Method of unknown protocol classification based on autoencoder by Chunxiang GU, Weisen WU, Ya’nan SHI, Guangsong LI

“…Aiming at the problem that a large number of unknown protocols exist in the Internet,which makes it very difficult to manage and maintain the network security,a classification and identification method of unknown protocols was proposed.Combined with the autoencoder technology and the improved K-means clustering technology,the unknown protocol was classified and identified for the network traffic.The autoencoder was used to reduce dimensionality and select features of network traffic,clustering technology was used to classify the dimensionality reduction data unsupervised,and finally unsupervised recognition and classification of network traffic were realized.Experimental results show that the classification effect is better than the traditional K-means,DBSCAN,GMM algorithm,and has higher efficiency.…”
Get full text

3D Modeling of Mine Protection Complex Steel Structure Based on BIM Technology by Fenhong Li, Zaisheng Wang, Chongan Pang, Haiping Yang

“…The vibration control algorithm of complex steel structure for mine protection is designed, and the boundary elastic constraint conditions are determined. …”
Get full text

Representing Images' Meanings by Associative Values with Given Lexicons Considering the Semantic Tolerance Relation by Ying Dai

“…For this, the semantic tolerance relation model (STRM) that reflects the tolerance degree between defined lexicons is generated, and two factors of semantic relevance (SR) and visual similarity (VS) are involved in generating associative values. Furthermore, the algorithm of calculating associative values using pixel-based bidirectional associative memories (BAMs) in combination with the STRM, which is easy in implementation, is depicted. …”
Get full text

Danger theory inspired intrusion detection model for wireless sensor networks by Rong-rong FU, Kang-feng ZHENG, Tian-liang LU, Yi-xian YANG

“…According to the challenges of intrusion detection technique for wireless sensor networks,a danger theory in-spired intrusion detection model was proposed by taking advantage of the working principle of artificial immune system.Due to the distributed and cooperative mechanism,the proposed model shows more advantages in detection performance and energy consumption than methods adopt promiscuous to get global knowledge.The simulation results show that compared to traditional Watchdog algorithm with single threshold and self-nonself(SNS)model,the model inspired by danger theory can provide highest correct detection rate and lowest false detection rate.Moreover,the model can also decrease the energy consumption of the system.…”
Get full text

ACCEPTABLE LIMITS FOR CORRECTION OF HEATING LOAD WHILE OPTIMIZING OPERATIONAL MODES OF HEAT SOURCES by P. I. Diachek, V. A. Sednin, A. E. Zakharevich, I. V. Shkliar

“…Numerical investigations of temperature fields in the apartments of a multi-dwelling building has been carried out on the basis of the developed mathematical model and algorithm of its realization. The investigations have  made it possible to evaluate dynamics of changes in air temperature under unsteady conditions due to increase or reduction heating device capacity with regard to standardized values. …”
Get full text

A new neurodynamic model with Adam optimization method for solving generalized eigenvalue problem by Ebrahim Ganjalipour, Khadijeh Nemati, Amir Hosein Refahi Sheikhani, Hashem Saberi Najafi

“…The experiments demonstrate that our algorithm using Adam optimizer, in comparison with other stochastic optimization methods like gradient descent works well in practice and improves complexity and accuracy of convergence.…”
Get full text

Behavior authentication of Web users based on machine learning by Zenan WU, Liqin TIAN, Zhigang WANG

“…According to the security problem of Web user information,the user behavior was analyzed and authenticated by the method of machine learning.First of all,through the principal component analysis to reduce the dimension of the original data set,then use the SVM algorithm to allow the computer to learn the history of user behavior evidence,to get a model to identify the user's identity.The practical application and theoretical analysis show that the model in user behavior identification authentication,can be more accurate and efficient classification of dangerous users and trusted users,analysis lay a solid theoretical and practical basis for the high performance user behavior such as electronic commerce,network finance and other key of Internet applications.…”
Get full text

System and application of video surrveillance based on edge computing by Sanming PAN, Mingqiang YUAN

“…With the popularization of video surveillance systems and the diversification of their applications,traditional data processing methods using cloud computing to handle all the computations are more and more unsustainable.Edge computing pre-processes video data nearby,and performs well in terms of bandwidth,storage,and latency,but edge-cloud collaboration is still required to improve overall performance.The architecture of edge-cloud collaborative video surveillance system was proposed,then an open edge node design scheme and algorithm training and inferencing ideas were proposed.Finally,taking forest fire prevention and smart poles ＆amp; towers as examples,the application realization and value of edge computing in video surveillance services were illustrated.…”
Get full text

Moving target defense solution on network layer based on OpenFlow by Yi-xun HU, Kang-feng ZHENG, Yi-xian YANG, Xin-xin NIU

“…In order to take an active part in network attack and defense,a moving target defense solution on network layer based on OpenFlow was proposed,using the flexibility of network brought by OpenFlow network architecture.On the network layer,through mapping the correspondent nodes’ addresses to pseudo-random virtual addresses in the LAN and mapping correspondent nodes’ ports to virtual ports,achieving the hiding of correspond nodes in the whole network and the information of network architecture.Researches verify the system’s effectiveness.Comparing with existing moving target defense solutions,the proposed algorithm can be deployed easily in the traditional network,and realize comprehensive protection of the corresponding in the whole network.…”
Get full text

