An survey on application of artificial intelligence in 5G system by Jianwu ZHANG, Luxin WANG, Lingfen SUN, Qianye ZHANG, Hangguan SHAN

“…With the continuous development of 5G, the era of the internet of everything is coming.Problems such as massive device connections, massive application requests, ultra-high network load and complex dynamic network environment pose great challenges to the optimization of 5G systems in the context of the internet of everything.Facing these challenges, artificial intelligence (AI) shows its unique advantages.Firstly, the advantages of deep learning driven AI algorithms in 5G system compared with conventional algorithms were briefly introduced.Then, the application of AI algorithms in multi-access edge computing (MEC) and mmWave massive multiple-input multiple-output (MIMO) system were described in detail, with advantages and disadvantages of each method being compared and analyzed.Finally, according to the existing research, the shortcomings of AI algorithms in 5G application scenarios were summarized and the future research directions were forecasted.…”
Get full text

Multi-channel based edge-learning graph convolutional network by Shuai YANG, Ruiqin WANG, Hui MA

“…Usually the edges of the graph contain important information of the graph.However, most of deep learning models for graph learning, such as graph convolutional network (GCN) and graph attention network (GAT), do not fully utilize the characteristics of multi-dimensional edge features.Another problem is that there may be noise in the graph that affects the performance of graph learning.Multilayer perceptron (MLP) was used to denoise and optimize the graph data, and a multi-channel learning edge feature method was introduced on the basis of GCN.The multi-dimensional edge attributes of the graph were encoded, and the attributes contained in the original graph were modeled as multi-channel.Each channel corresponds to an edge feature attribute to constrain the training of graph nodes, which allows the algorithm to learn multi-dimensional edge features in the graph more reasonably.Experiments based on Cora, Tox21, Freesolv and other datasets had proved the effectiveness of denoising methods and multi-channel methods.…”
Get full text

An end-to-end implicit neural representation architecture for medical volume data. by Armin Sheibanifard, Hongchuan Yu, Zongcai Ruan, Jian J Zhang

“…To address the challenges, we propose an end-to-end architecture for data compression, leveraging advanced deep learning technologies. This architecture consists of three key modules: downsampling, implicit neural representation (INR), and super-resolution (SR). …”
Get full text

Machine Learning Based Agricultural Profitability Recommendation Systems: A Paradigm Shift in Crop Cultivation by Nilesh P. Sable, Rajkumar V. Patil, Mahendra Deore, Ratnmala Bhimanpallewar, Parikshit N. Mahalle

“…To address this, we propose the use of Machine Learning (ML) and Deep Learning (DL) techniques to analyze historical market price data for fruits and vegetables from 2016 to 2021 and predict future prices. …”
Get full text

UAV path intelligent planning in IoT data collection by Shu FU, Xiangyue YANG, Haijun ZHANG, Chen CHEN, Peng YU, Xin JIAN, Min LIU

“…To solve the problem of path planning of UAV data collection, it was generally be divided into global path planning and local path planning.For global path planning, it was modeled as an orientation problem, which was a combination of two classical optimization problems, the knapsack problem and the traveling salesman problem.The pointer network of deep learning was used to solve the model to obtain the service node set and service order under the energy constraint of the UAV.In terms of the local path planning, the reference signal strength (RSS) of the sensor node received by UAV was employed to learn the local flight path of UAV by deep Q network, which enabled the UAV to approach and serve the nodes.Simulation results show that the proposed scheme can effectively improve the revenue of UAV data collection under the energy constraint of UAV.…”
Get full text

Research progress of KPI anomaly detection in intelligent operation and maintenance by Su WANG, Hua LU, Shuo WANG, Lei CAI, Tao HUANG

“…Existing network monitoring and fault repair mostly rely on rule systems or manual processing.However, the increase in network scale and the diversification of services make this approach difficult to deal with.With the rapid development of technology such as machine learning and deep learning, intelligent operation and maintenance theory has also made great progress, using artificial intelligence technology to enhance the intelligent ability of network operation and maintenance.KPI (key performance indicator) anomaly detection is an underlying core technology of intelligent operation and maintenance.A survey on the KPI anomaly detection technology was given.Firstly, the KPI data and KPI anomalies were described.Then the research progress of single-dimensional KPI and multi-dimensional KPI anomaly detection were introduced.Then, the deployment and application problems of KPI anomaly detection were analyzed.Finally, future research directions were discussed.…”
Get full text

Cryptocurrency Financial Risk Analysis Based on Deep Machine Learning by Si Chen

“…Transaction plan considered building nodes in terms of network. Development of deep learning algorithms opens the horizons for the development of electronic businesses that use digital currency. …”
Get full text

¿Singularidad? Limitaciones, capacidades y diferencias de la inteligencia artificial frente a la inteligencia humana by Pablo Carrera

“…We briefly review the historical development of AI and delineate the real capacities and important limitations of deep learning techniques, underlying most of the recent advancements in AI. …”
Get full text

Intrusion detection model based on non-symmetric convolution auto-encode and support vector machine by Jialin WANG, Jiqiang LIU, Di ZHAO, Yingdi WANG, Yingxiao XIANG, Tong CHEN, Endong TONG, Wenjia NIU

