The design of electrical, mechanical and fluid systems on aircraft is becoming increasingly integrated with the aircraft structure definition process. An example is the aircraft fuel quantity indication (FQI) system, of which the design is strongly dependent on the tank geometry definition. Flexible FQI design methods are therefore desirable to swiftly assess system-level impact due to aircraft level changes. For this purpose, a genetic algorithm with a two-stage fitness assignment and FQI specific crossover procedure is proposed (FQI-GA). It can handle multiple measurement accuracy constraints, is coupled to a parametric definition of the wing tank geometry and is tested with two performance objectives. A range of crossover procedures of comparable node placement problems were tested for FQI-GA. Results show that the combinatorial nature of the probe architecture and accuracy constraints require a probe set selection mechanism before any crossover process. A case study, using approximated Airbus A320 requirements and tank geometry, is conducted and shows good agreement with the probe position results obtained with the FQI-GA. For the objectives of accessibility and probe mass, the Pareto front is linear, with little variation in mass. The case study confirms that the FQI-GA method can incorporate complex requirements and that designers can employ it to swiftly investigate FQI probe layouts and trade-offs.
{"title":"Rapid design of aircraft fuel quantity indication systems via multi-objective evolutionary algorithms","authors":"D. Judt, C. Lawson, A. S. V. Heerden","doi":"10.3233/ica-200646","DOIUrl":"https://doi.org/10.3233/ica-200646","url":null,"abstract":"The design of electrical, mechanical and fluid systems on aircraft is becoming increasingly integrated with the aircraft structure definition process. An example is the aircraft fuel quantity indication (FQI) system, of which the design is strongly dependent on the tank geometry definition. Flexible FQI design methods are therefore desirable to swiftly assess system-level impact due to aircraft level changes. For this purpose, a genetic algorithm with a two-stage fitness assignment and FQI specific crossover procedure is proposed (FQI-GA). It can handle multiple measurement accuracy constraints, is coupled to a parametric definition of the wing tank geometry and is tested with two performance objectives. A range of crossover procedures of comparable node placement problems were tested for FQI-GA. Results show that the combinatorial nature of the probe architecture and accuracy constraints require a probe set selection mechanism before any crossover process. A case study, using approximated Airbus A320 requirements and tank geometry, is conducted and shows good agreement with the probe position results obtained with the FQI-GA. For the objectives of accessibility and probe mass, the Pareto front is linear, with little variation in mass. The case study confirms that the FQI-GA method can incorporate complex requirements and that designers can employ it to swiftly investigate FQI probe layouts and trade-offs.","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86799815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The scientific journal Integrated Computer-Aided Engineering (ICAE) is approaching its 30th anniversary. For nearly three decades it has been promoting innovative multidisciplinary research with absolute consistency, maintaining the highest standards of quality without compromise. The scientific community has honored ICAE with its trust and with a very high impact factor. I wish to thank the Editor in Chief Professor Hojjat Adeli, for giving me the chance to write and publish this brief analysis. We are grateful for his invaluable contribution. The recent flourishing of the 4th Industrial Revolution (4IR) is calling for interdisciplinary research efforts, aiming in the development of intelligent nonlinear models applied in every real-life domain. ICAE is a leading journal for the dissemination of timely synergistic research efforts in the fields of Engineering and Information-Communication technologies. It opens new frontiers for solving complex problems to meet the needs of our post-modern 21st century societies. A major part of the research papers published in the journal during the past three decades has been related mainly but not limited to a wide spectrum of Artificial Intelligence (AI) algorithms and approaches. In the 4IR era, the technological developments in the field of Intelligent Information Systems are rapid and having a decisive impact on the respective engineering applications. And ICAE has been at the forefront of this developments. The following Fig. ??, shows the frequency