Performance Prediction Analysis Research Articles

Comparative Analysis of Prediction Performance of Mine Subsidence Using Machine Learning Techniques

Comparative Analysis of Prediction Performance of Mine Subsidence Using Machine Learning Techniques

Prediction Performance of Deep Learning for Colon Cancer Survival Prediction on SEER Data.

Colon and rectal cancers are the most common kinds of cancer globally. Colon cancer is more prevalent in men than in women. Early detection increases the likelihood of survival, and treatment significantly increases the likelihood of eradicating the disease. The Surveillance, Epidemiology, and End Results (SEER) programme is an excellent source of domestic cancer statistics. SEER includes nearly 30% of the United States population, covering various races and geographic locations. The data are made public via the SEER website when a SEER limited-use data agreement form is submitted and approved. We investigate data from the SEER programme, specifically colon cancer statistics, in this study. Our objective is to create reliable colon cancer survival and conditional survival prediction algorithms. In this study, we have presented an overview of cancer diagnosis methods and the treatments used to cure cancer. This paper presents an analysis of prediction performance of multiple deep learning approaches. The performance of multiple deep learning models is thoroughly examined to discover which algorithm surpasses the others, followed by an investigation of the network's prediction accuracy. The simulation outcomes indicate that automated prediction models can predict colon cancer patient survival. Deep autoencoders displayed the best performance outcomes attaining 97% accuracy and 95% area under curve-receiver operating characteristic (AUC-ROC).

Marvellous significance performance analysis of PQ events prediction and classification

This paper compares various significant research techniques concerning the power quality (PQ) events prediction and classification system presented by the authors previously and examines its viability scale as far as the research gap. This paper examines some of the frequently exercised PQ classification techniques named as Feedforward Neural Network (FNN), Sequential Ant Lion Optimizer and Recurrent Neural Network (SALRNN), dual-layer Feedforward network and Short-Time Fourier Transform (STFT) from the most significant literature in order to have more insights of the techniques. The research work has presented a simple framework that retains a balance between higher accuracy in the detection of disturbances as well as also maintains an effective computational performance for a large number of the power signals. The principle aim of the paper is research and comparative analysis of above-mentioned algorithms for searching the best impressive technique to detect and classify the PQ events. The simulation results of this research can be reasoned that the SALRNN technique performed very well to detect and classify the PQ disturbances when compared with the other two techniques such as FNN and STFT. The SALRNN technique is more optimal than the other existing techniques in terms of RMSE, MAPE, MBE, sensitivity, specificity and consumption time is analyzed.

Performance Prediction and Action Performance Analysis of Sports Competitive Events Based on Deep Learning

Physical education performance in primary and secondary school classroom education seems mediocre, and many students treat it as a minor subject. With parents and schools paying attention to physical education, physical education performance is very important now, whether in primary and secondary schools or universities. Nowadays, college students have less and less physical exercise, and sports achievements are one of the index achievements for evaluating scholarships. Many teachers also arrange appropriate physical training reasonably in order to improve students’ sports achievements. Forecasting sports achievements is the key to making scientific sports training plans. According to the study of college students’ group sports achievements, we can predict students’ follow-up learning achievements, collect, sort out, and study students’ sports achievements information regularly, so as to better guarantee the quality of college sports teaching. This paper compares and analyzes the sports achievements of various schools from the aspects of strength, endurance, and sensitivity. At the same time, it compares and analyzes the sports achievements of major universities. Finally, from the perspective of physical education, this paper analyzes and studies the situation of individual schools and then finds out the pedagogical factors that make them achieve excellent physical education results and puts forward the teaching strategies to improve physical education results, as well as the positive influence of physical education teachers on teaching, school physical education results, and students’ physical quality. When teaching courses, use big data mining technology to find qualified students to study the actual teaching needs, recommend an efficient learning curriculum system to students with reference to research conclusions, and give rich material resources. Teachers can teach students in accordance with their aptitude with reference to their usual learning situation, instead of “one size fits all.”

Construction of Sports Training Performance Prediction Model Based on a Generative Adversarial Deep Neural Network Algorithm.

