Automatic Detection of Surface Damage on Forest Roads Using Mobile LiDAR and GIS Processing Tools

Roughness is a dynamic property of the gravel road surface that affects safety, ride comfort as well as vehicle tyre life and maintenance costs. A rapid survey of gravel road condition is fundamental for an effective maintenance planning and definition of the intervention priorities.Different non-contact techniques such as laser scanning, ultrasonic sensors and photogrammetry have recently been proposed to reconstruct three-dimensional topography of road surface and allow extraction of roughness metrics. The application of Microsoft Kinect™ depth camera is proposed and discussed here for collection of 3D data sets from gravel roads, to be implemented in order to allow quantification of surface roughness.The objectives are to: i) verify the applicability of the Kinect sensor for characterization of different forest roads, ii) identify the appropriateness and potential of different roughness parameters and iii) analyse the correlation with vibrations recoded by 3-axis accelerometers installed on different vehicles. The test took advantage of the implementation of the Kinect depth camera for surface roughness determination of 4 different forest gravel roads and one well-maintained asphalt road as reference. Different vehicles (mountain bike, off-road motorcycle, ATV vehicle, 4WD car and compact crossover) were included in the experiment in order to verify the vibration intensity when travelling on different road surface conditions. Correlations between the extracted roughness parameters and vibration levels of the tested vehicles were then verified. Coefficients of determination of between 0.76 and 0.97 were detected between average surface roughness and standard deviation of relative accelerations, with higher values in the case of lighter vehicles.

Autonomous road surface following on forest roads by mobile robots and forestry vehicles carrying large logs is required for work in the forestry industry. In such situations, the detection of a passable road surface has to respond to changes in road geometry, surface conditions, and lighting. In this paper, we propose an efficient road detection method using LiDAR-SLAM and U-Net architectures: LiDAR-SLAM can accurately estimate the shape of the road in response to environmental changes, while U-Net architectures can efficiently estimate the edge of the road in a forest road. In the experiment, we used IoU (Intersection over Union) to evaluate the accuracy of the road surface detection in passing through a forest road. As a result, the proposed method achieved an IoU value of more than 90.2%.

Forest roads are treeless strips of land without any natural cover, appropriately shaped in a longitudinal and transverse direction, along which traffic is possible. Road embankments and surfaces are made of proper materials, with the preservation of technological requirements and particular attention to the density of subbases in the road construction. Surface water runoff occurs on all roads as a result of rainfall, because material density of the surface hinders or blocks the infiltration and the road gradient causes the water movement. Precipitation intensity and ground filtration capacity determine the runoff quantity. In forest areas, the surface runoff basically occurs on road surfaces and timber depots, while outside those sites, it rarely occurs in natural and not devastated areas. The paper presents the results of measurements of the surface-runoff intensity from forest dirt roads along several surveyed sections. Some sections were characterised by a high escarpment of the excavation and cross-cut canal for subsurface runoff. The unit intensity from measurement sessions of various precipitation levels was presented, as well as those from the period of snow cover melting. Measurements were taken every 15 minutes. On the basis of these measurements, simulation calculations of the amount of water were performed assuming the homogeneity of the area, the road network and precipitation characteristics, which can occur in the form of surface runoff on forest roads with similar characteristics, in the area of 100 ha, with the road network density of 15 m·ha-1 and 25 m·ha-1, during the precipitation lasting 3 h. These values were referred to the total water quantity from such precipitation and compared with the standard water consumption by an average consumer.

