SFA-Net: A Selective Features Absorption Network for Object Detection in Rainy Weather Conditions

The computer vision systems driving autonomous vehicles are judged by their ability to detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing this ability of a self-driving car to distinguish between the elements of its environment under adverse conditions is an important challenge in computer vision. For example, poor weather conditions like fog and rain lead to image corruption which can cause a drastic drop in object detection (OD) performance. The primary navigation of autonomous vehicles depends on the effectiveness of the image processing techniques applied to the data collected from various visual sensors. Therefore, it is essential to develop the capability to detect objects like vehicles and pedestrians under challenging conditions such as like unpleasant weather. Ensembling multiple baseline deep learning models under different voting strategies for object detection and utilizing data augmentation to boost the models’ performance is proposed to solve this problem. The data augmentation technique is particularly useful and works with limited training data for OD applications. Furthermore, using the baseline models significantly speeds up the OD process as compared to the custom models due to transfer learning. Therefore, the ensembling approach can be highly effective in resource-constrained devices deployed for autonomous vehicles in uncertain weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and were able to identify objects from the images captured in the adverse foggy and rainy weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and reached 32.75% mean average precision (mAP) and 52.56% average precision (AP) in detecting cars in the adverse fog and rain weather conditions present in the dataset. The effectiveness of multiple voting strategies for bounding box predictions on the dataset is also demonstrated. These strategies help increase the explainability of object detection in autonomous systems and improve the performance of the ensemble techniques over the baseline models.

Download Full-text

Winter Wheat Straw Decomposition under Different Nitrogen Fertilizers

Agriculture ◽

10.3390/agriculture11020083 ◽

2021 ◽

Vol 11 (2) ◽

pp. 83

Author(s):

Gabriela Mühlbachová ◽

Pavel Růžek ◽

Helena Kusá ◽

Radek Vavera ◽

Martin Káš

Keyword(s):

Winter Wheat ◽

Wheat Straw ◽

Soil Surface ◽

Weather Conditions ◽

Mineral Nitrogen ◽

Nitrogen Fertilizers ◽

Pig Slurry ◽

Straw Decomposition ◽

Rainy Weather ◽

N Fertilisers

The climate changes and increased drought frequency still more frequent in recent periods bring challenges to management with wheat straw remaining in the field after harvest and to its decomposition. The field experiment carried out in 2017–2019 in the Czech Republic aimed to evaluate winter wheat straw decomposition under different organic and mineral nitrogen fertilizing (urea, pig slurry and digestate with and without inhibitors of nitrification (IN)). Treatment Straw 1 with fertilizers was incorporated in soil each year the first day of experiment. The Straw 2 was placed on soil surface at the same day as Straw 1 and incorporated together with fertilizers after 3 weeks. The Straw 1 decomposition in N treatments varied between 25.8–40.1% and in controls between 21.5–33.1% in 2017–2019. The Straw 2 decomposition varied between 26.3–51.3% in N treatments and in controls between 22.4–40.6%. Higher straw decomposition in 2019 was related to more rainy weather. The drought observed mainly in 2018 led to the decrease of straw decomposition and to the highest contents of residual mineral nitrogen in soils. The limited efficiency of N fertilisers on straw decomposition under drought showed a necessity of revision of current strategy of N treatments and reduction of N doses adequately according the actual weather conditions.

Download Full-text

Hubungan Shalat Fardu Berjamaah Dengan Kecerdasan Emosional Pada Jamaah Mesjid Al Jihad Banjarmasin

Jurnal Studia Insania ◽

10.18592/jsi.v5i1.1327 ◽

2017 ◽

Vol 5 (1) ◽

pp. 25

Author(s):

Ahmad Jauhari ◽

Asmaran AS ◽

Siti Faridah

Keyword(s):

