Pub Date : 2020-06-01DOI: 10.1109/ISSC49989.2020.9180214
Wesley O'Meara, Ruth G. Lennon
Serverless computing enables organisations to avail of the inherent and unlimited flexibility and scalability that serverless provides, without having to consider the underlying infrastructure. However, there are security considerations that are unique to serverless architectures, that if not included early in application design, can lead to vulnerabilities which could be exposed to common attack vectors. While cloud service providers manage the security of the underlying infrastructure, it is up to the consumer to ensure that serverless applications are fully protected. We go on to discuss common attack vectors, the risks associated with misconfiguration within security and application setup, how attackers target vulnerabilities within the workflow logic of serverless applications and their functions to focus their attacks, and how consumers can implement measures to protect their applications within a serverless architecture.
{"title":"Serverless Computing Security: Protecting Application Logic","authors":"Wesley O'Meara, Ruth G. Lennon","doi":"10.1109/ISSC49989.2020.9180214","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180214","url":null,"abstract":"Serverless computing enables organisations to avail of the inherent and unlimited flexibility and scalability that serverless provides, without having to consider the underlying infrastructure. However, there are security considerations that are unique to serverless architectures, that if not included early in application design, can lead to vulnerabilities which could be exposed to common attack vectors. While cloud service providers manage the security of the underlying infrastructure, it is up to the consumer to ensure that serverless applications are fully protected. We go on to discuss common attack vectors, the risks associated with misconfiguration within security and application setup, how attackers target vulnerabilities within the workflow logic of serverless applications and their functions to focus their attacks, and how consumers can implement measures to protect their applications within a serverless architecture.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130413632","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 : 2020-06-01DOI: 10.1109/ISSC49989.2020.9180183
Mats-Robin Jacobsen, D. Laverty, R. Best, John Hastings
This paper describes a multi-machine synchronous islanding technique. This can be used to aid management of both intentional and unintentional island operation where the part of the grid becomes fragmented from the bulk utility grid. The multi-machine control scheme presented builds upon previous work on single machine control by the authors. The control scheme presented is realized and tested using a physical laboratory test bed which was developed as part of this work. The results show that synchronous islanding was successfully demonstrated. The ability of the system to maintain frequency and phase angle during a considerable load step was acceptable.
{"title":"Multi-Machine Synchronous Islanding Achieved in a Laboratory Test Bed Utilizing PMUs","authors":"Mats-Robin Jacobsen, D. Laverty, R. Best, John Hastings","doi":"10.1109/ISSC49989.2020.9180183","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180183","url":null,"abstract":"This paper describes a multi-machine synchronous islanding technique. This can be used to aid management of both intentional and unintentional island operation where the part of the grid becomes fragmented from the bulk utility grid. The multi-machine control scheme presented builds upon previous work on single machine control by the authors. The control scheme presented is realized and tested using a physical laboratory test bed which was developed as part of this work. The results show that synchronous islanding was successfully demonstrated. The ability of the system to maintain frequency and phase angle during a considerable load step was acceptable.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131227469","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 : 2020-06-01DOI: 10.1109/ISSC49989.2020.9180210
P. Sun, Andrew Hines
Network delay remains a challenge for real-time voice communication on the web. Jitter buffer algorithms have been widely deployed in popular platforms such as webRTC to reduce the impact of delay with playout adjustments. A trade off must be made between speech loss and voice degradations as adjustments can either drop segments resulting in a loss of speech intelligibility or change the rate of playout and impact the pitch or natural sound of the speech. Both options can negatively influence a listener's quality of experience (QoE). Optimising this trade-off requires knowledge of how intelligibility and quality are perceived and priorities when a listener syntheses both factors into a fused QoE judgement. This study conducted two subjective experiments to evaluate intelligibility and quality independently along with a short descriptive analysis to address the interplay between the two factors. The study uses a dataset that simulated listener-end speech under extreme but realistic network delay conditions using webRTC's standard jitter buffer and a variation that prioritised minimisation of packet loss. The results show that intelligibility is a key dimension in quality judgement for the scenarios tested. As a result, this study calls for attention when comparing the quality scores as the overlooked non-traditional quality attributes are proven to be actively contributing to the overall QoE. The descriptive analysis also indicates there is inconsistency in the interpretation of ‘quality’ among the assessors. This finding questions the methodology used in standard QoE subjective experiment designs and proposes adopting a more flexible approach to measure subjective QoE.