Landslides, which usually occur in mountainous and hilly areas, occur as a result of the soil or rock material forming a slope moving down under the influence of gravity. Forested areas, mostly in mountainous regions, are susceptible to landslides. Forest roads are important infrastructure facilities to protect forest resources and to achieve sustainable management objectives. Forest roads provide many benefits such as facilitating the transportation of wood raw materials, preventing fires and providing access to areas where recreational activities are carried out. However, inappropriately opened forest roads in forest areas cause problems such as landslides, which cause both serious destruction of road networks and serious deformations in forest areas. Landslide-prone forest roads also cause serious economic losses due to disruption of product transport and road maintenance costs. Within the scope of this study, landslide susceptibility maps (LSMs) were produced to determine the relationship between landslides and landslide-causing factors in Handüzü Forest Management Unit of Kastamonu Regional Directorate of Forestry (KRDF) located in the Central Black Sea Region of Türkiye. Land use, altitude, slope, aspect, plan and profile curvature, topographic wetness index (TWI), distance to forest road, drainage networks and fault, crown closure and lithology were used as conditioning factors in the study. Logistic Regression (LR) and Support Vector Machine (SVM) based machine learning models were used to generate LSMs. The receiver operating characteristics (ROC) curve and area under the ROC curve (AUC) method were used to compare the performance of landslide susceptibility models. In the accuracy assessment using the prediction rate curve, the AUC value was 0.968 for the SVM model and 0.668 for the LR model. The AUC values confirmed that SVM performed much better than LR. In addition, the susceptibility of newly planned forest roads (not currently available in the field) in LSMs were determined in the study. As a result of the study, it was determined that the most effective factors affecting landslides in Handüzü Forest Management Directorate are distance to forest roads and drainage networks. In the analyses, it was found that 28.28% of the existing forest roads in the LSM produced with SVM and 56.57% in the LSM produced with LR were found to be in »high« and »very high« landslide susceptible areas. Similarly, 38.43% of the newly planned roads in the LSM produced with SVM and 52.23% in the LSM produced with LR were found to be in »high« and »very high« landslide susceptible areas. These findings showed that forest roads are the main factor in the occurrence of landslides in the study area. Therefore, taking LSMs into account in the planning of forest roads will contribute to reducing the damages that may occur in forest areas due to landslides.

Adverse road condition is the main cause of traffic accidents. Road surface condition recognition based on video image has become a central issue. However, hybrid road surface and road surface under different lighting environments are two crucial problems. In this paper, the road surface states are categorized into 5 types including dry, wet, snow, ice, and water. Then, according to the original image size, images are segmented; 9-dimensional color eigenvectors and 4 texture eigenvectors are extracted to construct road surface state characteristics database. Next, a recognition method of road surface state based on SVM (Support Vector Machine) is proposed. In order to improve the recognition accuracy and the universality, a grid searching algorithm and PSO (Particle Swarm Optimization) algorithm are used to optimize the kernel function factor and penalty factor of SVM. Finally, a large number of actual road surface images in different environments are tested. The results show that the method based on SVM and image segmentation is feasible. The accuracy of PSO algorithm is more than 90%, which effectively solves the problem of road surface state recognition under the condition of hybrid or different video scenes.

The specific way in which a forest road is designed affects the management in the forest environment and timber transport. The aim of this study was to find out whether an inclusion of the ecological criterion in the forest road design will change the parameter of the longitudinal gradient of forest hauling roads and whether these changes will have an effect on the accessibility of forest stands by timber hauling machinery. The possible changes in the longitudinal gradient can also affect the technology of forest road surfacing and the selection of the appropriate surface type. We can state that an inclusion of the ecological criterion in the forest road network design will bring statistically significant changes in longitudinal gradients of forest hauling roads. The mean longitudinal gradient of the current forest road network is 2.82 % and the mean longitudinal gradient of the forest road network designed with inclusion of the ecological criterion is 4.82 %. The results show statistically significant changes in the longitudinal parameters of forest hauling roads. However, it will not bring a need for a change in construction technology, and will not affect the accessibility of forest stands by timber hauling machinery.

Detection of damages in fibre reinforced plastic (FRP) composite structures is important from the safety and serviceability point of view. Usually, damage is realized as a local reduction of stiffness and if dynamic responses of the structure are sensitive enough to such changes in stiffness, then a well posed inverse problem can provide an efficient solution to the damage detection problem. Usually, such inverse problems are solved within the framework of pattern recognition. Support Vector Machine (SVM) Algorithm is one such methodology, which minimizes the weighted differences between the experimentally observed dynamic responses and those computed using the finite element model- by optimizing appropriately chosen parameters, such as stiffness. A damage detection strategy is hereby proposed using SVM which perform stepwise by first locating and then determining the severity of the damage. The SVM algorithm uses simulations of only a limited number of damage scenarios and trains the algorithm in such a way so as to detect damages at unknown locations by recognizing the pattern of changes in dynamic responses. A rectangular fiber reinforced plastic composite plate has been investigated both numerically and experimentally to observe the efficiency of the SVM algorithm for damage detection. Experimentally determined modal responses, such as natural frequencies and mode shapes are used as observable parameters. The results are encouraging since a high percentage of damage cases have been successfully determined using the proposed algorithm.

