Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449449
Y. Masutani
By the rapid development of medical imaging equipments such as X-ray CT, MRI, PET, etc., data quantity yielded in hospitals is still explosively increasing. For instance, it often reaches to more than 1000 slices of X-ray CT and MRI images in a single examination. This is mainly due to improvement in spatial and temporal resolution of images, and acquisition of multi-modal information from various imaging physics. In contrast to such rich information, image-reading workload for radiologists becomes extremely heavier. In some cases, radiologists can take only less than one second per slice image in average and oversights of abnormalities may possibly occur. Therefore, full or partial automation of such image-reading tasks is a natural demand. Generally, image-reading task includes visual search of abnormalities in images such as tumors, deformation or degeneration of tissues. The computational support technology for assisting radiologists, so-called “Computer-Assisted Diagnosis/Detection (CAD)”, based on image analysis and pattern recognition have a long history over 30 years. In the early phases of CAD technology development, simple schemes such as search of round-shaped structures were employed to obtain limited success due to lack of anatomical information. Recently, information of shape and structure of the inner organs as image analysis priors becomes indispensable for reliable results. That is, computational image understanding with anatomical knowledge is a certain standard of medical image analysis. Especially, thanks to machine learning approaches with high computational powers and large database, studies on statistical analysis and mathematical description of anatomical structures opened a new discipline called “Computational Anatomy”. In this lecture, several examples of state-of-the-art techniques and systems are introduced and discussed with the practical problems in clinical situations.
{"title":"Medical image understanding and Computational Anatomy","authors":"Y. Masutani","doi":"10.1109/IWCIA.2015.7449449","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449449","url":null,"abstract":"By the rapid development of medical imaging equipments such as X-ray CT, MRI, PET, etc., data quantity yielded in hospitals is still explosively increasing. For instance, it often reaches to more than 1000 slices of X-ray CT and MRI images in a single examination. This is mainly due to improvement in spatial and temporal resolution of images, and acquisition of multi-modal information from various imaging physics. In contrast to such rich information, image-reading workload for radiologists becomes extremely heavier. In some cases, radiologists can take only less than one second per slice image in average and oversights of abnormalities may possibly occur. Therefore, full or partial automation of such image-reading tasks is a natural demand. Generally, image-reading task includes visual search of abnormalities in images such as tumors, deformation or degeneration of tissues. The computational support technology for assisting radiologists, so-called “Computer-Assisted Diagnosis/Detection (CAD)”, based on image analysis and pattern recognition have a long history over 30 years. In the early phases of CAD technology development, simple schemes such as search of round-shaped structures were employed to obtain limited success due to lack of anatomical information. Recently, information of shape and structure of the inner organs as image analysis priors becomes indispensable for reliable results. That is, computational image understanding with anatomical knowledge is a certain standard of medical image analysis. Especially, thanks to machine learning approaches with high computational powers and large database, studies on statistical analysis and mathematical description of anatomical structures opened a new discipline called “Computational Anatomy”. In this lecture, several examples of state-of-the-art techniques and systems are introduced and discussed with the practical problems in clinical situations.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115640479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449462
Sokout Hamidullah, S. Paracha
Passing the university entrance examination is a crucial step in student's life because it opens the vistas of higher education in professional development. It is very competitive to a certain degree so students try their luck with necessary preparation. Those who not prepared well, they fail it. Kankor is one such university entrance examination in Afghanistan. However, majority of talented students could not pass it, not because they do not deserve higher education; but because they do not have any guideline, training facilities physical or online, and capabilities. In this paper we analyze the research methods, approaches and the result of an intelligent tutoring system called e-Kankor which has been developed to tackle the aforementioned issues. The system offers a variety of practice materials, students' progress reports, teacher assessments, Integrative design, feedbacks including teacher-to-student and peer-assessments. The system rationale are firmly rooted in the learning theories and learner centered design approaches. To measure the success, we have rigorously tested our system on 3-scales: Lab testing, Expert-walk through and Field testing. The research methods are predominantly quantitative-cum-qualitative. Data analysis is performed with the help of SPSS. The outcome of the results indicates positive developments in terms of motivation, pedagogy and usability.
