Response to reviewer

Sedona, Rocco

doi:10.5194/amt-2019-481-ac2

Cited by 2 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this example, the agent takes 1 = (0, 3, ) and 2 = (2, 3, ℎ ). The status of cell (2,3) changes by adding boundary lines. (2,3) becomes smaller because the percentage of the number of data in the partition becomes smaller instead of that in the cell is constant.…”

Section: Statementioning

confidence: 99%

“…The status of cell (2,3) changes by adding boundary lines. (2,3) becomes smaller because the percentage of the number of data in the partition becomes smaller instead of that in the cell is constant. We run the workload and obtain the reward for the episode after computing three partitions.…”

Section: Statementioning

confidence: 99%

“…Computation environment. We used Apache Sedona, the stateof-the-art distributed and parallel processing system for big spatial data [3]. We used nine computers with a Linux server with 32GB of memory and an Intel Celeron G4930T CPU@3.00GHz processor.…”

Section: Experimental Settingmentioning

confidence: 99%

“…mobility service [21], and route and point-of-interest recommendation [17,26]. For efficient analysis of spatial data, it is essential to use distributed parallel processing systems for spatial data such as Sedona [3], SpatialHadoop [7], and others [1,25,28,29,36].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Learned Spatial Data Partitioning

Hori,

Sasaki,

Amagata

et al. 2023

Proceedings of the Sixth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management

View full text Add to dashboard Cite

Due to the significant increase in the size of spatial data, it is essential to use distributed parallel processing systems to efficiently analyze spatial data. In this paper, we first study learned spatial data partitioning, which effectively assigns groups of big spatial data to computers based on locations of data by using machine learning techniques. We formalize spatial data partitioning in the context of reinforcement learning and develop a novel deep reinforcement learning algorithm. Our learning algorithm leverages features of spatial data partitioning and prunes ineffective learning processes to find optimal partitions efficiently. Our experimental study, which uses Apache Sedona and real-world spatial data, demonstrates that our method efficiently finds partitions for accelerating distance join queries and reduces the workload run time by up to 59.4%.

show abstract

Section: Statementioning

confidence: 99%

Section: Statementioning

confidence: 99%

Section: Experimental Settingmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Learned Spatial Data Partitioning

Hori,

Sasaki,

Amagata

et al. 2023

Proceedings of the Sixth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management

View full text Add to dashboard Cite

show abstract

“…The need for better search tools and methods within the area is reflected in the rapid growth of the E-Discovery market [32,10], as well as in the growing research interest [34,15,29]. This paper positions the research that is carried out through joined work from CREATE-IT Applied Research at the Amsterdam University of Applied Sciences [7] and the Intelligent Systems Lab Amsterdam at the University of Amsterdam [17].…”

Section: Risk Evaluationmentioning

confidence: 99%

Artificial Intelligence and the Law

Kumari¹

2020

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

This paper examines coding applied by seven different review groups on the same set of twenty eight thousand documents. The results indicate that the level of agreement between the reviewer groups is much lower than might be suspected based on the general level of confidence on the part of the legal profession in the accuracy and consistency of document review by humans. Each document from a set of twenty eight thousand documents was reviewed for responsiveness, privilege and relevance to specific issues by seven independent review teams. Examination of the seven sets of coding tags for responsiveness revealed an inter-reviewer agreement of 43% for either responsive or non-responsive determinations. The agreement on the responsive determination alone was 9% and on the non-responsive determination was 34% of the total document family count. Pair-wise analysis of the seven groups of reviewers provided higher rates, however no pairing of the teams indicated that there is an unequivocally 1 Thomas I. Barnett is the leader of the e-Discovery, records and information management consulting division of Iron Mountain, Inc.; Svetlana Godjevac is a senior consultant at Iron Mountain, Inc. 2 superior assessment of the dataset by any of the teams. This paper considers the ramifications of low agreement of human manual review in the legal domain and the need for industry benchmarks and standards. Suggestions are offered for improving the quality of human manual review using statistical quality control (QC) measures and machine-learning tools for pre-assessment and document categorization. 4 unit 2 size was two. The majority of the corpus, 99%, consisted of families with no more than eight attachments. The family size frequencies are provided in Figure 2. FIGURE 1-DATA COMPOSITION OF THE REVIEW SET FIGURE 2-FREQUENCY DISTRIBUTION OF FAMILY-UNIT SIZE-Most families consisted of two or one member. Bin Frequency Cumulative %

show abstract

Response to reviewer

Cited by 2 publications

References 0 publications

Learned Spatial Data Partitioning

Learned Spatial Data Partitioning

Artificial Intelligence and the Law

Contact Info

Product

Resources

About