Edward J. Kelly · IEEE Transactions on Aerospace and Electronic Systems · 1986
A general problem of signal detection in a background of unknown Gaussian noise is addressed, using the techniques of statistical hypothesis testing. Signal presence is sought in one data vector, and another independent set of signal-free data vectors is available which share the unknown covariance matrix of the noise in the former vector. A likelihood ratio decision rule is derived and its performance evaluated in both the noise-only and signal-plus-noise cases.
Cited by 1,516
Denis Pavliha (440915), Maja M. Mušič (440916), Gregor Serša (4743132) et al. · Figshare · 2015
<p>Demonstrated is the functioning of the algorithm comparing a slice while sweeping the intensity threshold value; presented are three examples where the intensity threshold value is set to 15.000 bits and similarity is 0.12 (A), 25.000 bits and similarity is 0.81 (B) and 35.000 bits and similarity is 0.95 (C); the comparison is done to the previous already-segmented slice (D).</p>
Cited by 0Open access
Sadiya Thazeen, S Mallikarjunaswamy, Mohamed Najmus Saqhib · 2022 International Conference on Smart Information Systems and Technologies (SIST) · 2022
With rapid advancement in technology, human kind has been able to come through wired landlines to handheld smart phone devices in just a few years of time. This is possible because of the digital signal processing (DSP). In wireless communications, with multiple access methods and high performing algorithms which DSP module makes use of, the machinery at the base station gets boosted up. This increases capacity of the RF spectrum which is well known to be a limited resource. The Quality of Service (QoS) also gets better with lesser interference and mean square error. The paper presents one such algorithm for the DSP block of the smart antenna system. The proposed algorithm called Septennial Adaptive Beamforming Algorithm (SABA), having seven functioning modules or blocks in it, reduces the interference and lowers the mean square error with increase in converging speed at lesser number of iterations.
Cited by 22
Heikki Haario, Eero Saksman, Johanna Tamminen · Bernoulli · 2001
A proper choice of a proposal distribution for Markov chain Monte Carlo methods, for example for the Metropolis-Hastings algorithm, is well known to be a crucial factor for the convergence of the algorithm. In this paper we introduce an adaptive Metropolis (AM) algorithm, where the Gaussian proposal distribution is updated along the process using the full information cumulated so far. Due to the adaptive nature of the process, the AM algorithm is non-Markovian, but we establish here that it has the correct ergodic properties. We also include the results of our numerical tests, which indicate that the AM algorithm competes well with traditional Metropolis-Hastings algorithms, and demonstrate that the AM algorithm is easy to use in practical computation.
Cited by 2,661
SONG Xin, WANG Jin-kuan, LIU Fu-lai et al. · SHILAP Revista de lepidopterología · 2009
The performance of least mean squares（LMS） algorithm degraded dramatically in the presence of even slight steering vector mismatches.In order to overcome the shortage,a novel robust adaptive beamforming algorithm based on the variable diagonal loading technique was proposed.The signal steering vector was obtained via the gradient-descent method and the diagonal loading term was incorporated at each recursive step.Then,the optimal weight vector was de-rived.To account for the contradiction of convergence rate and steady errors,a function between the step size and input signals was built to obtain the variable step size.The proposed algorithm had a low complexity cost without the inverse matrix and eigendecomposition.The proposed algorithm offered faster convergence rate,provided a sufficient robustness against the mismatches and made the mean output array SINR consistently close to the optimal one.The theoretical analysis and simulation results demonstrate that the performance of the proposed algorithm can outperform that of the conventional algorithm.
Cited by 1Open access
Fernandez Mira, Alonso · QRU Quaderns de Recerca en Urbanisme · 2024
In recent years there has been a surging requirement for precise and effective indoor localization measurements due to the emergence of innovative technologies such as the Internet of Things (IoT) [1] and smart home devices. Traditional localization technologies like GPS have been proven not to be precise in indoor environments. A new approach based on WiFi RTT (Round Trip Time) called FTM protocol (Fine Time Measurement) has gained popularity over the last years due to its low-cost implementation and wide distribution especially indoors. Accuracy issues within FTM have been pointed out by studies. In an environment where the signal bounces into walls and buildings, the signal is received through different paths. As the sampling interval of the radios is below the delay between the different paths, the receiver often sees a mixture of the signals over different paths. Therefore, it is not possible to distinguish the direct path (if it exists) from the reflected signals. The receiver measures a mixture of different signals with different amplitudes, phases, and probably also different frequencies. Recent studies analyzed the increase in accuracy by choosing different burst sizes and multiple positions. As expected, increasing the number of bursts in an FTM frame leads to a reduction in the error. However, this comes at the cost of consuming more channel time. The increase in accuracy is not directly proportional to the amount of channel time required to perform it. This thesis' objective will be to develop an algorithm capable of dynamically adapting its parameters to ensure, simultaneously, channel time optimization and precision in real-case scenarios.
