Two-Level Credit Financing for Noninstantaneous Deterioration Items in a Supply Chain with Downstream Credit-Linked Demand by Yong He, Hongfu Huang

“…Based on the theorems, an algorithm is designed, and numerical tests and sensitive analysis are provided. …”
Get full text

Cooperative Communication in Cognitive Radio Networks under Asymmetric Information: A Contract-Theory Based Approach by Nan Zhao, Minghu Wu, Wei Xiong, Cong Liu

“…A sequential optimization algorithm is proposed to obtain the optimal relay-reward strategy. …”
Get full text

Research and implementation on acquisition scheme of telecom big data based on Hadoop by Baoyou WANG, Jing QIAN, Shijin YUAN

“…ETL is a very important step in the implementation process of data warehouse.A good ETL flow is important,which can effectively process the telecom big data and improve the acquisition efficiency of the operation platform.Firstly,the main data content of the big data platform was expounded.Secondly,in order to improve the efficiency of massive data collection,Hadoop and Oracle mashup solution was suggested.Subsequently,a dynamic triggered ETL scheduling flow and algorithm was proposed.Compared with timer start ETL scheduling method,it could effectively shorten waiting time and avoid the phenomenon of resources to seize and congestion.Finally,according to the running log of Hadoop platform and Oracle database,the relationship between acquisition efficiency and data quantity was analyzed comparatively.Furthermore,practice result shows that the hybrid data structure of the big data platform complement each other and can effectively enhance the timeliness of data collection and access better application effect.…”
Get full text

Data management based on blockchain and edge computing for Internet of things by Guanjie CHENG, Zhengjie HUANG, Shuiguang DENG

“…The popularity of smart devices has driven the development of the application of Internet of things (IoT) technology,and the resulting massive amount of IoT data has brought challenges to traditional centralized data management methods,such as performance,privacy,and security.Therefore,a data management framework of IoT based on blockchain and edge computing was proposed to support the distributed IoT data management.The distributed storage and access control could be provided by the framework for the IoT data.At the same time,a set of the built-in encryption scheme was designed to protect the data security and privacy and safeguard the data ownership.By introducing edge computing,the scalability bottleneck of the blockchain the system was relieved.The processes of data storage and data access based on this framework were given,and the algorithm of the system implementation based on the smart contract technology was explained in detail.Experiments show that the IoT data management system based on this framework outperforms the traditional cloud-based data management systems.…”
Get full text

ORGANIZATIONAL-METHODICAL BASES OF THE FUNCTIONALLY-ORIENTED TRAINING OF SPECIALISTS IN THE STRUCTURE OF REGIONAL EDUCATIONAL CLUSTER by Pavel G. Kravtsov, Valentin N. Mikhelkevich

“…The article gives a definition of "regional educational cluster", RAS-considered its structure, socio-didactic value. The algorithm of creation and development of the education cluster in a particular region. …”
Get full text

Cracking-resistance net-flow fingerprint scheme based on multi-dimensional orthogonal carriers by Cheng LEI, Hong-qi ZHANG, Yi SUN, Xue-hui DU

“…Besides, it analyzes accuracy of fingerprint centroid algorithm and quantization index modulation decoding technique based on HMM under different cases. …”
Get full text

Backdoor defense method in federated learning based on contrastive training by Jiale ZHANG, Chengcheng ZHU, Xiang CHENG, Xiaobing SUN, Bing CHEN

“…In response to the inadequacy of existing defense methods for backdoor attacks in federated learning to effectively remove embedded backdoor features from models, while simultaneously reducing the accuracy of the primary task, a federated learning backdoor defense method called ContraFL was proposed, which utilized contrastive training to disrupt the clustering process of backdoor samples in the feature space, thereby rendering the global model classifications in federated learning independent of the backdoor trigger features.Specifically, on the server side, a trigger generation algorithm was developed to construct a generator pool to restore potential backdoor triggers in the training samples of the global model.Consequently, the trigger generator pool was distributed to the participants by the server, where each participant added the generated backdoor triggers to their local samples to achieve backdoor data augmentation.Experimental results demonstrate that ContraFL effectively defends against various backdoor attacks in federated learning, outperforming existing defense methods.…”
Get full text

3D Automatic Segmentation of Brain Tumor Based on Deep Neural Network and Multimodal MRI Images by Zhuliang Qian, Lifeng Xie, Yisheng Xu

“…The comparison of the results between the two algorithms proves that the CNN algorithm has the better processing power and higher efficiency.…”
Get full text

Crack simulation for the cover of the landfill � A seismic design by Mehran Karimpour-Fard, Omer Mughieda, Filippo Berto, Nurmunira Muhammad

“…Artificial Neural Networks (ANNs) based on Levenberg-Marquardt Algorithm and Abalone Rings Data Set mode were used to predict displacement in critical points of the model. …”
Get full text

DEEP NEURAL NETWORK-BASED APPROACH FOR COMPUTING SINGULAR VALUES OF MATRICES by Diyari A. Hassan

“…The proposed CNN-based SVD method is evaluated against the conventional SVD algorithm, demonstrating superior performance in terms of computational time and accuracy. …”
Get full text

