scholarly journals KORELASI SPASIAL FREKUENSI KEBAKARAN HUTAN DAN LAHAN DENGAN AKTIVITAS MANUSIA: STUDI KASUS DI SUB SUB DAS RIAM KANAN PROVINSI KALIMANTAN SELATAN

2021 ◽  
Vol 9 (1) ◽  
pp. 131
Author(s):  
Susilawati ◽  
Syam’ani
Keyword(s):  
Spatial Correlation ◽  
Human Activities ◽  
Regression Models ◽  
Euclidean Distance ◽  
Fire Occurrence ◽  
Common Phenomenon ◽  
Land Uses ◽  
The Road ◽  
Drastic Increase ◽  
Single Regression

Forest and land fires are a common phenomenon in several regions of Indonesia. It is assumed that most of the forest and land fires originate from human activities. This study aims to statistically test the spatial correlation between the number of hotspots or the frequency of forest and land fires, to the distance from various types of landuse in the Riam Kanan sub-watershed. The data used in this study are landuse and hotspot data. The spatial correlation analysis in this study was conducted using Euclidean Distance and single regression. Euclidean Distance is used to measure the flat distance between the fire location and the location of human activities. Meanwhile, single regression is used to measure the correlation between the number of fire occurrence points and the flat distance from the location of human activities. The single regression models used are linear, power, exponential, logarithmic, and polynomial. The results showed that the frequency of forest and land fires had a very strong spatial correlation with human activities, especially in the sub-watershed area of Riam Kanan. So it can be stated that the frequency of forest and land fires does have a strong correlation with human activities. The lowest spatial correlation is the distance from the rice fields, and the highest spatial correlation is the distance from the river. However, the number of hotspots increases drastically the more distance it is from the road, and almost approaches zero the farther the road is. Thus, although the spatial correlation with roads is not as high as other land uses, this drastic increase in the number of hotspots indicates that road accessibility has a strong contribution to forest and land fires.

scholarly journals Urbanization and Human Population Favor Species Richness of Alien Birds

Diversity ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 72
Author(s):  
Maria Lazarina ◽  
Mariana A. Tsianou ◽  
Georgios Boutsis ◽  
Aristi Andrikou-Charitidou ◽  
Elpida Karadimou ◽  
...  
Keyword(s):  
Species Richness ◽  
Alien Species ◽  
Human Activities ◽  
Native Species ◽  
Human Population ◽  
Generalized Additive Models ◽  
Additive Models ◽  
Land Uses ◽  
Time Periods ◽  
Native Species Richness

Human activities like urbanization and agriculture affect spatial biodiversity patterns. The presence and activities of humans richly benefit alien species, but native species usually decline in human-impacted areas. Considering that the richness of alien and native species are inter-related, we explored the effect of human population density, human-related land uses (agricultural and urban), and natural land area on avian (alien and native) species richness of Massachusetts for two time periods using Generalized Additive Models. Avian alien species richness increased with native species richness in both time periods. Despite the predominant role of native species richness as a major driver of alien species richness, human activities play an important additional role in shaping species richness patterns of established aliens. Human-related land uses (urban and agricultural) and human population favored alien species richness in both time periods. Counter to expectations, human activities were also positively associated to native avian species richness. Possible explanations of these patterns may include habitat heterogeneity, increased availability of resources, and reduced predation risk.

scholarly journals Speed Distribution Prediction of Freight Vehicles on Mountainous Freeway Using Deep Learning Methods

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Yuren Chen ◽  
Yu Chen ◽  
Bo Yu
Keyword(s):  
Deep Learning ◽  
Regression Models ◽  
Safety Evaluation ◽  
Learning Method ◽  
The Road ◽  
Speed Distribution ◽  
Driving Speed ◽  
Road Geometry ◽  
Speed Prediction ◽  
Freight Vehicles

Driving speed is one of the most critical indicators in safety evaluation and network monitoring in freight transportation. Speed prediction model serves as the most efficient method to obtain the data of driving speed. Current speed prediction models mostly focus on operating speed, which is hard to reveal the overall condition of driving speed on the road section. Meanwhile, the models were mostly developed based on the regression method, which is inconsistent with natural driving process. Recurrent neural network (RNN) is a distinctive type of deep learning method to capture the temporary dependency in behavioral research. The aim of this paper is to apply the deep learning method to predict the general condition of driving speed in consideration of the road geometry and the temporal evolutions. 3D mobile mapping was applied to obtain road geometry information with high precision, and driving simulation experiment was then conducted with the help of the road geometry data. Driving speed was characterized by the bimodal Gauss mixture model. RNN and its variants including long short-term memory (LSTM) and RNN and gated recurrent units (GRUs) were utilized to predict speed distribution in a spatial-temporal dimension with KL divergence being the loss function. The result proved the applicability of the model in speed distribution prediction of freight vehicles, while LSTM holds the best performance with the length of input sequence being 400 m. The result can be related to the threshold of drivers’ information processing on mountainous freeway. Multiple linear regression models were constructed to be a contrast with the LSTM model, and the results showed that LSTM was superior to regression models in terms of the model accuracy and interpretability of the driving process and the formation of vehicle speed. This study may help to understand speed change behavior of freight vehicles on mountainous freeways, while providing the feasible method for safety evaluation or network efficiency analysis.

