Multistep predictions for adaptive sampling in mobile robotic sensor networks using proximal ADMM
- Le, Viet-Anh, Nguyen, Linh, Nghiem, Truong
- Authors: Le, Viet-Anh , Nguyen, Linh , Nghiem, Truong
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 64850-64861
- Full Text:
- Reviewed:
- Description: This paper presents a novel approach, using multi-step predictions, to the adaptive sampling problem for efficient monitoring of environmental spatial phenomena in a mobile sensor network. We employ a Gaussian process to represent the spatial field of interest, which is then used to predict the field at unmeasured locations. The adaptive sampling problem aims to drive the mobile sensors to optimally navigate the environment while the sensors adaptively take measurements of the spatial phenomena at each sampling step. To this end, an optimal sampling criterion based on conditional entropy is proposed, which minimizes the prediction uncertainty of the Gaussian process model. By predicting the measurements the mobile sensors potentially take in a finite horizon of multiple future sampling steps and exploiting the chain rule of the conditional entropy, a multi-step-ahead adaptive sampling optimization problem is formulated. Its objective is to find the optimal sampling paths for the mobile sensors in multiple sampling steps ahead. Robot-robot and robot-obstacle collision avoidance is formulated as mixed-integer constraints. Compared with the single-step-ahead approach typically adopted in the literature, our approach provides better navigation, deployment, and data collection with more informative sensor readings. However, the resulting mixed-integer nonlinear program is highly complex and intractable. We propose to employ the proximal alternating direction method of multipliers to efficiently solve this problem. More importantly, the solution obtained by the proposed algorithm is theoretically guaranteed to converge to a stationary value. The effectiveness of our proposed approach was extensively validated by simulation using a real-world dataset, which showed highly promising results. © 2013 IEEE.
- Authors: Le, Viet-Anh , Nguyen, Linh , Nghiem, Truong
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 64850-64861
- Full Text:
- Reviewed:
- Description: This paper presents a novel approach, using multi-step predictions, to the adaptive sampling problem for efficient monitoring of environmental spatial phenomena in a mobile sensor network. We employ a Gaussian process to represent the spatial field of interest, which is then used to predict the field at unmeasured locations. The adaptive sampling problem aims to drive the mobile sensors to optimally navigate the environment while the sensors adaptively take measurements of the spatial phenomena at each sampling step. To this end, an optimal sampling criterion based on conditional entropy is proposed, which minimizes the prediction uncertainty of the Gaussian process model. By predicting the measurements the mobile sensors potentially take in a finite horizon of multiple future sampling steps and exploiting the chain rule of the conditional entropy, a multi-step-ahead adaptive sampling optimization problem is formulated. Its objective is to find the optimal sampling paths for the mobile sensors in multiple sampling steps ahead. Robot-robot and robot-obstacle collision avoidance is formulated as mixed-integer constraints. Compared with the single-step-ahead approach typically adopted in the literature, our approach provides better navigation, deployment, and data collection with more informative sensor readings. However, the resulting mixed-integer nonlinear program is highly complex and intractable. We propose to employ the proximal alternating direction method of multipliers to efficiently solve this problem. More importantly, the solution obtained by the proposed algorithm is theoretically guaranteed to converge to a stationary value. The effectiveness of our proposed approach was extensively validated by simulation using a real-world dataset, which showed highly promising results. © 2013 IEEE.
An efficient adaptive sampling approach for mobile robotic sensor networks using proximal ADMM
- Le, Viet-Anh, Nguyen, Linh, Nghiem, Truong
- Authors: Le, Viet-Anh , Nguyen, Linh , Nghiem, Truong
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 American Control Conference, ACC 2021 Vol. 2021-May, p. 1101-1106
- Full Text:
- Reviewed:
- Description: Adaptive sampling in a resource-constrained mobile robotic sensor network for monitoring a spatial phenomenon is a fundamental but challenging problem. In applications where a Gaussian Process is employed to model a spatial field and then to predict the field at unobserved locations, the adaptive sampling problem can be formulated as minimizing the negative log determinant of a predicted covariance matrix, which is a non-convex and highly complex function. Consequently, this optimization problem is typically addressed in a grid-based discrete domain, although it is combinatorial NP-hard and only a near-optimal solution can be obtained. To overcome this challenge, we propose using a proximal alternating direction method of multipliers (Px-ADMM) technique to solve the adaptive sampling optimization problem in a continuous domain. Numerical simulations using a real-world dataset demonstrate that the proposed PxADMM-based method outperforms a commonly used grid-based greedy method in the final model accuracy. © 2021 American Automatic Control Council.
- Authors: Le, Viet-Anh , Nguyen, Linh , Nghiem, Truong
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 American Control Conference, ACC 2021 Vol. 2021-May, p. 1101-1106
- Full Text:
- Reviewed:
- Description: Adaptive sampling in a resource-constrained mobile robotic sensor network for monitoring a spatial phenomenon is a fundamental but challenging problem. In applications where a Gaussian Process is employed to model a spatial field and then to predict the field at unobserved locations, the adaptive sampling problem can be formulated as minimizing the negative log determinant of a predicted covariance matrix, which is a non-convex and highly complex function. Consequently, this optimization problem is typically addressed in a grid-based discrete domain, although it is combinatorial NP-hard and only a near-optimal solution can be obtained. To overcome this challenge, we propose using a proximal alternating direction method of multipliers (Px-ADMM) technique to solve the adaptive sampling optimization problem in a continuous domain. Numerical simulations using a real-world dataset demonstrate that the proposed PxADMM-based method outperforms a commonly used grid-based greedy method in the final model accuracy. © 2021 American Automatic Control Council.
