Pub Date : 2018-02-01DOI: 10.1109/NCC.2018.8600202
Krishnachaitanya Gogineni, Jom Kuriakose, H. Murthy
The revolution in information technology has lead to the availability of vast and varied collections of music on the digital platform. With the widespread use of smartphones and other personal digital devices, there has been a growing interest in accessing music, based on its various characteristics using information retrieval technologies. But the unavailability of meta-tags or annotations has lead to the need for developing technologies to automatically extract relevant properties of music from the audio. Automatically identifying meta-data from audio like, artist information - especially instrument artists - is a very tough task, even for humans. In this paper, automatic identification of percussion artist is attempted on mridangam audio from Carnatic music concert using probabilistic models. Unlike speaker identification where the voice of the speaker is unique, the timbre of the percussion instruments will be more or less the same across instruments. The distinctive characteristics of a musician can be found in the style of him/her playing the instrument. A single Gaussian mixture model (GMM) is built across all musician data using tonic normalized cent-filterbank-cepstral-coefficients (CFCC) features. Each artist's percussion audio is converted to a sequence of GMM tokens. Sub-string matching between train and test data is used to identify the musician. The performance is evaluated on a dataset of 10 mridangam artist and could identify the artist with an accuracy of 72.5 %.
{"title":"Mridangam Artist Identification from Taniavartanam Audio","authors":"Krishnachaitanya Gogineni, Jom Kuriakose, H. Murthy","doi":"10.1109/NCC.2018.8600202","DOIUrl":"https://doi.org/10.1109/NCC.2018.8600202","url":null,"abstract":"The revolution in information technology has lead to the availability of vast and varied collections of music on the digital platform. With the widespread use of smartphones and other personal digital devices, there has been a growing interest in accessing music, based on its various characteristics using information retrieval technologies. But the unavailability of meta-tags or annotations has lead to the need for developing technologies to automatically extract relevant properties of music from the audio. Automatically identifying meta-data from audio like, artist information - especially instrument artists - is a very tough task, even for humans. In this paper, automatic identification of percussion artist is attempted on mridangam audio from Carnatic music concert using probabilistic models. Unlike speaker identification where the voice of the speaker is unique, the timbre of the percussion instruments will be more or less the same across instruments. The distinctive characteristics of a musician can be found in the style of him/her playing the instrument. A single Gaussian mixture model (GMM) is built across all musician data using tonic normalized cent-filterbank-cepstral-coefficients (CFCC) features. Each artist's percussion audio is converted to a sequence of GMM tokens. Sub-string matching between train and test data is used to identify the musician. The performance is evaluated on a dataset of 10 mridangam artist and could identify the artist with an accuracy of 72.5 %.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126684290","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 : 2018-02-01DOI: 10.1109/NCC.2018.8599964
S. Dash, R. K. Mallik, S. K. Mohammed
This paper proposes a novel optimal receiver for an $N$ -branch receive diversity power line communication (PLC) system subject to Rayleigh fading and perturbed by Nakagami-m background noise. A Gauss-optimal receiver is obtained from the optimal receiver which is further utilized to derive a closed form expression for the symbol error probability (SEP) for binary phase-shift keying (BPSK) modulation using a characteristic function approach under the condition that mN is an integer. An asymptotic expression for the SEP at high signal-to-noise ratio (SNR) shows the diversity order of the PLC system to be independent of the noise shape parameter $m$. Numerical studies demonstrate that the diversity order of the optimal receiver is preserved with the suboptimal receiver as well. Furthermore, the advantage of using multiple receive branches in terms of achieving better error performance and the effect of the shape parameter $m$ on the SEP of the suboptimal receiver are also presented.
