Pub Date : 2017-11-01DOI: 10.1109/SSCI.2017.8285177
D. Chitty, Shengxiang Yang, M. Gongora
Reducing costs whilst maintaining passenger satisfaction is an important problem for airports. One area this can be applied is the security lane checks at the airport. However, reducing costs through reducing lane openings typically increases queue length and hence passenger dissatisfaction. This paper demonstrates that evolutionary methods can be used to optimise airport security lane schedules such that passenger dissatisfaction and staffing costs can be minimised. However, it is shown that these schedules typically over-fit the forecasts of passenger arrivals at security such that in actuality significant passenger delays can occur with deviations from the forecast. Consequently, this paper further demonstrates that dynamic evolutionary re-optimisation of these schedules can significantly mitigate this over-fitting problem with much reduced passenger delays.
{"title":"Evolutionary dynamic optimisation of airport security lane schedules","authors":"D. Chitty, Shengxiang Yang, M. Gongora","doi":"10.1109/SSCI.2017.8285177","DOIUrl":"https://doi.org/10.1109/SSCI.2017.8285177","url":null,"abstract":"Reducing costs whilst maintaining passenger satisfaction is an important problem for airports. One area this can be applied is the security lane checks at the airport. However, reducing costs through reducing lane openings typically increases queue length and hence passenger dissatisfaction. This paper demonstrates that evolutionary methods can be used to optimise airport security lane schedules such that passenger dissatisfaction and staffing costs can be minimised. However, it is shown that these schedules typically over-fit the forecasts of passenger arrivals at security such that in actuality significant passenger delays can occur with deviations from the forecast. Consequently, this paper further demonstrates that dynamic evolutionary re-optimisation of these schedules can significantly mitigate this over-fitting problem with much reduced passenger delays.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115606436","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 : 2016-12-31DOI: 10.1109/SSCI.2016.7850087
Kenneth N. Reid, Jingpeng Li, J. Swan, A. McCormick, G. Owusu
This paper describes a Variable Neighbourhood Search (VNS) combined with Metropolis-Hastings acceptance to tackle a highly constrained workforce scheduling problem typical of field service operations (FSO) companies. A refined greedy algorithm is firstly designed to create an initial solution which meets all hard constraints and satisfies some of the soft constraints. The VNS is then used to swap out less promising combinations, continually moving towards a optimal solution until meeting finishing requirements, which are either a satisfactory mean fitness set as a parameter, or a time allowance of one hour. The results of this approach are promising when compared to the stand-alone greedy algorithm, and have showed an average of 10.3% increase in fitness when parameterized with expected demand data and real employee data.
{"title":"Variable Neighbourhood Search: A case study for a highly-constrained workforce scheduling problem","authors":"Kenneth N. Reid, Jingpeng Li, J. Swan, A. McCormick, G. Owusu","doi":"10.1109/SSCI.2016.7850087","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850087","url":null,"abstract":"This paper describes a Variable Neighbourhood Search (VNS) combined with Metropolis-Hastings acceptance to tackle a highly constrained workforce scheduling problem typical of field service operations (FSO) companies. A refined greedy algorithm is firstly designed to create an initial solution which meets all hard constraints and satisfies some of the soft constraints. The VNS is then used to swap out less promising combinations, continually moving towards a optimal solution until meeting finishing requirements, which are either a satisfactory mean fitness set as a parameter, or a time allowance of one hour. The results of this approach are promising when compared to the stand-alone greedy algorithm, and have showed an average of 10.3% increase in fitness when parameterized with expected demand data and real employee data.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116122446","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 : 2016-12-09DOI: 10.1109/SSCI.2016.7850109
C. Maddock, E. Minisci
In this paper, an evolutionary-based initialisation method is proposed based on Adaptive Inflationary Differential Evolution algorithm, which is used in conjunction with a deterministic local optimisation algorithm to efficiently identify clusters of optimal solutions. The approach is applied to an ascent trajectory for a single stage to orbit spaceplane, employing a rocket-based combine cycle propulsion system. The problem is decomposed first into flight phases, based on user defined criteria such as a propulsion cycle change translating to different mathematical system models, and subsequently transcribed into a multi-shooting NLP problem. Examining the results based on 10 independent runs of the approach, it can be seen that in all cases the method converges to clusters of feasible solutions. In 40% of the cases, the AIDEA-based initialisation found a better solution compared to a heuristic approach using constant control for each phase with a single shooting transcription (representing an expert user). The problem was run using randomly generated control laws, only 2/20 cases converged, both times with a less optimal solution compared to the baseline heuristic approach and AIDEA.
