检索结果-内蒙古大学图书馆

BLSNet: Skin lesion detection and classification using broad learning system with incremental learning algorithm

EXPERT SYSTEMS 2022年第9期39卷 e12938-e12938页

作者： Gottumukkala, V. S. S. P. Raju Kumaran, N. Sekhar, V. Chandra Annamalai Univ Dept Comp Sci & Engn Chidambaram 608002 Tamil Nadu India Sagi Rama Krishnam Raju Engn Coll Dept Comp Sci & Engn Bhimavaram Andhra Pradesh India

Background Skin lesion detection and classification (SLDC) is extremely important in the diagnosis of skin cancer and detection of melanoma cancer. As a result, the use of image processing equipment integrated with artificial intelligence can assist dermatologists in their decision-making and examination. In addition, all deep learning (DL) structures consumes more time due to the large number of associated factors in filters and layers. Furthermore, if the architecture is insufficient to prototype the classification system, it must go through a lengthy retraining procedure. Material and method Therefore, this article proposes a broad learning system (BLS) using incremental learning algorithm for the classification of non-melanoma and melanoma skin lesions from dermoscopic images. Here after the proposed model is termed as BLSNet. Results Experiments on ISIC 2019 and PH2 dataset indicate that proposed SLDC using BLSNet out-perform the existing DL-based SLDC models with an accuracy of 99.09% and F-1-score of 98.73%. Further, the overall execution time of proposed BLSNet is 0.93 s, which is superior as compared to the conventional approaches. Conclusion Thus, the performance trade-off between classification accuracy and execution time is achieved using proposed BLSNet model.

关键词： broad learning system deep learning convolutional neural networks incremental learning algorithm melanoma and non-melanoma classification skin lesion detection

来源：评论

学校读者我要写书评

暂无评论

IDLIQ: An incremental Deterministic Finite Automaton learning algorithm Through Inverse Queries for Regular Grammar Inference

引用

BIG DATA 2024年第6期12卷 446-455页

作者： Haneef, Farah Sindhu, Muddassar A. Quaid I Azam Univ Dept Comp Sci Islamabad Pakistan Quaid I Azam Univ Dept Comp Sci Islamabad 45320 Pakistan

We present an efficient incremental learning algorithm for Deterministic Finite Automaton (DFA) with the help of inverse query (IQ) and membership query (MQ). This algorithm is an extension of the Identification of Regular Languages (ID) algorithm from a complete to an incremental learning setup. The learning algorithm learns by making use of a set of labeled examples and by posing queries to a knowledgeable teacher, which is equipped to answer IQs along with MQs and equivalence query. Based on the examples (elements of the live complete set) and responses against IQs from the minimally adequate teacher (MAT), the learning algorithm constructs the hypothesis automaton, consistent with all observed examples. The incremental DFA learning algorithm through Inverse Queries (IDLIQ) takes O(|S|N+|P-c||F|) time complexity in the presence of a MAT and ensures convergence to a minimal representation of the target DFA with finite number of labeled examples. Existing incremental learning algorithms;the incremental ID, the incremental Distinguishing Strings have polynomial (cubic) time complexity in the presence of a MAT. Therefore, sometimes, these algorithms even fail to learn large complex software systems. In this research work, we have reduced the complexity (from cubic to square form) of the DFA learning in an incremental setup. Finally, we prove the correctness and termination of the IDLIQ algorithm.

