Introduction to ICN lab
With the proliferation of IoT devices and the advancement of Internet technologies, both wired and wireless connectivity play a critical role in providing end-users with a diverse range of services. Individuals, institutions, governments, and industries have all been influenced by such communication and networking technology. As a result, communication technology has become an essential part of our daily lives. Machine Learning (ML) technologies have recently made great progress. The growth of AI, when combined with communication technology, has resulted in innovative applications such as smart cities, self-driving automobiles, and so on. 
 
Our lab, ICN (Intelligent Communication Networks), is one of eight research groups at BK.AI center. We aim at exploring and creating high-speed, reliable, and flexible networking technologies, incorporating social, information, device, and energy issues using theoretical and practical methodologies. Furthermore, we investigate how AI might be used to improve and optimize network performance. We're also looking at data analytics and mining solutions for IoT devices.
Research Direction
Solving problems of NGN in expanding the existing access network infrastructure into networks capable of satisfying the user’s requirements.
Focusing on processing, analyzing and mining data collected from IoT devices.
Applying various machine learning, including graph networks, deep reinforcement learning to analyze and predict the network behavior. Leveraging AI in controlling network operations.
Addressing different problems in distributed systems such as Synchronization, Replication and Consistency, Fault tolerance.
Exploiting machine learning, deep learning, reinforcement learning, meta-heurisctic techniques to optimize network performance.
Proposing adaptive mechanisms to predict and optimize QoS/QoE in network systems.
Research Topics
This research topic, part of the VinIF-funded Fi-Mi project, presents a new mobile air quality monitoring network based on vehicle-mounted sensors. We explore various research issues, such as resource allocation, opportunistic communication, crowdsensing, and data mining. Reinforcement learning, fuzzy logic, and meta-heuristics are used to solve resource allocation and efficient communication. Machine learning methodologies are used to calibrate the acquired data. We also leverage graph neural networks, ensemble nearing, and other DL techniques to solve the prediction problem.
The learning phase of a multi-domain SDN network must address the following issues: due to the computational cost, training time, and accuracy, both solutions of 1) learning separately in each domain and 2) collecting all data from different controllers and launching the training phase in a centralized server are inefficient. This drives us to use Federated Learning, in which distant SDN controllers collaborate to develop a centralized learning model while maintaining data privacy by not sharing the training data.
We investigate a fascinating research problem that is how to calibrate the satellite precipitation data. Our method uses deep learning techniques to blend satellite data that is fine-grained but inaccurate with the coarse-but-accurate data from ground-based monitoring stations. We then leverage graph neural networks to model the spatial correlation between the ground-based monitoring stations. Besides, recurrent neural networks are utilized to capture the data's temporal properties.
This study focuses on data mining regarding river discharge and water levels in Vietnam. We apply data preprocessing techniques such as SSA to clean the data before feeding it into the forecasting models. Furthermore, we propose novel deep learning models that employ ensemble learning techniques and graph neural networks to capture both temporal and spatial correlation and extract relevant information from historical data. Furthermore, optimization techniques like metaheuristics are used to obtain the optimal hyper-parameters automatically.
In this research, we study how to learn and predict networks’ future behavior dynamically. From that, we design algorithms to control the network operations efficiently and intelligently. Several research problems are taking into account, such as exploiting the Graph Neural Networks to capture the spatial relation of the network and then leveraging deep learning to predict the network traffic; using reinforcement learning to guide the packets; utilizing metaheuristic algorithms and linear programming to optimize the routing paths. We perform experiments on network simulators such as OMNET, NS2, and real datasets such as Brain, Abilene, and Geant.
With the progress of Artificial Intelligence, it is now possible to manage computer networks in a self-adaptive manner. This means that every network node will be an AI node capable of making decisions on its own. However, because these network nodes only have a limited view and control, applying Artificial Intelligence to each one is not straightforward. A centralized control architecture, such as a Software-defined Network (SDN), is an excellent option for this purpose. Therefore, we decide to build a knowledge layer on top of the SDN architecture in this project, resulting in a Knowledge-defined Network.
SDN raises the challenge of scalability with its physically centralized control. The only and potential solution is to transform it into physically distributed SDN control. However, this solution requires the interoperability between SDN controllers and the consistency of network state being distributed across these controllers. We propose an East-West interface, called SINA, to provide the interoperability of a heterogeneous and distributed SDN network. In addition, a novel Reinforcement Learning-based consistency algorithm is introduced for an adaptive Quorum-based replication mechanism.
We focus on a new wireless charging paradigm that considers a variety of factors such as charging path, charging time, target coverage, and connectivity. We considers multiple optimization goals, including minimizing the number of mobile chargers, optimizing the depot placement, and extending the network lifetime. We leverage reinforcement learning, deep reinforcement learning, fuzzy logic, genetic algorithms to propose novel charging algorithms for wireless rechargeable IoT networks.