{"title":"Intelligent tutoring system: Approaches, researches and e-learning solution","authors":"Sokout Hamidullah, S. Paracha","doi":"10.1109/IWCIA.2015.7449462","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449462","url":null,"abstract":"Passing the university entrance examination is a crucial step in student's life because it opens the vistas of higher education in professional development. It is very competitive to a certain degree so students try their luck with necessary preparation. Those who not prepared well, they fail it. Kankor is one such university entrance examination in Afghanistan. However, majority of talented students could not pass it, not because they do not deserve higher education; but because they do not have any guideline, training facilities physical or online, and capabilities. In this paper we analyze the research methods, approaches and the result of an intelligent tutoring system called e-Kankor which has been developed to tackle the aforementioned issues. The system offers a variety of practice materials, students' progress reports, teacher assessments, Integrative design, feedbacks including teacher-to-student and peer-assessments. The system rationale are firmly rooted in the learning theories and learner centered design approaches. To measure the success, we have rigorously tested our system on 3-scales: Lab testing, Expert-walk through and Field testing. The research methods are predominantly quantitative-cum-qualitative. Data analysis is performed with the help of SPSS. The outcome of the results indicates positive developments in terms of motivation, pedagogy and usability.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122455162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449482
R. Tanaka, Shinya Sekizaki, I. Nishizaki, Tomohiro Hayashida
In the electricity deregulation, the electricity consumption of consumers depending on the electricity prices will change because the electricity prices are expected to fluctuate according to the market conditions. Therefore, the fluctuation of the electricity consumption can cause difficulty of distribution system operation, e.g. minimizing the distribution line losses, improving the voltage profile, and so on. Previous studies show that Distribution System Reconfiguration (DSR) is effective to minimize distribution line losses and improve voltage profile on the distribution lines. However, the DSR problems in the literatures considering the electricity deregulation are not studied sufficiently. In this paper, we formulate a multi-objective optimization problem about the distribution system operation with DSR, and search for quasi-Pareto optimal solutions using Non-dominated Sorting Genetic Algorithm-II (NSGA-II).
{"title":"The multi-objective optimization of Distribution System management in deregulated electricity market","authors":"R. Tanaka, Shinya Sekizaki, I. Nishizaki, Tomohiro Hayashida","doi":"10.1109/IWCIA.2015.7449482","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449482","url":null,"abstract":"In the electricity deregulation, the electricity consumption of consumers depending on the electricity prices will change because the electricity prices are expected to fluctuate according to the market conditions. Therefore, the fluctuation of the electricity consumption can cause difficulty of distribution system operation, e.g. minimizing the distribution line losses, improving the voltage profile, and so on. Previous studies show that Distribution System Reconfiguration (DSR) is effective to minimize distribution line losses and improve voltage profile on the distribution lines. However, the DSR problems in the literatures considering the electricity deregulation are not studied sufficiently. In this paper, we formulate a multi-objective optimization problem about the distribution system operation with DSR, and search for quasi-Pareto optimal solutions using Non-dominated Sorting Genetic Algorithm-II (NSGA-II).","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134104662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449455
R. Kamimura
The present paper proposes a new type of information-theoretic method called “pseudo potentiality maximization”. The potentiality means neurons' ability to respond appropriately to as many situations as possible. For the first approximation, the potentiality is represented by the variance of neurons toward input patterns. Because difficulty exists to compute and control this potentiality, the pseudo-potentiality is introduced with a parameter to control the amount of potentiality. By controlling this parameter, the potentiality is easily increased or decreased. The method was applied to the well-known Australian credit data set. The experimental results showed that the lowest generalization errors were obtained by the present method. In addition, interpretable connection weights were obtained, similar to the regression coefficients of the logistic analysis.
{"title":"Pseudo-potentiality maximization for improved interpretation and generalization in neural networks","authors":"R. Kamimura","doi":"10.1109/IWCIA.2015.7449455","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449455","url":null,"abstract":"The present paper proposes a new type of information-theoretic method called “pseudo potentiality maximization”. The potentiality means neurons' ability to respond appropriately to as many situations as possible. For the first approximation, the potentiality is represented by the variance of neurons toward input patterns. Because difficulty exists to compute and control this potentiality, the pseudo-potentiality is introduced with a parameter to control the amount of potentiality. By controlling this parameter, the potentiality is easily increased or decreased. The method was applied to the well-known Australian credit data set. The experimental results showed that the lowest generalization errors were obtained by the present method. In addition, interpretable connection weights were obtained, similar to the regression coefficients of the logistic analysis.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116133759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449467
J. Kushida, Akira Hara, T. Takahama
Genetic Programming (GP) is one of the evolutionary algorithm that automatically creates a computer program. Cartesian GP (CGP) is one of the extensions of GP, which generates the graph structural programs. By using the graph structure, the solutions can be represented by more compact programs. Therefore, CGP is widely applied to the various problems. As a different approach from the evolutionary algorithm, there is the Ant Colony Optimization (ACO), which is an optimization method for combinatorial optimization problems based on the cooperative behavior of ants. By using pheromone communication, the promising solution space can be searched intensively. A number of ACO variants have been proposed for the various problem domains. One of them, ACO to automatic programming has been proposed recently. This new model, called Cartesian Ant Programming (CAP), is based graph representations in CGP with search mechanism of ACO. The connections of nodes are optimized by ant-based search instead of genetic operators. However, it is difficult to utilize the most part of given nodes as an effective node which are contained in the created program. In this paper, we propose a node release mechanism for CAP in order to utilize given nodes more efficiently. In the mechanism, specific nodes are set to unavailable at the start of the run. After certain step, unavailable nodes are released and all nodes become available. We compared the search performance of CAP with node release mechanism and normal CAP, and showed the effectiveness of our method.
