Pub Date : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146059
Tibor Toth, G. Theodoropoulos, S. Boland, Ibad Kureshi, Adam Ghandar
Global emergencies such as epidemics present immense governance challenges to national, political and operational decision-makers. Modelling and Simulation has been identified as a crucial force multiplier in the development and implementation of preparedness and response measures for epidemics and pandemics outbreaks. Recent years have witnessed an explosion in modelling and simulation tools for this domain while emerging technologies such as IoT and remote sensing enable data collection as an unprecedented scale. However fragmentation and siloing of these efforts hamper their effectiveness. This paper argues that the complexity and scale of the challenge calls for an integrated “Big Modelling” approach which would bring all the different elements together to enable a holistic view and analysis and outlines a computation framework that can act as a catalyst in this direction.
{"title":"Global Challenge Governance: Time for Big Modelling?","authors":"Tibor Toth, G. Theodoropoulos, S. Boland, Ibad Kureshi, Adam Ghandar","doi":"10.1109/ICCICC46617.2019.9146059","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146059","url":null,"abstract":"Global emergencies such as epidemics present immense governance challenges to national, political and operational decision-makers. Modelling and Simulation has been identified as a crucial force multiplier in the development and implementation of preparedness and response measures for epidemics and pandemics outbreaks. Recent years have witnessed an explosion in modelling and simulation tools for this domain while emerging technologies such as IoT and remote sensing enable data collection as an unprecedented scale. However fragmentation and siloing of these efforts hamper their effectiveness. This paper argues that the complexity and scale of the challenge calls for an integrated “Big Modelling” approach which would bring all the different elements together to enable a holistic view and analysis and outlines a computation framework that can act as a catalyst in this direction.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126508965","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146069
Ferdous Ahmed, A. Bari, Brandon Sieu, Javad Sadeghi, Jeffrey Scholten, M. Gavrilova
Significant benefits can be achieved through the integration of cognitive computing technologies in healthcare delivery services, including physiotherapy. The traditional approach to physiotherapy requires attaching a marker-based tracking device with the patients and conducting analysis to diagnose by physiotherapists and chiropractors. Tracking efficiency of patient rehabilitation frequently depends on the physiotherapist's notes, which is tedious and prone to errors. In order to streamline the process of data collection and record-keeping, and to make more informed decisions on the effectiveness of prescribed therapy, depth sensors can be integrated with current physician practices. This paper is one of the very first attempts to assist physicians through proprietary Kinect sensor-based technologies. The goal is to make sure static posture estimation is highly accurate. Thus, this paper introduces the solution through a noise reduction framework where the Kalman filter and a recursive noise reduction algorithm are combined to improve the accuracy and the consistency of the human 3D skeleton motion data. The Kalman filter is used for the reduction of tremors by abnormal estimation of body joints in real-time using Kinect v2. The posture correction algorithm is incorporated in the proposed framework to reduce anthropometrically inconsistent estimation of limb lengths of the human body. The proposed posture correction algorithm was extensively validated on the proprietary data set.
