Current Issue : April - June Volume : 2018 Issue Number : 2 Articles : 5 Articles
This paper gives a modified Hestenes and Stiefel (HS) conjugate gradient algorithm under the Yuan-Wei-Lu inexact line search\ntechnique for large-scale unconstrained optimization problems, where the proposed algorithm has the following properties: (1) the\nnew search direction possesses not only a sufficient descent property but also a trust region feature; (2) the presented algorithm has\nglobal convergence for nonconvex functions; (3) the numerical experiment showed that the new algorithm is more effective than\nsimilar algorithms....
This paper presents a software library as a research and educational tool for Multi-Skill Resource-Constrained Scheduling\nProblem. The following useful tools have been implemented in Java: instance Generator, solution validator, solution visualizer\nand example solvers: Greedy algorithm and Genetic Algorithm. All tools are supported by iMOPSE dataset which consists\nof 36 instances and additional �small� 6 instances for educational purpose. In the paper, three test studies are described: (1)\neducational use of 6 �small� instances, (2) optimization of cost or duration of a schedule, and (3) simple bicritieria optimization\nof cost/duration of a final schedule. All described tools/examples are freely published on iMOPSE homepage....
Deep learning has been recently achieving a great performance for malware\nclassification task. Several research studies such as that of converting malware\ninto gray-scale images have helped to improve the task of classification in the\nsense that it is easier to use an image as input to a model that uses Deep\nLearning�s Convolutional Neural Network. In this paper, we propose a Convolutional\nNeural Network model for malware image classification that is able\nto reach 98% accuracy....
In order to improve the control precision and robustness of the existing proportion\nintegration differentiation (PID) controller of a 3-Revoluteââ?¬â??Revoluteââ?¬â??Revolute (3-RRR) parallel robot,\na variable PID parameter controller optimized by a genetic algorithm controller is proposed in this\npaper. Firstly, the inverse kinematics model of the 3-RRR parallel robot was established according to\nthe vector method, and the motor conversion matrix was deduced. Then, the error square integral\nwas chosen as the fitness function, and the genetic algorithm controller was designed. Finally, the\ncontrol precision of the new controller was verified through the simulation model of the 3-RRR planar\nparallel robotââ?¬â?built in SimMechanicsââ?¬â?and the robustness of the new controller was verified by\nadding interference. The results show that compared with the traditional PID controller, the new\ncontroller designed in this paper has better control precision and robustness, which provides the\nbasis for practical application....
This paper presents an algorithm/architecture and Hardware/Software co-designs for\nimplementing a digital edge computing layer on a Zynq platform in the context of the Internet of\nMultimedia Things (IoMT). Traditional cloud computing is no longer suitable for applications that\nrequire image processing due to cloud latency and privacy concerns. With edge computing, data\nare processed, analyzed, and encrypted very close to the device, which enable the ability to secure\ndata and act rapidly on connected things. The proposed edge computing system is composed of a\nreconfigurable module to simultaneously compress and encrypt multiple images, along with wireless\nimage transmission and display functionalities. A lightweight implementation of the proposed design\nis obtained by approximate computing of the discrete cosine transform (DCT) and by using a simple\nchaotic generator which greatly enhances the encryption efficiency. The deployed solution includes\nfour configurations based on HW/SW partitioning in order to handle the compromise between\nexecution time, area, and energy consumption. It was found with the experimental setup that by\nmoving more components to hardware execution, a timing speedup of more than nine times could be\nachieved with a negligible amount of energy consumption. The power efficiency was then enhanced\nby a ratio of 7.7 times....
Loading....