Cited by 0Open access
Richard M. Golden · 2020
Cited by 1
Ville Vainioranta · Osuva (University of Vaasa) · 2013
Differential Evolution is an evolutionary algorithm designed for global optimization. Its main assets are simplicity, ease of use, and effectiveness, which has been demonstrated in different research papers and evolution computation competitions. Differential Evolution has three control parameters and each of them has a significant impact on the performance of the algorithm. \n \nThis paper introduces three modified algorithms which adapt the control parameters during the optimization process. The first modification VDE-1 adapts the mutation factor, the second modification VDE-2 adapts the crossover factor and the third modification adapts both factors. The idea in these modified algorithms is to use previously successful factor parameter values and calculate an exponential moving average value of these parameter values. This average value is then utilized to generate new control parameter values. In addition, the modifications apply Daniela Zaharie’s theory on population diversity in Differential evolution and on how control parameters affect the convergence properties. \n \nThe performances of the modified algorithms are compared with the original algorithm version with results on a benchmark of 25 functions provided by the “IEEE Congress on Evolutionary Computation 2005” evolution computation contest. The 25 functions are run on two different dimensions, and the results are gathered from all algorithms. The results are then analyzed and compared with each other. The main focus in the analysis is on the behavior of the control parameters for the modified algorithms.\n \nThe experimental results indicate that the modified algorithms are promisingly more effective and efficient when compared to the original Differential Evolution. Especially the convergence speeds of VDE-1 and VDE-3 are much faster compared to the original algorithm. The differences in performance are remarkably high for certain functions.
Cited by 0Open access
Zhang, Jincheng · Zenodo (CERN European Organization for Nuclear Research) · 2025
This paper proposes a Gecko Adaptive Exploration Algorithm (GAEA) inspired by the behavioral characteristics of geckos. Geckos, with their unique attachment structure, acute perception, and tail-based escape mechanism, demonstrate exceptional adaptability in nature. GAEA leverages these characteristics by incorporating a multi-layered attachment perception mechanism, a tail energy release perturbation mechanism, a dynamic attachment step size, and a collaborative predation mechanism to achieve an efficient balance between global and local search. This paper provides a comprehensive mathematical model and formula derivation for GAEA, providing a solid theoretical foundation for subsequent optimization research.
Cited by 0Open access
2013
decision processes using pattern-matrix learning method This note is concerned with adaptive algorithm for uncertain Markov decision processes(MDPs) with the average reward criterion. As a sequel to [2], we consider the learning algorithm for investigating the structure of unknown transition matrices and getting adaptive policy in regularly communicating model where the state space is decomposed into a single communicating class and a transient class. Using pattern matrix learning method, we have an asymptotic sequence of adaptive policies with nearly average optimal properties. Key words: adaptive Markov decision processes, pattern-matrix learning algorithm, averageoptimal adaptive policy, regularly communicating case. 1. Notation Consider a controlled dynamic system with finite state space S = {1, 2,...,N}, containing N &lt; ∞ elements. For each i ∈ S, the finite set A(i) denotes the set of available actions at state i. Let Q denote the parameter space of unknown transition matrices, i.e., (1) Q = {q = (qij(a))|qij(a) = 0, ∑
Cited by 0
Marek Cornu, Tristan Cazenave, Daniel Vanderpooten · 2015
Dealing with multi-objective combinatorial optimization and local search, this article proposes a new multi-objective meta-heuristic named Pareto Adaptive Decomposition algorithm (PAD). Combining ideas from decomposition methods, two phase algorithms and multi-armed bandit, PAD provides a 2-phase modular framework for finding an approximation of the Pareto front. The first phase decomposes the search into a number of scalarized problems by linear aggregation of the original multi-objective problem. Following a data perturbation step, the second phase conducts an iterative process: a number of scalarized problems are selected by a multi-armed bandit policy and optimized by a single-objective local search solver. Resulting solutions will serve as a starting point of a multiobjective local search procedure, called Pareto Local Search. Based on this framework, we conduct experiments on several instances of the bi-objective symmetric Traveling Salesman Problem. The experiments show that our proposed algorithm outperforms the best current method on this problem.
Cited by 0
Ibidun Christiana Obagbuwa, Ademola P. Abidoye · AIP conference proceedings · 2017
An adaptive cockroach swarm optimization (ACSO) algorithm is proposed in this paper to strengthen the existing cockroach swarm optimization (CSO) algorithm. The ruthless component of CSO algorithm is modified by the employment of blend crossover predator-prey evolution method which helps algorithm prevent any possible population collapse, maintain population diversity and create adaptive search in each iteration. The performance of the proposed algorithm on 16 global optimization benchmark function problems was evaluated and compared with the existing CSO, cuckoo search, differential evolution, particle swarm optimization and artificial bee colony algorithms.
