检索结果-内蒙古大学图书馆

An Intelligent Learning System Based on random search algorithm and Optimized random Forest Model for Improved Heart Disease Detection

引用

IEEE ACCESS 2019年 7卷 180235-180243页

作者： Javeed, Ashir Zhou, Shijie Liao Yongjian Qasim, Iqbal Noor, Adeeb Nour, Redhwan Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu 611731 Peoples R China Univ Sci & Technol Bannu Dept Comp Sci Bannu 28100 Pakistan King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Technol Jeddah 80221 Saudi Arabia Taibah Univ Dept Comp Sci Medina 42353 Saudi Arabia

Heart failure is considered one of the leading cause of death around the world. The diagnosis of heart failure is a challenging task especially in under-developed and developing countries where there is a paucity of human experts and equipments. Hence, different researchers have developed different intelligent systems for automated detection of heart failure. However, most of these methods are facing the problem of overfitting i.e. the recently proposed methods improved heart failure detection accuracy on testing data while compromising heart failure detection accuracy on training data. Consequently, the constructed models overfit to the testing data. In order, to come up with an intelligent system that would show good performance on both training and testing data, in this paper we develop a novel diagnostic system. The proposed diagnostic system uses random search algorithm (RSA) for features selection and random forest model for heart failure prediction. The proposed diagnostic system is optimized using grid search algorithm. Two types of experiments are performed to evaluate the precision of the proposed method. In the first experiment, only random forest model is developed while in the second experiment the proposed RSA based random forest model is developed. Experiments are performed using an online heart failure database namely Cleveland dataset. The proposed method is efficient and less complex than conventional random forest model as it produces 3.3% higher accuracy than conventional random forest model while using only 7 features. Moreover, the proposed method shows better performance than five other state of the art machine learning models. In addition, the proposed method achieved classification accuracy of 93.33% while improving the training accuracy as well. Finally, the proposed method shows better performance than eleven recently proposed methods for heart failure detection.

关键词： Heart failure hyperparameters optimization feature selection random search algorithm grid search algorithm

来源：评论

学校读者我要写书评

暂无评论

A region based random multi-pixel search algorithm to improve the binary hologram reconstruction quality

引用

OPTICS AND LASERS IN ENGINEERING 2023年 161卷

作者： Lu, Changgui Jin, Shuping Hu, Xuefang Zhao, Xiangyue Qi, Zhengqing Chen, Weidong Cui, Yiping Southeast Univ Adv Photon Ctr Nanjing 210096 Peoples R China Jinling Inst Technol Sch Network & Commun Engn Nanjing 211169 Peoples R China Southeast Univ Sch Elect Sci & Engn Nanjing Jiangsu Peoples R China

Direct binary search (DBS) is an effective method for the generation of binary computer-generated holograms (CGHs), which has been widely used in wavefront synthesis, optical tweezers and 3D display. However, the correlation of pixels in holograms is neglected in DBS, resulting the algorithm easily converging to local minimum and leading to an unsatisfactory reconstruction quality. To ameliorate this disadvantage, we proposed a new algorithm by randomly selecting multiple related pixels in the same region to generate hologram. Compared with DBS, the mean square error (MSE) of reconstructed image in simulation has declined from 844.85 to 445.74, the peak signal to noise ratio (PSNR) has increased from 18.86 to 21.64 and structural similarity (SSIM) has increased from 0.336 to 0.459. The reconstructed image in experiment shows fewer noise points and clearer outline. Both the numerical and experimental results demonstrate that the reconstruction quality can be improved by this algorithm, which will exhibit great applications in the fields of data storage, microscopy, and true sense dynamic 3D display.

