This paper surveys dimension reduction techniques in medical big data using optimization algorithms to address challenges like computational inefficiency, overfitting, and interpretability in high-dimensional datasets...
详细信息
ISBN:
(纸本)9798350367782;9798350367775
This paper surveys dimension reduction techniques in medical big data using optimization algorithms to address challenges like computational inefficiency, overfitting, and interpretability in high-dimensional datasets. As medical data from sources like electronic health records, genomics, and imaging grow, efficient processing is essential for personalized healthcare. The paper explores feature extraction (PCA, LDA) and feature selection methods, emphasizing metaheuristic algorithms like Genetic algorithms (GA), Particle Swarm optimization (PSO), and Ant Colony optimization (ACO). These algorithms enhance machine learning model accuracy by selecting relevant features, reducing computational costs, and handling nonlinear relationships in medical data. Applications in diagnosis, treatment prediction, and disease classification are discussed. Future research aims to integrate various optimization strategies and deep learning for more effective dimensionality reduction in healthcare.
This paper analyzes distributed optimization algorithms from a frequency-domain perspective. We propose a general class of gradient-based distributed algorithms that can be characterized as Lur'e systems, thereby ...
详细信息
ISBN:
(纸本)9798350382662;9798350382655
This paper analyzes distributed optimization algorithms from a frequency-domain perspective. We propose a general class of gradient-based distributed algorithms that can be characterized as Lur'e systems, thereby enabling the analysis and synthesis of algorithms following a robust control approach facilitated by the Zames-Falb criterion. By identifying algorithmic convergence with the absolute stability of a corresponding Lur'e system and decomposing the optimization objective into two canonical control problems, namely tracking and servomechanism, the problem of optimizing convergence rate is recast as a Nevanlinna-Pick interpolation problem. The solutions to such analytic interpolation problems lead to a parameterization of distributed optimization algorithms that achieve specified convergence rates.
This paper captures our experience developing algorithms to solve Combinatorial Problems using different techniques. Because it is a Software Engineering problem, then to find better ways of developing algorithms, sol...
详细信息
ISBN:
(纸本)9783540733447
This paper captures our experience developing algorithms to solve Combinatorial Problems using different techniques. Because it is a Software Engineering problem, then to find better ways of developing algorithms, solvers and metaheuristics is our interest too. Here, we fixed some concepts from Knowledge Management and Software Engineering applied in our work.
作者:
Tao, HuanjieLu, XiaoboSoutheast Univ
Sch Automat Nanjing 210096 Jiangsu Peoples R China Southeast Univ
Key Lab Measurement & Control Complex Syst Engn Minist Educ Nanjing 210096 Jiangsu Peoples R China
Network-based wind speed forecasting has played an important role in the power system. The network parameters optimization is an important issue, and different optimization algorithms are believed to result in differe...
详细信息
ISBN:
(纸本)9789881563958
Network-based wind speed forecasting has played an important role in the power system. The network parameters optimization is an important issue, and different optimization algorithms are believed to result in different forecasting accuracies. In this paper, six network parameters optimization algorithms, including Gradient descent, Momentum, AdaGrad, RMSprop, Adam. and Adadelta, are implemented and compared in the application of wind speed forecasting. As a case study, this paper uses a wind speed data obtained from Ningxia, China. The performance is evaluated by three metrics, namely, mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). The experiment results show that, Adam algorithm and RMSprop algorithm achieve better forecasting accuracy and less training time than the other optimization algorithms. This study can be a guide to the selection of optimization algorithms on wind speed forecasting problems for researchers.
Unlike robots, humans have no problem working hand in hand. However, when robots try to perform tasks that require precision, they always face a major problem: they are not precise enough in combination. This problem ...
详细信息
ISBN:
(纸本)9781510673175;9781510673168
Unlike robots, humans have no problem working hand in hand. However, when robots try to perform tasks that require precision, they always face a major problem: they are not precise enough in combination. This problem is especially relevant when the application requires high precision. One of the main reasons for this is that the robots usually do not know each other's position or have an absolute calibration of the common coordinate system with the required accuracy. We will present our approach to introduce precise alignment procedures in a robotic cell using optically assisted methods. Subsequent analysis of the acquired data by tailored optimization algorithms provide an accurate and absolute coordinate system for a robot ensemble. The accuracy is typically limited by the workspace environment. Mostly acoustic vibrations will define the lower limit of the absolute precision to retrieve a global coordinate system within the working environment. In this work we present an analysis of common limitations as well as an algorithmic procedure to retrieve a global orthonormal basis for the robotic workcell, independent of the number of robots in the ensemble. As an intermediate result of our ongoing research, we can demonstrate a repeatable adjustment accuracy of less than 100 mu m euclidean distance from a common center.