{"title":"Spaceplane trajectory optimisation with evolutionary-based initialisation","authors":"C. Maddock, E. Minisci","doi":"10.1109/SSCI.2016.7850109","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850109","url":null,"abstract":"In this paper, an evolutionary-based initialisation method is proposed based on Adaptive Inflationary Differential Evolution algorithm, which is used in conjunction with a deterministic local optimisation algorithm to efficiently identify clusters of optimal solutions. The approach is applied to an ascent trajectory for a single stage to orbit spaceplane, employing a rocket-based combine cycle propulsion system. The problem is decomposed first into flight phases, based on user defined criteria such as a propulsion cycle change translating to different mathematical system models, and subsequently transcribed into a multi-shooting NLP problem. Examining the results based on 10 independent runs of the approach, it can be seen that in all cases the method converges to clusters of feasible solutions. In 40% of the cases, the AIDEA-based initialisation found a better solution compared to a heuristic approach using constant control for each phase with a single shooting transcription (representing an expert user). The problem was run using randomly generated control laws, only 2/20 cases converged, both times with a less optimal solution compared to the baseline heuristic approach and AIDEA.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123671733","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 : 2016-12-09DOI: 10.1109/SSCI.2016.7850081
Jianjun Chen, Ruibin Bai, Haibo Dong, R. Qu, G. Kendall
In this paper, a dynamic truck dispatching problem of a marine container terminal is described and discussed. In this problem, a few containers, encoded as work instructions, need to be transferred between yard blocks and vessels by a fleet of trucks. Both the yard blocks and the quay are equipped with cranes to support loading/unloading operations. In order to service more vessels, any unnecessary idle time between quay crane (QC) operations need to be minimised to speed up the container transfer process. Due to the unpredictable port situations that can affect routing plans and the short calculation time allowed to generate one, static solution methods are not suitable for this problem. In this paper, we introduce a new mathematical model that minimises both the QC makespan and the truck travelling time. Three dynamic heuristics are proposed and a genetic algorithm hyperheuristic (GAHH) under development is also described. Experiment results show promising capabilities the GAHH may offer.
{"title":"A dynamic truck dispatching problem in marine container terminal","authors":"Jianjun Chen, Ruibin Bai, Haibo Dong, R. Qu, G. Kendall","doi":"10.1109/SSCI.2016.7850081","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850081","url":null,"abstract":"In this paper, a dynamic truck dispatching problem of a marine container terminal is described and discussed. In this problem, a few containers, encoded as work instructions, need to be transferred between yard blocks and vessels by a fleet of trucks. Both the yard blocks and the quay are equipped with cranes to support loading/unloading operations. In order to service more vessels, any unnecessary idle time between quay crane (QC) operations need to be minimised to speed up the container transfer process. Due to the unpredictable port situations that can affect routing plans and the short calculation time allowed to generate one, static solution methods are not suitable for this problem. In this paper, we introduce a new mathematical model that minimises both the QC makespan and the truck travelling time. Three dynamic heuristics are proposed and a genetic algorithm hyperheuristic (GAHH) under development is also described. Experiment results show promising capabilities the GAHH may offer.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121897817","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 : 2016-12-09DOI: 10.1109/SSCI.2016.7850117
P. Angelov, Xiaowei Gu
In this paper, a new data partitioning algorithm, named “local modes-based data partitioning”, is proposed. This algorithm is entirely data-driven and free from any user input and prior assumptions. It automatically derives the modes of the empirically observed density of the data samples and results in forming parameter-free data clouds. The identified focal points resemble Voronoi tessellations. The proposed algorithm has two versions, namely, offline and evolving. The two versions are both able to work separately and start “from scratch”, they can also perform a hybrid. Numerical experiments demonstrate the validity of the proposed algorithm as a fully autonomous partitioning technique, and achieve better performance compared with alternative algorithms.
