Search

One of the most widely used measures of scientific impact is the number of citations. However, due to its heavy-tailed distribution, citations are fundamentally difficult to predict but can be improved. This study was aimed at investigating the factors and parts influencing the citation number of a scientific paper in the otology field. Therefore, this work proposes a new solution that utilizes machine learning and natural language processing to process English text and provides a paper citation as the predicted results. Different algorithms are implemented in this solution, such as linear regression, boosted decision tree, decision forest, and neural networks. The application of neural network regression revealed that papers' abstracts have more influence on the citation numbers of otological articles. This new solution has been developed in visual programming using Microsoft Azure machine learning at the back end and Programming Without Coding Technology at the front end. We recommend using machine learning models to improve the abstracts of research articles to get more citations. [ABSTRACT FROM AUTHOR]

Examination is a particularly important part of the students' whole learning process. Therefore, this paper designs and develops an online examination system. This paper studies an examination recommendation algorithm based on a machine learning neural network model. The algorithm can recommend problems for students according to students' error history, error prone, and knowledge poor problems. Experiments also show that the recommendation algorithm studied in this paper improves the recommendation effect compared with several other similar algorithms. [ABSTRACT FROM AUTHOR]

Lung disease is one of the most harmful diseases in traditional days and is the same nowadays. Early detection is one of the most crucial ways to prevent a human from developing these types of diseases. Many researchers are involved in finding various techniques for predicting the accuracy of the diseases. On the basis of the machine learning algorithm, it was not possible to predict the better accuracy when compared to the deep learning technique; this work has proposed enhanced artificial neural network approaches for the accuracy of lung diseases. Here, the discrete Fourier transform and the Burg auto-regression techniques are used for extracting the computed tomography (CT) scan images, and feature reduction takes place by using principle component analysis (PCA). This proposed work has used the 120 subjective datasets from public landmarks with and without lung diseases. The given dataset is trained by using an enhanced artificial neural network (ANN). The preprocessing techniques are handled by using a Gaussian filter; thus, our proposed approach provides enhanced classification accuracy. Finally, our proposed method is compared with the existing machine learning approach based on its accuracy. [ABSTRACT FROM AUTHOR]

The use of deep learning to improve English speaking has seen tremendous development in recent years. This study evaluates the noise that is present in the English speech environment, employs a two-way search method to select the optimum feature set, and applies a quick correlation filter to remove redundant features in order to increase the accuracy of English voice feature identification. In addition, this article designs a low-pass filter in the complex cepstrum domain to filter the room impulse response in order to obtain the estimated value of the complex cepstrum of the original speech signal. After doing so, the authors transform this estimated value into the time domain in order to obtain the estimated value of the original speech signal. In addition, this paper proposes a corresponding noise elimination model for the purpose of eliminating noise from English speech in a reverberant environment. It also designs a complex cepstrum domain filter in order to conduct simulation research on the different characteristics of the reverberation signal and the pure speech signal in the complex cepstrum domain. In conclusion, this study develops an English voice feature recognition model that is founded on a deep neural network. Furthermore, this paper uses experimental research to validate the validity of the algorithm model that was developed in this study. [ABSTRACT FROM AUTHOR]

The existing deep learning models have problems such as large weight parameters and slow inference speed of equipment. In practical applications such as fire detection, they often cannot be deployed on equipment with limited resources due to the huge amount of parameters and low efficiency. In response to this problem, this paper proposes a lightweight smoke detection model based on the convolutional attention mechanism module. The model is based on the YOLOv5 lightweight framework. The backbone network draws on the GhostNet design idea, replaces the CSP structure of the FPN and head layers with the GhostBottleNeck module, adds a convolutional attention mechanism module to the backbone network layer, and uses the CIoU loss function to improve the regression accuracy. Using YOLOv5s as the benchmark model, the parameter amount of the proposed lightweight neural network model is 2.75 M, and the floating-point calculation amount is 2.56 G, which is much lower than the parameter amount and calculation amount of the benchmark model. Tested on the public fire dataset, compared with the traditional deep learning algorithm, the model proposed in the paper has better detection performance and the detection speed is significantly better than the benchmark model. Tested under the unquantized simulator, the speed of the proposed model to detect a single picture is 60 ms, which can meet the requirements of real-time engineering applications. [ABSTRACT FROM AUTHOR]

The security issues with mobile devices have received more attention as a result of the development of mobile Internet technology and the adoption of mobile intelligent terminal devices. It is becoming more crucial to quickly and effectively identify and remove harmful applications from systems in order to protect user data and personal devices. The Dalvik bytecode, permission applications, and system calls of Android apps are the main targets of the current Android malware analysis approaches. However, in recent years, an increasing amount of Android malware conceals harmful code in native code. The method for using program gene technology to identify malware on the Android platform is presented in this research. This method extracts executable library files from the Native layer binary executable files of Android programs and disassembles the library files to obtain program genes. Then, the programs' genes perform feature screening by the information gain method and next use Word2Vec to express the semantic abstraction of the screened features. Finally, the screened features were used in deep neural network models for training and detection. The experimental results demonstrate that compared with KNN, SVM, and other machine learning algorithms, the deep neural network model is more effective and the detection accuracy reaches up to 97.51%. Thus, it confirmed the feasibility of the Android malicious program detection method based on program genes in this paper. [ABSTRACT FROM AUTHOR]

The low deployment cost and high mobility of unmanned aerial vehicles (UAV) have given UAVs widespread attention in mobile edge computing (MEC). Aiming at the characteristics of dynamic changes in computing tasks generated by the urban transportation network, this paper proposes an UAV-assisted edge computing offloading model; i.e., when the number of tasks is within the capacity of edge servers (ES), most of the tasks are processed by ESs, but when the amount exceeds the capacity, some tasks will be offloaded to UAV and processed by on-board servers on UAVs. To minimize the task delay and the cost of computing tasks, this paper formulates a mathematical model according to the task amount generated by the urban transportation network, in which the task delay is computed by using queueing theory. A deep reinforcement learning algorithm with double deep neural networks (DNN) is used to optimize the model and obtains the resource allocation strategy of UAVs and on-board servers and the offloading strategy of edge computing. Simulation experiments verify the effectiveness of these strategies. [ABSTRACT FROM AUTHOR]

