检索结果-内蒙古大学图书馆

Entropy query by bagging-based active learning approach in the extreme learning machine framework for hyperspectral image classification

引用

CURRENT SCIENCE 2020年第6期119卷 934-943页

作者： Pradhan, Monoj K. Minz, Sonajharia Shrivastava, Vimal K. Jawaharlal Nehru Univ Sch Comp & Syst Sci New Delhi 110067 India Kalinga Inst Ind Technol Sch Elect Engn Bhubaneswar 751024 India

Active learning (AL) technique is the classification of remote sensing images, where collecting efficient training data is costly in terms of labour and the time taken. The prime objective of AL technique is to obtain high classification accuracy with the training sample as compact as possible. Most studies on the classification of remote sensing images using AL, focused only on accuracy, with hardly any study on computation time. Keeping reduction of computation time as the objective, here we present, an entropy query by bagging (EQB)-based AL approach in the extreme learning machine (ELM) framework for remote sensing image classification. The performance of this approach is compared with the widely used support vector machine (SVM) AL framework in combination with different query strategies. To verify the efficacy of the study, the approaches were tested on two hyperspectral remote-sensing images, i.e. Kennedy Space Centre (KSC) and Botswana (BOT). The proposed system depicts competitive classification performance while significantly reducing computation time.

关键词： Active learning computation time extreme learning machine entropy query by bagging

来源：评论

学校读者我要写书评

暂无评论

Two viewpoints based real-time recognition for hand gestures

引用

IET IMAGE PROCESSING 2020年第17期14卷 4606-4613页

作者： Kumar, Amit Krishan Kumar, Abhishek Kaushal Guo, Shuli Beijing Inst Technol Sch Automat Key Lab Complex Syst Intelligent Control & Decis Beijing Peoples R China Univ South Pacific Sch Engn & Phys Laucala Fiji

It is extremely challenging to accomplish excellent accuracy for gesture recognition using an approach where complexity in computation time for recognition is less. This study compares accuracy in hand gesture recognition of a single viewpoint set-up with proposed two viewpoint set-up for different classification techniques. The efficacy of the presented approach is verified practically with various image processing, feature extraction and classification techniques. Two camera system make geometry learning and three-dimensional (3D) view feasible compared to a single camera system. Geometrical features from additional viewpoint contribute to 3D view estimation of the hand gesture. It also improves the classification accuracy. Experimental results demonstrate that the proposed method show escalation in recognition rate compared to the single-camera system, and also has great performance using simple classifiers like the nearest neighbour and decision tree. Classification within 1 s is considered as real-time in this study.

关键词： image classification feature extraction learning (artificial intelligence) cameras geometry gesture recognition decision trees computation time hand gesture recognition single viewpoint set-up image processing feature extraction three-dimensional view single camera system geometrical features 3D view estimation classification accuracy recognition rate single-camera system real-time recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing hybrid genetic algorithm performance in reducing steel usage for shipbuilding through sensitivity analysis

引用

COGENT ENGINEERING 2024年第1期11卷

作者： Istiyanto, Jos Putra, Gerry Liston Ramadhan, Muhammad Rifqi Univ Indonesia Dept Mech Engn Depok West Java Indonesia

In ship construction, material costs constitute a substantial portion of the overall expenses. With the surging steel prices, the shipbuilding industry faces a pressing challenge. To counterbalance this issue, optimizing the structural components of ships has emerged as a viable solution. Genetic Algorithm (GA) methods, known for their application in structural optimization, have demonstrated their potential. However, the protracted computational time associated with GA remains a limiting factor. This research introduces a novel approach by merging GA with Finite Element Method (FEM) for optimizing plate sizes, resulting in a hybrid GA system. Moreover, the study incorporates sensitivity analysis (SA) due to its proven efficacy in enhancing optimization processes involving multiple variables. The SA component investigates plate interrelationships and effectively clusters them. After this grouping, the hybrid GA executes parallel optimization of plates that influence each other under tension. By integrating SA, the optimization process becomes faster and more time-efficient, while preserving optimal manufacturing costs. Remarkably, this methodology culminates in a substantial reduction in computational time when contrasted with the hybrid GA approach devoid of SA, all the while maintaining a parallel manufacturing cost trajectory. In conclusion, this study presents an innovative hybrid GA approach, supplemented with SA, as an effective strategy for mitigating the escalating steel costs in shipbuilding. The amalgamation of GA, FEM and SA synergistically simplifies the optimization process, ensuring optimal results in a faster way.

关键词： Material selection sensitivity analysis hybrid genetic algorithm computation time material cost

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of a BLDC Motor Considering Three-Dimensional Structures Using the Response Surface Methodology

引用

ENERGIES 2022年第2期15卷 461页

作者： Jo, Seong-Tae Shin, Hyo-Seob Lee, Young-Geun Lee, Ji-Hun Choi, Jang-Young Chungnam Natl Univ Dept Elect Engn Daejeon 305764 South Korea

In this paper, the optimal design of a brushless direct current motor with a three-dimensional (3D) structure using the response surface methodology (RSM) is presented. There were two optimization goals: reduction of the cogging torque and maintenance of the back electromotive force to prevent performance degradation. For motors with a 3D structure, a 3D finite element method analysis is essential, though it requires considerable computation time. Therefore, to reduce the optimal design time, the 3D structure was placed on the 2D plane. Thereafter, a 2D corrected model was applied to the RSM. For the validity of the technique, the analysis results of the initial 3D model, 2D model, and 2D corrected model were compared, and the results of the optimal design 3D model, 2D corrected model, and experiment were compared.

