Construction And Performance Evaluation of Big Data Prediction Model Based on Fuzzy Clustering Algorithm in Cloud Computing Environment

In order to improve the task scheduling strategy, a method based on genetic algorithm in cloud computing environment was proposed. First, the independent task scheduling algorithm and associated task scheduling algorithm commonly used in cloud computing are studied and compared, respectively, and their application characteristics, advantages, and disadvantages are analyzed in detail. Second, an independent task scheduling strategy based on multipopulation genetic algorithm is proposed for independent task scheduling in cloud environment, considering the scheduling time, scheduling cost, and system resource utilization of task set. The implementation steps of the algorithm are given in detail. Finally, the simulation experiment is carried out on Cloud Sim platform. The experimental results show that computing resource M is 10, subtask N is 2000, population size S is 80, and ETC matrix and RCU array are randomly generated by the system. As the number of iterations increases, the scheduling scheme formed by MCGA and CGA is more obvious and close to the subtask execution cost optimization. Finally, the optimized scheme is basically formed. However, the scheduling scheme formed by TGA has no obvious optimization effect on the subtask execution cost. It is proved that the algorithm proposed in this paper can effectively optimize the task scheduling efficiency and improve the utilization of cloud computing resources at the same time, providing a feasible idea and method for task scheduling in the cloud computing environment.

Objectives: To enlighten the issues and challenges of Load Balancing Algorithm (LBA) for cloud computing environment. In this study the authors proposed a LBA for cloud computing server. Methods/Statistical Analysis: The numerous LBAs are compared with objective, merit, demerit and challenges of the LBA in terms of parameters such as performance, response time, scalability, overhead and many more. This study facilitates identification of efficient LBA for optimizes resource use, minimum response time, maximum throughput and avoidance of overload. Findings: The load balancer is permitted in most instances to provide support continuity as well as dealing with extra traffic. Consequently the useful load balancing algorithms required to find inexpensive resource usage by provisioning of resources to cloud users. The use of proposed algorithm is to improve the overhead and load imbalance factor of the system. Application: The Load Balancing (LB) is a vital feature of cloud computing environment. The economical LB algorithm assures cost effective resource usage by provisioning of resources to cloud users on demand schedule in pay-as-you-say-manner. The LB may actually provide assistance prioritizing users by using suitable scheduling requirements and also it is crucial part in cloud computing for maintaining the work load across various systems over the network and gives minimum processing time, minimum response time and ignores the workload.

Retracted: Intrusion Detection-Data Security Protection Scheme Based on Particle Swarm-BP Network Algorithm in Cloud Computing Environment

The Cloud Computing is a most widely spreading platform for executing tasks using virtual machines (VMs) as processing elements. Therefore, implementing HPC using Cloud Computing is considered a powerful approach by isolating tasks, reducing execution time, as well as, price, and satisfying load balance. In this paper, an enhancement task scheduling algorithm on the Cloud Computing environment has been introduced to reduce the make-span, as well as, decrease the price of executing the independent tasks on the cloud resources. The principles of the algorithm is based on calculating the total processing power of the available resources (i.e., VMs) and the total requested processing power by the users' tasks, then allocating a group of users' tasks to each VM based on the ratio of its needed power relative to the total processing power of all VMs. The power of VMs has been defined based on Amazon EC2 and Google pricing models. To evaluate the performance of the enhancement algorithm, a comparative study has been done among this enhancement algorithm, the default FCFS algorithm, and the existed GA, and PSO algorithms. The experimental results show that the enhancement algorithm outperforms other algorithms by reducing make-span and the price of the running tasks.

