Pub Date : 2019-07-01DOI: 10.1109/ICCICC46617.2019.9146067
A. Shaukat, Ammar Younis, M. Akram, M. Mohsin, Zartasha Mustansar
An automated system is proposed to recognize different sounds from the daily living activity of humans. Such automated systems can assist the humans and caretakers to recognize any abnormal sound activity and take instant actions. The sound detection model is proposed, which recognizes sounds of the daily activity of an individual. Three Benchmark datasets are used to test our proposed model. The datasets used for our system are Real World Computing Partnership Sound Database in Real Acoustical Environment (RWCP-DB), Urban Sound8K and ESC10 data set. We used Linear Spectrogram, MFCC, Gamma tone Spectrogram as a base line for feature extraction using Convolution Neural Networks (CNN). We proposed two models based on CNN and CNN-SVM architecture and also trained Alex Net and Goggle Net using transfer learning. Our system performed well on different combinations of features and showed improved classification accuracy. Our system performed well in comparison with the other methods reported in literature.
提出了一种自动识别人类日常生活活动中不同声音的系统。这种自动化系统可以帮助人类和看护人员识别任何异常的声音活动，并立即采取行动。提出了声音检测模型，该模型能够识别个体日常活动的声音。三个基准数据集被用来测试我们提出的模型。本系统使用的数据集是Real World Computing Partnership Sound Database in Real acoustic Environment (RWCP-DB)、Urban Sound8K和ESC10数据集。我们使用线性谱图、MFCC、Gamma tone谱图作为基线，使用卷积神经网络(CNN)进行特征提取。我们提出了两个基于CNN和CNN- svm架构的模型，并使用迁移学习训练了Alex Net和Goggle Net。我们的系统在不同的特征组合上表现良好，并显示出更高的分类精度。与文献报道的其他方法相比，我们的系统表现良好。
{"title":"Towards Automatic Recognition of Sounds Observed in Daily Living Activity","authors":"A. Shaukat, Ammar Younis, M. Akram, M. Mohsin, Zartasha Mustansar","doi":"10.1109/ICCICC46617.2019.9146067","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146067","url":null,"abstract":"An automated system is proposed to recognize different sounds from the daily living activity of humans. Such automated systems can assist the humans and caretakers to recognize any abnormal sound activity and take instant actions. The sound detection model is proposed, which recognizes sounds of the daily activity of an individual. Three Benchmark datasets are used to test our proposed model. The datasets used for our system are Real World Computing Partnership Sound Database in Real Acoustical Environment (RWCP-DB), Urban Sound8K and ESC10 data set. We used Linear Spectrogram, MFCC, Gamma tone Spectrogram as a base line for feature extraction using Convolution Neural Networks (CNN). We proposed two models based on CNN and CNN-SVM architecture and also trained Alex Net and Goggle Net using transfer learning. Our system performed well on different combinations of features and showed improved classification accuracy. Our system performed well in comparison with the other methods reported in literature.","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":"130460586","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/ICCICC46617.2019.9146045
Wei Ding, Tao Wu, Chengwang Liao, Junchang Wang, Yong Jiang
Data acquisition system is a key instrument to convert analog signals to digital signals in geophysics. To match high resolution sensors in seismometers systems, high resolution analog-digital conversion (ADC) is deployed in data acquisition system. Classical high resolution ADC models are based on architecture of Σ-Δ oversampling or pipeline ADC architecture separately. Those ADC architectures have following problems: increase power consumption, reduce linearity of modulators, depend on design of complex circuit, and the resolution is not easily regulated. To solve those problems and promote resolution of ADC, a novel architecture design is presented, which design principle is based on mathematical formulations combined advantages both previous pipeline and oversampling ADC architecture. A simple and mathematical combined ADC analysis model is presented. Using this model, this paper analyzes theoretically the various sources of noise of the adverse effects of the whole ADC architecture. Based on an assessment of noise simulation algorithm, an amended theoretical model is proposed. The results represent that noises level of integrator and subtractor in first level of combined model determine the whole performance. By controlling the noise level from these two components to less than 10−7V/✓Hz, the resolution of whole data acquisition system can achieve reservation resolution of 150 dB.
