scholarly journals Deep Learning Based Multi-Modal Fusion Architectures for Maritime Vessel Detection

2020 ◽  
Vol 12 (16) ◽  
pp. 2509
Author(s):  
Fahimeh Farahnakian ◽  
Jukka Heikkonen
Keyword(s):  
Deep Learning ◽  
Weather Conditions ◽  
Climatic Conditions ◽  
Camera Motion ◽  
Sea Waves ◽  
Illumination Changes ◽  
Infrared Cameras ◽  
Maritime Environment ◽  
Level Fusion ◽  
Different Levels

Object detection is a fundamental computer vision task for many real-world applications. In the maritime environment, this task is challenging due to varying light, view distances, weather conditions, and sea waves. In addition, light reflection, camera motion and illumination changes may cause to false detections. To address this challenge, we present three fusion architectures to fuse two imaging modalities: visible and infrared. These architectures can provide complementary information from two modalities in different levels: pixel-level, feature-level, and decision-level. They employed deep learning for performing fusion and detection. We investigate the performance of the proposed architectures conducting a real marine image dataset, which is captured by color and infrared cameras on-board a vessel in the Finnish archipelago. The cameras are employed for developing autonomous ships, and collect data in a range of operation and climatic conditions. Experiments show that feature-level fusion architecture outperforms the state-of-the-art other fusion level architectures.

PERSONALIZED APPROACH TO THE ORGANIZATION OF MEDICAL CARE FOR PATIENTS WITH WEATHER DEPENDENCE

2020 ◽  
pp. 35-39
Author(s):  
Klepikov O.V. ◽  
Kolyagina N.M. ◽  
Berezhnova T.A. ◽  
Kulintsova Ya.V.
Keyword(s):  
Medical Care ◽  
Cardiovascular System ◽  
Performance Indicators ◽  
Weather Conditions ◽  
Climatic Conditions ◽  
Outpatient Clinics ◽  
Vulnerable Groups ◽  
Pathological Effect ◽  
Weather Forecasts ◽  
Personalized Approach

Relevance. Today, in preventive medicine, climatic conditions that have a pathological effect on the functional state of a person are increasingly being updated. the occurrence of exacerbations of many diseases can be causally associated with various weather conditions. Aim: to develop the main tasks for improving the organization of medical care for weather-dependent patients with diseases of the cardiovascular system. Material and methods. The assessment of personnel, material and technical support and the main performance indicators of an outpatient clinic was carried out on the example of the Voronezh city polyclinic No. 18 to develop the main tasks for improving the organization of medical care for weather-dependent patients with diseases of the cardiovascular system. Results. The main personnel problem is the low staffing of district therapists and specialists of a narrow service. One of the priorities for reducing the burden on medical hospitals is the organization of inpatient replacement medical care on the basis of outpatient clinics. The indicators for the implementation of state guarantees for the outpatient network for 2018, which were fully implemented, are given. The analysis of the planned load performance by polyclinic specialists is presented. Cardiological and neurological services carry out measures to reduce the risk of exacerbations of diseases with cerebral atherosclerosis, hypertension, and major neurological nosologies. Conclusion. Improving the organization of medical care for weather-dependent patients with cardiovascular diseases are: informing patients about the sources of specialized medical weather forecasts in the region, organizing the work of the medical prevention office, implementing an interdepartmental approach to providing health care to the most vulnerable groups of the population.

Influence of meteorological factors on potato yield in the conditions of the Right-Bank Forest-steppe

2018 ◽  
Vol 1 (94) ◽  
pp. 55-61
Author(s):  
R.O. Myalkovsky
Keyword(s):  
Meteorological Factors ◽  
Weather Conditions ◽  
Climatic Conditions ◽  
Potato Yield ◽  
High Yield ◽  
Forest Steppe ◽  
Potato Tubers ◽  
Middle Aged ◽  
Lower Yield ◽  
The Right

