The Experts below are selected from a list of 65844 Experts worldwide ranked by ideXlab platform
Nashwan Dawood - One of the best experts on this subject based on the ideXlab platform.
-
estimating project and activity duration a risk management approach using Network analysis
Construction Management and Economics, 1998Co-Authors: Nashwan DawoodAbstract:Variations in the durations of activities are commonplace in the construction industry. This is due to the fact that the construction industry is influenced greatly by variations in weather, productivity of labour and plant, and quality of materials. Stochastic Network analysis has been used by previous researchers to model variations in activities and produce more effective and reliable project duration estimates. A number of techniques have been developed in previous literature to solve the uncertain nature of Networks, these are: PERT (program evaluation and review techniques), PNET (Probabilistic Network evaluation technique), NRB, (narrow reliability bounds methods) and MCS (Monte Carlo simulation). Although these techniques have proved to be useful in modelling variations in activities, dependence of activity duration is not considered. This can have a severe impact on realistically modelling projects. In this context, the objective of the present research is to develop a methodology that can accurately model activity dependence and realistically predict project duration using a risk management approach. A simulation model has been developed to encapsulate the methodology and run experimental work. In order to achieve this, the following tasks are tackled: identify risk factors that cause activity variations using literature reviews and conducting interviews with contractors; model risk factors and their influence on activity variations through conducting case studies and identifying any dependence between them; develop a computer based simulation model that uses a modified Monte Carlo technique to model activity duration and dependence of risk factors; and run experimental work to validate and verify the model.
-
estimating project and activity duration a risk management approach using Network analysis
Construction Management and Economics, 1998Co-Authors: Nashwan DawoodAbstract:Variations in the durations of activities are commonplace in the construction industry. This is due to the fact that the construction industry is influenced greatly by variations in weather, productivity of labour and plant, and quality of materials. Stochastic Network analysis has been used by previous researchers to model variations in activities and produce more effective and reliable project duration estimates. A number of techniques have been developed in previous literature to solve the uncertain nature of Networks, these are: PERT (program evaluation and review techniques), PNET (Probabilistic Network evaluation technique), NRB, (narrow reliability bounds methods) and MCS (Monte Carlo simulation). Although these techniques have proved to be useful in modelling variations in activities, dependence of activity duration is not considered. This can have a severe impact on realistically modelling projects. In this context, the objective of the present research is to develop a methodology that can accura...
Sham M Kakade - One of the best experts on this subject based on the ideXlab platform.
-
a tensor approach to learning mixed membership community models
Journal of Machine Learning Research, 2014Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced by Airoldi et al. (2008). This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning these models via a tensor spectral decomposition method. Our estimator is based on low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is fast and is based on simple linear algebraic operations, e.g., singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters and present a careful finite sample analysis of our learning method. As an important special case, our results match the best known scaling requirements for the (homogeneous) stochastic block model.
-
a tensor spectral approach to learning mixed membership community models
Conference on Learning Theory, 2013Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Detecting hidden communities from observed interactions is a classical problem. Theoretical analysis of community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced in Airoldi et al. (2008). This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning communities in these models via a tensor spectral decomposition approach. Our estimator uses low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is based on simple linear algebraic operations such as singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters, and present a careful finite sample analysis of our learning method. Additionally, our results match the best known scaling requirements for the special case of the (homogeneous) stochastic block model.
-
a tensor spectral approach to learning mixed membership community models
2013Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced by Airoldi et al. This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning these models via a tensor spectral decomposition method. Our estimator is based on low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is fast and is based on simple linear algebraic operations, e.g. singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters and present a careful finite sample analysis of our learning method. As an important special case, our results match the best known scaling requirements for the (homogeneous) stochastic block model.
Anima Anandkumar - One of the best experts on this subject based on the ideXlab platform.
-
a tensor approach to learning mixed membership community models
Journal of Machine Learning Research, 2014Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced by Airoldi et al. (2008). This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning these models via a tensor spectral decomposition method. Our estimator is based on low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is fast and is based on simple linear algebraic operations, e.g., singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters and present a careful finite sample analysis of our learning method. As an important special case, our results match the best known scaling requirements for the (homogeneous) stochastic block model.
-
a tensor spectral approach to learning mixed membership community models
Conference on Learning Theory, 2013Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Detecting hidden communities from observed interactions is a classical problem. Theoretical analysis of community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced in Airoldi et al. (2008). This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning communities in these models via a tensor spectral decomposition approach. Our estimator uses low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is based on simple linear algebraic operations such as singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters, and present a careful finite sample analysis of our learning method. Additionally, our results match the best known scaling requirements for the special case of the (homogeneous) stochastic block model.