{"title":"A High Resolution ADC Model Combined Pipeline and Sigma -Delta Oversampling Architecture","authors":"Wei Ding, Tao Wu, Chengwang Liao, Junchang Wang, Yong Jiang","doi":"10.1109/ICCICC46617.2019.9146045","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146045","url":null,"abstract":"Data acquisition system is a key instrument to convert analog signals to digital signals in geophysics. To match high resolution sensors in seismometers systems, high resolution analog-digital conversion (ADC) is deployed in data acquisition system. Classical high resolution ADC models are based on architecture of Σ-Δ oversampling or pipeline ADC architecture separately. Those ADC architectures have following problems: increase power consumption, reduce linearity of modulators, depend on design of complex circuit, and the resolution is not easily regulated. To solve those problems and promote resolution of ADC, a novel architecture design is presented, which design principle is based on mathematical formulations combined advantages both previous pipeline and oversampling ADC architecture. A simple and mathematical combined ADC analysis model is presented. Using this model, this paper analyzes theoretically the various sources of noise of the adverse effects of the whole ADC architecture. Based on an assessment of noise simulation algorithm, an amended theoretical model is proposed. The results represent that noises level of integrator and subtractor in first level of combined model determine the whole performance. By controlling the noise level from these two components to less than 10−7V/✓Hz, the resolution of whole data acquisition system can achieve reservation resolution of 150 dB.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"36 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":"131236753","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/ICCICC46617.2019.9146050
Ying Huang, Yingxu Wang, Omar A. Zatarain
Robot is an autonomous system that integrates advances AI technologies. This paper deals with the adaptive path planning and optimization problems for robots in dynamic environments. We propose a novel route planning method based on the maze representation of workplace layouts. We generate a universal path tree by a path optimization algorithm. Then, any given entrances and exits of target nodes can be reduced to a deterministic path searching problem. Our method can quickly determine the optimal path between any pair of entrance/exit nodes. The maze-based method provides an efficient and robust route planning solution for robots in real-time and dynamic workplaces. Experiments have demonstrated the effectiveness of the method beyond traditional heuristic technologies.
{"title":"Dynamic Path Optimization for Robot Route Planning","authors":"Ying Huang, Yingxu Wang, Omar A. Zatarain","doi":"10.1109/ICCICC46617.2019.9146050","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146050","url":null,"abstract":"Robot is an autonomous system that integrates advances AI technologies. This paper deals with the adaptive path planning and optimization problems for robots in dynamic environments. We propose a novel route planning method based on the maze representation of workplace layouts. We generate a universal path tree by a path optimization algorithm. Then, any given entrances and exits of target nodes can be reduced to a deterministic path searching problem. Our method can quickly determine the optimal path between any pair of entrance/exit nodes. The maze-based method provides an efficient and robust route planning solution for robots in real-time and dynamic workplaces. Experiments have demonstrated the effectiveness of the method beyond traditional heuristic technologies.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"45 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":"131323488","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/ICCICC46617.2019.9146092
Nagaraju Devarakonda, S. Anandarao, Raviteja Kamarajugadda, Yingxu Wang
In many applications, the feature selection plays an important role, as best feature can bring out the accurate results. The features selected must represent the entire dataset. Here we have considered “Sequential Forward Selection” for feature extraction and used refined dragonfly algorithm to approach and to migrate from the best and worst features respectively. We improvised the conventional dragonfly algorithm by adding the convergence and fitness functions. To access the accuracy of the algorithm we introduced the fitness function. This paper has discussed about the general hunting behaviour of the dragonfly and dragonfly algorithm (DA) with convergence and fitness functions. A comparative study was shown for the best search agent position between modified DA and traditional DA, at the same time test function values of refined dragonfly algorithm (RDA) is compared with whale optimization algorithm (WOA) and Tornadogenesis Optimization algorithm (TOA). We have evaluated refined DA on the 23 benchmark function corresponding values are shown in experiment.
{"title":"Unique Dragonfly Optimization Algorithm for Harvesting and Clustering the Key Features","authors":"Nagaraju Devarakonda, S. Anandarao, Raviteja Kamarajugadda, Yingxu Wang","doi":"10.1109/ICCICC46617.2019.9146092","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146092","url":null,"abstract":"In many applications, the feature selection plays an important role, as best feature can bring out the accurate results. The features selected must represent the entire dataset. Here we have considered “Sequential Forward Selection” for feature extraction and used refined dragonfly algorithm to approach and to migrate from the best and worst features respectively. We improvised the conventional dragonfly algorithm by adding the convergence and fitness functions. To access the accuracy of the algorithm we introduced the fitness function. This paper has discussed about the general hunting behaviour of the dragonfly and dragonfly algorithm (DA) with convergence and fitness functions. A comparative study was shown for the best search agent position between modified DA and traditional DA, at the same time test function values of refined dragonfly algorithm (RDA) is compared with whale optimization algorithm (WOA) and Tornadogenesis Optimization algorithm (TOA). We have evaluated refined DA on the 23 benchmark function corresponding values are shown in experiment.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"7 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":"121294593","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/ICCICC46617.2019.9146080
Hong Liu, Yuanyuan Huang, Xiaoyu Zhang, Zujie Bie, Jiayue Gu, Long He
Fracability is used to evaluate if it's easy to form complex fracture networks by the volumetric fracturing in shale gas or not. The main parameters of shale gas fracability evaluation methods at home and abroad are analyzed and summarized, combining the characteristics of high temperature, high pressure and strong plasticity in deep shale gas layers, the comprehensive evaluation parameters of deep shale reservoirs fracability based on the geological and engineering factors are optimized. Fully considering the effects of formation confining pressure and rock anisotropy on parameters, the calculation method of fracability evaluation parameters is formed. Using fuzzy grey correlation analysis method, the correlation between the fracability index curve of different weight combinations and the fracture complexity index curve is analyzed. According to the maximum principle of correlation coefficient, the weight combination is optimized, the comprehensive evaluation mathematical model of fracability is established, and the comprehensive evaluation method of deep shale gas fracability is formed. It is of guiding significance to the optimization design of fracturing parameters for deep shale gas to improve fracture complexity.
