Search

Garment fit evaluation is one of the main bottlenecks in current fashion design and manufacturing. In the process of remote customization and online shopping the size of the clothes that does not fit has become the primary reason for users to return or exchange them which has seriously affected the intelligent upgrade of the clothing industry. Therefore how to judge the fit degree of a garment without actually trying it on is one of the main problems that needs to be solved urgently in the clothing industry. In previous studies garment fit was usually evaluated by some characteristic indexes such as ease allowance clothing wrinkle the spatial relationship between clothing and the human body and clothing pressure. However most of them have some problems such as the need to try on clothes and the complicated evaluation process which are not suitable for remote customization of clothing and online shopping. With the development of computer vision and machine learning technology a small number of scholars use 2D images to judge garment fit based on clothing wrinkle but only for specific garments and the generalization ability is weak. To solve the problem that garment fit cannot be discriminated in advance in the process of remote customization and online shopping this study took women' s suits as an example and put forward a method to discriminate the fitness of women's suits based on 2D human images. Firstly 2D images and 3D human body size of 462 young women aged 18 - 25 in northeast China were collected and a human body data set was established. Twenty-two samples were selected from this data set and virtual models were established for virtual try-on by using CLO3D software. According to the national clothing size standard of China 10 virtual women's suits with the same style and different sizes were made to establish the garment data set. Based on the principle of Kansei engineering the fitting evaluation labels of women' s suits namely tight fit and loose types were given by expert evaluation method combined with virtual fitting. Then a method to discriminate the fit of women' s suits by using garment features and 2D human image features was proposed. As for the garment features GFs the bust girth and length characteristics of women's suits the features of 2D human body image including the key point distance features DFs and overall features OFs were extracted. The specific extraction method is as follows. Firstly the 2D human body image was preprocessed and normalized and the human body contour was extracted by Canny edge detector and the five DFs in the 2D human body image were obtained namely the distance of chest thickness key points distance waist thickness key points distance hip thickness key points distance waist width key points distance and hip breadth key points distance. Then three OFs of the 2D human body image were extracted namely the body height pixel value feature H the feature of the projected unit area ρ and the feature of the projected area ratio of the front and side of the human body C. Finally the Bayesian classifier was used to establish the garment fit prediction model and the Fisher linear discriminant function was used to establish the women' s suit fit discriminant equation. In this paper computer vision technology was used to extract the feature indexes of garment fit evaluation and a machine learning algorithm was combined to realize the women's suit fit discrimination based on 2D human body images. Experimental results indicate that the garment features proposed in this paper and the 2D human body image features based on computer vision technology can be used to predict the fit of women' s suits and the discriminant model of women' s suits based on the Bayesian algorithm has achieved good discriminant accuracy and the cross-validation discriminant accuracy rate can reach 84. 8% so the model is valid. The women' s suit fit discrimination model based on 2D human image feature learning provides an effective and feasible method for garment fit in fashion design production manufacturing and online shopping. This method provides a theoretical basis for the quantitative evaluation of garment fit and is beneficial to the recommendation of clothing size and the improvement of patterns in clothing customization enterprises and online shopping. [ABSTRACT FROM AUTHOR]

As the most dynamic component of terrestrial water cycling, soil moisture plays a pivotal role in the formation, transformation, and consumption of surface water. Simultaneously, it serves as a crucial parameter influencing hydrological processes, vegetation status, and climatic conditions. Therefore, highprecision, high spatiotemporal resolution soil moisture data holds significant importance across various fields, including agriculture, forestry, and meteorology. Presently, traditional methods such as the timeconsuming and labor-intensive drying-weighing technique are inadequate for large-scale monitoring demands, highlighting the advantages of remote sensing methods. However, optical sensors are susceptible to cloud cover and vegetation obscuration, while microwave remote sensing technology faces challenges in balancing spatial and temporal resolutions. The space-borne global navigation satellite system-reflectometry (GNSS R) technology, characterized by short revisit cycles and pseudo-random sampling, presents a new opportunity for soil moisture retrieval. This paper begins by introducing the fundamental theory of soil moisture retrieval using GNSS-R and analyzes error sources during the retrieval process. This includes the scattering and attenuation effects of surface factors such as vegetation and surface roughness on reflected signals, as well as the impact of water bodies on reflectivity. Existing error correction methods and their limitations are summarized, and potential avenues for improvement are discussed. Subsequently, the research progress in recent years regarding space-borne GNSS-R soil moisture retrieval is analyzed from three perspectives: (1) The development status of space-borne GNSS-R constellation. (2)An overview of algorithms for space-borne GNSS-R soil moisture retrieval, including empirical models, semi-empirical models, and machine learning methods. (3) Advancements and directions in integrating GNSS-R with other data for soil moisture retrieval. In conclusion, based on the scattering mechanism of reflected signals, the selection of auxiliary data, and the utilization of incident angle information, this paper discusses the technical challenges faced in current soil moisture retrieval using space-borne GNSS-R technology and provides insights into future research directions. [ABSTRACT FROM AUTHOR]

Clinical prediction models can predict individual outcomes or risks based on effect evidence obtained from the population, serving as a powerful tool linking evidence-based medicine and precision medicine. With the continuous advancement of data measurement, storage, interoperability, and analytical techniques, the application prospect for clinical prediction models is becoming increasingly clear. However, it also faces many problems and challenges. This paper aims to provide an overview of the fundamental concepts, application scenarios, current dilemmas, and development opportunities of clinical prediction models [ABSTRACT FROM AUTHOR]

Objectives: Global navigation satellite system (GNSS) interferometric reflectometry (GNSS-IR) is a new passive remote sensing technique for determining surface environment parameters, which places an important part in the inversion of earth's surface properties, such as soil moisture monitoring, snow parameter retrieval, and vegetation remote sensing, etc. GNSS-IR offers several benefits over the traditional soil moisture inversion approach, including all-weather capability, high temporal precision, and cheap cost. Methods: Considering the fact that the existing soil moisture inversion algorithms only utilize one single feature of GNSS reflected signal and from the perspective of increasing data availability, this paper proposes a GNSS-IR soil moisture inversion approach that integrates multi-type feature data by utilizing phase, amplitude, and frequency extracted GNSS signals reflected by soil. The main work is to effectively filter all available features extracted from the original GNSS signal-to-noise ratio observations. The feasibility and effect of the suggested method are compared and evaluated using three machine learning models, including least squares support vector machine (LSSVM), random forest (RF), and back propagation neural network (BPNN). Results: Comparing the inversion effects of above three models, BPNN model has the best inversion effect, followed by RF model, and LSSVM model is the worst. The results show that the correlation coefficients between the reference value and soil moisture inversed by the multi-feature fusion method LSSVM, RF, and BPNN models are 0.830, 0.953, and 0.980, respectively, and the corresponding root mean square errors are 0.045, 0.035 and 0.032 cm³ /cm³ Conclusions: Compared with the single feature inversion method, both the accuracy and correlation coefficient of soil moisture inversion increase significantly. The results demonstrated that the proposed method has higher inversion accuracy and reliability than the single feature inversion method. [ABSTRACT FROM AUTHOR]