With the application of cloud computing services in more and more fields, it will undertake more computing tasks and storage tasks. The problem of high energy consumption in data centers will become more serious. Virtualization technology is very important in cloud computing, which can improve the utilization rate of resources. At the same time, it has flexibility in resource scheduling and can integrate multiple virtual machines to achieve power efficiency. Using online virtual machine migration technology for energy-saving planning in cloud environment is a hot research topic in academic circles. The scheduling strategy proposed in this paper can reduce the server downtime and the number of server hosts, so as to achieve the maximum use of resources. The main research work of this paper includes the following aspects: Firstly, the energy consumption in the process of virtual machine energy-saving design is modeled, and the relationship between energy consumption and resource usage under different load conditions is analyzed, and the problems are abstracted, e.g., packaging box problem. Secondly, this paper uses genetic algorithm to solve the problem of high energy consumption. Finally, based on the target allocation scheme of virtual machines obtained by the above method, the migration problem of virtual machines is abstracted as the problem of finding the maximum weighted independent set of graphs. And a greedy algorithm is designed to solve this problem. In this paper, CloudSim simulation platform is used to verify the effectiveness of the proposed algorithm. Experiments show that the proposed algorithm can reduce data energy consumption and avoid frequent migration of virtual machines.

Anomaly based novel multi-source unsupervised transfer learning approach for carbon emission centric GDP prediction

Location prediction has attracted increasing attention in diverse fields due to its wide applications, such as traffic planning and control, weather forecasting, homeland security, and travel recommendation. Many existing algorithms forecast a user's next location by learning that user's past moving patterns. However, the individual moving patterns in many practical applications (e.g., the moving trajectory of a taxi driver) tend to be random, which poses a big challenge for location prediction. In this paper, we propose a new robust location prediction model that considers both individual preferences and social interactions (PSI) at a group level to alleviate the effect of randomness and improve the location prediction performance. Specifically, we first extract hot places of interesting (POIs) and normal POIs, respectively, via a two-stage clustering approach. To characterize exterior social interactions, an associated group is identified, and an outline of group moving patterns is then extracted based on association rule mining. Finally, the next location is predicted by learning the individual's regular patterns and group moving patterns via a pair-wise ridge regression. In contrast to the traditional approaches, our proposed algorithm has several desirable characteristics: 1) PSI provides an intuitive and quantitative way to model human movement from two aspects: the individual's internal moving preferences and group-level exterior social interactions; 2) Building upon group-level pattern mining, PSI provides a more robust prediction model by learning both individual and group trend information simultaneously, alleviating the randomness of location prediction from individual historical trajectory data only; and 3) The experimental results demonstrate that PSI achieves a better prediction performance compared to the state-of-the-art methods.

POPCORN: A web service for individual PrognOsis prediction based on multi-center clinical data CollabORatioN without patient-level data sharing.

An outlier removal and feature dimensionality reduction framework with unsupervised learning and information theory intervention for organic Rankine cycle (ORC)

Objective This study is aimed at exploring the efficacy of transarterial chemotherapy embolization (TACE)+radiofrequency ablation+sorafenib in the treatment of patients with recurrent liver cancer and at constructing its prediction model. Methods A total of 60 patients with recurrent liver cancer treated in our hospital from March 2020 to March 2022 were enrolled and divided into two groups according to treatment methods, with 30 patients in each group. Group A adopted TACE+radiofrequency ablation+sorafenib therapy while group B adopted TACE+radiofrequency ablation therapy. Clinical efficacy, complications, and adverse reactions of the two groups were observed. A total of 30 patients with nonrecurrent liver cancer in the same period were enrolled. 60 patients with recurrent liver cancer and 30 patients with nonrecurrent liver cancer were taken as the recurrence group and the nonrecurrence group, respectively. The baseline data and clinical data of the patients were queried by the Hospital Information System. The data included age, gender, Child-Pugh grade, HBV/HCV infection, portal vein tumor thrombus, degree of differentiation, vascular invasion, serum alpha fetal protein (AFP) level, number of tumors, maximum diameter of tumors, and number of nodules. The logistic regression analysis was used to analyze the independent risk factors for liver cancer recurrence. The Hosmer-Lemeshow test was used to analyze the degree of fitting between the prediction model and the standard curve. The ROC curve was used to analyze the predictive value of the model for liver cancer recurrence. Results The objective effective rate and disease control rate in group A (33.33% and 70.00%) were higher than those in group B (10.00% and 43.33%), and the differences were statistically significant (both P < 0.05). There were no significant differences in the incidence of complications such as embolism syndrome, hand and foot skin reaction, gastrointestinal reaction, hypertension, diaphragmatic injury and bleeding, and biliary leakage and fever between the two groups (all P > 0.05). The proportions of patients in the recurrence group with portal vein tumor thrombus (PVTT), medium and high degree of differentiation, combined with vascular invasion, serum AFP level ≥ 400 ng/dL, multiple tumors, maximum tumor diameter ≥ 5 cm, combined with cirrhosis, and polynodules were all higher than those in the nonrecurrence group; the differences were statistically significant (all P < 0.05). Complication of PVTT, the degree of medium and high differentiation, and the maximum tumor diameter ≥ 5 cm were independent risk factors for recurrence of liver cancer (all P < 0.05). The prediction model of liver cancer recurrence was obtained by multiple regression analysis, P = 1/[1 + e−(−5.441 + 6.154∗PVTT + 3.475∗differentiateddegree + 3.001∗maximumdiameteroftumor)]. The Hosmer-Lemeshow test showed that χ2 = 1.558 (P = 0.992). According to the ROC curve analysis, the AUC, SE, and 95% CI value of the prediction model for liver cancer recurrence were 0.977, 0.012, and 0.953-1.000, respectively. Conclusion TACE+radiofrequency ablation+sorafenib is effective in the treatment of recurrent liver cancer, and the prediction model established based on the risk factor has high predictive value for patients with recurrent liver cancer.