ADMM-based adaptive sampling strategy for nonholonomic mobile robotic sensor networks
- Le, Viet-Anh, Nguyen, Linh, Nghiem, Truong
- Authors: Le, Viet-Anh , Nguyen, Linh , Nghiem, Truong
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Sensors Journal Vol. 21, no. 13 (2021), p. 15369-15378
- Full Text:
- Reviewed:
- Description: This paper discusses the adaptive sampling problem in a nonholonomic mobile robotic sensor network for efficiently monitoring a spatial field. It is proposed to employ Gaussian process to model a spatial phenomenon and predict it at unmeasured positions, which enables the sampling optimization problem to be formulated by the use of the log determinant of a predicted covariance matrix at next sampling locations. The control, movement and nonholonomic dynamics constraints of the mobile sensors are also considered in the adaptive sampling optimization problem. In order to tackle the nonlinearity and nonconvexity of the objective function in the optimization problem we first exploit the linearized alternating direction method of multipliers (L-ADMM) method that can effectively simplify the objective function, though it is computationally expensive since a nonconvex problem needs to be solved exactly in each iteration. We then propose a novel approach called the successive convexified ADMM (SC-ADMM) that sequentially convexify the nonlinear dynamic constraints so that the original optimization problem can be split into convex subproblems. It is noted that both the L-ADMM algorithm and our SC-ADMM approach can solve the sampling optimization problem in either a centralized or a distributed manner. We validated the proposed approaches in 1000 experiments in a synthetic environment with a real-world dataset, where the obtained results suggest that both the L-ADMM and SC-ADMM techniques can provide good accuracy for the monitoring purpose. However, our proposed SC-ADMM approach computationally outperforms the L-ADMM counterpart, demonstrating its better practicality. © 2001-2012 IEEE.
- Authors: Le, Viet-Anh , Nguyen, Linh , Nghiem, Truong
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Sensors Journal Vol. 21, no. 13 (2021), p. 15369-15378
- Full Text:
- Reviewed:
- Description: This paper discusses the adaptive sampling problem in a nonholonomic mobile robotic sensor network for efficiently monitoring a spatial field. It is proposed to employ Gaussian process to model a spatial phenomenon and predict it at unmeasured positions, which enables the sampling optimization problem to be formulated by the use of the log determinant of a predicted covariance matrix at next sampling locations. The control, movement and nonholonomic dynamics constraints of the mobile sensors are also considered in the adaptive sampling optimization problem. In order to tackle the nonlinearity and nonconvexity of the objective function in the optimization problem we first exploit the linearized alternating direction method of multipliers (L-ADMM) method that can effectively simplify the objective function, though it is computationally expensive since a nonconvex problem needs to be solved exactly in each iteration. We then propose a novel approach called the successive convexified ADMM (SC-ADMM) that sequentially convexify the nonlinear dynamic constraints so that the original optimization problem can be split into convex subproblems. It is noted that both the L-ADMM algorithm and our SC-ADMM approach can solve the sampling optimization problem in either a centralized or a distributed manner. We validated the proposed approaches in 1000 experiments in a synthetic environment with a real-world dataset, where the obtained results suggest that both the L-ADMM and SC-ADMM techniques can provide good accuracy for the monitoring purpose. However, our proposed SC-ADMM approach computationally outperforms the L-ADMM counterpart, demonstrating its better practicality. © 2001-2012 IEEE.
Collision-free minimum-time trajectory planning for multiple vehicles based on ADMM
- Nguyen, Thanh, Nguyen, Thang, Nghiem, Truong, Nguyen, Linh, Baca, Jose, Rangel, Pablo, Song, Hyoung-Kyu
- Authors: Nguyen, Thanh , Nguyen, Thang , Nghiem, Truong , Nguyen, Linh , Baca, Jose , Rangel, Pablo , Song, Hyoung-Kyu
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, Kyoto, Japan, 23-27 October 2022, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Vol. 2022-October, p. 13785-13790
- Full Text: false
- Reviewed:
- Description: The paper presents a practical approach for planning trajectories for multiple vehicles where both collision avoidance and minimum travelling time are simultaneously considered. It is first proposed to exploit the mixed-integer programming (MIP) approach to formulate the collision avoidance paradigm, where the linear dynamic models are utilized to derive the linear constraints. Moreover, travelling time of each vehicle is compromised among them and set to be minimized so that all the vehicles can practically reach the expected destinations at the shortest time. Unfortunately, the formulated optimization problem is NP-hard. In order to effectively address it, we propose to employ the alternating direction method of multipliers (ADMM), which can share the computational burdens to distributive optimization solvers. Thus, the proposed method can enable each vehicle to obtain an expected trajectory in a practical time. Convergence of the proposed algorithm is also discussed. To verify effectiveness of our approach, we implemented it in a numerical example, where the obtained results are highly promising. © 2022 IEEE.
Distributed formation trajectory planning for multi-vehicle systems
- Nguyen, Binh, Nghiem, Truong, Nguyen, Linh, Nguyen, Tung, La, Hung, Sookhak, Mehdi, Nguyen, Thang
- Authors: Nguyen, Binh , Nghiem, Truong , Nguyen, Linh , Nguyen, Tung , La, Hung , Sookhak, Mehdi , Nguyen, Thang
- Date: 2023
- Type: Text , Conference paper
- Relation: 2023 American Control Conference, ACC 2023 Vol. 2023-May, p. 1325-1330
- Full Text: false
- Reviewed:
- Description: This paper addresses the problem of distributed formation trajectory planning for multi-vehicle systems with collision avoidance among vehicles. Unlike some previous distributed formation trajectory planning methods, our proposed approach offers great flexibility in handling computational tasks for each vehicle when the global formation of all the vehicles changes. It affords the system the ability to adapt to the computational capabilities of the vehicles. Furthermore, global formation constraints can be handled at any selected vehicles. Thus, any formation change can be effectively updated without recomputing all local formations at all the vehicles. To guarantee the above features, we first formulate a dynamic consensus-based optimization problem to achieve desired formations while guaranteeing collision avoidance among vehicles. Then, the optimization problem is effectively solved by ADMM-based or alternating projection-based algorithms, which are also presented. Theoretical analysis is provided not only to ensure the convergence of our method but also to show that the proposed algorithm can surely be implemented in a fully distributed manner. The effectiveness of the proposed method is illustrated by a numerical example of a 9-vehicle system. © 2023 American Automatic Control Council.
A study on the use of machine learning methods to improve reciprocating compressor reliability via torque tailoring
- Lu, Kui, Sultan, Ibrahim, Phung, Truong
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021, Ballarat, Australia, 12-15 December 2021, 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021
- Full Text:
- Reviewed:
- Description: Reciprocating compressors have found popularity in applications where compressed air is required at high pressure levels with moderate flow rates. The mechanical drives used for these compressors are based on the traditional slider-crank linkage which, despite its simplicity, does not lend itself to optimization effort aimed at improving the compressor reliability and performance. The work presented in this paper adopts the notion that the mechanical reliability of the compressor drive is limited by the level and cyclical variability of the loads transmitted through its members and the effectiveness of its cooling system. In the paper, machine learning methods will be employed to craft an objective function suitable to use in a Bayesian optimization effort undertaken to produce a more reliable compressor drive. A numerical example is presented to prove the validity of the presented method and its suitability for use in real life compressor designs. © 2021 IEEE.
