Mobile communication standards were developed for enhancing transmission and network performance by using more radio resources and improving spectrum and energy efficiency. How to effectively address diverse user requirements and guarantee everyone's Quality of Experience (QoE) remains an open problem. The Sixth Generation (6G) mobile systems will solve this problem by utilizing heterogenous network resources and pervasive intelligence to support everyone-centric customized services anywhere and anytime. In this article, we first coin the concept of Service Requirement Zone (SRZ) on the user side to characterize and visualize the integrated service requirements and preferences of specific tasks of individual users. On the system side, we further introduce the concept of User Satisfaction Ratio (USR) to evaluate the system's overall service ability of satisfying a variety of tasks with different SRZs. Then, we propose a network Artificial Intelligence (AI) architecture with integrated network resources and pervasive AI capabilities for supporting customized services with guaranteed QoEs. Finally, extensive simulations show that the proposed network AI architecture can consistently offer a higher USR performance than the cloud AI and edge AI architectures with respect to different task scheduling algorithms, random service requirements, and dynamic network conditions.
Mobile Crowd Sensing (MCS) has attracted extensive attention as a promising method for environmental sensing and data collection. However, due to the increasing computational tasks, bandwidth, and computing pressure, traditional “Cloud-Edge-End” MCS is insufficient to efficiently offload sensing data in real-time for data aggregation. Therefore, we consider a novel MCS framework based on the “Cloud-Enhanced-Edge-End”, the framework uses MCS idle users as edge nodes to assist edge servers to enhance computing power and reduce delay and energy consumption. To achieve efficient data aggregation in the “Cloud-Enhanced-Edge-End” MCS framework, we first consider the multi-objective optimization of delay and energy consumption to establish a utility function. Secondly, addressing the shortcomings of traditional optimization algorithms, which often struggle with complex decision spaces and dynamic environments, we propose a Mobile Crowd Sensing Offloading (MCSOL) algorithm based on Deep Q-Network (DQN). The algorithm uses reinforcement learning to adaptively offload computing tasks to the optimal edge nodes or servers to maximize utility function to reduce delay and energy consumption. Our experimental results reveal that, in comparison with the other five strategies like only offloading data to base stations and edge nodes, MCSOL enhances data aggregation performance within the range of 30%-60%.
In mobile crowd sensing (MCS), complex tasks often require collaboration among multiple workers with diverse expertise and sensors. However, few studies consider the sensing time redundancy of multiple workers to complete a task collaboratively, and the subjective and objective collaboration willingness of participating workers in forming collaboration groups for different tasks. If solely focusing on enhancing workers’ willingness to collaborate, it cannot guarantee the minimum time redundancy within the collaboration group, resulting in a decrease in the group’s efficiency. Similarly, if only aiming to reduce sensing time redundancy among the workers in the collaboration group, it may lead to a loss of workers’ willingness to collaborate, and the diminished motivation among workers will consequently reduce the group’s efficiency. To address these challenges, this paper proposes EGC-STRO, a method for forming efficient collaboration groups in MCS that optimizes sensing time redundancy while balancing the workers’ cooperation willingness as constraints. First, this method proposes an evaluation indicator to select workers who meet their reward expectations, i.e., objective collaboration willingness, and uses an incentive mechanism based on bargaining game to maximize the overall interests. Furthermore, subjective collaboration willingness is defined and a collaboration worker selection algorithm is designed. The algorithm adds workers who meet both subjective and objective willingness requirements to the candidate set and selects workers with the smallest sensing redundancy time in the worker candidate set to join the final collaboration group. Simulation results demonstrate that compared with the baseline methods, our proposed EGC-STRO increases the worker engagement by about 5%-20%, increases the task coverage by 6%-25%, increases the platform utility by 17%-50%, and increases the worker utility by 20%-60%.
16 July 2021 in IEEE Open Journal of the Computer Society
The massive data generated by large-scale dynamic systems makes its optimization facing a tough challenge. Traditional White Box-based methods directly model the internal operating mechanism of the system, so massive amounts of measured data need to be handled, which is costly and time-consuming. The poor interpretability of the Black Box-based methods makes it difficult to adapt to the dynamic environment. Thus we propose a novel Gray Box-based approach namely Deep Reinforcement Learning-enabled Constraint Set Inversion Algorithm (DRESIA), which establishes a quantitative model of the nonlinear interoperability effects of system internal states which simplifies the White Box's complex mechanism of reconstruction and prediction and retains the interpretability of the model, therefore improves the prediction efficiency of feasible region while also improving the generalization ability. It further improves the dynamic adaptability of the modeling environment, which provides a new performance balancing scheme for system modeling. Under the premise that the large-scale 5G Cyber-Twin system satisfies the given Quality of Service (QoS) requirements, we perform DRESIA to realize the efficient and dynamic optimal search of feasible region, the results show that the DRESIA reduces the computational cost, and balances the accuracy and robustness of the feasible region, which validate the effectiveness and superiority of Gray Box-based approach.
The electronic health record (EHR) surveillance process relies on wireless security administered in application technology, such as the Internet of Things (IoT). Automated supervision with cutting-edge data analysis methods may be a viable strategy to enhance treatment in light of the increasing accessibility of medical narratives in the electronic health record. EHR analysis structured data structure code was used to obtain data on initial fatality risk, infection rate, and hazard ratio of death from EHRs for prediction of unexpected deaths. Patients utilizing EHRs in general must keep in mind the significance of security. With the rise of the IoT and sensor-based Healthcare 4.0, cyber-resilience has emerged as a need for the safekeeping of patient information across all connected devices. Security for access, amendment, and storage is cumulatively managed using the common paradigm. For improving the security of surveillance in the aforementioned services, this article introduces an endorsed joint security scheme (EJSS). This scheme recognizes the EHR utilization based on the aforementioned processes. For each process, different security measures are administered for sustainable security. Access control and storage modification require relative security administered using mutual key sharing between the accessing user and the EHR database. In this process, the learning identifies the variations in different processes for reducing adversarial interruption. The federated learning paradigm employed in this scheme identifies concurrent adversaries in the different processes initiated at the same time. Differentiating the adversaries under each process strengthens mutual authentication using individual attributes. Therefore, individual surveillance efficiency through log inspection and adversary detection is improved for heterogeneous and large-scale EHR databases.
30 September 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Speech synthesis systems powered by neural networks hold promise for multimedia production, but frequently face issues with producing expressive speech and seamless editing. In response, we present the Cross-Utterance Conditioned Variational Autoencoder speech synthesis (CUC-VAE S2) framework to enhance prosody and ensure natural speech generation. This framework leverages the powerful representational capabilities of pre-trained language models and the re-expression abilities of variational autoencoders (VAEs). The core component of the CUC-VAE S2 framework is the cross-utterance CVAE, which extracts acoustic, speaker, and textual features from surrounding sentences to generate context-sensitive prosodic features, more accurately emulating human prosody generation. We further propose two practical algorithms tailored for distinct speech synthesis applications: CUC-VAE TTS for text-to-speech and CUC-VAE SE for speech editing. The CUC-VAE TTS is a direct application of the framework, designed to generate audio with contextual prosody derived from surrounding texts. On the other hand, the CUC-VAE SE algorithm leverages real mel spectrogram sampling conditioned on contextual information, producing audio that closely mirrors real sound and thereby facilitating flexible speech editing based on text such as deletion, insertion, and replacement. Experimental results on the LibriTTS datasets demonstrate that our proposed models significantly enhance speech synthesis and editing, producing more natural and expressive speech.