Application of Artificial Intelligence Technology Optimized by Deep Learning to Rural Financial Development and Rural Governance

The aim of this article is to promote the development of rural finance and the further informatization of rural banks. Based on DL (deep learning) and artificial intelligence technology, data pre-processing and feature selection are conducted on the customer information of rural banks in a certain region, including the historical deposit and loan, transaction record, and credit information. Besides, four DL models are proposed with a precision of more than 87% by test to improve the simulation effect and explore the application of DL. The BLSTM-CNN (Bi-directional Long Short-Term Memory-Convolutional Neural Network) model with a precision of 95.8%, which integrates RNN (Recurrent Neural Network) and CNN (Convolutional Neural Network) in parallel, solves the shortcomings of RNN and CNN separately. The research result can provide a more reasonable prediction model for rural banks, and ideas for the development of rural informatization and promoting rural governance.

Watermelon Sorting Process by Frequency Identification and Artificial Neural Network

This research aims to enhance the watermelon’s quality selection process, which was traditionally conducted by knocking the watermelon fruit and sort out by the sound’s character. The proposed method in this research is generating the sound spectrum through the watermelon and then analyzes the response signal’s frequency and the amplitude by Fast Fourier Transform (FFT). Then the obtained data were used to train and verify the neural network processor. The result shows that, the frequencies of 129 and 172 Hz were suit to be used in the comparison. Thirty watermelons, which were randomly selected from the orchard, were used to create a data set, and then were cut to manually check and match to the fruits’ quality. The 129 Hz frequency gave the response ranging from 13.57 and above in 3 groups of watermelons quality, including, not fully ripened, fully ripened, and close to rotten watermelons. When the 172 Hz gave the response between 11.11–12.72 in not fully ripened watermelons and those of 13.00 or more in the group of close to rotten and hollow watermelons. The response was then used as a training condition for the artificial neural network processor of the sorting machine prototype. The verification results provided a reasonable prediction of the ripeness level of watermelon and can be used as a pilot prototype to improve the efficiency of the tools to obtain a modern-watermelon quality selection tool, which could enhance the competitiveness of the local farmers on the product quality control.

A crack theory-based bonded particle model for rock particles considering size effect on crushing strength

Particle breakage shows significant effect on the macroscopic behavior of rock materials, and the discrete element method is a powerful tool to investigate the relationship between micro fracture and macro deformation and strength. In this study, the concept of crack is introduced into the bonded particle model (BPM) to simulate the breakage behaviour of rockfill materials, with randomly placed weak bonds representing cracks. Different from traditional BPM, the number, position and strength of the weak bonds are directly related to the number, position and length of cracks. With a reasonable length distribution of cracks, the proposed model can successfully reflect both the crushing strength variation and size effects. A set of crack parameters including the crack density, minimum crack length, maximum crack length and fractal dimension, are suggested. The crushing characteristics of realistic rockfill particles with two typical shapes are simulated quantitatively and verified with test data. It is found that the proposed model with suggested crack parameters can give reasonable prediction on the Weibull's modulus and size effect of rockfill particles.

The algorithm for generating the training set for the problem of elastoplastic deformation of the metal rod

The paper proposes an algorithm for forming a small training set, which will provide a reasonable quality of a surrogate ML-model for the problem of elastoplastic deformation of a metal rod under the action of a longitudinal load pulse. This dynamic physical problem is computationally simple and convenient for testing various approaches, but at the same time it is physically quite complex, because it contains a significant range of effects. So, the methods tested on this problem can be further applied to other areas. This work demonstrates the possibility of a surrogate ML-model to provide a reasonable prediction quality for a dynamic physical problem with a small training set size.

Prediction of Domestic Airline Tickets using Machine Learning

Airlines usually keep their price strategies as commercial secrets and information is always asymmetric, it is difficult for ordinary customers to estimate future flight price changes. However, a reasonable prediction can help customers make decisions when to buy air tickets for a lower price. Flight price prediction can be regarded as a typical time series prediction problem. When you give customers a device that can help them save some money, they will pay you back with loyalty, which is priceless. Interesting fact: Fareboom users started spending twice as much time per session within a month of the release of an airfare price forecasting feature. Considering the features such as departure time, the number of days left for departure and time of the day it will give the best time to buy the ticket. Features are extracted from the collected data to apply Random Forest Machine Learning (ML) model. Then using this information, we are intended to build a system that can help buyers whether to buy a ticket or not. We have used Random Forest Algorithm which is a popular machine learning algorithm that belongs to the supervised learning technique. It can be used for both Classification and Regression problems in ML. It is based on the concept of ensemble learning, which is a process of combining multiple classifiers to solve a complex problem and to improve the performance of the model. With that said, random forests are a strong modelling technique and much more robust than a single decision tree. They aggregate many decision trees to limit over fitting as well as error due to bias and therefore yield useful results. Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them.