Study of interstage channel of hybrid turbomolecular pump by J. A. Shostak, N. K. Nikulin, P. A. Shostak, G. T. Tsakadze, E. V. Svichkar

“…The article describes an algorithm to construct a mathematical model step by step. …”
Get full text

Detection of Two-Level Inverter Open-Circuit Fault Using a Combined DWT-NN Approach by Bilal Djamel Eddine Cherif, Azeddine Bendiabdellah

“…This paper work addresses a diagnostic technique based on the discrete wavelet transform (DWT) algorithm and the approach of neural network (NN), for the detection of an inverter IGBT open-circuit switch fault. …”
Get full text

Integrity verification protocol based on privacy homomorphism data aggregation by Xing LI, Chun-yan LI, Liang-min WANG

“…Secure data aggregation in wireless sensor networks can effectively prevent privacy leakage,data tampering and other issues,it also achieves efficient data transmission.An integrity verification protocol based on privacy homomorphism data aggregation (IV-PHDA) was presented.The protocol uses homomorphism encryption to ensure data privacy,then it used random detection nodes to detect the integrity of the aggregated results to verify whether the aggregation node faithfully transmit each data packet.The theoretical analysis and simulation comparison verify the performance of the algorithm,the results show that this protocol can detect data integrity through transmission,and achieve better privacy protection and higher data accuracy.…”
Get full text

Structural Parameters Optimization of Corona Ring of Tethered Balloon-Type VLF Antenna by Ao Wang, Xianqiang Li, Huajun Zhang, Ji Tian, Wenchuang Zhou

“…In this paper, the structural parameters of the corona ring, including ring radius, tube radius, and ring depth, are optimized based on intelligent optimization algorithm to significantly improve the electric field distribution and restrain the temperature rise to the maximum extent. …”
Get full text

UAV Path Prediction for CD&R to Manned Aircraft in a Confined Airspace for Cooperative Mission by Chin E. Lin, Ya-Hsien Lai

“…In this paper, a new path prediction approach for unmanned aerial vehicles (UAVs) for conflict detection and resolution (CD&R) to manned aircraft in cooperative mission in a confined airspace is proposed. Path prediction algorithm is established to estimate UAV flight trajectory to predict conflict threat to manned aircraft in time advances (front-end process of CD&R system). …”
Get full text

Large-scale resource state monitoring strategy in network function virtualization environment by Meisheng HAI, Peng YI, Yiming JIANG, Jichao XIE

“…In order to improve the utilization of the infrastructure resource and efficiently deploy the service function chain dynamically in network function virtualization,the orchestration management domain needs to monitor the network resources and virtual network function status in real time,but real-time monitoring will bring large communication overhead.An intelligent distributed monitoring strategy with minimal network communication overhead was proposed.The improved label propagation algorithm intelligently subnets and selects agent monitoring nodes to achieve efficient monitoring of resource and virtual function status and minimize monitoring information communication overhead.The simulation results show that the monitoring strategy proposed reduces the monitoring information communication overhead in the network by about 13%.…”
Get full text

Particle filtering based semi-blind estimation for MIMO-OFDM time-varying channel by JING Yuan, YIN Fu-liang, ZENG Shuo

“…A semi-blind channel estimation method based on the particle filtering was proposed for the MIMO-OFDM wireless communication system.By optimizing the particles distribution locally,the traditional particle filtering algorithm was modified,and a local optimized particle filtering was proposed.This local optimized particle filtering can achieve the low MSE,and improve the precision of the MIMO-OFDM time-varying channel estimation.Since this method was per-formed in frequency domain,it was not necessary to know（or estimate） the length of the channel.Compared with exist-ing approaches,the proposed method was more robust to the non-gauss distribution noise and the detection performance is nearly optimal.The simulation results show the effectiveness of the proposed method.…”
Get full text

Improving the Accuracy of the Diffusion Model in Highly Absorbing Media by Alexander X. Cong, Haiou Shen, Wenxiang Cong, Ge Wang

“…In this paper, we presented a method to improve the accuracy of the diffusion model in strongly absorbing media by adjusting the optical parameters. Genetic algorithm-based optimization tool is used to find the optimal optical parameters. …”
Get full text

WIDE-RANGE GROUND/BOARD-BASED SPECTRAL METHOD FOR DETERMINING THE CHLOROPHYLL а CONCENTRATION IN SEAWATER by Basti Leysan gyzy Dzhafarova

“…The author has developed an operational algorithm of the above system functioning and has analyzed the issues of the optimal structuring of the system.…”

Pole Placement-Based NMPC of Hammerstein Systems and Its Application to Grade Transition Control of Polypropylene by He De-Feng, Yu Li

“…This paper presents a new nonlinear model predictive control (MPC) algorithm for Hammerstein systems subject to constraints on the state, input, and intermediate variable. …”
Get full text

Research of Multi- Objective Optimization Design for Car Main Reduction Gear based on Response Surface Method by Zhou Dan

“…The main reducing gear parameter optimization are carried out by using the NSGA- Ⅱ multi- objective optimization genetic algorithm in which the tooth root bending stress,tooth surface contact stress and volume of the gears are defined as objective function,the solution set of the gears parameters are obtained. …”
Get full text