Recently, many studies are carried out on solar energy (SE) and global solar radiation (GSR) estimation. When the literature is examined, there are many GSR estimation models developed with different algorithms in dif...
详细信息
Recently, many studies are carried out on solar energy (SE) and global solar radiation (GSR) estimation. When the literature is examined, there are many GSR estimation models developed with different algorithms in different regions of the world. Although some of these models are seen to perform acceptable all over the world, the performance of some models differs according to their location. The minimax algorithm is a decision-making algorithm that maximizes the winning potential while minimizing the probability of losing. In this study, a new Angstorm model was developed for GSR with minimax algorithm. The most important aspect of this article in terms of originality is that the GSR estimation model is being developed with the minimax algorithm for the first time. The MATLAB program was used while developing the prediction model with the minimax algorithm. Different statistical error tests were used to evaluate the performance of the results. When these test results are evaluated in general, it is seen that the minimax algorithm gives acceptable results in GSR estimation.
In this work we aim to solve a convex-concave saddle point problem, where the convex-concave coupling function is smooth in one variable and nonsmooth in the other and not assumed to be linear in either. The problem i...
详细信息
In this work we aim to solve a convex-concave saddle point problem, where the convex-concave coupling function is smooth in one variable and nonsmooth in the other and not assumed to be linear in either. The problem is augmented by a nonsmooth regulariser in the smooth component. We propose and investigate a novel algorithm under the name of OGAProx, consisting of an optimistic gradient ascent step in the smooth variable coupled with a proximal step of the regulariser, and which is alternated with a proximal step in the nonsmooth component of the coupling function. We consider the situations convex-concave, convex-strongly concave and strongly convex-strongly concave related to the saddle point problem under investigation. Regarding iterates we obtain (weak) convergence, a convergence rate of order O(1/K) and linear convergence like O(theta(K)) with theta < 1, respectively. In terms of function values we obtain ergodic convergence rates of order O(1/K), O(1/K-2) and O(theta(K)) with theta < 1, respectively. We validate our theoretical considerations on a nonsmooth-linear saddle point problem, the training of multi kernel support vector machines and a classification problem incorporating minimax group fairness.
Global active noise control (ANC) employs multichannel filtered-x least mean square (MCFxLMS) algorithm as it is more suitable algorithm to obtain large quiet zone. minimax algorithm was proposed to counter the higher...
详细信息
ISBN:
(纸本)9781665426398
Global active noise control (ANC) employs multichannel filtered-x least mean square (MCFxLMS) algorithm as it is more suitable algorithm to obtain large quiet zone. minimax algorithm was proposed to counter the higher computational complexity faced in MCFxLMS based ANC by minimizing the square of the maximum of the absolute values of residual noise at the error microphones. However, the minimax approach leads to inferior performance in terms of convergence as well as noise reduction. Also, the classical minimax approach offers little flexibility in adjusting the ANC performance. In this paper, a novel minimax algorithm is proposed in order to tackle these shortcomings of conventional minimax algorithm at a cost of increase in computational complexity as compared to conventional minimax algorithm. The performance of the proposed approach is evaluated and compared with classical minimax for global noise reduction in a 2-dimensional quiet zone of size 1 m x 1 m in a 3-dimensional reverberant room. The proposed scheme is able to improve the performance with much reduced computational complexity as compared to MCFxLMS though with increased computational complexity as compared to classical minimax approach.
Parameter learning is an important aspect of learning in Bayesian networks. Although the maximum likelihood algorithm is often effective, it suffers from overfitting when there is insufficient data. To address this, p...
详细信息
Parameter learning is an important aspect of learning in Bayesian networks. Although the maximum likelihood algorithm is often effective, it suffers from overfitting when there is insufficient data. To address this, prior distributions of model parameters are often imposed. When training a Bayesian network, the parameters of the network are optimized to fit the data. However, imposing prior distributions can reduce the fitness between parameters and data. Therefore, a trade-off is needed between fitting and overfitting. In this study, a new algorithm, named minimax Fitness (MMF) is developed to address this problem. The method includes three main steps. First, the maximum a posterior estimation that combines data and prior distribution is derived. Then, the hyper-parameters of the prior distribution are optimized to minimize the fitness between posterior estimation and data. Finally, the order of posterior estimation is checked and adjusted to match the order of the statistical counts from the data. In addition, we introduce an improved constrained maximum entropy method, named Prior Free Constrained Maximum Entropy (PF-CME), to facilitate parameter learning when domain knowledge is provided. Experiments show that the proposed methods outperforms most of existing parameter learning methods. (C) 2019 Elsevier Inc. All rights reserved.
This paper presents the design and development of Dismath, a gamified educational tool for propositional logic introduction to undergraduate computer engineering students. Additionally, an artificial intelligence (AI)...
详细信息
ISBN:
(纸本)9781728130446
This paper presents the design and development of Dismath, a gamified educational tool for propositional logic introduction to undergraduate computer engineering students. Additionally, an artificial intelligence (AI) agent is developed for the proposed Dismath game based on minimax tree search with alpha-beta pruning (MMAB). Dismath is an international checker variant inspired by Damath game in which operations are defined in every checkerboard positions. Thus, the final score is not only dependent on the pieces left but also in the operation results. In a capture move, the jumping chip is the first operand, the captured piece acts as the second operand, and the operation defined in the destination block where the chip landed after the jump is utilized for the binary operation. Instead of arithmetic operators, Dismath designates logical connectives on the checkerboard. All white and black pieces were assigned true and false truth values. For scoring, a true (T) and a false (F) truth values are calculated as +1 and -1, while a dama or king chip is valued +2 and -2 for White and Black pieces, respectively. If the game ends with a positive value, then white wins;otherwise black wins, unless the score is zero in which the outcome is draw. Board balancing experiments were conducted using the win-win ratio between the two random players as evaluation metric. Furthermore, the MMAB agent was characterized against a random player baseline. The results showed dominant performance of MMAB AI agent in proposed Dismath game losing only at depth equal to 1. Overall, this result is promising on its own demonstrating the automated gameplay of the proposed Dismath educational tool for logic introduction.
