Article
Computer Science, Information Systems
Priyanka Nehra, A. Nagaraju
Summary: This paper proposes a Support Vector Regression-based methodology to predict a host's future utilization using multiple resource's utilization history. Compared to existing approaches, the proposed method performs better in terms of root mean square error, mean absolute percentage error, mean square error, mean absolute error, and R2.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Biochemical Research Methods
Amir Bahmani, Ziye Xing, Vandhana Krishnan, Utsab Ray, Frank Mueller, Amir Alavi, Philip S. Tsao, Michael P. Snyder, Cuiping Pan
Summary: Executing genomic applications on cloud computing facilities often lacks tools to predict the most appropriate instance type, leading to over- or under-matching of resources. Hummingbird, a tool for predicting performance of computing instances on multiple cloud platforms with varying memory and CPU, can accurately predict the fastest, cheapest, and most cost-efficient compute instances economically.
Article
Computer Science, Information Systems
Jiechao Gao, Haoyu Wang, Haiying Shen
Summary: Large-scale cloud data centers often face high failure rates due to hardware and software failures, which can greatly reduce service reliability and require significant resources for recovery. Predicting task and job failures with high accuracy is crucial to avoid wastage. This article proposes a failure prediction algorithm based on multi-layer Bi-LSTM, which outperforms other methods with 93% accuracy for task failure and 87% accuracy for job failures.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2022)
Article
Ergonomics
Dezso V. Silagyi II, Dahai Liu
Summary: The study aims to predict the severity of aircraft damage and personal injury during aircraft approach and landing accidents using SVM models. Three new factors related to inattentional blindness were introduced. SVM models using the RBF kernel achieved the highest accuracy for predicting the severity of aircraft damage and personal injury. The top predictors included flight hours, accident time, pilot's age, crosswind component, landing runway number, single-engine land certificate, and obstacle penetration.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Computer Science, Artificial Intelligence
M. Tanveer, A. Tiwari, R. Choudhary, M. A. Ganaie
Summary: This study proposes a novel large scale pinball twin support vector machine (LPTWSVM) to address the limitations of the twin support vector machines (TWSVMs), using a unique pinball loss function and improving model performance by eliminating matrix inversion calculation and minimizing structural risk.
Article
Computer Science, Artificial Intelligence
Guanjin Wang, Stephen Wai Hang Kwok, Daniel Axford, Mohammed Yousufuddin, Ferdous Sohel
Summary: This paper proposes a novel classifier PSVM-AUCMax to address the problem of partially labeled and skewed datasets. PSVM-AUCMax focuses on improving prediction performance by maximizing the AUC. It has several merits, including enhanced generalization capability, simplified model selection process, and the same analytical solution as traditional PSVM.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Green & Sustainable Science & Technology
Xuesong Zhang, Biao He, Mohanad Muayad Sabri Sabri, Mohammed Al-Bahrani, Dmitrii Vladimirovich Ulrikh
Summary: This study accurately predicted soil liquefaction potential using support vector machines (SVMs) and Bayesian optimization (BO). The evolutionary random forest (ERF) model was first used for input selection, which identified six important variables out of nine candidates. The results showed that the BOSVM model outperformed other models and achieved high accuracy and AUC values. The findings suggest that BOSVM is a viable alternative to conventional soil liquefaction prediction methods, and the BO method is successful in training the SVM model.
Article
Computer Science, Artificial Intelligence
Chun-Na Li, Yuan-Hai Shao, Huajun Wang, Yu-Ting Zhao, Naihua Xiu, Nai-Yang Deng
Summary: This paper investigates the general forms and characteristics of nonparallel support vector machines (NSVMs) and categorizes them into two types. It reveals the advantages and defects of different types and points out the inconsistency problems. Based on this observation, a novel max-min distance-based NSVM is proposed with desired consistency. The proposed NSVM has the consistency of training and test and the consistency of metric, and it assigns each sample an ascertained loss.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Software Engineering
Hao Wu, Yuqi Chen, Chi Zhang, Jiangchao Dong, Yuxin Wang
Summary: Virtual machine (VM) consolidation is the assignment of requested VMs to physical machines (PMs) in order to optimize certain objectives while considering resource constraints. Most existing solutions rely on frequent live migration, which consumes resources and time. To address this, this paper proposes a VM consolidation algorithm for predictable loads (VCPL) to reduce live migration operations. The algorithm predicts load using a cyclic usage prediction (CUP) method, separates VMs with stable and cyclic load, and consolidates them to PMs. Simulations show that VCPL significantly reduces live migration operations.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Xiaoming Wang, Shitong Wang, Zengxi Huang, Yajun Du
Summary: This paper introduces a novel method called sparse support vector machine guided by radius-margin bound (RMB-SSVM) to efficiently condense the basis vectors in support vector machines. By selecting basis vectors and learning corresponding coefficients with a criterion related to SVM's generalization ability, the RMB-SSVM model can yield better performance.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Sambhav Jain, Reshma Rastogi
Summary: This paper proposes Parametric non-parallel support vector machines for binary pattern classification. The model brings noise resilience and sparsity by intelligently redesigning the Support vector machine optimization. The experimental results validate its scalability for large scale problems.
Article
Automation & Control Systems
Ning Chu, Weimin Kang, Xinhua Yao, Jianzhong Fu
Summary: This paper proposes an online prediction method for the roundness of grinding workpieces based on vibration signals. Vibration sensors are used to collect vibration signals during grinding, and wavelet packet denoising is used to preprocess original signals to obtain effective vibration signals. Then use time domain analysis and frequency domain analysis to extract features and normalize them to form feature vectors. The roundness of the finished workpiece is measured using a shape-measuring instrument and integrated with the feature vectors to generate a usable data set. The support vector machine (SVM) algorithm is implemented using A Library for Support Vector Machines (LIBSVM), and a prediction model is constructed. Use the data set to train the model and evaluate the accuracy of the model to verify the effectiveness of the model. The results show that the prediction accuracy of the prediction method can reach 92.86%, and it can better predict whether the roundness is qualified.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Sebastian Maldonado, Julio Lopez, Carla Vairetti
Summary: The predictive performance of classification methods relies heavily on the nature of the environment and dataset shift issue. A novel Fuzzy Support Vector Machine strategy is proposed in this paper to improve performance by redefining the loss function and applying aggregation operators to deal with dataset shift. Our methods outperform traditional classifiers in terms of out-of-time prediction using simulated and real-world dataset for credit scoring.
INFORMATION SCIENCES
(2021)
Article
Chemistry, Multidisciplinary
Syed Asif Raza Shah, Ahmad Waqas, Moon-Hyun Kim, Tae-Hyung Kim, Heejun Yoon, Seo-Young Noh
Summary: Cloud computing manages system resources by providing virtual machines, with containerization growing rapidly as a popular method for handling scientific workloads. Using containers and virtual machines can improve the efficiency and throughput of scientific workloads.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Interdisciplinary Applications
Andre Luis Dias, Afonso Celso Turcato, Guilherme Serpa Sestito, Dennis Brandao, Rodrigo Nicoletti
Summary: This study presents a cloud-based condition monitoring system for fault detection and identification in rotating machines, using data mining techniques with high accuracy and robustness, as well as reducing total execution time.
COMPUTERS IN INDUSTRY
(2021)