scholarly journals New Method for Optimal Feature Set Reduction

2020 ◽  
Vol 19 (6) ◽  
pp. 1198-1221
Author(s):  
Oleg German ◽  
Sara Nasrh
Keyword(s):  
High Speed ◽  
Optimal Algorithm ◽  
Optimal Solution ◽  
Problem Formulation ◽  
Minimum Size ◽  
Computational Time ◽  
Coverage Problem ◽  
Comparative Review ◽  
Multidimensional Objects ◽  
Optimal Feature

A problem of searching a minimum-size feature set to use in distribution of multidimensional objects in classes, for instance with the help of classifying trees, is considered. It has an important value in developing high speed and accuracy classifying systems. A short comparative review of existing approaches is given. Formally, the problem is formulated as finding a minimum-size (minimum weighted sum) covering set of discriminating 0,1-matrix, which is used to represent capabilities of the features to distinguish between each pair of objects belonging to different classes. There is given a way to build a discriminating 0,1-matrix. On the basis of the common solving principle, called the group resolution principle, the following problems are formulated and solved: finding an exact minimum-size feature set; finding a feature set with minimum total weight among all the minimum-size feature sets (the feature weights may be defined by the known methods, e.g. the RELIEF method and its modifications); finding an optimal feature set with respect to fuzzy data and discriminating matrix elements belonging to diapason [0,1]; finding statistically optimal solution especially in the case of big data. Statistically optimal algorithm makes it possible to restrict computational time by a polynomial of the problem sizes and density of units in discriminating matrix and provides a probability of finding an exact solution close to 1. Thus, the paper suggests a common approach to finding a minimum-size feature set with peculiarities in problem formulation, which differs it from the known approaches. The paper contains a lot of illustrations for clarification aims. Some theoretical statements given in the paper are based on the previously published works. In the concluding part, the results of the experiments are presented, as well as the information on dimensionality reduction for the coverage problem for big datasets. Some promising directions of the outlined approach are noted, including working with incomplete and categorical data, integrating the control model into the data classification system.

scholarly journals PEM-PCA: A Parallel Expectation-Maximization PCA Face Recognition Architecture

2014 ◽  
Vol 2014 ◽  
pp. 1-16 ◽  
Author(s):  
Kanokmon Rujirakul ◽  
Chakchai So-In ◽  
Banchar Arnonkijpanich
Keyword(s):  
Feature Extraction ◽  
Face Recognition ◽  
Expectation Maximization ◽  
High Speed ◽  
Expectation Maximization Algorithm ◽  
Parallel Architecture ◽  
Principal Component ◽  
Eigenvalue Decomposition ◽  
Computational Time ◽  
Recognition Systems

Principal component analysis or PCA has been traditionally used as one of the feature extraction techniques in face recognition systems yielding high accuracy when requiring a small number of features. However, the covariance matrix and eigenvalue decomposition stages cause high computational complexity, especially for a large database. Thus, this research presents an alternative approach utilizing an Expectation-Maximization algorithm to reduce the determinant matrix manipulation resulting in the reduction of the stages’ complexity. To improve the computational time, a novel parallel architecture was employed to utilize the benefits of parallelization of matrix computation during feature extraction and classification stages including parallel preprocessing, and their combinations, so-called a Parallel Expectation-Maximization PCA architecture. Comparing to a traditional PCA and its derivatives, the results indicate lower complexity with an insignificant difference in recognition precision leading to high speed face recognition systems, that is, the speed-up over nine and three times over PCA and Parallel PCA.

scholarly journals Efficient Algorithms for Max-Weighted Point Sweep Coverage on Lines

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1457
Author(s):  
Dieyan Liang ◽  
Hong Shen
Keyword(s):  
Optimal Algorithm ◽  
Approximate Solutions ◽  
Approximation Ratio ◽  
Mobile Sensors ◽  
Np Hard ◽  
Coverage Problem ◽  
Polynomial Time Approximation Algorithm ◽  
Weighted Point ◽  
Eulerian Graph ◽  
Set Of Points

