Deep neural networks (DNNs) achieve state-of-the-art performance in video anomaly detection. However, the usage of DNNs is limited in practice due to their computational overhead, generally requiring significant resources and specialized hardware. Further, despite recent progress, current evaluation criteria of video anomaly detection algorithms are flawed, preventing meaningful comparisons among algorithms. In response to these challenges, we propose (1) a compression-based technique referred to as Spatio-Temporal N-Gram Prediction by Partial Matching (STNG PPM) and (2) simple modifications to current evaluation criteria for improved interpretation and broader applicability across algorithms. STNG PMM does not require specialized hardware, has few parameters to tune, and is competitive with DNNs on multiple benchmark data sets in video anomaly detection.
Sandia National Laboratories is a premier United States national security laboratory which develops science-based technologies in areas such as nuclear deterrence, energy production, and climate change. Computing plays a key role in its diverse missions, and within that environment, Research Software Engineers (RSEs) and other scientific software developers utilize testing automation to ensure quality and maintainability of their work. We conducted a Participatory Action Research study to explore the challenges and strategies for testing automation through the lens of academic literature. Through the experiences collected and comparison with open literature, we identify these challenges in testing automation and then present strategies for mitigation grounded in evidence-based practice and experience reports that other, similar institutions can assess for their automation needs.
The primary purpose of this document is to outline the progress made on the LDRD titled “Identifying and Explaining Anomalous Activity in Surveillance Video with Compression Algorithms” in FY22 and FY23. In this LDRD, we explored the usage of compression-based analytics to identify anomalous activity in video. We developed a novel algorithm, Spatio-Temporal N-Gram PPM (STNG PPM) that accounts for spatially and temporally aware anomalies in video. We extracted features using motions vectors from video as well as operating on the raw features. STNG PPM is comparable to many deep learning approaches but does not require specialized hardware (GPUs) to run efficiently. We also examine the evaluation metrics and propose novel measures addressing faults in the current evaluation measures.
The DevOps movement, which aims to accelerate the continuous delivery of high-quality software, has taken a leading role in reshaping the software industry. Likewise, there is growing interest in applying DevOps tools and practices in the domains of computational science and engineering (CSE) to meet the ever-growing demand for scalable simulation and analysis. Translating insights from industry to research computing, however, remains an ongoing challenge; DevOps for science and engineering demands adaptation and innovation in those tools and practices. There is a need to better understand the challenges faced by DevOps practitioners in CSE contexts in bridging this divide. To that end, we conducted a participatory action research study to collect and analyze the experiences of DevOps practitioners at a major US national laboratory through the use of storytelling techniques. We share lessons learned and present opportunities for future investigation into DevOps practice in the CSE domain.
U.S. national research laboratories and agencies play an integral role in advancing science and technology for the public good. The authors of this article, as research software engineers (RSEs) and allies from eight unique national R&D organizations, came together to explore RSE needs from the perspective of national institutions. We identified three key areas of improvement for future RSEs to pursue science in the national interest: community establishment, hiring and retention, and recognition. To retain and cultivate this essential talent, U.S. national institutions must evolve to support appropriate career pathways for RSEs, and to recognize and reward RSEs’ work.
In order for analysts to be able to do their work, they sift through hundreds, thousands, or even millions of documents to make connections between entities of interest. This process is time consuming, tedious, and prone to potential error from missed connections or connections made that should not have been. There exist many tools in natural language processing, or NLP, to extract information from documents. However, when it comes to relationship extraction, there has been varied success. This project began with a goal to solve the relationship extraction problem which developed into a deeper understanding of the problem and the associated challenges for solving this problem on a general scale. In this report, we explain our research and approach to relationship extraction, identify other auxiliary problems in NLP that provide additional challenges to solving relationship extraction generally, explain our analysis of the current state of relationship extraction, and postulate future work to address these problems.
In the area of information extraction from text data, there exists a number of tools with the capability of extracting entities, topics, and their relationships with one another from both structured and unstructured text sources. Such information has endless uses in a number of domains, however, the solutions to getting this information are still in early stages and has room for improvement. The topic has been explored from a research perspective by academic institutions, as well as formal tool creation from corporations but has not made much advancement since the early 2000's. Overall, entity extraction, and the related topic of entity linking, is common among these tools, though with varying degrees of accuracy, while relationship extraction is more difficult to find and seems limited to same sentence analysis. In this report, we take a look at the top state of the art tools currently available and identify their capabilities, strengths, and weaknesses. We explore the common algorithms in the successful approaches to entity extraction and their ability to efficiently handle both structured and unstructured text data. Finally, we highlight some of the common issues among these tools and summarize the current ability to extract relationship information.
In the realm of information extraction from text data, there exists a number of tools with the capability of extracting entities and their relationships with one another. Such information has endless uses in a number of domains, however, the solutions to getting this information is still in early stages and has room for improvement. The topic has been explored from a research perspective by academic institutions, as well as formal tool creation from corporations. Overall, entity extraction is common among these tools, though with varying degrees of accuracy, while relationship extraction is more difficult to find. In this report, we take a look at the top state of the art tools currently available and identify their capabilities, strengths, and weaknesses. We explore the common algorithms in the successful approaches and their ability to efficiently handle both structured and unstructured text data. Finally, we highlight some of the common issues among these tools and summarize the current status in the area of entity-relationship extraction.