{"title":"Performance Analysis of a Gauss-Optimal Receiver for a Receive Diversity PLC System in Nakagami-$m$ Noise Environment","authors":"S. Dash, R. K. Mallik, S. K. Mohammed","doi":"10.1109/NCC.2018.8599964","DOIUrl":"https://doi.org/10.1109/NCC.2018.8599964","url":null,"abstract":"This paper proposes a novel optimal receiver for an $N$ -branch receive diversity power line communication (PLC) system subject to Rayleigh fading and perturbed by Nakagami-m background noise. A Gauss-optimal receiver is obtained from the optimal receiver which is further utilized to derive a closed form expression for the symbol error probability (SEP) for binary phase-shift keying (BPSK) modulation using a characteristic function approach under the condition that mN is an integer. An asymptotic expression for the SEP at high signal-to-noise ratio (SNR) shows the diversity order of the PLC system to be independent of the noise shape parameter $m$. Numerical studies demonstrate that the diversity order of the optimal receiver is preserved with the suboptimal receiver as well. Furthermore, the advantage of using multiple receive branches in terms of achieving better error performance and the effect of the shape parameter $m$ on the SEP of the suboptimal receiver are also presented.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126520332","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 : 2018-02-01DOI: 10.1109/NCC.2018.8600113
A. Saxena, D. Banerjee, M. Hashmi
This paper proposes a novel design of a quarter-wave meandered coupled line based tri-band impedance transformer. The design utilizes cascade of two existing dual-band impedance transformer to achieve tri-band functionality. The proposed design matches a real load to a conventional 50n source at three arbitrary frequencies of IGHz, 2.4GHz and 3.8GHz. The design uses the concept of matching at a reference frequency that is common to both dual band matching sections. A prototype fabricated on FR4 shows good agreement between the simulated and measured results.
{"title":"A Novel Meandered Coupled-Line Tri-Band Impedance Matching Network","authors":"A. Saxena, D. Banerjee, M. Hashmi","doi":"10.1109/NCC.2018.8600113","DOIUrl":"https://doi.org/10.1109/NCC.2018.8600113","url":null,"abstract":"This paper proposes a novel design of a quarter-wave meandered coupled line based tri-band impedance transformer. The design utilizes cascade of two existing dual-band impedance transformer to achieve tri-band functionality. The proposed design matches a real load to a conventional 50n source at three arbitrary frequencies of IGHz, 2.4GHz and 3.8GHz. The design uses the concept of matching at a reference frequency that is common to both dual band matching sections. A prototype fabricated on FR4 shows good agreement between the simulated and measured results.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123876874","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 : 2018-02-01DOI: 10.1109/NCC.2018.8600119
Debasish Jyotishi, S. Deb, S. Dandapat
Nasal tract is an important part of our vocal tract system. It provides major impact for production of nasalised and hypernasal speech. Despite it's huge importance, the effect of nasal tract is not yet largely studied. This work is done with a motivation that, understanding characteristics of nasalised vowels and nasal filter will help in detecting nasalised speech. We have designed a device to separate nasal murmur from oral speech, when nasalised speech is spoken. In this work we have analysed speech data collected from different speakers. Firstly we have analysed nasalised vowels and found a novel feature for nasalised vowels. Then, various signal processing techniques are used to analyse the variability of nasal filter for different nasalised vowels. It is found that the nasal filter, which is the reason for nasalisation of vowels, is invariant across different nasalised vowels. Nasalised speech are produced when the nasal tract gets coupled with vocal tract. When the effect of coupling is experimented from a signal processing point of view, we found that it has an effect of addition.
{"title":"A Novel Feature for Nasalised Vowels and Characteristic Analysis of Nasal Filter","authors":"Debasish Jyotishi, S. Deb, S. Dandapat","doi":"10.1109/NCC.2018.8600119","DOIUrl":"https://doi.org/10.1109/NCC.2018.8600119","url":null,"abstract":"Nasal tract is an important part of our vocal tract system. It provides major impact for production of nasalised and hypernasal speech. Despite it's huge importance, the effect of nasal tract is not yet largely studied. This work is done with a motivation that, understanding characteristics of nasalised vowels and nasal filter will help in detecting nasalised speech. We have designed a device to separate nasal murmur from oral speech, when nasalised speech is spoken. In this work we have analysed speech data collected from different speakers. Firstly we have analysed nasalised vowels and found a novel feature for nasalised vowels. Then, various signal processing techniques are used to analyse the variability of nasal filter for different nasalised vowels. It is found that the nasal filter, which is the reason for nasalisation of vowels, is invariant across different nasalised vowels. Nasalised speech are produced when the nasal tract gets coupled with vocal tract. When the effect of coupling is experimented from a signal processing point of view, we found that it has an effect of addition.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124136297","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 : 2018-02-01DOI: 10.1109/NCC.2018.8600257
A. Kherani, R. Karthik
In millimeter Wave (mmWave) cellular communication systems, transmission range is inherently limited to only a short distance. In order to overcome this drawback, the mmWave-based cellular communications systems are limited to “pencilbeam” configuration to achieve larger cell radius. Small beam-width (typically 10°), coverage requirements, and physical constraint of small number of beams from an antenna array lead to requiring multiple antenna arrays at a mmWave cellular base-station. For such systems, we advocate the need for a structured approach to beam assignment for various users. We provide a problem formulation where beam assignment is done to achieve system-wide stability, design a learning algorithm to achieve the beam assignment under dynamically varying users' activity, and way of performing call admission control. Given the introductory nature of this problem, we intentionally refrain from delving into detailed scheduling aspects from point of view of fairness - with a remark that such a fairness-providing scheme will run as an inner loop to our proposed system.
