检索结果-内蒙古大学图书馆

Adaptive moment estimation for universal portfolio selection strategy

OPTIMIZATION AND ENGINEERING 2023年第4期24卷 2357-2385页

作者： He, Jin'an Peng, Fangping Sun Yat Sen Univ Sch Business Guangzhou 510275 Peoples R China

Since Cover's initial work in 1991, Online Portfolio Selection is undoubtedly one of crucial branches of portfolio optimization problem. The increasing development of high-frequency trading and the explosive growth of data volume increasingly require online portfolio strategies to have fast execution speed. However, almost all existing online portfolio strategies cannot satisfy both effective and full utilization of historical data and fast execution speed simultaneously. To this end, this work proposes the Adaptive Moment Estimation (AME) strategy. The proposed strategy makes effective and full utilization of historical data in an incremental way, which not only achieves improved robustness in performance but also keeps linear time complexity. Theoretical and experimental analysis are respectively established to analyze the effectiveness of the proposed AME strategy. For theoretical analysis, AME's universality is proved, which illustrates that it can theoretically compete with the benchmark Best Constant Rebalanced Portfolio in hindsight. For experimental analysis, AME achieves good performance on different evaluation metrics, and it can sustain reasonable transaction costs. Thus, it is a robust and excellent strategy with promising practical application prospects.

关键词： Online learning Universal portfolio selection adam algorithm High-frequency trading

来源：评论

学校读者我要写书评

暂无评论

Prediction of Health Level of Multiform Lithium Sulfur Batteries Based on Incremental Capacity Analysis and an Improved LSTM

引用

Protection and Control of Modern Power Systems 2024年第2期9卷 21-31页

作者： Hao Zhang Hanlei Sun Le Kang Yi Zhang Licheng Wang Kai Wang School of Materials Science and Engineering Xi’an University of Architecture and Technology in Xi’anShanxi ProvinceChina School of Electrical Engineering Qingdao UniversityQingdao 266000China College of Materials Science and Engineering Xi’an University of Science and TechnologyXi’anShaanxi ProvinceChina School of Energy Sciences and Engineering Nanjing Tech UniversityNanjingJiangsu ProvinceChina School of Information Engineering Zhejiang University of TechnologyHangzhou provinceChina

Capacity estimation plays a crucial role in battery management systems,and is essential for ensuring the safety and reliability of lithium-sulfur(Li-S)*** paper proposes a method that uses a long short-term memory(LSTM)neural network to estimate the state of health(SOH)of Li-S *** method uses health features extracted from the charging curve and incre-mental capacity analysis(ICA)as input for the LSTM *** enhance the robustness and accuracy of the network,the adam algorithm is employed to optimize specific *** data from three different groups of batteries with varying nominal capac-ities are used to validate the proposed *** results demonstrate the effectiveness of the method in accurately estimating the capacity degradation of all three ***,the study examines the impact of different lengths of network training sets on capacity *** results reveal that the ICA-LSTM model achieves a prediction accuracy of mean absolute error 4.6%and mean squared error 0.21%with three different training set lengths of 20%,40%,and 60%.The analysis demonstrates that the lightweight model maintains high SOH estimation accu-racy even with a small training set,and exhibits strong adaptive and generalization capabilities when applied to different Li-S ***,the proposed method,supported by experimental validation and analysis,demonstrates its efficacy in ensuring accurate and reliable SOH estimation,thereby enhancing the safety and per-formance of Li-S *** Terms—adam algorithm,incremental capacity analysis,Li-S battery,long short-term memory,state of health.

关键词： adam algorithm incremental capacity analysis Li-S battery long short-term memory state of health

来源：评论

学校读者我要写书评

暂无评论

adam teaching learning optimization enabled LeNet for autism spectrum disorder detection using brain MRI

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 90卷

作者： Dhamale, T. D. Bhandari, Sheetal U. Pimpri Chinchwad Coll Engn SPPU Dept Elect & Telecommun Pune Maharashtra India

