Loganathan Ponnambalam

RiskVis: Supply chain visualization with risk management and real-time monitoring

With increased complexity, supply chain networks (SCNs) of modern era face higher risks and lower efficiency due to limited visibility. Hence, there is an immediate need to provide end-to-end supply chain visibility for efficient management of complex supply chains. This paper proposes a visualization scheme based on multi-hierarchical modular design and develops a supply chain visualization platform with risk management and real-time monitoring, named RiskVis, for realizing better Supply Chain Risk Management (SCRM). A Supply Chain Visualizer (SCV) with a graphical visualization platform is mounted as a part of a SCRM management decision-making dashboard and it provides senior management a clearer view of supply chain operations in a local/regional/global setting. The platform not only displays spatio-temporal connectivity patterns of entities in a supply chain; it also accommodates real-time risk-related data collection and risk monitoring. The proposed platform offers the flexibility to be customized based on the users requirements - to process and store the supply chain data in the server, visualize the supply chain data, network map, risk alert, and other information needed for SCRM. Supply chain decision makers can deploy it on the desktop or embed it into the companys enterprise applications in a front office environment for better managing risks of their supply chains.

Maritime Traffic Probabilistic Forecasting Based on Vessels’ Waterway Patterns and Motion Behaviors

Maritime traffic prediction is critical for ocean transportation safety management. In this paper, we propose a novel knowledge assisted methodology for maritime traffic forecasting based on a vessel’s waterway pattern and motion behavior. The vessel’s waterway pattern is extracted through a proposed lattice-based DBSCAN algorithm that significantly reduces the problem scale, and its motion behavior is quantitatively modeled for the first time using kernel density estimation. The proposed methodology facilitates the knowledge extraction, storage, and retrieval, allowing for seamless knowledge transfer to support maritime traffic forecasting. By incorporating both the vessel’s waterway pattern and motion behavior knowledge, our solution suggests a set of probable coordinates with the corresponding probability as the forecasting output. The proposed forecasting algorithm is capable of accurately predicting maritime traffic 5, 30, and 60 min ahead, while its computation can be efficiently completed in milliseconds for single vessel prediction. Owing to such a high computational efficiency, an extensive predictive analysis of hundreds of vessels has been reported for the first time in this paper. A web-based prototype platform is implemented for Singapore waters to demonstrate the solution’s feasibility in a real-world maritime operation system. The proposed approaches can be generalized for other marine waters around the world.

An agent-based network analytic perspective on the evolution of complex adaptive supply chain networks

Supply chain networks of modern era are complex adaptive systems that are dynamic and highly interdependent in nature. Business continuity of these complex systems depend vastly on understanding as to how the supply chain network evolves over time (based on the policies it adapts), and identifying the susceptibility of the evolved networks to external disruptions. The objective of this article is to illustrate as to how an agent-based network analytic perspective can aid this understanding on the network-evolution dynamics, and identification of disruption effects on the evolved networks. To this end, we developed a 4-tier agent based supply chain model and simulated the evolution of the supply chain network based on two different partner selection scenarios. Network-evolution diagrams, change in structural characteristics over time and effect of disruptions on the critical nodes for the two different partner selection scenarios are presented. The networkevolution characteristics (social network analysis based node/network level metrics) over time have been quantified and the vulnerability of the evolved networks, due to disruptions that result in reduction in production of the networks critical producer node, has been identified.

Predicting Maritime Groundings Using Support Vector Data Description Model

This paper focuses on grounding prediction related to sea vessels. Grounding accidents are one of the most common causes for ship disasters. Hence, there is a growing need to assess and analyze probabilities as well as related consequences of ship running aground. Using a real world marine incident dataset obtained from the United States Coast Guard National Response Center, we have demonstrated that Support Vector Data Description based methods can be successfully used for grounding prediction. After preprocessing the raw data, a total of 15165 incidents were obtained out of which there were 291 cases of ship running aground and was used in our study. A prediction accuracy of 98.25 % was achieved using the Lightly Trained Support Vector Data Description.

A Study on Relationship between Modularity and Diffusion Dynamics in Networks from Spectral Analysis Perspective

Modular structure is a typical structure that is observed in most of real networks. Diffusion dynamics in network is getting much attention because of dramatic increasing of the data flows via the www. The diffusion dynamics in network have been well analysed as probabilistic process, but the proposed frameworks still shows the difference from the real observations. In this paper, we analysed spectral properties of the networks and diffusion dynamics. Especially, we focus on studying the relationship between modularity and diffusion dynamics. Our analysis as well as simulation results show that the relative influences from the non-largest eigenvalues and the corresponding eigenvectors increase when modularity of network increases. These results have the implication that, although network dynamics have been often analysed with the approximation manner utilizing only the largest eigenvalue, the consideration of the other eigenvalues is necessary for the analysis of the network dynamics on real networks. We also investigated Node-level Eigenvalue Influence Index (NEII) which can quantify the relative influence from each eigenvalues on each node. This investigation indicates that the influence from each eigenvalue is confined within the modular structures in the network. These findings should be made consideration by researchers interested in diffusion dynamics analysis on real networks for deeper analysis.

