Application and research of marketing using automatic similar users extension technology in telecom industry by Xu ZHANG, Yang LIU, Lei HU, Xiaodong ZHAO, Haibin ZHANG

“…With the explosive development of data service,TSP(telecommunication service provider) has taken advantages of owing massive user data.It is a necessity for TSP to develop value added business using big data techniques which explores the data value.The traditional way of marketing utilizes rules or supervised classification method meets the challenge of low success rate and long data acquisition period.Therefore,a new service named Lookalike was proposed.The service supports precision marketing by integrating matric learning and deep learning efficiently based on telecom operators’ data characteristics.The Lookalike service decreases the artificial participation and enhances the efficiency and success rate of marketing activity.The enhancement of TTM (time to market) has been improved in many real programs and the success rate of marketing has increased absolutely.…”
Get full text

Retracted: Image Recognition Technology Based on Neural Network by Jianqiu Chen

“…Image recognition is an important part of human-computer interaction. Using deep learning algorithms to recognize and classify image has become a hot issue for scholars from all walks of life. …”
Get full text

Application of image detection techniques in telecom operation and maintenance system by Bo FAN, Yun QIU, Lei SHEN

“…With the development of telecom industry,growing web service operations need more people to maintain the quality of the service.In the branch of telecom operation service,installation and maintenance service,the service quality is evaluated by human through assessing picture of construction site.The traditional way of evaluating quality of operation service brings low accuracy and high labor cost.In recent years,image recognition technology developed well with the deep learning raised,the related application field were broaden.If image recognition techniques were applied in telecom operation and maintenance system,the labor cost would be saved and the recognition accuracy would be improved.Several image recognition techniques were applied in installation quality assessment of telecom operation and maintenance system,and the performance and accuracy were analyzed.Based on analysis,a combining image recognition model was further proposed.The image recognition accuracy and efficiency of quality assessment was improved.…”
Get full text

Research on 5G base station energy saving system based on DCNN-LSTM load prediction algorithm by Jianbin WANG, Shuchun WANG, Shangjin LIAO, Shuyuan SHI

“…With the rapid construction of the 5G wireless communication network, the energy consumption pressure of operators, and even the overall communication industry, is simultaneously highlighted.Achieving sustainable development of the industry through energy conservation and consumption reduction has become a new research direction for the current 5G network development.Taking the PRB rate as the load evaluation index, LSTM model was improved by using DCNN to extract the depth feature of the cell’s indicators.A set of DCNN-LSTM deep learning model that could predict the future value of PRB rate was proposed.On the basis of the improved algorithm, the network topology of the current 5G access network was optimized.An additional network element and its working system were designed.An intelligent energy-saving system, which ensured the network experience, of 5G base stations was realized.…”
Get full text

FAULT DIAGNOSIS OF WIND TURBINE BEARING BASED ON SENET-RESNEXT-LSTM by DU HaoFei, ZHANG Chao, LI JianJun

“…The experimental results show that, compared with the current bearing fault diagnosis method based on deep learning, the proposed method performs better in bearing fault classification accuracy.…”
Get full text

Customer-centered mobile network intelligent operation approach by Kai LI, Wei LIU, Guiyang LUO, Jinglin LI

“…The rapid development of new types of services places greater demands on support ability of the personalized service in mobile communication systems.Traditional intelligent pipe carriers only consider limited factors such as current traffic status of the network and number of loading binding quantity,indicating that they don’t take account of the demands and features of wireless customers.Meanwhile,the rule-based method is overwhelmed due to numerous metrics of the wireless network,the complicated correlation among them and heterogeneous requirements of metrics from various users.Therefore,a user-centric intelligent network operation service was proposed,which utilized machine learning and deep learning method.The service had the ability to learn the correlation between user QoS guarantee requirements and wireless network metric status to construct a joint support architecture based on user requirements and wireless network status.The validity of the method on real data was verified.…”
Get full text

Comprehensive Analysis of Face Recognition Technologies by Liu Bowei

“…Among the various techniques reviewed, deep learning methods emerge as the most promising for face recognition due to their superior performance. …”
Get full text

Computer vision based automatic evaluation method of Y2O3 steel coating performance with SEM image by Jianhong Zhao, Huamin Yang, Yi Sui

“…Abstract This study introduces a deep learning-based automatic evaluation method for analyzing the microstructure of steel with scanning electron microscopy (SEM), aiming to address the limitations of manual marking and subjective assessments by researchers. …”
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

“…Due to the development of modern technology, it is very valuable to use deep learning (DL) and multimodal MRI images to study brain tumor segmentation. …”
Get full text

Alzheimer's disease image classification based on enhanced residual attention network. by Xiaoli Li, Bairui Gong, Xinfang Chen, Hui Li, Guoming Yuan

“…To address these issues, this study proposes a deep learning model to detect Alzheimer's disease; it is called Enhanced Residual Attention Network (ERAN) that can classify medical images. …”
Get full text