The autism spectrum disorder (ASD) is a complicated, lifetime, neuro-developmental circumstance of highly unknown causes. It is greatly more ordinary than formerly believed, frequency only to mental retardation amongst serious developmental disorders. Even though, a heritable element is demonstrated in the etiology of ASD, reputed risk genes are still to be detected. Therefore, adam Teaching Learning Optimization-LeNet (ATLOLeNet) is introduced for the detection of ASD utilizing brain Magnetic Resonance Imaging (MRI). Here, input considered is provided for the image pre-processing, wherein extraction of Region of Interest (ROI) is performed and median filter is used to eradicate noises. Then, extraction of the pivotal region is completed by the devised ATLO and hence, output-1 is obtained. On the other side, features are mined from an input MRI image. The extracted features include statistical features as well as texture features. From extracted features, output-2 is attained. By considering the output-1 and output-2, ASD classification is completed by LeNet. The LeNet is trained by ATLO, which is the amalgamation of the adam algorithm and Teaching-Learning-Based Optimization (TLBO). Moreover, ATLO-LeNet acquired a maximum accuracy of 0.916, Negative Predictive Value (NPV) of 0.916and Positive Predictive Value (PPV) of 0.917 whereas it attained a minimum False Positive Rate (FPR) of 0.132 and False Negative Rate (FNR) of 0.152.

关键词： Median filter LeNet ROI extraction adam algorithm Teaching-Learning-Based Optimization (TLBO)

来源：评论

学校读者我要写书评

暂无评论

Parameter Training Methods for Convolutional Neural Networks With Adaptive Adjustment Method Based on Borges Difference

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 673-685页

作者： Jian, Jing Gao, Zhe Kan, Tao Liaoning Univ Sch Math Shenyang 110036 Peoples R China Liaoning Univ Coll Light Ind Shenyang 110036 Peoples R China

This paper proposes a momentum algorithm based on Borges difference and an adaptive momentum (adam) algorithm based on Borges difference to update parameters, which can adjust the momentum information more flexibly. The Borges difference is proposed from the definition of Borges derivative to be combined with the gradient algorithm in convolutional neural networks. The proposed momentum algorithm based on Borges difference and adam algorithm based on Borges difference can be adjusted more flexibly in order to speed up the convergence. The parameter optimization algorithm with the Borges difference presents a better performance compared with the integer-order momentum algorithm and integer-order adam algorithm, with the proposed nonlinear adjustment method for the parameter tuning of convolutional neural networks. By analyzing experimental results of Fashion-MNIST dataset and CIFAR-10 dataset, the optimization algorithms based on Borges difference proposed in this paper gain better effects on the optimization model compared with the corresponding ones based on the integer-order difference, and can speed up the convergence speed and recognition accuracy of the image recognition.

关键词： Signal processing algorithms Optimization Neural networks Fractals Convergence Training Calculus Fractal difference convolution neural networks momentum adam algorithm nonlinear adaptive tuning method

来源：评论

学校读者我要写书评

暂无评论

Development of Design Patterns with Adaptive User Interface for Cloud Native Microservice Architecture Using Deep Learning With IoT 5

Development of Design Patterns with Adaptive User Interface ...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Cherukuri, Bangar Raju Germantown MD United States

ISBN: (纸本)9798350383522

The development of design patterns with adaptive user interfaces using deep learning provides an innovative solution to address the demands of modern software systems. The design patterns play an essential role in obtaining scalability and reliability in the systems. The various challenges in the architectural designs and automatic decision-making techniques are attained through the aid of adam optimization techniques integrated with the Internet of Things. Through the process of integration with an adaptive user interface, the changing user needs are monitored by the system. The deep learning techniques help to automatically adapt and optimize itself without any external parameters. This helps to analyze the user interactions and to promote system efficiency with an enhanced performance ratio. The generation of constant streams of data is obtained through the Internet of Things. The real-time decisions are adopted by analyzing the user behaviour. The adam optimization techniques are well-known for the training of neural networks. This helps to maintain and adopt fine-tuning of the system and maintaining optimum performance. Thus the integration of deep learning with cloud-native microstructure architecture provides self-optimizing networks for each user in the dynamic nature of the IoT data in real-time environments. © 2024 IEEE.