关键词： grammatical inference incremental learning algorithm delta inverse transitions inverse query live complete set distinguishing string

来源：评论

学校读者我要写书评

暂无评论

Evolving Connectionist System and Hidden Semi-Markov Model for learning-Based Tool Wear Monitoring and Remaining Useful Life Prediction

引用

IEEE ACCESS 2022年 10卷 82469-82482页

作者： Lin, Muquan Song Wanqing Chen, Dongdong Zio, Enrico Minnan Univ Sci & Technol Sch Elect & Elect Engn Quanzhou 362700 Peoples R China Jiangxi New Energy Technol Inst Xinyu 338000 Peoples R China Fujian Univ Key Lab Ind Automat Control Technol & Applicat Quanzhou 362700 Peoples R China PSL Res Univ MINES ParisTech CRC F-06904 Sophia Antipolis France Politecn Milan Dept Energy I-20156 Milan Italy

Tool wear can cause dimensional accuracy and poor surface quality in milling process. During the operation of tool wear, it can also cause breakage and damage of the workpieces. To prevent these conditions, it's important that the tool wear is monitored and the remaining useful life (RUL) is predicted in real time. In this paper, time domain and frequency domain statistical features are firstly extracted using multi-sensory fusion method, including the cutting force, vibration and acoustic emission sensor. Seven eigenvectors are selected as the input of the prediction model based on the distance correlation coefficient between 140 feature vectors and the wear value, which provide the most sensitive features to wear faults. The paper establishes a nonlinear relationship between high-dimensional feature vectors and tools wear based on the evolving connectionist system (ECoS), which uses the incremental learning algorithm to realize real-time prediction of the tools wear. Finally, using the wear value predicted by ECoS as hidden state sequence of Hidden Semi-Markov Model (HSMM), the RUL prediction of the tool based on HMM is established. The 2010 PHM challenge data were used to train the model. The experimental result shows that in comparison with artificial neural network, the ECoS model has higher prediction accuracy, and its mean RMSE error for three tools is 14.8. In comparison with the RUL prediction of HMM model, Probability-based RUL prediction of HSMM is more stable.

关键词： Monitoring Neurons Predictive models Hidden Markov models Prediction algorithms Force Feature extraction Multi-sensor fusion evolving connectionist system incremental learning algorithm HSMM remaining useful life prediction

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving vertical federated broad learning system for artificial intelligence generated image content

引用

JOURNAL OF REAL-TIME IMAGE PROCESSING 2024年第1期21卷 14-14页

作者： Li, Fengyin Ge, Junrong Wang, Xiaojiao Zhao, Gang Yu, Xilong Li, Xinru Qufu Normal Univ Sch Comp Sci Rizhao Peoples R China Rizhao Adm Examinat & Approval Serv Bur Rizhao Peoples R China

Artificial intelligence generated image content generates desired image content according to given instructions. It is widely applied in digital marketing, video game design, and movie production. How to efficiently detect the quality of the generated images is one of the key problems. A broad learning system is a feasible solution, because it requires no complex parameter calculation and depth expansion. However, the broad learning system is built by centralized learning, so it may not take advantage of isolated feature data, which prevents broad learning systems from detecting isolated AL-generated image content. To address the above problem, this paper proposes a privacy-preserving vertical federated broad learning system for artificial intelligence generated image content (PVF-BLS). In PVF-BLS, the vertical federated architecture is introduced into the broad learning system to utilize isolated feature data and interactive data are masked by matrix masks for security. To further improve the security of PVF-BLS, this paper proposes a secure incremental learning algorithm based on matrix masks (ILA-MM) to update PVF-BLS. In ILA-MM, the interaction data are processed by matrix masks, which makes PVF-BLS more secure. Experimental results show that PVF-BLS outperforms the traditional broad learning systems when the data are isolated.

关键词： Broad learning system Vertical federation incremental learning algorithm Isolated data Artificial intelligence generated content

来源：评论

学校读者我要写书评

暂无评论

An in-depth comparison of methods handling mixed-attribute data for general fuzzy min-max neural network

引用

NEUROCOMPUTING 2021年 464卷 175-204页

作者： Khuat, Thanh Tung Gabrys, Bogdan Univ Technol Sydney Data Sci Inst Complex Adapt Syst Lab Sydney NSW Australia