{"title":"Local modes-based free-shape data partitioning","authors":"P. Angelov, Xiaowei Gu","doi":"10.1109/SSCI.2016.7850117","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850117","url":null,"abstract":"In this paper, a new data partitioning algorithm, named “local modes-based data partitioning”, is proposed. This algorithm is entirely data-driven and free from any user input and prior assumptions. It automatically derives the modes of the empirically observed density of the data samples and results in forming parameter-free data clouds. The identified focal points resemble Voronoi tessellations. The proposed algorithm has two versions, namely, offline and evolving. The two versions are both able to work separately and start “from scratch”, they can also perform a hybrid. Numerical experiments demonstrate the validity of the proposed algorithm as a fully autonomous partitioning technique, and achieve better performance compared with alternative algorithms.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121401314","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 : 2016-12-08DOI: 10.1109/SSCI.2016.7850158
Kai-Ming Chang, M. D. Planque, K. Zauner
All known forms of life utilise information processing to maintain their complex organisation. In contrast to conventional information technology built on solid-state semiconductor devices, biological information processing is built on transformations through chemical reactions and interactions mediated by diffusion. The theoretical understanding of reaction-diffusion computing as well as prototype implementations have progressed in parallel over the past decades. We report here on a technique for studying spatially structured networks in which chemicals are compartmentalised as droplets-in-oil and laser-cut topologies impose spatial structure. Experiments with halogen displacement reactions demonstrate that the feature size achievable with laser cutting is well suited to practical diffusion time scales. Further advantages of the technique are the optical accessibility, enabling readout from bromine and iodine production, diffusion and indicator reactions, and the good chemical compatibility between the compartmentalisation medium (oil) and the structuring medium (PMMA), while the fast turn-around times enable rapid topology optimisation.
{"title":"Fabricating millifluidic reaction-diffusion devices: Droplet-in-oil networks structured by laser cutting","authors":"Kai-Ming Chang, M. D. Planque, K. Zauner","doi":"10.1109/SSCI.2016.7850158","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850158","url":null,"abstract":"All known forms of life utilise information processing to maintain their complex organisation. In contrast to conventional information technology built on solid-state semiconductor devices, biological information processing is built on transformations through chemical reactions and interactions mediated by diffusion. The theoretical understanding of reaction-diffusion computing as well as prototype implementations have progressed in parallel over the past decades. We report here on a technique for studying spatially structured networks in which chemicals are compartmentalised as droplets-in-oil and laser-cut topologies impose spatial structure. Experiments with halogen displacement reactions demonstrate that the feature size achievable with laser cutting is well suited to practical diffusion time scales. Further advantages of the technique are the optical accessibility, enabling readout from bromine and iodine production, diffusion and indicator reactions, and the good chemical compatibility between the compartmentalisation medium (oil) and the structuring medium (PMMA), while the fast turn-around times enable rapid topology optimisation.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122415856","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 : 2016-12-08DOI: 10.1109/SSCI.2016.7850014
Luis Montesdeoca, M. Niranjan
Prices of derivative contracts, such as options, traded in the financial markets are expected to have complex relationships to fluctuations in the values of the underlying assets, the time to maturity and type of exercise of the contracts as well as other macroeconomic variables. Hutchinson, Lo and Poggio showed in 1994 that a non-parametric artificial neural network may be trained to approximate this complex functional relationship. Here, we consider this model with additional inputs relevant to the pricing of options and show that the accuracy of approximation may indeed be improved. We consider volume traded, historic volatility, observed interest rates and combinations of these as additional features. In addition to giving empirical results on how the inclusion of these variables helps predicting option prices, we also analyse prediction errors of the different models with volatility and volume traded as inputs, and report an interesting correlation between their contributions.