- Authors: Lu, Kui , Sultan, Ibrahim , Phung, Truong
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021, Ballarat, Australia, 12-15 December 2021, 2021 International Conference on Maintenance and Intelligent Asset Management, ICMIAM 2021
- Full Text:
- Reviewed:
- Description: Reciprocating compressors have found popularity in applications where compressed air is required at high pressure levels with moderate flow rates. The mechanical drives used for these compressors are based on the traditional slider-crank linkage which, despite its simplicity, does not lend itself to optimization effort aimed at improving the compressor reliability and performance. The work presented in this paper adopts the notion that the mechanical reliability of the compressor drive is limited by the level and cyclical variability of the loads transmitted through its members and the effectiveness of its cooling system. In the paper, machine learning methods will be employed to craft an objective function suitable to use in a Bayesian optimization effort undertaken to produce a more reliable compressor drive. A numerical example is presented to prove the validity of the presented method and its suitability for use in real life compressor designs. © 2021 IEEE.
A fault-tolerant cascaded switched-capacitor multilevel inverter for domestic applications in smart grids
- Akbari, Ehsan, Teimouri, Ali, Saki, Mojtaba, Rezaei, Mohammad, Hu, Jiefeng, Band, Shahab, Pai, Hao-Ting, Mosavi, Amir
- Authors: Akbari, Ehsan , Teimouri, Ali , Saki, Mojtaba , Rezaei, Mohammad , Hu, Jiefeng , Band, Shahab , Pai, Hao-Ting , Mosavi, Amir
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 110590-110602
- Full Text:
- Reviewed:
- Description: Cascaded multilevel inverters (MLIs) generate an output voltage using series-connected power modules that employ standard configurations of low-voltage components. Each module may employ one or more switched capacitors to double or quadruple its input voltage. The higher number of switched capacitors and semiconductor switches in MLIs compared to conventional two-level inverters has led to concerns about overall system reliability. A fault-tolerant design can mitigate this reliability issue. If one part of the system fails, the MLI can continue its planned operation at a reduced level rather than the entire system failing, which makes the fault tolerance of the MLI particularly important. In this paper, a novel fault location technique is presented that leads to a significant reduction in fault location detection time based on the reliability priority of the components of the proposed fault-tolerant switched capacitor cascaded MLI (CSCMLI). The main contribution of this paper is to reduce the number of MLI switches under fault conditions while operating at lower levels. The fault-tolerant inverter requires fewer switches at higher reliability, and the comparison with similar MLIs shows a faster dynamic response of fault detection and reduced fault location detection time. The experimental results confirm the effectiveness of the presented methods applied in the CSCMLI. Also, all experimental data including processor code, schematic, PCB, and video of CSCMLI operation are attached. © 2013 IEEE.
- Authors: Akbari, Ehsan , Teimouri, Ali , Saki, Mojtaba , Rezaei, Mohammad , Hu, Jiefeng , Band, Shahab , Pai, Hao-Ting , Mosavi, Amir
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Access Vol. 10, no. (2022), p. 110590-110602
- Full Text:
- Reviewed:
- Description: Cascaded multilevel inverters (MLIs) generate an output voltage using series-connected power modules that employ standard configurations of low-voltage components. Each module may employ one or more switched capacitors to double or quadruple its input voltage. The higher number of switched capacitors and semiconductor switches in MLIs compared to conventional two-level inverters has led to concerns about overall system reliability. A fault-tolerant design can mitigate this reliability issue. If one part of the system fails, the MLI can continue its planned operation at a reduced level rather than the entire system failing, which makes the fault tolerance of the MLI particularly important. In this paper, a novel fault location technique is presented that leads to a significant reduction in fault location detection time based on the reliability priority of the components of the proposed fault-tolerant switched capacitor cascaded MLI (CSCMLI). The main contribution of this paper is to reduce the number of MLI switches under fault conditions while operating at lower levels. The fault-tolerant inverter requires fewer switches at higher reliability, and the comparison with similar MLIs shows a faster dynamic response of fault detection and reduced fault location detection time. The experimental results confirm the effectiveness of the presented methods applied in the CSCMLI. Also, all experimental data including processor code, schematic, PCB, and video of CSCMLI operation are attached. © 2013 IEEE.