A general fuzzy min-max (GFMM) neural network is one of the efficient neuro-fuzzy systems for classification problems. However, a disadvantage of most of the current learning algorithms for GFMM is that they can handle effectively numerical valued features only. Therefore, this paper provides some potential approaches to adapting GFMM learning algorithms for classification problems with mixed-type or only categorical features as they are very common in practical applications and often carry very useful information. We will compare and assess three main methods of handling datasets with mixed features, including the use of encoding methods, the combination of the GFMM model with other classifiers, and employing the specific learning algorithms for both types of features. The experimental results showed that the target and James-Stein are appropriate categorical encoding methods for learning algorithms of GFMM models, while the combination of GFMM neural networks and decision trees is a flexible way to enhance the classification performance of GFMM models on datasets with the mixed features. The learning algorithms with the mixed-type feature abilities are potential approaches to deal with mixed-attribute data in a natural way, but they need further improvement to achieve a better classification accuracy. Based on the analysis, we also identify the strong and weak points of different methods and propose potential research directions. (C) 2021 Elsevier B.V. All rights reserved.

关键词： General fuzzy min-max neural network Data encoding methods Categorical features Mixed-type features incremental learning algorithm Agglomerative learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Weighted Broad learning System and Its Application in Nonlinear Industrial Process Modeling

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2020年第8期31卷 3017-3031页

作者： Chu, Fei Liang, Tao Chen, C. L. Philip Wang, Xuesong Ma, Xiaoping China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China State Key Lab Proc Automat Min & Met Beijing 100160 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China Xuzhou Key Lab Artificial Intelligence & Big Data Xuzhou 221116 Jiangsu Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510641 Peoples R China Dalian Maritime Univ Nav Coll Dalian 116026 Peoples R China Univ Macau Fac Sci & Technol Macau 99999 Peoples R China

Broad learning system (BLS) is a novel neural network with effective and efficient learning ability. BLS has attracted increasing attention from many scholars owing to its excellent performance. This article proposes a weighted BLS (WBLS) based on BLS to tackle the noise and outliers in an industrial process. WBLS provides a unified framework for easily using different methods of calculating the weighted penalty factor. Using the weighted penalty factor to constrain the contribution of each sample to modeling, the normal and abnormal samples were allocated higher and lower weights to increase and decrease their contributions, respectively. Hence, the WBLS can eliminate the bad effect of noise and outliers on the modeling. The weighted ridge regression algorithm is used to compute the algorithm solution. Weighted incremental learning algorithms are also developed using the weighted penalty factor to tackle the noise and outliers in the additional samples and quickly increase nodes or samples without retraining. The proposed weighted incremental learning algorithms provide a unified framework for using different methods of computing weights. We test the feasibility of the proposed algorithms on some public data sets and a real-world application. Experiment results show that our method has better generalization and robustness.

关键词： learning systems Training Heuristic algorithms Neural networks Automation Process control Control engineering Broad learning system (BLS) incremental learning algorithm noise and outliers weighted penalty factor

来源：评论

学校读者我要写书评

暂无评论

Modeling Method for Performance Prediction of Centrifugal Compressor Based on Broad learning System 31

Modeling Method for Performance Prediction of Centrifugal Co...

引用

31st Chinese Control And Decision Conference (CCDC)

作者： Chu, Fei Su, Jiaming Liang, Tao Ma, Xiaoping Wang, Fuli China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China Northeastern Univ State Key Lab Integrated Automat Proc Ind Shenyang 110819 Peoples R China Northeastern Univ Sch Informat Sci & Engn Shenyang 110819 Peoples R China

ISBN: (纸本)9781728101057

An accurate model is very important for the design and control of centrifugal *** paper proposes a rapid modeling method for centrifugal compressor based on broad learning *** method can be used for off-line modeling of compressor performance prediction .When new data samples enter into the model, this paper uses incremental learning algorithm to realize fast online modeling of ***, simulation results show that the proposed method can achieve a good prediction precision and can be used in compressor performance prediction online.