{"title":"Kalman Filter-Based Noise Reduction Framework for Posture Estimation Using Depth Sensor","authors":"Ferdous Ahmed, A. Bari, Brandon Sieu, Javad Sadeghi, Jeffrey Scholten, M. Gavrilova","doi":"10.1109/ICCICC46617.2019.9146069","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146069","url":null,"abstract":"Significant benefits can be achieved through the integration of cognitive computing technologies in healthcare delivery services, including physiotherapy. The traditional approach to physiotherapy requires attaching a marker-based tracking device with the patients and conducting analysis to diagnose by physiotherapists and chiropractors. Tracking efficiency of patient rehabilitation frequently depends on the physiotherapist's notes, which is tedious and prone to errors. In order to streamline the process of data collection and record-keeping, and to make more informed decisions on the effectiveness of prescribed therapy, depth sensors can be integrated with current physician practices. This paper is one of the very first attempts to assist physicians through proprietary Kinect sensor-based technologies. The goal is to make sure static posture estimation is highly accurate. Thus, this paper introduces the solution through a noise reduction framework where the Kalman filter and a recursive noise reduction algorithm are combined to improve the accuracy and the consistency of the human 3D skeleton motion data. The Kalman filter is used for the reduction of tremors by abnormal estimation of body joints in real-time using Kinect v2. The posture correction algorithm is incorporated in the proposed framework to reduce anthropometrically inconsistent estimation of limb lengths of the human body. The proposed posture correction algorithm was extensively validated on the proprietary data set.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117192964","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146061
R. Saurabh, N. C. Singh, A. Duraiappah
The purpose of the present education system is economic growth not human flourishing. Recent reports have confirmed that the emphasis on material wellbeing has been at the expense of increasing anxiety, depression, insecurity and poor interpersonal relationships. This has resulted in a worldwide call for education to adopt a more holistic approach. Building on recent research from the neurosciences that demonstrates the need to build emotional along with intellectual intelligence, we advocate a ‘whole brain’ approach to education to achieve human flourishing. We posit that education needs to integrate socio-emotional learning skills in addition to skills of problem solving and logical inquiry. We postulate that such transformative developments in education can be best implemented through experiential learning using digital pedagogies leveraging models of AI. We detail embedded Ontology based User Model that power ‘individualized’ learning through performance based trajectories with appropriate new knowledge and complexity.
{"title":"The Alternate Education for the 21st Century","authors":"R. Saurabh, N. C. Singh, A. Duraiappah","doi":"10.1109/ICCICC46617.2019.9146061","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146061","url":null,"abstract":"The purpose of the present education system is economic growth not human flourishing. Recent reports have confirmed that the emphasis on material wellbeing has been at the expense of increasing anxiety, depression, insecurity and poor interpersonal relationships. This has resulted in a worldwide call for education to adopt a more holistic approach. Building on recent research from the neurosciences that demonstrates the need to build emotional along with intellectual intelligence, we advocate a ‘whole brain’ approach to education to achieve human flourishing. We posit that education needs to integrate socio-emotional learning skills in addition to skills of problem solving and logical inquiry. We postulate that such transformative developments in education can be best implemented through experiential learning using digital pedagogies leveraging models of AI. We detail embedded Ontology based User Model that power ‘individualized’ learning through performance based trajectories with appropriate new knowledge and complexity.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"3 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131437037","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146041
S. Kwong
In June 6th 2016, Cisco released the white paper [1], VNI Forecast and Methodology 2015–2020, reported that 82 percent of Internet traffic will come from video applications such as video surveillance, content delivery network, so on by 2020. It also reported that Internet video surveillance traffic nearly doubled, Virtual reality traffic quadrupled, TV grew 50 percent and similar increases for other applications in 2015. The annual global traffic will first time exceed the zettabyte (ZB;1000 exabytes[EB]) threshold in 2016, and will reach 2.3 ZB by 2020. It implies that 1.886ZB belongs to video data. Thus, in order to relieve the burden on video storage, streaming and other video services, researchers from the video community have developed a series of video coding standards. Among them, the most up-to-date is the High Efficiency Video Coding (HEVC) or H.265 standard, which has successfully halved the coding bits of its predecessor, H.264/AVC, without significant increase in perceived distortion. With the rapid growth of network transmission capacity, enjoying high definition video applications anytime and anywhere with mobile display terminals will be a desirable feature in the near future. Due to the lack of hardware computing power and limited bandwidth, lower complexity and higher compression efficiency video coding scheme are still desired. For higher video compression performance, the key optimization problems, mainly decision making and resource allocation problem, shall be solved. In this talk, I will present the most recent research results on machine learning and game theory based video coding. This is very different from the traditional approaches in video coding. We hope applying these intelligent techniques to vide coding could allow us to go further and have more choices in trading off between cost and resources.