{"title":"Should WebRTC Prioritise Intelligibility over Speech Quality?","authors":"P. Sun, Andrew Hines","doi":"10.1109/ISSC49989.2020.9180210","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180210","url":null,"abstract":"Network delay remains a challenge for real-time voice communication on the web. Jitter buffer algorithms have been widely deployed in popular platforms such as webRTC to reduce the impact of delay with playout adjustments. A trade off must be made between speech loss and voice degradations as adjustments can either drop segments resulting in a loss of speech intelligibility or change the rate of playout and impact the pitch or natural sound of the speech. Both options can negatively influence a listener's quality of experience (QoE). Optimising this trade-off requires knowledge of how intelligibility and quality are perceived and priorities when a listener syntheses both factors into a fused QoE judgement. This study conducted two subjective experiments to evaluate intelligibility and quality independently along with a short descriptive analysis to address the interplay between the two factors. The study uses a dataset that simulated listener-end speech under extreme but realistic network delay conditions using webRTC's standard jitter buffer and a variation that prioritised minimisation of packet loss. The results show that intelligibility is a key dimension in quality judgement for the scenarios tested. As a result, this study calls for attention when comparing the quality scores as the overlooked non-traditional quality attributes are proven to be actively contributing to the overall QoE. The descriptive analysis also indicates there is inconsistency in the interpretation of ‘quality’ among the assessors. This finding questions the methodology used in standard QoE subjective experiment designs and proposes adopting a more flexible approach to measure subjective QoE.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129248403","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 : 2020-06-01DOI: 10.1109/ISSC49989.2020.9180184
Fahd A. Shiwani, T. Siriburanon, Jianglin Du, R. Staszewski
This paper provides detailed mathematical analysis that investigate the effect of charge-sharing between an analog-to-digital converter (ADC) reference decoupling capacitor and a charge-redistribution based differential split-monotonic capacitive digital-to-analog converter (CDAC). A discrete-time reference driver is used to charge the decoupling capacitor in the sampling phase, forming a closed-system in the hold phase which allows us to apply a charge-based analysis to determine the voltages at several nodes within the system such as the reference capacitors and comparator inputs. The generalized mathematical model can be used to accurately determine the voltage shift on the comparator inputs and hence quantify the effect on the SAR comparator decision level with a varying reference decoupling capacitor which can ultimately be used to optimize the size of the capacitor while maintaining high SNDR/SFDR. In this design, we utilize a differential decoupling capacitor which provides a 4x capacitor area decrease compared to its single ended counterparts.
{"title":"Charge Analysis in SAR ADC with Discrete-Time Reference Driver","authors":"Fahd A. Shiwani, T. Siriburanon, Jianglin Du, R. Staszewski","doi":"10.1109/ISSC49989.2020.9180184","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180184","url":null,"abstract":"This paper provides detailed mathematical analysis that investigate the effect of charge-sharing between an analog-to-digital converter (ADC) reference decoupling capacitor and a charge-redistribution based differential split-monotonic capacitive digital-to-analog converter (CDAC). A discrete-time reference driver is used to charge the decoupling capacitor in the sampling phase, forming a closed-system in the hold phase which allows us to apply a charge-based analysis to determine the voltages at several nodes within the system such as the reference capacitors and comparator inputs. The generalized mathematical model can be used to accurately determine the voltage shift on the comparator inputs and hence quantify the effect on the SAR comparator decision level with a varying reference decoupling capacitor which can ultimately be used to optimize the size of the capacitor while maintaining high SNDR/SFDR. In this design, we utilize a differential decoupling capacitor which provides a 4x capacitor area decrease compared to its single ended counterparts.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121719483","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 : 2020-05-20DOI: 10.1109/ISSC49989.2020.9180182
M. Habiba, Barak A. Pearlmutter
Neural differential equations are a promising new member in the neural network family. They show the potential of differential equations for time-series data analysis. In this paper, the strength of the ordinary differential equation (ODE) is explored with a new extension. The main goal of this work is to answer the following questions: (i) can ODE be used to redefine the existing neural network model? (ii) can Neural ODEs solve the irregular sampling rate challenge of existing neural network models for a continuous time series, i.e., length and dynamic nature, (iii) how to reduce the training and evaluation time of existing Neural ODE systems? This work leverages the mathematical foundation of ODEs to redesign traditional RNNs such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The main contribution of this paper is to illustrate the design of two new ODE-based RNN models (GRU-ODE model and LSTM-ODE) which can compute the hidden state and cell state at any point of time using an ODE solver. These models reduce the computation overhead of hidden state and cell state by a vast amount. The performance evaluation of these two new models for learning continuous time series with irregular sampling rate is then demonstrated. Experiments show that these new ODE based RNN models require less training time than Latent ODEs and conventional Neural ODEs. They can achieve higher accuracy quickly, and the design of the neural network is more straightforward than the previous neural ODE systems.