关键词： Centrifugal compressor Broad learning system incremental learning algorithm Performance prediction

来源：评论

学校读者我要写书评

暂无评论

A Study on Radar Target Detection Based on Broad learning System

A Study on Radar Target Detection Based on Broad Learning Sy...

引用

作者： Bo Li Jun Tang Siyuan Ouyang Li Wang Department of Electronic Engineering Tsinghua University

Target detection is one of the most important tasks of radar. Statistical signal processing methods for target detection have made several achievements;meanwhile, neural network-based methods have also received increasing attention. The newly proposed broad learning system(BLS) is an effective and efficient incremental learning system without deep architecture, and it has been successfully applied to the classification problem. In this article, the BLS is applied for radar target detection. We design a BLS target detector using the incremental learning algorithm, and it's very attractive that the BLS detector shows a better performance in the experiment by comparison with the typical detectors.

关键词： Broad learning System (BLS) incremental learning algorithm neural network radar target detection

来源：评论

学校读者我要写书评

暂无评论

An Outpost Vector Placement Evaluation of an incremental learning algorithm for Support Vector Machine

An Outpost Vector Placement Evaluation of an Incremental Lea...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Fuangkhon, Piyabute Tanprasert, Thitipong Assumption Univ Fac Sci & Technol Distributed & Parallel Comp Res Lab Bangkok 10240 Thailand

ISBN: (纸本)9781424496365

Outpost Vector model synthesizes new vectors at the boundary of two classes of data in order to increase the level of accuracy of classification. This paper presents a performance evaluation of four different placements of outpost vectors in an incremental learning algorithm for Support Vector Machine (SVM) on a non-complex problem. The algorithm generates outpost vectors from selected new samples, selected prior samples, both samples, or generates no outpost vector at all. After that, they are included in the final training set, as well as new samples and prior samples, based on the specified parameters. The experiments are conducted with a 2-dimension partition problem. The distribution of training and test samples is created in a limited location of a 2-dimension donut ring. There are two classes of data which are represented as 0 and 1. The context of the problem is assumed to shift 45 degrees in counterclockwise direction. Every consecutive partition is set to have different class of data. The experimental results show that the placement of outpost vectors generated from only selected new samples yields the highest level of accuracy of classification for both new data and old data. As a result, using samples from different part of the algorithm to generate outpost vectors affects the level of accuracy of classification.

关键词： 2-dimension donut ring 2-dimension partition problem Accuracy Context Data models Shape Support vector machines Training Vectors data classification data handling data representation data structures incremental learning algorithm learning (artificial intelligence) noncomplex problem outpost vector placement evaluation pattern classification performance evaluation support vector machine support vector machines training set

来源：评论

学校读者我要写书评

暂无评论

A fast learning method for streaming and randomly ordered multi-class data chunks by using one-pass-throw-away class-wise learning concept

引用

EXPERT SYSTEMS WITH APPLICATIONS 2016年第0期63卷 249-266页

作者： Junsawang, Prem Phimoltares, Suphakant Lursinsap, Chidchanok Chulalongkorn Univ Fac Sci Dept Math & Comp Sci Adv Virtual & Intelligent Comp AVIC Res Ctr Bangkok Thailand

Presently, the amount of data occurring in several business and academic areas such as ATM transactions, web searches, and sensor data are tremendously and continuously increased. Classifying as well as recognizing patterns among these data in a limited memory space complexity are very challenging. Various incremental learning methods have proposed to achieve highly accurate results but both already learned data and new incoming data must be retained throughout the learning process, causing high space and time complexities. In this paper, a new neural learning method based on radial-shaped function and discard-after-learn concept in the data streaming environment was proposed to reduce the space and time complexities. The experimental results showed that the proposed method used 1 to 95 times fewer neurons and 1.2 to 2,700 times faster than the results produced by MLP, RBF, SVM, VEBF, ILVQ ASC, and other incremental learning methods. It is also robust to the incoming order of data chunks. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Classification Versatile elliptic basis function incremental learning algorithm

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：