely frustrations in展开更多
Content-based instruction(CBI)effectively combines language skills with subject.According to CBI teaching concept,teachers can improve students’academic English ability by effectively designing academic English class...Content-based instruction(CBI)effectively combines language skills with subject.According to CBI teaching concept,teachers can improve students’academic English ability by effectively designing academic English classroom activities.In this paper,the author tries to integrate the teaching idea of CBI in the course of academic English teaching,so as to cultivate students’ability to communicate in academic English.展开更多
Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measuremen...Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measurement based on deep learning.A multi-stream convolutional neural network(CNN)is proposed to learn the mapping relationship between camera array light filed wrapped phases and fringe orders of the expected central view,and is used to predict the fringe order to achieve the phase unwrapping.Experiments are performed on the light field fringe projection data generated by the simulated camera array fringe projection measurement system in Blender and by the experimental 3×3 camera array light field fringe projection system.The performance of the proposed network with light field wrapped phases using multiple directions as network input data is studied,and the advantages of phase unwrapping based on deep learning in light filed fringe projection are demonstrated.展开更多
Using a qualitative case study approach,the authors analyzed the curriculum adaptation process for one project learning activity in School K,which is a SID school in the context of school-university collaboration.Mult...Using a qualitative case study approach,the authors analyzed the curriculum adaptation process for one project learning activity in School K,which is a SID school in the context of school-university collaboration.Multiple sources of data were collected for triangulation,including interviews,documents and observations.Curriculum adaptation strategies in this study were analyzed from five perspectives:instructional goals,instructional content,instructional strategies,instructional settings,and student behavioral needs.It was found that curriculum adaptation efforts could help students with ID develop potential at their own level through project learning activates and teachers could also gain professional development during the university-school collaboration process.As for future studies,enlarging the sample size,involving teachers’past orientations and motivations in the project learning process,and collecting quantitative data could all be taken into account.展开更多
The new generation of world information technology revolution has promoted the vigorous development and rapid transform of the new economy.The in-depth implementation of a series of Chinese important national strategi...The new generation of world information technology revolution has promoted the vigorous development and rapid transform of the new economy.The in-depth implementation of a series of Chinese important national strategies such as“Made in China 2025”and“Internet+”is urgently needed the support of innovative and outstanding emerging engineering talents with cross-border integration abilities.Therefore,interdisciplinary education plays an important role in the training of the needed emerging engineering talents.Taking cybersecurity as an example,this paper summarizes the professional’s requirements and proposes the educational objectives of Harbin Institute of Technology.Then the objective oriented curriculum system and the teaching model emphasizing project-based learning are introduced.The practice and effect of interdisciplinary education are discussed and analyzed in four aspects including curriculum system,faculty,students and academy education.Finally,suggestions are made on the individualized education and sustainable competitiveness cultivation of the emerging engineering talents.展开更多
Machine learning(ML)techniques and algorithms have been successfully and widely used in various areas including software engineering tasks.Like other software projects,bugs are also common in ML projects and libraries...Machine learning(ML)techniques and algorithms have been successfully and widely used in various areas including software engineering tasks.Like other software projects,bugs are also common in ML projects and libraries.In order to more deeply understand the features related to bug fixing in ML projects,we conduct an empirical study with 939 bugs from five ML projects by manually examining the bug categories,fixing patterns,fixing scale,fixing duration,and types of maintenance.The results show that(1)there are commonly seven types of bugs in ML programs;(2)twelve fixing patterns are typically used to fix the bugs in ML programs;(3)68.80%of the patches belong to micro-scale-fix and small-scale-fix;(4)66.77%of the bugs in ML programs can be fixed within one month;(5)45.90%of the bug fixes belong to corrective activity from the perspective of software maintenance.Moreover,we perform a questionnaire survey and send them to developers or users of ML projects to validate the results in our empirical study.The results of our empirical study are basically consistent with the feedback from developers.The findings from the empirical study provide useful guidance and insights for developers and users to effectively detect and fix bugs in MLprojects.展开更多
基金Supported by the National Natural Science Foundation of China(61273160)the Fundamental Research Funds for the Central Universities(14CX06067A,13CX05021A)
文摘In soft sensor field, just-in-time learning(JITL) is an effective approach to model nonlinear and time varying processes. However, most similarity criterions in JITL are computed in the input space only while ignoring important output information, which may lead to inaccurate construction of relevant sample set. To solve this problem, we propose a novel supervised feature extraction method suitable for the regression problem called supervised local and non-local structure preserving projections(SLNSPP), in which both input and output information can be easily and effectively incorporated through a newly defined similarity index. The SLNSPP can not only retain the virtue of locality preserving projections but also prevent faraway points from nearing after projection,which endues SLNSPP with powerful discriminating ability. Such two good properties of SLNSPP are desirable for JITL as they are expected to enhance the accuracy of similar sample selection. Consequently, we present a SLNSPP-JITL framework for developing adaptive soft sensor, including a sparse learning strategy to limit the scale and update the frequency of database. Finally, two case studies are conducted with benchmark datasets to evaluate the performance of the proposed schemes. The results demonstrate the effectiveness of LNSPP and SLNSPP.