{"title":"Neural Ordinary Differential Equation based Recurrent Neural Network Model","authors":"M. Habiba, Barak A. Pearlmutter","doi":"10.1109/ISSC49989.2020.9180182","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180182","url":null,"abstract":"Neural differential equations are a promising new member in the neural network family. They show the potential of differential equations for time-series data analysis. In this paper, the strength of the ordinary differential equation (ODE) is explored with a new extension. The main goal of this work is to answer the following questions: (i) can ODE be used to redefine the existing neural network model? (ii) can Neural ODEs solve the irregular sampling rate challenge of existing neural network models for a continuous time series, i.e., length and dynamic nature, (iii) how to reduce the training and evaluation time of existing Neural ODE systems? This work leverages the mathematical foundation of ODEs to redesign traditional RNNs such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The main contribution of this paper is to illustrate the design of two new ODE-based RNN models (GRU-ODE model and LSTM-ODE) which can compute the hidden state and cell state at any point of time using an ODE solver. These models reduce the computation overhead of hidden state and cell state by a vast amount. The performance evaluation of these two new models for learning continuous time series with irregular sampling rate is then demonstrated. Experiments show that these new ODE based RNN models require less training time than Latent ODEs and conventional Neural ODEs. They can achieve higher accuracy quickly, and the design of the neural network is more straightforward than the previous neural ODE systems.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130965006","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 : 2020-05-20DOI: 10.1109/ISSC49989.2020.9180216
M. Habiba, Barak A. Pearlmutter
Informative missingness is unavoidable in the digital processing of continuous time series, where the value for one or more observations at different time points are missing. Such missing observations are one of the major limitations of time series processing using deep learning. Practical applications, e.g., sensor data, healthcare, weather, generates data that is in truth continuous in time, and informative missingness is a common phenomenon in these datasets. These datasets often consist of multiple variables, and often there are missing values for one or many of these variables. This characteristic makes time series prediction more challenging, and the impact of missing input observations on the accuracy of the final output can be significant. A recent novel deep learning model called GRU-D is one early attempt to address informative missingness in time series data. On the other hand, a new family of neural networks called Neural ODEs (Ordinary Differential Equations) are natural and efficient for processing time series data which is continuous in time. In this paper, a deep learning model is proposed that leverages the effective imputation of GRU-D, and the temporal continuity of Neural ODEs. A time series classification task performed on the PhysioNet dataset demonstrates the performance of this architecture.
