Publications
Influence estimation on social media networks using causal inference
June 11, 2018
Conference Paper
Published in:
Proc. IEEE Statistical Signal Processing (SSP) Workshop, 10-13 June 2018.
Summary
Estimating influence on social media networks is an important practical and theoretical problem, especially because this new medium is widely exploited as a platform for disinformation and propaganda. This paper introduces a novel approach to influence estimation on social media networks and applies it to the real-world problem of characterizing active influence operations on Twitter during the 2017 French presidential elections. The new influence estimation approach attributes impact by accounting for narrative propagation over the network using a network causal inference framework applied to data arising from graph sampling and filtering. This causal framework infers the difference in outcome as a function of exposure, in contrast to existing approaches that attribute impact to activity volume or topological features, which do not explicitly measure nor necessarily indicate actual network influence. Cramér-Rao estimation bounds are derived for parameter estimation as a step in the causal analysis, and used to achieve geometrical insight on the causal inference problem. The ability to infer high causal influence is demonstrated on real-world social media accounts that are later independently confirmed to be either directly affiliated or correlated with foreign influence operations using evidence supplied by the U.S. Congress and journalistic reports.
Summary
Estimating influence on social media networks is an important practical and theoretical problem, especially because this new medium is widely exploited as a platform for disinformation and propaganda. This paper introduces a novel approach to influence estimation on social media networks and applies it to the real-world problem of characterizing...
READ MORE
Multi-layered interactive energy space modeling for near-optimal electrification of terrestrial, shipboard and aircraft systems
April 22, 2018
Journal Article
Published in:
Annual Reviews in Control, no. 45, 2018, pp. 52-75.
Summary
In this paper, we introduce a basic multi-layered modeling framework for posing the problem of safe, robust and efficient design and control that may lend itself to ripping potential benefits from electrification. The proposed framework establishes dynamic relations between physical concepts such as stored energy, useful work, and wasted energy, on one hand; and modeling, simulation, and control of interactive modular complex dynamical systems, on the other. In particular, our recently introduced energy state-space modeling approach for electric energy systems is further interpreted using fundamental laws of physics in multi-physical systems, such as terrestrial energy-systems, aircrafts and ships. The interconnected systems are modeled as dynamically interacting modules. This approach is shown to be particularly well-suited for scalable optimization of large-scale complex systems. Instead of having to use simpler models, the proposed multi-layered modeling of system dynamics in energy space offers a promising basic method for modeling and controlling inter-dependencies across multi-physics subsystems for both ensuring feasible and near-optimal operation. It is illustrated how this approach can be used for understanding fundamental physical causes of inefficiencies created either at the component level or are a result of poor matching of their interactions.
Summary
In this paper, we introduce a basic multi-layered modeling framework for posing the problem of safe, robust and efficient design and control that may lend itself to ripping potential benefits from electrification. The proposed framework establishes dynamic relations between physical concepts such as stored energy, useful work, and wasted energy...
READ MORE
Hybrid mixed-membership blockmodel for inference on realistic network interactions
April 5, 2018
Journal Article
Published in:
IEEE Trans. Netw. Sci. Eng., Vol. 6, No. 3, July-Sept. 2019.
Summary
This work proposes novel hybrid mixed-membership blockmodels (HMMB) that integrate three canonical network models to capture the characteristics of real-world interactions: community structure with mixed-membership, power-law-distributed node degrees, and sparsity. This hybrid model provides the capacity needed for realism, enabling control and inference on individual attributes of interest such as mixed-membership and popularity. A rigorous inference procedure is developed for estimating the parameters of this model through iterative Bayesian updates, with targeted initialization to improve identifiability. For the estimation of mixed-membership parameters, the Cramer-Rao bound is derived by quantifying the information content in terms of the Fisher information matrix. The effectiveness of the proposed inference is demonstrated in simulations where the estimates achieve covariances close to the Cramer-Rao bound while maintaining good truth coverage. We illustrate the utility of the proposed model and inference procedure in the application of detecting a community from a few cue nodes, where success depends on accurately estimating the mixed-memberships. Performance evaluations on both simulated and real-world data show that inference with HMMB is able to recover mixed-memberships in the presence of challenging community overlap, leading to significantly improved detection performance over algorithms based on network modularity and simpler models.
Summary
This work proposes novel hybrid mixed-membership blockmodels (HMMB) that integrate three canonical network models to capture the characteristics of real-world interactions: community structure with mixed-membership, power-law-distributed node degrees, and sparsity. This hybrid model provides the capacity needed for realism, enabling control and inference on individual attributes of interest such as...
