A Large Goaf Group Treatment by means of Mine Backfill Technology

There are few studies on the management methods of large-scale goaf groups per the specific surrounding rock mass conditions of each goaf. This paper evaluates comprehensively the stability of the multistage large-scale goaf group in a Pb-Zn mine in Inner Mongolia, China, via the modified Mathews stability diagram technique. The volume of each goaf to be backfilled was quantitatively analyzed in the combination of theoretical analysis and three-dimensional laser scanning technology. The corresponding mechanical characteristics of the filling were determined by laboratory testing while formulating the treatment scheme of the large goaf group using the backfill method. The applicability of the treatment scheme using the backfill was verified by the combination of the numerical results of the distribution of the surrounding rock failure zone and the monitored data of the surface subsidence. The research results and treatment scheme using the backfill can provide a reference for similar conditions of mines worldwide.

Transformer + GAN based Traditional Chinese Medicine inpatient prescription recommendation (Preprint)

BACKGROUND Clinical diagnosis and treatment decision making support is at the core of medical artificial intelligent research, in which Traditional Chinese Medicine (TCM) decision making is an important part. Traditional Chinese Medicine is a traditional medical system originated from China, of which the main clinical model is to conduct individualized diagnosis and treatment by relying on the four-diagnosis information. One of the key tasks of the TCM artificial intelligence research is to develop techniques and methods of clinical prescription decision making which takes all the relevant information of a patient as input, and produces a diagnosis and treatment scheme as output. Given the complexity of TCM clinical diagnosis and treatment schemes, decision making support of clinical diagnosis and treatment schemes remains as a research challenge for lacking of an effective solution. Fortunately, as the volume of the massive clinical data in the form of electronic medical records increases rapidly, it becomes possible for the computer to produce personalized diagnosis and treatment scheme recommendation through machine learning on the basis of the clinical big data. OBJECTIVE The objective of this research is to develop a real-time diagnosis and treatment scheme recommendation model for TCM inpatients. This is accomplished by using historical clinical medical records as training data to train a Transformer network. Furthermore, to alleviate the issue of overfitting, a Generative Adversarial Network is used to generate noise-added samples from the original training data. These noise-added samples along with the original samples form the complete train data set. METHODS valid information, such as the patient’s current sickness situation, medicines taken, nursing care given, vital signs, examinations and test results, is extracted from the patient’s electronic medical records, then the obtained information is sorted chronically, to produce a sequence of data of each patient. These time-sequence data is then used as input to the Transformer network. The output of the network would be the prescription information a physician would give. Overfitting is a common problem in machine learning, and becomes especially server when the network is complex with insufficient training data. In this research, a Generative Adversarial Network, is used to double the number of training samples by producing noise-added samples from the original samples. This, to a great extent, lessens the overfitting problem. RESULTS A total of 21,295 copies of inpatient electronic medical records from Guang’anmen traditional Chinese medicine hospital was used in this research. These records were created between January 2017 and December 2018, covering a total of 6352 kinds of medicines. These medicines were sorted into 829 types of first category medicines based on the class relationships among medicines. As shown by the test results, the performance of a fully trained Transformer model can have an average precision rate of 80.58%，and an average recall rate of 68.49%. CONCLUSIONS As shown by the preliminary test results, the Transformer-based TCM prescription recommendation model outperforms the existing conventional methods. The extra training samples generated by the GAN network helps to overcome the overfitting issue, leading a further improved recall rate and precision rate.

Risk Prediction Algorithm of Social Security Fund Operation Based on RBF Neural Network

In order to ensure the benign operation of the social security fund system, it is necessary to understand the social security fund facing all aspects of the risk, more importantly to know the relationship between different risks. Based on RBF, the interpretative structure model is applied to draw the risk correlation hierarchy diagram, which provides a scientific risk management method for the social security fund. RBF neural network is used to build the risk warning model of social security fund operation. Then, put forward the corresponding risk treatment scheme to the warning signal. Finally, the RBF neural network is used for comprehensive risk warning. In this paper, the risk warning of social security fund operation is the research object, and the corresponding risk treatment scheme is put forward for the warning signal. This paper uses an improved ant colony algorithm to optimize the parameters of the RBF neural network, which overcomes the shortcomings of the traditional RBF neural network such as slow convergence, ease of falling into local extremes, and low accuracy, and improves the generalization ability of the RBF neural network. It has the characteristics of good output stability and fast convergence speed. On this basis, the prediction model based on the improved ANT colony-RBF neural network is established, and the MATLAB software calculation tool is used for accurate calculation, which makes the prediction results of coal mine safety risk more accurate and provides more reliable decision basis for decision makers. The results show that the network has small calculation error, fast convergence, and good generalization ability.

