A genetic algorithm (GA) which is a meta-heuristic approach was applied to optimize the landing flight path of a delta-winged supersonic transport (SST). However, at low speeds, particularly during take-off and landing, a complex flowfield surrounds the delta wing. This phenomenon requires time-series control optimization that yields an optimum control sequence by aerodynamic - flight dynamics with high-fidelity computational fluid dynamics to evaluate the flight path with the complex flowfield. To this end, we presented an efficient flight simulation based on Kriging-model-assisted aerodynamic estimation to carry out the global optimization via a GA. After establishing the efficient aerodynamics-flight dynamics optimization, we constructed the design of the flight and control sequence for the time-series optimization of an effective SST landing. Several solutions that provide an allowable SST landing performance, along with the knowledge on optimum flight and control sequence, are presented herein.
{"title":"Genetic Algorithm Applied to the Time-Series Landing Flight Path and Control Optimization of a Supersonic Transport","authors":"Masahiro Kanazaki, Ryouta Saisyo","doi":"10.1145/3325773.3325789","DOIUrl":"https://doi.org/10.1145/3325773.3325789","url":null,"abstract":"A genetic algorithm (GA) which is a meta-heuristic approach was applied to optimize the landing flight path of a delta-winged supersonic transport (SST). However, at low speeds, particularly during take-off and landing, a complex flowfield surrounds the delta wing. This phenomenon requires time-series control optimization that yields an optimum control sequence by aerodynamic - flight dynamics with high-fidelity computational fluid dynamics to evaluate the flight path with the complex flowfield. To this end, we presented an efficient flight simulation based on Kriging-model-assisted aerodynamic estimation to carry out the global optimization via a GA. After establishing the efficient aerodynamics-flight dynamics optimization, we constructed the design of the flight and control sequence for the time-series optimization of an effective SST landing. Several solutions that provide an allowable SST landing performance, along with the knowledge on optimum flight and control sequence, are presented herein.","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132954412","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}
Underwater wireless communication is a critical and challenging research area wherein acoustic signals are used to transfer data. The Underwater Wireless Sensor Network (UWSN) is used to transmit data sensed by the sensors in the sea bed to the surface sinks through intermediate nodes for seismic surveillance, border security and underwater environment monitoring applications. The nodes comprising of UWSN are battery operated and are subjected to failures leading to connectivity loss. And the propagation delay in sending the data in the form of acoustic signals is found to be high and as the depth increases the transmission delay also increases. Hence, routing in UWSN is a complex problem. The simulation experiments of the delay sensitive protocols are found to minimize the delay at the expense of network throughput which is not acceptable. The energy aware routing protocols on the other hand reduces energy consumption and routing overhead but has high delay involved in transmission. In this study, transmission delay and reliability estimation models are developed using which bi-objective routing model is proposed considering both delay and reliability in route selection. In the simulation studies, the bi-objective model reduced delay on an average by 9% and the reliability of the network is improved by 34% when compared to the delay sensitive and reliable routing strategies.
{"title":"A Bi-objective Routing Model for Underwater Wireless Sensor Network","authors":"D. Persis","doi":"10.1145/3325773.3325786","DOIUrl":"https://doi.org/10.1145/3325773.3325786","url":null,"abstract":"Underwater wireless communication is a critical and challenging research area wherein acoustic signals are used to transfer data. The Underwater Wireless Sensor Network (UWSN) is used to transmit data sensed by the sensors in the sea bed to the surface sinks through intermediate nodes for seismic surveillance, border security and underwater environment monitoring applications. The nodes comprising of UWSN are battery operated and are subjected to failures leading to connectivity loss. And the propagation delay in sending the data in the form of acoustic signals is found to be high and as the depth increases the transmission delay also increases. Hence, routing in UWSN is a complex problem. The simulation experiments of the delay sensitive protocols are found to minimize the delay at the expense of network throughput which is not acceptable. The energy aware routing protocols on the other hand reduces energy consumption and routing overhead but has high delay involved in transmission. In this study, transmission delay and reliability estimation models are developed using which bi-objective routing model is proposed considering both delay and reliability in route selection. In the simulation studies, the bi-objective model reduced delay on an average by 9% and the reliability of the network is improved by 34% when compared to the delay sensitive and reliable routing strategies.","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130600072","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}
Air pollutants such as fine dust and ozone are important factors in human health management. In this work, the future air quality of Daegu metropolitan city is predicted by using the past air quality data. Due to the time series nature of the data, we use recurrent neural networks for the experiments. The data is measured in units of one hour using various air quality sensors. Experiments were performed based on length of input data (time step) in order to obtain the optimal length. Various optimization functions and neural network structure were also investigated. The prediction accuracy of fine dust was found to be the most predictable among other environmental pollutants. Also, it was observed that learning models for nearby areas can be used to predict similar pollutant in another area without having to go through a separate learning process.
