Charalampos Chelmis

Social Networking Analysis: A State of the Art and the Effect of Semantics

This paper presents a comprehensive study of the state of the art in Social Networking Analysis and examines the impact of content analysis and the effects of semantics in social networking analysis research. We propose a taxonomy of current approaches, classifying them into the following main categories: 1) graph-theoretic approaches, 2) applications of semantic web technologies and emergent semantics modelling, and 3) data mining and analytics. The purpose is to increase awareness of the social networking analysis community about different ongoing efforts, which not only focus on the network aspect of social networks, shed some light into different approaches and advance the discussion about potential future directions.

Accurate and efficient selection of the best consumption prediction method in smart grids

Smart grids are becoming popular with the advent of sophisticated smart meters. They allow utilities to optimize energy consumption during peak hours by applying various demand response techniques including voluntary curtailment, direct control and price incentives. To sustain the curtailment over long periods of time of up to several hours utilities need to make fast and accurate consumption predictions on a large set of customers based on a continuous flow of real time data and huge historical data sets. Given the numerous consumption patterns customers exhibit, different prediction methods need to be used to reduce the prediction error. The straightforward approach of testing each customer against every method is unfeasible in this large volume and high velocity environment. To this aim, we propose a neural network based approach for automatically selecting the best prediction method per customer by relying only on a small subset of customers. We also introduce two historical averaging methods for consumption prediction that take advantage of the variability of the data and continuously update the results based on a sliding window technique. We show that once trained, the proposed neural network does not require frequent retraining, ensuring its applicability in online scenarios such as the sustainable demand response.

Accelerating Large-Scale Single-Source Shortest Path on FPGA

Many real-world problems can be represented as graphs and solved by graph traversal algorithms. Single-Source Shortest Path (SSSP) is a fundamental graph algorithm. Today, large-scale graphs involve millions or even billions of vertices, making efficient parallel graph processing challenging. In this paper, we propose a single-FPGA based design to accelerate SSSP for massive graphs. We adopt the well-known Bellman-Ford algorithm. In the proposed design, graph is stored in external memory, which is more realistic for processing large scale graphs. Using the available external memory bandwidth, our design achieves the maximum data parallelism to concurrently process multiple edges in each clock cycle, regardless of data dependencies. The performance of our design is independent of the graph structure as well. We propose a optimized data layout to enable efficient utilization of external memory bandwidth. We prototype our design using a state-of-the-art FPGA. Experimental results show that our design is capable of processing 1.6 billion edges per second (GTEPS) using a single FPGA, while simultaneously achieving high clock rate of over 200 MHz. This would place us in the 131st position of the Graph 500 benchmark list of supercomputing systems for data intensive applications. Our solution therefore provides comparable performance to state-of-the-art systems.

Social Link Prediction in Online Social Tagging Systems

Social networks have become a popular medium for people to communicate and distribute ideas, content, news, and advertisements. Social content annotation has naturally emerged as a method of categorization and filtering of online information. The unrestricted vocabulary users choose from to annotate content has often lead to an explosion of the size of space in which search is performed. In this article, we propose latent topic models as a principled way of reducing the dimensionality of such data and capturing the dynamics of collaborative annotation process. We propose three generative processes to model latent user tastes with respect to resources they annotate with metadata. We show that latent user interests combined with social clues from the immediate neighborhood of users can significantly improve social link prediction in the online music social media site Last.fm. Most link prediction methods suffer from the high class imbalance problem, resulting in low precision and/or recall. In contrast, our proposed classification schemes for social link recommendation achieve high precision and recall with respect to not only the dominant class (nonexistence of a link), but also with respect to sparse positive instances, which are the most vital in social tie prediction.

Influence in social networks: a unified model?

Understanding how information flows in online social networks is of great importance. It is generally difficult to obtain accurate prediction results of cascades over such networks, therefore a variety of diffusion models have been proposed in the literature to simulate diffusion processes instead. We argue that such models require extensive simulation results to produce good estimates of future spreads. In this work, we take a complimentary approach. We present a generalized, analytical model of influence in social networks that captures social influence at various levels of granularity, ranging from pairwise influence, to local neighborhood, to the general population, and external events, therefore capturing the complex dynamics of human behavior. We demonstrate that our model can integrate a variety of diffusion models. Particularly, we show that commonly used diffusion models in social networks can be reduced to special cases of our model, by carefully defining their parameters. Our goal is to provide a closed-form expression to approximate the probability of infection for every node in an arbitrary, directed network at any time t. We quantitatively evaluate the approximation quality of our analytical solution as compared to numerous popular diffusion models on a real-world dataset and a series of synthetic graphs.