{"title":"Extending the feature set of a data-driven artificial neural network model of pricing financial options","authors":"Luis Montesdeoca, M. Niranjan","doi":"10.1109/SSCI.2016.7850014","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850014","url":null,"abstract":"Prices of derivative contracts, such as options, traded in the financial markets are expected to have complex relationships to fluctuations in the values of the underlying assets, the time to maturity and type of exercise of the contracts as well as other macroeconomic variables. Hutchinson, Lo and Poggio showed in 1994 that a non-parametric artificial neural network may be trained to approximate this complex functional relationship. Here, we consider this model with additional inputs relevant to the pricing of options and show that the accuracy of approximation may indeed be improved. We consider volume traded, historic volatility, observed interest rates and combinations of these as additional features. In addition to giving empirical results on how the inclusion of these variables helps predicting option prices, we also analyse prediction errors of the different models with volatility and volume traded as inputs, and report an interesting correlation between their contributions.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116754356","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 : 2016-12-07DOI: 10.1109/SSCI.2016.7849911
Saeed M. Alqahtani, R. John
The use of Internet has been increasing day by day and the internet traffic is exponentially increasing. The services providers such as web services providers, email services providers, and cloud service providers have to deal with millions of users per second; and thus, the level of threats to their growing networks is also very high. To deal with this much number of users is a big challenge but detection and prevention of such kinds of threats is even more challenging and vital. This is due to the fact that those threats might cause a severe loss to the service providers in terms of privacy leakage or unavailability of the services to the users. To incorporate this issue, several Intrusion Detections Systems (IDS) have been developed that differ in their detection capabilities, performance and accuracy. In this study, we have used SNORT and SURICATA as well-known IDS systems that are used worldwide. The aim of this paper is to analytically compare the functionality, working and the capability of these two IDS systems in order to detect the intrusions and different kinds of cyber-attacks within MyCloud network. Furthermore, this study also proposes a Fuzzy-Logic engine based on these two IDSs in order to enhances the performance and accuracy of these two systems in terms of increased accuracy, specificity, sensitivity and reduced false alarms. Several experiments in this compatrative study have been conducted by using and testing ISCX dataset, which results that fuzzy logic based IDS outperforms IDS alone whereas FL-SnortIDS system outperforms FL-SuricataIDS.
{"title":"A comparative study of different fuzzy classifiers for Cloud Intrusion Detection Systems' alerts","authors":"Saeed M. Alqahtani, R. John","doi":"10.1109/SSCI.2016.7849911","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849911","url":null,"abstract":"The use of Internet has been increasing day by day and the internet traffic is exponentially increasing. The services providers such as web services providers, email services providers, and cloud service providers have to deal with millions of users per second; and thus, the level of threats to their growing networks is also very high. To deal with this much number of users is a big challenge but detection and prevention of such kinds of threats is even more challenging and vital. This is due to the fact that those threats might cause a severe loss to the service providers in terms of privacy leakage or unavailability of the services to the users. To incorporate this issue, several Intrusion Detections Systems (IDS) have been developed that differ in their detection capabilities, performance and accuracy. In this study, we have used SNORT and SURICATA as well-known IDS systems that are used worldwide. The aim of this paper is to analytically compare the functionality, working and the capability of these two IDS systems in order to detect the intrusions and different kinds of cyber-attacks within MyCloud network. Furthermore, this study also proposes a Fuzzy-Logic engine based on these two IDSs in order to enhances the performance and accuracy of these two systems in terms of increased accuracy, specificity, sensitivity and reduced false alarms. Several experiments in this compatrative study have been conducted by using and testing ISCX dataset, which results that fuzzy logic based IDS outperforms IDS alone whereas FL-SnortIDS system outperforms FL-SuricataIDS.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132405384","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 : 2016-12-06DOI: 10.1109/SSCI.2016.7849857
Valérian Guivarch, J. F. D. Paz, Gabriel Villarrubia, J. Bajo, A. Péninou, Valérie Camps
The evolution of ambient intelligence systems has allowed for the development of adaptable systems. These systems trace user's habits in an automatic way and act accordingly, resulting in a context aware system. The goal is to make these systems adaptable to the user's environment, without the need for their direct interaction. This paper proposes a system that can learn from users' behavior. In order for the system to perform effectively, an adaptable multi agent system is proposed and the results are compared with the use of several classifiers.