“…Network intrusion detection system plays an important role in protecting network security.With the continuous development of science and technology,the current intrusion technology cannot cope with the modern complex and volatile network abnormal traffic,without taking into account the scalability,sustainability and training time of the detection technology.Aiming at these problems,a new deep learning method was proposed,which used unsupervised non-symmetric convolutional auto-encoder to learn the characteristics of the data.In addition,a new method based on the combination of non-symmetric convolutional auto-encoder and multi-class support vector machine was proposed.Experiments on the data set of KDD99 show that the method achieves good results,significantly reduces training time compared with other methods,and further improves the network intrusion detection technology.…”
Get full text

Proposed Detection Face Model by MobileNetV2 Using Asian Data Set by Phat Nguyen Huu, Vinh Tran Quang, Chau Nguyen Le Bao, Quang Tran Minh

“…Therefore, we propose a model capable of distinguishing between masked and nonmasked faces using a convolutional neural network (CNN) based on deep learning (DL)—MobileNetV2 in this paper. The model can detect people who are not wearing masks. …”
Get full text

Prediction of Ubiquitination Sites Using UbiNets by Sarthak Yadav, Manoj Gupta, Ankur Singh Bist

“…The main target of this paper is to explore the significance of deep learning techniques for the prediction of ubiquitination sites in protein sequences. …”
Get full text

Super-Resolution and Large Depth of Field Model for Optical Microscope Imaging by Ruo-Peng Zheng, Shu-Bin Liu, Lei Li

“…Due to the limitation of numerical aperture (NA) in a microscope, it is very difficult to obtain a clear image of the specimen with a large depth of field (DOF). We propose a deep learning network model to simultaneously improve the imaging resolution and DOF of optical microscopes. …”
Get full text

RETRACTED: Bone Age Assessment Based on Deep Convolutional Features and Fast Extreme Learning Machine Algorithm by Longjun Guo, Juan Wang, Jiaqi Teng, Yukun Chen

“…As the development of deep learning DL-based bone age prediction methods have achieved great success. …”
Get full text

Enhancing of teaching and learning through constructive alignment by G. E. Dames

“… This article elucidates issues about practical knowledge/deep learning on the current teaching and learning preaching practices in the Department of Practical Theology at the Faculty of Theology of the University of the Free State. …”
Get full text

A Comparative Study of Some Automatic Arabic Text Diacritization Systems by Ali Mijlad, Yacine El Younoussi

“…The other one is a pipeline, which includes a Long Short-Term Memory deep learning model, a rule-based correction component, and a statistical-based component. …”
Get full text

Research on crowd flows prediction model for 5G demand by Zheng HU, Hao YUAN, Xinning ZHU, Wanli NI

“…The deployment and planning for ultra-dense base stations,multidimensional resource management,and on-off switching in 5G networks rely on the accurate prediction of crowd flows in the specific areas.A deep spatial-temporal network for regional crowd flows prediction was proposed,by using the spatial-temporal data acquired from mobile networks.A deep learning based method was used to model the spatial-temporal dependencies with different scales.External factors were combined further to predict citywide crowd flows.Only data from local regions was applied to model the closeness of properties of the crowd flows,in order to reduce the requirements for transmitting the globe data in real time.It is of importance for improving the performance of 5G networks.The proposed model was evaluated based on call detail record data set.The experiment results show that the proposed model outperforms the other prediction models in term of the prediction precision.…”
Get full text

Modulation recognition method based on multi-inputs convolution neural network by Xiong ZHA, Hua PENG, Xin QIN, Guang LI, Tianyun LI

“…In order to identify the main modulation modes adopted in current satellite communication systems,a signal modulation recognition algorithm based on multi-inputs convolution neural network was proposed.With the prior information of the signals and knowledge of the network topological structure,the time-domain signal waveforms were converted into eye diagrams and vector diagrams to represent the shallow features of the signals.Meanwhile,the modulation recognition model based on multi-inputs convolution neural network was designed.Through the training of the network,the shallow features were deeply extracted and mapped.Finally,the signal modulation recognition task was completed.The simulation results show that compared with the traditional algorithms and deep learning algorithms,the proposed method has a better anti-noise performance,and the overall recognition rate of this algorithm can reach 95% when the signal-to-noise ratio is 5 dB.…”
Get full text

Patch-based domain adversarial training for speech enhancement by WANG Hongtao, LU Zhihua, YE Qingwei, ZHANG Lianjun

“…In deep learning-based speech enhancement methods, mismatched distributions between training data and test data are often encountered. …”
Get full text

The tumour histopathology "glossary" for AI developers. by Soham Mandal, Ann-Marie Baker, Trevor A Graham, Konstantin Bräutigam

“…The applications of artificial intelligence (AI) and deep learning (DL) are leading to significant advances in cancer research, particularly in analysing histopathology images for prognostic and treatment-predictive insights. …”
Get full text

Research on the Application of Variational Autoencoder in Image Generation by Liu Jianing

“…The rapid development of artificial intelligence and deep learning has significantly influenced the domain of image creation, finding extensive applications in applications in fields like medical imaging, computer vision, and entertainment. …”
Get full text