文摘Learning a mapping between an input space and an output.space from training data canbe viewed as a problem of function approximation,which means that different criteria result in learningapproaches of different abilities.Among them,projection criterion proposed by one of the authors aimsdirectly at optimal generalization.The projection idea leads to three specific learning approaches,projection learning,partial projection learning,and averaged projection learning,and a framework of afamily of projection learning called S-L projection learning is established to discuss infinite kinds oflearning.S-L projection learning has a different form from the three methods,and it is not easy to analyzetheir relationship.This paper focuses on an equivalent form of S-L projection learning,which shows thatit is a transformed version of partial projection learning.
文摘The Wavelet-Domain Projection Pursuit Learning Network (WDPPLN) is proposedfor restoring degraded image. The new network combines the advantages of both projectionpursuit and wavelet shrinkage. Restoring image is very difficult when little is known about apriori knowledge for multisource degraded factors. WDPPLN successfully resolves this problemby separately processing wavelet coefficients and scale coefficients. Parameters in WDPPLN,which are used to simulate degraded factors, are estimated via WDPPLN training, using scalecoefficients. Also, WDPPLN uses soft-threshold of wavelet shrinkage technique to suppress noisein three high frequency subbands. The new method is compared with the traditional methodsand the Projection Pursuit Learning Network (PPLN) method. Experimental results demonstratethat it is an effective method for unsupervised restoring degraded image.
文摘All engineering students need to develop their important skills of leadership in project management. Many students have never been leaders in their social and school lives. A leading role is unimaginable to them and hence they cannot imagine how to achieve it. The purpose of this paper is to report a result of a new leadership education program which links a variety of simulated experiences with real actions of students in project based learning （PBL） to develop their leadership ability. The first step is for graduate students to gain knowledge in the leadership arena. Then, they utilize simulation to experience leadership actions many times. Simulation provides a safe environment in which they can try out many different approaches in taking leadership in various situations. In the next step, students as a team utilize PBL, so that the above simulated experiences can help them to actually take leadership. Students can apply trained leadership to actual projects. It is highly effective to apply conscious leadership to a project aimed at a specific goal in limited circumstances. This education repeats both of the steps above, raising leadership abilities in an upward spiral. In terms of students＇ evaluation of leadership education in project management, 360-degree assessments were carried out by teachers, senior, and junior students before and after the course, and authors compare their assessments thoroughly. As a result, authors are assured that students not only gained knowledge but also raised leadership abilities in their actions after this education. Six months after the time of leadership education employing simulated experiences and PBL, follow-up interviews were conducted on its effects. Authors recognized the cyclic period that students apply simulated experiences to PBL and that they seek different approaches in simulation for solving problems found in reality. This research concludes that this cycle of simulator and PBL can produce effective leadership actions.
文摘The peculiar nature of control theory as a course that cut across a lot of major engineering disciplines calls for a look into how its learning can best be done without students feeling like they are wasting their time.This paper takes a look at control theory as subject cut across various engineering field and has a wide background that students must really be comfortable with.Its wide application and background pose a huge challenge to the teaching of control.It goes further to look into traditional method of teaching,Project-Based Learning Blooms Taxonomy.It then proposes applying Flipped Bloom Taxonomy to Project-based learning for a deep understanding of control systems.
文摘In practice, it is necessary to implement an incremental and active learning for a learning method. In terms of such implementation, this paper shows that the previously discussed S-L projection learning is inappropriate to constructing a family of projection learning, and proposes a new version called partial oblique projection (POP) learning. In POP learning, a function space is decomposed into two complementary subspaces, so that functions belonging to one of the subspaces can be completely estimated in noiseless case; while in noisy case, the dispersions are set to be the smallest. In addition, a general form of POP learning is presented and the results of a simulation are given.
文摘Project-based learning （PBL） as an instructional approach focuses on student-centeredness through contextualizing learning by presenting students with real world issues and practices that aim at achieving enduring learning effects. As a challenge to traditional lecture-based instruction, PBL may generate positive backwash assessment effects via documenting the process of developing authentic language skills. These skills-oriented outcomes are achieved through proper curricula in appropriate learning situations via various dimensions. However, problems may occur such as management, pressure from administration, evaluation doing their selected projects. teacher/student attitude, class size and proper group process and criteria, and students＇ likely frustrations in
文摘Content-based instruction(CBI)effectively combines language skills with subject.According to CBI teaching concept,teachers can improve students’academic English ability by effectively designing academic English classroom activities.In this paper,the author tries to integrate the teaching idea of CBI in the course of academic English teaching,so as to cultivate students’ability to communicate in academic English.
