Deep Learning Based Car Damage Detection, Classification and Severity

In the accident insurance industry, settling the claim is a time-consuming process since it is a manual process and there is a gap between the optimal and the actual settlement. Using deep learning models, we are not only trying to speed up the process but also provide better customer service and increase the profitability of insurance companies. In this paper we are using various pretrained models such as VGG 16, VGG 19, Resnet50 and Densenet and based on these models, selecting the best performing models. We initially check whether the car is damaged or not using the Resnet50 model and if it’s a damaged one we use the WPOD-net model to detect the license plate. To identify the damaged region, we use the YOLO model. At last, comes the damage severity which is implemented using the Densenet model. After implementing various models, we find out that transfer learning gives better results than fine-tuning. In addition to that we propose a framework that integrates all of this into one application and in turn helps in the automation of the insurance industry

Linking National Immigration Data to Provincial Repositories: The case of Canada

BackgroundCanadian health data repositories link datasets at the provincial level, based on their residents’ registrations to provincial health insurance plans. Linking national datasets with provincial health care registries poses several challenges that may result in misclassification and impact the estimation of linkage rates. A recent linkage of a federal immigration database in the province of Manitoba illustrates these challenges. Objectivesa) To describe the linkage of the federal Immigration, Refugees and Citizenship Canada Permanent Resident (IRCC-PR) database with the Manitoba healthcare registry and b) compare data linkage methods and rates between four Canadian provinces accounting for interprovincial mobility of immigrants. MethodsWe compared linkage rates by immigrant’s province of intended destination (province vs. rest of Canada). We used external nationwide immigrant tax filing records to approximate actual settlement and obtain linkage rates corrected for interprovincial mobility. ResultsThe immigrant linkage rates in Manitoba before and after accounting for interprovincial mobility were 84.8% and 96.1, respectively. Linkage rates did not substantially differ according to immigrants’ characteristics, with a few exceptions. Observed linkage rates across the four provinces ranged from 74.0% to 86.7%. After correction for interprovincial mobility, the estimated linkage rates increased >10 percentage points for the provinces that stratified by intended destination (British Columbia and Manitoba) and decreased up to 18 percentage points for provinces that could not use immigration records of those who did not intend to settle in the province (New Brunswick and Ontario). ConclusionsDespite variations in methodology, provincial linkage rates were relatively high. The use of a national immigration dataset for linkage to provincial repositories allows a more comprehensive linkage than that of province-specific subsets. Observed linkage rates can be biased downwards by interprovincial migration, and methods that use external data sources can contribute to assessing potential selection bias and misclassification.

Beyond the Intention: Individual-Level Determinants and Intergenerational Differences of Floating Populations’ Actual Settlement Choices in Dongguan, China

The migration process and patterns of floating populations have received continuing attention from scholars and policymakers. In China, however, studies have been focused on the settlement intention of floating populations based on sampling surveys and yielded inconsistent findings. Drawing upon 18,178,167 authentic individual samples of floating populations in Dongguan city, this study contributes to the literature by examining the effect of individual characteristics on the actual resident actions of floating populations, and revealing both the heterogeneity and continuity of their urban residence among four generations (i.e., during the 1960s, 1970s, 1980s, and 1990s). The results show that the proportion of actual resident actions is lower than that reported by previous studies on settlement intentions, and that male, married, middle-aged, more educated, and long-residing members are more likely to choose to stay in Dongguan. Compared to their predecessors, the 1990 cohort reveals significant heterogeneities in their actual settlement choices. The study draws broad implications from the analysis, calling for the equalization of public welfare in Chinese cities and the encouragement of floating populations to sustain long-term residence in the destination cities.