Vehicle trajectory clustering based on dynamic representation learning of internet of vehicles
- Wang, Wei, Xia, Feng, Nie, Hansong, Chen, Zhikui, Gong, Zhiguo
- Authors: Wang, Wei , Xia, Feng , Nie, Hansong , Chen, Zhikui , Gong, Zhiguo
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Intelligent Transportation Systems Vol. 22, no. 6 (2021), p. 3567-3576
- Full Text:
- Reviewed:
- Description: With the widely used Internet of Things, 5G, and smart city technologies, we are able to acquire a variety of vehicle trajectory data. These trajectory data are of great significance which can be used to extract relevant information in order to, for instance, calculate the optimal path from one position to another, detect abnormal behavior, monitor the traffic flow in a city, and predict the next position of an object. One of the key technology is to cluster vehicle trajectory. However, existing methods mainly rely on manually designed metrics which may lead to biased results. Meanwhile, the large scale of vehicle trajectory data has become a challenge because calculating these manually designed metrics will cost more time and space. To address these challenges, we propose to employ network representation learning to achieve accurate vehicle trajectory clustering. Specifically, we first construct the k-nearest neighbor-based internet of vehicles in a dynamic manner. Then we learn the low-dimensional representations of vehicles by performing dynamic network representation learning on the constructed network. Finally, using the learned vehicle vectors, vehicle trajectories are clustered with machine learning methods. Experimental results on the real-word dataset show that our method achieves the best performance compared against baseline methods. © 2000-2011 IEEE. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
- Authors: Wang, Wei , Xia, Feng , Nie, Hansong , Chen, Zhikui , Gong, Zhiguo
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Intelligent Transportation Systems Vol. 22, no. 6 (2021), p. 3567-3576
- Full Text:
- Reviewed:
- Description: With the widely used Internet of Things, 5G, and smart city technologies, we are able to acquire a variety of vehicle trajectory data. These trajectory data are of great significance which can be used to extract relevant information in order to, for instance, calculate the optimal path from one position to another, detect abnormal behavior, monitor the traffic flow in a city, and predict the next position of an object. One of the key technology is to cluster vehicle trajectory. However, existing methods mainly rely on manually designed metrics which may lead to biased results. Meanwhile, the large scale of vehicle trajectory data has become a challenge because calculating these manually designed metrics will cost more time and space. To address these challenges, we propose to employ network representation learning to achieve accurate vehicle trajectory clustering. Specifically, we first construct the k-nearest neighbor-based internet of vehicles in a dynamic manner. Then we learn the low-dimensional representations of vehicles by performing dynamic network representation learning on the constructed network. Finally, using the learned vehicle vectors, vehicle trajectories are clustered with machine learning methods. Experimental results on the real-word dataset show that our method achieves the best performance compared against baseline methods. © 2000-2011 IEEE. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
Dual mechanical port machine based hybrid electric vehicle using reduced switch converters
- Bizhani, Hamed, Yao, Gang, Muyeen, S., Islam, Syed, Ben-Brahim, Lazhar
- Authors: Bizhani, Hamed , Yao, Gang , Muyeen, S. , Islam, Syed , Ben-Brahim, Lazhar
- Date: 2019
- Type: Text , Journal article
- Relation: IEEE Access Vol. 7, no. (2019), p. 33665-33676
- Full Text:
- Reviewed:
- Description: Due to the increased environmental pollution, hybrid vehicles have attracted enormous attention in today's society. The two most important factors in designing these vehicles are size and weight. For this purpose, some researchers have presented the use of the dual-mechanical-port machine (DMPM) in hybrid electric vehicles (HEVs). This paper presents two modified converter topologies with a reduced number of switching devices for use on DMPM-based HEVs, with the goal of reducing the overall size and weight of the system. Beside the design of the DMPM in the series-parallel HEV structure along with the energy management unit, the conventional back-to-back (BB) converter is replaced with nine-switch (NS) and five-leg (FL) converters. These converters have never been examined for the DMPM-based HEV, and therefore, the objective of this paper is to reveal the operational characteristics and power flow mechanism of this machine using the NS and FL converters. The simulation analysis is carried out using MATLAB/Simulink considering all HEV operational modes. In addition, two proposed and the conventional converters are compared in terms of losses, maximum achievable voltages, required dc-link voltages, the rating of the components, and torque ripple, and finally, a recommendation is made based on the obtained results.
- Authors: Bizhani, Hamed , Yao, Gang , Muyeen, S. , Islam, Syed , Ben-Brahim, Lazhar
- Date: 2019
- Type: Text , Journal article
- Relation: IEEE Access Vol. 7, no. (2019), p. 33665-33676
- Full Text:
- Reviewed:
- Description: Due to the increased environmental pollution, hybrid vehicles have attracted enormous attention in today's society. The two most important factors in designing these vehicles are size and weight. For this purpose, some researchers have presented the use of the dual-mechanical-port machine (DMPM) in hybrid electric vehicles (HEVs). This paper presents two modified converter topologies with a reduced number of switching devices for use on DMPM-based HEVs, with the goal of reducing the overall size and weight of the system. Beside the design of the DMPM in the series-parallel HEV structure along with the energy management unit, the conventional back-to-back (BB) converter is replaced with nine-switch (NS) and five-leg (FL) converters. These converters have never been examined for the DMPM-based HEV, and therefore, the objective of this paper is to reveal the operational characteristics and power flow mechanism of this machine using the NS and FL converters. The simulation analysis is carried out using MATLAB/Simulink considering all HEV operational modes. In addition, two proposed and the conventional converters are compared in terms of losses, maximum achievable voltages, required dc-link voltages, the rating of the components, and torque ripple, and finally, a recommendation is made based on the obtained results.
Data exchange in delay tolerant networks using joint inter- and intra-flow network coding
- Ostovari, Pouya, Wu, Jie, Jolfaei, Alireza
- Authors: Ostovari, Pouya , Wu, Jie , Jolfaei, Alireza
- Date: 2018
- Type: Text , Conference proceedings
- Relation: 37th IEEE International Performance Computing and Communications Conference, IPCCC 2018; Orlando, United States; 17th-19th November 2018 p. 1-8
- Full Text:
- Reviewed:
- Description: Data transmission in delay tolerant networks (DTNs) is a challenging problem due to the lack of continuous network connectivity and nondeterministic mobility of the nodes. Epidemic routing and spray-and-wait methods are two popular mechanisms that are proposed for DTNs. In order to reduce the transmission delay in DTNs, some previous works combine intra-flow network coding with the routing protocols. In this paper, we propose two routing mechanisms using systematic joint inter- and intra-flow network coding for the purpose of data exchange between the nodes. We discuss the reasons why inter-flow network coding helps to reduce the delivery delay of the packets, and we also analyze the delays related with only using intra-flow coding, and joint inter- and intra-flow coding methods. We empirically show the benefit of joint coding over just intra-flow coding. Based on our simulation, joint coding can reduce the delay up to 40%, compared to only intra-flow coding.
- Description: 2018 IEEE 37th International Performance Computing and Communications Conference, IPCCC 2018
- Authors: Ostovari, Pouya , Wu, Jie , Jolfaei, Alireza
- Date: 2018
- Type: Text , Conference proceedings
- Relation: 37th IEEE International Performance Computing and Communications Conference, IPCCC 2018; Orlando, United States; 17th-19th November 2018 p. 1-8
- Full Text:
- Reviewed:
- Description: Data transmission in delay tolerant networks (DTNs) is a challenging problem due to the lack of continuous network connectivity and nondeterministic mobility of the nodes. Epidemic routing and spray-and-wait methods are two popular mechanisms that are proposed for DTNs. In order to reduce the transmission delay in DTNs, some previous works combine intra-flow network coding with the routing protocols. In this paper, we propose two routing mechanisms using systematic joint inter- and intra-flow network coding for the purpose of data exchange between the nodes. We discuss the reasons why inter-flow network coding helps to reduce the delivery delay of the packets, and we also analyze the delays related with only using intra-flow coding, and joint inter- and intra-flow coding methods. We empirically show the benefit of joint coding over just intra-flow coding. Based on our simulation, joint coding can reduce the delay up to 40%, compared to only intra-flow coding.
