A5017830007- Advanced Data and IoT Technologies
- Telecommunications and Broadcasting Technologies
- IoT and Edge/Fog Computing
- Green IT and Sustainability
- Software-Defined Networks and 5G
- Power Line Communications and Noise
- Technology and Security Systems
- Millimeter-Wave Propagation and Modeling
- COVID-19 diagnosis using AI
- Indoor and Outdoor Localization Technologies
- Caching and Content Delivery
- E-commerce and Technology Innovations
- Internet Traffic Analysis and Secure E-voting
- Advanced Wireless Communication Technologies
- Advanced MIMO Systems Optimization
- Context-Aware Activity Recognition Systems
- Privacy-Preserving Technologies in Data
China United Network Communications Group (China)
2021-2024
Minimization of driving test (MDT) is a key feature for network performance monitoring and optimization in mobile cellular networks. It has been widely used coverage estimation. However, the utility MDT data envisages some challenges, especially positioning inaccuracy sparsity. This paper innovatively constructs multi-source dataset, which mainly based on combined with human empirical data. Then, we train supervised learning model using Gradient Boosting Decision Tree (GBDT). Furthermore,...
The identification and financial aid for poverty stricken students in colleges is significant alleviation education equity while the traditional method based on voluntary reporting or subjective factors not accurate enough. In this paper, we propose an architecture telecom big data XGBoost (eXtreme Gradient Boosting) Algorithm. ensemble learning algorithm its ordinary parameters adjusting cannot improve performance of model significantly. Thus QBFO (Quantum Bacterial Foraging Optimization),...
MDT data have been widely used for 4G/5G wireless network coverage estimation. Whereas the sparsity of makes rate bias when it applied into realistic analysis. To achieve a more precise estimation, this paper proposes an approach that adding geographical and landform information to estimation in order refine rate. An attention U-Net model was landforms recognition from online satellite map with low cost. It can effectively assists telecom operators filter out areas, which are users...
Providing good user perception is the objective of telecom operators' mobile network operation and optimization. Specifically, operators try to improve quality meet customers' business needs. However, envisage a key problem that statistics from dimension do not directly reflect network. This results in disconnection between actual perception. paper mainly discusses relationship indicators Then, this realizes prediction side through random forest algorithm. The proposed algorithm can...
With the 5G commercial deployments rapidly proceeding, operating mobile networks efficiently has become a great challenge. Self-organizing have been proposed to focus on automatically monitoring, analyzing and optimizing networks. Regarding growing scale complexity, self-organizing confront challenge handle massive data. Therefore, AI models are urgently needed enable end-to-end network automation. In this demonstration, benefiting from open data interfaces of standardized NWDAF within 5GC...
We are going to enter the most intelligent era than ever before. Intelligent electronics network is infiltrating into our life and making it more convenient. Nonetheless, users always want smart home be complete features. users' issues endless. Modular packaging device services effective choreography algorithms can flexible fit different issues. Many organizations have been proving, implementing managing business solutions for many specific individual industries. However, when comes end...
With the increasing market competition, telecom operators need to improve level of services, ensure quality experience, as well reduce cost enterprise. Therefore it is crucial evaluate value customers accurately. The traditional method customer assessment mainly based on ARPU (Average Revenue Per User), which one-dimensional and cannot comprehensively. This paper proposes a multidimensional method, including two perspectives, Current Potential accuracy comprehensiveness evaluation. Also, an...
With AI and big data technologies, telecom operators are looking to change the traditional O&M model from reactive problem handling proactive prevention prediction. This paper proposes a framework trained on multiple sources for 5G wireless network support tasks based complaint By grouping user complaints into base station prediction, enhanced precision scores while maintaining high recall scores. The has been integrated operator's work order system intelligent operational optimization workflow.
When the data service latency of mobile network is too large, it will cause problems such as slow page opening, game stuck, video stuck and seriously affect user perception. Therefore, optimizing reducing become one main tasks in network. This paper researches on analysis method 5G problem. A set methods, which are for problem demarcation localization, provided to support operation maintenance personnel improving perception, focusing key performance wireless core networks that service.
With the continuous expansion of network construction, 4G/5G networks have gradually developed into hybrid multi-frequency heterogeneous networks, while difficulty inter-RAT mobility assurance is increasing. Traditional interoperability optimization requires enormous labor costs, and accuracy low. This paper proposes an AI-based collaborative scheme under based on XGBoost prediction model DNN algorithm. It aims to comprehensively improve performance different users in terms neighborhood...