distribution of the topics covered by the journal’s publications during the past two years (2018–2019). More specifically, 15 published papers are in the thematic area of Image-Video Processing (IMVP), 12 are related to Machine Learning (ML), 9 to Robotics, and 8 to Optimization (OPT). It is of great importance that the ICAE journal also covers a wide spectrum of topics namely: Big Data, Filtering, Control Systems, Autonomous Vehicles, Cognitive modeling and Bioinformatics. ML publications are related to Classification, Ensembles, Deep – Convolutional and Transfer Learning algorithms with respective applications. On the other hand, OPT papers have employed Meta Heuristic approaches. A comparison of the 2012–2013 article list with 2018–2019 article list shows many additional research
{"title":"Evolution of a model journal in the era of digital revolution","authors":"","doi":"10.3233/ica-200639","DOIUrl":"https://doi.org/10.3233/ica-200639","url":null,"abstract":"The scientific journal Integrated Computer-Aided Engineering (ICAE) is approaching its 30th anniversary. For nearly three decades it has been promoting innovative multidisciplinary research with absolute consistency, maintaining the highest standards of quality without compromise. The scientific community has honored ICAE with its trust and with a very high impact factor. I wish to thank the Editor in Chief Professor Hojjat Adeli, for giving me the chance to write and publish this brief analysis. We are grateful for his invaluable contribution. The recent flourishing of the 4th Industrial Revolution (4IR) is calling for interdisciplinary research efforts, aiming in the development of intelligent nonlinear models applied in every real-life domain. ICAE is a leading journal for the dissemination of timely synergistic research efforts in the fields of Engineering and Information-Communication technologies. It opens new frontiers for solving complex problems to meet the needs of our post-modern 21st century societies. A major part of the research papers published in the journal during the past three decades has been related mainly but not limited to a wide spectrum of Artificial Intelligence (AI) algorithms and approaches. In the 4IR era, the technological developments in the field of Intelligent Information Systems are rapid and having a decisive impact on the respective engineering applications. And ICAE has been at the forefront of this developments. The following Fig. ??, shows the frequency distribution of the topics covered by the journal’s publications during the past two years (2018–2019). More specifically, 15 published papers are in the thematic area of Image-Video Processing (IMVP), 12 are related to Machine Learning (ML), 9 to Robotics, and 8 to Optimization (OPT). It is of great importance that the ICAE journal also covers a wide spectrum of topics namely: Big Data, Filtering, Control Systems, Autonomous Vehicles, Cognitive modeling and Bioinformatics. ML publications are related to Classification, Ensembles, Deep – Convolutional and Transfer Learning algorithms with respective applications. On the other hand, OPT papers have employed Meta Heuristic approaches. A comparison of the 2012–2013 article list with 2018–2019 article list shows many additional research","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83965622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Transfer learning methods exploit similarities between different datasets to improve the performance of the target task by transferring knowledge from source tasks to the target task. “What to transfer” is a main research issue in transfer learning. The existing transfer learning method generally needs to acquire the shared parameters by integrating human knowledge. However, in many real applications, an understanding of which parameters can be shared is unknown beforehand. Transfer learning model is essentially a special multi-objective optimization problem. Consequently, this paper proposes a novel auto-sharing parameter technique for transfer learning based on multi-objective optimization and solves the optimization problem by using a multi-swarm particle swarm optimizer. Each task objective is simultaneously optimized by a sub-swarm. The current best particle from the sub-swarm of the target task is used to guide the search of particles of the source tasks and vice versa. The target task and source task are jointly solved by sharing the information of the best particle, which works as an inductive bias. Experiments are carried out to evaluate the proposed algorithm on several synthetic data sets and two real-world data sets of a school data set and a landmine data set, which show that the proposed algorithm is effective.