- Description: 2018 IEEE 37th International Performance Computing and Communications Conference, IPCCC 2018
Bidirectional mapping coupled GAN for generalized zero-shot learning
- Shermin, Tasfia, Teng, Shyh, Sohel, Ferdous, Murshed, Manzur, Lu, Guojun
- Authors: Shermin, Tasfia , Teng, Shyh , Sohel, Ferdous , Murshed, Manzur , Lu, Guojun
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Image Processing Vol. 31, no. (2022), p. 721-733
- Full Text:
- Reviewed:
- Description: Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen classes and preserving the distinction between seen-unseen classes is crucial for GZSL methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining seen-unseen classes distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the concept of the coupled generative adversarial network into a bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining distinctive information of seen-unseen classes in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods. © 1992-2012 IEEE.
- Authors: Shermin, Tasfia , Teng, Shyh , Sohel, Ferdous , Murshed, Manzur , Lu, Guojun
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Image Processing Vol. 31, no. (2022), p. 721-733
- Full Text:
- Reviewed:
- Description: Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen classes and preserving the distinction between seen-unseen classes is crucial for GZSL methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining seen-unseen classes distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the concept of the coupled generative adversarial network into a bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining distinctive information of seen-unseen classes in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods. © 1992-2012 IEEE.
Random walks : a review of algorithms and applications
- Xia, Feng, Liu, Jiaying, Nie, Hansong, Fu, Yonghao, Wan, Liangtian, Kong, Xiangjie
- Authors: Xia, Feng , Liu, Jiaying , Nie, Hansong , Fu, Yonghao , Wan, Liangtian , Kong, Xiangjie
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Emerging Topics in Computational Intelligence Vol. 4, no. 2 (2020), p. 95-107
- Full Text:
- Reviewed:
- Description: A random walk is known as a random process which describes a path including a succession of random steps in the mathematical space. It has increasingly been popular in various disciplines such as mathematics and computer science. Furthermore, in quantum mechanics, quantum walks can be regarded as quantum analogues of classical random walks. Classical random walks and quantum walks can be used to calculate the proximity between nodes and extract the topology in the network. Various random walk related models can be applied in different fields, which is of great significance to downstream tasks such as link prediction, recommendation, computer vision, semi-supervised learning, and network embedding. In this article, we aim to provide a comprehensive review of classical random walks and quantum walks. We first review the knowledge of classical random walks and quantum walks, including basic concepts and some typical algorithms. We also compare the algorithms based on quantum walks and classical random walks from the perspective of time complexity. Then we introduce their applications in the field of computer science. Finally we discuss the open issues from the perspectives of efficiency, main-memory volume, and computing time of existing algorithms. This study aims to contribute to this growing area of research by exploring random walks and quantum walks together. © 2017 IEEE.
- Authors: Xia, Feng , Liu, Jiaying , Nie, Hansong , Fu, Yonghao , Wan, Liangtian , Kong, Xiangjie
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Emerging Topics in Computational Intelligence Vol. 4, no. 2 (2020), p. 95-107
- Full Text:
- Reviewed:
- Description: A random walk is known as a random process which describes a path including a succession of random steps in the mathematical space. It has increasingly been popular in various disciplines such as mathematics and computer science. Furthermore, in quantum mechanics, quantum walks can be regarded as quantum analogues of classical random walks. Classical random walks and quantum walks can be used to calculate the proximity between nodes and extract the topology in the network. Various random walk related models can be applied in different fields, which is of great significance to downstream tasks such as link prediction, recommendation, computer vision, semi-supervised learning, and network embedding. In this article, we aim to provide a comprehensive review of classical random walks and quantum walks. We first review the knowledge of classical random walks and quantum walks, including basic concepts and some typical algorithms. We also compare the algorithms based on quantum walks and classical random walks from the perspective of time complexity. Then we introduce their applications in the field of computer science. Finally we discuss the open issues from the perspectives of efficiency, main-memory volume, and computing time of existing algorithms. This study aims to contribute to this growing area of research by exploring random walks and quantum walks together. © 2017 IEEE.
MODEL : motif-based deep feature learning for link prediction
- Wang, Lei, Ren, Jing, Xu, Bo, Li, Jianxin, Luo, Wei, Xia, Feng
- Authors: Wang, Lei , Ren, Jing , Xu, Bo , Li, Jianxin , Luo, Wei , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 7, no. 2 (2020), p. 503-516
- Full Text:
- Reviewed:
- Description: Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this article, we propose a novel embedding algorithm that incorporates network motifs to capture higher order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the state-of-the-art embedding-based algorithms (by 19%). © 2014 IEEE.
- Authors: Wang, Lei , Ren, Jing , Xu, Bo , Li, Jianxin , Luo, Wei , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 7, no. 2 (2020), p. 503-516
- Full Text:
- Reviewed:
- Description: Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this article, we propose a novel embedding algorithm that incorporates network motifs to capture higher order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the state-of-the-art embedding-based algorithms (by 19%). © 2014 IEEE.
Fast intermode selection for HEVC video coding using phase correlation
- Podder, Pallab, Paul, Manoranjan, Murshed, Manzur, Chakraborty, Subrata
- Authors: Podder, Pallab , Paul, Manoranjan , Murshed, Manzur , Chakraborty, Subrata
- Date: 2015
- Type: Text , Conference proceedings , Conference paper
- Relation: 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014; Wollongong, Australia; 25th-27th November 2014 p. 1-8
- Relation: http://purl.org/au-research/grants/arc/DP130103670
- Full Text:
- Reviewed:
- Description: The recent High Efficiency Video Coding (HEVC) Standard demonstrates higher rate-distortion (RD) performance compared to its predecessor H.264/AVC using different new tools especially larger and asymmetric inter-mode variable size motion estimation and compensation. This requires more than 4 times computational time compared to H.264/AVC. As a result it has always been a big concern for the researchers to reduce the amount of time while maintaining the standard quality of the video. The reduction of computational time by smart selection of the appropriate modes in HEVC is our motivation. To accomplish this task in this paper, we use phase correlation to approximate the motion information between current and reference blocks by comparing with a number of different binary pattern templates and then select a subset of motion estimation modes without exhaustively exploring all possible modes. The experimental results exhibit that the proposed HEVC-PC (HEVC with Phase Correlation) scheme outperforms the standard HEVC scheme in terms of computational time while preserving-the same quality of the video sequences. More specifically, around 40% encoding time is reduced compared to the exhaustive mode selection in HEVC. © 2014 IEEE.