{"title":"Machine Learning based Video Coding using Data-driven Techniques and Advanced Models","authors":"S. Kwong","doi":"10.1109/ICCICC46617.2019.9146041","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146041","url":null,"abstract":"In June 6th 2016, Cisco released the white paper [1], VNI Forecast and Methodology 2015–2020, reported that 82 percent of Internet traffic will come from video applications such as video surveillance, content delivery network, so on by 2020. It also reported that Internet video surveillance traffic nearly doubled, Virtual reality traffic quadrupled, TV grew 50 percent and similar increases for other applications in 2015. The annual global traffic will first time exceed the zettabyte (ZB;1000 exabytes[EB]) threshold in 2016, and will reach 2.3 ZB by 2020. It implies that 1.886ZB belongs to video data. Thus, in order to relieve the burden on video storage, streaming and other video services, researchers from the video community have developed a series of video coding standards. Among them, the most up-to-date is the High Efficiency Video Coding (HEVC) or H.265 standard, which has successfully halved the coding bits of its predecessor, H.264/AVC, without significant increase in perceived distortion. With the rapid growth of network transmission capacity, enjoying high definition video applications anytime and anywhere with mobile display terminals will be a desirable feature in the near future. Due to the lack of hardware computing power and limited bandwidth, lower complexity and higher compression efficiency video coding scheme are still desired. For higher video compression performance, the key optimization problems, mainly decision making and resource allocation problem, shall be solved. In this talk, I will present the most recent research results on machine learning and game theory based video coding. This is very different from the traditional approaches in video coding. We hope applying these intelligent techniques to vide coding could allow us to go further and have more choices in trading off between cost and resources.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125281951","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146103
Yingxu Wang, Omar A. Zatarain, Tony Tsai, D. Graves
Sequence learning from real-time videos is one of the hard challenges to current machine learning technologies and classic neural networks. Since existing supervised learning technologies are heavily dependent on intensive data and prior training, new methodologies for learning temporal sequences by unsupervised learning theories and technologies are yet to be developed. This paper presents the design and implementation of a novel Differential Neural Network (∇NN) for unsupervised sequence learning. The methodology is developed with a set of fundamental theories and enabling technologies for solving the problems of visual object recognition, motion detection, and visual semantic analysis in video sequence. A set of experiments on ∇NN for sequence learning is demonstrated. This work has not only led to a theoretical breakthrough to novel machine sequence learning, but also applicable to a wide range of challenging problems in computational intelligence and the AI industry.
{"title":"Sequence Learning for Images Recognition in Videos with Differential Neural Networks","authors":"Yingxu Wang, Omar A. Zatarain, Tony Tsai, D. Graves","doi":"10.1109/ICCICC46617.2019.9146103","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146103","url":null,"abstract":"Sequence learning from real-time videos is one of the hard challenges to current machine learning technologies and classic neural networks. Since existing supervised learning technologies are heavily dependent on intensive data and prior training, new methodologies for learning temporal sequences by unsupervised learning theories and technologies are yet to be developed. This paper presents the design and implementation of a novel Differential Neural Network (∇NN) for unsupervised sequence learning. The methodology is developed with a set of fundamental theories and enabling technologies for solving the problems of visual object recognition, motion detection, and visual semantic analysis in video sequence. A set of experiments on ∇NN for sequence learning is demonstrated. This work has not only led to a theoretical breakthrough to novel machine sequence learning, but also applicable to a wide range of challenging problems in computational intelligence and the AI industry.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130305188","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146046
Junjie Bai, Jun Peng, Xue Zhang, Xiuyan Zhang, Zuojin Li, Jing Huang, Kan Luo, Jianxing Li
Using thermal tactile sensing mechanism based on semi-infinite body model, and combining with the advantages of maximum proportional controller, fuzzy and PID controller, a thermal tactile perception and reproduction experiment device (TTPRED) was designed based on the composite control strategy of threshold switching. The finger difference threshold measurement experiment of thermal tactile was carried out and the finger thermal tactile difference threshold was measured. The experiment results show that, the temperature control range of TTPRED is from −10°C to 130°C, the temperature resolution and precision are 0.01°e and ±0.1 °C respectively, the maximum heating or cooling rate is greater than 12 °C, and the TTPRED can realize the temperature output of the specific waveform quickly and accurately. The experiment results of psychophysical experiment will provide the experimental foundations and technical support for the further study of thermal tactile perception and reproduction.
