Search

As an effective method for clustering applications, the clustering ensemble algorithm integrates different clustering solutions into a final one, thus improving the clustering efficiency. The key to designing the clustering ensemble algorithm is to improve the diversities of base learners and optimize the ensemble strategies. To address these problems, we propose a clustering ensemble framework that consists of three parts. First, three view transformation methods, including random principal component analysis, random nearest neighbor, and modified fuzzy extension model, are used as base learners to learn different clustering views. A random transformation and hybrid multiview learning-based clustering ensemble method (RTHMC) is then designed to synthesize the multiview clustering results. Second, a new random subspace transformation is integrated into RTHMC to enhance its performance. Finally, a view-based self-evolutionary strategy is developed to further improve the proposed method by optimizing random subspace sets. Experiments and comparisons demonstrate the effectiveness and superiority of the proposed method for clustering different kinds of data.

Lithology interpretation is important for understanding subsurface properties. Yet, the common manual well log interpretation is usually with low efficiency and bad consistency. Therefore, the automatic well log interpretation tools based on machine learning and deep learning have been developed. Although the state-of-the-art sophisticated models can show fine interpretation performance with acceptable accuracies, ``blind'' tests do not always exhibit satisfactory results because of the complexity of lithology interpretation with respect to subsurface rock properties and the data-labeling quality. To solve this generalization challenge, we propose to leverage the parameterized quantum circuits in the deep-learning model. The quantum computing takes advantages of the superposition and entanglement quantum systems, which could potentially endow the generalization power or capability to the deep-learning model. Using the proposed quantum-enhanced deep-learning (QEDL) model, we have tested the model performance on field well log data from different wells. Compared with the classic fine convolutional neural network (CNN) model and the long short-term memory (LSTM) model, the proposed QEDL model achieves comparable model performance with a clearly improved generalization power for interpreting both thin and thick lithology layers. In addition, because of the quantum circuit structure, the QEDL model needs much fewer model parameters than LSTM and CNN models, i.e., the QEDL parameter number in our study can be approximately 75% less than that of LSTM and 89% less than that of CNN.

To study the microscopic pore characteristics of marine–continental transitional shale, we studied the Daning–Jixian block of the Shanxi Formation using low-pressure CO2 adsorption (LP-CO2A) and low-temperature N2 adsorption (LT-N2A) methods in conjunction with field emission scanning electron microscopy (FE-SEM), geochemistry, and mineral composition analysis in order to obtain pore structure characteristic parameters. The fractal dimension of the pores was calculated using the Frankel–Halsey–Hill (FHH) model, and the study also discusses the factors that influence the pore structure. The study found that the marine–continental transitional phase shale of the Shanxi Formation has clay mineral contents ranging from 36.24% to 65.21%. The total organic carbon (TOC) contents range from 0.64% to 9.70%. Additionally, the organic matter maturity is high. The FE-SEM and gas adsorption experiments revealed that the transitional shale of the Shanxi Formation possesses a diverse range of pore types with relatively large pore sizes. The dominant pore types are organic and intragranular pores, with pore morphologies predominantly appearing as slit and parallel plate structures. According to the experimental data on gas adsorption, the total SSA values range from 11.126 to 47.220 m2/g. The total PV values range from 0.014 to 0.056 cm3/g. Micropores make up a greater proportion of the total SSA, whereas mesoporous pores make up a greater proportion of the total PV. The distribution of shale pore fractal dimensions D1 and D2 (D1 is 2.470 to 2.557; D2 is 2.531 to 2.755), obtained through LT-N2A data, is relatively concentrated. D1 and D2 have a positive correlation with the TOC content, clay mineral content, and BET-SSA, and D1 and D2 have a negative correlation with the quartz content. D2 is positively correlated with the Langmuir volume, showing that D2 can be used to evaluate the methane adsorption capacity.