The generative adversarial neural network algorithm is used for in-depth research and analysis of sports training performance prediction, and the corresponding model is built and used for practical applications. To address the problems of gradient disappearance, training instability, lack of local consistency of repair results, and long training time in the image restoration algorithm based on generative adversarial networks, this paper proposes a multigenerative adversarial image restoration algorithm based on multigranularity reconstruction sampling. The algorithm changes the distribution initialization of the generative network and uses reconstruction sampling to ensure that the Lebesgue measure of the overlapping part of the generative sample space and the real sample space is not 0 to further stabilize the gradient, and it is demonstrated that reconstruction sampling can stabilize the training and gradient. In addition, segmentation invariance is used to shorten the training time while ensuring the quality of the restored images, and an algorithm adaptability metric is proposed to comprehensively evaluate the image restoration algorithm. Based on the results of the fusion model analysis, an attention-based mechanism for the student performance prediction model is proposed. First, deep student behavioral features are extracted using a generative adversarial deep neural network, and the salient features in the student behavioral features are selected using a maximum pooling method; then, the extracted features are used as the input of the generative adversarial deep neural network for student performance prediction. Finally, a temporal attention mechanism is introduced at the output of the generative adversarial deep neural network to assign attention weights to different weekly student behavioral features.

Short-Term Traffic Flow Prediction of the Smart City Using 5G Internet of Vehicles Based on Edge Computing

The paper aims to explore the performance of short-term traffic flow prediction of the 5G (5th Generation Mobile Communication Technology) Internet of Vehicles (IoV) based on edge computing (EC) for the smart city and to further improve the intelligence of the smart city. Aiming at the current emergency of traffic congestion and road congestion, the present work adds EC to the current vehicle network, and integrates a deep convolution random forest neural network (DCRFNN). Additionally, it implements a model for short-term traffic flow prediction of a 5G vehicle network based on EC and deep learning (DL), and analyzes its performance by simulation. The results reveal that the proposed algorithm has a lower average delay cost, and the average unloading utility is stable at approximately 70%. In the prediction performance analysis, the recognition accuracy of the proposed algorithm reaches 98.06%. It is at least 1.14% higher than that of the advanced convolution neural network (CNN) algorithm proposed by other scholars and achieves a faster convergence rate. Therefore, the constructed short-term traffic prediction model implemented has a high-quality prediction performance while also ensuring a better unloading performance. The results can provide an experimental basis for traffic flow prediction and intelligent development of the smart city.

Performance prediction analysis of college aerobics course based on Back Propagation neural network

Performance prediction analysis of college aerobics course based on Back Propagation neural network

Design and Implementation of Intelligent Educational Administration System Using Fuzzy Clustering Algorithm

The present work aims to solve the problems that the traditional educational administration management system has, such as low efficiency in analyzing big data, and the analysis results have low value, which is based on manual rules definition in big data analysis and processing. The work proposes a student achievement prediction model FCM-CF based on Fuzzy C-means (FCM) and Collaborative Filtering (CF). The work also introduces it into the research of educational administration management to construct an intelligent educational administration management system. At the beginning, the FCM-CF model is described in detail. Then, the system requirements and specific design methods are described in detail. Eventually, with the students’ performance prediction as an example, the performance of the system is tested by designed simulation experiments. The result shows that the students’ achievement in study is closely related to their daily study performance such as preparation before class, classroom performance, attendance, extracurricular study, and homework completion. Generally, the examination scores of students are significant to their daily performances. Under the same experimental conditions, the prediction error of the FCM-CF model proposed here is less than 10.8% of that of other algorithms. The model has better prediction performance and is more suitable for the prediction of middle school students’ examination scores in educational administration management system. The innovation of intelligent educational administration management system is that, in addition to the basic information management function, it also has two other functions: students’ performance prediction analysis and teacher evaluation prediction. It can provide data support for improving teaching quality. The research purpose is to provide important technical support for more intelligent educational administration and reduce the loss of human resources in educational administration.

Co-Simulation Analysis for Performance Prediction of Synchronous Reluctance Drives

To improve the design of electric drives and to better predict the system performance, numerical simulation has been widely employed. Whereas in the majority of the approaches, the machines and the power electronics are designed and simulated separately, to improve the fidelity, a co-simulation should be performed. This paper presents a complete coupled co-simulation model of synchronous reluctance machine (SynRel) drive, which includes the finite element model of the SynRel, the power electronics inverter, the control system, and application examples. The model of SynRel is based on a finite element model (FEM) using Simcenter MagNet. The power electronics inverter is built using PLECS Blockset, and the drive control model is built in Simulink environment, which allows for coupling between MagNet and PLECS. The proposed simulation model provides high accuracy thanks to the complete FEA-based model fed by actual inverter voltage. The comparison of the simulation results with experimental measurements shows good correspondence.