Identification of the actual excess excavation ratio (Stakhanovskaya street – Nizhegorodskaya street site)

Introduction. Redundant strain arises in buildings and structures in areas of construction work influence caused by the deep bore tunneling performed by tunnel boring machines. The strain analysis must include an excess excavation ratio that depends on the structural features of the shield, the technology of grouting mixture injection outside the lining, the counterweight pressure applied to the shield face and geotechnical conditions so that excessive settlement could be taken account of. The purpose of the article is to identify actual values of the excess excavation ratio to raise excavation and determine the values of standard averaged excess excavation to be further applied in design. Materials and methods. This paper focuses on tunnel driving between “Stakhanovskaya Street” and “Nizhegorodskaya Street” stations. The project excess excavation ratio was applied pursuant to the regulatory documents in order to perform the analysis using PLAXIS 2D and PLAXIS 3D software packages. The method of sequential iteration was applied to identify the value of excess excavation in line with the actual settlement of buildings and structures obtained by means of monitoring. Results. The analysis has shown that the actual excess excavation ratio varies between 0.1 and 1.2 % for this construction site which is below the values required by the regulatory documents. As for the 3D setting, the values of actual excess excavation ratios are 2 to 4 times higher than those obtained for the 2D setting, although the value of the actual building settlement remains the same. Conclusions. Since the actual building settlement is smaller than the projected one, the cost of deep bored tunneling can be reduced by cutting the cost of protection of nearby buildings and structures within the area of tunneling influence without violating any safety requirements and also by reducing the number of buildings withing the projected area of influence, and respectively, by reducing the cost of geodetic monitoring over their displacements.

Optimization of Flocculation Settling Parameters of Whole Tailings Based on Spatial Difference Algorithm

In order to obtain the optimum parameters of total tailings flocculation settling, an optimization method of total tailings flocculation settling parameters based on the spatial difference algorithm was proposed. Firstly, the input and output factors of the whole tailings flocculation settling parameters are effectively analyzed, and the relevant factors affecting the flocculation settling parameters are obtained. Secondly, the flocculation settling velocity of the whole tailings is optimized by combining the spatial difference algorithm with the mathematical symmetry algorithm, and the optimal value of the flocculation settling velocity of the whole tailings is obtained. The experimental results show that anionic flocculation has the best flocculation settling effect on the whole tailings. The optimal settlement velocity is close to the actual settlement velocity, and the error of settlement velocity is less than 3.5%. The results show that compared with the traditional method, this method is an effective method to optimize the flocculation and settlement parameters of the whole tailings.

EVALUATION FINAL SETTLEMENT IN FIED UING OBSERVATIONAL METHOD: ASAOKA AND HYPERBOLIC IN PPKA PROJECT SECTION 2 PALEMBANG SOUTH SUMATRA

In the construction of the Trans Sumatra Toll Road, the existing land that will be used as a foundation belongs to the soft soil category. This is because the original soil to be built by the toll road is swamps. The soil improvement method used in PPKA section 2 is Vacuum Consolidation. In this study, a geotechnical instrument evaluation was carried out using the Settlement Plate to evaluate the actual settlement, then calculate the final settlement prediction with the Asaoka and Hyperbolic observation methods. Then from the monitoring data, the prediction of the final settlement was calculated using the Asaoka and hyperbolic observation methods, calculated the value of the degree of consolidation from each method. So that the results of the calculation can be concluded in the form of the superiority of each method used as consideration for further planning. The results obtained in this study are the actual settlement with theoretical and settlement predictions along with the comparison of the two observation methods. From the average value of the degree of consolidation produced also in the percentage of 98.68% while the hyperbolic is 99.35%. The calculation of soil subsidence using the Asaoka method is more same with the field (actual). Because the data used for the Asaoka comes from all monitoring data on the field settlement plate. Pada pembangunan jalan Tol Trans Sumatra, tanah eksisting yang akan dijadikan pondasi tergolong dalam kategori tanah lunak. Hal itu dikarenkan tanah asli yang akan dibangun jalan tol merupakan rawa-rawa. Metode perbaikan tanah yang digunakan di PPKA seksi 2 adalah Vacuum Consolidation. Dalam kajian ini, dilakukan evaluasi instrumen geoteknik menggunakan Settlement Plate untuk mengevaluasi penurunan aktual, kemudian menghitung prediksi penurunan akhir (final settlement) dengan metode observasi Asaoka dan Hiperbolik. Kemudian dari data monitoring dihitung besar prediksi penurunan akhir tanah menggunakan metode observasi asaoka dan hiperbolik, dihitung nilai derajat konsolidasi dari setiap metode. Sehingga dari hasil perhitungan didapat kesimpulan berupa keunggulan setiap metode yang digunakan sebagai pertimbangan untuk perencanaan lanjutan. Hasil yang diperoleh dalam kajian ini adalah besar penurunan aktual dengan teoritis dan prediksi settlement beserta mengetahui perbandingan dari kedua metode observasi. Dari nilai rerata derajat konsolidasi yang dihasilkan juga pada asaoka sebesar 98,68% sedangkan pada hiperbolik sebesar 99,35%. Perhitungan penurunan tanah menggunakan metode asaoka lebih sesuai dengan lapangan (aktual). Dikarenakan data yang digunakan untuk asaoka berasal dari semua data monitoring settlement plate lapangan.