- Description: 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014
- Authors: Podder, Pallab , Paul, Manoranjan , Murshed, Manzur , Chakraborty, Subrata
- Date: 2015
- Type: Text , Conference proceedings , Conference paper
- Relation: 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014; Wollongong, Australia; 25th-27th November 2014 p. 1-8
- Relation: http://purl.org/au-research/grants/arc/DP130103670
- Full Text:
- Reviewed:
- Description: The recent High Efficiency Video Coding (HEVC) Standard demonstrates higher rate-distortion (RD) performance compared to its predecessor H.264/AVC using different new tools especially larger and asymmetric inter-mode variable size motion estimation and compensation. This requires more than 4 times computational time compared to H.264/AVC. As a result it has always been a big concern for the researchers to reduce the amount of time while maintaining the standard quality of the video. The reduction of computational time by smart selection of the appropriate modes in HEVC is our motivation. To accomplish this task in this paper, we use phase correlation to approximate the motion information between current and reference blocks by comparing with a number of different binary pattern templates and then select a subset of motion estimation modes without exhaustively exploring all possible modes. The experimental results exhibit that the proposed HEVC-PC (HEVC with Phase Correlation) scheme outperforms the standard HEVC scheme in terms of computational time while preserving-the same quality of the video sequences. More specifically, around 40% encoding time is reduced compared to the exhaustive mode selection in HEVC. © 2014 IEEE.
- Description: 2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014
Attacks on self-driving cars and their countermeasures : a survey
- Chowdhury, Abdullahi, Karmakar, Gour, Kamruzzaman, Joarder, Jolfaei, Alireza, Das, Rajkumar
- Authors: Chowdhury, Abdullahi , Karmakar, Gour , Kamruzzaman, Joarder , Jolfaei, Alireza , Das, Rajkumar
- Date: 2020
- Type: Text , Journal article , Review
- Relation: IEEE Access Vol. 8, no. (2020), p. 207308-207342
- Full Text:
- Reviewed:
- Description: Intelligent Traffic Systems (ITS) are currently evolving in the form of a cooperative ITS or connected vehicles. Both forms use the data communications between Vehicle-To-Vehicle (V2V), Vehicle-To-Infrastructure (V2I/I2V) and other on-road entities, and are accelerating the adoption of self-driving cars. The development of cyber-physical systems containing advanced sensors, sub-systems, and smart driving assistance applications over the past decade is equipping unmanned aerial and road vehicles with autonomous decision-making capabilities. The level of autonomy depends upon the make-up and degree of sensor sophistication and the vehicle's operational applications. As a result, self-driving cars are being compromised perceived as a serious threat. Therefore, analyzing the threats and attacks on self-driving cars and ITSs, and their corresponding countermeasures to reduce those threats and attacks are needed. For this reason, some survey papers compiling potential attacks on VANETs, ITSs and self-driving cars, and their detection mechanisms are available in the current literature. However, up to our knowledge, they have not covered the real attacks already happened in self-driving cars. To bridge this research gap, in this paper, we analyze the attacks that already targeted self-driving cars and extensively present potential cyber-Attacks and their impacts on those cars along with their vulnerabilities. For recently reported attacks, we describe the possible mitigation strategies taken by the manufacturers and governments. This survey includes recent works on how a self-driving car can ensure resilient operation even under ongoing cyber-Attack. We also provide further research directions to improve the security issues associated with self-driving cars. © 2013 IEEE.
- Authors: Chowdhury, Abdullahi , Karmakar, Gour , Kamruzzaman, Joarder , Jolfaei, Alireza , Das, Rajkumar
- Date: 2020
- Type: Text , Journal article , Review
- Relation: IEEE Access Vol. 8, no. (2020), p. 207308-207342
- Full Text:
- Reviewed:
- Description: Intelligent Traffic Systems (ITS) are currently evolving in the form of a cooperative ITS or connected vehicles. Both forms use the data communications between Vehicle-To-Vehicle (V2V), Vehicle-To-Infrastructure (V2I/I2V) and other on-road entities, and are accelerating the adoption of self-driving cars. The development of cyber-physical systems containing advanced sensors, sub-systems, and smart driving assistance applications over the past decade is equipping unmanned aerial and road vehicles with autonomous decision-making capabilities. The level of autonomy depends upon the make-up and degree of sensor sophistication and the vehicle's operational applications. As a result, self-driving cars are being compromised perceived as a serious threat. Therefore, analyzing the threats and attacks on self-driving cars and ITSs, and their corresponding countermeasures to reduce those threats and attacks are needed. For this reason, some survey papers compiling potential attacks on VANETs, ITSs and self-driving cars, and their detection mechanisms are available in the current literature. However, up to our knowledge, they have not covered the real attacks already happened in self-driving cars. To bridge this research gap, in this paper, we analyze the attacks that already targeted self-driving cars and extensively present potential cyber-Attacks and their impacts on those cars along with their vulnerabilities. For recently reported attacks, we describe the possible mitigation strategies taken by the manufacturers and governments. This survey includes recent works on how a self-driving car can ensure resilient operation even under ongoing cyber-Attack. We also provide further research directions to improve the security issues associated with self-driving cars. © 2013 IEEE.