{"title":"Auto-sharing parameters for transfer learning based on multi-objective optimization","authors":"Hai-Lin Liu, Fangqing Gu, Zixian Lin","doi":"10.3233/ICA-210655","DOIUrl":"https://doi.org/10.3233/ICA-210655","url":null,"abstract":"Transfer learning methods exploit similarities between different datasets to improve the performance of the target task by transferring knowledge from source tasks to the target task. “What to transfer” is a main research issue in transfer learning. The existing transfer learning method generally needs to acquire the shared parameters by integrating human knowledge. However, in many real applications, an understanding of which parameters can be shared is unknown beforehand. Transfer learning model is essentially a special multi-objective optimization problem. Consequently, this paper proposes a novel auto-sharing parameter technique for transfer learning based on multi-objective optimization and solves the optimization problem by using a multi-swarm particle swarm optimizer. Each task objective is simultaneously optimized by a sub-swarm. The current best particle from the sub-swarm of the target task is used to guide the search of particles of the source tasks and vice versa. The target task and source task are jointly solved by sharing the information of the best particle, which works as an inductive bias. Experiments are carried out to evaluate the proposed algorithm on several synthetic data sets and two real-world data sets of a school data set and a landmine data set, which show that the proposed algorithm is effective.","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79713615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sometimes all it takes to realize the significance of a thing is simply to understand its name. This is certainly the case for the journal Integrated ComputerAided Engineering (ICAE), which has now been benefitting interdisciplinary researchers for 30 years. The name ICAE starts with “integrated,” which speaks to the very interdisciplinary nature of the journal. ICAE is about research projects, not simple research papers. To publish in ICAE is to present research in a larger context, making ICAE articles of interest to researchers and enthusiasts in several technology fields at once. The second part of ICAE’s name is “computer,” and some elaboration is necessary here. ICAE papers are not about computer architecture or about computer networks; instead, ICAE is about using computer architectures and networks in optimal ways to solve technical problems. This comes to the third part of the four-part name: “aided”. Computing is used to aid technologists in their research and development challenges. Computing is a tool, and ICAE authors are expected to actually use their tools properly. If it’s a nail, you’d better use a hammer, but if it’s a screw, you’d better use a screwdriver. If a paper is submitted to ICAE, it had better not simply grab the latest convolutional neural network (CNN) design and apply it to a known data set and present its 2% reduction in error rate as a finding. That is simply a verification that CNN designs continue to incrementally improve, and as such is nothing more than a verification that CNNs continue to be useful tools for the technical community. Reaching back to the earlier analogy, that is tantamount to showing that the latest hammer will pound a nail with 2% more efficiency. Nice to know, but not interesting. Perhaps this is why the third part of the name of ICAE is so important. When one must use a tool to aid in a task, it should be an interesting task. For me, this is why ICAE is one of my favorite journals. It is both interdisciplinary and interesting. Incremental articles are not ICAE articles. Hojjat Adeli, the Founder and Editor-in-Chief of ICAE, makes this clear in the reviewer form for ICAE, which specifically asks “If you are aware of the authors’ other recent publications please explain how the current submission is different from their previous publication. Please point out the duplication, if any, and provide specific suggestions to minimize any duplication.” In other words, any duplication is grounds for constructive, but also restrictive, feedback to the authors. It is computer-aided, not computer-using, research. This brings us to the fourth part of the name, “engineering.” Engineers are applied researchers. They build devices, they test what they build, they create useful and reproducible outputs. We need only consider the next part of the reviewer feedback to see this need for building, testing, and utility: “Please comment whether examples presented in the paper are appropriate and justified consideri
{"title":"Both Interdisciplinary and Interesting","authors":"H. Adeli","doi":"10.3233/ICA-210648","DOIUrl":"https://doi.org/10.3233/ICA-210648","url":null,"abstract":"Sometimes all it takes to realize the significance of a thing is simply to understand its name. This is certainly the case for the journal Integrated ComputerAided Engineering (ICAE), which has now been benefitting interdisciplinary researchers for 30 years. The name ICAE starts with “integrated,” which speaks to the very interdisciplinary nature of the journal. ICAE is about research projects, not simple research papers. To publish in ICAE is to present research in a larger context, making ICAE articles of interest to researchers and enthusiasts in several technology fields at once. The second part of ICAE’s name is “computer,” and some elaboration is necessary here. ICAE papers are not about computer architecture or about computer networks; instead, ICAE is about using computer architectures and networks in optimal ways to solve technical problems. This