As an important application of wireless sensor networks (WSNs), deployment of mobile sensors to periodically monitor (sweep cover) a set of points of interest (PoIs) arises in various applications, such as environmental monitoring and data collection. For a set of PoIs in an Eulerian graph, the point sweep coverage problem of deploying the fewest sensors to periodically cover a set of PoIs is known to be Non-deterministic Polynomial Hard (NP-hard), even if all sensors have the same velocity. In this paper, we consider the problem of finding the set of PoIs on a line periodically covered by a given set of mobile sensors that has the maximum sum of weight. The problem is first proven NP-hard when sensors are with different velocities in this paper. Optimal and approximate solutions are also presented for sensors with the same and different velocities, respectively. For M sensors and N PoIs, the optimal algorithm for the case when sensors are with the same velocity runs in O(MN) time; our polynomial-time approximation algorithm for the case when sensors have a constant number of velocities achieves approximation ratio 12; for the general case of arbitrary velocities, 12α and 12(1−1/e) approximation algorithms are presented, respectively, where integer α≥2 is the tradeoff factor between time complexity and approximation ratio.

scholarly journals An ANN-GA Framework for Optimal Engine Modeling

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Khaldoun K. Tahboub ◽  
Mahmoud Barghash ◽  
Mazen Arafeh ◽  
Osama Ghazal
Keyword(s):  
High Speed ◽  
Internal Combustion Engines ◽  
Optimization Technique ◽  
Peak Torque ◽  
Computational Time ◽  
Optimal Power ◽  
Power Setting ◽  
Optimal Setting ◽  
Artificial Neural Network Ann ◽  
Variable Valve

Internal combustion engines are a main power source for vehicles. Improving the engine power is important which involved optimizing combustion timing and quantity of fuel. Variable valve timing (VVT) can be used in this respect to increase peak torque and power. In this work Artificial Neural Network (ANN) is used to model the effect of the VVT on the power and genetic algorithm (GA) as an optimization technique to find the optimal power setting. The same proposed technique can be used to improve fuel economy or a balanced combination of both fuel and power. Based on the findings of this work, it was noticed that the VVT setting is more important at high speed. It was also noticed that optimal power can be obtained by changing the VVT settings as a function of speed. Also to reduce computational time in obtaining the optimal VVT setting, an ANN was successfully used to model the optimal setting as a function of speed.

Inductive graph invariants and approximation algorithms

2021 ◽  
Author(s):  
C. R. Subramanian
Keyword(s):  
Optimization Problems ◽  
Independence Number ◽  
Optimal Solution ◽  
Maximum Size ◽  
Chordal Graphs ◽  
Minimum Size ◽  
Optimal Size ◽  
Induced Subgraph ◽  
Special Cases ◽  
Optimal Formula

We introduce and study an inductively defined analogue [Formula: see text] of any increasing graph invariant [Formula: see text]. An invariant [Formula: see text] is increasing if [Formula: see text] whenever [Formula: see text] is an induced subgraph of [Formula: see text]. This inductive analogue simultaneously generalizes and unifies known notions like degeneracy, inductive independence number, etc., into a single generic notion. For any given increasing [Formula: see text], this gets us several new invariants and many of which are also increasing. It is also shown that [Formula: see text] is the minimum (over all orderings) of a value associated with each ordering. We also explore the possibility of computing [Formula: see text] (and a corresponding optimal vertex ordering) and identify some pairs [Formula: see text] for which [Formula: see text] can be computed efficiently for members of [Formula: see text]. In particular, it includes graphs of bounded [Formula: see text] values. Some specific examples (like the class of chordal graphs) have already been studied extensively. We further extend this new notion by (i) allowing vertex weighted graphs, (ii) allowing [Formula: see text] to take values from a totally ordered universe with a minimum and (iii) allowing the consideration of [Formula: see text]-neighborhoods for arbitrary but fixed [Formula: see text]. Such a generalization is employed in designing efficient approximations of some graph optimization problems. Precisely, we obtain efficient algorithms (by generalizing the known algorithm of Ye and Borodin [Y. Ye and A. Borodin, Elimination graphs, ACM Trans. Algorithms 8(2) (2012) 1–23] for special cases) for approximating optimal weighted induced [Formula: see text]-subgraphs and optimal [Formula: see text]-colorings (for hereditary [Formula: see text]’s) within multiplicative factors of (essentially) [Formula: see text] and [Formula: see text] respectively, where [Formula: see text] denotes the inductive analogue (as defined in this work) of optimal size of an unweighted induced [Formula: see text]-subgraph of the input and [Formula: see text] is the minimum size of a forbidden induced subgraph of [Formula: see text]. Our results generalize the previous result on efficiently approximating maximum independent sets and minimum colorings on graphs of bounded inductive independence number to optimal [Formula: see text]-subgraphs and [Formula: see text]-colorings for arbitrary hereditary classes [Formula: see text]. As a corollary, it is also shown that any maximal [Formula: see text]-subgraph approximates an optimal solution within a factor of [Formula: see text] for unweighted graphs, where [Formula: see text] is maximum size of any induced [Formula: see text]-subgraph in any local neighborhood [Formula: see text].