BACKGROUND: This study sought to investigate the clinical efficacy and safety of minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF) in the treatment of lumbar degenerative diseases. METHODS: The clinical data of 55 patients with lumbar degenerative diseases treated at our hospital from January 2018 to January 2020 were analyzed retrospectively. Of the 55 patients, 35 who underwent MIS-TLIF were included in the MIS-TLIF group, and 20 who underwent posterior lumbar interbody fusion (PLIF) were included in the PLIF group. The visual analogue scale (VAS) score, Oswestry disability index (ODI) score, operation time, incision length, intraoperative bleeding, postoperative drainage, postoperative landing time, postoperative hospital stay, postoperative interbody fusion rate, and complications were compared between the two groups. RESULTS: The patients in both groups were followed-up for at least 1.5 years (range, 18–30 months; with an average of 27.5±2.6 months). There was no significant difference in the operation time, incision length, intraoperative bleeding, VAS score for low back and leg pain, ODI score, interbody fusion rate, hospitalization expenses, and complication rate between the two groups (P>0.05). One patient had nail failure in the MIS-TLIF group, 1 patient in each group had nerve root irritation, and 1 patient in each group had superficial incision infection and local suture dehiscence. The postoperative drainage volume, postoperative landing time, and postoperative hospital stay of the MIS-TLIF group were less than those of the PLIF group (P

Elastic constants derived from seismic-scale measurements are often used to infer subsurface petrophysical properties based on rock-physics relationships established from either theoretic model or core-scale measurements. However, the spatial heterogeneity of rock physical properties at the local scale has a significant impact on this relation. To understand this problem, we built a scaled physical model comprised of artificial porous layers with different pore fluids. After conducting a two-dimensional marine seismic survey over the physical model, the physical modeling data ware then used to retrieve the elastic constants of the layered package. The seismic-scale results reveal that the identification of reservoir fluid properties is improved using elastic constants that is more sensitive to pore fluid properties. The results of numerical simulations show that Lamé moduli provide more insight into rock properties and pore-fluid contents than P-wave impedances, and that the relationship between the upscaled elastic constants and the effective fluid bulk moduli at the seismic scale is usually not perfectly preserved at the reservoir scale. To interpret seismic-scale elastic constants for petrophysical properties, the rock physics relationship need to be carefully calibrated. The findings will help us understand the upscaling of rock-physics transform, which will improve the accuracy of geological property predictions from seismic-scale elastic constants.

Vehicular Ad hoc NETwork (VANET) is a multi-hop and high-speed mobile wireless communication network. In order to realize the security authentication of the information transmission between vehicle nodes in vehicular ad hoc networks, a certificateless aggregate signature scheme is designed. The proposed scheme uses certificateless cryptography, which eliminates the complex maintenance cost of certificate and solves the problem of key escrow. Communicating through pseudonyms and nodes around the roadside units generated, the conditional privacy protection is achieved for vehicle users. Then, the efficiency of the scheme is analyzed, and the relationship between the traffic density in VANETs environment and the time delay of message verification is simulated. The results show that the scheme satisfies the message authentication, anonymity, unforgeability and traceability, as well as the higher communication efficiency and the shorter delay of message verification, which is more suitable for dynamic vehicular ad hoc network environment.

Background The 8th edition of the American Joint Committee on Cancer (AJCC) staging system for gallbladder carcinoma (GBC) came into force since 2018. However, the prognostic precision of this staging system has not been properly assessed. This study aimed to evaluate the latest staging system and suggest modifications to improve its prognostic precision. Methods Data of patients with GBC was included from the Surveillance, Epidemiology and End Results (SEER) database (2004–2015) and multicenter database (2010–2017). Baseline clinicopathologic characteristics were recorded including age, sex, race, grade, T category, N category, M category and stage. The Kaplan-Meier method was used to plot survival functions. The prediction power of the AJCC 8th edition and its modified version were evaluated using the concordance index (C-index). Results A total of 2779 GBC patients were included in the SEER database and 591 were collected from multicenter database. While no significant difference in survival of patients was observed between stages IVA and IVB using the 8th AJCC staging system (p > 0.05), the prognosis of stage IIIA showed a slightly better outcome than stage IIIB (p = 0.046) in the SEER database. In the multicenter database, there was no significant difference between stage IIIA and stage IIIB (p > 0.05). Similarly, no significant difference in the survival of patients between stages IIIA and IIIB was observed when M0 patients with at least 6 lymph nodes (LNs) were analyzed (p > 0.05) for both SEER and multicenter database. On the other hand, a modified staging system was able to stratify patients from stage IIIA, stage IIIB and stage IV (p Conclusions The modified 8th staging system proposed in this study can improve the prognostic precision of the 8th AJCC staging system for GBC. We therefore suggest including these modifications in the next update of AJCC staging system for GBC.

