arXiv subjects

Calton Pu

Publications and source records attributed to Calton Pu.

22 records · Page 2Linked to original sources

arXiv2019

Concept Drift Adaptive Physical Event Detection for Social Media Streams

Event detection has long been the domain of physical sensors operating in a static dataset assumption. The prevalence of social media and web access has led to the emergence of social, or human sensors who report on events globally. This warrants development of event detectors that can take advantage of the truly dense and high spatial and temporal resolution data provided by more than 3 billion social users. The phenomenon of concept drift, which causes terms and signals associated with a topic to change over time, renders static machine learning ineffective. Towards this end, we present an application for physical event detection on social sensors that improves traditional physical event detection with concept drift adaptation. Our approach continuously updates its machine learning classifiers automatically, without the need for human intervention. It integrates data from heterogeneous sources and is designed to handle weak-signal events (landslides, wildfires) with around ten posts per event in addition to large-signal events (hurricanes, earthquakes) with hundreds of thousands of posts per event. We demonstrate a landslide detector on our application that detects almost 350% more land-slides compared to static approaches. Our application has high performance: using classifiers trained in 2014, achieving event detection accuracy of 0.988, compared to 0.762 for static approaches.

cs.SI↗

arXiv2019

ASSED -- A Framework for Identifying Physical Events through Adaptive Social Sensor Data Filtering

Physical event detection has long been the domain of static event processors operating on numeric sensor data. This works well for large scale strong-signal events such as hurricanes, and important classes of events such as earthquakes. However, for a variety of domains there is insufficient sensor coverage, e.g., landslides, wildfires, and flooding. Social networks have provided massive volume of data from billions of users, but data from these generic social sensors contain much more noise than physical sensors. One of the most difficult challenges presented by social sensors is \textit{concept drift}, where the terms associated with a phenomenon evolve and change over time, rendering static machine learning (ML) classifiers less effective. To address this problem, we develop the ASSED (Adaptive Social Sensor Event Detection) framework with an ML-based event processing engine and show how it can perform simple and complex physical event detection on strong- \textit{and} weak-signal with low-latency, high scalability, and accurate coverage. Specifically, ASSED is a framework to support continuous filter generation and updates with machine learning using streaming data from high-confidence sources (physical and annotated sensors) and social networks. We build ASSED to support procedures for integrating high-confidence sources into social sensor event detection to generate high-quality filters and to perform dynamic filter selection by tracking its own performance. We demonstrate ASSED capabilities through a landslide detection application that detects almost 350\% more landslides compared to static approaches. More importantly, ASSED automates the handling of concept drift: four years after initial data collection and classifier training, ASSED achieves event detection accuracy of 0.988 (without expert manual intervention), compared to 0.762 for static approaches.

cs.SI↗

arXiv2019

A Comparative Measurement Study of Deep Learning as a Service Framework

Big data powered Deep Learning (DL) and its applications have blossomed in recent years, fueled by three technological trends: a large amount of digitized data openly accessible, a growing number of DL software frameworks in open source and commercial markets, and a selection of affordable parallel computing hardware devices. However, no single DL framework, to date, dominates in terms of performance and accuracy even for baseline classification tasks on standard datasets, making the selection of a DL framework an overwhelming task. This paper takes a holistic approach to conduct empirical comparison and analysis of four representative DL frameworks with three unique contributions. First, given a selection of CPU-GPU configurations, we show that for a specific DL framework, different configurations of its hyper-parameters may have a significant impact on both performance and accuracy of DL applications. Second, to the best of our knowledge, this study is the first to identify the opportunities for improving the training time performance and the accuracy of DL frameworks by configuring parallel computing libraries and tuning individual and multiple hyper-parameters. Third, we also conduct a comparative measurement study on the resource consumption patterns of four DL frameworks and their performance and accuracy implications, including CPU and memory usage, and their correlations to varying settings of hyper-parameters under different configuration combinations of hardware, parallel computing libraries. We argue that this measurement study provides in-depth empirical comparison and analysis of four representative DL frameworks, and offers practical guidance for service providers to deploying and delivering DL as a Service (DLaaS) and for application developers and DLaaS consumers to select the right DL frameworks for the right DL workloads.

cs.PF↗

arXiv2018

A Comparative Study of Containers and Virtual Machines in Big Data Environment

Container technique is gaining increasing attention in recent years and has become an alternative to traditional virtual machines. Some of the primary motivations for the enterprise to adopt the container technology include its convenience to encapsulate and deploy applications, lightweight operations, as well as efficiency and flexibility in resources sharing. However, there still lacks an in-depth and systematic comparison study on how big data applications, such as Spark jobs, perform between a container environment and a virtual machine environment. In this paper, by running various Spark applications with different configurations, we evaluate the two environments from many interesting aspects, such as how convenient the execution environment can be set up, what are makespans of different workloads running in each setup, how efficient the hardware resources, such as CPU and memory, are utilized, and how well each environment can scale. The results show that compared with virtual machines, containers provide a more easy-to-deploy and scalable environment for big data workloads. The research work in this paper can help practitioners and researchers to make more informed decisions on tuning their cloud environment and configuring the big data applications, so as to achieve better performance and higher resources utilization.

cs.DC↗