Accurate fault detection in high-voltage direct current (HVDC) transmission lines plays a pivotal role in enhancing operational efficiency, reducing costs, and ensuring grid reliability. This research aims to develop a cost-effective and high-performance fault detection solution for HVDC systems. The primary objective is to accurately identify and localize faults within the power system. In pursuit of this goal, the paper presents a comparative analysis of current and voltage characteristics between the rectifier and inverter sides of the HVDC transmission system and their associated alternating current (AC) counterparts under various fault conditions. Voltage and current features are extracted and optimized using a metaheuristic approach, specifically Harris Hawk's optimization method. Leveraging machine learning (ML) and artificial neural networks (ANN), this technique demonstrates its effectiveness in generating a fault locator with exceptional accuracy. With a substantial volume of data employed for learning and training, the Harris Hawks optimization method exhibits faster convergence compared to other metaheuristic methods examined in this study. The research findings are applied to simulate diverse fault types and unknown fault locations at multiple system points. Evaluating the fault detection system's effectiveness, quantified through metrics such as specificity, accuracy, F1 score, and sensitivity, yields remarkable results, with percentages of 99.01%, 98.69%, 98.64%, and 98.67%, respectively. This research underscores the critical role of accurate fault detection in HVDC systems, offering valuable insights into optimizing grid performance and reliability. [ABSTRACT FROM AUTHOR]

In order to improve the reactive power optimization effect of the distribution network, this paper combines the multiagent deep reinforcement learning algorithm to analyze the reactive power optimization strategy of the distribution network and constructs an intelligent optimization model. Moreover, the simulation models of power conversion elements, power transmission elements, control elements, and measurement elements in the platform are described, and the program structure and interactive functions are analyzed. In addition, this paper proposes a reactive power optimization method for distribution networks based on data-driven thinking. Finally, by using historical data and an artificial neural network, this paper extracts electrical quantity data such as load power and distributed power output and environmental data such as temperature and wind speed to perform multiagent analysis. The experimental verification shows that the reactive power optimization effect of the distribution network based on multiagent and multiagent deep reinforcement learning proposed in this paper is very good. [ABSTRACT FROM AUTHOR]

Network information technology and distance technology learning provide convenience for college students to learn online courses, but some problems have also been found in practice, and schools need to pay attention to improving students' learning quality and supervision. The cross-spatial nature of the study can be used to study how to detect students' learning fatigue and learning concentration in online classrooms. This paper first designs a lightweight convolutional neural network model for eye state classification and verifies the performance of the model. The designed model has a compact structure and a high recognition rate. Combined with the human eye positioning algorithm, the recognition of the opening and closing state of the eyes is realized. Finally, the feasibility of using the PERCLOS value for fatigue detection, Euler pitch angle, and yaw is verified by experiments. Corners can be used to detect student attention. The method can enhance the synergistic supervision of other cooperative methods, thus improving the quality and effectiveness of online learning for college students, promoting the development of digital modern teaching and learning management models, and exploring possible future technologies and corresponding changes in teaching methods and management models. [ABSTRACT FROM AUTHOR]

Contextual representation recommendation directly uses contextual prefiltering technology when processing user contextual data, which is not the integration of context and model in the true sense. To this end, this paper proposes a context-aware recommendation model based on probability matrix factorization. We design a music genre style recognition and generation network. In this network, all the sub-networks of music genres share the explanation layer, which can greatly reduce the learning of model parameters and improve the learning efficiency. Each music genre sub-network analyzes music of different genres, realizing the effect of multitasking simultaneous processing. In this paper, a music style recognition method using a combination of independent recurrent neural network and scattering transform is proposed. The relevant characteristics of traditional audio processing methods are analyzed, and their suitable application scenarios and inapplicability in this task scenario are expounded. Starting from the principle of scattering transform, the superiority and rationality of using scattering transform in this task are explained. This paper proposes a music style recognition method combining two strategies of scattering transform and independent recurrent neural network. In the case that the incremental data set is all labeled, this paper introduces the solution of the convex hull vector, which reduces the training time of the initial sample. According to the error push strategy, an incremental learning algorithm based on convex hull vector and error push strategy is proposed, which can effectively filter historical useful information and at the same time eliminate useless information in new samples. Experiments show that this method improves the accuracy of music style recognition to a certain extent. Music style recognition based on independent recurrent neural network can achieve better performance. [ABSTRACT FROM AUTHOR]

In order to solve the shortcomings of complex calculation and time consumption of fabric physical simulation methods, many single-precision fabric simulation technologies based on machine learning methods have emerged and the amount of calculation is increased for regions with small changes. Aiming at this problem, this paper proposes two multi-precision fabric modeling method based on machine learning. Firstly, the fabric mesh is simulated by the physical method, the initial position of the vertex is calculated, and the deformation of each region of the fabric is measured by Rayleigh quotient curvature, and the multi-precision fabric mesh is constructed. Secondly, the multi-precision fabric graph structure and geometry image are extracted from the multiprecision fabric mesh. Finally, the subgraph convolutional neural network and super-resolution network are trained to model the multi-precision fabric, and we compared the two different multi-precision fabric machine learning modeling methods. Through the experimental verification, in the garment modeling, the garment modeled by the subgraph convolutional neural network is no longer only dependent on the change of human joints, resulting in a more realistic effect. At the same time, the efficiency of the subgraph convolutional neural network is 25.3% higher than that of the single-precision garment modeling based on the machine learning method. In the cloth simulation, speed of the super-resolution network is nearly 16 times faster than that of the physical simulation, which supplements the imperfection of insufficient flexibility of the subgraph convolutional neural network modeling. [ABSTRACT FROM AUTHOR]

Tennis is an important sporting event. In China, the number of people who study and participate in tennis can be said to be quite large, but there are not many people who insist on playing tennis in the end. Some coaches and tennis groups have come up with a number of different teaching styles in order to keep tennis players going. Its main features are as follows: To cultivate students' interest in learning, the sequence of strokes in tennis is used for teaching. Although tennis has no special requirements for the physical condition of the athlete, tennis is a relatively difficult sport to master. What is lacking at present is more effective and simpler teaching methods, so training should be carried out in a targeted manner in the tennis baseline stroke technique. In order to make the tennis baseline stroke teaching more intuitive and easy to learn, this paper applies the neural network learning algorithm to the research and analysis of the tennis baseline stroke technique and proposes the core technology of the tennis baseline stroke technique. On this basis, the key techniques of tennis baseline stroke technique are discussed. Based on this, a basic model based on deep convolutional neural network is proposed. The experimental results show that the forehand scores of the three throwing methods in the experimental group are 6.47 and 7.28, respectively, which is better than the control group. The three throwing methods are self-throwing, close throwing, and long throwing. It shows that the teaching method in this paper can greatly improve the students' tennis baseline hitting skills. [ABSTRACT FROM AUTHOR]

The Internet has now ingrained itself into every aspect of people's lives and has grown to be a necessity. Machine learning technology is applied to the design of music teaching and teaching assistant systems with the aim of bringing convenience to students and teachers in teaching and learning and improving teaching efficiency and quality through the design and implementation of a friendly and interactive intelligent music assistant teaching system. The B/S mode framework aids in the realisation of the hierarchy and module structure of the system design during the system implementation process. Last but not least, this paper looks at the system modules, confirms all of the system's operations, and makes sure each functional module is working properly. The algorithm is straightforward, effective, simple to use, and user-friendly, and the system is expandable, portable, and transparent. It is an excellent teaching tool for music. [ABSTRACT FROM AUTHOR]