Thin-walled shell foundations

The article presents a study of the interaction of strip foundations of multistorey apartment houses united by flat cylindrical shells with a ground base. The foundation of a 17-storey residential building has been taken as an example. The ground base consists of strong upper and highly compressible underlying layers. The use of traditional foundations under the specified conditions is hardly possible. The calculation scheme of the building and the stages of the ground foundation work are represented. Also, the researchers share the results of geotechnical monitoring in the construction process including observations of settlings at 25 points with an accuracy of 0.1 mm and measurement of layer-by-layer deformations of the ground base under the building to a depth of 10 meters from the surface. The diagrams demonstrate the actual settlement of the building with increasing load and layer-by-layer deformations of the ground base in depth are presented.

Lenape-Colonist Land Conveyances in West New Jersey: Evolving Expectations in Space and Time

European colonizers and Lenape Indians brought different expectations to treaty conferences regarding land. Analysis of West New Jersey deeds and related documents shows how the Dutch, Swedes, and English in West New Jersey—like fellow colonists in East Jersey—sought full ownership of territory first along the bays, rivers, and mouths of large streams to access trade, transportation, and arable land, then moved inland. While the deeds were European documents, close scrutiny shows how the Lenapes of southern and western New Jersey delayed European takeover by imposing their own norms. The Lenapes viewed the conveyances as leases, expecting annual payments and actual settlement for continued tenure.

Ground settlement prediction of embankment treated with prefabricated vertical drains in soft soil

Excessive settlement due to consolidation can cause damage to the structure’s rest on soft soil. The settlement takes place in relatively longer. The preloading and prefabricated vertical drain (PVD) is often applied to accelerate the primary settlement. The issue in this research is the estimation of the settlement. The Asaoka method and the finite element method using PLAXIS-2D are used to estimate the final settlement of a PVD treated embankment. For the former, a complete record of the settlement was required; for the latter, some ground parameters are needed for the PLAXIS-2D analysis, such as the permeability of the soil. Because the installation process of PVD tends to influence the permeability of the in-situ soil around the PVD, the soil permeability after the installation of PVD needs to be adjusted. The numerical results were compared with actual settlement data to find out the best-fit input parameters (i.e. soil permeability) of the actual data. It was found that the best-fit soil permeability (k) used in the numerical study was about one-half of the k value determined from the laboratory test. The Root Mean Square Deviation shows that the settlement predicted by the numerical analysis has approximately 30% of the actual settlement.

Prediction on Ground Surface Settlement Caused by Subway Shield Construction in Xi'an

In order to study the ground surface settlement induced by shield tunneling, on the background of Xi'an metro line 2, this paper made use of the measured ground surface settlement to conduct characteristic parameters fitting of the settlement trough by Peck formula and the modified stiffness approach, proposed the initial suggestive value of the relevant calculation parameters, predicted the ground surface settlement by the formula with the determined parameters and compared the settlement with the actual settlement observation. The results show that the determination of the parameters is basicly right, the revised formula can be used to forecast ground surface settlement of Xi'an subway construction and finally a modified prediction formula is given.