In order to further improve the accuracy and efficiency of predicted compressible flowfields arounds airfoils at high Reynolds number, large angle of attack (AoA), and high Mach numbers, a machine learning inference method based on coordinate transformation method and UNet neural network is propesed. Firstly, a novel coordinate transformation method for data pre-processing is developed. This method transforms physical quantities and grid information in computational fluid dynamics into spatial information of neural network, making the distribution of flowfield information more in line with the input requirements of the neural network. Secondly, an improved deep UNet neural network is established, allowing the model to learn the fine and complex localized flow characteristics of the airfoil flowfield. The two innovative methods are combined to establish a machine learning inference method for the compressible flowfield of airfoils, and a fast and high-precision inference model is obtained. Finally, the flowfields and aerodynamic forces of different types of airfoils are predicted and analyzed, and results are compared with those from traditional machine learning method. The results show that the machine learning inference method proposed in this paper can better predict the compressible flowfield of airfoils, and can better capture the complex flow behavior at high Reynolds numbers, and predict the flow separation and shock waves phenomena under high Mach numbers with large AoA. [ABSTRACT FROM AUTHOR]

Traditional geological stratification methods usually rely on manual interpretation and empirical judgment, which have shortcomings such as cumbersome processes, heavy workload, and large impact from human factors. This paper aims to study the ideas and methods of regional engineering geological stratification based on machine learning, and convert the stratigraphic stratification problem into a sequence-to-sequence prediction task of geological body spatial units and a geological attribute feature classification task, so as to improve the accuracy of geological stratification. and efficiency. Based on in-depth research on the original data of engineering geology, this paper proposes to use deep learning methods to train and predict geological stratification of static cone test data, and use classification algorithms to stratify borrow hole soil samples and quantify them. The applicability of the relevant algorithms was evaluated. By comparing the results of traditional methods and machine learning methods, the advantages of machine learning in geological stratification are verified. This study provides a new geological layering idea for regional engineering geology research, which has important practical significance. [ABSTRACT FROM AUTHOR]

The modeling process and uncertainty of different machine learning models to predict landslide susceptibility are different. High-precision assessment of post-seismic landslide susceptibility is the key to effective disaster prevention and mitigation. This paper established the post-seismic landslide database of the Jiuzhaigou earthquake, and 12 causative factors were finally selected for landslide susceptibility modeling by eliminating two factors from 14 initial landslide factors through factor covariance diagnosis. Then selects logical regression（LR）, support vector machine（SVM）, random forest（RF）, and artificial neural network（ANN） machine learning models and 10-fold cross-validation data sampling methods. Finally, the receiver operating characteristic curve and the distribution characteristics of the susceptibility index（mean and standard deviation） are used to discuss the modeling of landslide susceptibility based on machine learning and its uncertainty. The results show that the high susceptibility areas of landslides after the earthquake are mainly developed and distributed along the epicenter and valleys. The AUC values of the four machine learning models all exceed 0.87, which has achieved good applicability for predicting potential post-seismic landslides in the study area. Among them, the mean value and standard deviation of the susceptibility index of SVM are small, indicating that the model has good recognition ability for landslides, and it has the highest prediction accuracy(CVmean=0.925), whereas the other models are ANN（0.920）, LR（0.894） and RF（0.877）. The results of this paper are of great significance for popularizing and promoting the development of machine-learning models in other regions. [ABSTRACT FROM AUTHOR]

Osteoporosis (OP) is one of the main problems affecting the health of middle-aged and elderly people, and its most serious complication is osteoporotic fracture (OPF), which also has a high disability and mortality rate. The accurate screening and diagnosis of OP mainly rely on imaging analysis, and the diagnosis result rely on the subjective judgment of doctors. Therefore, the traditional imaging method of OP have certain challenges to the accurate screening, diagnosis and differentiation of OP. The cross-fusion of machine learning (ML) and imaging images effectively improves the diagnostic efficiency of clinicians, while realizing the prediction of unknown diseases (such as OPF). Recently, significant progress has been made in the screening and diagnosis of OP and in the diagnosis and prediction of OPF. This paper will review the recent related studies on ML model-assisted screening and diagnosis of OP based on imaging data, so as to provide new ideas for accurate clinical diagnosis and treatment of OP. [ABSTRACT FROM AUTHOR]

The increase of IC design complexity and the continuous reduction of process feature size bring new severe challenges to static timing analysis (STA) and chip design cycle. In order to improve the efficiency of STA and shorten the chip design cycle, this paper fully considers the FinFET process characteristics and the principle of STA, and predicts the timing characteristics of another part of corners by introducing machine learning methods based on the timing characteristics of some corners. The experiment is based on an industrial design, and the results show that the proposed method uses 5 corners to predict the timing of other 31 corners, which can achieve an average absolute error of less than 2 ps, far better than the 21 process angles required by traditional methods. Thus, the proposed method significantly improves the prediction accuracy and significantly reduces the workload of static time series analysis. [ABSTRACT FROM AUTHOR]

Exploring the particle size distribution of suspended load and bed material load in river channels helps to analyze the overall sedimentation situation of river sediment and provide feedback to guide the optimization of reservoir operation. In order to systematically grasp the distribution pattern of suspended load and bed material load particle size in the lower Yellow River, this paper collected and organized the water and sediment series data from 6 key sections such as Huayuankou in the lower Yellow River. Recursive feature elimination algorithm was used for variable selection, and a prediction model for sediment particle size in the lower Yellow River was built based on different machine learning algorithms. The results show that the variable selection algorithm can effectively extract the main influencing factors in the model, and when using machine learning models to predict the sediment particle size of different sections, the overall performance is good on the test set. The R² values of suspended load and bed material load particle size prediction under each section optimization model are between 0.64 and 0.89, and 0.37 and 0.72 respectively. At the same time, when using 2020 data to further verify the predictive effect of the model, the predicted and actual values of suspended load and bed material load particle sizes R² are also up to 0.609 7 and 0.445 6 respectively, which indicates that the built model can effectively achieve the prediction of sediment particle sizes in the lower Yellow River channel. [ABSTRACT FROM AUTHOR]