comes to the third part of the four-part name: “aided”. Computing is used to aid technologists in their research and development challenges. Computing is a tool, and ICAE authors are expected to actually use their tools properly. If it’s a nail, you’d better use a hammer, but if it’s a screw, you’d better use a screwdriver. If a paper is submitted to ICAE, it had better not simply grab the latest convolutional neural network (CNN) design and apply it to a known data set and present its 2% reduction in error rate as a finding. That is simply a verification that CNN designs continue to incrementally improve, and as such is nothing more than a verification that CNNs continue to be useful tools for the technical community. Reaching back to the earlier analogy, that is tantamount to showing that the latest hammer will pound a nail with 2% more efficiency. Nice to know, but not interesting. Perhaps this is why the third part of the name of ICAE is so important. When one must use a tool to aid in a task, it should be an interesting task. For me, this is why ICAE is one of my favorite journals. It is both interdisciplinary and interesting. Incremental articles are not ICAE articles. Hojjat Adeli, the Founder and Editor-in-Chief of ICAE, makes this clear in the reviewer form for ICAE, which specifically asks “If you are aware of the authors’ other recent publications please explain how the current submission is different from their previous publication. Please point out the duplication, if any, and provide specific suggestions to minimize any duplication.” In other words, any duplication is grounds for constructive, but also restrictive, feedback to the authors. It is computer-aided, not computer-using, research. This brings us to the fourth part of the name, “engineering.” Engineers are applied researchers. They build devices, they test what they build, they create useful and reproducible outputs. We need only consider the next part of the reviewer feedback to see this need for building, testing, and utility: “Please comment whether examples presented in the paper are appropriate and justified consideri","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88784686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. Macias-Garcia, Deysy Galeana Pérez, Jesus Medrano-Hermosillo, E. Bayro-Corrochano
This paper presents a novel multi-stage perception system for collision avoidance in mobile robots. In the here considered scenario, a mobile robot stands in a workspace with a set of potential targets to reach or interact with. When a human partner appears gesturing to the target, the robot must plan a collision-free trajectory to reach the goal. To solve this problem, a full-perception system composed of consecutive convolutional neural networks in parallel and processing stages is proposed for generating a collision-free trajectory according to the desired goal. This system is evaluated at each step in real environments and through several performance tests, proving to be a robust and fast system suitable for real-time applications.
{"title":"Multi-stage deep learning perception system for mobile robots","authors":"E. Macias-Garcia, Deysy Galeana Pérez, Jesus Medrano-Hermosillo, E. Bayro-Corrochano","doi":"10.3233/ICA-200640","DOIUrl":"https://doi.org/10.3233/ICA-200640","url":null,"abstract":"This paper presents a novel multi-stage perception system for collision avoidance in mobile robots. In the here considered scenario, a mobile robot stands in a workspace with a set of potential targets to reach or interact with. When a human partner appears gesturing to the target, the robot must plan a collision-free trajectory to reach the goal. To solve this problem, a full-perception system composed of consecutive convolutional neural networks in parallel and processing stages is proposed for generating a collision-free trajectory according to the desired goal. This system is evaluated at each step in real environments and through several performance tests, proving to be a robust and fast system suitable for real-time applications.","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87986117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Membrane computing models are parallel and distributed natural computing models. These models are often referred to as P systems. This paper proposes a novel multi-behaviors co-ordination controller model using enzymatic numerical P systems for autonomous mobile robots navigation in unknown environments. An environment classifier is constructed to identify different environment patterns in the maze-like environment and the multi-behavior co-ordination controller is constructed to coordinate the behaviors of the robots in different environments. Eleven sensory prototypes of local environments are presented to design the environment classifier, which needs to memorize only rough information, for solving the problems of poor obstacle clearance and sensor noise. A switching control strategy and multi-behaviors coordinator are developed without detailed environmental knowledge and heavy computation burden, for avoiding the local minimum traps or oscillation problems and adapt to the unknown environments. Also, a serial behaviors control law is constructed on the basis of Lyapunov stability theory aiming at the specialized environment, for realizing stable navigation and avoiding actuator saturation. Moreover, both environment classifier and multi-behavior coordination controller are amenable to the addition of new environment models or new behaviors due to the modularity of the hierarchical architecture of P systems. The simulation of wheeled mobile robots shows the effectiveness of this approach.