Quantitative investment is the process of establishing mathematical models using statistics, information technology, and mathematics to quantify and implement risks, returns, and traditional investment concepts. However, due to the backwardness of computing tools in the past, quantitative investment has not received much recognition. With the improvement of computer science and quantitative analysis theory, traditional fundamental analysis and the use of sampling statistical technology to build advanced mathematical models for investment analysis have failed to meet the requirements of investors. Therefore, the Quantitative investment strategies based on data mining technology are receiving more and more attention. In this paper, we uses MATLAB software to capture big data from financial and economic websites, and then uses neural network training models to predict the trend of stock changes, and finally establishes a suitable quantitative stock selection model. The simulation results show that only by using quantitative stock selection strategies to curb risks and selecting a suitable investment portfolio can achieve the ideal goals in the stock market.

The event represents the formation interface with different lithology, namely sediment interface. It can also represent the geochronologic isochronous stratigraphic interfaces. This is the basis of the seismic interpretation, including the research of sequence stratigraphy, reservoir prediction and characterization. Events picking play a decisive role in the determination of the reflection interface. This paper is a research on the events extraction from pre/post stack reflection seismic data. The mathematical morphology is widely used in denoising, feature extraction, edge detection and other fields. In this paper, we proposed a mathematical morphology algorithm that is suitable for the seismic events picking. Based on cognitive computing, the mathematical morphology was applied to the SSPA section to reduce the noise, where eight structure elements with the size of 5 × 5 and weighing fusion based on the theory of entropy were proposed to improve the accuracy and computational efficiency. The proposed structure elements can approximate the shape of the events which are hyperbolic curve in pre-stack seismic data, VSP data and the crosswell seismic data. The event curves obtained by applying the proposed method to the synthetic layered model and field record is continuous and correspond to the events in the original data. The results indicate the high accuracy and efficiency of the proposed method.

Additional file 1: Supplement 1.

Based on the rock physical analysis of tight gas reservoirs in He8 Member of Permian Lower Shihezi Formation of Ordos Basin, and considering that bulk modulus is sensitive to pore fluid, this study proposes a fluid property detection method by compression coefficient of tight sandstone reservoirs under the constraint of reservoir lithofacies. In this method, lithofacies is identified first by calculating distribution of tight sandstone facies with the cross plot of Vp and Vs obtained from pre-stack seismic inversion; secondly, the compression coefficient is calculated by P-wave impendance and velocity from stable pre-stack seismic inversion with the restriction of lithofacies (excluding the influence of clay content); and finally, pore fluid properties are determined using the differences of compression coefficients in gas and water layers. Its application in tight gas exploration and development in Sulige gas field of Ordos Basin shows that this pore fluid prediction method by calculating compression coefficient can effectively and efficiently delineate the distribution of gas-bearing and water-bearing sandstone. Key words: Ordos Basin, Permian Lower Shihezi Formation, tight reservoir, elastic parameters, compression coefficient, pore fluid prediction

To find out the seismic wave field propagation principles in loess plateau near surface of the Ordos Basin and the seismic response characteristics of tight oil reservoirs, this study established a geological-geophysical model under the real conditions of ground surface of loess plateau, and launched full elastic seismic wave equation forward modeling and pre-stack elastic seismic inversion study. Comparison of modeling and real seismic data shows that, the loose and wavy loess plateau surface is the main reason for causing the problems of seismic static correction and interference wave. Tomographic static correction method with the constraint of traces near shot point can effectively solve the problem of seismic static correction in the loess plateau and enhance seismic imaging accuracy, S-wave impedance obtained from pre-stack seismic inversion can identify sandstone effectively, and Poisson's ratio can identify oil-bearing reservoirs. The seismic forward and inverse simulation and rock physical analysis provide a solid theoretical and experimental basis for the seismic prediction of tight oil reservoir, and have worked well in the oil exploration and development in the loess plateau of the Ordos Basin. Key words: loess plateau surface, tight reservoir, wave equation forward simulation, tomographic inversion static correction, pre-stack elastic inversion