{"title":"Hybrid system to analyze user's behaviour","authors":"Valérian Guivarch, J. F. D. Paz, Gabriel Villarrubia, J. Bajo, A. Péninou, Valérie Camps","doi":"10.1109/SSCI.2016.7849857","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7849857","url":null,"abstract":"The evolution of ambient intelligence systems has allowed for the development of adaptable systems. These systems trace user's habits in an automatic way and act accordingly, resulting in a context aware system. The goal is to make these systems adaptable to the user's environment, without the need for their direct interaction. This paper proposes a system that can learn from users' behavior. In order for the system to perform effectively, an adaptable multi agent system is proposed and the results are compared with the use of several classifiers.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129044140","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 : 2016-12-06DOI: 10.1109/SSCI.2016.7850249
Garibaldi Pineda Garcia, Patrick Camilleri, Qian Liu, S. Furber
Vision is one of our most important senses, a vast amount of information is perceived through our eyes. Neuroscientists have performed many studies using vision as input to their experiments. Computational neuroscientists have typically used a brightness-to-rate encoding to use images as spike-based visual sources for its natural mapping. Recently, neuromorphic Dynamic Vision Sensors (DVSs) were developed and, while they have excellent capabilities, they remain scarce and relatively expensive. We propose a visual input system inspired by the behaviour of a DVS but using a conventional digital camera as a sensor and a PC to encode the images. By using readily-available components, we believe most scientists would have access to a realistic spiking visual input source. While our primary goal is to provide systems with a live real-time input, we have also been successful in transcoding well established image and video databases into spike train representations. Our main contribution is a DVS emulator framework which can be extended, as we demonstrate by adding local inhibitory behaviour, adaptive thresholds and spike-timing encoding.
{"title":"pyDVS: An extensible, real-time Dynamic Vision Sensor emulator using off-the-shelf hardware","authors":"Garibaldi Pineda Garcia, Patrick Camilleri, Qian Liu, S. Furber","doi":"10.1109/SSCI.2016.7850249","DOIUrl":"https://doi.org/10.1109/SSCI.2016.7850249","url":null,"abstract":"Vision is one of our most important senses, a vast amount of information is perceived through our eyes. Neuroscientists have performed many studies using vision as input to their experiments. Computational neuroscientists have typically used a brightness-to-rate encoding to use images as spike-based visual sources for its natural mapping. Recently, neuromorphic Dynamic Vision Sensors (DVSs) were developed and, while they have excellent capabilities, they remain scarce and relatively expensive. We propose a visual input system inspired by the behaviour of a DVS but using a conventional digital camera as a sensor and a PC to encode the images. By using readily-available components, we believe most scientists would have access to a realistic spiking visual input source. While our primary goal is to provide systems with a live real-time input, we have also been successful in transcoding well established image and video databases into spike train representations. Our main contribution is a DVS emulator framework which can be extended, as we demonstrate by adding local inhibitory behaviour, adaptive thresholds and spike-timing encoding.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115650389","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：