Not only were traditional artificial neural networks and machine learning difficult to meet the processing needs of massive images in feature extraction and model training but also they had low efficiency and low classification accuracy when they were applied to image classification. Therefore, this paper proposed a deep learning model of image classification, which aimed to provide foundation and support for image classification and recognition of large datasets. Firstly, based on the analysis of the basic theory of neural network, this paper expounded the different types of convolution neural network and the basic process of its application in image classification. Secondly, based on the existing convolution neural network model, the noise reduction and parameter adjustment were carried out in the feature extraction process, and an image classification depth learning model was proposed based on the improved convolution neural network structure. Finally, the structure of the deep learning model was optimized to improve the classification efficiency and accuracy of the model. In order to verify the effectiveness of the deep learning model proposed in this paper in image classification, the relationship between the accuracy of several common network models in image classification and the number of iterations was compared through experiments. The results showed that the model proposed in this paper was better than other models in classification accuracy. At the same time, the classification accuracy of the deep learning model before and after optimization was compared and analyzed by using the training set and test set. The results showed that the accuracy of image classification had been greatly improved after the model proposed in this paper had been optimized to a certain extent. [ABSTRACT FROM AUTHOR]

As China's economic level and industrial volume continue to develop and expand, the traditional methods of business management and resource scheduling demonstrate significant limitations and misalignments with China's daily economic activities. Traditional industrial and commercial management resource scheduling is highly reliant on manual labor. When confronted with the requirements of large-scale project management, the pure manual mode cannot track the real-time progress of the project flexibly, effectively, and in a timely manner, resulting in the inability to complete the corresponding resource-scheduling work efficiently, which will affect the overall operation progress of the project. Deep neural networks have a high-application potential for solving extremely complex and highly nonlinear optimization problems. Artificial intelligence and deep learning research have advanced at a rapid pace over the past few decades, thanks to the efforts of numerous researchers. Combined with GPU technology, the deep learning framework can provide an extremely complex optimization problem with a practical and feasible optimization scheme and corresponding solution path in a very short amount of time. Therefore, this paper explores the potential application of deep learning technology to industrial and commercial resource-scheduling management. By analyzing the benefits of deep learning technology and the bottleneck issues of existing industrial and commercial resource scheduling, a real-time optimized industrial and commercial resource-scheduling model based on deep learning technology is developed. The model is evaluated using the respective data set. The test results demonstrate that the resource-scheduling model proposed in this paper has strong real-time and high-operation efficiency and can assist engineers in completing the corresponding resource-scheduling tasks. [ABSTRACT FROM AUTHOR]

Liuzhou is a rich tourism city in China. It is well known for its ethnic and prehistoric culture, folk songs, rare stones, and urban landscape. The demand of tourism in Liuzhou city is increasing day by day. Therefore, a system is needed to accurately predict the increasing demand of tourism in Liuzhou city. For this reason, based on the examination of historical visitor data in natural sites especially in Liuzhou city, this research employs an important machine learning and deep learning approach. The purpose of this study is to identify the consumption patterns and improve prediction, prejudgment, and preparation abilities by incorporating them into an intelligent tourism service platform, preventing visitors from travelling at inconvenient times and providing appropriate suggestions to scenic site managers. In this paper, the Sparse Principal Component Analysis-Long-Short-Term Memory (SPCA-LSTM) model has been updated to the Sparse Principal Component Analysis Convolutional Neural Network Long-Short-Term Memory (SPCA-CNNLSTM) model to accurately predict the tourist traffic during the holidays. Convolutional and pooling layers are added to the network topology to extract the local characteristics of the input data. The data of passenger traffic and influencing factors of Liuzhou scenic area from the months of Sept. 2015 to Nov. 2019 were used as the data set for the experiments. A hybrid-forecasting model is also proposed in the paper, which first removes noise from international crude oil data using compression-aware denoising preprocessing and then combines compression-aware denoising with machine learning using artificial neural network (ANN) and support vector regression (SVR). The experimental result shows that the SPCA-CNNLSTM model predicts better values than the SPCA-LSTM model. [ABSTRACT FROM AUTHOR]

This paper proposes a nonlinear autoregressive neural network (NARNET) method for the investment performance evaluation of state-owned enterprises (SOE). It is different from the traditional method based on machine learning, such as linear regression, structural equation, clustering, and principal component analysis; this paper uses a regression prediction method to analyze investment efficiency. In this paper, we firstly analyze the relationship between diversified ownership reform, corporate debt leverage, and the investment efficiency of state-owned enterprises (SOE). Secondly, a set of investment efficiency evaluation index system for SOE was constructed, and a nonlinear autoregressive neural network approach was used for verification. The data of A-share state-owned listed companies in Shanghai and Shenzhen stock exchanges from 2009 to 2018 are taken as a sample. The experimental results show that the output value from the NARNET is highly fitted to the actual data. Based on the neural network model regression analysis, this paper conducts a descriptive statistical analysis of the main variables and control variables of the evaluation indicators. It verifies the direct impact of diversified ownership reform on the investment efficiency of SOE and the indirect impact on the investment efficiency of SOE through corporate debt leverage. [ABSTRACT FROM AUTHOR]

In order to effectively reduce the energy consumption, improve the efficiency of data collection in HWSNs, and prolong the lifetime of the overall network, the clustering method is one of the most effective methods in the data collection methods for HWSNs. The data collection strategy of HWSNs based on the clustering method mainly includes three stages: (1) selecting the appropriate cluster head, (2) forming between clusters, and (3) transferring data between clusters. Among them, the selection of the cluster heads in the first stage. The optimal number of cluster heads in the formation of clusters in the second stage is the core and key to the clustering data collection of HWSNs. In the stage of cluster head selection, a data collection strategy for HWSNs based on the clustering method is proposed. Sink establishes an extreme learning machine neural network model. The cluster member nodes select cluster heads based on the remaining energy of the sensor node, the number of the neighbor node, and the distance to the sink. The best cluster head node is selected through the adaptive learning of the online sequence extreme learning machine. Through comprehensive consideration of various factors to complete the clustering process, the gray wolf algorithm is used to optimize the number of clusters, balance the effect of clustering, and improve the efficiency of data collection while reducing energy consumption. An energy efficient and reliable clustering data collection strategy for HWSNs based on the online sequence extreme learning machine and the gray wolf optimization algorithm is proposed in this paper. The simulation results show that the proposed algorithm not only significantly improves the efficiency of the data collection and reduces energy consumption but also comprehensively improves the reliability of the network and prolongs the network's lifetime. [ABSTRACT FROM AUTHOR]

