Multimodal Spatio-Temporal-Spectral Fusion for Deep Learning Applications in Physiological Time Series Processing: A Case Study in Monitoring the Depth of Anesthesia

Information on the spatial and temporal of fishing activity can optimize a fisheries management and increase their economical and biological benefit. For effective management and good understanding of fishing activities, information about fishing ground is crucial. In this study, we aimed to analyze the spatio-temporal of lift net fisheries in Kepulauan Seribu by analyzing their fishing season, investigating their hotspot of fishing ground using GIS-based hotspot model, and mapping the potential fishing ground of each target species. We found that anchovy and scad could be caught throughtout the year, while sardine and squid had high fishing season in west monsoon. Hotspot of fishing ground of lift net fisheries in Kepulauan Seribu waters generally was concentrated around Lancang Island and in southern part of Kotok Island. Potential fishing ground for sardines was located in around Lancang Island on west monsoon. Squids were highly distributed around Lancang Island in December to January and around Lancang and Rambut Islands in November. Anchovy and scad had more potential fishing ground in around Kepulauan Seribu waters. Keywords: fishing ground, lift net, hotspot, fishing season

Download Full-text

Characterizing urbanization-induced land surface phenology change from time-series remotely sensed images at fine spatio-temporal scale: A case study in Nanjing, China (2001–2018)

Journal of Cleaner Production ◽

10.1016/j.jclepro.2020.122487 ◽

2020 ◽

Vol 274 ◽

pp. 122487 ◽

Cited By ~ 2

Author(s):

Xin Wang ◽

Peijun Du ◽

Dongmei Chen ◽

Cong Lin ◽

Hongrui Zheng ◽

...

Keyword(s):

Time Series ◽

Land Surface ◽

Remotely Sensed ◽

Temporal Scale ◽

Land Surface Phenology ◽

Remotely Sensed Images ◽

Spatio Temporal

Download Full-text

Estimating long-term spatio-temporal variations of urban vegetation using Landsat time series: a case study of Kyiv city, Ukraine

10.3997/2214-4609.20215521130 ◽

2021 ◽

Author(s):

D. Svidzinska

Keyword(s):

Time Series ◽

Temporal Variations ◽

Urban Vegetation ◽

Spatio Temporal

Download Full-text

Using Syntactic Similarity to Shorten the Training Time of Deep Learning Models using Time Series Datasets: A Case Study

Proceedings of the 2nd International Conference on Deep Learning Theory and Applications ◽

10.5220/0010515700930100 ◽

2021 ◽

Author(s):

Silvestre Malta ◽

Pedro Pinto ◽

Manuel Veiga

Keyword(s):

Time Series ◽

Deep Learning ◽

Learning Models ◽

Training Time ◽

Syntactic Similarity

Download Full-text

Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph182212213 ◽

2021 ◽

Vol 18 (22) ◽

pp. 12213

Author(s):

Taesung Kim ◽

Jinhee Kim ◽

Wonho Yang ◽

Hunjoo Lee ◽

Jaegul Choo

Keyword(s):

Time Series ◽

Deep Learning ◽

Air Quality ◽

Time Series Data ◽

Quality Data ◽

Series Data ◽

Missing Value ◽

Missing Value Imputation ◽

Spatio Temporal ◽

Air Quality Data

To prevent severe air pollution, it is important to analyze time-series air quality data, but this is often challenging as the time-series data is usually partially missing, especially when it is collected from multiple locations simultaneously. To solve this problem, various deep-learning-based missing value imputation models have been proposed. However, often they are barely interpretable, which makes it difficult to analyze the imputed data. Thus, we propose a novel deep learning-based imputation model that achieves high interpretability as well as shows great performance in missing value imputation for spatio-temporal data. We verify the effectiveness of our method through quantitative and qualitative results on a publicly available air-quality dataset.

Download Full-text