Detection of forest road damage using mobile laser profilometry

The life and robustness of forest roads depend on their protection from the harmful effects of water coming into the road surface. In particular, the deterioration of the road surface affects the safe navigation of vehicles and traffic safety. This situation requires that the surface be stable on forest roads. The aim of the study is to examine whether surface deterioration (erosion and accumulation) on forest roads due to the drainage problem of water falling on the road surface can be minimized by open-top culverts and to determine their effectiveness. These are used in three separate trial blocks every 25 m (A parcels; total of 3 parcels), every 50 m (B parcels; total of 3 parcels) and control block (C). Volumetric erosion and accumulation in these blocks was compared by UAV for about 3 years and the effectiveness of the open-top culverts was examined by this method. A 500 m section of the forest road coded 001 of the Kardüz Forest Operations Directorate (Düzce/Türkiye) was examined in the study. As a result, erosion and accumulation in all blocks have been found to have a dynamic course. It was determined that this mobility was greater in the control block than in the blocks with open-top culverts installed at intervals of 25 m and 50 m. The mean Z values for the blocks showed that the deterioration in the control block (C) was higher than in the blocks with 25 m and 50 m open culverts. The volumetric deterioration rate was 5 times higher in the control block than in the block installed at 25 m interval (A plots) and 2 times higher than in the block installed at 50 m interval (B plots). Similarly, the areal deterioration rate was 3.3 times higher in the control block than in the block installed at 25 m interval (A plots) and 1.4 times higher than in the block installed at 50 m interval (B plots). These results showed the effectiveness of open-top culverts and it was also determined that the open-top culverts installed at 25 m intervals were more effective than the open-top culverts established at 50 m intervals. In addition, according to the statistical analysis, a statistically significant difference was found between the erosion volume in the blocks. Open-top culverts should be used against forest road surface deterioration and UAV technology should be used for deterioration detection.

According to statistics from the Global Burden of Cancer Study (Globocon) of the World Health Organization (WHO), cancer, particularly breast cancer, is a severe health issue in Indonesia with 68,858 new cases and 22,000 deaths recorded in 2020. Ultrasonography (USG) technology is acknowledged as one of the potentials to support early detection, which is vital in reducing mortality from breast cancer. This study focuses on classifying ultrasound images using the Support Vector Machine (SVM) algorithm, GLCM feature extraction, Min-Max normalization, and Mutual Information with SelectKBest Feature Selection. From several experiments using the SVM algorithm with various combinations of parameter values that have been set and different Tests, namely using a Train/Test Split with a proportion of 80/20 and K-Fold Cross Validation, it shows that the SVM algorithm is capable of classifying ultrasound images of breast cancer. into two categories (Benign Tumor and Malignant Tumor) with the same maximum accuracy of 79% after applying the SMOTE Balancing Data technique or without using the Balancing Data technique. As a result, the Support Vector Machine (SVM) algorithm has the potential to be an effective model for identifying breast cancer ultrasound images, both on data from the original set that has not been balanced and data from the set that has been balanced.

Credit is the main product of savings and loan cooperatives to increase profitability. The greater the credit issued, the greater the benefits obtained by cooperatives. Each cooperative will package credit products in such a way as to attract the attention of every customer. However, cooperatives can find problems in the process of lending, such as the “Daruzzakah Rensing” Cooperative located in “Desa Rensing, Kecamatan Sakra Barat, Lombok Timur-NTB-Indonesia”. The main products of the Cooperative “Daruzzakah Rensing” are savings and loans. In distributing credit, the cooperative always decides based on statistical data. This data is sometimes not useful if the supporting methods used to predict and classify the data are not appropriate. Therefore, this research requires a method that can classify and predict problematic and non-problematic customers. To answer this question, using the SVM (Support Vector Machine) algorithm to find out the level of accuracy in analyzing creditworthiness proposed by prospective debtors. The SVM algorithm is used to predict, classify, evaluate, and analyze credit. From the results of data processing carried out using the SVM algorithm (Support Vector Machine), it can be categorized as an excellent method, with an accuracy of 90.42% and AUC at 0.957. Accuracy of 90.42% means the SVM algorithm can provide decisions about feasible or not feasible in granting credit to customers who apply for loans.