Local search algorithms perform an important role when being employed with optimization algorithms tackling numerous optimization problems since they lead to getting better solutions. However, this is not practical in...
详细信息
Local search algorithms perform an important role when being employed with optimization algorithms tackling numerous optimization problems since they lead to getting better solutions. However, this is not practical in many applications as they do not contribute to the search process. This was not much studied previously for traditional optimization algorithms or for parallel optimization algorithms. This paper investigates this issue for parallel optimization algorithms when tackling high dimensional subset problems. The acquired results show impressive recommendations.
In this paper, a different type of initialization technique called the two stage initialization (TSI) is used for initializing the population vectors of differential evolution (DE) and particle swarm optimization (PSO...
详细信息
ISBN:
(纸本)9781509033645
In this paper, a different type of initialization technique called the two stage initialization (TSI) is used for initializing the population vectors of differential evolution (DE) and particle swarm optimization (PSO). These two stage initialized optimization algorithms are then used to tune the PID controller for a coupled tank liquid level control system. In TSI, the population vector is randomly generated in two stages which would then go through the various phases involved in the algorithms. The PID controller is the most preferred controller in almost all process control industries due to its robustness and dynamic behavior. Hence it has been chosen for controlling the coupled tank liquid level system in this paper. Comparison of the application of four optimization algorithms out of which two are already existing ones and the other two are their TSI versions to PID-coupled tank liquid level system is also done. It can be found that TSI not only helps the existing optimization algorithms to start at a better optima but also to converge at a lesser minimum value of the objective function, which is often desirable.
Nowadays, it is clear that the old mathematical models are incomplete because of the large size of image data set. For this reason, the Deep Learning models introduced in the field of image processing meet this need i...
详细信息
ISBN:
(纸本)9781728129334;9781728129327
Nowadays, it is clear that the old mathematical models are incomplete because of the large size of image data set. For this reason, the Deep Learning models introduced in the field of image processing meet this need in the software field In this study, Convolutional Neural Network (CNN) model from the Deep Learning algorithms and the optimization algorithms used in Deep Learning have been applied to international image data sets. optimization algorithms were applied to both datasets respectively, the results were analyzed and compared The success rate was approximately 96.21% in the Caltech 101 data set, while it was observed to be approximately 10% in the Cifar-100 data set.
This study explores the application of multi-objective optimization algorithms in logistics sensor networks, with a particular focus on real-time tracking in cold chain logistics. Leveraging technologies such as RFID,...
详细信息
ISBN:
(纸本)9798350373301;9798350373295
This study explores the application of multi-objective optimization algorithms in logistics sensor networks, with a particular focus on real-time tracking in cold chain logistics. Leveraging technologies such as RFID, sensor networks, and intelligent computing, the study proposes efficient solutions for inventory management, route optimization, and smart logistics. The proposed HEMO-MRSS algorithm addresses the Vehicle Routing Problem (VRP) to minimize the number of vehicles and increase efficiency. Through a comprehensive literature review, recent advances in wireless sensor networks (WSNs) are examined and their contributions to various domains are highlighted. The methodology section describes the design of logistics systems with sensors and the application of multi-objective optimization algorithms, and presents a detailed model for integrated vehicle routing with time windows. The simulation, performed on a Windows 11 system, evaluates the effectiveness of the proposed algorithms using four evaluation metrics. The results show improved performance under optimized conditions, especially in the mean and optimal values, suggesting the importance of optimization in improving algorithmic efficiency in logistics sensor networks.
Tensor completion is a powerful tool used to estimate or recover missing values in multi-way data. It has seen great success in domains such as product recommendation and healthcare. Tensor completion is most often ac...
详细信息
ISBN:
(纸本)9781467388153
Tensor completion is a powerful tool used to estimate or recover missing values in multi-way data. It has seen great success in domains such as product recommendation and healthcare. Tensor completion is most often accomplished via low-rank sparse tensor factorization, a computationally expensive non-convex optimization problem which has only recently been studied in the context of parallel computing. In this work, we study three optimization algorithms that have been successfully applied to tensor completion: alternating least squares (ALS), stochastic gradient descent (SGD), and coordinate descent (CCD++). We explore opportunities for parallelism on shared-and distributed-memory systems and address challenges such as memory-and operation-efficiency, load balance, cache locality, and communication. Among our advancements are an SGD algorithm which combines stratification with asynchronous communication, an ALS algorithm rich in level-3 BLAS routines, and a communication-efficient CCD++ algorithm. We evaluate our optimizations on a variety of real datasets using a modern supercomputer and demonstrate speedups through 1024 cores. These improvements effectively reduce time-to-solution from hours to seconds on real-world datasets. We show that after our optimizations, ALS is advantageous on parallel systems of small-to-moderate scale, while both ALS and CCD++ will provide the lowest time-to-solution on large-scale distributed systems.
暂无评论