Article
Engineering, Electrical & Electronic
Fariha Afsana, Manoranjan Paul, Manzur Murshed, David Taubman
Summary: This paper proposes a novel intra and inter-frame coding scheme to improve the compression efficiency of SHVC. By separating the common/visually important information and applying cuboid-based variable size block partitioning and coding process, the proposed method achieves better coding efficiency.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Qing Li, Ying Chen, Aoyang Zhang, Yong Jiang, Longhao Zou, Zhimin Xu, Gabriel-Miro Muntean
Summary: This paper proposes a flexible super-resolution-based video coding and uploading framework to improve the quality of live video streaming in limited uplink network bandwidth conditions. By employing a flexible video coding scheme and bitrate adaptation algorithm, the framework reduces the required bandwidth while maintaining video quality, thereby enhancing users' Quality of Experience.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Green & Sustainable Science & Technology
Muhammad Hamza Bin Waheed, Faisal Jamil, Amir Qayyum, Harun Jamil, Omar Cheikhrouhou, Muhammad Ibrahim, Bharat Bhushan, Habib Hmam
Summary: The demand for multimedia content over the Internet protocol network is growing with the increase of Internet users, making Quality of Experience (QoE) a primary concern. This article proposes a design to distribute and cache multimedia content effectively, with experiments and statistical analysis conducted to evaluate factors impacting QoE. The impact of network infrastructure and video delivery methods on QoE is significant, with the use of specialized Content Delivery Networks (CDNs) aiming to improve overall efficiency.
Article
Engineering, Electrical & Electronic
Hengrun Zhao, Bolun Zheng, Shanxin Yuan, Hua Zhang, Chenggang Yan, Liang Li, Gregory Slabaugh
Summary: This study proposes a model based on neural networks to enhance the quality of CBR compressed videos. By utilizing a dual-domain restoration module and a two-step quantization degradation estimation strategy, the degradation caused by compression is effectively reduced, while a multi-scale network is employed to address block distortion. The experimental results demonstrate that this method outperforms existing approaches in both CBR and CQP video enhancement tasks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Nuowen Kan, Junni Zou, Chenglin Li, Wenrui Dai, Hongkai Xiong
Summary: This paper proposes a tile-based rate adaptation strategy called RAPT360 for adaptive 360-degree video streaming. It uses reinforcement learning to dynamically learn the optimal bitrate allocation of tiles, aiming to improve the quality of experience (QoE) under constrained network conditions.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
G. Esakki, A. S. Panayides, V Jalta, M. S. Pattichis
Summary: The study focuses on transforming video encoding into a multi-objective optimization process and jointly optimizing video quality, bitrate demands, and encoding rate. It creates a dense video encoding space and uses regression to generate forward prediction models. The adaptive video encoding approach is demonstrated for real-time adaptation with different codecs.
Article
Computer Science, Information Systems
Duc Nguyen, Nguyen Viet Hung, Nguyen Tien Phong, Truong Thu Huong, Truong Cong Thang
Summary: A novel framework is proposed in this paper for live 360-degree video streaming to multiple users over mobile networks, utilizing Scalable Video Coding and multicast. The framework splits 360-degree video into tiles, each encoded into multiple layers, to maximize the overall Quality of Experience for users. Experimental results show significant improvement in viewport quality compared to state-of-the-art methods.