{"title":"Air Pollution Matter Prediction Using Recurrent Neural Networks with Sequential Data","authors":"Y. B. Lim, I. Aliyu, C. Lim","doi":"10.1145/3325773.3325788","DOIUrl":"https://doi.org/10.1145/3325773.3325788","url":null,"abstract":"Air pollutants such as fine dust and ozone are important factors in human health management. In this work, the future air quality of Daegu metropolitan city is predicted by using the past air quality data. Due to the time series nature of the data, we use recurrent neural networks for the experiments. The data is measured in units of one hour using various air quality sensors. Experiments were performed based on length of input data (time step) in order to obtain the optimal length. Various optimization functions and neural network structure were also investigated. The prediction accuracy of fine dust was found to be the most predictable among other environmental pollutants. Also, it was observed that learning models for nearby areas can be used to predict similar pollutant in another area without having to go through a separate learning process.","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126064628","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}
We have fulfilled a completely automated system of evolutionary design optimization with unstructured computational fluid dynamics. Until now, we cannot automatize aerodynamic design optimization to deal with geometry with high degrees of freedom. However, we achieved to simply iterate large-scale (it takes huge time to evaluate objective functions) and real-world evolutionary multiobjective optimizations. As a result, we efficiently obtained design knowledge for a next-step problem by applying the system to the design problem of a booster stage for two-stage-to-orbit. Moreover, this study yields the hypothesis regarding the appropriate algorithm of evolutionary computation for not only mathematical benchmark but also large-scale real-world problems.
{"title":"Completely Automated System for Evolutionary Design Optimization with Unstructured Computational Fluid Dynamics","authors":"Kazuhisa Chiba, Tsuyoshi Sumimoto, Masataka Sawahara","doi":"10.1145/3325773.3325778","DOIUrl":"https://doi.org/10.1145/3325773.3325778","url":null,"abstract":"We have fulfilled a completely automated system of evolutionary design optimization with unstructured computational fluid dynamics. Until now, we cannot automatize aerodynamic design optimization to deal with geometry with high degrees of freedom. However, we achieved to simply iterate large-scale (it takes huge time to evaluate objective functions) and real-world evolutionary multiobjective optimizations. As a result, we efficiently obtained design knowledge for a next-step problem by applying the system to the design problem of a booster stage for two-stage-to-orbit. Moreover, this study yields the hypothesis regarding the appropriate algorithm of evolutionary computation for not only mathematical benchmark but also large-scale real-world problems.","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134383239","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}
Deadlock occurs when all threads of a program remain in their current state and cannot move forward. These threads execute concurrently in multi-core CPUs. As the execution order of their code lines is uncertain, it is extremely difficult to locate the accurate position that deadlock occurs without modifying the source code. C/C++, Qt and Java are three commonly used programming languages in Linux. This paper presents an intelligent scheme of deadlock locating for these languages. By modifying the kernel of pthreads, Qt and OpenJDK, we redesign three kinds of resource functions: mutex, lock and semaphore. At runtime, the file names and line numbers of these functions which a user's program calls are written to a shared memory database called Redis. The data in Redis can be fetched by two tools. One graphical tool is responsible for displaying the usage of resources and do deadlock analysis. Another is used to detect deadlock periodically and write deadlock to a journal file, or notify users by mail or short message. A plugin is also developed respectively for QtCreator and Eclipse. Both tools can be started from either plugin. The deadlock detection method does not need to modify the source code of a user program, which greatly facilitates the user to determine the location of deadlock.
{"title":"An Intelligent Deadlock Locating Scheme for Multithreaded Programs","authors":"Jiaqi Li, Xiaodong Liu, Linxuan Jiang, Buquan Liu, Zhaojun Yang, Xianlang Hu","doi":"10.1145/3325773.3325781","DOIUrl":"https://doi.org/10.1145/3325773.3325781","url":null,"abstract":"Deadlock occurs when all threads of a program remain in their current state and cannot move forward. These threads execute concurrently in multi-core CPUs. As the execution order of their code lines is uncertain, it is extremely difficult to locate the accurate position that deadlock occurs without modifying the source code. C/C++, Qt and Java are three commonly used programming languages in Linux. This paper presents an intelligent scheme of deadlock locating for these languages. By modifying the kernel of pthreads, Qt and OpenJDK, we redesign three kinds of resource functions: mutex, lock and semaphore. At runtime, the file names and line numbers of these functions which a user's program calls are written to a shared memory database called Redis. The data in Redis can be fetched by two tools. One graphical tool is responsible for displaying the usage of resources and do deadlock analysis. Another is used to detect deadlock periodically and write deadlock to a journal file, or notify users by mail or short message. A plugin is also developed respectively for QtCreator and Eclipse. Both tools can be started from either plugin. The deadlock detection method does not need to modify the source code of a user program, which greatly facilitates the user to determine the location of deadlock.","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125590396","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}
Dimension reduction realize extraction of substantial low dimensional latent structure in high-dimensional data. Due to recent developments in information and measurement technology, it becomes more important to develop dimension reduction algorithms for high dimensional time series data. Gaussian process dynamic model (GPDM) is a method that can obtain low dimensional latent variable representation by using Gaussian process state space model. However, it is difficult to obtain an appropriate latent variable representation of new data point in the GPDM. In this study, we propose a Gaussian Process dynamic autoencoder model (GPDAEM), which consists of Gaussian process state space model and Gaussian process encoder model, in order to estimate appropriate latent variables corresponding to additional new time series data. Experimental results on low dimensional latent variable representation of time series data show that the proposed GPDAEM has better performance than the existing Gaussian process based latent variable models.