Our People
Professor and PhD
Graduate Students
Talented Program - K62
Talented Program - K62
Talented Program - K62
Computer Science - K61
Master's Student - DS&AI
Master's Student - DS&AI
Undergraduates
Computer Science - K65
Computer Science - K64
HEDSPI - K64
Talented Program - K64
HEDSPI - K64
HEDSPI - K64
Computer Science - K63
Computer Science - K63
Talented Program - K63
HEDSPI - K63
HEDSPI - K63
Talented Program - K63
Talented Program - K63
Computer Science - K63
Computer Science - K63
Computer Science - K63
Computer Sicence - K63
HEDSPI - K63
Computer Science - K61
Alumni
Talented Program - K62
Talented Program - K61
Computer Science - K61
Talented Program - K61
HEDSPI - K61
HEDSPI - K61
Talented Program - K61
Talented Program - K61
HEDSPI - K61
HEDSPI - K61
HEDSPI - K61
Talented Program - K61
HEDSPI - K61
Publications
FY2021
Transaction Papers
Van Quan La, Anh Duy Nguyen, Thanh Hung Nguyen, Kien Nguyen, Phi Le Nguyen, "An On-demand Charging for Connected Target Coverage in WRSNs using Fuzzy Logic and Q-learning", MDPI Sensors, 21(16), 5520. (SCIMago Q2, IF: 3.576).
Phi Le Nguyen, Nang Hung Nguyen, Tuan Anh Nguyen Dinh, Khanh Le, Thanh Hung Nguyen, Kien Nguyen, "QIH: an Efficient Q-learning Inspired Hole-Bypassing Routing Protocol for WSNs", IEEE Access, Vol 4, 2021 (Scimago, Q1, IF: 3.36)
Tran Thi Huong, Le Van Cuong, Ngo Minh Hai, Phi Le Nguyen, Le Trong Vinh, Huynh Thi Thanh Binh, "A bi-level optimized charging algorithm for energy depletion avoidance in wireless rechargeable sensor networks", Applied Intelligence, 2021 (Accepted).
Phi Le Nguyen, Yusheng Ji, Minh Khiem Pham, Hieu Le, Thanh Hung Nguyen, “(1+epsilon)2- and Polynomial-Time Approximation Algorithms for Network Lifetime Maximization with Relay Hop Bounded Connected Target Coverage in WSNs”, IEEE Sensors Journal, 2021. (SCIMago Q1, IF: 3.037).
Kien Nguyen, Phi Le Nguyen, Li Zhe-tao, Hiroo Sekiya, "Empowering 5G Mobile Devices with Network Softwarization", IEEE Transactions on Network and Service Management, 2021 (SCIMagoQ1, IF: 4.1).
Minh Hieu Nguyen, Phi Le Nguyen, Kien Nguyen, Van An Le, Thanh-Hung Nguyen, Yusheng Ji, "PM2.5 Prediction Using Genetic Algorithm-based Feature Selection and Encoder-Decoder Model", IEEE Access, 2021 (SCIMagoQ1, IF: 3.7).
Van Nguyen, Chi-Hieu Nguyen, Phi Le Nguyen, Tien Van Do, Imrich Chlamtac, “Energy-efficient routing in the proximity of a complicated hole in wireless sensor networks”, Wireless Networks, 2021. (SCIMago Q2, IF: 2.357).
Refereed Proceedings
Thanh Thi-Hien Duong, Manh Nguyen Huu, Thi-Hai Nghiem, Thi-Lan Le, Phi Le Nguyen, Quoc-Cuong Nguyen, "Visual-guided audio source separation: an empirical study", MAPR 2021 (Accepted).
Do Bao Son, Vu Tri An, Trinh Thu Hai, Binh Minh Nguyen, Phi Le Nguyen, Huynh Thi Thanh Binh, “Fuzzy Deep Q-learning Task Offloading in Delay Constrained Vehicular Fog Computing”, International Joint Conference on Neural Network, IJCNN 2021.
Anh Duy Nguyen, Viet Hung Vu, Minh Hieu Nguyen, Duc Viet Hoang, Thanh Hung Nguyen, Kien Nguyen, Phi Le Nguyen, “Efficient Prediction of Discharge and WaterLevels Using Ensemble Learning andSingular-Spectrum Analysis-based Denoising”, The 34th International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems IEA/AIE 2021.
Van An Le, Tien Thanh Le, Phi Le Nguyen, Huynh Thi Thanh Binh, Rajendra Akerkar, Yusheng Ji, “GCRINT: Network Traffic Imputation Using Graph Convolutional Recurrent Neural Network”, IEEE International Conference on Communications (ICC2021), Virtual / Montreal.
Van An Le, Tien Thanh Le, Phi Le Nguyen, Huynh Thi Thanh Binh, Yusheng Ji, “Multi-time-step Segment Routing based Traffic Engineering Leveraging Traffic Prediction”, IFIP/IEEE International Symposium on Integrated Network Management (IM2021), Bordeaux, France.