Article
Computer Science, Information Systems
Guanghui Zhang, Jie Zhang, Yan Liu, Haibo Hu, Jack Y. B. Lee, Vaneet Aggarwal
Summary: Video streaming has become a major application on the Internet, but existing algorithms fail to efficiently improve Quality-of-Experience (QoE) due to the differing preferences of viewers. This study introduces a new framework called Post Streaming Quality Analysis (PSQA) to automatically tune streaming algorithms and maximize QoE under any preference. Evaluation results demonstrate that the PSQA significantly outperforms existing approaches and even achieves near-optimal performance in some scenarios. Additionally, the PSQA can be easily implemented into real streaming platforms, providing a practical and reliable solution for high-performance streaming services.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Qi Jiang, Victor C. M. Leung, Hao Tang
Summary: This article presents an adaptive modulation and coding scheme to provide quality of service (QoS) in wireless scalable video multicast. An adaptive policy iteration algorithm is developed to find the optimal modulation and coding policy online without any prior knowledge of users' channel statistics or intensive calculations. The proposed scheme demonstrates its effectiveness through simulation results.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Eliecer Pena-Ancavil, Claudio Estevez, Andres Sanhueza, Marcos Orchard
Summary: ASViS is a scalable video streaming protocol that addresses buffering issues in DASH by incorporating scalable video coding, flow-controlled UDP, and deadline-based criteria. It adjusts data flow and discards outdated information to provide more consistent and higher-quality video streaming.
Article
Engineering, Electrical & Electronic
Zongju Peng, Fen Chen, Dongrong Jiang, Chao Huang, Gangyi Jiang, Mei Yu, Jinlong Li
Summary: In this paper, a bit allocation algorithm is proposed for the enhancement layer in SHVC, which aims to improve video coding performance by optimizing bit allocation for both initial and subsequent frames. The experimental results show that the proposed algorithm outperforms state-of-the-art algorithms in terms of PSNR improvement and bitrate control accuracy.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Engineering, Electrical & Electronic
Liqiang He, Xiaohai He, Shuhua Xiong, Zeming Zhao, Hang Xiao, Honggang Chen
Summary: Despite the superior coding performance of Versatile Video Coding (VVC), the rate control (RC) model still faces two major problems. The deviation between the target bit allocation strategy in RC and the human visual attention mechanism (HVAM) results in unclear regions of interest in the coded video. Additionally, inappropriate updating speed leads to significant quality fluctuations in the coded video frames. To address these issues, an efficient rate control (ERC) model is proposed, which extracts spatial-temporal information and utilizes an adaptive parameter updating (APU) method. The ERC outperforms the default RC model of VVC Test Model (VTM) 9.1 in terms of bitrate accuracy, saving the average Bjontegaard Delta Rate (BD-Rate) by 3.60% and 4.94% under different configurations.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Shuoyao Wang, Suzhi Bi, Ying-Jun Angela Zhang
Summary: In this paper, we propose an online joint transcoding and transmission resource allocation algorithm for a heterogeneous multi-user MEC-enabled video streaming network with time-varying wireless channels. The algorithm maximizes the QoE of ABR streaming users while considering bandwidth and CPU constraints. By introducing queueing model constraints and decoupling the multi-stage problem, we propose a low-complexity online algorithm that provides additional QoE compared to state-of-the-art approaches.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Sheng Cheng, Han Hu, Xinggong Zhang
Summary: This article proposes ABRF, a QoE-oriented adaptive bitrate-FEC joint control algorithm. ABRF predicts the network loss pattern in the future and calculates the optimal bitrate-FEC decision based on a QoE model for real-time video streaming. Moreover, ABRF is equipped with a fast adaptation method to generalize across diverse network environments.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Xiaobin Tan, Lei Xu, Jiawei Ni, Simin Li, Xiaofeng Jiang, Quan Zheng
Summary: A game theory based NDN Adaptive Bitrate algorithm is proposed to achieve proactive aggregation of requests in multi-client scenarios, reducing repeated traffic and achieving fairness through Bayesian Nash Equilibrium. The algorithm outperforms existing solutions in terms of Quality of Experience, fairness and network bandwidth utilization in simulation and real-world experiments.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Hardware & Architecture
Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolo Michelusi, Vaneet Aggarwal, David J. Love, Huaiyu Dai