With the emergence of various delay-sensitive applications, how to improve the system's delay performance has be come a hot topic in academic. However, it is difficult for existing multi-domain embedding algorithms to meet the delay per- formance requirements of virtual networks. Therefore, to solve this problem, this paper proposed a TDS-VNE algorithm. In the node embedding phase, it defined a propagation delay evaluation function(D). In the link embedding phase, it defined a path delay sensing parameter. Simulation results show that the proposed embedding algorithm reduces the average network propaga tion delay and has good results on the virtual network request acceptance rate and long-term benefit-cost ratio [ABSTRACT FROM AUTHOR]

With the increasing diversity and complexity of material requirements for underground water conservancy and water pipeline networks, the efficient and convenient design of special materials to meet individual needs through machine learning has become a hot topic of concern. Traditional supervised learning methods are all based on a large dataset to train models, but obtaining large datasets for special materials required in deeply buried underground water pipeline networks and high-end military equipment, such as rare and high-entropy alloys, etc. requires extremely high cost and a long period. To solve this problem, we propose a small sample expansion model-RX-SMOGN, using XGBoost and RFECV algorithms for feature screening. We enrich the dataset with the SMOGN algorithm. In this paper, the phase structure of high-entropy alloys is used as the research object, and traditional machine learning models are trained to predict them to verify the effectiveness of the RX-SMOGN model. From the results of 5-fold cross-verification and 4 evaluation indicators, it can be seen that the RX-SMOGN model fully improves the performance of the machine learning model, provides a more convenient method for alloy material design, and fully improves the efficiency of alloy material design. [ABSTRACT FROM AUTHOR]

As a classification task, the detection of new malicious users in social networks has been facing the lack of datasets and labels of malicious users. With limited data, this paper proposed a method based on adaptive differential graph convolution to detect malicious users accurately. By extracting user features and social relationships in the social network, the method constructed the social network graph. After this, it calculated the similarities between node and its neighbors to prioritize the neighbors, and used the priority order to sample key neighbors. The node used adaptive weighted average to aggregate the features of key neighbors to itself, to update its features. After feature updating, by feature dimension reduction and normalization, the node got its malicious value, for malicious detection. The experiment results show that, compared to other methods, the method proposed in the paper achieves higher precision and overall accuracy on detection of new malicious users, with a satisfactory speed. Results also demonstrate that adaptive differential graph convolutional networks can effectively capture the key features of a small number of data samples. [ABSTRACT FROM AUTHOR]

In order to explore the correlation between the elastic energy index, stress coefficient, brittleness coefficient and burial depth of four rockburst indexes and the rockburst grade, and to solve the black box problem of complex machine learning algorithms. The LIME algorithm was introduced in this paper to improve the interpretability of machine learning in rock burst prediction. In this paper, 190 sets of rockburst engineering construction data sets at home and abroad were collected. After preprocessing, the optimal algorithm was obtained by comparing 9 kinds of machine learning algorithms. The optimal parameters of the algorithm were obtained by Bayesian optimization, and the rockburst prediction model was established. Four kinds of rockburst were analyzed based on LIME algorithm. The correlation analysis, regression analysis and threshold analysis were carried out on the indexes. Finally, the rockburst of Zhongnanshan tunnel shaft project was predicted by using two thresholds of elastic energy index and stress coefficient. The research results show as follows. The rockburst grade is linearly related to the elastic energy index and stress coefficient, and the linear relationship of the elastic energy index is more obvious. The rockburst grade is nonlinearly related to the brittleness coefficient and burial depth, and the brittleness coefficient. The nonlinear relationship is more obvious. the four rockburst indexes influence the rockburst grade in order: elastic energy index, stress coefficient, burial depth, and brittleness coefficient. The LIME algorithm can accurately express the relationship between rockburst grade and rockburst grade. The correlation between the explosion indicators and the obtained thresholds of the two indicators are consistent with the Zhongnanshan tunnel shaft project example. [ABSTRACT FROM AUTHOR]

In this paper, the effects of different task allocation strategies on the performance of sparse matrix and dense vector multiplication are discussed. It is observed that the selection of task allocation strategy can significantly affect the performance of sparse matrix, and there is no fixed task allocation strategy that can obtain the best performance for all sparse matrices. Therefore, this paper proposes an optimal task allocation strategy selection method based on machine learning. Its training process only uses sparse matrix features to characterize the input data set, and can automatically train the model for a given data set and target platform. Experiments show that, compared with the default block allocation method, the task allocation method selected by this model can achieve an average performance improvement of about 35%. [ABSTRACT FROM AUTHOR]

As a result of the development of industrial intelligence, intelligent control systems have been equipped in industrial production systems, and one of the important requirements is intelligent anomaly detection. However, achieving intelligent anomaly detection is often difficult due to the streaming data format of dynamic runtime parameters and the coupling of high-dimensional data, which make it challenging to perform reliable and efficient anomaly detection. To this end, this paper proposes an anomaly detection method based on joint distribution. Firstly, the dynamic operating data was sampled from both real-time detection and overall detection perspectives. Then, the joint distribution was modeled using empirical Copula. Finally, the anomaly score was determined based on the model. The dataset of the drainage system in a hydropower station on Dadu River was used to investigate the effectiveness of the proposed method, and the results show that this method is more efficient than traditional anomaly detection methods and improves area under curve(AUC) value and average precision. Meanwhile, the interpretability of this method also provides a reliable basis for subsequent troubleshooting and maintenance of the drainage system. [ABSTRACT FROM AUTHOR]