关键词： Holography Binary hologram random search algorithm Direct binary search

来源：评论

学校读者我要写书评

暂无评论

random search algorithms for redundancy allocation problem of a queuing system with maintenance considerations

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2019年 185卷 144-162页

作者： Sabri-Laghaie, Kamyar Karimi-Nasab, Mehdi Urmia Univ Technol Fac Ind Engn Orumiyeh Iran Univ Hamburg Inst Operat Res Hamburg Germany

The Redundancy Allocation Problem (RAP) is becoming all the time more important in system reliability design. Therefore, RAP has been studied vastly for different systems and under various assumptions. One of the important systems that RAP can be applied to them is queuing systems. In many applications, reliability of queuing systems need to be improved with regard to some queuing and reliability cost constraints. Despite the importance of queuing systems in real world situations, RAP of these systems have not gained attention in the literature. Therefore, RAP of a queuing system with maintenance considerations and including queueing costs in the modeling of RAP is considered in this paper. To find optimal solutions of the problem, four random search algorithms are developed and compared based on the problem structures. According to the experiments, for unimodal solution spaces algorithms 1 and 2 and for multimodal solution spaces algorithms 3 and 4 are recommended.

关键词： Queuing system Redundancy Allocation Problem (RAP) Standby server Reliability analysis Repairman random search algorithm

来源：评论

学校读者我要写书评

暂无评论

A Portable Meconium Aspirator With Fractional Augmented Pressure Control System

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2025年第5期72卷 733-737页

作者： Dudhe, Suraj Dheer, Dharmendra Kumar Raja, G. Lloyds Natl Inst Technol Patna Elect Engn Dept Patna 800005 India GH Raisoni Coll Engn Nagpur Elect Engn Dept Nagpur 440016 India

A simple and robust automatic suction pressure control system is designed for a newly developed portable meconium aspirator system (PMAS). From the step response data of the system, the transfer function (TF) of PMAS is obtained. Using the obtained TF, a proportional-integral-derivative controller in series with a fractional-order filter (PIDFF) is designed using a fractional-augmented internal model control (FAIMC) strategy. The adjustable parameter of the PIDFF controller is obtained using the reference to disturbance ratio (RDR) and random search algorithm. The designed controller is then simulated using MATLAB which is interfaced with the PMAS hardware. Simulation and experimental results in comparison with prevalent fractional-order schemes demonstrate the superior control performance achieved by the proposed pressure control system in terms of overshoot-free servo tracking and faster disturbance rejection. It is vindicated that the suction pressure is maintained in the desired value effectively amid disturbances and uncertainties in the obtained transfer function. Finally, a robust stability analysis of the suggested design is also carried out.

关键词： Pressure control Pediatrics Transfer functions Mathematical models Delays Vacuum systems Pressure sensors Portable meconium aspirator suction pressure control fractional augmented IMC PIDFF controller reference to disturbance ratio random search algorithm

来源：评论

学校读者我要写书评

暂无评论

Regularization in machine learning models for MVT Pb-Zn prospectivity mapping: applying lasso and elastic-net algorithms

引用

EARTH SCIENCE INFORMATICS 2024年第5期17卷 4859-4873页

作者： Hajihosseinlou, Mahsa Maghsoudi, Abbas Ghezelbash, Reza Amirkabir Univ Technol Dept Min Engn Tehran Iran Univ Tehran Coll Engn Sch Min Engn Tehran Iran

The current research employed the least absolute shrinkage and selection operator (Lasso) and Elastic-net algorithms to examine their potential utilization in MVT Pb-Zn prospectivity modeling. In training the model, both Elastic-net and Lasso regularization approaches include a penalty term to the loss function. Since this penalty term limits the feature coefficients, the model is motivated to prioritize the most informative features and penalize the less relevant ones. The Varcheh district in western Iran was the source of the geological, geochemical, tectonic, and alteration dataset. We applied stratified 5-fold cross-validation to train the dataset, ensuring consistent and comprehensive performance evaluation across different data subsets. This method improved data utilization and provided more reliable performance estimates by averaging metrics over multiple folds, thereby enhancing the model's generalization assessment. The hyperparameters were adjusted using random search, quickly finding near-optimal solutions. Our investigation revealed that Elastic-net exhibited superior prediction accuracy and model robustness compared to Lasso. The combination of L1 and L2 regularization in Elastic-net, offers a more adaptable technique than Lasso, which just utilizes L1 regularization. This feature enables Elastic-net to handle scenarios in which there have been correlated predictors successfully.