遗传规划(GP)是一种自动生成计算机程序的进化算法。Cartesian GP (CGP)是GP的一种扩展，用于生成图的结构规划。通过使用图结构，解可以用更紧凑的程序表示。因此，CGP被广泛应用于各种问题。蚁群优化(Ant Colony Optimization, ACO)是一种与进化算法不同的方法，它是一种基于蚂蚁合作行为的组合优化问题的优化方法。利用信息素通信，可以集中搜索有前途的解空间。针对不同的问题领域，已经提出了许多蚁群算法的变体。其中一种是近年来提出的自动编程的蚁群算法。基于蚁群算法(ACO)的搜索机制，提出了一种基于图表示的蚁群算法(CGP)。采用蚁群搜索代替遗传算子优化节点间的连接。然而，很难将所创建程序中包含的大部分给定节点作为有效节点来利用。为了更有效地利用给定节点，本文提出了一种CAP节点释放机制。在该机制中，在运行开始时将特定节点设置为不可用。经过一定步骤后，不可用的节点被释放，所有节点变为可用。比较了节点释放机制和普通CAP的搜索性能，证明了该方法的有效性。
{"title":"Cartesian Ant Programming with node release mechanism","authors":"J. Kushida, Akira Hara, T. Takahama","doi":"10.1109/IWCIA.2015.7449467","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449467","url":null,"abstract":"Genetic Programming (GP) is one of the evolutionary algorithm that automatically creates a computer program. Cartesian GP (CGP) is one of the extensions of GP, which generates the graph structural programs. By using the graph structure, the solutions can be represented by more compact programs. Therefore, CGP is widely applied to the various problems. As a different approach from the evolutionary algorithm, there is the Ant Colony Optimization (ACO), which is an optimization method for combinatorial optimization problems based on the cooperative behavior of ants. By using pheromone communication, the promising solution space can be searched intensively. A number of ACO variants have been proposed for the various problem domains. One of them, ACO to automatic programming has been proposed recently. This new model, called Cartesian Ant Programming (CAP), is based graph representations in CGP with search mechanism of ACO. The connections of nodes are optimized by ant-based search instead of genetic operators. However, it is difficult to utilize the most part of given nodes as an effective node which are contained in the created program. In this paper, we propose a node release mechanism for CAP in order to utilize given nodes more efficiently. In the mechanism, specific nodes are set to unavailable at the start of the run. After certain step, unavailable nodes are released and all nodes become available. We compared the search performance of CAP with node release mechanism and normal CAP, and showed the effectiveness of our method.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125109634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449472
Keiichi Tamura, H. Kitakami, Tatsuhiro Sakai, Yoshifumi Takahashi
Identifying similar structures in proteins has emerged as one of the most attractive research topics in the post-genome era. Protein structure alignment, which is similar to sequence alignment, identifies the structural homology between two protein structures according to their three-dimensional conformation. One of the simplest yet most robust techniques for optimizing protein structure alignment is the contact map overlap maximization problem (the CMO problem). In this paper, we focus on heuristics for the CMO problem. In our previous work, we proposed a bio-inspired heuristic using distributed modified extremal optimization (DMEO) for the CMO problem. DMEO is a hybrid of population-based modified extremal optimization (PMEO) and the island model. DMEO enhances population diversity; however, individual evolution is extremely monotonous because evolutions of it is based on the greedy moving approach. To address this issue, we propose a novel bio-inspired heuristic, i.e., DMEO with different evolutionary strategy (DMEODES). DMEODES is also based on the island model; however, some of the islands, called hot-spot islands, have a different evolutionary strategy. To evaluate DMEODES, we used actual protein structures. Experimental results showed that DMEODES outperforms DMEO.