In order to support the formulation of audit plan with scientific data, an audit doubt prediction algorithm based on parallel improved random forest algorithm is proposed under the background of audit big data. Firstly, a Hadoop-based audit big data management scheme for electric power enterprises is established, and the heterogeneous audit data collected by various power grid subsystems are integrated and stored. With the advent of the era of big data, the geometric growth of audit data and the increasing complexity of data types have brought great challenges to the audit work, and the traditional sampling audit and query-based audit methods can no longer meet the requirements of “full audit coverage”. This paper combines theory with practice, uses big data analysis methods such as k-means++ clustering analysis and text mining in financial internal audit to help determine audit priorities, find audit doubts, improve audit efficiency, provide technical basis for full coverage of audit supervision, and provide solutions for the development of large data internal audit, which has certain theoretical significance and practical value.

Recently, the distribution of dental caries has been shown to be skewed, and precise prediction models cannot be obtained using all the data. We applied a balancing technique to obtain more appropriate and robust models, and compared their accuracy with that of the conventional model. The data were obtained from annual oral check-ups for schoolchildren conducted in Japan. Five hundred children were followed from ages 5 to 8, and the three-year follow-up data were used. The variables used were salivary levels of mutans streptococci and lactobacilli, 3-min stimulated saliva volume, salivary pH, fluoride usage, and frequency of consumption of sweet snacks and beverages. Initially, conventional models were constructed by logistic regression analysis, neural network (a kind of prediction method), and decision analysis. Next, the balancing technique was used. To construct new models, we randomly sampled the same number of subjects with and without new dental caries. By repeated sampling, 10 models were constructed for each method. Application of the balancing technique resulted in the most robust model, with 0.73 sensitivity and 0.77 specificity obtained by C 5.0 analysis. For data with a skewed distribution, the balancing method could be one of the important techniques for obtaining a suitable and robust prediction model for dental caries.

The Predictive Analytics Toolkit (PAT) was developed to facilitate use of new approach methodologies (NAMs) to predict health hazards and risks from chemicals. PAT is a user-friendly web application that integrates many R packages to enable development and testing of prediction models without any programming. We drew from the work of Ring et al. 2021 (https://doi.org/10.1016/j.comtox.2021.100166), who used random forest models to predict in vivo transcriptomic responses in rat liver from in vitro Tox21 AC50 values for a set of 221 chemicals. Gene ontologies helped identify 735 biological pathways based on differential in vivo expression of specific gene sets. Ring et al. used 12 models that varied in use of toxicokinetics to predict in vivo activity using 5000 random forest iterations for each chemical/pathway combination (the area under the receiver-operator characteristic curve (AUC-ROC) was the measure of model performance). The highest-ranking model (Model 10) used Tox21 AC50 nominal concentrations converted to media concentrations and in vivo doses converted to circulating plasma concentrations; the lowest ranking model (Model 2) used nominal in vitro concentrations and administered in vivo dose levels. Using a subset of 10 pathways from the Ring et al. data, we used PAT to predict the AUC-ROC and to compare the best (Model 10) and worst (Model 2) performing models with only 100 random forest iterations. Using the results from PAT, Model 10 “won” in 60% of the comparisons, a value similar to that calculated for the identical set of comparisons using the supplemental data from Ring et al. (52.2%). Hence, PAT can provide a useful alternative to programming in R for prediction modeling and model performance evaluation, even for extensive genomic data sets.