-
a tensor spectral approach to learning mixed membership community models
2013Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced by Airoldi et al. This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning these models via a tensor spectral decomposition method. Our estimator is based on low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is fast and is based on simple linear algebraic operations, e.g. singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters and present a careful finite sample analysis of our learning method. As an important special case, our results match the best known scaling requirements for the (homogeneous) stochastic block model.
Zhipeng Cai - One of the best experts on this subject based on the ideXlab platform.
-
A Genetic Algorithm for Constructing a Reliable MCDS
2016Co-Authors: Zhipeng Cai, Raheem Beyah, Yi PanAbstract:Abstract. Minimum Connected Dominating Sets (MCDSs) are used as virtual backbones for efficient routing and broadcasting in wireless net-works extensively. However, the MCDS problem is NP-Complete even in Unit Disk Graphs. Therefore, many heuristic-based approximation algo-rithms have been proposed recently. In these approaches, Networks are deterministic where two nodes are assumed either connected or discon-nected. In most real applications, however, there are many intermittently connected wireless links called lossy links, which only provide proba-bilistic connectivity. For wireless Networks with lossy links, we propose a Probabilistic Network Model (PNM). Under this model, we measure the quality of Connected Dominating Sets (CDSs) using CDS reliabil-ity defined as the minimum upper limit of the node-to-node delivery ratio between any pair of dominators in a CDS. We attempt to con-struct a MCDS while its reliability is above a preset application-specified threshold, called Reliable MCDS (RMCDS). We claim that constructing a RMCDS is NP-Hard under the PNM model. We propose a novel Ge-netic Algorithm (GA) called RMCDS-GA to solve the RMCDS problem. To evaluate the performance of RMCDS-GA, we conduct comprehensive simulations. The simulation results show that compared with the tra-ditional MCDS algorithms, RMCDS-GA can construct a more reliable CDS without increasing the size of a CDS.
-
snapshot and continuous data collection in Probabilistic wireless sensor Networks
IEEE Transactions on Mobile Computing, 2014Co-Authors: Raheem Beyah, Zhipeng CaiAbstract:Data collection is a common operation of Wireless Sensor Networks (WSNs), of which the performance can be measured by its achievable Network capacity. Most existing works studying the Network capacity issue are based on the unpractical model called deterministic Network model. In this paper, a more reasonable model, Probabilistic Network model, is considered. For snapshot data collection, we propose a novel Cell-based Path Scheduling (CPS) algorithm that achieves capacity of Ω(1/ 5ω ln n·W) in the sense of the worst case and order-optimal capacity in the sense of expectation, where n is the number of sensor nodes, ω is a constant, and W is the data transmitting rate. For continuous data collection, we propose a Zone-based Pipeline Scheduling (ZPS) algorithm. ZPS significantly speeds up the continuous data collection process by forming a data transmission pipeline, and achieves a capacity gain of N√n/√(log n) ln n or n/log n ln n times better than the optimal capacity of the snapshot data collection scenario in order in the sense of the worst case, where N is the number of snapshots in a continuous data collection task. The simulation results also validate that the proposed algorithms significantly improve Network capacity compared with the existing works.
Daniel Hsu - One of the best experts on this subject based on the ideXlab platform.
-
a tensor approach to learning mixed membership community models
Journal of Machine Learning Research, 2014Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced by Airoldi et al. (2008). This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning these models via a tensor spectral decomposition method. Our estimator is based on low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is fast and is based on simple linear algebraic operations, e.g., singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters and present a careful finite sample analysis of our learning method. As an important special case, our results match the best known scaling requirements for the (homogeneous) stochastic block model.
-
a tensor spectral approach to learning mixed membership community models
Conference on Learning Theory, 2013Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Detecting hidden communities from observed interactions is a classical problem. Theoretical analysis of community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced in Airoldi et al. (2008). This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning communities in these models via a tensor spectral decomposition approach. Our estimator uses low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is based on simple linear algebraic operations such as singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters, and present a careful finite sample analysis of our learning method. Additionally, our results match the best known scaling requirements for the special case of the (homogeneous) stochastic block model.
-
a tensor spectral approach to learning mixed membership community models
2013Co-Authors: Anima Anandkumar, Daniel Hsu, Sham M KakadeAbstract:Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection for a family of Probabilistic Network models with overlapping communities, termed as the mixed membership Dirichlet model, first introduced by Airoldi et al. This model allows for nodes to have fractional memberships in multiple communities and assumes that the community memberships are drawn from a Dirichlet distribution. Moreover, it contains the stochastic block model as a special case. We propose a unified approach to learning these models via a tensor spectral decomposition method. Our estimator is based on low-order moment tensor of the observed Network, consisting of 3-star counts. Our learning method is fast and is based on simple linear algebraic operations, e.g. singular value decomposition and tensor power iterations. We provide guaranteed recovery of community memberships and model parameters and present a careful finite sample analysis of our learning method. As an important special case, our results match the best known scaling requirements for the (homogeneous) stochastic block model.