Using core, well logging, geological analysis, production, and test data, this study characterizes a method of well logging for identifying lithology, oil or water layers, and thickness of oil layers of tight sandstone reservoir in the Chang 7 member of the Upper Triassic Yanchang Formation, southwestern Ordos Basin, China. This reservoir consists of two rock types: fine sandstone and siltstone. The fine sandstone has distinct oil traces and flecks, which strongly indicate the presence of oil, and this rock is therefore the superior reservoir. The siltstone exhibits essentially no oil shows and thus is an unproductive layer. A method of density and neutron curve normalization and overlay was used to identify the tight fine sandstone, tight siltstone, mudstone, and shale. The criteria for identifying the tight fine sandstone are a natural gamma value of less than 93 API (American Petroleum Institute units) and a difference between the normalized curves exceeding 0.05. A resistivity-porosity plot was used to identify oil or water layers relatively effectively. The criteria for identifying the tight oil layers are (1) a resistivity exceeding 28 Ω·m and a porosity exceeding 9.5% or (2) a resistivity between 20 and 28 Ω·m, a porosity exceeding 9.5%, and an oil saturation exceeding 65%. Based on the lithologic identification via normalization and overlay of the density and neutron curves and the criteria for distinguishing the tight oil layers, the thickness of the tight fine sandstone oil reservoir was accurately determined by overlaying the normalized difference curve on the resistivity curve.

— Events picking is one of the fundamental tasks in interpreting seismic data. To extract the correct travel-time of reflected waves, picking events in a wide range of source-receiver offsets is needed. Compared to post-stack seismic data, pre-stack seismic data has an accurate horizon and abundant travel-time, amplitude, and frequency while the waveform of post-stack data is damaged by normal move-out (NMO) applications. In this paper, we focus on automatic event extraction from pre-stack reflection seismic data. With the deep development of oil-gas exploration, the difficulty of petroleum exploration is being increased. Auto recognition and picking of seismic horizon is presented as the basis for oil-gas detection. There is a correspondence between the real geology horizon and events of seismic profiles. As a result, firstly, recognizing and tracing continuous events from real seismic records are needed to acquire significant horizon locations. Picking events is in this context the recognition and tracing of waves reflected from the same interfaces according to kinematics and dynamic characteristics of seismic waves. Current extraction algorithms are well able to trace these events of the seismic profile and are undergoing great development and utilization. In this paper, a method is proposed to pick travel-time and local continuous events based on edges obtained by slant-stacked peak amplitude section (SSPA). How to calculate the SSPA section is discussed in detail. The new method can improve the efficiency and accuracy without windowing and manual picking of seed points. The event curves obtained from both the synthetic layered model and field record have validated the high accuracy and efficiency of the proposed methodology.

Recommender system can effectively solve the information overload problem in the era of big data. Recent research on recommender systems, specifically Collaborative Filtering, has focused on Matrix Factorization methods, which have been shown to have excellent performance in the recommendation. However, these methods do not pay attention to the influence of user's rating characteristics, which are especially important for the accuracy of prediction or recommendation. Therefore, in order to get better performance, this paper proposes a novel method based on matrix factorization. We consider that the user's rating score is composed of two parts, one part is called real score which is decided by the user's preferences, and another part is called bias score, which is decided by the user's rating characteristics. We analyze the user's historical behavior to find his rating characteristics by using the matrix factorization technique, and then use them to adjust the final prediction results. By comparing with the latest algorithms on the existing datasets, we verified that the proposed method can significantly improve the accuracy of recommender systems and achieves the best performance in terms of prediction accuracy criterion over the state-of-the-art methods.