Emotional Intelligence ◽

Weather Conditions ◽

Technical Data ◽

Rainy Weather ◽

The Face ◽

Qualitative Descriptive ◽

Distance Difference ◽

Stress Burden ◽

Heart And Mind ◽

Relationship Of

Al Jihad Mosque Banjarmasin is a mosque that is identical with Muhammadiyah, this mosque is followed by many pilgrims and loyal at the time of the implementation of prayers fardu congregation. Jamaah consists of various groups regardless of background, both in terms of age, economy, organization and even the sick pilgrims (post-stroke) are actively involved in congregation. Active Jamaat prayers in congregation do not only come from residents around the mosque complex, but also many pilgrims who come from outside the mosque complex, even the distance difference between their residence with the mosque a few kilometers. In heavy rainy weather conditions, they still enthusiastically follow the prayers in congregation fardu mosque. In addition, there are things that are felt by pilgrims such as comfort, tranquility of heart and mind, emotional stability, silaturrahim which all is related to emotional intelligence.In this study, the main problem is how is the relationship of prayer in congregation with emotional intelligence in the congregation of Al Jihad Mosque Banjarmasin ?. The method used is quantitative and qualitative descriptive method with methodological arrangement such as approach and type of research, research location, population and sample, data and data source, procedure and data collection, quantitative and qualitative technical data analysis.The result of the study found that there is a correlation between salat fardu congregation with emotional intelligence, this is proved by the data from questionnaires from 30 pilgrims (respondents) that is: able to control the impulse of worldly lusts with the highest opinion is 60% said yes and 40% stated sometimes .Motivating yourself with the highest opinion is 90% states yes and 10% states sometimes. Able to survive in the face of trials with the highest opinion is 86.67 states yes and 13, 33 states sometimes. No exaggeration with the highest opinion is 90% states yes and 10% states sometimes. Being able to set the mood with the highest opinion is 86.33% and 13.33 states sometimes. Keeping the stress burden does not cripple the thinking ability with the highest opinion is 90% states yes and 10% states sometimes. The ability to empathize and pray with the highest opinion is 90% say yes and 10% say sometimes.

Download Full-text

Improving the transfer learning performances in the classification of the automotive traffic roads signs

E3S Web of Conferences ◽

10.1051/e3sconf/202123400064 ◽

2021 ◽

Vol 234 ◽

pp. 00064

Author(s):

Anass Barodi ◽

Abderrahim Bajit ◽

Mohammed Benbrahim ◽

Ahmed Tamtaoui

Keyword(s):

Transfer Learning ◽

Intelligent System ◽

Confusion Matrix ◽

Weather Conditions ◽

Classification Model ◽

Road Signs ◽

Road Sign ◽

Rainy Weather ◽

Depth Analysis ◽

Driving Assistance

This paper represents a study for the realization of a system based on Artificial Intelligence, which allows the recognition of traffic road signs in an intelligent way, and also demonstrates the performance of Transfer Learning for object classification in general. When systems are trained on the aspects of human visualization (HVS), which helps or generates the same decisions, the construct robust and efficient systems. This allows us to avoid many environmental risks, both for weather conditions, such as cloudy or rainy weather that causes obscured vision of signs, but the main objective is to avoid all road risks that are dangerous to achieve road safety, such as accidents due to non-compliance with traffic rules, both for vehicles and passengers. However, simply collecting road signs in different places does not solve the problem, an intelligent system for classifying road signs is needed to improve the safety of people in its environment. This study proposed a traffic road sign classification system that extracts visual characteristics from a Convolution Neural Network (CNN) classification model. This model aims to assign a class to the image of the road sign through the classifier with the most efficient optimized. Then the evaluation of its effectiveness according to several criteria, using the Confusion Matrix and the classification report, with an in-depth analysis of the results obtained by the images that are taken from the urban world. The results obtained by the system are encouraging in comparison with the systems developed in the scientific literature, for example, the Advanced Driving Assistance Systems (ADAS) of the sector automobile.

Download Full-text

Net ecosystem exchange and energy fluxes in a West Siberian bog

10.5194/acp-2017-43 ◽

2017 ◽

Author(s):

Pavel Alekseychik ◽

Ivan Mammarella ◽

Dmitry Karpov ◽

Sigrid Dengel ◽

Irina Terentieva ◽

...