The role of organization hierarchy in technology adoption at the workplace

Popular social networking sites have revolutionized the way people interact on the Web, enabling rapid information dissemination and search. In an enterprise, understanding how information flows within and between organizational levels and business units is of great importance. Despite numerous studies in information diffusion in online social networks, little is known about factors that affect the dynamics of technological adoption at the workplace. Here, we address this problem, by examining the impact of organizational hierarchy in adopting new technologies in the enterprise. Our study suggests that middle-level managers are more successful in influencing employees into adopting a new microblogging service. Further, we reveal two distinct patterns of peer pressure, based on which employees are not only more likely to adopt the service, but the rate at which they do so quickens as the popularity of the new technology increases. We integrate our findings into two intuitive, realistic agent-based computational models that capture the dynamics of adoption at both microscopic and macroscopic levels. We evaluate our models in a real-world dataset we collected from a multinational Fortune 500 company. Prediction results show that our models provide great improvements over commonly used diffusion models. Our findings provide significant insights to managers seeking to realize the dynamics of adoption of new technologies in their company, and could assist in designing better strategies for rapid and efficient technology adoption and information dissemination at the workplace.

High-Throughput and Energy-Efficient Graph Processing on FPGA

In this paper, we propose a novel design for large-scale graph processing on FPGA. Our design uses large external memory for storing massive graph data and FPGA for acceleration, and leverages edge-centric computing principles. We propose a data layout which optimizes the external memory performance and leads to an efficient memory activation schedule to reduce on-chip memory power consumption. Further, we develop a parallel architecture on FPGA which can saturate the external memory bandwidth and concurrently process multiple input data to increase throughput. We use our design to accelerate several classic graph algorithms, including single-source shortest path, weakly connected component, and minimum spanning tree. Experimental results show that for all the considered graph algorithms, our design achieves high throughput of over 600 million traversed edges per second (MTEPS) and high energy-efficiency of over 30 MTEPS/W. Compared with a baseline design, our optimizations result in over 3.6× throughput and 5.8× energy-efficiency improvements, respectively. Our design achieves 32% throughput improvement when compared with state-of-the-art FPGA designs, and up to 7.8× speedup when compared with state-of-the-art multi-core implementation.

Optimizing memory performance for FPGA implementation of pagerank

Recently, FPGA implementation of graph algorithms arising in many areas such as social networks has been studied. However, the irregular memory access pattern of graph algorithms makes obtaining high performance challenging. In this paper, we present an FPGA implementation of the classic PageRank algorithm. Our goal is to optimize the overall system performance, especially the cost of accessing the off-chip DRAM. We optimize the data layout so that most of memory accesses to the DRAM are sequential. Post-place-and-route results show that our design on a state-of-the-art FPGA can achieve a high clock rate of over 200 MHz. Based on a realistic DRAM access model, we build a simulator to estimate the execution time including memory access overheads. The simulation results show that our design achieves at least 96% of the theoretically best performance of the target platform. Compared with a baseline design, our optimized design dramatically reduces the number of random memory accesses and improves the execution time by at least 70%.

Predicting Failures from Oilfield Sensor Data using Time Series Shapelets

Increasing instrumentation of the modern digital oilfield produces streams of data from sensors that monitor the functioning of different components in the field. This data should be converted to actionable information rapidly in order to respond to events as they happen or are predicted. The challenge is therefore to develop technologies that can process these large sensor datasets rapidly and with minimal manual supervision to ensure a data processing system that can scale with the increasing instrumentation. We consider as a use-case an oilfield with several Electrical Submersible Pumps (ESPs), each instrumented with sensors that continually measure electrical properties of the pump (the streams of sensor data), which are then relayed to a central location. In this paper, we demonstrate how a time-series analysis approach can be applied to failure detection and failure prediction from the streams of sensor data. The method involves identifying “shapelets” – short instances that are particularly distinct – in the streams of sensor data. The shapelets approach is particularly applicable to large oil and gas enterprise datasets because the algorithm does not need access to the entire historical data. This greatly reduces the amount of data that needs to be stored for data analysis. Moreover, unlike model-based approaches, shapelet-based analysis does not make any assumptions about the underlying nature of the data, making it practical for applications where a detailed physical model of the pump is not available. We validate our proposed method by analysis on a representative set of instrumented ESPs. We describe the preprocessing steps that were applied in our analysis. We report the results of experiments to study the effects of varying the data processing parameters on the accuracy of fault detection and prediction. These results indicate that shapelet-based approaches are promising for analysis of time-series data in the oil and gas industry.

Efficient customer selection for sustainable demand response in smart grids

Regulating the power consumption to avoid peaks in demand is a common practice. Demand Response(DR) is being used by utility providers to minimize costs or ensure system reliability. Although it has been used extensively there is a shortage of solutions dealing with dynamic DR. Past attempts focus on minimizing the load demand without considering the sustainability of the reduced energy. In this paper an efficient algorithm is presented which solves the problem of dynamic DR scheduling. Data from the USC campus micro grid were used to evaluate the efficiency as well as the robustness of the proposed solution. The targeted energy reduction is achieved with a maximum average approximation error of ≈ 0.7%. Sustainability of the reduced energy is achieved with respect to the optimal available solution providing a maximum average error less than 0.6%. It is also shown that a solution is provided with a low computational cost fulfilling the requirements of dynamic DR.