{"title":"Multi-behaviors coordination controller design with enzymatic numerical P systems for robots","authors":"Xueyuan Wang, Gexiang Zhang, Xiantai Gou, Prithwineel Paul, Ferrante Neri, Haina Rong, Qiang Yang, Hua Zhang","doi":"10.3233/ica-200627","DOIUrl":"https://doi.org/10.3233/ica-200627","url":null,"abstract":"Membrane computing models are parallel and distributed natural computing models. These models are often referred to as P systems. This paper proposes a novel multi-behaviors co-ordination controller model using enzymatic numerical P systems for autonomous mobile robots navigation in unknown environments. An environment classifier is constructed to identify different environment patterns in the maze-like environment and the multi-behavior co-ordination controller is constructed to coordinate the behaviors of the robots in different environments. Eleven sensory prototypes of local environments are presented to design the environment classifier, which needs to memorize only rough information, for solving the problems of poor obstacle clearance and sensor noise. A switching control strategy and multi-behaviors coordinator are developed without detailed environmental knowledge and heavy computation burden, for avoiding the local minimum traps or oscillation problems and adapt to the unknown environments. Also, a serial behaviors control law is constructed on the basis of Lyapunov stability theory aiming at the specialized environment, for realizing stable navigation and avoiding actuator saturation. Moreover, both environment classifier and multi-behavior coordination controller are amenable to the addition of new environment models or new behaviors due to the modularity of the hierarchical architecture of P systems. The simulation of wheeled mobile robots shows the effectiveness of this approach.","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81656553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luis Roda-Sanchez, T. Olivares, Celia Garrido-Hidalgo, J. Vara, A. Fernández-Caballero
In the context of fast-growing digitization of industrial environments, Industry 4.0 aims to improve key elements to achieve more efficient processes, flexibility in customizing products and reduction in energy consumption, among other objectives. This paper presents a system that exploits the Internet of Things (IoT), massive data computation, and human-robot collaboration to reach these goals. The described system combines technological and human-centered aspects to enhance human-robot interaction. In fact, the human factor cannot be left aside when technological advances affecting society are foreseen. The proposal has been tested on a gesture control system that enables a natural interaction with a robotic arm through the use of IoT-oriented inertial measurement unit devices. These devices capture the movements of both human’s arms. Experiments of a technical nature have been run to measure accuracy and latency. In addition, human-centered tests have been conducted with real users to determine the level of intuitiveness and acceptance of the proposed gesture control. The results obtained demonstrate that the proposal meets the demands in terms of real-time, success rate, flexibility and scalability, which are fundamental requirements in Industry 4.0. The usability results have enabled drawing useful conclusions on the use of such human-robot interaction systems.