Keyword(s):

Net Ecosystem Exchange ◽

Bowen Ratio ◽

Heavy Rain ◽

West Siberia ◽

Weather Conditions ◽

Middle Taiga ◽

Energy Budgets ◽

Co2 Uptake ◽

Surface Exchange ◽

Rainy Weather

Abstract. Very few studies of ecosystem-atmosphere exchange involving eddy-covariance data have been conducted in Siberia, and none in West Siberia. This work provides the first estimates of carbon dioxide (CO2) and energy budgets at a typical bog of the West Siberian middle taiga based on May-August measurements in 2015. The footprint of measured fluxes consisted of homogeneous mixture of tree-covered ridges and hollows with the vegetation represented by typical sedges and shrubs. Generally, the surface exchange rates resembled those of pine-covered bogs elsewhere. The surface energy balance closure was 90 %. Net CO2 uptake was comparatively high, summing up to 196 gC m−2 for the four measurement months, while the Bowen ratio was typical at 30 %. The ecosystem turned into a net CO2 source during several front passage events in June and July. Several periods of heavy rain helped keep the water table at a constant level, preventing a usual drawdown in summer. However, because of the cloudy and rainy weather, the observed fluxes might rather represent the special weather conditions of 2015 than their typical level.

Download Full-text

Perception of Natural Hazards in Rural Areas: A Case Study Examination of the Influence of Seasonal Weather

Sustainability ◽

10.3390/su12062251 ◽

2020 ◽

Vol 12 (6) ◽

pp. 2251 ◽

Cited By ~ 1

Author(s):

Rodrigo Rudge Ramos Ribeiro ◽

Samia Nascimento Sulaiman ◽

Michelle Bonatti ◽

Stefan Sieber ◽

Marcos Alberto Lana

Keyword(s):

Natural Hazards ◽

Rural Areas ◽

Secondary Data ◽

Weather Conditions ◽

Primary Data ◽

Rainy Weather ◽

The Social ◽

Time Of Year ◽

Ranking Order

A series of factors affect the social perception of hazards in a rural context. This article analyzes how weather conditions influence farmers’ perceptions of natural hazards. In order to understand the relationship between time of year/season and farmers’ concerns about hazards, this study was undertaken. The methodology was based on surveys done to obtain a base-collection of primary data, as well as a meteorological and production analysis using secondary data. A case study of small coffee farms was carried out in a Brazilian municipality with questionnaires applied during the dry season in 2016 and the rainy season in 2017. The results indicate that drought is the main hazard identified by farmers in both weather seasons. Although there were some changes in perceptions observed, the ranking order of the main hazards did not change over the dry and rainy weather seasons.

Download Full-text

Discovering Insightful Rules among Truck Crash Characteristics using Apriori Algorithm

Journal of Advanced Transportation ◽

10.1155/2020/4323816 ◽

2020 ◽

Vol 2020 ◽

pp. 1-16 ◽

Cited By ~ 3

Author(s):

Jungyeol Hong ◽

Reuben Tamakloe ◽

Dongjoo Park

Keyword(s):

Risk Factors ◽

Association Rules ◽

Weather Conditions ◽

Parametric Models ◽

Apriori Algorithm ◽

Drowsy Driving ◽

Crash Data ◽

Rainy Weather ◽

Crash Characteristics ◽

Strength Of Association

This study aims to discover hidden patterns and potential relationships in risk factors in freight truck crash data. Existing studies mainly used parametric models to analyze the causes of freight vehicle crashes. However, predetermined assumptions and underlying relationships between independent and dependent variables have been cited as its limitations. To overcome these limitations and provide a better understanding of factors that lead to truck crashes on the expressways, we applied the Association Rules Mining (ARM) technique, which is a nonparametric method. ARM quantifies the interrelationships between the antecedents and consequents of truck-involved crashes and provides researchers with the most influential set of factors that leads to crashes. We utilized a freight vehicle-involved crash data consisting of 19,038 crashes that occurred on the Korean expressways from 2008 to 2017 for this investigation. From the data, 90,951 association rules were generated through ARM employing the Apriori algorithm. The lift values estimated by the Apriori algorithm showed the strength of association between risk factors, and based on the estimated lift values, we identified key crash contributory factors that lead to truck-involved crashes at various segment types, under different weather conditions, considering the driver’s age, crash type, driver’s faults, vehicle size, and roadway geometry type. From the generated rules, we demonstrated that overspeeding with medium-weight trucks was highly associated with crashes during the rainy weather, whereas drowsy driving during the evening was correlated with crashes during fine weather. Segment-related crashes were mainly associated with driver’s faults and roadway geometry. Our results present useful insights and suggestions that can be used by transport stakeholders, including policymakers and researchers, to create relevant policies that will help reduce freight truck crashes on the expressways.