{"title":"Dynamic Beam Assignment in Narrow Beamforming and mmWave Systems","authors":"A. Kherani, R. Karthik","doi":"10.1109/NCC.2018.8600257","DOIUrl":"https://doi.org/10.1109/NCC.2018.8600257","url":null,"abstract":"In millimeter Wave (mmWave) cellular communication systems, transmission range is inherently limited to only a short distance. In order to overcome this drawback, the mmWave-based cellular communications systems are limited to “pencilbeam” configuration to achieve larger cell radius. Small beam-width (typically 10°), coverage requirements, and physical constraint of small number of beams from an antenna array lead to requiring multiple antenna arrays at a mmWave cellular base-station. For such systems, we advocate the need for a structured approach to beam assignment for various users. We provide a problem formulation where beam assignment is done to achieve system-wide stability, design a learning algorithm to achieve the beam assignment under dynamically varying users' activity, and way of performing call admission control. Given the introductory nature of this problem, we intentionally refrain from delving into detailed scheduling aspects from point of view of fairness - with a remark that such a fairness-providing scheme will run as an inner loop to our proposed system.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115024478","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 : 2018-02-01DOI: 10.1109/NCC.2018.8599945
Ameya Godbole, Spoorthy Bhat, P. Guha
Decision trees are discriminative classifiers that hierarchically partition the input space to achieve regions containing instances having uniform class label. Existing works in this area have mostly focused on C4.S trees that learn axis aligned partitions. On the other hand, neural trees learn oblique partitions from data and use lesser number of decision nodes hosting perceptrons. However, these perceptrons are susceptible to data imbalances. This motivated us to propose a progressively balanced neural tree where training dataset are balanced prior to perceptron learning. The second contribution is the optimization of the decision function with respect to entropy impurity based objective functions. This formulation also allows a parent node to have more than two child nodes. The proposed algorithm is benchmarked on ten standard datasets against three baseline multi-class classification algorithms.
{"title":"Progressively Balanced Multi-class Neural Trees","authors":"Ameya Godbole, Spoorthy Bhat, P. Guha","doi":"10.1109/NCC.2018.8599945","DOIUrl":"https://doi.org/10.1109/NCC.2018.8599945","url":null,"abstract":"Decision trees are discriminative classifiers that hierarchically partition the input space to achieve regions containing instances having uniform class label. Existing works in this area have mostly focused on C4.S trees that learn axis aligned partitions. On the other hand, neural trees learn oblique partitions from data and use lesser number of decision nodes hosting perceptrons. However, these perceptrons are susceptible to data imbalances. This motivated us to propose a progressively balanced neural tree where training dataset are balanced prior to perceptron learning. The second contribution is the optimization of the decision function with respect to entropy impurity based objective functions. This formulation also allows a parent node to have more than two child nodes. The proposed algorithm is benchmarked on ten standard datasets against three baseline multi-class classification algorithms.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115444372","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 : 2018-02-01DOI: 10.1109/NCC.2018.8599936
Vinay Kumar B.R., Roshan Antony, N. Kashyap
This paper is concerned with the problem of broadcasting information from a source node to every node in an ad-hoc network. Flooding, as a broadcast mechanism, involves each node forwarding any packet it receives to all its neighbours. This results in excessive transmissions and thus a high energy expenditure overall. Probabilistic forwarding or gossiping involves each node forwarding a received packet to all its neighbours only with a certain probability p. In this paper, we study the effect of introducing redundancy, in the form of coded packets, into a probabilistic forwarding protocol. Specifically, we assume that the source node has $k$ data packets to broadcast, which are encoded into $n$ 2: $k$ coded packets, such that any $k$ of these coded packets are sufficient to recover the original $k$ data packets. Our interest is in determining the minimum forwarding probability $p$ for a “successful broadcast”, which we take to be the event that the expected fraction of network nodes that receive at least $k$ of the $n$ coded packets is close to 1. We examine, via simulations and analysis of a number of different network topologies (e.g., trees, grids, random geometric graphs), how this minimum forwarding probability, and correspondingly, the expected total number of packet transmissions varies with the amount of redundancy added. Our simulation results indicate that over network topologies that are highly connected, the introduction of redundancy into the probabilistic forwarding protocol is useful, as it can significantly reduce the expected total number of transmissions needed for a successful broadcast. On the other hand, for trees, our analysis shows that the expected total number of transmissions needed increases with redundancy.