Goal. The purpose of the research was to determine the influence of meteorological factors on potato yield in the conditions of the Right Bank Forest-steppe of Ukraine. Methods.Field, analytical and statistical. Results.It was established that among the mid-range varieties Divo stands out with a yield of 42.3 t/ha, Malin white – 39.8 t/ha, and Legend – 37.1 t/ ha. The most favourable weather and climatic conditions for the production of potato tubers were for the Divo 2011 variety with a yield of 45.9 t/ha and 2013 – 45.1 t/ha. For the Legenda variety 2016, the yield of potato tubers is 40.6 t/ha and 2017 – 43.2 t/ha. Malin White 2013 is 41.4 t/ha and 2017 42.1 t/ha. The average varieties of potatoes showed a slightly lower yield on average over the years of research. However, among the varieties is allocated Nadiyna – 40.3 t/ha, Slovyanka – 37.2 t/ ha and Vera 33.8 t/ha. Among the years, the most high-yielding for the Vera variety was 2016 with a yield of 36.6 t/ha and 2017 year – 37.8 t/ha. Varieties Slovyanka and Nadiyna 2011 and 2012 with yields of 42.6 and 44.3 t/ha and 46.5 and 45.3 t/ha, respectively. Characterizing the yield of potato tubers of medium-late varieties over the years of research, there was a decrease in this indicator compared with medium-early and middle-aged varieties. However, the high yield of the varieties of Dar is allocated – 40.0 t/ha, Alladin – 33.6 t/ha and Oxamit 31.3 t/ha. Among the years, the most favourable ones were: for Oxamit and Alladin – 2011 – 33.5 and 36.5 t/ha, and 2017 – 34.1 and 36.4 t/ha, respectively. Favourable years for harvesting varieties were 2011 and 2012 with yields of 45.7 and 45.8 t/ha. Thus, the highest yield of potato tubers on average over the years of studies of medium-early varieties of 41.2-43.3 t / ha were provided by weather conditions of 2011 and 2017 years, medium-ripe varieties 41.0-41.1 - 2012 and 2011, medium- late 37,6-38,5 t / ha - 2012 and 2011, respectively.

Optimal Command for Photovoltaic Systems in Real Outdoor Weather Conditions

2019 ◽  
Vol 142 (1) ◽  
Author(s):  
Hafsa Abouadane ◽  
Abderrahim Fakkar ◽  
Benyounes Oukarfi
Keyword(s):  
Maximum Power Point Tracking ◽  
Accurate Determination ◽  
Weather Conditions ◽  
Climatic Conditions ◽  
Maximum Power ◽  
Photovoltaic System ◽  
Maximum Power Point ◽  
Point Tracking ◽  
Power Point Tracking ◽  
Power Point

The photovoltaic panel is characterized by a unique point called the maximum power point (MPP) where the panel produces its maximum power. However, this point is highly influenced by the weather conditions and the fluctuation of load which drop the efficiency of the photovoltaic system. Therefore, the insertion of the maximum power point tracking (MPPT) is compulsory to track the maximum power of the panel. The approach adopted in this paper is based on combining the strengths of two maximum power point tracking techniques. As a result, an efficient maximum power point tracking method is obtained. It leads to an accurate determination of the MPP during different situations of climatic conditions and load. To validate the effectiveness of the proposed MPPT method, it has been simulated in matlab/simulink under different conditions.

scholarly journals Orchard Mapping with Deep Learning Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3813
Author(s):  
Athanasios Anagnostis ◽  
Aristotelis C. Tagarakis ◽  
Dimitrios Kateris ◽  
Vasileios Moysiadis ◽  
Claus Grøn Sørensen ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Semantic Segmentation ◽  
Automated Detection ◽  
Aerial Images ◽  
Training Dataset ◽  
Field Boundary ◽  
Different Seasons ◽  
Detection And Localization ◽  
Different Levels

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

Deep Learning Associated with Laser-Induced Breakdown Spectroscopy (LIBS) for the Prediction of Lead in Soil

2019 ◽  
Vol 73 (5) ◽  
pp. 565-573 ◽  
Author(s):  
Yun Zhao ◽  
Mahamed Lamine Guindo ◽  
Xing Xu ◽  
Miao Sun ◽  
Jiyu Peng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Confusion Matrix ◽  
Principal Component ◽  
Classification Performance ◽  
Soil Samples ◽  
Laser Induced Breakdown Spectroscopy ◽  
Support Vector ◽  
Breakdown Spectroscopy ◽  
Laser Induced Breakdown ◽  
Different Levels

In this study, a method based on laser-induced breakdown spectroscopy (LIBS) was developed to detect soil contaminated with Pb. Different levels of Pb were added to soil samples in which tobacco was planted over a period of two to four weeks. Principal component analysis and deep learning with a deep belief network (DBN) were implemented to classify the LIBS data. The robustness of the method was verified through a comparison with the results of a support vector machine and partial least squares discriminant analysis. A confusion matrix of the different algorithms shows that the DBN achieved satisfactory classification performance on all samples of contaminated soil. In terms of classification, the proposed method performed better on samples contaminated for four weeks than on those contaminated for two weeks. The results show that LIBS can be used with deep learning for the detection of heavy metals in soil.