关键词： Elatic-net Lasso Mineral prospectivity mapping random search algorithm MVT Pb-Zn

来源：评论

学校读者我要写书评

暂无评论

Evaluating the impact of tuned pre-trained architectures'feature maps on deep learning model performance for tomato disease detection

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第6期83卷 18147-18168页

作者： Bakir, Halit Sivas Univ Sci & Technol Fac Engn & Nat Sci Comp Engn Dept Sivas Turkiye

As global food demands escalate, ensuring optimal crop health has become paramount. Traditional disease detection methods often fall short in terms of speed and accuracy, emphasizing the need for advanced, technology-driven solutions. Thus, this paper explores the impact of fine-tuning pre-trained CNN architectures synchronously with the structure of CNN model, focusing on disease detection in tomato leaves. We suggested utilizing these pre-trained CNN architectures as a feature extraction phase and tuning them alongside the classification phase of the proposed model. We posit that the harmonious tuning of both the feature extraction phase and the classification phase holds the potential to enhance the performance of any deep-learning model. In pursuit of this objective, we extended the concept of hyperparameters to encompass the feature extraction phase, alongside a comprehensive spectrum of hyperparameters that influence deep-learning models. Subsequently, we harnessed the random search algorithm to optimize these hyperparameters and determine the optimal model architecture for enhanced tomato disease detection accuracy. The model refined through the random search algorithm was designated as Xception-CNN. Initially, we trained and evaluated the proposed Xception-CNN model using the tomato leaves dataset. Subsequently, we conducted an experiment by removing the feature extraction phase from the Xception-CNN model and transforming it into an end-to-end scratch-CNN model. This step aimed to both validate the efficacy of our approach and unveil the impact of fine-tuned pre-trained model feature maps on CNN model performance. The outcomes indicated the superior performance of the proposed Xception-CNN model compared to the Scratch-CNN model across all evaluation metrics. Notably, the classification accuracy of the Scratch-CNN model peaked at 76.70%, whereas the Xception-CNN model achieved an impressive accuracy of 99.40%. These findings underscore the significance of m

关键词： Plant disease detection random search algorithm Hyperparameter tuning Pre-trained CNN model Feature extractor tuning

来源：评论

学校读者我要写书评

暂无评论

Image Steganography based on improved LSB algorithm 39

Image Steganography based on improved LSB algorithm

引用

39th Youth Academic Annual Conference of Chinese-Association-of-Automation (YAC)

作者： Hu, JiaWei Wuhan Univ Technol Sch Econ Wuhan Peoples R China

ISBN: (纸本)9798350390780;9798350379228

Aiming at the problem of copyright protection of electronic resources, this paper establishes a model based on the optimized LSB algorithm to implicitly write the target information into the image. The model first encodes the text and optimizes the LSB algorithm with a random search algorithm, so as to obtain picture after embedding the information. The output image is measured in terms of SSIM(StructureSimilarity Index Measure), MSE(Mean Square Error), PSNR(Peak Signal-to-Noise Ratio), and compared with the original unimproved LSB algorithm, which shows that the optimized LSB algorithm has improved compared with the original one.