{"title":"Thermal Tactile Experiment Device Based on Fuzzy PID Controller and Perception Experiments","authors":"Junjie Bai, Jun Peng, Xue Zhang, Xiuyan Zhang, Zuojin Li, Jing Huang, Kan Luo, Jianxing Li","doi":"10.1109/ICCICC46617.2019.9146046","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146046","url":null,"abstract":"Using thermal tactile sensing mechanism based on semi-infinite body model, and combining with the advantages of maximum proportional controller, fuzzy and PID controller, a thermal tactile perception and reproduction experiment device (TTPRED) was designed based on the composite control strategy of threshold switching. The finger difference threshold measurement experiment of thermal tactile was carried out and the finger thermal tactile difference threshold was measured. The experiment results show that, the temperature control range of TTPRED is from −10°C to 130°C, the temperature resolution and precision are 0.01°e and ±0.1 °C respectively, the maximum heating or cooling rate is greater than 12 °C, and the TTPRED can realize the temperature output of the specific waveform quickly and accurately. The experiment results of psychophysical experiment will provide the experimental foundations and technical support for the further study of thermal tactile perception and reproduction.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129034108","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146034
R. Fiorini
In previous paper we showed that Symbiotic System Science (SSS) is a growing scientific area which is taking a leadership role in fostering consensus on how best to bring about symbiotic relationships between autonomous systems. Capitalizing on SSS insights and development, the recognition that SAS (Symbiotic Autonomous Systems) are poised to have a revolutionary impact on society over the coming years is quite straightforward. The promise of SSS is to reveal a convenient roadmap to arrive to Human-centered Symbiotic System Science (HCSSS) to develop more reliable Human-centered Symbiotic System (HCSS), to fully utilize the capabilities of cognitive computing and brain-inspired system as support for more effective application of our higher human faculties. In present paper we discuss HCSSS to bring about symbiotic relationships between HCSS, as evidenced by the living human brain modalities, supported by the CICT OUM framework.
{"title":"Human-Centered Symbiotic System Science","authors":"R. Fiorini","doi":"10.1109/ICCICC46617.2019.9146034","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146034","url":null,"abstract":"In previous paper we showed that Symbiotic System Science (SSS) is a growing scientific area which is taking a leadership role in fostering consensus on how best to bring about symbiotic relationships between autonomous systems. Capitalizing on SSS insights and development, the recognition that SAS (Symbiotic Autonomous Systems) are poised to have a revolutionary impact on society over the coming years is quite straightforward. The promise of SSS is to reveal a convenient roadmap to arrive to Human-centered Symbiotic System Science (HCSSS) to develop more reliable Human-centered Symbiotic System (HCSS), to fully utilize the capabilities of cognitive computing and brain-inspired system as support for more effective application of our higher human faculties. In present paper we discuss HCSSS to bring about symbiotic relationships between HCSS, as evidenced by the living human brain modalities, supported by the CICT OUM framework.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127673063","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146101
Z. Qu, Z. Ding, P. Moo
A machine learning radar scheduling method is proposed based on the earliest start time (EST) algorithm. In this method, the EST algorithm is used to find an initial schedule, and a reinforcement learning approach is conducted to reduce the cost of the initial schedule. In search for a better starting point, the start time of all the tasks are randomly shifted within their allowed time ranges, the shifted tasks are scheduled with the EST again. Then the gradient descent algorithm is applied to further shift the tasks' start times, in order to find an enhanced solution. The procedure is repeated several times. The schedule with the minimal cost is the final solution. The performance of the proposed method is evaluated numerically, showing 1.3 to 10.5 times less cost than the EST, depending on the scenario. In addition, a full cycle of scheduling takes a few tens of milliseconds thus the method could be considered in real radar systems.