Aiming at improving the performance of the default loop scheduling and tile size of Pluto, a commonly used polyhedral compiler, this paper proposes a method to compute a variety of legal permutations for its default scheduling and auto-tune its performance according to the configuration space composed of permutations and tile sizes. Through the processing of scalar dimension that defines loop fusion, both intra and inter permutations for imperfect loop nest are realized. Four machine learning driven auto-tuning strategies are proposed to find the optimized combination of permutation order and tile size for a loop with a given problem size. Under the default tile size, the optimal permutation generated by the extended Pluto compiler in a parallel environment achieves a maximum speedup of 4.02 and a geometric mean of 2.12 compared with the default scheduling of Pluto. By further searching for a better combination of permutation order and tile size, the best auto-tuning strategy achieves a maximum speedup of 5.48 and a geometric mean of 2.86 compared with Pluto's default optimization in a parallel environment. In addition, the best configuration and the learned model obtained by auto-tuning for a particular problem size, when being applied to similar problem sizes, also outperform the default optimization of Pluto in various degrees. [ABSTRACT FROM AUTHOR]

Machine learning, as a new technique combining statistics and computer science, has been widely used in crop information acquisition tasks in recent years. Traditional methods for obtaining crop information mainly rely on chemical detection methods, which is time-consuming and labor-intensive. Based on machine learning algorithms and hyperspectral remote sensing techniques, crop appearance and internal physical and chemical parameters can be quickly sensed in a non-destructive way, which has obvious application advantages and development prospects. First, the researches related to the hyperspectral remote sensing of crop information were systematically reviewed in this paper. Second, the application, advantages and disadvantages and uncertainties of different machine learning algorithms in hyperspectral sensing crop information were summarized. Finally, it was pointed out that the future development trends of hyperspectral sensing crop information were as follows: (1) complementary crop information acquisition methods could be realized through multi-source remote sensing collaborative observations. (2) The assimilation technologies of hyperspectral remote sensing and crop model as well as the deep integration technologies of hyperspectral remote sensing and artificial intelligence could be developed. (3) The intelligent acquisition of key information oriented to the whole growth period of crops and decision-making could be realized. [ABSTRACT FROM AUTHOR]

In wind tunnel experiments, sensors are normally placed on wing surfaces to measure the aerodynamic load at the corresponding positions. Due to the limited number of the placed sensors, it is difficult to directly obtain the holographic aerodynamic load distribution of the whole wing. In this paper, we use machine learning methods to reconstruct the holographic aerodynamic load on the wing surface from the limited sensor data, and propose a method to optimize the placement of sensors using the simulation data. We select limited position data from the wing holographic aerodynamic data calculated by computational fluid dynamics (CFD) to simulate the sensor experimental data, and compare the reconstruction accuracy of the deep learning model, Gaussian process regression (GPR), support vector regression (SVR) and BP neural network (NN) to the aerodynamic load. The sensor layout is optimized by evaluating the holographic load accuracy reconstructed by the sensor data. The M6 wing is taken as an example to verify the proposed method under two given working conditions. The experimental results show that the GPR model achieves the best accuracy of aerodynamic load reconstruction. The optimal section number and single section number of M6 wing under different total number of sensors, the optimal arrangement under the lowest number of sensors, and the arrangement of sensors in the leading edge area and spanwise section where the flow field changes greatly are all given. [ABSTRACT FROM AUTHOR]

The complexity of modern war is increasing，and the rapid operational mission planning is of great importance to improve the efficiency of command and control. This paper presents a joint operational Task Matrix （TM） model，which is a theoretical method for mission planning; A belief network model is put forward to describe the relationship among the elements in TM model ;A naive bayesian learning method for belief network is designed; A mechanism of imagination is put forward to speed up the learning process ; A search algorithm named Deep Minimum Threat Generation Tree（DMTGT） is proposed, which can efficiently calculate task priority by balancing search error and search speed. Finally, the validity of above models and algorithms is verified by simulation experiments. [ABSTRACT FROM AUTHOR]

The article was to apply the LightGBM algorithm to provide early warning on financial situation of listed feed companies, combining LightGBM algorithm with Z-score model. The financial data of 14 A-share listed feed companies from 2012 to 2021 were selected to calculate the Z-values, and the obtained Z-values were used as input to LightGBM algorithm to obtain final optimised Z-values. The results showed that the overall financial position of listed feed companies was good and the level of risk was low, with debt servicing capacity having the greatest impact on the company's financial position, with the proportion of importance of this characteristic being 27.90%. The LightGBM algorithm optimised Z-score model had an R² of 0.915 and 0.903 for training and test sets respectively in terms of accuracy, and the lowest root mean square error (RMSE) of 0.787 and 0.700 errors respectively were smaller. The paper indicates that the optimised Z-score model has good stability and application prospects in financial early warning of listed feed companies, and can provide some reference value for listed feed company managers and investors to prevent corporate financial risks. [ABSTRACT FROM AUTHOR]

Standard cell library is the foundation of chip design, analysis, and verification, and its generation requires a lot of time and server resources. Therefore, vendors often only provide standard cell libraries under a few corners. However, the design of chip performance, power consumption, and reliability requires delay information of standard cells under multiple voltages, temperatures, and parameters (such as drive strength, channel length, and threshold voltage). To quickly and accurately calculate the delay of standard cells under multiple corners, this paper proposes a machine learning-based method for multi-voltage, multi-temperature, and multi-parameter standard cell delay calculation. By studying the factors that affect the delay of standard cells in depth, data sets are extracted from the 28nm process standard cell library and timing reports. Machine learning algorithms are used to train and calibrate the standard cell delay calculation model. The establishment of the model takes only a few minutes, which is much less than the time consumed by simulation methods (usually hundreds of hours). The average calculation error of the model is 1.542 ps for unknown voltage cell delay, 1.814 ps for unknown temperature cell delay, and 2.202 ps for cell delay under different parameters. The prediction error of cell delay in the static timing analysis process is less than 3%. This method can quickly and accurately calculate the delay of standard cells in real-time and can be applied to fast timing analysis under multiple scenarios before sign-off. [ABSTRACT FROM AUTHOR]

