Optimal Route Selection Decision-Making Based on Intelligent Network by Mengshu Zhao, Zhaohui Zhang

“…We construct some dynamic multiobjective network problems and use heuristic algorithm to solve the two problems in four levels in the paper. …”
Get full text

A New Method to Improve the Measurement Accuracy of Autonomous Astronomical Navigation by Yu-Feng Yang, Xiang Han, Ning-Ning Song, Zi-Chen Wang

“…Based on the theory of atmospheric refraction, combined with the atmospheric parameter data of NCEP (National Centers for environmental prediction), the Fourier interpolation fitting algorithm is used to model and analyze the parameters affecting atmospheric refraction on a global scale. …”
Get full text

Computer 3D Scene Simulation of Ecological Landscape Layout Planning by Tong Ling, Yun Ma

“…OpenGL shader language was used for rendering, improved NSGA-II algorithm was used with the help of bionic logic of the genetic evolution process to achieve landscape land allocation optimization. …”
Get full text

Image Fusing by Block Compressed Sensing in Contourlet Domain by Aiping Tang, Hui Cao

“…For traditional image fusion method results in loss of texture detail, a block compressed sensing image fusion algorithm in contourlet domain with a shift invariant and anti-aliasing ability called Contourlet_BCS was proposed. …”
Get full text

Internet traffic classification using SVM with flexible feature space by Yaguan QIAN, Xiaohui GUAN, Bensheng YUN, Qiong LOU, Pengfei MA

“…SVM is a typical machine learning algorithm with prefect generalization capacity,which is suitable for the internet traffic classification.At present,there are two approaches,One-Against-All and One-Against-One,proposed for extending SVM to multi-class problem like traffic classification.However,these approaches are both based on a unique feature space.In fact,the separating capacity of a special traffic feature is not similar to different applications.Hence,flexible feature space for extending SVM was proposed,which constructs independent feature space with optimal discriminability for each binary-SVM and trains them under their own feature space.Finally,these trained binary-SVM were ensemble by One-Against-All and One-Against-One approaches.The experiments show that the proposed approach can efficiently improve the precision and callback of the traffic classifier and easily obtain more reasonable optimal separating hyper-plane.…”
Get full text

Analysis and Optimization of the Vibro-acoustic Coupled of Crane Reducer by Dai Jun

“…The acoustic optimization model of crane reducer is established by setting the box thickness of reducer as design variable,the mass of the reducer as constraint condition,the field pressure as objective function,the optimal design variable is obtained by using normal boundary intersection optimization algorithm. The results show that the peak amplitude of surface sound pressure occur at center frequency of 500 Hz before and after optimization,the sound pressure of the four field points of the reducer are reduced after optimization.…”
Get full text

Optimal Quantum Circuit Cuts with Application to Clustered Hamiltonian Simulation by Aram W. Harrow, Angus Lowe

“…As an application, we give an improved algorithm for clustered Hamiltonian simulation. Specifically we show that interactions can be removed at a cost, which is exponential in the sum of their strengths times the evolution time, and vanishing in the limit of weak interactions. …”
Get full text

Fuzzy sliding mode control based on an adaptive sliding surface and extended state observer for automotive electric power steering by Tuan Anh Nguyen

“…Overall, the performance of the proposed algorithm is significantly improved compared with the traditional control methods.…”
Get full text

Off-line emergency communication method of power internet of things based on edge computing by Donghong FU, Dan LIU, Guijun SHI, Anxin WANG, Chunxue FAN, Haijun WANG, Yiying ZHANG

“…A new multi-mode node was designed for the emergency communication with the demand of electricity.The node had the multi-mode communication capability of the private network and the public network technology,which could switch smoothly in three modes:the power private network,the wireless Ad Hoc network and the wireless public network.Data were automatically uploaded to the multi-mode terminal,multi-mode terminal through the mode of rapid switching,with the public network resources to achieve rapid network recovery and continuous transmission of data to achieve off-line emergency communications.Meanwhile,an intelligent routing algorithm based on smoothness was proposed,and the three principles of edge network communication were defined.Through the edge calculation method,the calculation and updating of the smoothness were realized to ensure the intelligent,efficient and reliable operation of the edge network in the offline state.…”
Get full text

