Author name cluster

Charalampos Chelmis

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAAI Conference 2025 Conference Paper

Predictive Modeling of Homeless Service Assignment: A Representation Learning Approach

Khandker Sadia Rahman
Charalampos Chelmis

In recent years, there has been growing interest in leveraging machine learning for homeless service assignment. However, the categorical nature of administrative data recorded for homeless individuals hinders the development of accurate machine learning methods for this task. This work asserts that deriving latent representations of such features, while at the same time leveraging underlying relationships between instances is crucial in algorithmically enhancing the existing assignment decision-making process. Our proposed approach learns temporal and functional relationships between services from historical data, as well as unobserved but relevant relationships between individuals to generate features that significantly improve the prediction of the next service assignment compared to the state-of-the-art.

PDF Details DOI

AAMAS Conference 2018 Conference Paper

FActCheck: Keeping Activation of Fake News at Check

Ajitesh Srivastava
Rajgopal Kannan
Charalampos Chelmis
Viktor K. Prasanna

The diffusion of fake news has become a crucial problem in recent years. One way to battle it is to propagate the corresponding real news. To achieve this goal, we find a set of individuals who are likely to receive the fake news so that they can test its credibility, and when they propagate the corresponding real news, it is likely to reach a large number of individuals. For this problem, we propose a polynomial time greedy algorithm (AFC) which provides (1 − 1/e −ϵ)-approximation. We further optimize the runtime of AFC by developing a fast graph-pruning heuristic (RAFC) that performs as well as AFC in checking the spread of fake news. Our experiments on real-world networks demonstrate that our approach outperforms popular methods in social network analysis literature.

PDF

IJCAI Conference 2016 Conference Paper

Implementation of Learning-Based Dynamic Demand Response on a Campus Micro-Grid

Sanmukh R. Kuppannagari
Rajgopal Kannan
Charalampos Chelmis
Viktor K. Prasanna

Demand Response (DR) allows utilities to curtail electricity consumption during peak demand periods. Real time automated DR can offer utilities a scalable solution for fine grained control of curtailment over small intervals for the duration of the entire DR event. In this work, we demonstrate a system for a real time automated Dynamic DR (D2R). Our system has already been integrated with the electrical infrastructure of the University of Southern California, which offers a unique environment to study the impact of automated DR in a complex social and cultural environment including 170 buildings in a city-within-a-city scenario. Our large scale information processing system coupled with accurate forecasting models for sparse data and fast polynomial time optimization algorithms for curtailment maximization provide the ability to adapt and respond to changing curtailment requirements in near real-time. Our D2 R algorithms automatically and dynamically select customers for load curtailment to guarantee the achievement of a curtailment target over a given DR interval.

PDF Details

IJCAI Conference 2016 Conference Paper

Thou Shalt ASQFor and Shalt Receive the Semantic Answer

Muhammad Rizwan Saeed
Charalampos Chelmis
Viktor K. Prasanna

The combination of data, semantics, and the Web has led to an ever growing and increasingly complex body of semantic data. Accessing such structured data requires learning formal query languages, such as SPARQL, which poses significant difficulties for non-expert users. Many existing interfaces for querying Ontologies are based on approaches that rely on predefined templates and require expensive customization. To avoid the pitfalls of existing approaches, while at the same time retaining the ability to capture users' complex information needs, we have developed a simple keyword-based search interface to the Semantic Web. In this demonstration, we will present ASQFor, a systematic framework for automated SPARQL query formulation and execution over RDF repository using simple concept-based search primitives. Allowing end-users to express simple queries based on a list of "key-value" pairs that are then translated on-the-fly into SPARQL queries is a hard problem. In this demonstration, we will discuss the challenges that we have addressed to bring ASQFor to real practice, and also the difficult problems that remain to be solved in future work. During our demonstration, we will show how ASQFor can be used for decision support as well as an intelligent Q/A System.

PDF Details

AAAI Conference 2015 Conference Paper

Influence-Driven Model for Time Series Prediction from Partial Observations

Saima Aman
Charalampos Chelmis
Viktor Prasanna

Applications in sustainability domains such as in energy, transportation, and natural resource and environment monitoring, increasingly use sensors for collecting data and sending it back to centrally located processing nodes. While data can usually be collected by the sensors at a very high speed, in many cases, it can not be sent back to central nodes at a frequency that is required for fast and real-time modeling and decisionmaking. This may be due to physical limitations of the transmission networks, or due to consumers limiting frequent transmission of data from sensors located at their premises for security and privacy concerns. We propose a novel solution to the problem of making short term predictions in absence of real-time data from sensors. A key implication of our work is that by using real-time data from only a small subset of influential sensors, we are able to make predictions for all sensors. We evaluated our approach with a large real-world electricity consumption data collected from smart meters in Los Angeles and the results show that between prediction horizons of 2 to 8 hours, despite lack of real time data, our influence model outperforms the baseline model that uses real-time data. Also, when using partial real-time data from only ≈ 7% influential smart meters, we witness prediction error increase by only ≈ 0. 5% over the baseline, thus demonstrating the usefulness of our method for practical scenarios.

PDF Details