Cited by 2
Abaoubida, Sarra, Bédard, Mylène, Maire, Florian · ArXiv.org · 2025
The Pseudo-Marginal (PM) algorithm is a popular Markov chain Monte Carlo (MCMC) method used to sample from a target distribution when its density is inaccessible, but can be estimated with a non-negative unbiased estimator. Its performance depends on a key parameter, N, the number of iterations (or particles) used to approximate the target density. Larger values of N yield more accurate estimates but at increased running time. Previous studies has provided guidelines for selecting an optimal value of N to balance this tradeoff. However, this approach involves multiple steps and manual adjustments. To overcome these limitations, we introduce an adaptive version of the PM algorithm, where N is automatically adjusted during the iterative process toward its optimal value, thus eliminating the need for manual intervention. This algorithm ensures convergence under certain conditions. On two examples, including a real data problem on pulmonary infection in preschool children, the proposed algorithm compares favorably to the existing approach.
Cited by 0Open access
Jia Liu (41593), Wang Yinchai (14247870), Teh Chee Siong (14247873) et al. · Figshare · 2022
Cited by 0Open access
B. Caron, G. Balik, L. Brunetti et al. · 2011
Least-squares algorithm Optical feedback Parameter optimization Noise control Vibration measurement This paper proposes a new approach for beam stabilization of the future Compact LInear Collider (CLIC). The method attempts to increase the efficiency of traditional methods. It is composed of a hybrid adaptive filtering algorithm that uses both feedback and adaptive control. The scheme uses an estimate of the prediction error to update the adaptive filter&apos;s parameters. The strategy of this method is described considering the process environment. The method efficiency is evaluated, and it is demonstrated that it provides high damping, fast vibration suppression, good robustness and easy realization thanks to the simplicity of the computations. 1
Cited by 0
Based On Umda, Mitra Hashemi, Mohammad Reza Meybodi · 2016
UMDA algorithm is a type of Estimation of Distribution Algorithms. This algorithm has better performance compared to others such as genetic algorithm in terms of speed, memory consumption and accuracy of solutions. It can explore unknown parts of search space well. It uses a probability vector and individuals of the population are created through the sampling. Furthermore, EO algorithm is suitable for local search of near global best solution in search space, and it does not stuck in local optimum. Hence, combining these two algorithms is able to create interaction between two fundamental concepts in evolutionary algorithms, exploration and exploitation, and achieve better results of this paper is used adaptive version of -EO algorithm called EO-LA. In this method the task of choosing a replacement component is assigned to Learning Automata. During the implementation of this algorithm, according to the suitability of produced solutions, feedback signals are sent to Learning Automata until adapt selected replacement component well. In this paper, results represent the better performance of the proposed algorithm (combination of three methods) on a Graph Bi-partitioning, NP-hard problem.
Cited by 0
A. Segalen, G. Demoment · Electronics Letters · 1982
A new least-mean-squares (LMS) adaptive algorithm is developed in the letter. This new algorithm solves a specific variance problem that occurs in LMS algorithms in the presence of high noise levels and when the input signal is bandlimited. Quantitative results in terms of an accuracy measure of a finite impulse response (FIR) system identification are presented.
Cited by 14
Alexander D. Poularikas · 2018
Cited by 6
Tep Sastri · IIE Transactions · 1988
Abstract An adaptive approach for sequential parameter-change detection and revision of the moving average parameter in the first-order integrated-moving average time series model is presented. Derivation of recursive formulas based on least squares estimation theory is given. Simulation experiments of this study indicate its validity for on-line parameter tracking applications. Practical considerations in implementing the proposed adaptive estimation system and its extensions to higher-order models are discussed. Notes Handled by the Applied Probability: Statistics Department.
Cited by 9
Yvon Maday, Olga Mula · arXiv (Cornell University) · 2019
In this paper, we consider the problem of accelerating the numerical simulation of time dependent problems by time domain decomposition. The available algorithms enabling such decompositions present severe efficiency limitations and are an obstacle for the solution of large scale and high dimensional problems. Our main contribution is the improvement of the parallel efficiency of the parareal in time method. The parareal method is based on combining predictions made by a numerically inexpensive solver (with coarse physics and/or coarse resolution) with corrections coming from an expensive solver (with high-fidelity physics and high resolution). At convergence, the algorithm provides a solution that has the fine solver's high-fidelity physics and high resolution. In the classical version, the fine solver has a fixed high accuracy which is the major obstacle to achieve a competitive parallel efficiency. In this paper, we develop an adaptive variant that overcomes this obstacle by dynamically increasing the accuracy of the fine solver across the parareal iterations. We theoretically show that the parallel efficiency becomes very competitive in the ideal case where the cost of the coarse solver is small, thus proving that the only remaining factors impeding full scalability become the cost of the coarse solver and communication time. The developed theory has also the merit of setting a general framework to understand the success of several extensions of parareal based on iteratively improving the quality of the fine solver and re-using information from previous parareal steps. We illustrate the actual performance of the method in stiff ODEs, which are a challenging family of problems since the only mechanism for adaptivity is time and efficiency is affected by the cost of the coarse solver.
Cited by 0Open access