关键词： BLDC motor magnet overhang housing-integrated rotor 2D equivalent response surface methodology computation time

来源：评论

学校读者我要写书评

暂无评论

Simplified calculation method for spectral fatigue analysis of hull structure

引用

OCEAN ENGINEERING 2022年 243卷 110204-110204页

作者： Liu, Yuchao Ren, Huilong Feng, Guoqing Sun, Shili Harbin Engn Univ Coll Shipbldg Engn Harbin 150001 Peoples R China

The spectral fatigue analysis method has irreplaceable advantages in the fatigue evaluation and optimization design of hull structure, but its calculation process is too complex and time-consuming, which limits the application of it. Thus, this paper considers simplifying the calculation process of the spectral fatigue analysis method. First, this paper conducted a simplified study on wave frequencies. The lj wave frequencies of wavedirection j were screened, and the vj wave frequencies that contribute greatly to partial damage Dj were determined as the main relevant frequencies. Based on this, the simplified calculation method of partial damage Dj (SCM-I) was given. Then, this paper considered simplifying wave-directions in the fatigue analysis of hull structure, and ultimately determined the judgment conditions and specific methods for the simplification of wave-directions. Similarly, this paper also proposed the simplified calculation method of damage D (SCM-II). Finally, this paper selected a parent target, and obtained an application target of the simplified calculation method on the basis of it. And then, the simplified calculation method was studied based on them. Related studies indicate: compared with the spectral fatigue analysis method, the simplified calculation method proposed in this paper can not only fully ensure the accuracy of the calculation results, but also greatly reduce the computation time.

关键词： Spectral fatigue analysis Simplified calculation method Main relevant frequencies Judgment conditions Calculation error control computation time

来源：评论

学校读者我要写书评

暂无评论

The Pareto-optimal temporal aggregation of energy system models

引用

APPLIED ENERGY 2022年 315卷

作者： Hoffmann, Maximilian Kotzur, Leander Stolten, Detlef Forschungszentrum Julich GmbH Technoecon Syst Anal IEK 3 Wilhelm Johnen Str D-52428 Julich Germany Rhein Westfal TH Aachen Chair Fuel Cells Aachen Germany

The growing share of intermittent renewable energy sources, storage technologies, and the increasing degree of so-called sector coupling necessitates optimization-based energy system models with high temporal and spatial resolutions, which significantly increases their runtimes and limits their maximum sizes. In order to maintain the computational viability of these models for large-scale application cases, temporal aggregation has emerged as a technique for reducing the number of considered time steps by reducing the original time horizon down to fewer, more representative *** study presents advanced but generally applicable clustering techniques that allow for ad-hoc improvements of current approaches without requiring profound knowledge of the individual energy system model. These improvements comprise a method to find the optimal tradeoff between the number of typical days and inner-daily temporal resolutions, and a representation method that can reproduce the value distribution of the original time series. We prove the superiority of these approaches by applying them to two fundamentally different model types and benchmarking them against state-of-the-art approaches. This is performed for a variety of temporal resolutions, which leads to many hundreds of model *** results show that the proposed improvements on current methods strictly dominate the status quo with respect to Pareto-optimality in terms of runtime and accuracy. Although a speeding up factor of one magnitude could be achieved using traditional aggregation methods within a cost deviation range of two percent, the algorithms proposed herein achieve this accuracy with a runtime speedup by a factor of two orders of magnitude.

关键词： Typical days Segmentation time slices Energy system models time series aggregation Temporal aggregation Temporal resolution Renewable energy systems Clustering computation time Pareto optimality

来源：评论

学校读者我要写书评

暂无评论

Acceleration of multi-task cascaded convolutional networks

引用

IET IMAGE PROCESSING 2020年第11期14卷 2435-2441页

作者： Ma, Long-Hua Fan, Hang-Yu Lu, Zhe-Ming Tian, Dong Zhejiang Univ Ningbo Inst Technol Sch Informat Sci & Engn Ningbo 315100 Peoples R China Zhejiang Univ Sch Aeronaut & Astronaut Hangzhou 310027 Peoples R China

Multi-task cascaded convolutional neural network (MTCNN) is a human face detection architecture which uses a cascaded structure with three stages (P-Net, R-Net and O-Net). The authors intend to reduce the computation time of the whole process of the MTCNN. They find that the non-maximum suppression (NMS) processes after the P-Net occupy over half of the computation time. Therefore, the authors propose a self-fine-tuning method which makes the control of computation time for the NMS process easier. Self-fine-tuning is a training trick which uses hard samples generated by P-Net to retrain P-Net. After self-fine-tuning, the distribution of human face probabilities generated by P-Net is changed, and the tail of distribution becomes thinner. The control of the number of NMS input boxes can be made easier when the distribution has a thinner tail, and choosing a suitable threshold to filter the face boxes will generate less boxes. So the computation time can be reduced. In order to keep the performance of MTCNN, the authors still propose a landmark data set augmentation, which can enhance the performance of the self-fine-tuned MTCNN. From the experiments, it is found that the proposed scheme can significantly reduce the computation time of MTCNN.