READ MORE
Machine learning for medical ultrasound: status, methods, and future opportunities
February 28, 2018
Journal Article
Published in:
Abdom. Radiol., 2018, doi: 10.1007/s00261-018-1517-0.
Topic:
R&D area:
Summary
Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant challenges and opportunities. Challenges include high inter- and intra-operator variability and limited image quality control. Tremendous opportunities have arisen in the last decade as a result of exponential growth in available computational power coupled with progressive miniaturization of US devices. As US devices become smaller, enhanced computational capability can contribute significantly to decreasing variability through advanced image processing. In this paper, we review leading machine learning (ML) approaches and research directions in US, with an emphasis on recent ML advances. We also present our outlook on future opportunities for ML techniques to further improve clinical workflow and US-based disease diagnosis and characterization.
Summary
Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant challenges and opportunities. Challenges include high inter- and intra-operator variability and limited...
READ MORE
Trust and performance in human-AI systems for multi-domain command and control
January 14, 2018
Project Report
Published in:
MIT Lincoln Laboratory Report 116777
Summary
Command and Control is one of the core tenants of joint military operations, however, the nature of modern security threats, the democratization of technology globally, and the speed and scope of information flows are stressing traditional operational paradigms, necessitating a fundamental shift to better concurrently integrate and operate across multiple physical and virtual domains. In this paper, we aim to address these challenges through the proposition of three concepts that will guide the creation of integrated human-AI Command and Control systems, inspired by recent advances and successes within the commercial sector and academia. The first concept is a framework for integration of AI capabilities into the enterprise that optimizes trust and performance within the workforce. The second is an approach for facilitating multi-domain operations though realtime creation of multi-organization multi-domain task teams by dynamic management of information abstraction, teaming, and risk control. The third is a new paradigm for multi-level data security and multi-organization data sharing that will be a key enabler of joint and coalition multi-domain operation in the future. Lastly, we propose a set of recommendations towards the research, development, and instantiation of these transformative advances in Command and Control capability.
Summary
Command and Control is one of the core tenants of joint military operations, however, the nature of modern security threats, the democratization of technology globally, and the speed and scope of information flows are stressing traditional operational paradigms, necessitating a fundamental shift to better concurrently integrate and operate across multiple...
READ MORE
XLab: early indications & warning from open source data with application to biological threat
January 3, 2018
Conference Paper
Published in:
Proc. 51st Hawaii Int. Conf. on System Sciences, HICSS 2018, pp. 944-953.
Summary
XLab is an early warning system that addresses a broad range of national security threats using a flexible, rapidly reconfigurable architecture. XLab enables intelligence analysts to visualize, explore, and query a knowledge base constructed from multiple data sources, guided by subject matter expertise codified in threat model graphs. This paper describes a novel system prototype that addresses threats arising from biological weapons of mass destruction. The prototype applies knowledge extraction analytics—including link estimation, entity disambiguation, and event detection—to build a knowledge base of 40 million entities and 140 million relationships from open sources. Exact and inexact subgraph matching analytics enable analysts to search the knowledge base for instances of modeled threats. The paper introduces new methods for inexact matching that accommodate threat models with temporal and geospatial patterns. System performance is demonstrated using several simplified threat models and an embedded scenario.
Summary
XLab is an early warning system that addresses a broad range of national security threats using a flexible, rapidly reconfigurable architecture. XLab enables intelligence analysts to visualize, explore, and query a knowledge base constructed from multiple data sources, guided by subject matter expertise codified in threat model graphs. This paper...
READ MORE
Potential impacts of climate warming and increased summer heat stress on the electric grid: a case study for a large power transformer (LPT) in the Northeast United States
November 20, 2017
Journal Article
Published in:
Climatic Change, 20 November 2017, https://doi-org.ezproxyberklee.flo.org/10.1007/s10584-017-2114-x
Summary
Large power transformers (LPTs) are critical yet vulnerable components of the power grid. More frequent and intense heat waves or high temperatures can degrade their operational lifetime and increase the risk of premature failure. Without adequate preparedness, a widespread situation could ultimately lead to prolonged grid disruption and incur excessive economic costs. Here, we investigate the potential impact of climate warming and corresponding shifts in summertime "hot days" on a selected LPT located in the Northeast United States. We apply an analogue method, which detects the occurrence of hot days based on the salient, associated large-scale atmospheric conditions, to assess the risk of future change in their occurrence. Compared with the more conventional approach that relies on climate model simulated daily maximum temperature, the analogue method produces model medians of late twentieth century hot day frequency that are more consistent with observation and have stronger inter-model consensus. Under the climate warming scenarios, multi-model medians of both model daily maximum temperature and the analogue method indicate strong decadal increases in hot day frequency by the late twenty-first century, but the analogue method improves model consensus considerably. The decrease of transformer lifetime with temperature increase is further assessed. The improved inter-model consensus of the analogue method is viewed as a promising step toward providing actionable information for a more stable, reliable, and environmentally responsible national grid.