Pretreatment for Tunnel Karst Cave during Excavation: A Case Study of Guangxi, China

Karst landscape is a general term for earth surfaces and underground patterns that have been formed by the dissolution of soluble rock. Karst landscapes are widely distributed throughout China—particularly in the Guangxi and Guangdong provinces. The main features of karst landscapes are typically reflected in karst caverns, sinkholes, and other geographical phenomena. During tunnel construction in karst areas, various forms of karst caverns may appear on the construction route, and they can cause hazards—such as water inrush and collapse—during tunnel construction. These hazards affect the tunnel construction process. As such, it is necessary to propose a treatment for karst caverns. In this work, a case study of the tunnels on the Hechi-Baise expressway is presented. A comprehensive pretreatment method suitable for this tunnel is proposed. On the premise of prioritizing the safety and timeline of construction, an optimized treatment scheme for the karst caverns of Hebai tunnel is followed. The optimized treatment scheme primarily includes calculation of safe thickness of tunnel face, strengthening the initial support and increasing the thickness of the second lining, increasing the reserved deformation, and grouting. The proposed scheme achieved favorable results in the treatment of a karst cavern in the Hebai tunnels.

Study on the effectiveness of chemical and biological agents to control tomato leaf miner (Tuta absoluta Meyrick, 1917)

In growing four tomato varieties in greenhouses, the effect of a conventional and integrated scheme for control of tomato leaf miner (Tuta absoluta Meyrick, 1917) was studied. Six consecutive treatments were performed at ten-day intervals. The conventional scheme includes the following products: Confidor Energy OD 0.08%, Ampligo 150 ZC 400 ml/ha, Coragen 20 SC 200 ml/ha, Exalt 25 SC 2400 ml/ha, Voliam Targo 063 SC 800 ml/ha and Voliam Targo 063 SC 800 ml/ha. In the integrated scheme the following products for plant protection are used – Confidor Energy OD 0.08%, Sineis 480 SC 250 ml/ha, Sineis 480 SC 250 ml/ha, Voliam Targo 063 SC 800 ml/ha, Neem Azal T/S 0.3% and Neem Azal T/S 0.3%. The effectiveness of the plant protection products against the tomato leaf miner, the degree of pest attack of the different varieties and the tomato productivity were studied in this experiment. It was established that in the conventional and in the integrated treatment scheme, the highest efficiency was shown by the product Voliam Targo 063 SC, applied in a dose of 800 ml/ha on the seventh day after spraying. The percentage of damaged plants was the lowest in the variety Clarosa F1 (4.00%), with the application of the conventional plant protection scheme. The results were similar in the integrated scheme – 6.00%, while in the control the degree of infestation reached 18.00%. The percentage of damaged fruits in both treatment schemes was 6.00%, significantly lower than in the control (24.00%). The highest tomato productivity was observed with the application of the conventional plant protection scheme in Manusa F1 variety.

The Application of Dynamic Uncertain Causality Graph Based Diagnosis and Treatment Unification Model in the Intelligent Diagnosis and Treatment of Hepatitis B

Although hepatitis B is widespread, it is hard to cure. This paper presents a new and more accurate model for the diagnosis and treatment of hepatitis B. Based on previous research, the diagnosis and treatment modes were combined into one. By adding more influencing factors and risk factors, the overall diagnosis and treatment model will be further expanded, and a richer and more detailed overall diagnosis and treatment model will be constructed. Reverse logic gates are used in the model to improve the accuracy of the treatment planning. The new unified model is more accurate in subdividing diagnosis results, and it is more flexible and accurate in providing dynamic treatment plans. The prediction process and the static diagnosis process of the model are symmetric, and the related sub-graph is symmetric in structure. In addition, an algorithm for predicting the response probability of treatment scheme is developed, so as to predict the subsequent treatment effects of the current treatment scheme, such as the probability of drug resistance. The results show that this method is more accurate than other available systems, and it has encouraging diagnostic accuracy and effectiveness, which provides a promising help for doctors in diagnosing hepatitis B.