Integrated Optimal Design of Planar Mechanisms Using Fuzzy Theories

1989 ◽  
Author(s):  
A. K. Dhingra ◽  
S. S. Rao
Keyword(s):  
Nonlinear Programming ◽  
High Speed ◽  
Integrated Approach ◽  
Problem Formulation ◽  
Optimization Techniques ◽  
Motion Path ◽  
Programming Formulation ◽  
Planar Mechanisms ◽  
Dynamic Synthesis ◽  
Motion Characteristics

Abstract A new integrated approach to the design of high speed planar mechanisms is presented. The resulting nonlinear programming formulation combines both the kinematic and dynamic synthesis aspects of mechanism design. The multiobjective optimization techniques presented in this work facilitate the design of a linkage to meet several kinematic and dynamic design criteria. The method can be used for motion, path, and function generation problems. The nonlinear programming formulation also permits the imposition of constraints to eliminate solutions which possess undesirable kinematic and motion characteristics. To model the vague and imprecise information in the problem formulation, the tools of fuzzy set theory have been used. A method of solving the resulting fuzzy multiobjective problem using mathematical programming techniques is presented. The outlined procedure is expected to be useful in situations where doubt arises about the exactness of permissible values, degree of credibility, and correctness of statements and judgements.

Fast Filtering of Search Results Sorted by Attribute

2022 ◽  
Vol 40 (2) ◽  
pp. 1-24
Author(s):  
Franco Maria Nardini ◽  
Roberto Trani ◽  
Rossano Venturini
Keyword(s):  
Heuristic Algorithms ◽  
State Of The Art ◽  
Optimal Algorithm ◽  
Computational Cost ◽  
Approximation Error ◽  
Optimal Solution ◽  
Exact Algorithm ◽  
Performance Bounds ◽  
Search Results ◽  
Filtering Problem

Modern search services often provide multiple options to rank the search results, e.g., sort “by relevance”, “by price” or “by discount” in e-commerce. While the traditional rank by relevance effectively places the relevant results in the top positions of the results list, the rank by attribute could place many marginally relevant results in the head of the results list leading to poor user experience. In the past, this issue has been addressed by investigating the relevance-aware filtering problem, which asks to select the subset of results maximizing the relevance of the attribute-sorted list. Recently, an exact algorithm has been proposed to solve this problem optimally. However, the high computational cost of the algorithm makes it impractical for the Web search scenario, which is characterized by huge lists of results and strict time constraints. For this reason, the problem is often solved using efficient yet inaccurate heuristic algorithms. In this article, we first prove the performance bounds of the existing heuristics. We then propose two efficient and effective algorithms to solve the relevance-aware filtering problem. First, we propose OPT-Filtering, a novel exact algorithm that is faster than the existing state-of-the-art optimal algorithm. Second, we propose an approximate and even more efficient algorithm, ϵ-Filtering, which, given an allowed approximation error ϵ, finds a (1-ϵ)–optimal filtering, i.e., the relevance of its solution is at least (1-ϵ) times the optimum. We conduct a comprehensive evaluation of the two proposed algorithms against state-of-the-art competitors on two real-world public datasets. Experimental results show that OPT-Filtering achieves a significant speedup of up to two orders of magnitude with respect to the existing optimal solution, while ϵ-Filtering further improves this result by trading effectiveness for efficiency. In particular, experiments show that ϵ-Filtering can achieve quasi-optimal solutions while being faster than all state-of-the-art competitors in most of the tested configurations.