Thanh Le-Cong, Xuan Bach Le D., Phi Le Nguyen and Quyet Thang Huynh, "Usability and Aesthetics: Better Together for Automated Repair of Web Pages", ISSRE 2021 (Accepted)
Thanh T. H. Duong, Phi Le Nguyen, Hong-Son Nguyen, Duc-Chien Nguyen, Huy Phan, Ngoc Q. K. Duong, "Speaker count: a new building block for speaker diarization", APSIPA 2021 (Accepted)
Viet An Nguyen, Viet Hung Vuy, Van Sang Doan, Thanh Hung Nguyen, Phan Thuan Do, Kien Nguyen, Phi Le Nguyen, Minh Thuy Le, "Realizing Mobile Air Quality Monitoring System: Architectural Concept and Device Prototype", Asia Pacific Conference on Communications (APCC) 2021 (Accepted).
Duc-Huy LE, Hai-Anh TRAN, and Sami SOUIHI, "A Reinforcement Learning-based solution for Intra-domain Egress Selection," IEEE International Conference on High Performance Switching and Routing (HPSR21). 01-06. Paris, France. 07 June 2021.
The-Anh Le, Quyet-Thang Huynh, Thanh-Hung Nguyen, "A New Method to Improve Quality Predicting of Software Project Completion Level," Industrial Networks and Intelligent Systems, INISCOM 2021. 211-219. Hanoi. 22 April 2021
Hai-Anh TRAN, Thi-Thanh-Tu NGUYEN, Sami SOUIHI, and Abdelhamid MELLOUK, "Towards a Novel Congestion Notification Algorithm for a Software-Defined Data Center Networks," IFIP/IEEE International Symposium on Integrated Network Management, 2021. 99-106. Bordeaux, France. 17 May 2021.
Duc-Huy LE, Hai-Anh TRAN, Sami SOUIHI, and Abdelhamid MELLOUK, "An AI-based Traffic Matrix Prediction Solution for Software-Defined Network," IEEE International Conference on Communications (ICC), 2021. 01-06. Online. 14 June 2021.
Viet An Nguyen, Viet Hung Vuy, Van Sang Doan, Thanh Hung Nguyen, Phan Thuan Do, Kien Nguyen, Phi Le Nguyen, Minh Thuy Le, "Realizing Mobile Air Quality Monitoring System: Architectural Concept and Device Prototype", Asia Pacific Conference on Communications 2021 (Accepted).
Trung Thanh Nguyen, Truong Thao Nguyen, Tuan Anh Nguyen Dinh, Thanh-Hung Nguyen, Phi Le Nguyen, "Q-learning-based Opportunistic Communication for Real-time Mobile Air Quality Monitoring Systems", 40th IEEE International Performance Computing and Communications Conference, IPCCC 2021 (accepted)
Nang Hung Nguyen, Phi Le Nguyen, Hieu Dinh, Thanh Hung Nguyen, Kien Nguyen, “Multi-Agent Multi-Armed Bandit Learning for Offloading Delay Minimization in V2X Networks”, IThe 19th IEEE international conference on embedded and ubiquitous computing (EUC 2021) (Accepted).
Tran Bao Hieu, Hoang Duc Viet, Nguyen Manh Hiep, Pham Ngoc Bao Anh, Nguyen Duc Anh, Hoang Gia Bao, Hai-Phong Bui, Thanh Hung Nguyen, Phi Le Nguyen, Thi-Lan Le, “MC-OCR Challenge 2021: A Multi-modalApproach for Mobile-Captured Vietnamese ReceiptsRecognition”, The 15th IEEE-RIVF International Conference on Computing and Communication Technologies, RIVF 2021 (Accepted).
News
2021
01.05
Le Anh Duc, Le Minh Quang, Do Dinh Dac were qualified for the ICPC World Final 2021 in Dhaka.
2021
01.07
Nguyen Minh Hieu, Vu Viet Hung, Nguyen Anh Duy, Nguyen Viet Huy, Pham Quoc Viet, Nguyen Thuy Dung won the first prize in IBM Hackathon (call4code track).
2021
01.07
Nguyen Trung Thanh, Pham Ngoc Bao Anh, Nguyen Manh Hiep, Hoang Duc Viet, Nguyen Nang Hung, Tran Huu Huy won the first prize in IBM Hackathon (open track).
2021
15.06
Le Anh Duc got the best presentation award nomination for the Bachelor thesis defense.
2021
15.06
Bui Hong Ngoc got the best presentation award nomination for the Bachelor thesis defense.
2021
01.06
Vu Viet Hung got the best presentation award nomination for the Bachelor thesis defense.
2021
01.06
Pham Minh Khiem got the best presentation award nomination for the Bachelor thesis defense.
2021
01.06
Dang Tran Quang got the best presentation award nomination for the Bachelor thesis defense.
2021
01.06
Tran Bao Hieu got the best presentation award nomination for the Bachelor thesis defense.
2021
01.05
Vu Viet Hung, Nguyen Anh Duy, Nguyen Viet Huy, Pham Quoc Viet, Nguyen Thuy Dung won the first prize in the student scientific research conference (HUST).
2021
01.05
Pham Minh Khiem, Nguyen Nang Hung, Nguyen Trung Thanh, Dinh Van Hieu, Nguyen Dinh Tuan Anh won the third prize in the student scientific research conference (HUST).
2021
22.04
Nguyen Minh Hieu, Nguyen Viet Dung, and Tran Thanh Tung won the best presentation award at DS&AI Summer school.
Back To Top