关键词： adam algorithm Adaptive user interface Decision-making Deep learning Design patterns Internet of Things Software systems

来源：评论

学校读者我要写书评

暂无评论

A Linear Interpolation and Curvature-Controlled Gradient Optimization Strategy Based on adam

引用

algorithmS 2024年第5期17卷 185页

作者： Sun, Haijing Zhou, Wen Shao, Yichuan Cui, Jiaqi Xing, Lei Zhao, Qian Zhang, Le Shenyang Univ Sch Intelligent Sci & Engn Shenyang 110044 Peoples R China Shenyang Univ Sch Informat Engn Shenyang 110044 Peoples R China Univ Surrey Sch Chem & Chem Engn Guildford GU2 7XH Surrey England Shenyang Univ Technol Sch Sci Shenyang 110044 Peoples R China

The adam algorithm is a widely used optimizer for neural network training due to efficient convergence speed. The algorithm is prone to unstable learning rate and performance degradation on some models. To solve these problems, in this paper, an improved algorithm named Linear Curvature Momentum adam (LCMadam) is proposed, which introduces curvature-controlled gradient and linear interpolation strategies. The curvature-controlled gradient can make the gradient update smoother, and the linear interpolation technique can adaptively adjust the size of the learning rate according to the characteristics of the curve during the training process so that it can find the exact value faster, which improves the efficiency and robustness of training. The experimental results show that the LCMadam algorithm achieves 98.49% accuracy on the MNIST dataset, 75.20% on the CIFAR10 dataset, and 76.80% on the Stomach dataset, which is more difficult to recognize medical images. The LCMadam optimizer achieves significant performance gains on a variety of neural network structures and tasks, proving its effectiveness and utility in the field of deep learning.

关键词： deep learning adam algorithm curvature-controlled gradient linear interpolation LCMadam algorithm

来源：评论

学校读者我要写书评

暂无评论

Advancing Supervised Learning with the Wave Loss Function: A Robust and Smooth Approach

引用

PATTERN RECOGNITION 2024年 155卷

作者： Akhtar, Mushir Tanveer, M. Arshad, Mohd. Indian Inst Technol Indore Dept Math Indore 453552 India

Loss function plays a vital role in supervised learning frameworks. The selection of the appropriate loss function holds the potential to have a substantial impact on the proficiency attained by the acquired model. The training of supervised learning algorithms inherently adheres to predetermined loss functions during the optimization process. In this paper, we present a novel contribution to the realm of supervised machine learning: an asymmetric loss function named wave loss. It exhibits robustness against outliers, insensitivity to noise, boundedness, and a crucial smoothness property. Theoretically, we establish that the proposed wave loss function manifests the essential characteristic of being classification-calibrated. Leveraging this breakthrough, we incorporate the proposed wave loss function into the least squares setting of support vector machines (SVM) and twin support vector machines (TSVM), resulting in two robust and smooth models termed as Wave-SVM and Wave-TSVM, respectively. To address the optimization problem inherent in Wave-SVM, we utilize the adaptive moment estimation (adam) algorithm, which confers multiple benefits, including the incorporation of adaptive learning rates, efficient memory utilization, and faster convergence during training. It is noteworthy that this paper marks the first instance of adam's application to solve an SVM model. Further, we devise an iterative algorithm to solve the optimization problems of Wave-TSVM. To empirically showcase the effectiveness of the proposed Wave-SVM and Wave-TSVM, we evaluate them on benchmark UCI and KEEL datasets (with and without feature noise) from diverse domains. Moreover, to exemplify the applicability of Wave-SVM in the biomedical domain, we evaluate it on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The experimental outcomes unequivocally reveal the prowess of Wave-SVM and Wave-TSVM in achieving superior prediction accuracy against the baseline models. The source code

关键词： Supervised learning Pattern classification Loss function Support vector machine Twin support vector machine Wave loss function adam algorithm Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

A Novel algorithm for Solving High-Dimensional Poisson Equations Based on Radial Basis Function Neural Networks

引用

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 2024年第13期33卷 2450223-2450223页

作者： Lu, Peixiao Sun, Shaoming Xinjiang Univ Sch Math & Syst Sci Urumqi 830046 Xinjiang Peoples R China Hefei Sci Isl Hefei Intelligence Hefei 230031 Anhui Peoples R China

As a widely used equation in electrostatics, the Poisson equation has significant research value in numerical solution. The basic principle of existing methods is to divide the solution domain into various grids and solve the numerical solutions at each grid node. Therefore, the accuracy of the solution is strongly correlated with the grid density divided. Based on this, this paper proposes a grid-free numerical calculation method that requires far fewer model parameters than traditional methods, and can ignore the order of the equation to solve high-dimensional Poisson equations. Given a Poisson equation, which has a certain type of boundary condition. A certain number of coordinate points are selected on the solution space and its boundary to construct a dataset. Using automatic differentiation technique to fit the differential operator in the equation, a loss function is constructed by incorporating the given boundary conditions or initial conditions, and the final numerical solution is obtained through iterative optimization algorithms. In the numerical experiment section, the algorithm proposed in this paper was used to solve the two-dimensional and three-dimensional Poisson equations with given exact solutions. The relative errors between the numerical solution and the true solution were 8.53e-4 and 6.40e-2, which are within the acceptable range. This proves that the proposed algorithm is feasible for solving the two-dimensional and three-dimensional Poisson equations with precise solutions. Secondly, the proposed algorithm is used to solve the four-dimensional Poisson equation with first-type boundary conditions, and the relative error range of the solution was within [0,0.56], which successfully extends the algorithm to solve high-dimensional Poisson equations and verifies its feasibility and efficiency in solving high-dimensional Poisson equations regardless of the dimension restriction.