{"title":"Fracability Evaluation in Deep Shale Reservoirs Based on a Fuzzy Grey Correlation Analysis Method","authors":"Hong Liu, Yuanyuan Huang, Xiaoyu Zhang, Zujie Bie, Jiayue Gu, Long He","doi":"10.1109/ICCICC46617.2019.9146080","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146080","url":null,"abstract":"Fracability is used to evaluate if it's easy to form complex fracture networks by the volumetric fracturing in shale gas or not. The main parameters of shale gas fracability evaluation methods at home and abroad are analyzed and summarized, combining the characteristics of high temperature, high pressure and strong plasticity in deep shale gas layers, the comprehensive evaluation parameters of deep shale reservoirs fracability based on the geological and engineering factors are optimized. Fully considering the effects of formation confining pressure and rock anisotropy on parameters, the calculation method of fracability evaluation parameters is formed. Using fuzzy grey correlation analysis method, the correlation between the fracability index curve of different weight combinations and the fracture complexity index curve is analyzed. According to the maximum principle of correlation coefficient, the weight combination is optimized, the comprehensive evaluation mathematical model of fracability is established, and the comprehensive evaluation method of deep shale gas fracability is formed. It is of guiding significance to the optimization design of fracturing parameters for deep shale gas to improve fracture complexity.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"76 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":"123822159","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/ICCICC46617.2019.9146027
M. Burgin, P. Rocchi
This paper assumes probability is a bridge linking cognition and computing. We begin with the dynamic and causal structuring of random events and represent them in the form of ‘named sets’. We construct a probability function called ‘ample probability’ for such events and develop elements of an axiomatic ample probability theory. The proposed axioms are consistent and independent giving in the limit Kolmogorov's axiom system for conventional probability. In addition, we comment on the relations between ample probability, conditional probability and quantum probability.
{"title":"Ample Probability in Cognition","authors":"M. Burgin, P. Rocchi","doi":"10.1109/ICCICC46617.2019.9146027","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146027","url":null,"abstract":"This paper assumes probability is a bridge linking cognition and computing. We begin with the dynamic and causal structuring of random events and represent them in the form of ‘named sets’. We construct a probability function called ‘ample probability’ for such events and develop elements of an axiomatic ample probability theory. The proposed axioms are consistent and independent giving in the limit Kolmogorov's axiom system for conventional probability. In addition, we comment on the relations between ample probability, conditional probability and quantum probability.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"25 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":"130637827","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/ICCICC46617.2019.9146091
N. Saavedra-Rivano
This paper analyzes the short-term and longer-term impacts of AI. While the short-term impact is deemed to be mostly positive, the longer-term impacts are considered to be disastrous under a variety of scenarios, including the adoption of man-machine symbiosis tools. The paper offers suggestions as to policy measures that could correct this disastrous outlook.
{"title":"AI and Us: Existential Risk or Transformational Tool?","authors":"N. Saavedra-Rivano","doi":"10.1109/ICCICC46617.2019.9146091","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146091","url":null,"abstract":"This paper analyzes the short-term and longer-term impacts of AI. While the short-term impact is deemed to be mostly positive, the longer-term impacts are considered to be disastrous under a variety of scenarios, including the adoption of man-machine symbiosis tools. The paper offers suggestions as to policy measures that could correct this disastrous outlook.","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":"129796405","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/ICCICC46617.2019.9146100
Qi Liu, Hongguang Liu, Lei Zhang
Concealed information test based on P300 and machine learning has become increasingly popular in the fields of cognitive psychology. Numerous studies have set up mock crime scenario to identify changes in EEG cognitive components. However, only two kinds of subjects are taken into account in most previous studies. Therefore, if an innocent person had been aware of case-related information, i.e., probe items, which is likely to happen in practice, recognition capability will be significantly compromised. In order to simulate practical cases, three kinds of subjects needed to be discriminated, including guilty, innocent and informed. 36 subjects went through a mock crime scenario, and EEG signals obtained on 8 electrodes were analyzed. After preprocessing, the discrete wavelet packet decomposition was used to extract EEG features. Subsequently, a multi-scale wavelet kernel extreme learning machine classifier is proposed to recognize the group to which a specific subject belongs. To further reduce computation, Cholesky decomposition is introduced during the calculation of the output weights. Our results demonstrate that the proposed algorithm can achieve good recognition performance and has low computational burden.