Summary: This paper proposes a multi-stage hybrid federated learning (MH-FL) method, extending the traditional federated learning topology through the network dimension and considering a multi-layer cluster-based structure. The research results demonstrate the advantages of MH-FL in terms of resource utilization metrics.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2022)
Article
Computer Science, Information Systems
Guanghui Zhang, Jie Zhang, Ke Liu, Jing Guo, Jack Y. B. Lee, Haibo Hu, Vaneet Aggarwal
Summary: Fueled by emerging short video applications, streaming short-form videos has become ubiquitous among mobile users. However, frequent video switching results in significant data loss, which is financially burdensome for both users and vendors. To tackle this problem, this study proposes a novel system called DUASVS, which uses integrated learning to capture network conditions and trains intelligent adaptation models to reduce data loss and save data usage.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Guanghui Zhang, Ke Liu, Haibo Hu, Vaneet Aggarwal, Jack Y. B. Lee
Summary: This work investigates the issue of data wastage in mobile video streaming, where downloaded video data that is not played back is discarded, resulting in wasted bandwidth. The study shows significant data wastage in practice and proposes a new framework called PSWA to tackle this problem. PSWA can reduce data wastage by 80% without impacting user experience and is robust across different network environments.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Nan Geng, Qinbo Bai, Chenyi Liu, Tian Lan, Vaneet Aggarwal, Yuan Yang, Mingwei Xu
Summary: This paper proposes a holistic framework for reinforcement learning-based vehicular network routing, which satisfies both peak and average constraints. The routing problem is modeled as a Constrained Markov Decision Process and is solved by an extended Q-learning algorithm based on Constraint Satisfaction Problems. The framework is further decentralized using a cluster-based learning structure. Simulation results show that the proposed algorithm achieves significant improvement in average transmission rate and does not violate any constraints.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Divija Swetha Gadiraju, V. Lalitha, Vaneet Aggarwal
Summary: Blockchains have shown high levels of security and reliability in various applications. Prism is a new blockchain algorithm that achieves maximum throughput and minimal latency without compromising security. This study applies Deep Reinforcement Learning (DRL) to optimize the performance of Prism and proposes a DRL-based Prism Blockchain (DRLPB) scheme. Two widely used DRL algorithms, Dueling Deep Q Networks (DDQN) and Proximal Policy Optimization (PPO), are applied in DRLPB to compare their performance. The DRLPB scheme enhances the number of votes by up to 84% compared to Prism, while maintaining the security and latency performance guarantees.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Chang-Lin Chen, Christopher G. Brinton, Vaneet Aggarwal
Summary: In this work, a novel methodology is proposed to optimize communication, computation, and caching configurations in mobile edge computing (MEC) systems, aiming at minimizing the mean latency of mobile devices. The transmission and computation processes are modeled using M/G/1 queues, considering service rates and warm-up times. The caching scheme includes time variables for each file at each edge server to determine when to discard files from storage. Theoretical analysis is conducted to examine the impact of communication, computation, and caching on the latency experienced by mobile devices in MEC systems, incorporating offloading decisions, resource allocation, and expiration times of files.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Guanghui Zhang, Jie Zhang, Yan Liu, Haibo Hu, Jack Y. B. Lee, Vaneet Aggarwal
Summary: Video streaming has become a major application on the Internet, but existing algorithms fail to efficiently improve Quality-of-Experience (QoE) due to the differing preferences of viewers. This study introduces a new framework called Post Streaming Quality Analysis (PSQA) to automatically tune streaming algorithms and maximize QoE under any preference. Evaluation results demonstrate that the PSQA significantly outperforms existing approaches and even achieves near-optimal performance in some scenarios. Additionally, the PSQA can be easily implemented into real streaming platforms, providing a practical and reliable solution for high-performance streaming services.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Hanhan Zhou, Tian Lan, Vaneet Aggarwal
Summary: This paper presents a new training framework called LSF-SAC, which utilizes a variational inference-based information-sharing mechanism to assist individual agents in value function factorization. The evaluation on the StarCraft II micromanagement benchmark demonstrates that LSF-SAC outperforms several state-of-the-art methods in collaborative tasks.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Abhishek K. K. Umrawal, Christopher J. J. Quinn, Vaneet Aggarwal