Heuristic algorithm for optimal redundancy allocation in complex systems

2019 ◽  
Vol 25 (1) ◽  
pp. 54-64 ◽  
Author(s):  
Sudhanshu Aggarwal
Keyword(s):  
Complex Systems ◽  
Heuristic Algorithm ◽  
Communication Systems ◽  
Heuristic Algorithms ◽  
Real Life ◽  
Optimal Solution ◽  
Systems Design ◽  
Computational Time ◽  
Coherent System ◽  
Content Type

PurposeThe purpose of this paper is to present an efficient heuristic algorithm based on the 3-neighborhood approach. In this paper, search is made from sides of both feasible and infeasible regions to find near-optimal solutions.Design/methodology/approachThe algorithm performs a series of selection and exchange operations in 3-neighborhood to see whether this exchange yields still an improved feasible solution or converges to a near-optimal solution in which case the algorithm stops.FindingsThe proposed algorithm has been tested on complex system structures which have been widely used. The results show that this 3-neighborhood approach not only can obtain various known solutions but also is computationally efficient for various complex systems.Research limitations/implicationsIn general, the proposed heuristic is applicable to any coherent system with no restrictions on constraint functions; however, to enforce convergence, inferior solutions might be included only when they are not being too far from the optimum.Practical implicationsIt is observed that the proposed heuristic is reasonably proficient in terms of various measures of performance and computational time.Social implicationsReliability optimization is very important in real life systems such as computer and communication systems, telecommunications, automobile, nuclear, defense systems, etc. It is an important issue prior to real life systems design.Originality/valueThe utilization of 3-neighborhood strategy seems to be encouraging as it efficiently enforces the convergence to a near-optimal solution; indeed, it attains quality solutions in less computational time in comparison to other existing heuristic algorithms.

scholarly journals A Feature Extraction Method of Wheelset-Bearing Fault Based on Wavelet Sparse Representation with Adaptive Local Iterative Filtering

2020 ◽  
Vol 2020 ◽  
pp. 1-20
Author(s):  
Zhan Xing ◽  
Jianhui Lin ◽  
Yan Huang ◽  
Cai Yi
Keyword(s):  
Feature Extraction ◽  
Sparse Representation ◽  
Extraction Method ◽  
High Speed ◽  
Optimal Solution ◽  
Feature Extraction Method ◽  
Bearing Fault ◽  
Fault Features ◽  
Iterative Filtering ◽  
The Impact

The feature extraction of wheelset-bearing fault is important for the safety service of high-speed train. In recent years, sparse representation is gradually applied to the fault diagnosis of wheelset-bearing. However, it is difficult for traditional sparse representation to extract fault features ideally when some strong interference components are imposed on the signal. Therefore, this paper proposes a novel feature extraction method of wheelset-bearing fault based on the wavelet sparse representation with adaptive local iterative filtering. In this method, the adaptive local iterative filtering reduces the impact of interference components effectively and contributes to the extraction of sparse impulses. The wavelet sparse representation, which adopts L1-regularized optimization for a globally optimal solution in sparse coding, extracts intrinsic features of fault in the wavelet domain. To validate the effectiveness of this proposed method, both simulated signals and experimental signals are analyzed. The results show that the fault features of wheelset-bearing are sufficiently extracted by the proposed method.

Long Term Dynamic Simulation of a Stem Cell Nucleus

2020 ◽  
Vol 15 (11) ◽  
Author(s):  
Manoochehr Rabiei ◽  
Andrew McColloch ◽  
Parisa Rabbani ◽  
Michael Cho ◽  
Alan Bowling
Keyword(s):  
Stem Cell ◽  
High Speed ◽  
Multiple Scales ◽  
Adipogenic Differentiation ◽  
Computational Time ◽  
Desktop Computer ◽  
Biological Phenomena ◽  
Time Histories ◽  
Biomolecular Simulations

Abstract Biomolecular simulations are computationally expensive. Simulating time histories larger than seconds remain elusive even with the help of supercomputers. Biological phenomena are multiscale in nature. The dynamics range from atomistic to microscale. Herein a recently developed scaling approach, based on the method of multiple scales (MMS), is used to accomplish a long term simulation of a subcellular system. The first key advantage of this approach is the drastic reduction in computational time. This approach is illustrated using a mesenchymal stem cell (MSC) as it undergoes adipogenic differentiation, a process that takes 15 days, which was simulated in less than 1.5 h on a typical desktop computer. The second key advantage of the high-speed simulation is that it facilitates the study of mechanical properties, such as nucleus membrane stiffness, that are difficult to measure experimentally with certainty.

Sign in / Sign up

Export Citation Format

Share Document