关键词： Poisson equation radial basis neural (RBF) network automatic differentiation technology adam algorithm mesh free numerical algorithm

来源：评论

学校读者我要写书评

暂无评论

A general deep hybrid model for bioreactor systems: Combining first principles with deep neural networks

引用

COMPUTERS & CHEMICAL ENGINEERING 2022年 165卷

作者： Pinto, Jose Mestre, Mykaella Ramos, J. Costa, Rafael S. Striedner, Gerald Oliveira, Rui NOVA Univ Lisbon NOVA Sci & Engn Sch LAQV REQUIMTE Lisbon Portugal BOKU Univ Dept Biotechnol Vienna Austria

Numerous studies have reported the use of hybrid semiparametric systems that combine shallow neural networks with First Principles for bioprocess modeling. Here we revisit the general bioreactor hybrid model and introduce some deep learning techniques. Multi-layer networks with varying depths were combined with First Principles equations in the form of deep hybrid models. Deep learning techniques, namely the adaptive moment estimation method (adam), stochastic regularization and depth-dependent weights initialization were evaluated in a hybrid modeling context. Modified sensitivity equations are proposed for the computation of gradients in order to reduce CPU time for the training of deep hybrid models. The methods are illustrated with applications to a synthetic dataset and a pilot 50 L MUT+ Pichia pastoris process expressing a single chain antibody fragment. All in all, the results point to a systematic generalization improvement of deep hybrid models over its shallow counterpart. Moreover, the CPU cost to train the deep hybrid models is shown to be lower than for the shallow counterpart. In the pilot 50L MUT+ Pichia pastoris data set, the prediction accuracy was increased by 18.4% and the CPU decreased by 43.4%.

关键词： Hybrid semiparametric modeling Deep neural networks adam algorithm Stochastic regularization Bioprocess dynamics Pichia pastoris

来源：评论

学校读者我要写书评

暂无评论

Short-term building cooling load prediction model based on Dwdadam-ILSTM algorithm: A case study of a commercial building

引用

ENERGY AND BUILDINGS 2022年 272卷

作者： Dong, Fangnan Yu, Junqi Quan, Wei Xiang, Yalun Li, Xiang Sun, Fukang Xian Univ Architecture & Technol Xian Shaanxi Peoples R China

Traditional prediction methods of building cooling load fail to consider load changes caused by the time factor, which results in the failure of the best predicting effect and portability. To explore a more accurate cooling load predicting approach, in this paper, a new hybrid model based on decoupled weight decay adam optimized improved LSTM neural network, denoted as Dwdadam-ILSTM, is proposed. First, the cross-correlation function is used to extract features with a high degree as the input data. Then, the decoupling weight decay adaptive moment estimation (Dwdadam) optimization algorithm is utilized to optimize the parameters of the improved long short term memory (ILSTM) prediction model. Next, the ILSTM is employed to establish a prediction model. Finally, to verify the validity and prediction accu-racy of the proposed model, this paper selects the hourly cooling load data of a large commercial building in Xi'an as the research sample. Results of the experiment show that the Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), Variation Coefficient of Root Mean Square Error (CV-RMSE) and Range of Relative Errors (E-R) of Dwdadam-ILSTM predicting the cooling load are 2.2%, 2.74, 5.2%, 0.061, 0.216. Compared with three version variant LSTM neural networks, the MSE and E-R values of this model are decreased by 74%-53%, 42%-49%, and 69%-64%, which has better performance in accuracy and stability. It testifies that the proposed strategy is reliable and effective. Additionally, this model can provide important guidance for daily energy management and multi -energy scheduling of buildings, which is helpful to the application of cooling load prediction. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Building cooling load Short-term prediction Long short-term memory adam algorithm Predictive performance

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：