Selection of drought-resistant crops for South Steppe of Ukraine

2021 ◽  
Vol 5 (1) ◽  
pp. 13-22
Author(s):  
V. V. Gamayunova ◽  
L. H. Khonenko ◽  
M. I. Fedorchuk ◽  
O. A. Kovalenko
Keyword(s):  
Humus Content ◽  
Soil Layer ◽  
Weather Conditions ◽  
Growing Season ◽  
Grain Sorghum ◽  
Climatic Conditions ◽  
Mineral Fertilizers ◽  
Chemical Application ◽  
Sowing Dates ◽  
Drought Resistant

The cultivation expediency of more drought-resistant crops, in particular sorghum, millet, false flax, safflower and others, instead of sunflower in the area of the Southern Steppe of Ukraine is substantiated. This is, first of all, required by climate change both in Ukraine and in the world. Since 2004, researches of field crops were carried out in the conditions of the Educational and Scientific Practical Center of the Mykolaiv National Agrarian University. Soil phase is the southern chernozem with humus content in the 0–30 cm soil layer which consist of 2.96–3.21 %, with medium and high level of availability of mobile phosphorus and potassium and low – mobile nitrogen. Experiments with soriz (Oksamyt hybrid) were conducted during 2004–2006, millet (Tavriiske, Kostantynivske, Skhidnevarieties) in 2008–2010, grain sorghum (Stepovyi 5 hybrid) in 2014–2016, safflower dye (Lahidnyi variety) in 2017–2019. The years of research differed significantly in temperature and even more in the amount of precipitation before sowing and during the growing season of crops. However, the weather conditions were typical of the Southern Steppe zone of Ukraine. It is established that all studied drought-resistant crops respond positively to nutrition optimization – the level of yield and quality of grain or seeds increases. It was found that the soriz productivity depending on the application of fertilizers and sowing dates increased by 37.6–39.2 %, millet –by 33.3–41.6 %, grain sorghum depending on the background of nutrition and growing conditions – by 8.2–33.2 %, dye safflower – by 11.1–64.6 %. It was determined that the optimization of nutrition of cultivated crops allows to increase their resistance to adverse conditions and productivity in the case of application of low doses of the mineral fertilizers before sowing, pre-sowing treatment of seeds, and growth-regulating chemical application of plants on the main stages of the growing season. Key words: drought-resistant plants, climatic conditions, nutrition optimization, yield, crop quality, varieties, sowing dates.

scholarly journals Surface Changes of Selected Hardwoods Due to Weather Conditions

Forests ◽  
2018 ◽  
Vol 9 (9) ◽  
pp. 557 ◽  
Author(s):  
Ivan Kubovský ◽  
Eliška Oberhofnerová ◽  
František Kačík ◽  
Miloš Pánek
Keyword(s):  
Laser Scanning ◽  
Weather Conditions ◽  
Degradation Process ◽  
Climatic Conditions ◽  
Laser Scanning Microscopy ◽  
Dust Particles ◽  
Confocal Laser ◽  
Chemical Changes ◽  
Colour Changes ◽  
Surface Changes

The study is focused on the surface changes of five hardwoods (oak, black locust, poplar, alder and maple) that were exposed to natural weathering for 24 months in the climatic conditions of Central Europe. Colour, roughness, visual and chemical changes of exposed surface structures were examined. The lowest total colour changes (ΔE*) were found for oak (23.77), the highest being recorded for maple (34.19). Roughness differences after 24-month exposure (ΔRa) showed minimal changes in poplar wood (9.41); the highest changes in roughness were found on the surface of alder (22.18). The presence of mould and blue stains was found on the surface of maple, alder and poplar. Chemical changes were characterized by lignin and hemicelluloses degradation. Decreases of both methoxy and carbonyl groups, cleavage of bonds in lignin and hemicelluloses, oxidation reaction and formation of new chromophores were observed. In the initial phases of the degradation process, the discoloration was related to chemical changes; in the longer period, the greying due to settling of dust particles and action of mould influenced the wood colour. The data were confirmed by confocal laser scanning microscopy. The obtained results revealed degradation processes of tested hardwood surfaces exposed to external environmental factors.

scholarly journals AGRO-CLIMATIC SUITABILITY AND WATER REQUIREMENT FOR TANZANIA GUINEAGRASS CULTIVATION IN THE STATE OF CEARÁ

2017 ◽  
Vol 30 (4) ◽  
pp. 1028-1038 ◽  
Author(s):  
NAILSON LIMA SANTOS LEMOS ◽  
ANA CLARA RODRIGUES CAVALCANTE ◽  
THIERES GEORGE FREIRE DA SILVA ◽  
JOSÉ RICARDO MACEDO PEZZOPANE ◽  
PATRÍCIA MENEZES SANTOS ◽  
...  
Keyword(s):  
Sandy Soils ◽  
Weather Conditions ◽  
Climatic Conditions ◽  
Water Requirement ◽  
The State ◽  
Climatic Suitability ◽  
Irrigation Water Requirement ◽  
Productive Potential ◽  
Shallow Soils ◽  
Water Holding