{"title":"Human-robot interaction in Industry 4.0 based on an Internet of Things real-time gesture control system","authors":"Luis Roda-Sanchez, T. Olivares, Celia Garrido-Hidalgo, J. Vara, A. Fernández-Caballero","doi":"10.3233/ica-200637","DOIUrl":"https://doi.org/10.3233/ica-200637","url":null,"abstract":"In the context of fast-growing digitization of industrial environments, Industry 4.0 aims to improve key elements to achieve more efficient processes, flexibility in customizing products and reduction in energy consumption, among other objectives. This paper presents a system that exploits the Internet of Things (IoT), massive data computation, and human-robot collaboration to reach these goals. The described system combines technological and human-centered aspects to enhance human-robot interaction. In fact, the human factor cannot be left aside when technological advances affecting society are foreseen. The proposal has been tested on a gesture control system that enables a natural interaction with a robotic arm through the use of IoT-oriented inertial measurement unit devices. These devices capture the movements of both human’s arms. Experiments of a technical nature have been run to measure accuracy and latency. In addition, human-centered tests have been conducted with real users to determine the level of intuitiveness and acceptance of the proposed gesture control. The results obtained demonstrate that the proposal meets the demands in terms of real-time, success rate, flexibility and scalability, which are fundamental requirements in Industry 4.0. The usability results have enabled drawing useful conclusions on the use of such human-robot interaction systems.","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77529799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lun Hu, Xiangyu Pan, Hong Yan, Pengwei Hu, Tiantian He
As a fundamental task in cluster analysis, community detection is crucial for the understanding of complex network systems in many disciplines such as biology and sociology. Recently, due to the increase in the richness and variety of attribute information associated with individual nodes, detecting communities in attributed graphs becomes a more challenging problem. Most existing works focus on the similarity between pairwise nodes in terms of both structural and attribute information while ignoring the higher-order patterns involving more than two nodes. In this paper, we explore the possibility of making use of higher-order information in attributed graphs to detect communities. To do so, we first compose tensors to specifically model the higher-order patterns of interest from the aspects of network structures and node attributes, and then propose a novel algorithm to capture these patterns for community detection. Extensive experiments on several real-world datasets with varying sizes and different characteristics of attribute information demonstrated the promising performance of our algorithm.
{"title":"Exploiting higher-order patterns for community detection in attributed graphs","authors":"Lun Hu, Xiangyu Pan, Hong Yan, Pengwei Hu, Tiantian He","doi":"10.3233/ica-200645","DOIUrl":"https://doi.org/10.3233/ica-200645","url":null,"abstract":"As a fundamental task in cluster analysis, community detection is crucial for the understanding of complex network systems in many disciplines such as biology and sociology. Recently, due to the increase in the richness and variety of attribute information associated with individual nodes, detecting communities in attributed graphs becomes a more challenging problem. Most existing works focus on the similarity between pairwise nodes in terms of both structural and attribute information while ignoring the higher-order patterns involving more than two nodes. In this paper, we explore the possibility of making use of higher-order information in attributed graphs to detect communities. To do so, we first compose tensors to specifically model the higher-order patterns of interest from the aspects of network structures and node attributes, and then propose a novel algorithm to capture these patterns for community detection. Extensive experiments on several real-world datasets with varying sizes and different characteristics of attribute information demonstrated the promising performance of our algorithm.","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76165550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This is my deep honor and great pleasure to share my thoughts on the celebration of almost 3 decades of continuous publication of the Integrated ComputerAided Engineering (ICAE) Journal. Of course such an international journal is indebted to its Editorial Board, to the numerous reviewers, to the even more numerous authors who trusted the journal and to the readers, and I would like to thank them all for their willingness, their work and their trust. In the current case, the journal’s excellence is also in no small measure due to the work and personal involvement of its founder and Editorin-Chief, Professor Hojjat Adeli, and I would like to emphasize his vision and work in the next paragraphs. I was greatly honored when Prof. Adeli asked me to join the ICAE Editorial Advisory Board in 2000. This enrolment lasted until 2006. Around this date, I became the Chief of the French section of IEEE Signal Processing Society (2003–2013), then an Associate Editor of the IEEE Transactions on Signal Processing (2005–2008); since these commitments generated