In order to accurately predict the ozone concentration level, this paper used the EC_ Thin global weather model products, global numerical weather prediction products from GRAPES_GFS, which are the graphs independently developed in China, and South China GRACEs atmospheric composition model output products to integrate meteorological and environmental observation data, and used six machine learning intelligent algorithms to build a hybrid model that coupled numerical prediction models with machine learning, in order to give full play to the advantages, complementarity and synergy of numerical prediction and machine learning intelligent algorithms, and improve the accuracy of ozone concentration level prediction by leaps and bounds. Four control experiments were set up for which different characteristic products were selected and the classical classification algorithm of machine learning was used to classify and predict the ozone concentration level in Changsha for any four days to come. The model output with the highest test accuracy was taken as the result statistics. It is found that the test accuracy of the optimal model in 1 to 4 days is 81.7%, 81.7%, 78.3% and 60.9% respectively, which is much higher than the atmospheric composition model prediction and forecaster experience, and achieves the expected design goal. The contribution of high-quality weather model products to product quality is large while that of atmospheric composition model products is limited. The prediction performance of the model within 3 days is good, and low-level prediction performance is good, and high-level prediction performance is general. The following solutions for discussion are proposed: the number of high-level samples is to be increased; the recognition ability of the model is to be enhanced for such events; the mechanism analysis of high-grade ozone pollution is to be strengthened; and more refined factors for the use of the model are to be combined. [ABSTRACT FROM AUTHOR]

Osteoporosis (OP) is a kind of bone disease related to aging. Its onset is obscure and development is gradual. Patients are without obvious clinical manifestations in the early stage. However, with the progress of the disease, bone loss and bone tissue microstructure destruction occur, and bone pain, spine deformation, and even osteoporotic fracture (OPF) and other serious complications may develop. Dual-energy X-ray absorption method is the current gold standard for clinical diagnosis of OP. Because its diagnostic accuracy is affected by the factors of body weight, lumbar degenerative changes, and aortic wall calcification, a false negative diagnosis is possible. In recent years, artificial intelligence (AI) has developed rapidly in the medical field. At present, AI has been widely used in the research of OP. Its research in the field of OP screening, diagnosis, and prediction has become a new hot spot. This paper expounds the application status and advantages of AI in OP diagnosis and treatment from four aspects, i.e., OP early screening, medical imaging performance, clinical diagnosis and treatment data, and OPF risk prediction, so as to provide a new direction for the accurate diagnosis and treatment of OP. [ABSTRACT FROM AUTHOR]

The production and sales of high-quality fruits are inseparable from fruit quality testing, while traditional fruit quality testing methods have low precision, high cost, poor timeliness, and strong destructiveness. With the continuous advancement of science and technology in recent years, low-cost and high-efficiency non-destructive testing technology for fruit quality has been developed rapidly. Among them, hyperspectral imaging technology has gradually become a research hotspot. This paper summarizes the technical principle, application and development status of this technology in the field of fruit quality, and discusses its performance potential, existing problems, development trend and application prospects in the field of non-destructive testing of fruit quality. On the whole, hyperspectral imaging technology can non-destructively and efficiently realize the effective detection of various fruits and various quality indicators, such as maturity, sugar content, acidity, red index, etc.; Limited by hardware technology, its development focuses on data mining, that is, in the case of limited hardware development, accurate analysis results can be obtained through continuously updated and optimized targeted algorithms; on the other hand, expensive equipment, complex data processing, and poor model universality are the main problems that this technology needs to be further optimized and improved; Its future development will be based on efficient data processing of cloud computing and artificial intelligence, research and development of hyperspectral detection equipment for fruit quality with a wider range of applications, and multi-source comprehensive non-destructive testing. With the continuous development of technology, hyperspectral imaging technology has broad application prospects in non-destructive testing of fruit quality, and will become one of the important means of fruit quality testing in the future. [ABSTRACT FROM AUTHOR]

[Objective] By standardizing, expediting, and automating the evaluation of integrated farmland soil fertility, the present paper aimed to optimize crop planting patterns and make use of land resources rationally. [Method] Taking the tobacco planting areas of Fuchuan Yao Autonomous County as examples, 1038 sample points from Guangxi tobacco planting areas were selected as training data. Based on the consideration of soil conditions, climate environment, and topography, 15 indicators were chosen to calculate the integrated soil fertility index. The Stacking algorithm was applied to establish a regression prediction model for evaluating the integrated fertility of the study area. [Result] The Stacking02 model based on six key factors exhibited excellent performance on the test set, with mean absolute error, mean squared error, and R2 coefficient of determination of 0.0066, 0.0084, and 0.9529, respectively. The Stacking02 model was used to assess the integrated fertility of the study area, showing that the northern part of study area was better than the southern part, with a higher proportion of high-quality production areas. Low comprehensive fertility index regions had relatively high soil pH values and low total nitrogen and available potassium contents. [Conclusion] Compared to primary learners, the performance of the Stacking model improved. The Stacking02 model established using six key factors demonstrated excellent generalization performance, simplifying the calculation process and saving computational power. The same method can also be used to evaluate the soil integrated fertility of the study area. It suggests that this method should be extended to the comprehensive fertility evaluation of other regions and crops’ soils to develop targeted crop utilization schemes. [ABSTRACT FROM AUTHOR]

Gastrointestinal stromal tumor (GIST) is the most common mesenchymal tumor in the gastrointestinal tract, with complex biological characteristics and varying risks, and the treatment methods and prognosis of patients with different risks are quite different; therefore, early diagnosis and risk assessment are crucial for its precision treatment. In recent years, CT radiomics, as an emerging imaging technology, can transform traditional CT image features into a large number of data, thereby reflecting the inherent heterogeneity of GIST and even correlating with its gene expression features. This paper reviews the research progress of CT radiomics in the diagnosis and prediction of GIST with the help of machine learning. The current CT radiomics can not only be used for the differential diagnosis of GIST and other gastric diseases, but also for the risk evaluation of GIST. Furthermore, pathological analysis and gene diagnosis can be performed based on CT images, and then the first-line treatment effect and longterm prognosis can be predicted. At present, various prediction models constructed by combination of CT radiomics and clinical information have been well verified in the specific practice of different clinical problems, showing broad application prospects. However, in the specific clinical application process, different methods of sample data collection and processing, differences in the selection of machine learning algorithms, and the selection of 2D or 3D images all affect the specific effectiveness of CT radiomics. Hence, unified and standardized application rules for radiomics has to be established. [ABSTRACT FROM AUTHOR]

Network fault management aims to detect, identify and correct error conditions occurring in the network, providing users with reliable and stable network services. Recently, the utilization of machine learning methods for network fault management has attracted widespread attention. In this regard, this paper first introduced the research background of cell network fault management and explain the process and function of network fault management, and then introduced the existing cell network fault management frameworks. Subsequently, this paper reviewed the existing research on machine learning methods in cell network fault management. Referring to the fault management lifecycle, this paper introduced, summarized and compared the machine learning methods for fault detection, fault diagnosis and fault prediction for the purpose of providing reference for research in related fields. [ABSTRACT FROM AUTHOR]