In this paper, an in-depth study and analysis of attribute modelling and knowledge acquisition of massive images are conducted using image recognition. For the complexity of association relationships between attributes of incomplete data, a single-output subnetwork modelling method for incomplete data is proposed to build a neural network model with each missing attribute as output alone and other attributes as input in turn, and the network structure can deeply portray the association relationships between each attribute and other attributes. To address the problem of incomplete model inputs due to the presence of missing values, we propose to treat and describe the missing values as system-level variables and realize the alternate update of network parameters and dynamic filling of missing values through iterative learning among subnets. The method can effectively utilize the information of all the present attribute values in incomplete data, and the obtained subnetwork population model is a fit to the attribute association relationships implied by all the present attribute values in incomplete data. The strengths and weaknesses of existing image semantic modelling algorithms are analysed. To reduce the workload of manually labelling data, this paper proposes the use of a streaming learning algorithm to automatically pass image-level semantic labels to pixel regions of an image, where the algorithm does not need to rely on external detectors and a priori knowledge of the dataset. Then, an efficient deep neural network mapping algorithm is designed and implemented for the microprocessing architecture and software programming framework of this edge processor, and a layout scheme is proposed to place the input feature maps outside the kernel DDR and the reordered convolutional kernel matrices inside the kernel storage body and to design corresponding efficient vectorization algorithms for the multidimensional matrix convolution computation, multidimensional pooling computation, local linear normalization, etc., which exist in the deep convolutional neural network model. The efficient vectorized mapping scheme is designed for the multidimensional matrix convolution computation, multidimensional pooling computation, local linear normalization, etc. in the deep convolutional neural network model so that the utilization of MAC components in the core loop can reach 100%. [ABSTRACT FROM AUTHOR]

Intelligent diagnosis applies deep learning algorithms to mechanical fault diagnosis, which can classify the fault forms of machines or parts efficiently. At present, the intelligent diagnosis of rolling bearings mostly adopts a single-sensor signal, and multisensor information can provide more comprehensive fault features for the deep learning model to improve the generalization ability. In order to apply multisensor information more effectively, this paper proposes a multiscale convolutional neural network model based on global average pooling. The diagnostic model introduces a multiscale convolution kernel in the feature extraction process, which improves the robustness of the model. Meanwhile, its parallel structure also makes up for the shortcomings of the multichannel input fusion method. In the multiscale fusion process, the global average pooling method is used to replace the way to reshape the feature maps into a one-dimensional feature vector in the traditional convolutional neural network, which effectively retains the spatial structure of the feature maps. The model proposed in this paper has been verified by the bearing fault data collected by the experimental platform. The experimental results show that the algorithm proposed in this paper can fuse multisensor data effectively. Compared with other data fusion algorithms, the multiscale convolutional neural network model based on global average pooling has shorter training epochs and better fault diagnosis results. [ABSTRACT FROM AUTHOR]

The performance of any machine learning model largely depends on the type of input data provided. The higher the volume and variety of the data, the better the machine learning models get trained, thereby producing more accurate results. However, it is a challenging task to get high volume of data in some cases containing enough variety. Handwritten character recognition for Odia language is one of them. NITROHCS v1.0 for handwritten Odia characters and the ISI image database for handwritten Odia numerals are the standard Odia language datasets available for the research community. This paper shows the performance of five different machine learning models that uses a convolutional neural network to identify handwritten characters in response to handwritten datasets that are manipulated and expanded using several augmentation techniques to create variation and increase the volume of the data in the given dataset. These models, with the augmentation techniques discussed in the paper, even lead to a further increase in accuracy by approximately 1% across the models. The claims are supported by the results from the experiments done on the proposed convolutional neural network models on standard available Odia character and numeral data set. [ABSTRACT FROM AUTHOR]

Summary: Many electricity consumers around the world are billed electric peak load charges. In the United States, these demand charges can contribute up to 70% of a consumer's electricity bill. Research has shown that the financial impact of these charges to the consumers can be reduced by acting on the intelligence provided by peak electric load day (PELD) forecasts. Unfortunately, published research detailing PELDs forecasting methodologies for facilities adopting behind the meter renewable electricity generation (BTMREG) is non‐existent. This paper contributes: (a) a PELD forecasting methodology applicable to consumers with BTMREG. A case study demonstrates the methodology's ability to achieve 93% of the potential savings in kW, translating to demand charge reductions of approximately US$ 142 129 per year. (b) The first side‐by‐side performance comparisons of electric load and PELD forecasting models for scenarios with and without BTMREG. (c) The first PELD forecasting model savings comparison for scenarios with and without BTMREG. Experimental results suggest that counterintuitively, BTMREG adoption can translate into higher peak load savings for electricity consumers. [ABSTRACT FROM AUTHOR]

Medical imaging is an essential technique for the diagnosis and treatment of diseases in modern clinics. Soft computing plays a major role in the recent advances in medical imaging. It handles uncertainties and improves the qualities of an image. Until now, various soft computing approaches have been proposed for medical applications. This paper discusses various medical imaging modalities and presents a short review of soft computing approaches such as fuzzy logic, artificial neural network, genetic algorithm, machine learning, and deep learning. We also studied and compared each approach used for other imaging modalities based on the certain parameter used for the system evaluation. Finally, based on comparative analysis, the possible research strategies for further development are proposed. As far as we know, no previous work examined this issue. [ABSTRACT FROM AUTHOR]

Potential topics include but are not limited to the following: (1) Security machine learning modelling and architecture (2) Secure multiparty computation techniques for machine learning (3) Attacks against machine learning (4) Machine learning threat intelligence (5) Machine learning for cybersecurity (6) Machine learning for intrusion detection and response (7) Machine learning for multimedia data security (8) Machine learning for public safety After a thorough review process, this special issue has selected a set of eight papers to provide new insights on the abovementioned research areas. Machine learning (ML) has recently gained a renewed interest as the technology powering it has become more widely available and accessible to organizations of all sizes. [Extracted from the article]

With the continuous development of Earth science, soil temperature has received more and more attention in Earth system research as an important parameter. The change of soil temperature (Ts) in different regions and related time series is affected by many factors, which bring certain difficulties to the accuracy of soil temperature prediction and the robustness of the algorithm. In this paper, an embedded network prediction model based on the gated recurrent unit (GRU) model is proposed to learn the local and global features of historical temperature for improving the prediction performance of soil temperature. We input different steps into the GRU model, and the output is weighted to obtain the final prediction result. In order to obtain the global characteristics of soil temperature, we connect the previous steps to the output layer directly, and the local characteristics of soil temperature are obtained through the following steps. This paper uses the soil temperature data from two meteorological stations (Laegern and Fluehli) in Switzerland as the input data to predict the soil temperature for different soil depths (5 cm, 10 cm, and 15 cm) at different time points (6 hrs, 12 hrs, and 24 hrs), using RMSE, MAE, MSE, and R 2 performance indicators as evaluation criteria to verify the accuracy of prediction. As the experimental results show, our method has the best performance compared to the others (artificial neural networks (ANN), extreme learning machine model (ELM), long short-term memory network (LSTM), gated recurrent unit network (GRU)). In particular, we estimated the soil temperature at the soil depth of 10 cm of the Fluehli station in the coming 6 hrs; our method achieved the best performance; and, meanwhile, our model achieved the maximum value of R 2 (0.9914) and the minimum values of RMSE (0.4668), MAE (0.2585), and MSE (0.2214) compared with the other four models. Therefore, our model can not only predict the soil temperature at different depths but also improve the accuracy. [ABSTRACT FROM AUTHOR]