Case studies on performance prediction of radial inflow turbine under multiple rotor structures and organic fluids

Due to the lack of selection criteria for the ORC radial inflow turbine's loss models, and information about the models' limitations. This paper presents a comprehensive analysis for performance prediction of the ORC radial inflow turbine, and a novel turbine performance prediction program is proposed. This study can be divided into two parts, during the analysis part, 125 cases of CFD simulation were conducted under 5 rotor structures and R245fa as the working fluid. The performance of 6 loss models and their 18 combinations were compared. And in the examination part, another three organic fluids from different categories were chosen to exam the reliability of the proposed prediction program. The results show that loss model combinations E, O, and Q have a good performance in rotor loss prediction. Besides, Δβ4 has an important influence on prediction reliability and turbine performance, it should be lower than a certain value (about 40° in this paper) during the analysis process to get relatively reliable results under different rotor structures. The proposed program can realize an acceptable accuracy for turbine performance prediction under multiple organic fluids and rotor structures, with an efficiency deviation within ±5% and an output power relative error within ±10%.

Adiabatic compressed air energy storage technology

Adiabatic compressed air energy storage technology

Analysis of Effectiveness and Performance Prediction of Sports Flipped Classroom Teaching Based on Neural Networks

Traditional physical education methods are unable to meet this requirement due to the practical nature of sports skill teaching. As a result, as the times demanded, the flipped classroom based on neural network technology arose. It has the potential to not only promote the modernization of physical education but also to ensure that it has a positive educational impact. This is a mode of instruction. Furthermore, colleges and universities are increasingly focusing on college students’ overall quality development. A method for predicting college students’ sports performance using a particle swarm optimization neural network is proposed to accurately predict sports performance and provide a reliable analysis basis for the establishment of sports teaching goals. Neural networks are used in the model. The particle swarm optimization algorithm optimizes the variance and weights of the neural network to improve the accuracy of college students’ sports performance predicted by the neural network by updating the particle position and speed through the two extreme values of individual extreme values and global extreme values. Teachers always play the role of the facilitator and helper in the teaching process, which realizes the transformation of teachers’ and students’ self-positioning, allows students to better play the lead role, and stimulates students’ interest in learning.

Fuzzy System Based Medical Image Processing for Brain Disease Prediction.

The present work aims to explore the performance of fuzzy system-based medical image processing for predicting the brain disease. The imaging mechanism of NMR (Nuclear Magnetic Resonance) and the complexity of human brain tissues cause the brain MRI (Magnetic Resonance Imaging) images to present varying degrees of noise, weak boundaries, and artifacts. Hence, improvements are made over the fuzzy clustering algorithm. A brain image processing and brain disease diagnosis prediction model is designed based on improved fuzzy clustering and HPU-Net (Hybrid Pyramid U-Net Model for Brain Tumor Segmentation) to ensure the model safety performance. Brain MRI images collected from a Hospital, are employed in simulation experiments to validate the performance of the proposed algorithm. Moreover, CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), FCM (Fuzzy C-Means), LDCFCM (Local Density Clustering Fuzzy C-Means), and AFCM (Adaptive Fuzzy C-Means) are included in simulation experiments for performance comparison. Results demonstrate that the proposed algorithm has more nodes, lower energy consumption, and more stable changes than other models under the same conditions. Regarding the overall network performance, the proposed algorithm can complete the data transmission tasks the fastest, basically maintaining at about 4.5 s on average, which performs remarkably better than other models. A further prediction performance analysis reveals that the proposed algorithm provides the highest prediction accuracy for the Whole Tumor under DSC (Dice Similarity Coefficient), reaching 0.936. Besides, its Jaccard coefficient is 0.845, proving its superior segmentation accuracy over other models. In a word, the proposed algorithm can provide higher accuracy, a more apparent denoising effect, and the best segmentation and recognition effect than other models while ensuring energy consumption. The results can provide an experimental basis for the feature recognition and predictive diagnosis of brain images.

Analytical prediction of electromagnetic performance of dual-stator consequent-pole PM machines based on subdomain model accounting for tooth-tips

