Study of using machine learning for level 1 trigger decision in JUNO experiment

A Machine Learning Approach to Cloud Masking in Sentinel-3 SLSTR Data

10.5194/egusphere-egu2020-21593 ◽

2020 ◽

Author(s):

Samuel Jackson ◽

Jeyarajan Thiyagalingam ◽

Caroline Cox

Keyword(s):

Machine Learning ◽

Remote Sensing ◽

Land Surface ◽

Satellite Images ◽

Binary Classification ◽

Gradient Boosting ◽

Learning Approach ◽

Persistent Problem ◽

Machine Learning Approach ◽

Level 1

Clouds appear ubiquitously in the Earth's atmosphere, and thus present a persistent problem for the accurate retrieval of remotely sensed information. The task of identifying which pixels are cloud, and which are not, is what we refer as the cloud masking problem. The task of cloud masking essentially boils down to assigning a binary label, representing either "cloud" or "clear", to each pixel. Although this problem appears trivial, it is often complicated by a diverse number of issues that affect the imagery obtained from remote sensing instruments. For instance, snow, sea ice, dust, smoke, and sun glint can easily challenge the robustness and consistency of any cloud masking algorithm. The cloud masking problem is also further complicated by geographic and seasonal variation in acquired scenes. In this work, we present a machine learning approach to handle the problem of cloud masking for the Sea and Land Surface Temperature Radiometer (SLSTR) on board the Sentinel-3 satellites. Our model uses Gradient Boosting Decision Trees (GBDTs), to perform pixel-wise segmentation of satellite images. The model is trained using a hand labelled dataset of ~12,000 individual pixels covering both the spatial and temporal domains of the SLSTR instrument and utilises the combined channels of the dual-view swaths. Pixel level annotations, while lacking spatial context, have the advantage of being cheaper to obtain compared to fully labelled images, a major problem in applying machine learning to remote sensing imagrey.We validate the performance of our mask using cross validation and compare its performance with two baseline models provided in the SLSTR level 1 product. We show up to 10% improvement in binary classification accuracy compared with the baseline methods. Additionally, we show that our model has the ability to distinguish between different classes of cloud to reasonable accuracy.

Download Full-text

Artificial Neural Networks as a Level-2 Trigger for the H1 Experiment: Status of the Hardware Implementation

International Journal of Modern Physics C ◽

10.1142/s012918319500040x ◽

1995 ◽

Vol 06 (04) ◽

pp. 541-548

Author(s):

D. Goldner ◽

H. Getta ◽

M. Kolander ◽

T. Krämerkämper ◽

H. Kolanoski ◽

...

Keyword(s):

Trigger System ◽

Intrinsic Parallelism ◽

Fast Processing ◽

Level 1 ◽

Artificial Neural ◽

Trigger Decision ◽

Artificial Neural Network Ann ◽

Level 2 ◽

Dedicated Hardware ◽

Made In

Triggering at the HERA ep collider is challenging because of the high bunch crossing rate and an expected large background. In the H1 experiment, a trigger decision is made in four steps (level 1–4), stepwise decreasing the event rate and allowing for more sophisticated trigger decisions. The time available for L2 is about 20 μs. We have proposed to use an artificial neural network (ANN) for the L2 trigger based on the CNAPS-1064 chip available from Adaptive Solutions, (Oregon, USA). The intrinsic parallelism of the ANN algorithm together with the dedicated hardware offers fast processing of the trigger informations. The trigger system uses up to 10 decision units, each consisting of a Pattern Recognition Module (PRM) and a Data Distribution Board (DDB). A DDB receives the L2 data stream and generates the network inputs used by the algorithms on the PRM. A PRM is a commercial VME board carrying the CNAPS processors.

Download Full-text

Predicting 72-hour and 9-day return to the emergency department using machine learning

JAMIA Open ◽

10.1093/jamiaopen/ooz019 ◽

2019 ◽

Vol 2 (3) ◽

pp. 346-352 ◽

Cited By ~ 1

Author(s):

Woo Suk Hong ◽

Adrian Daniel Haimovich ◽

Richard Andrew Taylor

Keyword(s):