This paper implements a deep learning-based modulation pattern recognition algorithm for communication signals using a convolutional neural network architecture as a modulation recognizer. In this paper, a multiple-parallel complex convolutional neural network architecture is proposed to meet the demand of complex baseband processing of all-digital communication signals. The architecture learns the structured features of the real and imaginary parts of the baseband signal through parallel branches and fuses them at the output according to certain rules to obtain the final output, which realizes the fitting process to the complex numerical mapping. By comparing and analyzing several commonly used time-frequency analysis methods, a time-frequency analysis method that can well highlight the differences between different signal modulation patterns is selected to convert the time-frequency map into a digital image that can be processed by a deep network. In order to fully extract the spatial and temporal characteristics of the signal, the CLP algorithm of the CNN network and LSTM network in parallel is proposed. The CNN network and LSTM network are used to extract the spatial features and temporal features of the signal, respectively, and the fusion of the two features as well as the classification is performed. Finally, the optimal model and parameters are obtained through the design of the modulation recognizer based on the convolutional neural network and the performance analysis of the convolutional neural network model. The simulation experimental results show that the improved convolutional neural network can produce certain performance gains in radio signal modulation style recognition. This promotes the application of machine learning algorithms in the field of radio signal modulation pattern recognition. [ABSTRACT FROM AUTHOR]

As the level of tennis improves, the ability and strategy to play in the game determine the responsibility for the outcome of the game. It is committed to improving the professional and strategic level of Asian tennis players and narrowing the gap with high-level European and American tennis players. The purpose of this paper is to study the application of machine learning in the study of the evaluation model of the technical and tactical effectiveness of tennis matches, and proposes the decision tree algorithm, artificial neural network, reinforcement learning algorithm, and related concepts of tennis matches. Therefore, this paper selects Federer's technical and tactical games from 2013 to 2017 as the research object. And by paying attention to the application characteristics of Federer's methods and strategies in each stage, a detailed statistical analysis of the data is carried out point by point. The exploratory outcomes show that through the AI calculation, it is found that the incredible skill and vital sufficiency of Federer's hard court game change around 0.600, and the typical worth is 0.594. Particular and vital efficiency showed a sluggish recuperation in 2017. [ABSTRACT FROM AUTHOR]

In recent years, the increase of customer loan risk and the aggravation of the epidemic have led to the increase of customer default risk. Therefore, identifying high-risk customers has become an important research hotspot for banks. The customer's credit is the standard to evaluate the loan amount and interest rate, and the ability to quickly identify customer information has become a research hotspot. Based on the bank credit application scenario, this paper realizes function extraction and data processing for customer basic attribute data and download transaction data. Then, a linear regression model with penalty and a neural network prediction model are proposed to improve the accuracy of bankruptcy assessment and achieve local optimization. In this way, the implicit risk prediction and control of customer credit are improved, and the default risk of bank loans is significantly reduced. According to the characteristics of the collected sample data, the most appropriate penalty linear regression prediction algorithm is selected and the experimental analysis is carried out to improve the risk management level of banks. The experimental results show that the improved logistic regression and neural network model has obvious advantages in the prediction effect for four models. [ABSTRACT FROM AUTHOR]

BIM (building information modeling) is a building information modeling technology. It is a modeling technology that has quietly emerged in the architectural design and construction industry and will gradually replace the traditional CAD drawing technology. In addition to carrying geometric information of graphics, it can also carry buildings and building components. The engineering and nonengineering information of the building space has a higher degree of visualization and a stronger sense of three-dimensionality, and all the building information can be put into a model. The model can provide dynamic information on engineering construction cost management processes and can be processed by a computer in real time. The purpose of this paper is to study the new method of stadium project building information model management after the introduction of deep learning technology. This article first introduces the artificial neural network under machine learning algorithms by building a neural network model and combining it with the engineering construction information model and then integrating machine learning algorithms into the construction information model technology so that the originally three-dimensional model can further information integration. Compared with the original building information model, the data processing is more efficient and the management level has greatly improved. The experimental results of this paper show that machine learning algorithms can optimize the construction information model of stadium engineering and increase the efficiency of project management by 20%. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs), commonly known as drones, have been progressively prevalent due to their capability to operate quickly and their vast range of applications in a variety of real-world circumstances. The utilization of UAVs in precision farming has lately gained a lot of attention from the scientific community. This study addresses with the assistance of drones in the precision agricultural area. This paper makes significant contributions by analyzing communication protocols and applying them to the challenge of commanding a fleet of drones to protect crops from parasite infestations. In this research, the effectiveness of nine powerful deep neural network models is measured for the detection of plant diseases using diverse methodologies. These deep neural networks are adapted to the immediate situation using transfer learning and deep extraction of features approaches. The presented study takes into account the used pretrained deep learning model for extracting features and fine-tuning. The deep feature extraction characteristics are subsequently categorized using support vector machines (SVMs) and extreme learning machines (ELMs). For measuring performance, the precision, sensitivities, specific, and F1-score are all evaluated. Deep feature extraction and SVM/ELM classification generated better outcomes than transfer learning, according to the analysis result. Furthermore, the analysis of the various methodologies tries to assess their effectiveness and costs. The different approaches, for example, confront difficulties such as investigating the region in the shortest possible time feasible, while eliminating the same region being searched by more drones, detecting parasites, and stopping their spread by applying the appropriate number of pesticides. Simulation models are a significant aid to researchers in conducting to evaluate these technologies and creating specific tactics and coordinating procedures capable of effectively supporting farms and achieving the aim. The main objective of this paper is to compare the search techniques of two distinct methods of parasitic to identify performance. [ABSTRACT FROM AUTHOR]

The demand for talents extends beyond theoretical knowledge to include students' IPE (Ideological and Political Education). We can only continue to promote the rapid development of university teaching in China by putting in place a solid management system. It is the foundation of college students' IPE in this era of rapid information technology development to accurately adapt to and understand the actual problems and requirements of IPE proposed by the development of the times and innovate and develop accordingly. Deep learning (DL) is a sophisticated machine learning algorithm that outperforms previous technologies in speech and image recognition. In this paper, DLNN (deep learning neural network) technology is applied to IPE evaluation and a set of university-specific IPE evaluation index systems is developed. The BPNN (BP Neural Network) evaluation model is used to train and study a specific amount of teaching quality data in the MATLAB simulation tool. On the prediction of IPE evaluation, the BPNN algorithm has a prediction error of about 0.050.4 according to the findings. The validity and accuracy of using the BPNN algorithm to model IPE quality are demonstrated. [ABSTRACT FROM AUTHOR]