VisionMD: an open-source tool for video-based analysis of motor function in movement disorders by Gabriela Acevedo, Florian Lange, Carolina Calonge, Robert Peach, Joshua K. Wong, Diego L. Guarin

“…Abstract VisionMD, an open-source software for automated video-based analysis of MDS-UPDRS Part III motor tasks, offers precise, objective, and scalable assessments of motor symptoms in Parkinson’s disease and other movement disorders. Leveraging deep learning, VisionMD tracks body movements to compute kinematic features that quantify symptoms severity and supports longitudinal monitoring. …”
Get full text

Vers une ontologie de domaine pour l’analyse des tissus anciens. Le projet Silknow et le cas du patrimoine soyeux européen by Marie Puren, Pierre Vernus

“…In this article, we present the Silknow project (Silk heritage in the knowledge society: from punched card to big data, deep learning and visual/tangible simulations, 2018-2021). …”
Get full text

Proposing Algorithm Using YOLOV4 and VGG-16 for Smart-Education by Phat Nguyen Huu, Khang Doan Xuan

“…We rely on traditional solution methods to build algorithms to solve automated equations based on deep learning. The proposal method includes two main steps. …”
Get full text

Global Information Management Model and Identification Method Based on Deep Reinforcement Learning by RuiLe Lan, XiJia He

“…Many countries in the world are actively conducting research on information technology and management. And deep learning is a new type of efficient and open technology system and tool. …”
Get full text

GAN-based channel estimation for massive MIMO system by Yuxiu HUA, Rongpeng LI, Zhifeng ZHAO, Jianjun WU, Honggang ZHANG

“…As a key technology of 5G, massive MIMO system can significantly improve spectrum efficiency and energy efficiency by equipping a large number of antennas in base stations.However, in massive MIMO system, accurate channel estimation faces severe challenges.In order to estimate the channel accurately when the pilot sequence length is smaller than the number of transmitting antennas and the channel noise is strong, the estimation method N2N-GAN was proposed.N2N-GAN firstly denoised the pilot channel at the receiving end, and then used the conditional generative adversarial network to estimate the channel matrix according to the denoised pilot signal.Simulation experiments show that N2N-GAN achieves better robustness against noise compared with traditional channel estimation algorithms and deep learning-based methods.Meanwhile, it can adapt to scenarios with fewer pilot symbols and more antennas.…”
Get full text

Faster R-CNN and 3D reconstruction for handling tasks implementing a Scara robot by Julian Herrera-Benavidez, Cesar Pachón-Suescún, Robinson Jimenez-Moreno

“…This paper presents the design and results of using a deep learning algorithm for robotic manipulation in object handling tasks in a virtual industrial environment. …”
Get full text

Transverse cracking in glass fibre-reinforced composites monitored with synchrotron X-ray multi-projection imaging by Elise Van Vlierberghe, Jeroen Soete, Eleni Myrto Asimakopoulou, Zisheng Yao, Julia Rogalinski, Zhe Hu, Kannara Mom, Bratislav Lukić, Christian Breite, Pablo Villanueava Perez, Yentl Swolfs

“…Radiographs taken at three angles with synchrotron radiation enabled the detection of crack propagation and other damage mechanisms related to the final failure of composites. Deep learning segmentation has been proven effective in analysing the crack shape before a crack opening occurs. …”
Get full text

Research on RNN and LSTM Method for Dynamic Prediction of Landslide Displacement by ZHANG Mingyue, LI Limin, WEN Zongzhou

“…Good landslide displacement prediction is an important part of the landslide disaster warning.Limited by the nonlinear dynamic characteristics of landslide displacement evolution,historical data is generally missing in traditional prediction methods,resulting in low prediction accuracy.To this end,this paper proposes a deep learning method for landslide displacement prediction to establish two dynamic displacement prediction models of recurrent neural network (RNN) and long short term memory network (LSTM) for comparison,and selects the displacement changes of multiple monitoring points for dynamic prediction by the method of “circulation training”,taking the Xintan landslide project as an example.The results show that when the error function meets the expected accuracy,the LSTM model has higher prediction accuracy.In addition,various evaluation indicators also show that the overall prediction effect of the LSTM model is better.…”
Get full text

Improving the Accuracy of Batik Classification using Deep Convolutional Auto Encoder by Muhammad Faqih Dzulqarnain, Abdul Fadlil, Imam Riadi

“…This study highlights the potential of deep convolutional autoencoders as a powerful tool for augmenting image data and improving the performance of deep learning models in the context of batik image classification.…”
Get full text

Data-Driven Bearing Fault Diagnosis for Induction Motor by Aqib Raqeeb, Fahim Shah, Zaheer Alam, Subhashree Choudhury, Bilal Khan, R. Palanisamy

“…In contrast, our work leverages deep learning, particularly convolutional neural networks, to automatically extract fault features from raw data. …”
Get full text