Summary: We propose a novel approach to the Influence Maximization problem that takes into account the community structure of social networks. Our experiments show that our approach outperforms standard methods in terms of run-time and heuristic methods in terms of influence. We also find that higher modularity in community structures leads to better performance of our approach in terms of run-time and influence.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Article
Computer Science, Hardware & Architecture
Bhargav Ganguly, Vaneet Aggarwal
Summary: Federated Learning (FL) is a new emerging domain in AI research, aiming to achieve optimal global model with restricted data sharing. However, most existing FL literature assumes stationary data, which is unrealistic in real-world conditions where concept drift occurs. This paper proposes a multiscale algorithmic framework combining theoretical guarantees of FedAvg and FedOMD algorithms with non-stationary detection and adaptation techniques to improve FL generalization performance in the presence of concept drifts.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Hardware & Architecture
Seyyedali Hosseinalipour, Su Wang, Nicolo Michelusi, Vaneet Aggarwal, Christopher G. Brinton, David J. Love, Mung Chiang
Summary: In this paper, we propose parallel successive learning (PSL) to expand the architecture of federated learning in terms of network, heterogeneity, and proximity. PSL considers decentralized cooperation among devices, heterogeneous learning and data environments, and devices with different capabilities. We also analyze the concepts of cold vs. warmed up models and propose a network-aware dynamic model tracking method to optimize the tradeoff between model learning and resource efficiency. Our numerical results reveal new insights on the interdependencies between idle times, model/concept drift, and D2D cooperation configuration.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Hardware & Architecture
Bhargav Ganguly, Seyyedali Hosseinalipour, Kwang Taik Kim, Christopher G. Brinton, Vaneet Aggarwal, David J. Love, Mung Chiang
Summary: We propose a cooperative edge-assisted dynamic federated learning (CE-FL) approach. CE-FL introduces a distributed machine learning (ML) architecture, where data collection is carried out at the end devices, while the model training is conducted cooperatively at the end devices and the edge servers, enabled via data offloading from the end devices to the edge servers through base stations. CE-FL also introduces a floating aggregation point, where the local models generated at the devices and the servers are aggregated at an edge server, which varies from one model training round to another to cope with the network evolution in terms of data distribution and users' mobility.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Engineering, Biomedical
Glebys Gonzalez, Mythra Balakuntala, Mridul Agarwal, Tomas Low, Bruce Knoth, Andrew W. W. Kirkpatrick, Jessica McKee, Gregory Hager, Vaneet Aggarwal, Yexiang Xue, Richard Voyles, Juan Wachs
Summary: Telesurgery in remote and disadvantaged areas is hindered by communication infrastructure limitations. To address communication delays, a semi-autonomous system is introduced to separate user interaction from robot execution. Using a physics-based simulator, surgeons can demonstrate surgical tasks with immediate feedback, while a recognition module extracts intended actions. The system showed robustness to delays, maintaining high performance rates and reducing completion time.
IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS
(2023)
Article
Optics
Dheeraj Peddireddy, Utkarsh Priyam, Vaneet Aggarwal
Summary: This research proposes an improved VQE algorithm by utilizing a classical gradient computation method that uses tensor-ring approximation. By truncating singular values and preserving the structure of the tensor ring, this method allows for faster evaluation of gradients on classical simulators, addressing the scalability challenge of VQE.
Article
Mathematics
Vaneet Aggarwal, Rakhi Pratihar
Summary: This paper investigates the constructions and limitations of insertion and deletion (insdel) codes, and connects them with rank metric and subspace codes. The research reveals that subspace codes are a suitable choice for constructing insdel codes, and shows that interleaved Gabidulin codes can be used to construct nonlinear insdel codes. Additionally, the indexing scheme for transforming efficient Hamming metric codes is adapted for rank metric codes, improving the base field size of insdel code constructions. It is also demonstrated that the size of insdel codes from subspace codes can be significantly improved compared to previous constructions. The paper provides an algebraic condition for a linear Gabidulin rank metric code to be an optimal insdel code, adapting the condition proved for Reed-Solomon codes. Moreover, constructions of both linear and nonlinear insdel codes from Sidon spaces are presented.
DISCRETE MATHEMATICS
(2024)