{"title":"Gaussian Process Dynamical Autoencoder Model","authors":"Jo Takano, T. Omori","doi":"10.1145/3325773.3325784","DOIUrl":"https://doi.org/10.1145/3325773.3325784","url":null,"abstract":"Dimension reduction realize extraction of substantial low dimensional latent structure in high-dimensional data. Due to recent developments in information and measurement technology, it becomes more important to develop dimension reduction algorithms for high dimensional time series data. Gaussian process dynamic model (GPDM) is a method that can obtain low dimensional latent variable representation by using Gaussian process state space model. However, it is difficult to obtain an appropriate latent variable representation of new data point in the GPDM. In this study, we propose a Gaussian Process dynamic autoencoder model (GPDAEM), which consists of Gaussian process state space model and Gaussian process encoder model, in order to estimate appropriate latent variables corresponding to additional new time series data. Experimental results on low dimensional latent variable representation of time series data show that the proposed GPDAEM has better performance than the existing Gaussian process based latent variable models.","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123170789","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}
In industry the condition monitoring of rotating machinery gear is very important. The defect in gear mesh may cause the failure in machinery and that causes a severe loss in industry. The failure in gear mesh reduces the efficiency and hence decreases the productivity in industrial operation. Therefore the health monitoring of gear mesh is very important. Proper health monitoring of gears can avoid the failure in machinery and can save money in industrial applications. The acoustic emission and vibration are the two widely used measuring parameters which is used for the condition monitoring of gear mesh. In this work the gear fault detection by using the acoustic emission monitoring technique is used. This experimentation is done by using an efficient instrumentation system. The experimental set-up is designed which consists of a gear mesh driving system and a hand-held sound analyzer. To carry out the experiment the measuring signals from the defective and healthy gears are captured and compared. In this work the measuring signal is the acoustic emission from the tested gears. Then for the fault detection, two signal processing techniques are followed. These are statistical analysis and adaptive wavelet transform (AWT) analysis. The comparison in statistical as well as in AWT analysis used to detect the fault present in gears. In AWT analysis the adaptive noise cancellation is used to enhance the signal to noise ratio (SNR). Finally faults in gears are classified using the machine learning classifier. The statistical parameter data are used as the input data for the classifiers to train the system to classify the fault.
{"title":"Gear Fault Diagnosis and Classification Using Machine Learning Classifier","authors":"S. Sahoo, R. A. Laskar, J. K. Das, S. Laskar","doi":"10.1145/3325773.3325782","DOIUrl":"https://doi.org/10.1145/3325773.3325782","url":null,"abstract":"In industry the condition monitoring of rotating machinery gear is very important. The defect in gear mesh may cause the failure in machinery and that causes a severe loss in industry. The failure in gear mesh reduces the efficiency and hence decreases the productivity in industrial operation. Therefore the health monitoring of gear mesh is very important. Proper health monitoring of gears can avoid the failure in machinery and can save money in industrial applications. The acoustic emission and vibration are the two widely used measuring parameters which is used for the condition monitoring of gear mesh. In this work the gear fault detection by using the acoustic emission monitoring technique is used. This experimentation is done by using an efficient instrumentation system. The experimental set-up is designed which consists of a gear mesh driving system and a hand-held sound analyzer. To carry out the experiment the measuring signals from the defective and healthy gears are captured and compared. In this work the measuring signal is the acoustic emission from the tested gears. Then for the fault detection, two signal processing techniques are followed. These are statistical analysis and adaptive wavelet transform (AWT) analysis. The comparison in statistical as well as in AWT analysis used to detect the fault present in gears. In AWT analysis the adaptive noise cancellation is used to enhance the signal to noise ratio (SNR). Finally faults in gears are classified using the machine learning classifier. The statistical parameter data are used as the input data for the classifiers to train the system to classify the fault.","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133572564","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}
{"title":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","authors":"","doi":"10.1145/3325773","DOIUrl":"https://doi.org/10.1145/3325773","url":null,"abstract":"","PeriodicalId":419017,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127302557","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：