{"title":"The Effect of Introducing Redundancy in a Probabilistic Forwarding Protocol","authors":"Vinay Kumar B.R., Roshan Antony, N. Kashyap","doi":"10.1109/NCC.2018.8599936","DOIUrl":"https://doi.org/10.1109/NCC.2018.8599936","url":null,"abstract":"This paper is concerned with the problem of broadcasting information from a source node to every node in an ad-hoc network. Flooding, as a broadcast mechanism, involves each node forwarding any packet it receives to all its neighbours. This results in excessive transmissions and thus a high energy expenditure overall. Probabilistic forwarding or gossiping involves each node forwarding a received packet to all its neighbours only with a certain probability p. In this paper, we study the effect of introducing redundancy, in the form of coded packets, into a probabilistic forwarding protocol. Specifically, we assume that the source node has $k$ data packets to broadcast, which are encoded into $n$ 2: $k$ coded packets, such that any $k$ of these coded packets are sufficient to recover the original $k$ data packets. Our interest is in determining the minimum forwarding probability $p$ for a “successful broadcast”, which we take to be the event that the expected fraction of network nodes that receive at least $k$ of the $n$ coded packets is close to 1. We examine, via simulations and analysis of a number of different network topologies (e.g., trees, grids, random geometric graphs), how this minimum forwarding probability, and correspondingly, the expected total number of packet transmissions varies with the amount of redundancy added. Our simulation results indicate that over network topologies that are highly connected, the introduction of redundancy into the probabilistic forwarding protocol is useful, as it can significantly reduce the expected total number of transmissions needed for a successful broadcast. On the other hand, for trees, our analysis shows that the expected total number of transmissions needed increases with redundancy.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123514332","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 : 2018-02-01DOI: 10.1109/NCC.2018.8600013
Srikanth Raj Chetupalli, Ashwin Ram, V. Sreenivas Thippur
Passive sound source localization (SSL) using time-difference-of-arrival (TDOA) measurements is a non-linear inversion problem. In this paper, a data-driven approach to SSL using TDOA measurements is considered. A neural network (NN) is viewed as an architecture constrained non-linear function, with its parameters learnt from the training data. We consider a three layer neural network with TDOA measurements between pairs of microphones as input features and source location in the Cartesian coordinate system as output. Experimentally, we show that, NN trained even on noise-less TDOA measurements can achieve good performance for noisy TDOA inputs also. These performances are better than the traditional spherical interpolation (SI) method. We show that the NN trained offline using simulated TDOA measurements, performs better than the SI method, on real-life speech signals in a simulated enclosure.
{"title":"Robust offline trained neural network for TDOA based sound source localization","authors":"Srikanth Raj Chetupalli, Ashwin Ram, V. Sreenivas Thippur","doi":"10.1109/NCC.2018.8600013","DOIUrl":"https://doi.org/10.1109/NCC.2018.8600013","url":null,"abstract":"Passive sound source localization (SSL) using time-difference-of-arrival (TDOA) measurements is a non-linear inversion problem. In this paper, a data-driven approach to SSL using TDOA measurements is considered. A neural network (NN) is viewed as an architecture constrained non-linear function, with its parameters learnt from the training data. We consider a three layer neural network with TDOA measurements between pairs of microphones as input features and source location in the Cartesian coordinate system as output. Experimentally, we show that, NN trained even on noise-less TDOA measurements can achieve good performance for noisy TDOA inputs also. These performances are better than the traditional spherical interpolation (SI) method. We show that the NN trained offline using simulated TDOA measurements, performs better than the SI method, on real-life speech signals in a simulated enclosure.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114945569","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 : 2018-02-01DOI: 10.1109/NCC.2018.8600145
A. Yadav, Prateek, Subrat Kart, V. Jain
In this paper, a comparative analysis of various performance enhancement techniques in two-dimensional (2-D) atmospheric optical code division multiple access (OCDMA) system is studied in presence of beam divergence, multiple access interference (MAI), noise and atmospheric turbulence. Lognormal and gamma-gamma probability density functions (pdfs) are considered for evaluating fading process due to atmospheric turbulence. Further, double hard limiters, spatial diversity and error correcting code (ECC) are used for performance improvement of the 2-D atmospheric OCDMA system. Double hard limiters and ECC improve performance substantially as compared to spatial diversity. In addition, double hard limiters are cost-effective than the spatial diversity and ECC. Thus, double hard limiters are superior to the other performance improvement techniques in 2-D atmospheric OCDMA system.
