Indian Institute of Management Calcutta

About: Indian Institute of Management Calcutta is a education organization based out in Kolkata, India. It is known for research contribution in the topics: Supply chain & Emerging markets. The organization has 415 authors who have published 1354 publications receiving 21725 citations. The organization is also known as: IIMC & IIM Calcutta.

An Empirical Investigation of Collaborative Conflict Management Style in Group Support System-Based Global Virtual Teams

Abstract: Virtual teams cut across national, organizational, and functional boundaries, often resulting in diversity in team composition. This paper presents the results of a laboratory study involving groupware-supported, culturally homogeneous, and heterogeneous virtual teams where collaborative conflict management style, a team's cultural orientation as measured by the degree of individualism-collectivism, and group diversity affect several group performance variables. Collaborative conflict management style was positively related to performance, group diversity was found to have a moderating influence between collaborative style and group performance, and collaborative style was influenced by the individualistic-collectivistic orientations. Consistent with prior research, we found that collectivistic orientations help enhance the level of collaborative conflict management style prevailing in teams. Our research also indicates that the process to motivate team members may differ depending on their orientation.

A network-aware MAC and routing protocol for effective load balancing in ad hoc wireless networks with directional antenna

Abstract: Use of directional antenna in the context of ad hoc wireless networks can largely reduce radio interference, thereby improving the utilization of wireless medium. Our major contribution in this paper is to devise a routing strategy, along with a MAC protocol, that exploits the advantages of directional antenna in ad hoc networks for improved system performance. In this paper, we have illustrated a MAC and routing protocol for ad hoc networks using directional antenna with the objective of effective load balancing through the selection of maximally zone disjoint routes. Zone-disjoint routes would minimize the effect of route coupling by selecting routes in such a manner that data communication over one route will minimally interfere with data communication over the others. In our MAC protocol, each node keeps certain neighborhood status information dynamically in order that each node is aware of its neighborhood and communications going on in its neighborhood at that instant of time. This status information from each node is propagated periodically throughout the network. This would help each node to capture the approximate network status periodically that helps each node to become topology-aware and aware of communications going on in the network, although in an approximate manner. With this status information, each intermediate node adaptively computes routes towards destination. The performance of the proposed framework has been evaluated on QualNet Network Simulator with DSR (as in QualNet) as a benchmark. Our proposed mechanism shows four to five times performance improvement over DSR, thus demonstrating the effectiveness of this proposal.

Preprocessing unbalanced data using support vector machine

Abstract: This paper deals with the application of support vector machine (SVM) to deal with the class imbalance problem. The objective of this paper is to examine the feasibility and efficiency of SVM as a preprocessor. Our study analyzes different classification algorithms that are employed to predict the customers with caravan car policy based on his/her sociodemographic data and history of product ownership. A series of experiments was conducted to test various computational intelligence techniques viz., Multilayer Perceptron (MLP), Logistic Regression (LR), and Random Forest (RF). Various standard balancing techniques such as under-sampling, over-sampling and Synthetic Minority Over-sampling TEchnique (SMOTE) are also employed. Subsequently, a strategy of data balancing for handling imbalanced distribution in data is proposed. The proposed approach first employs SVM as a preprocessor and the actual target values of training data are then replaced by the predictions of trained SVM. Later, this modified training data is used to train techniques such as MLP, LR, and RF. Based on the measure of sensitivity, it is observed that the proposed approach not only balances the data effectively but also provides more number of instances for minority class, which in turn enhances the performance of the intelligence techniques. Highlights?Support vector machine (SVM) acts as a preprocessor for unbalanced data. ?SVM generates extra data related to minority class. ?The modified training data is used to train multiple classification techniques. ?The hybrid approach performs well in terms of sensitivity.