Choosing the right algorithm for Intelligent Agent is very important in determining the next step. Actions taken by an Intelligent Agent with less optimum algorithm can be figured out easily by the player competing wi...
详细信息
ISBN:
(纸本)9781728147147
Choosing the right algorithm for Intelligent Agent is very important in determining the next step. Actions taken by an Intelligent Agent with less optimum algorithm can be figured out easily by the player competing with it. This certainly makes it easier for the player to win the game. Card Battle is a game that compares the strength of both card decks. They competed to determine who has the best cards on deck to reduce the enemy health point. Intelligent Agent need to act as the competing enemy called Non-Player Character (NPC). Presently, Intelligent Agent on Card Battle Games still use the minimax algorithm. This algorithm thinks only to counter enemy summoned card without considering other things such as enemy health point left, the cost for summoning a card, etc. Improvisation of minimax algorithm with Multi Criteria Decision Maker (MCDM) provides a new way of thinking for the decision making during the game. The results of this study increase the difficulty of the NPC by making it possible for the Intelligent Agent to consider more game properties and counter the player cards.
In the implementation of a multi-channel feedforward active noise control (ANC) system, the standard FxLMS algorithm demands too much computational power to be real-time processed by a low-cost digital processor. Ther...
详细信息
ISBN:
(纸本)9781538681510
In the implementation of a multi-channel feedforward active noise control (ANC) system, the standard FxLMS algorithm demands too much computational power to be real-time processed by a low-cost digital processor. Therefore, various algorithms have been proposed to reduce their computational complexity by modifying the cost function and introducing the partial update (P-U). This paper proposes a new P-U minimax algorithm, which minimizes the uniform-norm instead of the 2-norm of the error signals and updates the filtered reference signals partially. The P-U minimax algorithm is compared with existing algorithms based on an experimental setup of a case (1, 4, 8) ANC system. The proposed P-U minimax algorithm is validated to be efficient and outperform the scanning error and mixed-error algorithms with the same degree of computational complexity.
Random minimaxing studies the consequences of using a random number for scoring the leaf nodes of a full width game tree and then computing the best move using the standard minimax procedure. Experiments in Chess show...
详细信息
Random minimaxing studies the consequences of using a random number for scoring the leaf nodes of a full width game tree and then computing the best move using the standard minimax procedure. Experiments in Chess showed that the strength of play increases as the depth of the lookahead is increased. Previous research by the authors provided a partial explanation of why random minimaxing can strengthen play by showing that, when one move dominates another move, then the dominating move is more likely to be chosen by minimax. This paper examines a special case of determining the move probability when domination does not occur. Specifically, we show that, under a uniform branching game tree model, whether the probability that one move is chosen rather than another depends not only on the branching factors of the moves involved, but also on whether the number of ply searched is odd or even. This is a new type of game tree pathology, where the minimax procedure will change its mind as to which move is best, independently of the true value of the game, and oscillate between moves as the depth of lookahead alternates between odd and even.
Vector signal analysis requires digital down-conversion, low-pass filtering, matching filtering, timing synchronization, carrier synchronization, equalization and other modules. Timing synchronization is the key to ve...
详细信息
ISBN:
(纸本)9798350300284
Vector signal analysis requires digital down-conversion, low-pass filtering, matching filtering, timing synchronization, carrier synchronization, equalization and other modules. Timing synchronization is the key to vector signal analysis. Traditional timing synchronization, such as Gardner feedback algorithm, has self-noise. The method to reduce self-noise is to design a pre-filter for a specific roll down coefficient before timing synchronization. However, these methods need to redesign the pre-filter coefficient when the roll down coefficient changes, so the signal roll down coefficient can't meet the test requirements when the signal roll down coefficient changes in a wide range. Therefore, this paper proposes a timing synchronization algorithm based on Farrow structure FIR pre-filter. The sub-filter coefficients of Farrow structure of pre-filter are solved offline by minimax algorithm. Pre-filter redesign can be avoided according to different roll down coefficients. The proposed pre-filtering algorithm can be used in vector signal analysis modules with roll down coefficients ranging from 0.1 to 1 and symbol rates ranging from 1kBaud to 8GBaud. The experimental results show that the modulated signal can be demodulated successfully in the range of 0.1-1 roll down coefficient, and the timing jitter can be reduced by 2-3 orders of magnitude when the signal-to-noise ratio(SNR) is greater than 20dB.
In this letter, we present a method to design an elevation beam pattern mask for spaceborne synthetic aperture radar (SAR) to reduce the range ambiguity. The proposed two-way elevation beam pattern mask, which require...
详细信息
In this letter, we present a method to design an elevation beam pattern mask for spaceborne synthetic aperture radar (SAR) to reduce the range ambiguity. The proposed two-way elevation beam pattern mask, which requires relatively low sidelobe levels only in the direction of strong range ambiguous echoes, can be highly suitable for enhancing the range ambiguity to signal ratio (RASR). The power levels of the different ambiguous echoes are estimated based on the backscattering coefficient model and satellite geometry. To meet the two-way beam pattern mask, both transmit and receive beam patterns are synthesized simultaneously through the minimax algorithm. To confirm the effectiveness of this mask design method, the RASR performance is evaluated by using various swaths.
暂无评论