Adversarial network with multiple classifiers for open set domain adaptation
- Shermin, Tasfia, Lu, Guojun, Teng, Shyh, Murshed, Manzur, Sohel, Ferdous
- Authors: Shermin, Tasfia , Lu, Guojun , Teng, Shyh , Murshed, Manzur , Sohel, Ferdous
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Multimedia Vol. 23, no. (2021), p. 2732-2744
- Full Text:
- Reviewed:
- Description: Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set domain adaptation settings in the literature to extend the applications of domain adaptation methods in real-world scenarios. This paper focuses on the type of open set domain adaptation setting where the target domain has both private ('unknown classes') label space and the shared ('known classes') label space. However, the source domain only has the 'known classes' label space. Prevalent distribution-matching domain adaptation methods are inadequate in such a setting that demands adaptation from a smaller source domain to a larger and diverse target domain with more classes. For addressing this specific open set domain adaptation setting, prior research introduces a domain adversarial model that uses a fixed threshold for distinguishing known from unknown target samples and lacks at handling negative transfers. We extend their adversarial model and propose a novel adversarial domain adaptation model with multiple auxiliary classifiers. The proposed multi-classifier structure introduces a weighting module that evaluates distinctive domain characteristics for assigning the target samples with weights which are more representative to whether they are likely to belong to the known and unknown classes to encourage positive transfers during adversarial training and simultaneously reduces the domain gap between the shared classes of the source and target domains. A thorough experimental investigation shows that our proposed method outperforms existing domain adaptation methods on a number of domain adaptation datasets. © 1999-2012 IEEE.
- Authors: Shermin, Tasfia , Lu, Guojun , Teng, Shyh , Murshed, Manzur , Sohel, Ferdous
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Multimedia Vol. 23, no. (2021), p. 2732-2744
- Full Text:
- Reviewed:
- Description: Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set domain adaptation settings in the literature to extend the applications of domain adaptation methods in real-world scenarios. This paper focuses on the type of open set domain adaptation setting where the target domain has both private ('unknown classes') label space and the shared ('known classes') label space. However, the source domain only has the 'known classes' label space. Prevalent distribution-matching domain adaptation methods are inadequate in such a setting that demands adaptation from a smaller source domain to a larger and diverse target domain with more classes. For addressing this specific open set domain adaptation setting, prior research introduces a domain adversarial model that uses a fixed threshold for distinguishing known from unknown target samples and lacks at handling negative transfers. We extend their adversarial model and propose a novel adversarial domain adaptation model with multiple auxiliary classifiers. The proposed multi-classifier structure introduces a weighting module that evaluates distinctive domain characteristics for assigning the target samples with weights which are more representative to whether they are likely to belong to the known and unknown classes to encourage positive transfers during adversarial training and simultaneously reduces the domain gap between the shared classes of the source and target domains. A thorough experimental investigation shows that our proposed method outperforms existing domain adaptation methods on a number of domain adaptation datasets. © 1999-2012 IEEE.
Reduced switch multilevel inverter topologies for renewable energy sources
- Sarebanzadeh, Maryam, Hosseinzadeh, Mohammad, Garcia, Cristian, Babaei, Ebrahim, Islam, Syed, Rodriguez, Jose
- Authors: Sarebanzadeh, Maryam , Hosseinzadeh, Mohammad , Garcia, Cristian , Babaei, Ebrahim , Islam, Syed , Rodriguez, Jose
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Access Vol. 9, no. (2021), p. 120580-120595
- Full Text:
- Reviewed:
- Description: This article proposes two generalized multilevel inverter configurations that reduce the number of switching devices, isolated DC sources, and total standing voltage on power switches, making them suitable for renewable energy sources. The main topology is a multilevel inverter that handles two isolated DC sources with ten power switches to create 25 voltage levels. Based on the main proposed topology, two generalized multilevel inverters are introduced to provide flexibility in the design and to minimize the number of elements. The optimal topologies for both extensive multilevel inverters are derived from different design objectives such as minimizing the number of elements (gate drivers, DC sources), achieving a large number of levels, and minimizing the total standing voltage. The main advantages of the proposed topologies are a reduced number of elements compared to those required by other existing multilevel inverter topologies. The power loss analysis and standalone PV application of the proposed topologies are discussed. Experimental results are presented for the proposed topology to demonstrate its correct operation. © 2013 IEEE.
- Authors: Sarebanzadeh, Maryam , Hosseinzadeh, Mohammad , Garcia, Cristian , Babaei, Ebrahim , Islam, Syed , Rodriguez, Jose
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Access Vol. 9, no. (2021), p. 120580-120595
- Full Text:
- Reviewed:
- Description: This article proposes two generalized multilevel inverter configurations that reduce the number of switching devices, isolated DC sources, and total standing voltage on power switches, making them suitable for renewable energy sources. The main topology is a multilevel inverter that handles two isolated DC sources with ten power switches to create 25 voltage levels. Based on the main proposed topology, two generalized multilevel inverters are introduced to provide flexibility in the design and to minimize the number of elements. The optimal topologies for both extensive multilevel inverters are derived from different design objectives such as minimizing the number of elements (gate drivers, DC sources), achieving a large number of levels, and minimizing the total standing voltage. The main advantages of the proposed topologies are a reduced number of elements compared to those required by other existing multilevel inverter topologies. The power loss analysis and standalone PV application of the proposed topologies are discussed. Experimental results are presented for the proposed topology to demonstrate its correct operation. © 2013 IEEE.
Rectified softmax loss with all-sided cost sensitivity for age estimation
- Li, Daxiang, Ma, Xuan, Ren, Yaqiong, Teng, Shyh-Wei
- Authors: Li, Daxiang , Ma, Xuan , Ren, Yaqiong , Teng, Shyh-Wei
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Access Vol. 8, no. (2020), p. 32551-32563
- Full Text:
- Reviewed:
- Description: In Convolutional Neural Network (ConvNet) based age estimation algorithms, softmax loss is usually chosen as the loss function directly, and the problems of Cost Sensitivity (CS), such as class imbalance and misclassification cost difference between different classes, are not considered. Focus on these problems, this paper constructs a rectified softmax loss function with all-sided CS, and proposes a novel cost-sensitive ConvNet based age estimation algorithm. Firstly, a loss function is established for each age category to solve the imbalance of the number of training samples. Then, a cost matrix is defined to reflect the cost difference caused by misclassification between different classes, thus constructing a new cost-sensitive error function. Finally, the above methods are merged to construct a rectified softmax loss function for ConvNet model, and a corresponding Back Propagation (BP) training scheme is designed to enable ConvNet network to learn robust face representation for age estimation during the training phase. Simultaneously, the rectified softmax loss is theoretically proved that it satisfies the general conditions of the loss function used for classification. The effectiveness of the proposed method is verified by experiments on face image datasets of different races. © 2013 IEEE.