Drying Stress and Strain of Wood: A Review

Wood drying stress causes various drying defects, which result from the wood microstructure and the transfer of heat and mass during the drying. It is the fundamental way to solve the problem of defects to clarify the law and mechanism of wood stress and strain development during drying. In this paper, based on the defects of wood drying, the theory and experimental testing methods of drying stress and strain were summarized. Meanwhile, artificial neural networks (ANN) and their application in the wood drying field were also investigated. The traditional prong and slicing methods were used practically in the research and industry of wood drying, but the stress changes in-process cannot be trapped. The technologies of image analysis and near-infrared spectroscopy provide a new opportunity for the detection of drying stress and strain. Hence, future interest should be attached to the combination of the theory of heat and mass transfer and their coupling during drying with the theory of microscopic cell wall mechanics and macroscopic drying. A more complete image acquisition and analysis system should be developed to realize the real-time monitoring of drying strain and cracking, practically. A more feasible and reasonable prediction model of wood drying stress and strain should be established to achieve the accuracy of the prediction.

Experimental Study on the Pullout Resistance of Smooth Steel Strip Reinforcement with Transverse Members

This paper presents an experimental study on the pullout resistance of a newly improved reinforcement. The applied reinforcement was a smooth steel strip reinforcement with transverse members used to improve the pullout-resistance problems of the smooth steel strip reinforcement. The pullout and bearing resistance of the improved reinforcement were evaluated using results of large-scale pullout tests. The evaluation result confirmed that the bearing resistance of the improved reinforcement was about 33–66% of the total pullout resistance, and it had an evenly distributed friction and bearing resistance. The bearing bond coefficient, considering the interference effect, gradually converged when normal stress was higher than a certain value. This result confirmed that the increment of interference effect is caused by the increment of the transverse member and normal stress. In the pullout-resistance evaluation of the improved reinforcement, a number of transverse members can be predicted using the relationship between bearing-resistance stress and the bearing bond coefficient due to normal stress, which can be applied as a reasonable prediction method.

On the application of surrogate regression models for aerodynamic coefficient prediction

Computational fluid dynamics (CFD) simulations are nowadays been intensively used in aeronautical industries to analyse the aerodynamic performance of different aircraft configurations within a design process. These simulations allow to reduce time and cost compared to wind tunnel experiments or flight tests. However, for complex configurations, CFD simulations may still take several hours using high-performance computers to deliver results. For this reason, surrogate models are currently starting to be considered as a substitute of the CFD tool with a reasonable prediction. This paper presents a review on surrogate regression models for aerodynamic coefficient prediction, in particular for the prediction of lift and drag coefficients. To compare the behaviour of the regression models, three different aeronautical configurations have been used, a NACA0012 airfoil, a RAE2822 airfoil and 3D DPW wing. These databases are also freely provided to the scientific community to allow other researchers to make further comparison with other methods.

SISTEM PREDIKSI TINGKAT KRIMINALITAS MENGGUNAKAN METODE TRIPLE EXPONENTIAL SMOOTHING: STUDI KASUS PADA POLRES KABUPATEN PROBOLINGGO

Criminality is all forms of action and conduct that violate the law as well social and religious norms that are detrimental to the society both economically and psychologically. The emergence of verious crime forms with new dimension recently shows that the criminality is always developing. In the effort to reduce the increase of the crime rate, a crime action prediction system is needed to anticipate the future. In this research a crime rate prediction system based in the types of criminal action using Triple Exponential Smoothing (TES) method has been developed, and the prediction accuracy of the system is measured by using Mean Absolute Percentage Error (MAPE) method with a case study on Resort Police of Kabupaten Probolinggo, East Jawa. From the conducted test, obtained results MAPE score of theft by weighting (Curat) type is 7% or Very Accurate prediction criterion. MAPE score for crime action type Others, motor vehicle theft (Curanmor), Destruction, and Fraud are 9.8%, 14.4%, 13.6%, and 16%, or Good prediction criterion. For crime action type Beatings, violent theft (Curas), severe persecution (Anirat), Murder, and Thief each one has MAPE score 23.2%, 31.2%, 21.2%, 33.2%, and 50%, or Reasonable prediction criterion, while MAPE score for Animal Theft is 92% or Inaccurate prediction criterion. In general, the criminality rate prediction system using TES method that has been developed for the case study on Resort Police of Kabupaten Probolinggo obtains MAPE score 28,3% or Reasonable prediction criterion.

Foundation Treatment Assessment and Postconstruction Settlement Prediction of a Loess High Fill Embankment: A Case Study

The design of high fill embankments (HFEs) on the loess plateau requires proper foundation treatment methods and reasonable prediction of postconstruction settlement (PCS). In situ tests were carried out on a test section of the collapsible loess foundation of a high fill airport to assess the reinforcement effects of common treatment methods. Based on in situ monitored data, the spatial-temporal variations of the PCS of the HFE were investigated, with a simple empirical formula proposed for PCS prediction. The PCS increases linearly with the fill thickness, and the PCS rate varies exponentially with the fill rate. Two engineering recommendations were made to reduce differential PCS and water damage for the test site. The first is to combine the reinforcement methods to reduce PCS of the HFE, i.e., dynamic compaction for loess foundation with lower water content and gravel piles with stabilizers for that with higher water content. The second is to employ the dynamic compaction (DC), percussive compaction (PC), and vibration compaction (VC) to strengthen the fill to reach an average compaction degree above 0.93 and a water content close to the optimal.