Background: The primary objective of this study is to employ machine learning (ML) algorithms to develop predictive models for renal function recovery in critically ill patients undergoing continuous renal replacement therapy (CRRT) due to acute kidney injury (AKI). Methods: Data were retrospectively collected from patients with AKI who underwent CRRT during their first Intensive Care Unit (ICU) admission from the Medical Information Mart for Intensive Care-IV database and at Huzhou Central Hospital. The evaluation of model performance was conducted utilizing metrics including the area under the receiver operating characteristic curve (AUROC), calibration curves and decision curve analysis (DCA). Results: A total of 1078 AKI patients undergoing CRRT were included, with a renal function recovery rate of 18.18% (n = 196). Six features that significantly affect renal function recover rate were identified through least absolute shrinkage and selection operator (LASSO) regression with cross-validation. The Lasso-LR model was chosen as the definitive clinical risk prediction model for this study and served as the basis for constructing the nomogram. Its AUROCs in the training and external validation cohorts were 0.774 (95% CI: 0.735 ∼ 0.814) and 0.748 (95% CI: 0.685 ∼ 0.812), respectively. The calibration curve and ideal curve fit were generally found to be suboptimal. Simultaneously, the DCA curve suggested that the nomogram has clinical value. Conclusions: Among the ML models developed using data from the two datasets to predict renal function recovery in critically ill AKI patients undergoing CRRT, the Lasso-LR model demonstrated the best performance. It can serve as a valuable tool for more efficient clinical disease management and prognostic evaluation.

e17621 Background: TCGA molecular typing was proposed by The Cancer Genome Atlas (TCGA) in 2013 and recommended by the fifth edition of WHO, which has a strong prognositic value and is included in the risk stratification system, clinical diagnosis and treatment decision-making system of endometrial cancer (EC) patients. Meanwhile, Lymph node management in patients with EC is still controversial. Lymph node dissection (LND) and sentinel lymph node biopsy (SLNB) have their own advantages and limitations. This study attempts to establish a predictive model for lymph node metastasis (LNM) in patients with EC based on molecular typing and other clinical features and establish risk stratification, in order to provide a feasible method for predicting LNM in EC. Methods: In this study, SPSS19, R 4.2.1 and python 3.6 were used to establish a nomogram and evaluate it through a number of indicators, and the model was repeatedly verified by machine learning algorithms. With LNM as the outcome, risk stratification was set through the cut-off value of nomogram score to guide clinical treatment. Finally, an online LNM prediction website was designed to help patients. Results: A total of 325 EC patients were included, 35 (10.8%) with LNM and 290 (89.2%) without LNM. CA125 and cervical involvement were significantly correlated with LNM (p &lt; 0.001), molecular typing, neutrophil to lymphocyte ratio (NLR), menstrual status were associated with LNM (p &lt; 0.05). Lasso analysis screened out four independent factors: molecular typing, CA125, cervical involvement and menstrual status. The nomogram model was established by logistics regression (LR), with the prediction accuracy of the training set and validation set of 0.890 and 0.886, respectively. Machine learning algorithms in the training set also validates the model. Meanwhile, a risk stratification is established by the cut-off value of nomogram. We define high-risk group of LNM with more than the cut-off value and LND is recommended, while below the value is low-risk group and SLNB is recommended. Conclusions: We have established a nomogram clinical prediction model incorporating four factors, practicing stratified medical treatment about LND and SLNB, and formed a website for LNM prediction, genuinely providing patients recommendations.