Current Issue : January - March Volume : 2020 Issue Number : 1 Articles : 5 Articles
In the Forex market, the price of the currencies increases and decreases rapidly based on many economic and political factors such\nas commercial balance, the growth index, the inflation rate, and the employment indicators. Having a good strategy to buy and\nsell can make a profit from the above changes. A successful strategy in Forex should take into consideration the relation between\nbenefits and risks. In this work, we propose an intra week foreign exchange speculation strategy for currency markets based on a\ncombination of technical indicators. This system has a two-level decision and is composed of the Probit regression model and rules\ndiscovery using Random Forest. There are two minimum requirements for a trading strategy: a rule to enter the market and a rule to\nexit it. Our proposed system, to enter the currency market, should validate two conditions. First, it should validate Random Forest\naccess rules over the following week while in the second one the predicted value of the next day using Probit should be positive.\nTo exit the currency market just one negative warning from Probit or Random Forest is enough. This system was used to develop\ndynamic portfolio trading systems. The profitability of the model was examined for USD/(EUR, JYN, BRP) variation within the\nperiod from January 2014 to January 2016. The proposed system allows improving the prediction accuracy. This indicates a good\nprediction of the behavior market and it helps to identify the good times to enter it or to leave it....
In order to solve the problem of interference and spectrum optimization caused by D2D\n(device-to-device) communication multiplexing uplink channel of heterogeneous cellular networks,\nthe allocation algorithm based on the many-to-one Gale-Shapley (M21GS) algorithm proposed in\nthis paper can effectively solve the resource allocation problem of D2D users multiplexed cellular\nuser channels in heterogeneous cellular network environments. In order to improve the utilization\nof the wireless spectrum, the algorithm allows multiple D2D users to share the channel resources of\none cellular user and maintains the communication service quality of the cellular users and D2D\nusers by setting the signal to interference and noise ratio (SINR) threshold. A D2D user and channel\npreference list are established based on the implemented systemâ??s capacity to maximize the system\ntotal capacity objective function. Finally, we use the Kuhnâ??Munkres (KM) algorithm to achieve the\noptimal matching between D2D clusters and cellular channel to maximize the total capacity of D2D\nusers. The MATLAB simulation is used to compare and analyze the total system capacity of the\nproposed algorithm, the resource allocation algorithm based on the delay acceptance algorithm, the\nrandom resource allocation algorithm and the optimal exhaustive search algorithm, and the\nmaximum allowable access for D2D users. The simulation results show that the proposed algorithm\nhas fast convergence and low complexity, and the total capacity is close to the optimal algorithm....
The Eclat algorithm is a typical frequent pattern mining algorithm using vertical data.\nThis study proposes an improved Eclat algorithm called ETPAM, based on the tissue-like P system\nwith active membranes. The active membranes are used to run evolution rules, i.e., object rewriting\nrules, in parallel. Moreover, ETPAM utilizes subsume indices and an early pruning strategy to\nreduce the number of frequent pattern candidates and subsumes. The time complexity of ETPAM is\ndecreased from O(t^2) to O(t) as compared with the original Eclat algorithm through the parallelism\nof the P system. The experimental results using two databases indicate that ETPAM performs very\nwell in mining frequent patterns, and the experimental results using four databases prove that\nETPAM is computationally very efficient as compared with three other existing frequent pattern\nmining algorithms....
Swarming small unmanned aerial or ground vehicles (UAVs or UGVs) have attracted the attention of worldwide military powers\nas weapons, and the weapon-target assignment (WTA) problem is extremely significant for swarming combat. The problem\ninvolves assigning weapons to targets in a decentralized manner such that the total damage effect of targets is maximized while\nconsidering the nonlinear cumulative damage effect. Two improved optimization algorithms are presented in the study. One is the\nredesigned auction-based algorithm in which the bidding rules are properly modified such that the auction-based algorithm is\napplied for the first time to solve a nonlinear WTA problem. The other one is the improved task swap algorithm that eliminates the\nrestriction in which the weights of the edges on graph G must be positive. Computational results for up to 120 weapons and 110\ntargets indicate that the redesigned auction-based algorithm yields an average improvement of 37% over the conventional\nauction-based algorithm in terms of solution quality while the additional running time is negligible. The improved task swap\nalgorithm and the other two popular task swap algorithms almost achieve the same optimal value, while the average time-savings\nof the proposed algorithm correspond to 53% and 74% when compared to the other two popular task swap algorithms. Furthermore,\nthe hybrid algorithm that combines the above two improved algorithms is examined. Simulations indicate that the\nhybrid algorithm exhibits superiority in terms of solution quality and time consumption over separately implementing the\naforementioned two improved algorithms....
Nowadays, when people want to predict the result of a football match, most\nof them just refer to their own experience or some specialistsâ?? opinions.\nHowever, since artificial intelligence is very good at analyzing big data, it is\nmore and more used to predict the result instead of oneâ??s experience in order\nto approach the accuracy. There are three typical algorithms---convolutional\nneural network (ANN), random forest (RF) and support vector machine\n(SVM). In this paper, these three algorithms are all applied to predict the result\nof a football match, and the accuracy of them is also compared....
Loading....