{"title":"Comparative Analysis of Different Performance Enhancement Techniques in 2-D Atmospheric OCDMA System","authors":"A. Yadav, Prateek, Subrat Kart, V. Jain","doi":"10.1109/NCC.2018.8600145","DOIUrl":"https://doi.org/10.1109/NCC.2018.8600145","url":null,"abstract":"In this paper, a comparative analysis of various performance enhancement techniques in two-dimensional (2-D) atmospheric optical code division multiple access (OCDMA) system is studied in presence of beam divergence, multiple access interference (MAI), noise and atmospheric turbulence. Lognormal and gamma-gamma probability density functions (pdfs) are considered for evaluating fading process due to atmospheric turbulence. Further, double hard limiters, spatial diversity and error correcting code (ECC) are used for performance improvement of the 2-D atmospheric OCDMA system. Double hard limiters and ECC improve performance substantially as compared to spatial diversity. In addition, double hard limiters are cost-effective than the spatial diversity and ECC. Thus, double hard limiters are superior to the other performance improvement techniques in 2-D atmospheric OCDMA system.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"80 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129856126","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 : 2018-02-01DOI: 10.1109/NCC.2018.8599916
A. Bashar
Effective management of Cloud Data Center (CDC) and the provisioning of services with desired QoS guarantees is a challenge which needs to be addressed through autonomous mechanisms which are intelligent, lightweight and scalable. Recent focus on applying Machine Learning approaches to model the CDC and service behavioral patterns have proved to be quite effective in fulfilling the objectives of autonomous management. To this end, this paper advances on the idea of implementing a distributed management solution which harnesses the predictive capability of Bayesian Networks (BN). Multiple CDCs which are usually geographically distributed are modeled through a Multiple Entity Bayesian Network (MEBN) formulation. The framework termed as BNDSAC (Bayesian Network based Distributed Services Admission Control) is proposed and evaluated to study the services admission control of cloud service requests from the cloud consumers. A thorough evaluation of BNDSAC is presented in terms of its prediction accuracy, algorithmic complexity and decision-making speed. In an online setup, performance of BNDSAC is evaluated and compared with a centralized scenario, to demonstrate its superior performance for Services Blocking Probability and QoS provisioning. Simulation results based on Riverbed Modeler and Hugin Researcher show the feasibility and applicability of BNDSAC solution for real-time operation and management of real world CDCs.
{"title":"ML-based Admission Control of Cloud Services: Centralized versus Distributed Approaches","authors":"A. Bashar","doi":"10.1109/NCC.2018.8599916","DOIUrl":"https://doi.org/10.1109/NCC.2018.8599916","url":null,"abstract":"Effective management of Cloud Data Center (CDC) and the provisioning of services with desired QoS guarantees is a challenge which needs to be addressed through autonomous mechanisms which are intelligent, lightweight and scalable. Recent focus on applying Machine Learning approaches to model the CDC and service behavioral patterns have proved to be quite effective in fulfilling the objectives of autonomous management. To this end, this paper advances on the idea of implementing a distributed management solution which harnesses the predictive capability of Bayesian Networks (BN). Multiple CDCs which are usually geographically distributed are modeled through a Multiple Entity Bayesian Network (MEBN) formulation. The framework termed as BNDSAC (Bayesian Network based Distributed Services Admission Control) is proposed and evaluated to study the services admission control of cloud service requests from the cloud consumers. A thorough evaluation of BNDSAC is presented in terms of its prediction accuracy, algorithmic complexity and decision-making speed. In an online setup, performance of BNDSAC is evaluated and compared with a centralized scenario, to demonstrate its superior performance for Services Blocking Probability and QoS provisioning. Simulation results based on Riverbed Modeler and Hugin Researcher show the feasibility and applicability of BNDSAC solution for real-time operation and management of real world CDCs.","PeriodicalId":121544,"journal":{"name":"2018 Twenty Fourth National Conference on Communications (NCC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126128560","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：