THE TECHNIQUES SEPARATING THREE OVERLAP PEAKS IN GAMMA SPECTRUM by Trịnh Ngọc Pháp, Mai Xuân Trung

“…The calculation procedure was performed by the Levenberg-Marquardt algorithm with linear and nonlinear background. Based on separating the two overlap peaks method has been implemented in our previous article, the separating three overlap peaks was successfully implemented in this paper, in which the calculations were tested with gamma-ray spectra by using a Semiconductor detector and a Scintillator detector.…”
Get full text

Green city: An efficient task joint execution strategy for mobile micro-learning by Li Yang, Ruijuan Zheng, Junlong Zhu, Mingchuan Zhang, Ruoshui Liu, Qingtao Wu

“…Finally, the genetic algorithm is used to find the optimal executive strategy. …”
Get full text

Decision Tree Classification Model for Popularity Forecast of Chinese Colleges by Xiangxiang Zeng, Sisi Yuan, You Li, Quan Zou

“…We first extract a feature called “popularity change ratio” from existing data and then use a simplified but efficient algorithm based on “gain ratio” for decision tree construction. …”
Get full text

Detecting P2P botnet based on the role of flows by Yuan-zhang SONG, Jun-ting HE, Bo ZHANG, Jun-jie WANG, An-bang WANG

“…Towards the weaknesses of the existing detection methods of P2P botnet,a novel real-time detection model based on the role of flows was proposed,which was named as RF.According to the characteristics of flows,the model made the flows play the different roles in the detection of the P2P botnet to detect the essential abnormality and the attacking abnormality.And the model considered the influence on the detection of the P2P botnet which the Web applications generated,especially the applications based on the P2P protocols.To minimize the false positive rate and false negative rate,a real-time method based on the sliding window to estimate the Hurst parameter was proposed,and the Kaufman algorithm was applied to adjust the threshold dynamically.The experiments showed that the model was able to detect the new P2P botnet with a relatively high precision.…”
Get full text

Research status of channel estimation and signal detection techniques for orthogonal time frequency space modulation by WANG Yongchuan, ZHOU Ping, HUANG Ju

“…In order to obtain the time-frequency full diversity gain, a receiver with advanced channel estimation and signal detection algorithm is needed. The basic principle and system model of OTFS was firstly introduced, then the existing channel estimation and signal detection algorithms were reviewed, finally the future challenges and solutions for channel estimation and signal detection were discussed.…”
Get full text

Review on autoencoder and its application by Jie LAI, Xiaodan WANG, Qian XIANG, Yafei SONG, Wen QUAN

“…As a typical deep unsupervised learning model, autoencoder can automatically learn effective abstract features from unlabeled samples.In recent years, autoencoder has been widely used in target recognition, intrusion detection, fault diagnosis and many other fields.Thus, the theoretical basis, improved methods, application fields and research directions of autoencoder were described and summarized comprehensively.At first, the network structure, theoretical derivation and algorithm flow of traditional autoencoder were introduced and analyzed, and the difference between autoencoder and other unsupervised learning algorithms was compared.Then, common improved autoencoders were discussed, and their innovation, improvement methods and relative merits were analyzed.Next, the practical application status of autoencoder in target recognition, intrusion detection and other fields were introduced.At last, the existing problems of autoencoder were summarized, and the possible research directions were prospected.…”
Get full text

One-way hash function construction based on Chen-type hyper-chaotic system and key-stream by REN Hai-peng, ZHUANG Yuan

“…Theoretical analysis and experimental results indicate that the proposed algorithm can satisfy the required security performance, such as data compression function, irreversibility, initial value sensitivity forgery resistance and collision resistance. …”
Get full text

Blockchain-based distributed EHR fine-grained traceability scheme by Zuobin YING, Yuanping SI, Jianfeng MA, Ximeng LIU

“…Aiming at the key management of electronic health records (EHR) in a distributed system and user identity tracing issues, a distributed EHR fine-grained traceability scheme based on blockchain was proposed.Combining chameleon hash and zero-knowledge proof technology, the registration of nodes on the blockchain and the generation of identity certificates were realized, and the traceability of malicious users on the blockchain was realized.Besides, given the single point of failure problem of key management, the attribute-based encryption scheme of distributed ciphertext strategy was designed to achieve secure and fine-grained data access control, and multiple decryption agency blockchain nodes were set up to jointly distribute the attribute private keys of user nodes.The security analysis shows that the traceable distributed key generation attribute-based encryption algorithm based on the blockchain is adaptively secure under the random oracle model, and through experiments, the feasibility and practicability of the proposed scheme are shown.…”
Get full text

Application of New Media Big Data in Visual Performance of Axonometric Illustration by Jia Zhou

“…On the basis of analyzing related theories at home and abroad, the literature research method and algorithm-driven method are used comprehensively. It can not only effectively improve the visual effect of axonometric illustration by 12.3% but also solve the problems and challenges faced by the current China’s axonometric illustration industry.…”
Get full text

Identifying the Effective Factors on Neuropathic Diseases in Patients with Chronic pain Using Deep Neural Networks by Mobin Shaterian, Mohammad Teshnehlab

“…By using the deep neural network and the nearest neighbor and the genetic algorithm and the auto encoder, the list of features was obtained with a precision measurement of 75 percentage. …”
Get full text