{"title":"Neural ODEs for Informative Missingess in Multivariate Time Series","authors":"M. Habiba, Barak A. Pearlmutter","doi":"10.1109/ISSC49989.2020.9180216","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180216","url":null,"abstract":"Informative missingness is unavoidable in the digital processing of continuous time series, where the value for one or more observations at different time points are missing. Such missing observations are one of the major limitations of time series processing using deep learning. Practical applications, e.g., sensor data, healthcare, weather, generates data that is in truth continuous in time, and informative missingness is a common phenomenon in these datasets. These datasets often consist of multiple variables, and often there are missing values for one or many of these variables. This characteristic makes time series prediction more challenging, and the impact of missing input observations on the accuracy of the final output can be significant. A recent novel deep learning model called GRU-D is one early attempt to address informative missingness in time series data. On the other hand, a new family of neural networks called Neural ODEs (Ordinary Differential Equations) are natural and efficient for processing time series data which is continuous in time. In this paper, a deep learning model is proposed that leverages the effective imputation of GRU-D, and the temporal continuity of Neural ODEs. A time series classification task performed on the PhysioNet dataset demonstrates the performance of this architecture.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"361 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120893928","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 : 2020-05-06DOI: 10.1109/ISSC49989.2020.9180170
C. Behera, Ruairi O’Sullivan, J. Sanchez-Bornot, Alok Joshi, G. Prasad, T. Sharp, KongFatt Wong-Lin
Studies have shown that the firing activity of single neurons in brainstem dorsal raphe nucleus (DRN) is linked to slow-wave oscillations in the cortex, especially the frontal cortex. However, most studies consist of either single DRN neuronal or single-channel electrocorticogram (ECoG) recording. Hence, it is unclear how a population of DRN neurons with electrophysiologically diverse characteristics can coordinate and relate to the oscillatory rhythms in different cortical regions. In this work, we explored the technical feasibility of such an investigation. We simultaneously recorded extracellularly a group of DRN neurons and three cortical regions using electrocorticogram (ECoG) in two anaesthetized SERT-Cre mice. The cortical regions were the two bi-hemispheric frontal and one (right) occipital regions. We then used coherence analysis to quantify the relationship between DRN neurons and cortical activity rhythms. We also computed the coherence between firing activities of DRN neurons to quantify their relationship. We found slow-firing DRN neurons with regular and irregular spiking characteristics, potentially serotonergic neurons, were more likely to have stronger relationships with cortical ECoG signals, especially the frontal cortex. Moreover, the DRN neurons were generally found to be weakly correlated with each other. Future investigation with more samples and analytical methods will be conducted to validate our results.
{"title":"Revealing the Dynamic Relationship Between Neural Population Activities in Corticoraphe System","authors":"C. Behera, Ruairi O’Sullivan, J. Sanchez-Bornot, Alok Joshi, G. Prasad, T. Sharp, KongFatt Wong-Lin","doi":"10.1109/ISSC49989.2020.9180170","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180170","url":null,"abstract":"Studies have shown that the firing activity of single neurons in brainstem dorsal raphe nucleus (DRN) is linked to slow-wave oscillations in the cortex, especially the frontal cortex. However, most studies consist of either single DRN neuronal or single-channel electrocorticogram (ECoG) recording. Hence, it is unclear how a population of DRN neurons with electrophysiologically diverse characteristics can coordinate and relate to the oscillatory rhythms in different cortical regions. In this work, we explored the technical feasibility of such an investigation. We simultaneously recorded extracellularly a group of DRN neurons and three cortical regions using electrocorticogram (ECoG) in two anaesthetized SERT-Cre mice. The cortical regions were the two bi-hemispheric frontal and one (right) occipital regions. We then used coherence analysis to quantify the relationship between DRN neurons and cortical activity rhythms. We also computed the coherence between firing activities of DRN neurons to quantify their relationship. We found slow-firing DRN neurons with regular and irregular spiking characteristics, potentially serotonergic neurons, were more likely to have stronger relationships with cortical ECoG signals, especially the frontal cortex. Moreover, the DRN neurons were generally found to be weakly correlated with each other. Future investigation with more samples and analytical methods will be conducted to validate our results.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127990138","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 : 2020-05-06DOI: 10.1109/ISSC49989.2020.9180192
Moreno Jaramillo, A. M. Jaramillo, D. Laverty, Jesús Martínez, del Rincón, P. Brogan, D. Morrow
This paper presents a novel approach for identification of photovoltaic systems in the residential sector. This is needed in response to increasing embedded generation on distribution networks. To date non-intrusive load monitoring techniques have focused mostly on identifying conventional loads on the customer side. This paper demonstrates the application of non-intrusive load monitoring to identify residential distributed generation, thereby enabling techniques to improve system flexibility and stability. The demonstrated methodology combines basic statistics with the Support Vector Machine technique, to identify PV load signatures. PMU measurements from the residential sector are used to aggregate measurements based largely on electric current records. The methods presented have applications for network operators, both in real time control and generation scheduling.