ABSTRACT This study aimed to define areas suitable, and the irrigation water requirement for, cultivation of Tanzania guineagrass in the state of Ceará, Brazil. Tanzania guineagrass yield was estimated by a mathematical model, which considers the crop actual evapotranspiration, resulting from the crop climatological water balance. The water requirement throughout the year was estimated for soils with a water holding capacity of 20 (shallow soils), 40 (sandy soils), 60 (soils with medium texture) and 100 mm (clay soils). The relative frequency of occurrence of monthly productions greater than 2,750 kg DM ha-1 month-1 was obtained for different areas in Ceará, representative of most of the state's economic mesoregions. Tanzania guineagrass annual yields in the state of Ceará were between 20,000-30,000 kg DM ha-1 year-1. During the rainy season, the productive potential varies with the economic mesoregion, which presents different climatic conditions. The state of Ceará is only suitable for the rainfed production of Tanzania guineagrass for 4 months each year, predominantly from February to May, while weather conditions do not favor the development of this grass in the remaining months.

scholarly journals Risk Analysis and Management of Moored Ships in Ports

2018 ◽  
Author(s):  
Liliana V. Pinheiro ◽  
Conceição J. E. M. Fortes ◽  
João A. Santos
Keyword(s):  
Integrated Management ◽  
Warning System ◽  
Weather Conditions ◽  
Complete Information ◽  
Decision Makers ◽  
Modular System ◽  
Economic Losses ◽  
Sea Waves ◽  
Bad Weather ◽  
Port Areas

The risks associated with mooring of ships are a major concern for port and maritime authorities. Sea waves and extreme weather conditions can lead to excessive movements of vessels and mooring loads affecting the safety of ships, cargo, passengers, crew or port infrastructures. Normally, port activities such as ships’ approach manoeuvres and loading/unloading operations, are conditioned or suspended based solely on weather or wave forecasts, causing large economic losses. Nevertheless, it has been shown that some of the most hazardous events with moored ships happen on days with mild sea and wind conditions, being the culprit long waves and resonance phenomena. Bad weather conditions can be managed with an appropriate or reinforced mooring arrangement. A correct risk assessment must be based on the movements of the ship and on the mooring loads, taking into account all the moored ship’s system. In this paper, the development of a forecast and warning system based on the assessment of risks associated with moored ships in port areas, SWAMS ALERT, is detailed. This modular system can be scaled and adapted to any port, providing decision-makers with accurate and complete information on the behaviour of moored ships, movements and mooring loads, allowing a better planning and integrated management of port areas.

scholarly journals Sensing Technology Survey for Obstacle Detection in Vegetation

2021 ◽  
Vol 1 (3) ◽  
pp. 672-685
Author(s):  
Shreya Lohar ◽  
Lei Zhu ◽  
Stanley Young ◽  
Peter Graf ◽  
Michael Blanton
Keyword(s):  
Autonomous Vehicles ◽  
Weather Conditions ◽  
Climatic Conditions ◽  
Obstacle Detection ◽  
Agricultural Field ◽  
Thermal Camera ◽  
Agricultural Vehicles ◽  
Sensing Systems ◽  
Sensing Technology ◽  
Hyperspectral Sensing

This study reviews obstacle detection technologies in vegetation for autonomous vehicles or robots. Autonomous vehicles used in agriculture and as lawn mowers face many environmental obstacles that are difficult to recognize for the vehicle sensor. This review provides information on choosing appropriate sensors to detect obstacles through vegetation, based on experiments carried out in different agricultural fields. The experimental setup from the literature consists of sensors placed in front of obstacles, including a thermal camera; red, green, blue (RGB) camera; 360° camera; light detection and ranging (LiDAR); and radar. These sensors were used either in combination or single-handedly on agricultural vehicles to detect objects hidden inside the agricultural field. The thermal camera successfully detected hidden objects, such as barrels, human mannequins, and humans, as did LiDAR in one experiment. The RGB camera and stereo camera were less efficient at detecting hidden objects compared with protruding objects. Radar detects hidden objects easily but lacks resolution. Hyperspectral sensing systems can identify and classify objects, but they consume a lot of storage. To obtain clearer and more robust data of hidden objects in vegetation and extreme weather conditions, further experiments should be performed for various climatic conditions combining active and passive sensors.

Sign in / Sign up

Export Citation Format

Share Document