Improving the Self-Explaining Performance of Czech National Roads

2017 ◽  
Vol 2635 (1) ◽  
pp. 62-70 ◽  
Author(s):  
Jiří Ambros ◽  
Veronika Valentová ◽  
Ondřej Gogolín ◽  
Richard Andrášik ◽  
Jan Kubeček ◽  
...  
Keyword(s):  
Traffic Control ◽  
Regression Models ◽  
The Self ◽  
Crash Frequency ◽  
The Road ◽  
Horizontal Curves ◽  
Floating Car Data ◽  
Control Devices ◽  
National Road

Improving the road network according to the principles of self-explaining roads is a promising way to increase the level of safety; however, there are no universal guidelines on how to measure and improve the self-explaining performance of existing roads. To apply this approach on Czech national roads, the present study was conducted, consisting of five steps: ( a) automated segmentation into tangents and horizontal curves; ( b) collection of floating car data and calculation of speed; ( c) development of multivariate speed models for estimation of speed, including on segments not covered by floating car data; ( d) networkwide application of the models and evaluation of speed consistency, such as differences in speeds on tangents and following curves; and ( e) identification of substandard curves, and categorization and proposal of optimization for consistent placement of traffic control devices or reconstructions. The paper describes all the steps as well as several checks conducted along the way, such as comparison of profile speed and floating car speed, interpretation of regression models, and validation of predicted speed consistency against long-term average crash frequency. The methodology has been certified for use in practice and will be applied by the Czech national road agency.

scholarly journals IDENTIFIKASI KARAKTER PERMUKIMAN DI TIGA WILAYAH PEMBANGUNAN KABUPATEN BADUNG

2020 ◽  
Vol 14 (1) ◽  
pp. 76
Author(s):  
Anak Agung Keswari Krisnandika ◽  
Lury Sevita Yusiana ◽  
I Made Agus Dharmadiatmika ◽  
Mar’ie Abda U’Zal
Keyword(s):  
Land Use ◽  
Human Factors ◽  
Human Activities ◽  
Regional Policy ◽  
Rice Fields ◽  
Main Road ◽  
The Road ◽  
The North ◽  
Survey Results ◽  
Development Area

Badung Regency is a rapidly development area in Bali Province that caused by highly human activities. This development can be seen from the character of settlements in the are. Badung regency is divided into 3 development areas namely North Badung (sub-District Petang and Abiansemal), Middle Badung (sub-District Mengwi) and South Badung (sub-District Kuta Selatan, Kuta and Kuta Utara). The survey results on biophysical factors such as vegetation, land use, landforms and human factors i.e. land boundaries, patterns, infrastructure, and regional policy show that there are some different unique characteristics between these 3 development areas in Badung Regency. In general, landscapes of settlement in the North Badung are composed of linear housing along the main road but between houses tend to be separated by plantation area. Landscapes of settlement in the Middle Badung, consist of clustered housing along the road, with small access to the back of the house (rice fields) while, houses along the main road in the South Badung are shophouses and the residents' houses are clustered linear along small alley.

scholarly journals Trafic Signs Detection Based On Saliency Map Using Canny Edge

2018 ◽  
Vol 2 (1) ◽  
pp. 1
Author(s):  
Putri Alit Widyastuti Santiary ◽  
I Made Oka Widyantara ◽  
Rukmi Sari Hartati
Keyword(s):  
Edge Detection ◽  
Euclidean Distance ◽  
Exact Result ◽  
Saliency Map ◽  
Traffic Sign ◽  
Canny Edge Detection ◽  
Pixel Intensity ◽  
The Road ◽  
Road Sign ◽  
Canny Edge

This paper proposed Canny edge detection to detected saliency map on traffic sign. The edge detection functions by identifying the bounds from an object on an image. The edge of an image is an area that has a strong intensity of light.The pixel intensity of an image changes from low to high values or otherwise. Detecting the edge of an image significantly will decrease the amount of data and filters insignificant information by not deleting necessary structure from the image. The image used for this paper is a digital capture of a traffic sign with a background. The result of this study shows that Canny edge detection creates saliency map from the traffic sign and separates the road sign from the background. The image result tested by calculating the saliency distance between a tested image and trained image using normalized Euclidean distance. The value ofnormalized Euclidean distance is set between 0 to 2. The testing process is done by calculating the nearest distance between the tested vector features and trained vector features. From the examination as a whole, it can be concluded that road sign detection using saliency map model can be built by Canny edge detection. From the whole system examination, it resulted a accuracy value of 0,65. This value shows that the data was correctly classified by 65%. The precision value has an outcome of 0,64, shows that the exact result of the classification is 64%. The recall value has an outcome of 0,94. This value shows that the success rate of recognizing a data from the whole data is 94%.

