scholarly journals Autoencoder‐based abnormal activity detection using parallelepiped spatio‐temporal region

2018 ◽  
Vol 13 (1) ◽  
pp. 23-30 ◽  
Author(s):  
Michael George ◽  
Babita Roslind Jose ◽  
Jimson Mathew ◽  
Pranjali Kokare
Author(s):  
M. McDermott ◽  
S. K. Prasad ◽  
S. Shekhar ◽  
X. Zhou

Discovery of interesting paths and regions in spatio-temporal data sets is important to many fields such as the earth and atmospheric sciences, GIS, public safety and public health both as a goal and as a preliminary step in a larger series of computations. This discovery is usually an exhaustive procedure that quickly becomes extremely time consuming to perform using traditional paradigms and hardware and given the rapidly growing sizes of today’s data sets is quickly outpacing the speed at which computational capacity is growing. In our previous work (Prasad et al., 2013a) we achieved a 50 times speedup over sequential using a single GPU. We were able to achieve near linear speedup over this result on interesting path discovery by using Apache Hadoop to distribute the workload across multiple GPU nodes. Leveraging the parallel architecture of GPUs we were able to drastically reduce the computation time of a 3-dimensional spatio-temporal interest region search on a single tile of normalized difference vegetative index for Saudi Arabia. We were further able to see an almost linear speedup in compute performance by distributing this workload across several GPUs with a simple MapReduce model. This increases the speed of processing 10 fold over the comparable sequential while simultaneously increasing the amount of data being processed by 384 fold. This allowed us to process the entirety of the selected data set instead of a constrained window.


2020 ◽  
Vol 14 (4) ◽  
pp. 1347-1383 ◽  
Author(s):  
Mark J. Hopwood ◽  
Dustin Carroll ◽  
Thorben Dunse ◽  
Andy Hodson ◽  
Johnna M. Holding ◽  
...  

Abstract. Freshwater discharge from glaciers is increasing across the Arctic in response to anthropogenic climate change, which raises questions about the potential downstream effects in the marine environment. Whilst a combination of long-term monitoring programmes and intensive Arctic field campaigns have improved our knowledge of glacier–ocean interactions in recent years, especially with respect to fjord/ocean circulation, there are extensive knowledge gaps concerning how glaciers affect marine biogeochemistry and productivity. Following two cross-cutting disciplinary International Arctic Science Committee (IASC) workshops addressing the importance of glaciers for the marine ecosystem, here we review the state of the art concerning how freshwater discharge affects the marine environment with a specific focus on marine biogeochemistry and biological productivity. Using a series of Arctic case studies (Nuup Kangerlua/Godthåbsfjord, Kongsfjorden, Kangerluarsuup Sermia/Bowdoin Fjord, Young Sound and Sermilik Fjord), the interconnected effects of freshwater discharge on fjord–shelf exchange, nutrient availability, the carbonate system, the carbon cycle and the microbial food web are investigated. Key findings are that whether the effect of glacier discharge on marine primary production is positive or negative is highly dependent on a combination of factors. These include glacier type (marine- or land-terminating), fjord–glacier geometry and the limiting resource(s) for phytoplankton growth in a specific spatio-temporal region (light, macronutrients or micronutrients). Arctic glacier fjords therefore often exhibit distinct discharge–productivity relationships, and multiple case-studies must be considered in order to understand the net effects of glacier discharge on Arctic marine ecosystems.


Sensors ◽  
2016 ◽  
Vol 16 (6) ◽  
pp. 822 ◽  
Author(s):  
Xiaomu Luo ◽  
Huoyuan Tan ◽  
Qiuju Guan ◽  
Tong Liu ◽  
Hankz Zhuo ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document