Gene splicing site recognition is a very important research topic in smart healthcare. Gene splicing site recognition is of great significance, not only for the large-scale and high-quality computational annotation of genomes but also for the analysis and recognition of the gene sequences evolutionary process. It is urgent to study a reliable and effective algorithm for gene splice site recognition. Traditional Twin Support Vector Machine (TWSVM) algorithm has advantages in solving small-sample, nonlinear, and high-dimensional problems, but it cannot deal with parameter selection well. To avoid the blindness of parameter selection, particle swarm optimization algorithm was used to find the optimal parameters of twin support vector machine. Therefore, a Particle Swarm Optimization Twin Support Vector Machine (PSO-TWSVM) algorithm for gene splicing site recognition was proposed in this paper. The proposed algorithm was compared with traditional Support Vector Machine algorithm, TWSVM algorithm, and Least Squares Support Vector Machine algorithm. The comparison results show that the positive sample recognition rate, negative sample recognition rate, and correlation coefficient (CC) of the proposed algorithm are the best among the four different support vector machine algorithms. The proposed algorithm effectively improves the recognition rate and the accuracy of splice sites. The comparison experiments verify the feasibility of the proposed algorithm.

Forest road construction for harvest operation are always been subjected to certain constrictions and limitations. Engineering practices on forest road alignment are hindered by costly environmental and operational assessment. GIS tools and related data such as remote sensing allows in allocating suitable access road by taking consideration of environmental and cost implication. The aim of this study is to present the method of integration of remote sensing data and GIS in allocating access road for forest harvesting using best path modeling. Therefore, the specific objectives of this study are to allocate the optimal forest roads network in forest operation, and to determine the density of forest road network. Allocating the best paths for forest road access for timber harvesting is a problem that can be solved by computer based approaches using spatial modeling. Spatial modeling is used to compute the indicative factors that suit road allocation. The model developed and designed using GIS to propose feasibility forest road allocation in the hill area. The method was designed to produce road layouts taking topographical features and forest environmental constraints into special consideration. In this study, four grid themes influencing the road construction were identified; elevation, slope, barrier of lake and distance to existing roads. The total of access road aligned and proposed in the respective area was 28,745.35m. Meanwhile the overall density calculated in selected compartments was about 9.93m/ha (0.80%). The densities of road paths presented here were achieved below as outlined by the forestry department. Thus, there is potential to reduce damage to the residual stand and to the ground area disturbance by the harvesting operation. The forest road alignment and information in this study provides an initial foundation on which GIS can be used for this kind of analysis in forest road planning. The result is not only associated with forest transportation, but at the same time is useful to identify a risk of road construction to the environment. This revealed that the minimum density of forest road construction can help mitigate the loss of ecological services of tropical forest subject to logging pressure and lead to greater financial benefit in future operations.

Corrosion fatigue effects on life estimation of deteriorated bridges under vehicle impacts

The objective of the present paper is to confirm or reject the possible use of recycled asphalt to reinforce forest haul roads regarding the technical requirements set by the standards and directives relevant to the construction of forest road surfaces. The hypothesis is based on the presumption that recycled materials, if correctly used, can reach the same construction properties as standard materials, hence their application does not have a negative effect on reinforcement quality. On a selected stretch of forest road, three test sections were constructed with the use of recycled asphalt, however, each of them with a different technological solution. The first section was reinforced with unbound mixture – Type1 without added water, the second section was constructed using a version of vibrated macadam technology, and recycled asphalt was applied to the third section by the method of basic compacting. In each of the sections, tacheometric cross profile measurement was carried out at monthly intervals to monitor the changes in the cross profile shape, and the number of passages of fully loaded logging trucks was registered; static load tests were performed at pre-defined time intervals to determine the deformation moduli such as deformation characteristics of the road surface structural layers. In all three reinforcement versions, the values of deformation moduli observed during the static load tests were between 68–90 % of the values set by relevant standards for these technologies using natural aggregates. However, the tacheometric measurements did not reveal statistically significant changes in the shape of the reinforcement cross-section. Based on the obtained results, applying recycled asphalt to reinforce forest roads seems to be a suitable alternative to natural quarry aggregate used in unbound structural layers. Recycled material needs to meet the regulatory limits for foreign elements and pass ecotoxicity tests, which is evidenced by a certificate on material compliance issued by the test laboratory.