基金the National Natural Science Foundation of China(No.61905178)the Science&Technology Development Fund of Tianjin Education Commission for Higher Education(No.2019KJ021)the Natural Science Foundation of Tianjin(No.18JCQNJC71100)。
文摘Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measurement based on deep learning.A multi-stream convolutional neural network(CNN)is proposed to learn the mapping relationship between camera array light filed wrapped phases and fringe orders of the expected central view,and is used to predict the fringe order to achieve the phase unwrapping.Experiments are performed on the light field fringe projection data generated by the simulated camera array fringe projection measurement system in Blender and by the experimental 3×3 camera array light field fringe projection system.The performance of the proposed network with light field wrapped phases using multiple directions as network input data is studied,and the advantages of phase unwrapping based on deep learning in light filed fringe projection are demonstrated.
文摘Using a qualitative case study approach,the authors analyzed the curriculum adaptation process for one project learning activity in School K,which is a SID school in the context of school-university collaboration.Multiple sources of data were collected for triangulation,including interviews,documents and observations.Curriculum adaptation strategies in this study were analyzed from five perspectives:instructional goals,instructional content,instructional strategies,instructional settings,and student behavioral needs.It was found that curriculum adaptation efforts could help students with ID develop potential at their own level through project learning activates and teachers could also gain professional development during the university-school collaboration process.As for future studies,enlarging the sample size,involving teachers’past orientations and motivations in the project learning process,and collecting quantitative data could all be taken into account.
基金supported in part by the Ministry of Education of the People’s Republic of China under the Emerging Engineering Education Research and Practice Projects of”Research and Practice on the Cooperative Education Model of Industry-Academic Cooperation in the Emerging Engineering Education System of Chinese Universities”and“Exploration and Practice of Engineering Talent Education Model with Multidisciplinary Integration”and under Grant 18JDGC014,and by the Shandong Provincial Department of Education under Grant M2018B336.
文摘The new generation of world information technology revolution has promoted the vigorous development and rapid transform of the new economy.The in-depth implementation of a series of Chinese important national strategies such as“Made in China 2025”and“Internet+”is urgently needed the support of innovative and outstanding emerging engineering talents with cross-border integration abilities.Therefore,interdisciplinary education plays an important role in the training of the needed emerging engineering talents.Taking cybersecurity as an example,this paper summarizes the professional’s requirements and proposes the educational objectives of Harbin Institute of Technology.Then the objective oriented curriculum system and the teaching model emphasizing project-based learning are introduced.The practice and effect of interdisciplinary education are discussed and analyzed in four aspects including curriculum system,faculty,students and academy education.Finally,suggestions are made on the individualized education and sustainable competitiveness cultivation of the emerging engineering talents.
基金This work was supported partially by the National Natural Science Foundation of China(Grant Nos.61872312,61972335,61472344,61611540347,61402396 and 61662021)partially by the Open Funds of State Key Laboratory for Novel Software Technology of Nanjing University(KFKT2020B15 and KFKT2020B16)+3 种基金partially by the Jiangsu“333”Project,partially by the Six Talent Peaks Project in Jiangsu Province(RJFW-053)partially by the Natural Science Foundation of Jiangsu(BK20181353)partially by the Yangzhou city-Yangzhou University Science and Technology Cooperation Fund Project(YZU201803),by the CERNET Innovation Project(NGII20180607)partially by the Yangzhou University Top-level Talents Support Program(2019).
文摘Machine learning(ML)techniques and algorithms have been successfully and widely used in various areas including software engineering tasks.Like other software projects,bugs are also common in ML projects and libraries.In order to more deeply understand the features related to bug fixing in ML projects,we conduct an empirical study with 939 bugs from five ML projects by manually examining the bug categories,fixing patterns,fixing scale,fixing duration,and types of maintenance.The results show that(1)there are commonly seven types of bugs in ML programs;(2)twelve fixing patterns are typically used to fix the bugs in ML programs;(3)68.80%of the patches belong to micro-scale-fix and small-scale-fix;(4)66.77%of the bugs in ML programs can be fixed within one month;(5)45.90%of the bug fixes belong to corrective activity from the perspective of software maintenance.Moreover,we perform a questionnaire survey and send them to developers or users of ML projects to validate the results in our empirical study.The results of our empirical study are basically consistent with the feedback from developers.The findings from the empirical study provide useful guidance and insights for developers and users to effectively detect and fix bugs in MLprojects.