Generally, in-depth learning has been extensively employed in numerous industries to enhance the growth of economic globalization since the dawn of the big data age. At the same time, the demand for foreign language talent has risen dramatically, and more and more businesses are steadily raising their English proficiency standards. International interactions, as well as scientific and technical exchanges, are influenced by English communicating competence. As a result, colleges and universities place a high value on students studying English. However, English learning is also a compulsory course in Colleges and universities, which is different from other courses. Therefore, in setting teaching objectives, arranging teaching activities, and compiling teaching contents, we should highlight students' personalized needs and formulate learning plans in combination with the individual requirements of each student. Aiming at this problem, this paper adopts the deep learning method to study the personalized learning of College English. Deep learning algorithm utilization in the development of college students' English learning reduces teachers' workload and focuses more on students' personalized needs, which is beneficial to teachers' teaching and students' learning. By analyzing the deep learning neural network model, the process of English speech recognition is described, and the characteristic parameters of English speech are extracted. Then compare and explain the characteristics of deep learning and shallow learning, analyze the relationship between them, and clarify the route of deep learning. Finally, the effect of College Students' personalized learning is analyzed by random sampling, and the effect of College English personalized learning based on deep learning is explained from two aspects: listening effect and reading practice. [ABSTRACT FROM AUTHOR]

In the field of intelligent transportation systems (ITS), video surveillance is a hot research topic; this surveillance is used in a variety of applications, such as detecting the cause of an accident, tracking down a specific vehicle, and discovering routes between major locations. Object detection and shadow elimination are the main tasks in this area. Object detection in computer vision is a critical and vital part of object and scene recognition, and its applications are vast in the fields of surveillance and artificial intelligence. Additionally, other challenges arise in regard to video surveillance, including the recognition of text. Based on shadow elevation, we present in this work an inner-outer outline profile (IOOPL) algorithm for detecting the three levels of object boundaries. A system of video surveillance monitoring of traffic can be incorporated into this method. It is essential to identify the type of detected objects in intelligent transportation systems (ITS) to track safely and estimate traffic parameters correctly. This work addresses the problem of not recognizing object shadows as part of the object itself in-vehicle image segmentation. This paper proposes an approach for detecting and segmenting vehicles by eliminating their shadow counterparts using the delta learning algorithm (Widrow-Hoff learning rule), where the system is trained with various types of vehicles according to their appearance, colors, and build types. An essential aspect of the intelligent transportation system is recognizing the type of the detected object so that it can be tracked reliably and the traffic parameters can be estimated correctly. Furthermore, we propose to classify vehicles using a machine learning algorithm consisting of artificial neural networks trained using the delta learning algorithm, a high-performance machine learning algorithm, to obtain information regarding their travels. The paper also presents a method for recognizing the number plate using text correlation and edge dilation techniques. In regard to video text recognition, number plate recognition is a challenging task. [ABSTRACT FROM AUTHOR]

Physical exercise behavior is to protect physical health through scientific physical activity (certain frequency, time, and intensity) in leisure time. The purpose of this paper is to study how to analyze and study the related factors of adolescent physical exercise behavior based on an artificial neural network model and describe the BP learning algorithm. This paper raises the question of the influencing factors of adolescents' physical exercise behavior. This problem is based on an artificial neural network, so the paper expounds around the concept of artificial neural network and related algorithms and designs and analyzes relevant factors. The experimental results show that among the 4-17-year-old respondents, 45 students have the habit of physical exercise, accounting for 37.5% of the respondents in this age group. Among the 59 people with the habit of physical exercise in this survey, 41 people, accounting for 69.5%, believed that their interest in sports was greatly influenced by their surrounding classmates. There are 40 parents who have one parent who is college or above, accounting for 67.8% and other data. All of them show that the influencing factors of adolescents' physical exercise behavior come from many aspects. [ABSTRACT FROM AUTHOR]

Optimizing the detection of intrusions is becoming more crucial due to the continuously rising rates and ferocity of cyber threats and attacks. One of the popular methods to optimize the accuracy of intrusion detection systems (IDSs) is by employing machine learning (ML) techniques. However, there are many factors that affect the accuracy of the ML-based IDSs. One of these factors is noise, which can be in the form of mislabelled instances, outliers, or extreme values. Determining the extent effect of noise helps to design and build more robust ML-based IDSs. This paper empirically examines the extent effect of noise on the accuracy of the ML-based IDSs by conducting a wide set of different experiments. The used ML algorithms are decision tree (DT), random forest (RF), support vector machine (SVM), artificial neural networks (ANNs), and Naïve Bayes (NB). In addition, the experiments are conducted on two widely used intrusion datasets, which are NSL-KDD and UNSW-NB15. Moreover, the paper also investigates the use of these ML algorithms as base classifiers with two ensembles of classifiers learning methods, which are bagging and boosting. The detailed results and findings are illustrated and discussed in this paper. [ABSTRACT FROM AUTHOR]

At present, there are more and more frauds in the financial field. The detection and prevention of financial frauds are of great significance for regulating and maintaining a reasonable financial order. Deep learning algorithms are widely used because of their high recognition rate, good robustness, and strong implementation. Therefore, in the context of e-commerce big data, this paper proposes a quantitative detection algorithm for financial fraud based on deep learning. First, the encoders are used to extract the features of the behaviour. At the same time, in order to reduce the computational complexity, the feature extraction is restricted to the space-time volume of the dense trajectory. Second, the neural network model is used to transform features into behavioural visual word representations, and feature fusion is performed using weighted correlation methods to improve feature classification capabilities. Finally, sparse reconstruction errors are used to judge and detect financial fraud. This method builds a deep neural network model with multiple hidden layers, learns the characteristic expression of the data, and fully depicts the rich internal information of the data, thereby improving the accuracy of financial fraud detection. Experimental results show that this method can effectively learn the essential characteristics of the data, and significantly improve the detection rate of fraud detection algorithms. [ABSTRACT FROM AUTHOR]