Privacy Preserving for Location-Based Services in Road Networks

2014 ◽  
Vol 998-999 ◽  
pp. 1165-1168
Author(s):  
Kan Gong Liu ◽  
Jian Pei Zhang ◽  
Jing Yang
Keyword(s):  
Theoretical Analysis ◽  
Relative Position ◽  
Privacy Protection ◽  
Road Network ◽  
Euclidean Distance ◽  
Location Based Services ◽  
Experimental Results ◽  
Network Characteristics ◽  
The Road ◽  
Projection Distance

The existing road network privacy protection models do not consider the density of the user and the road length. To solve this problem, we propose a Euclidean distance-based road network privacy protection model. First, we put the projection distance of sections in the road network context as the actual distance between two users located in this section. For users in different sections, we put the sum of distance with respect to the length of sections as the relative position between them. Secondly, combining traditional anonymity models and road network characteristics, we propose the road network (k, l)-anonymous model and design algorithms to implement it. Finally, we use the experimental verify performance of the algorithm. Theoretical analysis and experimental results show that the algorithm is correct and effective.

scholarly journals Agricultural Monitoring Using Polarimetric Decomposition Parameters of Sentinel-1 Data

2021 ◽  
Vol 13 (4) ◽  
pp. 575 ◽  
Author(s):  
Katharina Harfenmeister ◽  
Sibylle Itzerott ◽  
Cornelia Weltzien ◽  
Daniel Spengler
Keyword(s):  
Multiple Regression ◽  
Plant Height ◽  
Regression Models ◽  
Alpha Angle ◽  
Growth Stages ◽  
Biophysical Parameters ◽  
Growth Variability ◽  
Multiple Regression Models ◽  
Temporal Profiles ◽  
Single Regression

The time series of synthetic aperture radar (SAR) data are commonly and successfully used to monitor the biophysical parameters of agricultural fields. Because, until now, mainly backscatter coefficients have been analysed, this study examines the potentials of entropy, anisotropy, and alpha angle derived from a dual-polarimetric decomposition of Sentinel-1 data to monitor crop development. The temporal profiles of these parameters are analysed for wheat and barley in the vegetation periods 2017 and 2018 for 13 fields in two test sites in Northeast Germany. The relation between polarimetric parameters and biophysical parameters observed in the field is investigated using linear and exponential regression models that are evaluated using the coefficient of determination (R2) and the root mean square error (RMSE). The performance of single regression models is furthermore compared to those of multiple regression models, including backscatter coefficients in VV and VH polarisation as well as polarimetric decomposition parameters entropy and alpha. Characteristic temporal profiles of entropy, anisotropy, and alpha reflecting the main phenological changes in plants as well as the meteorological differences between the two years are observed for both crop types. The regression models perform best for data from the phenological growth stages tillering to booting. The highest R2 values of the single regression models are reached for the plant height of wheat related to entropy and anisotropy with R2 values of 0.64 and 0.61, respectively. The multiple regression models of VH, VV, entropy, and alpha outperform single regression models in most cases. R2 values of multiple regression models of plant height (0.76), wet biomass (0.7), dry biomass (0.7), and vegetation water content (0.69) improve those of single regression models slightly by up to 0.05. Additionally, the RMSE values of the multiple regression models are around 10% lower compared to those of single regression models. The results indicate the capability of dual-polarimetric decomposition parameters in serving as meaningful input parameters for multiple regression models to improve the prediction of biophysical parameters. Additionally, their temporal profiles indicate phenological development dependent on meteorological conditions. Knowledge about biophysical parameter development and phenology is important for farmers to monitor crop growth variability during the vegetation period to adapt and to optimize field management.

scholarly journals ANALISA KEBERAGAMAN (DIVERSTY) TERHADAP IDENTITAS KOTA

2018 ◽  
Vol 9 (1) ◽  
pp. 107-112
Author(s):  
Iqbal Pulungta Bancin ◽  
Hilma Tamiami Fachrudin
Keyword(s):  
Qualitative Methods ◽  
Urban Area ◽  
Land Uses ◽  
The Public ◽  
The Road ◽  
Building Typology ◽  
The Difference ◽  
Characteristic Features ◽  
The City ◽  
Town Area

Urban area will not be separated from the diversity that is owned by the region. A wide variety of diverse elements or objects (buildings, monuments, squares, signs, or the historic old town area, etc.) will give the characteristic features or the identity of a city. The presence of identity on a city course will provide an overview of the place of the region and made the difference with other places. This research was conducted in the road corridor Pemuda, district of Medan Maimun with qualitative methods of observation to the study site for the study using elements of diversity with the aim to discover the diversity of research sites and how with regard to the identity of the city. From the observation there is diversity in terms of different land uses (the function of the building), building typology, activities and others thus creating an identity that can be recognized by the public.

Sign in / Sign up

Export Citation Format

Share Document