PurposeThe purpose of this paper is to analytically predict the on-load field distribution and electromagnetic performance (induced voltage, electromagnetic torque, winding inductances and unbalanced magnetic force) of dual-stator consequent-pole permanent magnet (DSCPPM) machines using subdomain model accounting for tooth-tip effect. The finite element (FE) results are presented to validate the accuracy of this subdomain model.Design/methodology/approachDuring the preliminary design and optimization of DSCPPM machines, FE method requires numerous computational resources and can be especially time-consuming. Thus, a subdomain model considering the tooth-tip effect is presented in this paper. The whole field domain is divided into four different types of sub-regions, where the analytical solutions of vector potential in each sub-region can be rapidly calculated. The proposed subdomain model can accurately predict the on-load flux density distributions and electromagnetic performance of DSCPPM machines, which is verified by FE method.FindingsThe radial and tangential components of flux densities in each sub-region of DSCPPM machine can be obtained according to the vector potential distribution, which is calculated based on the boundary and interface conditions using variable separation approach. The tooth-tip effect is investigated as well. Moreover, the phase-induced voltage, winding inductances, electromagnetic torque and X-axis/Y-axis components of unbalanced magnetic forces are calculated and compared by FE analysis, where excellent agreements are consistently exhibited.Originality/valueThe on-load field distributions and electromagnetic performance of DSCPPM machines are analytically investigated using subdomain method, which can be beneficial in the process of initial design and optimization for such DSCPPM machines.

솔리드 모델링과 레벨셋 기법을 이용한 고체 로켓 추진기관 성능해석

The performance prediction and grain burn-back analysis of rocket motor are important steps in the designing of a solid propellant rocket motor. The grain burn-back analysis of the solid grain identifies the burning surface area at each burning step in order to predict pressure-time history of the rocket motor. In this study, the shape of propellant grains was conveniently designed based on a solid modeling program of conventional purpose and the internal ballistics analysis was performed using a Matlab code which was developed to analyze the grain burn-back for this shape model. Upon carrying several analyses for rocket motors, it was confirmed that the developed code is suitable and useful.

Mathematical model analysis of axisymmetric nozzle performance prediction for complex system based on numerical simulation

Mathematical model analysis of axisymmetric nozzle performance prediction for complex system based on numerical simulation

Analysis of Groundwater Level Prediction Performance with Influencing Factors by Artificial Neural Network

Analysis of Groundwater Level Prediction Performance with Influencing Factors by Artificial Neural Network

Comparison and analysis of prediction performance of fine particulate matter(PM2.5) based on deep learning algorithm

Comparison and analysis of prediction performance of fine particulate matter(PM2.5) based on deep learning algorithm

Predictive Performance Analysis of PDF – IDF Model Types Using Rainfall Observations from Fourteen Gauged Stations

The design of structures for flood mitigation depends on the adequate estimation of rainfall intensity over a given catchment which is achieved by the rainfall intensity duration frequency modelling. In this study, an extensive comparative analyses were carried out on the predictive performance of three PDF – IDF model types, namely: Gumbel Extreme Value Type 1 (GEVT – 1), Log-Pearson Type 3 (LPT – 3) and Normal Distribution (ND) in 14 selected cities in Southern Nigeria. This is to rank the order of best performance. The principle of general model development was adopted in which rainfall intensities at different durations and specified return periods were used as input data set. This is not same as return period specific model that involves rainfall intensities for various durations and a given return period. The predicted rainfall intensity values with the PDF – IDF model types indicate high goodness of fit (R2) and Mean Squared Errors (MSE) ranging from: (a) R2 = 0.875 – 0.992; MSE = 33.17 – 224.6 for GEVT – 1; (b) R2 = 0.849 – 0.990; MSE = 65.34 – 405.5 for LPT – 3 and (c) R2 = 0.839 – 0.992; MSE = 29.23 – 200.2 for ND. The comparative analysis of all the 42 general models (14 locations versus 3 model types) considered showed that the order of best performance is LPT – 3 1st, GEVT - 1 2nd and ND 3rd for each return period (10, 50 and 100 years). The Kruskal Wallis test of significance indicates that no significant difference exists in the predictive performance of the three General models across the board. This may be due to the fact that the fourteen locations of the study area are bordering with the Atlantic Ocean and seems to have similar climatology. These developed General models are recommended for the computation of intensities in the fourteen locations for the design of flood control structures; and the order of preference should be LPT – 3 > GEVT – 1 > ND.

A Comparative Analysis of Decision Trees Vis-`a-vis Other Computational Data Mining Techniques in Automotive Insurance Fraud Detection

The development and application of computational data mining techniques in financial fraud detection and business failure prediction has become a popular cross-disciplinary research area in recent times involving financial economists, forensic accountants and computational modellers. Some of the computational techniques popularly used in the context of financial fraud detection and business failure prediction can also be effectively applied in the detection of fraudulent insurance claims and therefore, can be of immense practical value to the insurance industry. We provide a comparative analysis of prediction performance of a battery of data mining techniques using real-life automotive insurance fraud data. While the data we have used in our paper is US-based, the computational techniques we have tested can be adapted and generally applied to detect similar insurance frauds in other countries as well where an organized automotive insurance industry exists.