{"title":"A new distributed modified extremal optimization for optimizing protein structure alignment","authors":"Keiichi Tamura, H. Kitakami, Tatsuhiro Sakai, Yoshifumi Takahashi","doi":"10.1109/IWCIA.2015.7449472","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449472","url":null,"abstract":"Identifying similar structures in proteins has emerged as one of the most attractive research topics in the post-genome era. Protein structure alignment, which is similar to sequence alignment, identifies the structural homology between two protein structures according to their three-dimensional conformation. One of the simplest yet most robust techniques for optimizing protein structure alignment is the contact map overlap maximization problem (the CMO problem). In this paper, we focus on heuristics for the CMO problem. In our previous work, we proposed a bio-inspired heuristic using distributed modified extremal optimization (DMEO) for the CMO problem. DMEO is a hybrid of population-based modified extremal optimization (PMEO) and the island model. DMEO enhances population diversity; however, individual evolution is extremely monotonous because evolutions of it is based on the greedy moving approach. To address this issue, we propose a novel bio-inspired heuristic, i.e., DMEO with different evolutionary strategy (DMEODES). DMEODES is also based on the island model; however, some of the islands, called hot-spot islands, have a different evolutionary strategy. To evaluate DMEODES, we used actual protein structures. Experimental results showed that DMEODES outperforms DMEO.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127173144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449452
Shinya Sekizaki, Tomohiro Hayashida, I. Nishizaki
A Home Energy Management System (HEMS), which enables residential users to effectively manage the energy consumption in their home, can optimize the operation schedule of household appliances according to environments, e.g. indoor temperature and electricity prices. HEMS monitors the environment and the energy usage, visually represents the energy consumption, and effectively controls the appliances, thus HEMS helps to reduce the energy cost as well as to maintain users' comfort. The optimal operation schedule of the appliances for the cost saving, however, does not always coincident with the user's desired operation schedule of the appliances because the optimal operation schedule is fixed by HEMS and hence the users could not change the operation schedule even when they need. From this point of view, we address the energy management system which enables the users to use the appliances at their disposal, not only for saving the cost. Because the operation schedule of the household appliances which does not disturb the user's behavior should be calculated, we develop the intelligent HEMS based on eXtended Classifier System (XCS) in this paper. The effectiveness of the proposed HEMS is confirmed by the computational experiments.
{"title":"An intelligent Home Energy Management System with classifier system","authors":"Shinya Sekizaki, Tomohiro Hayashida, I. Nishizaki","doi":"10.1109/IWCIA.2015.7449452","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449452","url":null,"abstract":"A Home Energy Management System (HEMS), which enables residential users to effectively manage the energy consumption in their home, can optimize the operation schedule of household appliances according to environments, e.g. indoor temperature and electricity prices. HEMS monitors the environment and the energy usage, visually represents the energy consumption, and effectively controls the appliances, thus HEMS helps to reduce the energy cost as well as to maintain users' comfort. The optimal operation schedule of the appliances for the cost saving, however, does not always coincident with the user's desired operation schedule of the appliances because the optimal operation schedule is fixed by HEMS and hence the users could not change the operation schedule even when they need. From this point of view, we address the energy management system which enables the users to use the appliances at their disposal, not only for saving the cost. Because the operation schedule of the household appliances which does not disturb the user's behavior should be calculated, we develop the intelligent HEMS based on eXtended Classifier System (XCS) in this paper. The effectiveness of the proposed HEMS is confirmed by the computational experiments.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122118082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449453
Takashi Matsumoto, H. Takase, H. Kawanaka, S. Tsuruoka
SpikeProp, which is proposed by Booij, is a kind of spiking neural networks. It can learn the timing of output spikes, but cannot adjust the number of output spikes. Our research group has discussed the problem and proposed a learning method that can adjust both timing and number of spikes. However, its learning performance depends on the initial network structure (the number of hidden units, delay, the number of sub-connections, and so on). In this article, we discuss the problem, especially the dependency to delay. We proposed the method that removes sub-connections that have unnecessary delay during training. By the proposed method, we successed training more than 87% regardless of the number of initial delays.