Optimizing of Transmission Gear Ratio based on Cruise-Isight Co-simulation by Ai Xiaochen, Zheng Guangyong, Zhang Shoufeng, Zeng Hao

“…By using multi-island genetic algorithm,the transmission gear ratio is optimized separately under certain traction ability and structural design constraints,a basic optimized scheme which can meets performance target is gotten. …”
Get full text

Detection and Classification of Single Machining Error of Non-circular Gear by Dai Jianqing, Wang Shengze

“…The studies on non-circular gear cutting and using errors are generally based on theory of cylindrical gear errors,and the similarities and differences between cylindrical gear and non-circular gear are combined to study the change rule of non-circular gear contacting line and obtained corresponding conclusions.From a different perspective,by starting from the non-circular gear engagement principle,on the basis of analyzing the concrete geometric error conditions,the new type tooth profile algorithm routine is reasonably modified,and the non-circular gear tooth profile error contrast figure is obtained.Furthermore,the theoretical verification is carried out by incorporating analytical method and contacting line incremental method,a reasonable classification method is proposed based on the characterization of the error characteristic code in the general case and the error genetic map used to guide practical production is summed up which possess enormous significance to non-circular gear machining.…”
Get full text

A Demand Forecasting Model Leveraging Machine Learning to Decode Customer Preferences for New Fashion Products by S. Anitha, R. Neelakandan

“…K-means clustering, an unsupervised machine learning algorithm, is applied to form clusters by grouping similar profiles. …”
Get full text

Anomaly intrusion detection based on modified SVM by Hui ZHANG, Cheng LIU

“…A modified SVM multi-classification algorithm integrated with discriminant analysis (D-SVM) was pro-posed,which could solve the problem of low detection accuracy and high false alarm rate caused by unbalanced datasets.For a multi-classification problem could be divided into several binary classification problems,D-SVM could not only have the virtue of high detection accuracy,but also have a low false alarm rate even confronted with unbalanced datasets.Experiments based on KDD99 dataset verify the feasibility and validity of the integrated ap-proach.Results show that when confronted with multi-classification problems,D-SVM could achieve a high detec-tion accuracy and low false alarm rate even when SVM alone fails because of the unbalanced datasets.…”
Get full text

Design of a Machine Learning-Based Platform for Currency Market Prediction: A Fundamental Design Model by Kevin Gordillo-Orjuela, Paulo Alonso Gaona-García, Carlos Enrique Montenegro-Marín

“…This growth has made it possible to train several techniques that increasingly allow us to improve predictions according to the criteria that each algorithm supports and can cover. However, the development of these models and their deployment within computer platforms is a complex task, given the variety of approaches that each researcher uses based on the training process and therefore by definition of the model, which leads to the consumption of high computing resources for its training, as well as various processes for its deployment. …”
Get full text

Performance enhancement scheme for IRS-assisted cognitive backscatter communication network by Bin LYU, Yi CAO, Jian LI, Ting QI

“…In order to achieve the self-sustainable cognitive radio network （CRN） and improve its communication efficiency， an efficient multi-mode switching scheme assisted by the intelligent reflecting surface （IRS） for the overlay scenario was proposed.In particular， the secondary transmitter （ST） could work in either backscatter communication （BackCom） mode or harvest-then-transmit （HTT） mode.The IRS was exploited to enhance the energy harvesting， information backscattering， and information transmission efficiencies at the ST.To maximize the system sum-rate， an optimization problem about the phase shirts at the IRS， time scheduling， and power allocation was formulated.Since the formulated problem was non-convex， an efficient block coordinate descent （BCD） based algorithm was proposed to achieve the sub-optimal solution.Simulation results confirm that the proposed scheme can achieve up to 200% sum-rate gain over the benchmark schemes.…”
Get full text

