Sumit Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sumit Kumar has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Garimella Rama Murthy
International Institute of Information Technology
2 shared publications - Chandan Pradhan
Signal Processing and Communication Research Center, International Institute of Information Technology, Hyderabad, India
1 shared publication - Deepti Singhal
International Institute of Information Technology Hyderabad, India
1 shared publication - Kunal Sankhe
Signal Processing and Communication Research Center International Institute of Information Technology Hyderabad India
1 shared publication
Latest Publications
- Open Access
Machine Learning Based Cooperative Relay Selection in Virtual MIMO
In cellular systems, virtual multiple-input multiple-output (V-MIMO) technology promises to achieve performance gains comparable to conventional MIMO. In this paper, we propose cooperative relay selection algorithm based on machine learning techniques. Willingness of user to cooperate in V-MIMO depends on his current battery power, time and day along with incentives offered by service provider. Every user has different criterion to participate in V-MIMO, but allows a specific behavior pattern. Therefore, it is required to predict willing users in the neighborhood of source user (SU), before selecting users as cooperative nodes. Only inactive users belonging to Virtual Antenna Array (VAA) cell of SU are assumed to cooperate. This reduces control overheads in cooperative node discovery. In this paper, we employ prediction algorithm using two machine learning techniques i.e. ANN and SVM to find out inactive willing users within VAA cell. The parameters such as MSE, accuracy, precision and recall are calculated to evaluate performance of ANN and SVM model. Prediction using ANN has MSE of 3% with average accuracy of 97% (variance 0.37), whereas SVM has MSE of 2.58% with average accuracy of 97.56% (variance 0.17). We also observe that proposed prediction method reduces the node discovery time by approximately 29%.
Open AccessMachine Learning Based Cooperative Relay Selection in Virtual MIMO
In cellular systems, virtual multiple-input multiple-output (V-MIMO) technology promises to achieve performance gains comparable to conventional MIMO. In this paper, we propose cooperative relay selection algorithm based on machine learning techniques. Willingness of user to cooperate in V-MIMO depends on his current battery power, time and day along with incentives offered by service provider. Every user has different criterion to participate in V-MIMO, but allows a specific behavior pattern. Therefore, it is required to predict willing users in the neighborhood of source user (SU), before selecting users as cooperative nodes. Only inactive users belonging to Virtual Antenna Array (VAA) cell of SU are assumed to cooperate. This reduces control overheads in cooperative node discovery. In this paper, we employ prediction algorithm using two machine learning techniques i.e. ANN and SVM to find out inactive willing users within VAA cell. The parameters such as MSE, accuracy, precision and recall are calculated to evaluate performance of ANN and SVM model. Prediction using ANN has MSE of 3% with average accuracy of 97% (variance 0.37), whereas SVM has MSE of 2.58% with average accuracy of 97.56% (variance 0.17). We also observe that proposed prediction method reduces the node discovery time by approximately 29%.
- Open Access
Doubly Cognitive Architecture Based Cognitive Wireless Sensor Network
Nowadays scarcity of spectrum availability is increasing highly. Adding cognition to the existing Wireless Sensor Network (WSN) infrastructure will help in this situation. As sensor nodes in WSN are limited with some constrains like power, efforts are required to increase the lifetime and other performance measures of the network. In this paper we propose the idea of Doubly Cognitive WSN. The basic idea is to progressively allocate the sensing resources only to the most promising areas of the spectrum. This work is based on Artificial Neural Network as well as on Support Vector Machine (SVM) concept. As the load of sensing resource is reduced significantly, this approach will save the energy of the nodes, and also reduce the sensing time dramatically. The proposed work can be enhanced by doing the pattern analysis thing after a sufficiently long time again and again to review the strategy of sensing. Thus Doubly Cognitive WSN will enable current WSN to overcome the spectrum scarcity as well as save the energy of the sensor nodes.
Open AccessDoubly Cognitive Architecture Based Cognitive Wireless Sensor Network
Nowadays scarcity of spectrum availability is increasing highly. Adding cognition to the existing Wireless Sensor Network (WSN) infrastructure will help in this situation. As sensor nodes in WSN are limited with some constrains like power, efforts are required to increase the lifetime and other performance measures of the network. In this paper we propose the idea of Doubly Cognitive WSN. The basic idea is to progressively allocate the sensing resources only to the most promising areas of the spectrum. This work is based on Artificial Neural Network as well as on Support Vector Machine (SVM) concept. As the load of sensing resource is reduced significantly, this approach will save the energy of the nodes, and also reduce the sensing time dramatically. The proposed work can be enhanced by doing the pattern analysis thing after a sufficiently long time again and again to review the strategy of sensing. Thus Doubly Cognitive WSN will enable current WSN to overcome the spectrum scarcity as well as save the energy of the sensor nodes.