Multiple random empirical kernel learning machine(MREKLM) selects a small number of samples to construct the empirical feature space, but does not take into account the distribution of data when projecting, and takes a long time to select samples. In order to utilize the distribution information of samples, this paper introduced the intraclass dispersion matrix, and proposed an intra-class variance based multiple empirical kernel learning(ICVMEKL), which enabled samples to take into account the intra-class information when projecting. The method enhanced the classification boundary and improved the classification accuracy. Further, in order to reduce the selection time of samples, this paper proposed an improved ICVMEKL(ICVMEKL＿I) based on locality-sensitive hashing algorithm by using the border point extraction based on locality-sensitive hashing(BPLSH) to select samples, so that the samples for constructing the empirical kernel no longer need to be obtained from the candidate set, and the method reduced the training time. Experiments on multiple datasets show that ICVMEKL can effectively improve the accuracy, ICVMEKL＿I can significantly reduce the training time, both of which show good generalization performance. [ABSTRACT FROM AUTHOR]

Discrete sequence generation is widely used in text generation, sequence recommendation and other fields. The current research work mainly focuses on improving the accuracy of sequence generation, but ignores the diversity of generation. To address this phenomenon, this paper proposed an adaptive sequence generation method ( ECoT), and designed a two-layer meta controller. In the data layer, the function of meta controller was to realize adaptive learning sampling, automatically balance the distribution of real data and generated data,and obtain mixed data distribution. At the model level, this paper added diversity constraints. The function of the meta controller was to adaptively learn the optimal update gradient to improve the generation diversity of the generation model. In addition, in order to improve the accuracy of the generation model, this paper proposed a method combining cooperative training and adversarial learning. Compared with the current mainstream models, the results show that the adaptive cooperative training sequence generation method has more balanced accuracy and diversity in terms of generation accuracy and diversity, and can effectively alleviate the pattern collapse of the generation model. [ABSTRACT FROM AUTHOR]

The paper proposes a robot zero calibration device and method based on spatial parameter clustering identification to overcome the shortcomings of traditional shaft pin and laser tracker calibration. The dial indicator and spatial analytic geometry are used to construct the zero calibration equation， which analyzes the robot’s theoretical post and posture values to obtain the zero-position training parameters. The clustering module identifies multiple sets of zero-position training parameters， and the optimal zero-position parameters of each joint can be solved. The experimental results show that spatial parameter clustering can improve the absolute accuracy by 72.9%， compared to the most commonly used shaft pin calibration method. Compared with the laser tracker calibration method with the highest accuracy， the time efficiency is improved by 87.5%. This method considers the calibration accuracy and efficiency and significantly improves the adaptability to the calibration environment. [ABSTRACT FROM AUTHOR]

LLP is a machine learning method that puts instances into packages. It only provides instance information and label proportional information in packages, but does not provide label information. Aiming at the LLP problem of multiple related tasks, this paper proposed a label proportion integrated learning model based on transfer learning, called AT-LLP for short. The model connected related tasks by constructing shared parameters between tasks, and migrated the knowledge learned in the source task to the target task, so as to improve the learning efficiency of the target task. At the same time, the algorithm introduced the ensemble learning algorithm, which continuously adjusted the weight coefficient of the training set in the multi-iteration learning process of the classifier, so as to further train the weak classifier into a strong classifier. Experiments show that the proposed AT-LLP model has better performance than the existing LLP method. [ABSTRACT FROM AUTHOR]

Directed evolution can increase the rate of enzyme evolution by mimicking the natural evolutionary process and has become a key technology for enzyme engineering. Directed evolution has played an important role in biocatalysis and drug design, however the experimental screening is in great challenge due to the large number of mutant libraries caused by the randomness of mutations. In recent years, emerging technologies such as artificial intelligence and big data processing have also become crucial in biocatalysis researches. Machine learning methods are statistical learning approaches to obtain sequence/structure mappings to enzyme function in a data-driven manner, which will improve the efficiency of enzyme engineering. This paper reviews the state-of-the-art technologies involved in machine learning models, especially focusing on the research and application progresses of machine learning methods in enzyme engineering. With the advancement of machine learning algorithms and technologies, it is expected that more accurate and effective models will be proposed in the future to promote screening of new enzymes and accurate design of biocatalysts [ABSTRACT FROM AUTHOR]

As a key problem and hub link between problem discovery and problem solving, the current research on root cause analysis mainly includes two types of methods: data-driven and causality-driven. In view of the advantages of data-driven methods in narrowing the range of root causes, at present, root cause research mainly focusses on datadriven methods such as association rule mining, heuristic search, machine learning and deep learning. There are few root cause analysis from the perspective of causal knowledge, nor has it been based on method dimension. The inductive analysis of the root cause is carried out, and there is a lack of relevant research results. Therefore, this paper sorts out and summarizes the main results of root cause analysis in recent years, analyses the differences and advantages of root cause analysis under different method dimensions, and proposes a root cause analysis method that integrates causal knowledge, and combines asymmetric Shapley value with causal chain diagram to improve the accuracy of root cause analysis. Finally, the existing some research difficulties and development trends put forward scientific and meaningful future research directions. [ABSTRACT FROM AUTHOR]

Displacement prediction has been one of the hot spots in landslide studies. In recent years, with the development of computer science, artificial intelligent models have been increasingly used in displacement prediction of landslide. Compared with the commonly used machine learning methods like LSTM neural network, the XGBoost（eXtreme Gradient Boosting） model in integrated algorithms is not common in landslide displacement prediction. However, it has become a hot field of research in academia because it has higher prediction accuracy and faster operating speed in the prediction. Taking the monitoring data of the landslide disaster site in Yaoshan Village, Anxi County, Quanzhou, Fujian as an example, Python is used to build the XGBoost model in this paper. By comparing the maximum information coefficients, the feature with a higher correlation to the displacement is selected and put into the model for landslide displacement prediction. The results show as follows: the XGBoost model can predict rainfall-induced step-like landslide displacement more accurately than most machine learning models. This is because it has advantages such as introducing a regular term in the objective function to control model overfitting, and using forward validation for model dataset partitioning. Meanwhile, it is of important significance for the displacement prediction, monitoring and early warning of such landslides. [ABSTRACT FROM AUTHOR]