Solar energy is widely adopted today and produced by photovoltaic or concentrator solar power (CSP). Photovoltaic technology is the most prevalent, thanks to its well-established technology and low costs. CSP technology, on the other hand, has received less attention and interest, as it requires larger investments and a considerable surface. A relevant difficulty connected to the CSP is decoupling solar randomness and energy production. This paper proposes an artificial neural network (ANN) which foresees energy production using a solar parabolic dish installed at Politecnico di Torino (Energy Center Lab). The investigation was performed using a backpropagation ANN. Different learning algorithms were used: Levenberg-Marquardt, Bayesian regularization, resilient backpropagation, and scaled conjugate gradient. Seven atmospheric condition parameters were adopted (humidity, temperature, pressure, wind velocity and direction, solar radiation, and rain), to calculate the receiver temperature as an output. Bayesian regularization was found to be the optimal model for CSP energy production. The results of this investigation suggest that the ANNs are a strong, reliable, and useful tool for predicting temperature in a CSP receiver that can be of great value in the forecasting of energy production. The outcome of this investigation can simplify energy production forecasting using readily available meteorological data. [ABSTRACT FROM AUTHOR]

The computational aesthetics of pictorial art is an important part of human artistic creation, and the computational aesthetics of pictorial art images is a computationally computable human aesthetic process using machines, which has important applications and scientific significance in the automated analysis of large-scale paintings and the computational modeling of perception by machines. To this end, this paper proposes a multitask convolutional neural network model for emotion and rating of artworks. (1) An artwork appreciation dataset consisting of fifty Chinese paintings and fifty Western oil paintings was created, and twenty subjects were recruited to score the art appreciation of one hundred artworks in the dataset, covering both painting aesthetic evaluation and painting emotion evaluation. (2) Based on the artwork art appreciation dataset, an AlexNet-based convolutional neural network model is proposed to utilize the powerful feature extraction and classification capabilities of neural networks to complete artwork art appreciation, and an oversampling method and multitask learning method are used to improve the overall recognition accuracy. (3) Compared with the combination of traditional manual features + machine learning algorithms, the end-to-end multitask convolutional neural network proposed in this paper has the highest accuracy rate of 74.57%/71.43%/74.12%. [ABSTRACT FROM AUTHOR]

This paper presents a fluid sloshing model using the artificial neural network method (ANN). Determining the fluid sloshing model in the tank is a challenging task due to its nonlinearity and complexity of behavior to its environmental and operational conditions. Due to the problems of laboratory modeling, the use of numerical modeling to analyze this phenomenon can be justified. In this paper, first, the fluid sloshing in the tank is simulated by the smooth particle hydrodynamics method (SPH). The input-output data for training the artificial neural network is based on the obtained results. Finally, the maximum force due to the fluid sloshing is obtained by changing different parameters. [ABSTRACT FROM AUTHOR]

As a result of the fast rise of globalization, people in China are learning English at a rapid pace. However, there is a severe shortage of English teachers in the region, which is a major hindrance. To address these concerns, a deep learning-based algorithm is proposed that can not only check English pronunciation but also help learners distinguish between phonemic and quality phonemic while listening and differentiating, as well as correct phonemic errors, thereby increasing their language learning capacity. In order to study the application of nonlinear network identification technology in English learning, this paper evaluates the English pronunciation quality through the deep learning algorithm of deep learning combined with the related contents of neural network data model, and the experimental results of speech recognition structure are analyzed and discussed in detail. The concordance between machine and manual intonation evaluation is 80%, the concordance rate of adjacent intonation evaluation is 98.33%, and the Pearson correlation coefficient is 0.627 that shows the technique is reliable. The method of English pronunciation and speech identification model is sensible and dependable, which can give beginners a punctual, exact and impartial judgment and response guidance, assist learners to get on the differences between their phonemic and standard phonemic, and correct phonemic mistakes, in order to enhance the ability of oral English learning. [ABSTRACT FROM AUTHOR]

As the core of artificial intelligence, machine learning has strong application advantages in multi-criteria intelligent evaluation and decision-making. The level of sustainable development is of great significance to the safety evaluation of coal mining enterprises. BP neural network is a classical algorithm model in machine learning. In this paper, the BP neural network is applied to the sustainable development level decision-making and safety evaluation of coal mining enterprises. Based on the analysis of the evaluation method for sustainable development of coal enterprises, the evaluation index system of sustainable development of coal enterprises is established, and a multi-layer forward neural network model based on error backpropagation algorithm is constructed. Based on the system theory of man, machine, environment, and management, and taking the four single elements and the whole system in a coal mine as the research object, this paper systematically analyzes and studies the evaluation and continuous improvement of coal mine intrinsic safety. The BP neural network evaluation model is used to analyze and study the intrinsic safety of coal mines, the shortcomings of the intrinsic safety construction of coal mines are found, and then improvement measures are put forward to effectively promote the safe production of coal mines and finally realize the intrinsic safety goal of the coal mine. [ABSTRACT FROM AUTHOR]

The development and distribution of geologically complicated fault structure have the characteristics of uncertainty, randomness, ambiguity, and variability. Therefore, the prediction of complicated fault structures is a typical nonlinear problem. Neither fuzzy logic method nor artificial neural network alone can solve this problem well because the fuzzy method is generally not easy to realize adaptive learning function, and the neural network method is not suitable for describing sedimentary microfacies or geophysical facies. Therefore, taking the marginal subsags in the Jiyang Depression, Eastern China, as a study case, this paper uses the method of combining artificial neural network and fuzzy logic to study geologically complicated fault structure prediction model. This paper expounds on the research status and significance of geologically complicated fault structure prediction model, elaborates the development background, current status, and future challenges of artificial neural networks and fuzzy logic, introduces the method and principle of fuzzy neural network structure and fuzzy logic analysis algorithm, conducts prediction model design and implementation based on fuzzy neural network, proposes the learning algorithm of fuzzy neural network, analyzes the programming realization of fuzzy neural network, constructs complicated fault structure prediction model based on the artificial neural network and fuzzy logic, performs the fuzzy logic system selection of complicated fault structure prediction model, carries out the artificial neural network structure design of complicated fault structure prediction model, compares the prediction effects of the geologically complicated fault structure model based on artificial neural networks and fuzzy logic, and finally discusses the system design and optimization of the prediction model for geologically complicated fault structures. The study results show that the fuzzy neural network fully integrates the advantages of artificial neural network and fuzzy logic system; based on the clear physical background of fuzzy logic system, it effectively integrates powerful knowledge expression ability and fuzzy reasoning ability into the network knowledge structure of neural network, which greatly improves the prediction accuracy of geologically complicated fault structure. [ABSTRACT FROM AUTHOR]