{"title":"Awareness of Crime-related Information and Concealed Information Detection method","authors":"Qi Liu, Hongguang Liu, Lei Zhang","doi":"10.1109/ICCICC46617.2019.9146100","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146100","url":null,"abstract":"Concealed information test based on P300 and machine learning has become increasingly popular in the fields of cognitive psychology. Numerous studies have set up mock crime scenario to identify changes in EEG cognitive components. However, only two kinds of subjects are taken into account in most previous studies. Therefore, if an innocent person had been aware of case-related information, i.e., probe items, which is likely to happen in practice, recognition capability will be significantly compromised. In order to simulate practical cases, three kinds of subjects needed to be discriminated, including guilty, innocent and informed. 36 subjects went through a mock crime scenario, and EEG signals obtained on 8 electrodes were analyzed. After preprocessing, the discrete wavelet packet decomposition was used to extract EEG features. Subsequently, a multi-scale wavelet kernel extreme learning machine classifier is proposed to recognize the group to which a specific subject belongs. To further reduce computation, Cholesky decomposition is introduced during the calculation of the output weights. Our results demonstrate that the proposed algorithm can achieve good recognition performance and has low computational burden.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"11 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":"132562361","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/ICCICC46617.2019.9146095
W. Kinsner, R. Saracco
In the past, professional education lasted for a lifetime. Since then, the industrial revolutions have accelerated the pace of knowledge doubling from a lifetime to months, and have altered the working environment so that professionals will have to move between many jobs in their life. Are we capable of adjusting to that pace? How can we learn all that is needed in the old educational system? The time has come to revamp the educational system at the core. The new system must be personalized to match the diversity of individual abilities and styles of learning. The new system must also be based not only on the body of knowledge (BoK), but body of experience (BoX). We envisage that the new personalized system of education being sufficiently agile and interactive so that it would become evolving in its symbiosis with humans. For that to happen, we must coexist with symbiotic autonomous cognitive systems, specifically involving digital twins. This paper addresses some aspects of this view.
{"title":"Towards Evolving Symbiotic Cognitive Education Based on Digital Twins","authors":"W. Kinsner, R. Saracco","doi":"10.1109/ICCICC46617.2019.9146095","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146095","url":null,"abstract":"In the past, professional education lasted for a lifetime. Since then, the industrial revolutions have accelerated the pace of knowledge doubling from a lifetime to months, and have altered the working environment so that professionals will have to move between many jobs in their life. Are we capable of adjusting to that pace? How can we learn all that is needed in the old educational system? The time has come to revamp the educational system at the core. The new system must be personalized to match the diversity of individual abilities and styles of learning. The new system must also be based not only on the body of knowledge (BoK), but body of experience (BoX). We envisage that the new personalized system of education being sufficiently agile and interactive so that it would become evolving in its symbiosis with humans. For that to happen, we must coexist with symbiotic autonomous cognitive systems, specifically involving digital twins. This paper addresses some aspects of this view.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"07 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":"127243881","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/ICCICC46617.2019.9146066
Kei Takahata, T. Miura
In this investigation, we discuss a game of pursuit-evasion, or a hunter-prey problems using Q-learning framework. This has always been a popular research subject in the field of robotics where a hunter moves around in pursuit a prey. We involve Kalman filters to estimate the prey's status (location and velocity) and learn Q-values based on the estimated status. We evaluate our approach by convergence of Q-values and capturing steps.
{"title":"Reinforcement Learning using Kalman Filters","authors":"Kei Takahata, T. Miura","doi":"10.1109/ICCICC46617.2019.9146066","DOIUrl":"https://doi.org/10.1109/ICCICC46617.2019.9146066","url":null,"abstract":"In this investigation, we discuss a game of pursuit-evasion, or a hunter-prey problems using Q-learning framework. This has always been a popular research subject in the field of robotics where a hunter moves around in pursuit a prey. We involve Kalman filters to estimate the prey's status (location and velocity) and learn Q-values based on the estimated status. We evaluate our approach by convergence of Q-values and capturing steps.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"207 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120864981","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：