Summary
Large power transformers (LPTs) are critical yet vulnerable components of the power grid. More frequent and intense heat waves or high temperatures can degrade their operational lifetime and increase the risk of premature failure. Without adequate preparedness, a widespread situation could ultimately lead to prolonged grid disruption and incur excessive...
READ MORE
Cloud computing in tactical environments
October 23, 2017
Conference Paper
Published in:
MILCOM 2017, 23-25 October 2017.
Topic:
Summary
Ground personnel at the tactical edge often lack data and analytics that would increase their effectiveness. To address this problem, this work investigates methods to deploy cloud computing capabilities in tactical environments. Our approach is to identify representative applications and to design a system that spans the software/hardware stack to support such applications while optimizing the use of scarce resources. This paper presents our high-level design and the results of initial experiments that indicate the validity of our approach.
Summary
Ground personnel at the tactical edge often lack data and analytics that would increase their effectiveness. To address this problem, this work investigates methods to deploy cloud computing capabilities in tactical environments. Our approach is to identify representative applications and to design a system that spans the software/hardware stack to...
READ MORE
Lessons learned from hardware-in-the-loop testing of microgrid control systems
October 22, 2017
Conference Paper
Published in:
CIGRE 2017 Grid of the Future Symp., 22-25 Oct. 2017.
Summary
A key ingredient for the successful completion of any complex microgrid project is real-time controller hardware-in-the-loop (C-HIL) testing. C-HIL testing allows engineers to test the system and its controls before it is deployed in the field. C-HIL testing also allows for the simulation of test scenarios that are too risky or even impossible to test in the field. The results of C-HIL testing provide the necessary proof of concept and insight into any microgrid system limitations. This type of testing can also be used to create awareness among potential microgrid customers. This paper describes the modeling benefits, challenges, and lessons learned associated with C-HIL testing. The microgrid system used in this study has a 3 MW battery, 5 MW photovoltaic (PV) array, 4 MW diesel generator set (genset), and 3.5 MW combined heat and power generation system (CHP).
Summary
A key ingredient for the successful completion of any complex microgrid project is real-time controller hardware-in-the-loop (C-HIL) testing. C-HIL testing allows engineers to test the system and its controls before it is deployed in the field. C-HIL testing also allows for the simulation of test scenarios that are too risky...
READ MORE
Super-resolution community detection for layer-aggregated multilayer networks
September 26, 2017
Journal Article
Published in:
Phys. Rev. X, Vol. 7, No. 3, July-September 2017, 031056.
Summary
Applied network science often involves preprocessing network data before applying a network-analysis method, and there is typically a theoretical disconnect between these steps. For example, it is common to aggregate time-varying network data into windows prior to analysis, and the trade-offs of this preprocessing are not well understood. Focusing on the problem of detecting small communities in multilayer networks, we study the effects of layer aggregation by developing random-matrix theory for modularity matrices associated with layer-aggregated networks with N nodes and L layers, which are drawn from an ensemble of Erdős–Rényi networks with communities planted in subsets of layers. We study phase transitions in which eigenvectors localize onto communities (allowing their detection) and which occur for a given community provided its size surpasses a detectability limit K*. When layers are aggregated via a summation, we obtain K* is proportional to O(square root of NL/T), where T is the number of layers across which the community persists. Interestingly, if T is allowed to vary with L, then summation-based layer aggregation enhances small-community detection even if the community persists across a vanishing fraction of layers, provided that T=L decays more slowly than O(L^−1/2). Moreover, we find that thresholding the summation can, in some cases, cause K* to decay exponentially, decreasing by orders of magnitude in a phenomenon we call super-resolution community detection. In other words, layer aggregation with thresholding is a nonlinear data filter enabling detection of communities that are otherwise too small to detect. Importantly, different thresholds generally enhance the detectability of communities having different properties, illustrating that community detection can be obscured if one analyzes network data using a single threshold.
Summary
Applied network science often involves preprocessing network data before applying a network-analysis method, and there is typically a theoretical disconnect between these steps. For example, it is common to aggregate time-varying network data into windows prior to analysis, and the trade-offs of this preprocessing are not well understood. Focusing on...
READ MORE