Recommendations based on user behavior sequences are becoming more and more common. Some studies consider user behavior sequences as interests directly, ignoring the mining and representation of implicit features. However, user behaviors contain a lot of information, such as consumption habits and dynamic preferences. In order to better locate user interests, this paper proposes a Bi-GRU neural network with attention to model user's long-term historical preferences and short-term consumption motivations. First, a Bi-GRU network is established to solve the long-term dependence problem in sequences, and attention mechanism is introduced to capture user interest changes related to the target item. Then, user's short-term interaction trajectory based on self-attention is modeled to distinguish the importance of each potential feature. Finally, combined with long-term and short-term interests, the next behavior is predicted. We conducted extensive experiments on Amazon and MovieLens datasets. The experimental results demonstrate that the proposed model outperforms current state-of-the-art models in Recall and NDCG indicators. Especially in MovieLens dataset, compared with other RNN-based models, our proposed model improved at least 2.32% at Recall@20, which verifies the effectiveness of modeling long-term and short-term interest of users, respectively. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is the most generally known neurodegenerative disorder, leading to a steady deterioration in cognitive ability. Deep learning models have shown outstanding performance in the diagnosis of AD, and these models do not need any handcrafted feature extraction over conventional machine learning algorithms. Since the 2012 AlexNet accomplishment, the convolutional neural network (CNN) has been progressively utilized by the medical community to assist practitioners to early diagnose AD. This paper explores the current cutting edge applications of CNN on single and multimodality (combination of two or more modalities) neuroimaging data for the classification of AD. An exhaustive systematic search is conducted on four notable databases: Google Scholar, IEEE Xplore, ACM Digital Library, and PubMed in June 2021. The objective of this study is to examine the effectiveness of classification approaches on AD to analyze different kinds of datasets, neuroimaging modalities, preprocessing techniques, and data handling methods. However, CNN has achieved great success in the classification of AD; still, there are a lot of challenges particularly due to scarcity of medical imaging data and its possible scope in this field. [ABSTRACT FROM AUTHOR]

A convolutional neural network has the characteristics of sharing information between layers, which can realize high-dimensional data processing. In general, the convolutional neural network uses a feedback mechanism to realize parameter self-regulation, which solves the disadvantages of manual parameter adjustment. However, it is unable to determine the iteration number with the best calculation accuracy. Calculation efficiency cannot be guaranteed while achieving the best accuracy. In this paper, a multilayer extreme learning convolutional neural network model is proposed for feature recognition and classification. Firstly, two-dimensional spatial characteristics of planetary bearing status data were enhanced. Then, extreme learning machine is embedded in a convolution layer to solve convex optimization problems. Finally, the parameters obtained from the training model were nested into a network to initialize the model parameters to separate each status feature. Planetary bearing experimental cases show the effectiveness and superiority of the proposed model in the recognition and classification of weak signals. [ABSTRACT FROM AUTHOR]

Federated learning is a distributed machine learning framework that has been widely applied in scenarios that require data privacy. To obtain a neural network model that performs well, when the model falls into a bug, existing solutions retrain it on a larger training dataset or the carefully selected samples from model diagnosis. To overcome this challenge, this paper presents Fed-DNN-Debugger, which can automatically and efficiently fix DNN models in federated learning. Fed-DNN-Debugger fixes the federated model by fixing each client model. Fed-DNN-Debugger consists of two modules for debugging a client model: nonintrusive metadata capture (NIMC) and automated neural network model debugging (ANNMD). NIMC collects the metadata with deep learning software syntax automatically. It does not insert any code for metadata collection into modeling scripts. ANNMD scores samples according to metadata and searches for high-quality samples. Models are retrained on the selected samples to repair their weights. Our experiments with popular federated models show that Fed-DNN-Debugger can improve the test accuracy by 8% by automatically fixing models. [ABSTRACT FROM AUTHOR]

Horizontal well fracturing technology is widely used in unconventional reservoirs such as tight or shale oil and gas reservoirs. Meanwhile, the potential of enhanced oil recovery (EOR) methods including huff-n-puff miscible gas injection are used to further increase oil recovery in unconventional reservoirs. The complexities of hydraulic fracture properties and multiphase flow make it difficult and time-consuming to understand the well performance (i.e., well production) in fractured shale reservoirs, especially when using conventional numerical methods. Therefore, in this paper, two methods are developed to bridge this gap by using the machine learning technique to forecast well production performance in unconventional reservoirs, especially on the EOR pilot projects. The first method is the artificial neural network, through which we can analyze the big data from unconventional reservoirs to understand the underlying patterns and relationships. A bunch of factors is contained such as hydraulic fracture parameters, well completion, and production data. Then, feature selection is performed to determine the key factors. Finally, the artificial neural network is used to determine the relationship between key factors and well production performance. The second is time series analysis. Since the properties of the unconventional reservoir are the function of time such as fluid properties and reservoir pressure, it is quite suitable to apply the time series analysis to understand the well production performance. Training and test data are from over 10000 wells in different fractured shale reservoirs, including Bakken, Eagle Ford, and Barnett. The results demonstrate that there is a good match between the available and predicated well performance data. The overall R values of the artificial neural network and time series analysis are both above 0.8, indicating that both methods can provide reliable results for the prediction of well performance in fractured shale reservoirs. Especially, when dealing with the EOR field cases, such as huff-n-puff miscible gas injection, Time series analysis can provide more accurate results than the artificial neural network. This paper presents a thorough analysis of the feasibility of machine learning in multiple fractured shale reservoirs. Instead of using the time-consuming numerical methods, it also provides a more robust way and meaningful reference for the evaluation of the well performance. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) training often necessitates a considerable amount of computational resources. In recent years, several studies have proposed for CNN inference and training accelerators in which the FPGAs have previously demonstrated good performance and energy efficiency. To speed up the processing, CNN requires additional computational resources such as memory bandwidth, a FPGA platform resource usage, time, power consumption, and large datasets for training. They are constrained by the requirement for improved hardware acceleration to support scalability beyond existing data and model sizes. This paper proposes a procedure for energy efficient CNN training in collaboration with an FPGA-based accelerator. We employed optimizations such as quantization, which is a common model compression technique, to speed up the CNN training process. Additionally, a gradient accumulation buffer is used to ensure maximum operating efficiency while maintaining gradient descent of the learning algorithm. To validate the design, we implemented the AlexNet and VGG-16 models on an FPGA board and laptop CPU along side GPU. It achieves 203.75 GOPS on Terasic DE1 SoC with the AlexNet model and 196.50 GOPS with the VGG-16 model on Terasic DE-SoC. Our result also exhibits that the FPGA accelerators are more energy efficient than other platforms. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a deep neural network (DNN) for forecasting the intra-day solar irradiance, photovoltaic PV plants, regardless of whether or not they have energy storage, can benefit from the work being done here. The proposed DNN utilises a number of different methodologies, two of which are cloud motion analysis and machine learning, in order to make forecasts regarding the climatological conditions of the future. In addition to this, the accuracy of the model was evaluated in light of the data sources that were easily accessible. In general, four different cases have been investigated. According to the findings, the DNN is capable of making more accurate and reliable predictions of the incoming solar irradiance than the persistent algorithm. This is the case across the board. Even without any actual data, the proposed model is considered to be state-of-the-art because it outperforms the current NWP forecasts for the same time horizon as those forecasts. When making predictions for the short term, using actual data to reduce the margin of error can be helpful. When making predictions for the long term, however, weather information can be beneficial. [ABSTRACT FROM AUTHOR]