{"title":"A Machine Learning Radar Scheduling Method Based on the EST Algorithm","authors":"Z. Qu, Z. Ding, P. Moo","doi":"10.1109/ICCICC46617.2019.9146101","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146101","url":null,"abstract":"A machine learning radar scheduling method is proposed based on the earliest start time (EST) algorithm. In this method, the EST algorithm is used to find an initial schedule, and a reinforcement learning approach is conducted to reduce the cost of the initial schedule. In search for a better starting point, the start time of all the tasks are randomly shifted within their allowed time ranges, the shifted tasks are scheduled with the EST again. Then the gradient descent algorithm is applied to further shift the tasks' start times, in order to find an enhanced solution. The procedure is repeated several times. The schedule with the minimal cost is the final solution. The performance of the proposed method is evaluated numerically, showing 1.3 to 10.5 times less cost than the EST, depending on the scenario. In addition, a full cycle of scheduling takes a few tens of milliseconds thus the method could be considered in real radar systems.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121270357","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146065
W. Kinsner
The complexity of a deterministic differentiable process is lower than that of a stochastic nondifferentiable process. Measuring the complexity of such processes may be useful in extracting objective features from the processes for their classification in either reactive, adaptive, or predictive control. This applies to classifiers based not only on the traditional neural networks, but also on deep learning systems, and particularly in cognitive systems. This paper describes a robust algorithm to measure the variance complexity of a self-affine time series using multiscale and polyscale analyses, and provides new insight in the theoretical and practical aspects of extracting the measure.
{"title":"A Robust Variance Complexity Measure for Stochastic Self-Affine Processes","authors":"W. Kinsner","doi":"10.1109/ICCICC46617.2019.9146065","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146065","url":null,"abstract":"The complexity of a deterministic differentiable process is lower than that of a stochastic nondifferentiable process. Measuring the complexity of such processes may be useful in extracting objective features from the processes for their classification in either reactive, adaptive, or predictive control. This applies to classifiers based not only on the traditional neural networks, but also on deep learning systems, and particularly in cognitive systems. This paper describes a robust algorithm to measure the variance complexity of a self-affine time series using multiscale and polyscale analyses, and provides new insight in the theoretical and practical aspects of extracting the measure.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126591742","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 : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146044
M. Pandey, Rituparna Datta, Rajarshi Dey, B. Bhattacharya
The optimization problem of the carbody dynamic response for a freight wagon fitted with three-piece bogie can be formulated as a multi-objective optimisation problem wherein four of the dynamic response parameters i.e. vertical acceleration on straight track in empty and loaded condition, lateral acceleration on 2° curve in empty and loaded condition, may be selected as representative objective functions for the overall dynamic response of the freight wagon. In this paper, attempts are made to form non-linear regression equations with experimental data to formulate the objective functions. After that, computational intelligence based evolutionary multi-objective optimisation is used to solve the problem and Pareto fronts are drawn for the objective functions using NSGA-II. Subsequently, the weighted optimization problem is solved for a different combination of weights.
{"title":"Multi-objective Optimisation of Dynamic Responses for a Rail Freight Wagon using Regression Models","authors":"M. Pandey, Rituparna Datta, Rajarshi Dey, B. Bhattacharya","doi":"10.1109/ICCICC46617.2019.9146044","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146044","url":null,"abstract":"The optimization problem of the carbody dynamic response for a freight wagon fitted with three-piece bogie can be formulated as a multi-objective optimisation problem wherein four of the dynamic response parameters i.e. vertical acceleration on straight track in empty and loaded condition, lateral acceleration on 2° curve in empty and loaded condition, may be selected as representative objective functions for the overall dynamic response of the freight wagon. In this paper, attempts are made to form non-linear regression equations with experimental data to formulate the objective functions. After that, computational intelligence based evolutionary multi-objective optimisation is used to solve the problem and Pareto fronts are drawn for the objective functions using NSGA-II. Subsequently, the weighted optimization problem is solved for a different combination of weights.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126974091","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：