This paper applied the classical ID3 decision tree algorithm for discrete data classification. However, it required data discretization for continuous data processing, and this process easily caused information loss. This paper proposed the neighborhood equivalence relationship to induce the neighborhood ID3 ( NID3) decision tree algorithm. The NID3 algorithm improved the ID3 decision tree algorithm, which could directly implement continuous prediction and obtained better classification results. In the neighborhood decision system, this paper mined a neighborhood equivalence relationship. Then, based on the equivalent granulation of the neighborhood, this paper constructed the neighborhood information metric. Finally, this paper designed the NID3 decision tree algorithm based on the neighborhood information gain. As verified by both case analyses and data experiments, algorithm NID3 is effective for continuous data classification, and it outperforms ID3 algorithm in classification machine learning. [ABSTRACT FROM AUTHOR]

The traditional landslide identification is mainly through remote sensing visual interpretation and human-computer interaction identification, which has the problems of time-consuming and laborious, subjective and low extraction accuracy. In this paper, a highway in Fujian Province is taken as the experimental area, and a rapid landslide identification method based on high-resolution remote sensing data for mountainous roads in southeast Fujian is proposed. Firstly, by analyzing and studying landslide features such as hue, topography, spectrum, vegetation index and texture using sub-meter high-resolution remote sensing images, the multi-dimensional multi-scale landslide classification and identification rules applicable to the mountainous roads in southeast Fujian are established. Secondly, a road landslide identification model is constructed by combining the classification tool of machine learning algorithm with the multi-dimensional multi-scale feature screening set, and the preliminary identification of landslides based on high-resolution remote sensing images in terms of hue. Finally, the landslides are further segmented and extracted by slope, normalized vegetation index and texture feature screening set, so as to accurately identify the spatial distribution of landslides on mountainous roads. The average accuracy of landslide identification by this method reaches 85.73%, and the morphological features extracted from the landslides are complete, which can clearly show the "tongue" and "dustpan" shape of the landslides, and also clearly identify the slide walls and piles of the landslides. The research results can provide scientific reference for landslide identification and risk assessment of mountainous traffic routes in vegetation development areas in China. [ABSTRACT FROM AUTHOR]

Qualitative safety evaluation and analysis can not meet individual safety requirements gradually. In order to better quantify the degree of risk in life and find the quantitative relationship between outliers and individual risk, this paper uses logical regression method to analyze the specific dependencies between independent variables and dependent variables. Taking a cement plant in Henan Province as the investigation object, an emergency early warning model based on logistic regression method is established. The linear relationship between independent variables and accident consequences is calculated and analyzed by SAS software, and compared with cluster analysis method. The results show that compared with clustering analysis, logistic regression model has better accuracy in monitoring outliers, which provides a good analysis basis for individual risk warning and accident prevention. [ABSTRACT FROM AUTHOR]

The application of artificial intelligence (AI) and machine learning develops new pathways and new modalities for the diagnosis and treatment of hypertension. This paper reviews the progress of AI applied in aspects of hypertension prediction, assessment, and assistance for treatment decision-making. In terms of hypertension prediction, AI could build hypertension risk prediction models based on traditional hypertension risk factors combined with imaging, genomics and other factors, which improves the early diagnosis rate of hypertension. The AI expert system identifies complex etiology of hypertension, which makes up for the limitations of clinicians in diagnosis. In terms of hypertension assessment, the prediction model of hypertension complication constructed by AI could predict complications in the heart and the brain blood vessel, and screen out high-risk population for early intervention. In terms of hypertension treatment, the application of clinical decision-making model, drug factor analysis model, monitoring and early warning system, human-computer interaction, etc. could improve the accuracy, timeliness and patient compliance of hypertension treatment, and assist clinicians in making optimal treatment decisions. The exploration of AI in the field of hypertension diagnosis and treatment has established a new model for the chronic disease management of hypertension. [ABSTRACT FROM AUTHOR]

The increasingly frequent illegal transactions hinder the secure transactions of Ethereum, and the anonymity of electronic currency makes it difficult to track and analyze illegal transactions. This paper used the transaction data of the Ethereum platform as the data source, the marked illegal account and unmarked normal account data set as the training set, and the characteristic attributes of the transaction data as the construction basis. Account for the overall forecast. The process uses the T-SNE algorithm to realize the dimensionality reduction and visualization of transaction features, adopts multiple cross-validation, and introduces the SHAP Value factor to judge the positive and negative attributes of the feature. The prediction effect accuracy rate of the established model reaches 94.29%. The evaluation metric for the area (AUC) value reached 0.9846. The proposed scheme can more accurately predict the illegal behavior on the Ethereum trading platform, and will effectively improve the blockchain-based trading environment. [ABSTRACT FROM AUTHOR]

The scale of supercomputers is expanding. Meanwhile, the complexity of scientific applications is also increasing, which leads to many job failures on supercomputers. These failed jobs causes a waste of resources and prolong the waiting time of queuing jobs, which seriously affects the reliability of the system. If these failed jobs can be predicted in advance, necessary measures can be taken to improve the system resource utilization and system execution efficiency, which is very important for the future exascale supercomputers. Therefore, this paper attempts to predict these job failures from the known traditional features and construction features, and find the features and processing methods that can reflect the user􀆳s work behavior patterns and submission behavior patterns. By combining behavior features and traditional features, a comprehensive framework based on tree structure model is proposed to predict job failure. The prediction experimental results show that the comprehensive prediction framework is better than the single model prediction, and the comparative experimental results show that the prediction effect is better than other related methods. [ABSTRACT FROM AUTHOR]

With the widespread popularity of the mobile Internet, the domestic online game market has become increasingly saturated. The cost of acquiring new users for game companies continues to increase. How to prevent the loss of existing users has become the focus of marketing. This paper predicts user churn based on a real game log data. First, user features are extracted and computed from log data. Second, a set of important features is selected by weight. Finally, a binary classification model is constructed with features as input and churn as output. 6 common algorithms such as random forest, support vector machine, multi-layer perceptron, gradient boosting decision tree, and logistic regression are comprehensively compared. The experimental results show that the random forest algorithm performs the best, and its model prediction accuracy reaches 91%. [ABSTRACT FROM AUTHOR]