more demanding tasks, I had to resign from my ICAE duties. But I have been serving the ICAE journal as a member of the Editorial Board again since 2017, which is very motivating. Thus, in the light of my own experience, I can make several remarks. First, it is most unusual for scientific journals to keep the same Editor-in-Chief for such a long time: such a position must generate an enormous workload, obviously not compatible with a mere scientific activity, and the enthusiasm of any normally skilled scientist begins to fade over the years. When I compare my two terms with ICAE, I can assure that our EIC’s engagement in this journal has been constant over the years, albeit Prof. Adeli’s scientific outreach is one of the most prominent and influential researchers of our time. Second, one can see that, nowadays, high standard scientific journals have to cope with a couple of rather new challenges: the growing number of potential publications and the inevitable broadening of their scope. On the one hand, the number of papers spreading over the scientific and technical fields of the journal has been dramatically increasing over the last decades. Many new small conferences in touristic locations, many internetonly journals, without solid reviewing policy, generate a lot of papers, which is part of the equation. Concurrently, it is fairly easy for a scientist to upload preprints over the Internet which are made available without any review, which are sometimes unfinished papers (or papers without any verified result), all these materials making cross-references: this is another quite substantial part of the same equation. One of the risks in such an absence of sufficiently strict rules and sufficiently rigorous selection criteria is that excellent works may be drowned among the noise. Nevertheless, the ICAE journal has always maintained (almost) drastic selection rules. I have reviewed plenty of submissions myself
{"title":"How to maintain the highest quality standards of a leading journal after three decades: An extraordinary Editor-in-Chief leading by example","authors":"","doi":"10.3233/ica-200644","DOIUrl":"https://doi.org/10.3233/ica-200644","url":null,"abstract":"This is my deep honor and great pleasure to share my thoughts on the celebration of almost 3 decades of continuous publication of the Integrated ComputerAided Engineering (ICAE) Journal. Of course such an international journal is indebted to its Editorial Board, to the numerous reviewers, to the even more numerous authors who trusted the journal and to the readers, and I would like to thank them all for their willingness, their work and their trust. In the current case, the journal’s excellence is also in no small measure due to the work and personal involvement of its founder and Editorin-Chief, Professor Hojjat Adeli, and I would like to emphasize his vision and work in the next paragraphs. I was greatly honored when Prof. Adeli asked me to join the ICAE Editorial Advisory Board in 2000. This enrolment lasted until 2006. Around this date, I became the Chief of the French section of IEEE Signal Processing Society (2003–2013), then an Associate Editor of the IEEE Transactions on Signal Processing (2005–2008); since these commitments generated more demanding tasks, I had to resign from my ICAE duties. But I have been serving the ICAE journal as a member of the Editorial Board again since 2017, which is very motivating. Thus, in the light of my own experience, I can make several remarks. First, it is most unusual for scientific journals to keep the same Editor-in-Chief for such a long time: such a position must generate an enormous workload, obviously not compatible with a mere scientific activity, and the enthusiasm of any normally skilled scientist begins to fade over the years. When I compare my two terms with ICAE, I can assure that our EIC’s engagement in this journal has been constant over the years, albeit Prof. Adeli’s scientific outreach is one of the most prominent and influential researchers of our time. Second, one can see that, nowadays, high standard scientific journals have to cope with a couple of rather new challenges: the growing number of potential publications and the inevitable broadening of their scope. On the one hand, the number of papers spreading over the scientific and technical fields of the journal has been dramatically increasing over the last decades. Many new small conferences in touristic locations, many internetonly journals, without solid reviewing policy, generate a lot of papers, which is part of the equation. Concurrently, it is fairly easy for a scientist to upload preprints over the Internet which are made available without any review, which are sometimes unfinished papers (or papers without any verified result), all these materials making cross-references: this is another quite substantial part of the same equation. One of the risks in such an absence of sufficiently strict rules and sufficiently rigorous selection criteria is that excellent works may be drowned among the noise. Nevertheless, the ICAE journal has always maintained (almost) drastic selection rules. I have reviewed plenty of submissions myself","PeriodicalId":50358,"journal":{"name":"Integrated Computer-Aided Engineering","volume":null,"pages":null},"PeriodicalIF":6.5,"publicationDate":"2020-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80501079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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：