Gravitational search algorithm–optimized neural misuse detector with selected features by fuzzy grids–based association rules mining

Feature selection is one of the most important techniques for data preprocessing in classification problems. In this paper, fuzzy grids–based association rules mining, as an effective data mining technique, is used for feature selection in misuse detection application in computer networks. The main idea of this algorithm is to find the relationships between items in large datasets so that it detects correlations between inputs of the system and then eliminates the redundant inputs. To classify the attacks, a fuzzy ARTMAP neural network is employed whose training parameters are optimized by gravitational search algorithm. The performance of the proposed system is compared with some other machine learning methods in the same application. Experimental results show that the proposed system, when choosing optimum “feature subset size-adjustment” parameter, performs better in terms of detection rate, false alarm rate, and cost per example in classification problems. In addition, employing the reduced-size feature set results in more than 8.4 percent reduction in computational complexity.     

An intelligent hybrid meta-heuristic for solving a case of no-wait two-stage flexible flow shop scheduling problem with unrelated parallel machines

This paper addresses the problem of no-wait two-stage flexible flow shop scheduling problem (NWTSFFSSP) considering unrelated parallel machines, sequence-dependent setup times, probable reworks and different ready times to actualize the problem. The performance measure used in this study is minimizing maximum completion time (makespan). Because of the complexity of addressed problem, we propose a novel intelligent hybrid algorithm [called hybrid algorithm (HA)] based on imperialist competitive algorithm (ICA) which are combined with simulated annealing (SA), variable neighborhood search (VNS) and genetic algorithm (GA) for solving the mentioned problem. The hybridization is carried out to overcome some existing drawbacks of each of these three algorithms and also for increasing the capability of ICA. To achieve reliable results, Taguchi approach is used to define robust parameters' values for our proposed algorithm. A simulation model is developed to study the performance of our proposed algorithm against ICA, SA, VNS, GA and ant colony optimization (ACO). The results of the study reveal the relative superiority of HA studied. In addition, potential areas for further researches are highlighted.     

Explicit rate allocation algorithm of generalised max-min fairnessfor ATM ABR services

A distributed explicit rate allocation algorithm based on the generalised max-min (GMM) fairness principle is proposed for the available bit rate (ABR) ATM services. Compared with a similar algorithm for GMM, it employs fewer fields in an RM cell and imposes lower requirements on the computational capability of the switches     

Production of Al–20 wt.% Al2O3 composite powder using high energy milling

High energy ball milling was used to produce a nanostructured Al matrix composite reinforced by submicron α-alumina particles. Scanning electron microscopy analysis as well as tap and green density measurements were used to optimize the milling time needed for the completion of the mechanical milling process. Results show that addition of alumina particles as the reinforcement has a drastic effect on the size, morphology and pressability of the powder. Scanning electron microscopy shows that distribution of alumina particles in the Al matrix reaches a full homogeneity after steady state. This would increase the hardness of powder due to a nano-structured matrix and oxide dispersion strengthening.     

Adaptive time-delay controller

A time-delay controller is proposed in this letter. This controller possesses attractive properties, such as requiring only one tuning parameter. Furthermore, it can be applied to higher order systems as well as systems with dominant delay. The basic structure is integrated with an online estimation algorithm to form an adaptive time-delay controller. An experimental study is included to demonstrate its performance and merits compared with two similar controllers.     

Performance Comparison of Automated Vehicle Controllers

１IntroductionAutomatedhighwaysystems穴AHS雪havedrawnmoreandmoreattentioninrecentyearsbecausefullautomationcangreatlyincreasehighwaycapacitywhileimprovingsafety．IneachplatoonofAHS熏everyvehicle穴excepttheleadingcar雪tightlyfollowstheprecedingvehicle熏andcanreactquicklytotheprecedingcarandemergency．Thedesignofintelligentvehiclecontrolsystemisanim鄄portantpartofAHS熏anditinvolvesautomaticcontrolofthrottleandbrake眼１演．Oneoftheobjectivesofintelligentvehiclecontrolistoachieveautomaticvehic…     

Wavelet‐Based Method for Generating Nonstationary Artificial Pulse‐Like Near‐Fault Ground Motions

A method to generate a suite of artificial near‐fault ground motion time histories for specified earthquakes is presented. A wavelet‐based nonstationary (WB‐NS) model has been employed to effectively capture the time‐varying frequency content of a particular acceleration record and continuous wavelet transform has been used to simulate the largest velocity pulse. Furthermore, an iterative procedure using discrete wavelet transform is utilized to modify an earthquake ground motion and generate energy‐compatible ground motion. Eventually, the artificial near‐fault accelerogram is achieved via the superposition of a coherent extracted velocity pulse with a random acceleration record corresponding to a WB‐NS model and multiplied by a time‐modulating envelope function. The effectiveness of the method is demonstrated by comparing the spectral response and Arias intensity curves of the simulated accelerograms with those of the real records.     

3D experimental and numerical analysis of wind flow around domed-roof buildings with open and closed apertures

This paper presents experimental and numerical study of airflow distribution around a reduced-scale model of a common type of domed-roof building. Measurements are performed in an open loop wind tunnel. A new modified Counihan scheme is developed for constructing a part-depth atmospheric boundary layer (ABL). Measured quantities include: wind velocity profile, turbulence intensity and airflow pattern around the building. To conduct the experiments, a 1:54 scale model of a real domed-roof building with six windows and an aperture on the roof is fabricated and placed in the test section of the wind tunnel. In addition, using a numerical modeling, turbulent airflow around such scale model in the wind tunnel is simulated and airflow field inside and outside the model as well as ventilating discharge coefficient are computed. It is illustrated that, airflow around this type of building contains complex adjacent recirculation flows. The building with open apertures has acceptable discharge coefficient for ventilation, which can be a factor to ensure comfort condition for residents as well as complying with energy-saving considerations.