关键词： Image Steganography Optimization Model random search algorithm LSB algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel geometric model of breathing crack and its influence on rotor dynamics

引用

JOURNAL OF VIBRATION AND CONTROL 2022年第21-22期28卷 3411-3425页

作者： Ganguly, Krishanu Roy, Haraprasad Natl Inst Technol Dept Mech Engn Rourkela Orissa India

The present research focuses on performing the dynamic study of a cracked, internally damped, composite rotating shaft system with journal bearing end supports. A novel mathematical formulation is proposed to introduce a time-varying stiffness matrix for simulating the breathing behaviour of the crack. The random search algorithm is used as one of the metaheuristic processes to carry out the optimization and generate time-dependent geometric parameters of the cracked surface for one full rotation. The derived stiffness matrix is used in the composite shaft's higher order motion equation obtained through equivalent modulus theory, whose internal damping properties are incorporated using operator-based viscoelastic model. Eigenanalysis is carried out to perform a thorough study of dynamic characteristics of cracked shaft considering the crack depth and crack position as two important parameters. The effect of crack on stacking sequence as well as mode shapes of the heterogeneous laminated shaft is also studied.

关键词： Cracked composite shaft breathing crack model random search algorithm time-varying stiffness eigenanalysis

来源：评论

学校读者我要写书评

暂无评论

Radioactive source search problem and optimisation model based on meta-heuristic algorithm

引用

APPLIED MATHEMATICS AND NONLINEAR SCIENCES 2022年第1期7卷 927-956页

作者： Zhang, Min Lu, Xuewen Hoffman, Ettiene Kharabsheh, Radwan Xiao, Qianghua Univ South China Sch Math & Phys Hengyang Hunan Peoples R China Sch Math Phys & Energy Engn Hengyang Hunan Peoples R China Univ Calgary Dept Math & Stat Calgary AB T2N 1N4 Canada Canadian Univ Dubai Dubai U Arab Emirates Appl Sci Univ Bahrain Business Adm Econ & Adm Sci Al Hidd Bahrain

In the process of rational development and utilisation of nuclear energy, people often face nuclear accidents such as lost and stolen radioactive sources;so, the means of searching for these sources quickly in highly radioactive environments is an important security challenge. In the past, these jobs were limited to workers specialising in nuclear technology. They used gamma-ray detection equipment to search for radioactive sources, but the search efficiency was low. The main purpose of this article is to design a meta-heuristic algorithm based on imitating professional technicians to locate radioactive sources in a computer-aided manner. At the same time, due to the complexity that may characterise the actual search, the search strategy must be optimised. The article established an intelligent random search model with human thinking Finally, it was proved based on the mathematical theory that the complexity of the model search algorithm is linear, and the simulation experiment results show that the optimisation algorithm has good efficiency and fault tolerance.

关键词： nuclear radioactive source random search algorithm complexity

来源：评论

学校读者我要写书评

暂无评论

Research on Loss Reduction Tracking and Tuning Method of Distribution Network Based on Time-domain Load Integration

Research on Loss Reduction Tracking and Tuning Method of Dis...

引用

2023 IEEE Sustainable Power and Energy Conference, iSPEC 2023

作者： Cui, Jianye Jia, Lihong Zhao, Guanjun Zhang, Bo Zhang, Yihang Ma, Jiming State Grid Zhejiang Province Power Company Zhejiang Province Hangzhou City China State Grid Jinhua Power Supply Company Zhejiang Province Jinhua City China Hangzhou YangSi Information Technology Limited Company Zhejiang Province Hangzhou City China

ISBN: (纸本)9798350322699

Reducing the power loss of medium-voltage distribution network by adjusting the operation mode of distribution network is a key step towards reducing the power grid energy loss. This paper presents a loss reduction, tracking and tuning method of distribution network based on time-domain load integration. In this method, the daily load of 10kV line is predicted by least squares support vector machine. Aiming at the optimization of daily loss reduction integral, the random search algorithm of group cooperation is used to track and optimize the distribution network based on the predicted line load. This method solves the problem that the single and fixed operation mode can't adapt to the frequent fluctuation of line load and effectively improves the economic operation level of 10kV line in the whole time-domain. Examples demonstrated the feasibility and effectiveness of the approach. © 2023 IEEE.

关键词： least squares support vector machine random search algorithm short-term load forecasting time-domain load integration

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：