Social media for supply chain risk management

With the rapid increase of online social network users worldwide, social media feeds have become a rich and valuable information resource and attract great attention across diversified domains. In social media data, there are abundant contents of two-way and interactive communication about products, demand, customer services and supply. This makes social media a valuable channel for listening to the voices from the market and measuring supply chain risks and new market trends for companies. In this study, we surveyed the potential value of social media in supply chain risk management (SCRM) and examined how they can be applied to SCRM systematically. We found that while such medium is very useful in supply chain risk management, it also brings along a new risk to supply chains, so called social media risk, as supply chain incidents may be rapidly transmitted and magnified through social media platforms worldwide. Accordingly, a new framework is proposed that assists the hiring of social media to serve supply chain risk management tasks.

Decision trees to model the impact of disruption and recovery in supply chain networks

Increase in the frequency of disruptions in the recent times and their impact have increased the attention in supply chain disruption management research. The objective of this paper is to understand as to how a disruption might affect the supply chain network - depending upon the network structure, the node that is disrupted, the disruption in production capacity of the disrupted node and the period of the disruption - via decision trees. To this end, we first developed a 5-tier agent-based supply chain model and then simulated it for various what-if disruptive scenarios for 3 different network structures (80 trials for each network). Decision trees were then developed to model the impact due to varying degrees of disruption, and the recovery time from these disruptions. Visual outputs of the developed decision trees are presented to better interpret the rules. Supply chain managers can use the approach presented in this work to generate rules that can aid their mitigation planning during future disruptions.

GIS based modeling of marine incident hotspots: A cloud-based framework for navigational alerts

Spatio-temporal modeling of historical marine incidents to identify the hotspots can aid scenario planning to strategize safer navigation in the region of interest. However, applications of GIS based approaches for spatio-temporal modeling to identify the hotspots and utilizing these results to plan a safer navigation through a cloud-based framework is a rarity in the literature. The proposed approach has been illustrated using the realistic data of marine incidents that occurred in the US waters from 2006-2015. The incident of interest in the study is allision and QGIS was used for the spatio-temporal modeling. The heatmap and hotspots for allision incidents that occurred within the last five years and ten years are presented. The vectors generated from the hotspots contain the information on the incident-prone zones in the US waters. This information was then used as the basis in the proposed cloud-based framework to upload the AIS data and identify the alert-zones in the navigational path.

A multi-agent model for adaptive vaccination during infectious disease outbreaks

Infectious disease outbreaks are a huge burden on healthcare, causing hospitalizations, deaths and rigorously impairing the economy. In this work, an age-structured multi-agent model has been developed to simulate an epidemic spread among the US population and strategize adaptive vaccination planning to control the spread. The population was split into six distinct groups of agents depending upo on their age. In addition, the calibration of the multi-agent model parameters for H1N1 2009 pandemic, validation of the model using H1N1 2009 pandemic data from Centers for Disease Control and Prevention (CDC, US) was carried out. Using these data, the model was calibrated such that the H1N1 deaths predicted by the model was comparable to that of the deaths reported by CDC, while the H1N1 hospitalizations predicted were within the 95% confidence interval. A series of hypothetical simulations of a H1N1 like pandemic outbreak among the US population to illustrate the effectiveness of various adaptive strategies proposed in the literature will be presented. Each set of simulation was replicated 100 times so as to average the stochastic effects of parameter(s) uncertainty. The multi-agent model developed in this work can be used as a decision support system to systematically gauge the effectiveness of various interventions so as to aid healthcare policy makers to design dynamic, optimal health interventions to counter disease outbreaks.

An Agent-Based Model for Intervention Planning Among Communities During Epidemic Outbreaks

We developed an agent-based model containing 50 communities, replicating the 50 states of USA. The age distribution, approximate household size and the socio-structural determinants of each community were modeled based on the US Census. The agent-based model was validated using in-silico seroprevalence data collection. Medical seeking behavior of individuals was parameterized based on the socio-structural determinants of the community. The interventions proposed in literature were tested and the optimal intervention strategy to counter an epidemic outbreak has been identified. In addition, we included novel interventions like coordination among the communities and increasing the awareness of individuals in the lower ranked communities based on information exchange between communities.