Low frequency acoustic source imaging method based on coprime position non-synchronous measurement by Juan WEI, Yutao HE, Fangli NING

“…In order to solve the problem that the acoustic imaging resolution was low under the condition of low frequency and low SNR due to the limited microphone array aperture and element density, a high resolution imaging method of low frequency and low SNR sound source was proposed based on the non-synchronous measurement of the coprime position.Firstly, the acoustic signal was received at the coprime position and the missing cross-spectrum matrix was calculated by the mobile prototype array.Then, the improved accelerated proximity gradient algorithm was used to complete the missing cross-spectrum matrix, and the complete cross-spectrum matrix was vectorized.Finally, the virtual array signal model was established and solved.The simulation results demonstrate that the proposed method has lower positioning error, higher imaging resolution, and better robustness and noise immunity than the previous methods under the condition of low frequency and low SNR.…”
Get full text

Adaptive Complex-Valued Independent Component Analysis Based on Second-Order Statistics by Yanfei Jia, Xiaodong Yang

“…The simulation results demonstrate the validity of the proposed algorithm.…”
Get full text

Research on the multiuser MIMO linear cooperative spectrum sensing in cognitive radio networks by Yong-qiang HEI, Xiao-hui LI, Wen-tao LI

“…The multiuser MIMO based linear cooperative spectrum sensing problem was investigated in cognitive radio system to improve the reliability of spectrum sensing.Both the local spectrum detecting strategy and global spectrum detecting strategy for multiuser MIMO based linear cooperative spectrum sensing system were derived.Then the optimization model that the different weights assigned on the receive signals of each user at the fusion center for global decision were optimized to maximize the detection probability given a targeted probability of false alarm is established.Furthermore,genetic algorithm (GA) was introduced to find the optimal weight vector of the above-mentioned cooperative spectrum sensing problem,with the purpose of reducing the sensing time in the spectrum sensing process.The simulation results show that,the reliability of spectrum sensing in cooperative spectrum sensing system can be efficiently enhanced with multiple antennas.Besides,the proposed GA method is efficient and stable,and achieves better detection performance when compared with the existing methods.…”
Get full text

Optimal service selection approach considering both atomic transaction and end-to-end QoS constraints by LIU Hai1, ZHANG Wei-min1, ZHANG Zhu-xi2, JIA Xiong1, LIAO Wei1

“…An actual SCG（service candidate graph） model-based optimal service selection approach was proposed.Firstly,the approach created transactional constraint relationships among candidates as an actual SCG model with several build-ing rules,whose correctness had been also proved;Then,an optimal QoS-aware service selection algorithm on the basis of BFS（breadth first search） was designed,where a relaxing and pruming method was applied to keep the computation scale in polynomial time.Finally,simulation experiments were conducted with real-world QoS dataset and random data-set,whose results demonstrated the beneficial performance on global QoS utility and outstanding successful selecting ra-tio over other related work.Meanwhile,the correctnesss has also been proved in practice by implementing a transactional automation.…”
Get full text

Flow-of-traffic prediction program based mobile edge computing for Internet of vehicles using double auction by Yan LIN, Shuai YAN, Yijin ZHANG, Chunguo LI, Feng SHU

“…With an aim of maximizing the efficiency of edge offloading and the resource utilization of edge computing server simultaneously, a new flow-of-traffic prediction based edge computing offloading solution was proposed for Internet of vehicles (IoV).Firstly, both the efficiency utility function of vehicle and the resource utilization of mobile edge computing (MEC) server were established by considering task priority.Next, the formulated dual-objective optimization problem was transformed into a double auction problem between vehicles and MEC servers.Finally, based on the designed flow-of-traffic based pricing function of vehicle and MEC server, a McAfee auction algorithm was adopted to complete the edge computing process.Simulation results show that benefiting from the flow-of-traffic prediction information, the proposed solution can significantly improve both the efficiency of computation offloading and the utilization of computation resource.…”
Get full text