Download Full-text

Optimized Single-Axis Schedule Solar Tracker in Different Weather Conditions

Energies ◽

10.3390/en13195226 ◽

2020 ◽

Vol 13 (19) ◽

pp. 5226

Author(s):

Nurzhigit Kuttybay ◽

Ahmet Saymbetov ◽

Saad Mekhilef ◽

Madiyar Nurgaliyev ◽

Didar Tukymbekov ◽

...

Keyword(s):

Rotation Angle ◽

Tracking System ◽

Weather Conditions ◽

Main Task ◽

Solar Panels ◽

Simple Method ◽

Solar Tracking ◽

Rainy Weather ◽

Solar Tracker ◽

One Year

Improving the efficiency of solar panels is the main task of solar energy generation. One of the methods is a solar tracking system. One of the most important parameters of tracking systems is a precise orientation to the Sun. In this paper, the performance of single-axis solar trackers based on schedule and light dependent resistor (LDR) photosensors, as well as a stationary photovoltaic installation in various weather conditions, were compared. A comparative analysis of the operation of a manufactured schedule solar tracker and an LDR solar tracker in different weather conditions was performed; in addition, a simple method for determining the rotation angle of a solar tracker based on the encoder was proposed. Finally, the performance of the manufactured solar trackers was calculated, taking into account various weather conditions for one year. The proposed single-axis solar tracker based on schedule showed better results in cloudy and rainy weather conditions. The obtained results can be used for designing solar trackers in areas with a variable climate.

Download Full-text

METAPHORICAL EXPRESSION IN MANADO MALAY

Journal of English Language and Literature Teaching ◽

10.36412/jellt.v5i1.2436 ◽

2021 ◽

Vol 5 (1) ◽

Author(s):

Kristian Rumengan ◽

Deane J. Wowor ◽

Tirza Kumayas

Keyword(s):

Qualitative Research ◽

Figurative Language ◽

Weather Conditions ◽

Qualitative Approach ◽

Connotative Meaning ◽

Descriptive Research ◽

Rainy Weather ◽

The Subject ◽

Metaphorical Expression ◽

Data Collections

The purpose of this study is to identify the metaphorical expression in Manado Malay and also to describe the meaning of those metaphors. Metaphor is a kind of figurative language which uses connotative meaning through the comparison without using the word “like” or “as”. Most of metaphorical expression comes from a human behavior. The subject consisted of speakers of Manado Malay particularly the researcher himself and those who lives in Wuwuk village. The writer used descriptive research. Qualitative research is the suitable method to analyze the metaphorical expression. The writer used qualitative approach to find the actual data about metaphorical expression, the data collections are in the form of words, pictures, rather than numbers. The result shows that there are 53 metaphorical expressions in Manado Malay commonly used in everyday speech. It can be indicate by through, human's behavior, human's characteristics, and feelings, such as “Putar bale” which means someone who is lie and “Bobou seho” which means someone who has drunk. Some other metaphor is used to describe a circumstance such as, “ujang kopi” which mean zenithal rain or refer to the hot rainy weather conditions. It is expected that many other researches could be conducted especially the problem which concerned with metaphorical expression. Studying language and it’s relation with metaphorical expression leave many question to answer. That is why, by conducting this research, other researchers can get some information about metaphorical expression in Manado Malay. Keywords: Metaphorical Expression; Manado Malay; Figurative Language

Download Full-text