{"title":"Non-Intrusive Load Monitoring Algorithm for PV Identification in the Residential Sector","authors":"Moreno Jaramillo, A. M. Jaramillo, D. Laverty, Jesús Martínez, del Rincón, P. Brogan, D. Morrow","doi":"10.1109/ISSC49989.2020.9180192","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180192","url":null,"abstract":"This paper presents a novel approach for identification of photovoltaic systems in the residential sector. This is needed in response to increasing embedded generation on distribution networks. To date non-intrusive load monitoring techniques have focused mostly on identifying conventional loads on the customer side. This paper demonstrates the application of non-intrusive load monitoring to identify residential distributed generation, thereby enabling techniques to improve system flexibility and stability. The demonstrated methodology combines basic statistics with the Support Vector Machine technique, to identify PV load signatures. PMU measurements from the residential sector are used to aggregate measurements based largely on electric current records. The methods presented have applications for network operators, both in real time control and generation scheduling.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131333271","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 : 2020-05-06DOI: 10.1109/ISSC49989.2020.9180217
Shane Trimble, W. Naeem, S. McLoone, Pantelis Sopasakis
The growing number of collaborative robotics in unstructured environments creates highly nonconvex nonlinear shared dynamical systems. For safety and speed, path planning and collision avoidance are of the utmost importance in these situations. We present a novel nonlinear MPC solution for use on a three-dimensional four-axis robotic manipulator. The system is the first of it's kind to take into account moving obstacles. Using the OpEn framework, optimisation is done by the PANOC and ALM techniques. Experimentation demonstrates extremely fast solver times on both PC and embedded platforms.
{"title":"Context-aware robotic arm using fast embedded model predictive control","authors":"Shane Trimble, W. Naeem, S. McLoone, Pantelis Sopasakis","doi":"10.1109/ISSC49989.2020.9180217","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180217","url":null,"abstract":"The growing number of collaborative robotics in unstructured environments creates highly nonconvex nonlinear shared dynamical systems. For safety and speed, path planning and collision avoidance are of the utmost importance in these situations. We present a novel nonlinear MPC solution for use on a three-dimensional four-axis robotic manipulator. The system is the first of it's kind to take into account moving obstacles. Using the OpEn framework, optimisation is done by the PANOC and ALM techniques. Experimentation demonstrates extremely fast solver times on both PC and embedded platforms.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116801111","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 : 2020-05-06DOI: 10.1109/ISSC49989.2020.9180165
Aqib Javed, J. Harkin, L. McDaid, Junxiu Liu
Networks-on-Chip (NoC) were designed to enhance the communication performance of Multi-processor Systems-on-Chip (MPSoC). NoCs are equipped with buffered input channels which queue incoming data and minimise routing stress especially under uneven traffic distributions. Buffer utilization of a router node provides an early indication to potential local congestion. In this work we propose a novel Spiking Neural Network (SNN) based congestion prediction model to predict input buffer utilization as a congestion parameter to minimize impact of potential local congestion. Router-level and Network-level models are proposed in predicting congestion at each NoC router node. Results show that the router and network models can predict buffer utilization patterns with an average accuracy of 91.89% and 93.76%, respectively.
{"title":"Minimising Impact of Local Congestion in Networks-on-Chip Performance by Predicting Buffer Utilisation","authors":"Aqib Javed, J. Harkin, L. McDaid, Junxiu Liu","doi":"10.1109/ISSC49989.2020.9180165","DOIUrl":"https://doi.org/10.1109/ISSC49989.2020.9180165","url":null,"abstract":"Networks-on-Chip (NoC) were designed to enhance the communication performance of Multi-processor Systems-on-Chip (MPSoC). NoCs are equipped with buffered input channels which queue incoming data and minimise routing stress especially under uneven traffic distributions. Buffer utilization of a router node provides an early indication to potential local congestion. In this work we propose a novel Spiking Neural Network (SNN) based congestion prediction model to predict input buffer utilization as a congestion parameter to minimize impact of potential local congestion. Router-level and Network-level models are proposed in predicting congestion at each NoC router node. Results show that the router and network models can predict buffer utilization patterns with an average accuracy of 91.89% and 93.76%, respectively.","PeriodicalId":351013,"journal":{"name":"2020 31st Irish Signals and Systems Conference (ISSC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127986299","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：