- Authors: Li, Daxiang , Ma, Xuan , Ren, Yaqiong , Teng, Shyh-Wei
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Access Vol. 8, no. (2020), p. 32551-32563
- Full Text:
- Reviewed:
- Description: In Convolutional Neural Network (ConvNet) based age estimation algorithms, softmax loss is usually chosen as the loss function directly, and the problems of Cost Sensitivity (CS), such as class imbalance and misclassification cost difference between different classes, are not considered. Focus on these problems, this paper constructs a rectified softmax loss function with all-sided CS, and proposes a novel cost-sensitive ConvNet based age estimation algorithm. Firstly, a loss function is established for each age category to solve the imbalance of the number of training samples. Then, a cost matrix is defined to reflect the cost difference caused by misclassification between different classes, thus constructing a new cost-sensitive error function. Finally, the above methods are merged to construct a rectified softmax loss function for ConvNet model, and a corresponding Back Propagation (BP) training scheme is designed to enable ConvNet network to learn robust face representation for age estimation during the training phase. Simultaneously, the rectified softmax loss is theoretically proved that it satisfies the general conditions of the loss function used for classification. The effectiveness of the proposed method is verified by experiments on face image datasets of different races. © 2013 IEEE.
An efficient selective miner consensus protocol in blockchain oriented iot smart monitoring
- Uddin, Ashraf, Stranieri, Andrew, Gondal, Iqbal, Balasubramanian, Venki
- Authors: Uddin, Ashraf , Stranieri, Andrew , Gondal, Iqbal , Balasubramanian, Venki
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 2019 IEEE International Conference on Industrial Technology, ICIT 2019; Melbourne; Australia; 13th-15th February 2019 Vol. 2019-February, p. 1135-1142
- Full Text:
- Reviewed:
- Description: Blockchains have been widely used in Internet of Things(IoT) applications including smart cities, smart home and smart governance to provide high levels of security and privacy. In this article, we advance a Blockchain based decentralized architecture for the storage of IoT data produced from smart home/cities. The architecture includes a secure communication protocol using a sign-encryption technique between power constrained IoT devices and a Gateway. The sign encryption also preserves privacy. We propose that a Software Agent executing on the Gateway selects a Miner node using performance parameters of Miners. Simulations demonstrate that the recommended Miner selection outperforms Proof of Works selection used in Bitcoin and Random Miner Selection.
- Description: Proceedings of the IEEE International Conference on Industrial Technology
- Authors: Uddin, Ashraf , Stranieri, Andrew , Gondal, Iqbal , Balasubramanian, Venki
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 2019 IEEE International Conference on Industrial Technology, ICIT 2019; Melbourne; Australia; 13th-15th February 2019 Vol. 2019-February, p. 1135-1142
- Full Text:
- Reviewed:
- Description: Blockchains have been widely used in Internet of Things(IoT) applications including smart cities, smart home and smart governance to provide high levels of security and privacy. In this article, we advance a Blockchain based decentralized architecture for the storage of IoT data produced from smart home/cities. The architecture includes a secure communication protocol using a sign-encryption technique between power constrained IoT devices and a Gateway. The sign encryption also preserves privacy. We propose that a Software Agent executing on the Gateway selects a Miner node using performance parameters of Miners. Simulations demonstrate that the recommended Miner selection outperforms Proof of Works selection used in Bitcoin and Random Miner Selection.
- Description: Proceedings of the IEEE International Conference on Industrial Technology
Cell-free massive MIMO for wireless federated learning
- Vu, Tung, Ngo, Duy, Tran, Nguyen, Ngo, Hien, Dao, Minh, Middleton, Richard
- Authors: Vu, Tung , Ngo, Duy , Tran, Nguyen , Ngo, Hien , Dao, Minh , Middleton, Richard
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Wireless Communications Vol. 19, no. 10 (2020), p. 6377-6392
- Full Text:
- Reviewed:
- Description: This paper proposes a novel scheme for cell-free massive multiple-input multiple-output (CFmMIMO) networks to support any federated learning (FL) framework. This scheme allows each instead of all the iterations of the FL framework to happen in a large-scale coherence time to guarantee a stable operation of an FL process. To show how to optimize the FL performance using this proposed scheme, we consider an existing FL framework as an example and target FL training time minimization for this framework. An optimization problem is then formulated to jointly optimize the local accuracy, transmit power, data rate, and users' processing frequency. This mixed-Timescale stochastic nonconvex problem captures the complex interactions among the training time, and transmission and computation of training updates of one FL process. By employing the online successive convex approximation approach, we develop a new algorithm to solve the formulated problem with proven convergence to the neighbourhood of its stationary points. Our numerical results confirm that the presented joint design reduces the training time by up to 55% over baseline approaches. They also show that CFmMIMO here requires the lowest training time for FL processes compared with cell-free time-division multiple access massive MIMO and collocated massive MIMO. © 2002-2012 IEEE.
- Authors: Vu, Tung , Ngo, Duy , Tran, Nguyen , Ngo, Hien , Dao, Minh , Middleton, Richard
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Transactions on Wireless Communications Vol. 19, no. 10 (2020), p. 6377-6392
- Full Text:
- Reviewed:
- Description: This paper proposes a novel scheme for cell-free massive multiple-input multiple-output (CFmMIMO) networks to support any federated learning (FL) framework. This scheme allows each instead of all the iterations of the FL framework to happen in a large-scale coherence time to guarantee a stable operation of an FL process. To show how to optimize the FL performance using this proposed scheme, we consider an existing FL framework as an example and target FL training time minimization for this framework. An optimization problem is then formulated to jointly optimize the local accuracy, transmit power, data rate, and users' processing frequency. This mixed-Timescale stochastic nonconvex problem captures the complex interactions among the training time, and transmission and computation of training updates of one FL process. By employing the online successive convex approximation approach, we develop a new algorithm to solve the formulated problem with proven convergence to the neighbourhood of its stationary points. Our numerical results confirm that the presented joint design reduces the training time by up to 55% over baseline approaches. They also show that CFmMIMO here requires the lowest training time for FL processes compared with cell-free time-division multiple access massive MIMO and collocated massive MIMO. © 2002-2012 IEEE.