关键词： face recognition learning (artificial intelligence) object detection probability convolutional neural nets convolutional neural network human face detection architecture cascaded structure P-Net computation time weight pruning channel pruning self-fine-tuning method NMS process human face probabilities NMS input boxes face boxes self-fine-tuned MTCNN multitask cascaded convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Smart feature extraction and classification of hyperspectral images based on convolutional neural networks

引用

IET IMAGE PROCESSING 2020年第10期14卷 1999-2005页

作者： Hamouda, Maissa Ettabaa, Karim Saheb Bouhlel, Med Salim Univ Sousse SETIT Lab ISITCom Sousse Tunisia Univ Sousse IMT Atlantique ISITCom Sousse Tunisia Univ Sfax ENIS SETIT Lab Sfax Tunisia

Hyperspectral satellite imagery (HSI) is an advanced technology for object detection because it provides a large amount of information. Thus, the classification of HSIs is very complicated, so the methods of reducing spectral or spatial information generally degrade the quality of classification. In order to solve this problem and guarantee faster and more efficient processing, we propose a smart feature extraction (SFE) and classification by convolutional neural network (2D-CNN) method made up of two parts. The first consists in reducing spectral information by a probabilistic method based on the Softmax function. The second is classification by processing batches of data in the proposed CNN network. The method was tested on two public hyperspectral images (Indian Pines and SalinasA) to prove its effectiveness in increasing classification accuracy and reducing computing time.

关键词： feature extraction neural nets object detection geophysical image processing image classification spectral analysis hyperspectral imaging hyperspectral images computation time processing capacity spectral information spectral band reduction convolutional neural network algorithms HSI classification extraction methods band-by-band class previous bands probabilistic reduction method called Smart feature extraction 2D-CNN hyperspectral pixel authors spatial neighbourhood convolutional neural networks hyperspectral satellite imagery object detection spatial information

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Fuzzy Engine for Adaptive Control towards improvement of Network Performance in Big Data Environment

引用

Procedia Computer Science 2022年 215卷 24-32页

作者： S. Saravanan J. Samuel Manoharan Vimal Kumar M N S. Surenderanath Professor/Dept. of IT Karpagam College of Engineering Coimbatore India Professor/Dept. of ECE Sir Isaac Newton College of Engineering & Technology Nagapattinam India Associate Professor/Dept. of Mechatronics Engineering Sona College of Technology Salem India Asst. Professor/Dept. of ECE Sri Sai Ram Institute of Technology Chennai India

With increasing computational utilities in recent times, the need for systems capable of processing immense and voluminous amount of information has witnessed an exponential rise. Concepts of cloud computing and Big Data have proved to be promising solutions to the emerging problems of handling huge volume of data. Big data finds utilities over a wide range of applications starting from sensor networks, data processing involving image acquisition of high-definition data (HD), predictor models involving huge volumes of historical data, classification models involving sentimental analysis, emotion analysis etc. A classic case of big data processing in sensor networks for an IoT environment has been investigated in this research paper with the sole objective of tuning the network performance using a dynamic fuzzy based model. The experimentation has been conducted on a wearable technology database based on IoT comprising of several sensors incorporated in a WBAN (Wireless body area network) technology. Superior performance is reported in the form of improved computation time, accuracy, precision when compared with the big data model without fuzzy engine.

关键词： Big Data Adaptive Network Optimization Wearable IoT (Internet of Things) Sensor Networks computation time

来源：评论

学校读者我要写书评

暂无评论

Alternative representations for the probability of detection of non-fluctuating targets

引用

ELECTRONICS LETTERS 2020年第21期56卷 1136-1138页

作者： Garcia, F. D. A. Mora, H. R. C. Garzon, N. V. O. Santos Filho, J. C. S. Univ Estadual Campinas UNICAMP Dept Commun Campinas Brazil Univ Las Amer UDLA Fac Engn & Appl Sci Telecommun Engn Quito Ecuador

The authors derive a closed-form exact expression and a fast convergent series for the probability of phased-array detection of non-fluctuating targets embedded in complex white Gaussian noise. To be realistic, they assume that the amplitude of the target echoes and the noise power are unknown parameters. Their series representation achieved impressive savings in computational load and computation time when compared to the numerical evaluation of the existing integral-form solution.

关键词： AWGN Gaussian noise approximation theory radar clutter radar detection probability nonfluctuating targets closed-form exact expression fast convergent series phased-array detection complex white Gaussian noise target echoes noise power series representation computational load computation time

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：