Accurate estimation of crop coefficient(Kc) is crucial for calculating crop evapotranspiration(ETc), and achieving accurate and effective water management. In order to grasp the continuous dynamic change of Kc in time and further estimate the crop water requirement to guide crop irrigation,in this paper, the super-green algorithm and maximum interclass variance method was adopted for image segmentation to extract the lettuce canopy coverage(PGC), and a lettuce Kc estimation model based on Bayesian optimization XGBoost(Bayesian-XGBoost) was proposed. It provided a new way to guide scientific and rational irrigation for crops. The experimental results showed that: PGC showed a rapid growth trend at first and then tended to be stable during the whole growth period, with a range of 10.38%-81.00% and an average daily increase rate of PGC of 1.56%, which could effectively reflect the change trend of Kc. The Bayesian XGBoost lettuce Kc estimation model constructed with PGC as input achieved the optimal estimation effect when iterating for 400 times. Kc of lettuce at seedling stage, rosette stage, and heading stage was 1.12, 1.29, and 2.26, respectively, with an average error of 2.13% compared with the measured true value. In addition, penman-monteith formula(PM) was further used with Kc estimation model to realize the real-time calculation of lettuce ETc. The average daily ETc of lettuce in the autumn cropping period was 2.38 mm/d. The lettuce Kc estimation model based on Bayesian XGBoost could better estimate lettuce Kc and crop water requirement. [ABSTRACT FROM AUTHOR]

This paper made a comprehensive literature review on the topic of applying machine learning methods to shield tunnelling parameter predictions, stratum predictions ahead of a tunnel face, surface settlements prediction, shield attitude deviation and tool wear predictions. The selections of machine learning methods and the associated input and output parameters were analyzed, and the shortcomings and challenges of existing research were summarized. Some prospects were given, including the model generalization, multi-source heterogeneous data compression and assimilation, data-physics-based intelligent shield tunnelling, big data in shield tunnelling, in order to provide reference and guidance for the future research and engineering practice. [ABSTRACT FROM AUTHOR]

How to select features on semi-supervised data sets by incomplete supervisory information has become a research hotspot in the field of pattern recognition and machine learning. In order to facilitate researchers to systematically understand the research status and development trend of semi-supervised feature selection, this paper reviewed the semi-supervised featu re selection methods. This paper first discussed the classification of semi-supervised feature selection methods and divided them into graph-based methods, pseudo-label-based methods, SVM-based methods and other methods according to their theoretical basis, then introduced and compared typical methods for each category, and then sorted out hot applications of semi-supervised feature selection. Finally, this paper looked forward to the future research directions of semi-supervised feature selection. [ABSTRACT FROM AUTHOR]

The development of society has brought countless data, with the unbalancedness becoming a significant feature of many data sets. So it has come to be a research hotspot for machine learning on how to make those unbalanced data sets obtain better effects of classification. Based on this, this paper conducted a comprehensive research on the current unbalanced data set classification method, and made an overall interpretation and conclusion from such three aspects as the unbalanced data sampling method, the method of machine learning-based improved algorithm and the combination method. It also analyzed and took int o account many factors, including the problems solved by each method, algorithm mentality, application scenarios, as well as the advantages and disadvantages of each, and delivered a summary on potential problems of the classification methods and a prospect on the future research directions [ABSTRACT FROM AUTHOR]

Collecting wearable motion sensor signals and using transfer learning to overcome the inconsistency of data distribution to identify the daily behavior of the human body are very popular technologies. Using wearable sensors to collect signals will result in generating noise samples that affect the transfer effect. Traditional algorithms lack the processing of these samples. To solve this problem， the traditional algorithm was improved by introducing a sample screening algorithm based on Mahalanobis distance， and a transfer learning algorithm T-WMD was proposed that can be used for human activity recognition. And compared with other five algorithms on two public human activity recognition data sets， the results show that the algorithm proposed in this paper can effectively improve the effect of transfer learning. [ABSTRACT FROM AUTHOR]

In the field of tumor diagnosis, the AI-assisted diagnosis system can accurately distinguish tumor attributes and malignant tumor stages, thereby prolonging the survival time of patients. Taking breast tumor as an example, this paper proposes an artificial intelligence-assisted diagnosis model based on supervised learning to solve the problem of overfitting caused by the large amount of data in the feature extraction process. When extracting features, effective feature dimensionality reduction is achieved by introducing hierarchical clustering analysis, and the classified feature data is used as the feature input of the artificial neural network model, so as to realize the effective training of the classifier. The experimental results show that the accuracy and AUC value of the proposed algorithm are improved compared with the control algorithm, indicating that the model can not only solve the problem of overfitting caused by the description of massive feature regions, but also enhance the generalization of the artificial intelligence-aided diagnosis system. The ability to achieve high-precision differentiation of mammography-targeted breast tumors. [ABSTRACT FROM AUTHOR]

In view of the slow detection speed of traditional grain flour species, this study implemented the random forest algorithm-assisted microwave nondestructive testing technology to identify grain flour species efficiently and accurately based on ZYNQ platform. By analyzing the hardware implementation of the random forest model, this paper proposed an improved model parameter structure, which could effectively save the consumption of hardware storage resources. In order to shorten the prediction time of the algorithm and reduce the power consumption of the system, it introduced the early termination recognition mechanism in the hardware implementation to avoid the unnecessary decision tree prediction process on the premise of keeping the accuracy unchanged. In view of the Zedboard development board, it designed a storage scheme for model parameters to make full use of on-board resources and ensure the normal operation of the system. The experimental results show that the implementation time of the scheme with ZYNQ is about 54. 2% shorter than that of the random forest algorithm with traditional CPU, and no loss of recognition accuracy is caused. [ABSTRACT FROM AUTHOR]

Aiming at the security problems caused by fraudulent accounts in the blockchain, this paper proposed a machine learning-based fraud account detection and feature analysis model. It took the real on-chain data on Ethereum into feature extraction and used it as the data source of the model. It obtained the optimal model by comparing different machine learning methods and performing iterative training to obtain the best predictive model. At the same time, it introduced SHAP value to analyze data characteristics. The experimental results show that the fraud account detection model based on XGBoost achieves 0. 205, 0. 084 and 0. 833 in RMSE, MAE and R², which is better than the other comparison models. Combined with the SHAP value, it identifies the key factors that predict fraudulent accounts to provide decision-making reference for the transaction security of blockchain. [ABSTRACT FROM AUTHOR]