Machine Learning ◽

Emergency Department ◽

Administrative Data ◽

Trauma Center ◽

Community Hospital ◽

Gradient Boosting ◽

Health Record ◽

Test Sets ◽

Level 1 ◽

Level 1 Trauma Center

Abstract Objectives To predict 72-h and 9-day emergency department (ED) return by using gradient boosting on an expansive set of clinical variables from the electronic health record. Methods This retrospective study included all adult discharges from a level 1 trauma center ED and a community hospital ED covering the period of March 2013 to July 2017. A total of 1500 variables were extracted for each visit, and samples split randomly into training, validation, and test sets (80%, 10%, and 10%). Gradient boosting models were fit on 3 selections of the data: administrative data (demographics, prior hospital usage, and comorbidity categories), data available at triage, and the full set of data available at discharge. A logistic regression (LR) model built on administrative data was used for baseline comparison. Finally, the top 20 most informative variables identified from the full gradient boosting models were used to build a reduced model for each outcome. Results A total of 330 631 discharges were available for analysis, with 29 058 discharges (8.8%) resulting in 72-h return and 52 748 discharges (16.0%) resulting in 9-day return to either ED. LR models using administrative data yielded test AUCs of 0.69 (95% confidence interval [CI] 0.68–0.70) and 0.71(95% CI 0.70–0.72), while gradient boosting models using administrative data yielded test AUCs of 0.73 (95% CI 0.72–0.74) and 0.74 (95% CI 0.73–0.74) for 72-h and 9-day return, respectively. Gradient boosting models using variables available at triage yielded test AUCs of 0.75 (95% CI 0.74–0.76) and 0.75 (95% CI 0.74–0.75), while those using the full set of variables yielded test AUCs of 0.76 (95% CI 0.75–0.77) and 0.75 (95% CI 0.75–0.76). Reduced models using the top 20 variables yielded test AUCs of 0.73 (95% CI 0.71–0.74) and 0.73 (95% CI 0.72–0.74). Discussion and Conclusion Gradient boosting models leveraging clinical data are superior to LR models built on administrative data at predicting 72-h and 9-day returns.

Download Full-text

Data Acquisition and Software for the ATLAS Tile Calorimeter Phase-II Upgrade Demonstrator

EPJ Web of Conferences ◽

10.1051/epjconf/201921401004 ◽

2019 ◽

Vol 214 ◽

pp. 01004 ◽

Cited By ~ 1

Author(s):

Xiaoguang Yue

Keyword(s):

Data Processing ◽

Phase Ii ◽

Software Components ◽

High Luminosity ◽

Readout Electronics ◽

Front End ◽

Design Value ◽

Level 1 ◽

Trigger Decision ◽

Energy Information

After a series of upgrades, the High Luminosity LHC (HL-LHC) will have an instantaneous luminosity of 5-7 times larger than the LHC design value. The readout electronics of the ATLAS Tile Calorimeter (TileCal) will undergo a substantial upgrade during the Phase-II upgrade to accommodate the HL-LHC requirements. After the Phase-II upgrade, the TileCal detector signals will be digitized by on-detector electronics and transferred to the the TileCal PreProcessors (TilePPr), which is a part of the off-detector electronics. In the TilePPr, the digitized data will be stored in pipeline buffers and be packed and readout to the Front-End Link eXchange (FELIX) system upon receiving a trigger decision. At the same time, the energy information will be reconstructed from the detector data and transferred to the Level-1 Calorimeter Trigger (L1Calo) system in different granularity for every bunch crossing. The TileCal Demonstrator is designed to evaluate the performance of the TileCal with new readout electronics without compromising the present data taking. This contribution describes in detail the data processing and the hardware, firmware, software components of the TileCal Demonstrator system, together with the results of beam tests performed at CERN.

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text

Ultrastructural study on the development of rat amygdaloid body

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100159709 ◽

1990 ◽

Vol 48 (3) ◽

pp. 432-433

Author(s):

A. Manolova ◽

S. Manolov

Keyword(s):

Nerve Cells ◽

Amygdaloid Complex ◽

Amygdaloid Body ◽

Thin Ring ◽

Morphological Criteria ◽

Neural Processes ◽

Abundant Cytoplasm ◽

Level 1 ◽

Few Data ◽

Oval Shape

Relatively few data on the development of the amygdaloid complex are available only at the light microscopic level (1-3). The existence of just general morphological criteria requires the performance of other investigations in particular ultrastructural in order to obtain new and more detailed information about the changes in the amygdaloid complex during development.The prenatal and postnatal development of rat amygdaloid complex beginning from the 12th embrionic day (ED) till the 33rd postnatal day (PD) has been studied. During the early stages of neurogenesis (12ED), the nerve cells were observed to be closely packed, small-sized, with oval shape. A thin ring of cytoplasm surrounded their large nuclei, their nucleoli being very active with various size and form (Fig.1). Some cells possessed more abundant cytoplasm. The perikarya were extremely rich in free ribosomes. Single sacs of the rough endoplasmic reticulum and mitochondria were observed among them. The mitochondria were with light matrix and possessed few cristae. Neural processes were viewed to sprout from some nerve cells (Fig.2). Later the nuclei were still comparatively large and with various shape.

Download Full-text