{"title":"A learning method for SpikeProp without redundant spikes -automatic adjusting delay of connections","authors":"Takashi Matsumoto, H. Takase, H. Kawanaka, S. Tsuruoka","doi":"10.1109/IWCIA.2015.7449453","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449453","url":null,"abstract":"SpikeProp, which is proposed by Booij, is a kind of spiking neural networks. It can learn the timing of output spikes, but cannot adjust the number of output spikes. Our research group has discussed the problem and proposed a learning method that can adjust both timing and number of spikes. However, its learning performance depends on the initial network structure (the number of hidden units, delay, the number of sub-connections, and so on). In this article, we discuss the problem, especially the dependency to delay. We proposed the method that removes sub-connections that have unnecessary delay during training. By the proposed method, we successed training more than 87% regardless of the number of initial delays.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128042863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449475
Hiroto Komaki, Shunsuke Shimazaki, K. Sakakibara, Takuya Matsumoto
We focus on a timetabling problem of university makeup classes and construct a scheduling system based on man-machine interaction which enables to reveal the essential and additional information of the problem domain. In order to achieve operable timetables of the makeup classes it is required to consider the courses of every student in the university, because the makeup class timetable is made after the courses of each student were registered. Therefore, it is especially difficult to find feasible timetables. In this paper, we focus on the makeup class timetabling problem and develop the optimization system based on man-machine interaction using the column generation heuristics. In order to adopt the column generation heuristics, we show a set partitioning model of the target problem. Through some preliminary computational results, the effectiveness and the potential, e.g, for clarifying the effect of the column generation heuristics are investigated.
{"title":"Interactive optimization techniques based on a column generation model for timetabling problems of university makeup courses","authors":"Hiroto Komaki, Shunsuke Shimazaki, K. Sakakibara, Takuya Matsumoto","doi":"10.1109/IWCIA.2015.7449475","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449475","url":null,"abstract":"We focus on a timetabling problem of university makeup classes and construct a scheduling system based on man-machine interaction which enables to reveal the essential and additional information of the problem domain. In order to achieve operable timetables of the makeup classes it is required to consider the courses of every student in the university, because the makeup class timetable is made after the courses of each student were registered. Therefore, it is especially difficult to find feasible timetables. In this paper, we focus on the makeup class timetabling problem and develop the optimization system based on man-machine interaction using the column generation heuristics. In order to adopt the column generation heuristics, we show a set partitioning model of the target problem. Through some preliminary computational results, the effectiveness and the potential, e.g, for clarifying the effect of the column generation heuristics are investigated.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130486348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-11-01DOI: 10.1109/IWCIA.2015.7449464
Toshihiko Nishimura, T. Nagao, H. Iseki, Y. Muragaki, M. Tamura, Shinji Minami
There is a need of surgery workflow analysis to increase an efficiency of advanced medical care. Surgical Operations have been recorded by several sensors for such as postoperative analysis and incidents detection. In particular, surgical video recording is commonly used, so there are some audio-visual recorded data, and they are useful to obtain a better understandings and description of advanced surgical operations. However, the recorded videos are not usually annotated, so it is not simple to conduct computational analysis, and data annotation is necessary to handle by computer. We target videos of awake craniotomy which is a special neurosurgery in this work. The cortical mapping process is the most important for brain tumor resection in awake craniotomy. Therefore, we aim to annotate this process to analyze medical staff's knowledge. We assume that the factor that affects the surgical procedures is below: positions of direct electric stimulations, duration of the stimulus, current intensity, tasks presented for patients. In this paper, we constructed annotated data from clinical recorded awake craniotomy videos. Data collection is performed manually by graphical user interface because several terms of annotation are hard to annotate completely automatically. After that, we visualized the several of annotated data and discussed the effect.
{"title":"Construction of annotated data for analysis of recorded cortical mapping videos","authors":"Toshihiko Nishimura, T. Nagao, H. Iseki, Y. Muragaki, M. Tamura, Shinji Minami","doi":"10.1109/IWCIA.2015.7449464","DOIUrl":"https://doi.org/10.1109/IWCIA.2015.7449464","url":null,"abstract":"There is a need of surgery workflow analysis to increase an efficiency of advanced medical care. Surgical Operations have been recorded by several sensors for such as postoperative analysis and incidents detection. In particular, surgical video recording is commonly used, so there are some audio-visual recorded data, and they are useful to obtain a better understandings and description of advanced surgical operations. However, the recorded videos are not usually annotated, so it is not simple to conduct computational analysis, and data annotation is necessary to handle by computer. We target videos of awake craniotomy which is a special neurosurgery in this work. The cortical mapping process is the most important for brain tumor resection in awake craniotomy. Therefore, we aim to annotate this process to analyze medical staff's knowledge. We assume that the factor that affects the surgical procedures is below: positions of direct electric stimulations, duration of the stimulus, current intensity, tasks presented for patients. In this paper, we constructed annotated data from clinical recorded awake craniotomy videos. Data collection is performed manually by graphical user interface because several terms of annotation are hard to annotate completely automatically. After that, we visualized the several of annotated data and discussed the effect.","PeriodicalId":298756,"journal":{"name":"2015 IEEE 8th International Workshop on Computational Intelligence and Applications (IWCIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129839428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：