Search

The advent of the digital era has profoundly transformed marketing and variousorganizational functions, largely driven by the accessibility to vast repositories ofdigitized data and the integration of artificial intelligence (AI). The purpose of this studyis to examine the impact of artificial intelligence-driven personalization on customerexperience within the context of TikTok, a leading social media platform known for itsinnovative use of AI technology. TikTok leverages AI to analyze user behaviors andpreferences, delivering tailored content that enhances user engagement and satisfaction.The deductive approach is the selected approach to fulfill this study is objective.Particularly, the research hypothesis (H1) posits that AI-driven personalization positivelyinfluences customer experience on TikTok. To test this hypothesis, we conducted aquantitative study involving structured questionnaires distributed to a diverse sample ofTikTok users via social media platforms, resulting in 365 usable answers. The findingsconfirm a significant positive relationship between AI-driven personalization andcustomer experience, underscoring the critical role of AI in shaping user interactions andexperiences on social media platforms - TikTok. This study contributes to the literatureon digital marketing and customer experience management by highlighting theeffectiveness of AI-driven personalization in fostering engagement and satisfaction.

The advent of the digital era has profoundly transformed marketing and variousorganizational functions, largely driven by the accessibility to vast repositories ofdigitized data and the integration of artificial intelligence (AI). The purpose of this studyis to examine the impact of artificial intelligence-driven personalization on customerexperience within the context of TikTok, a leading social media platform known for itsinnovative use of AI technology. TikTok leverages AI to analyze user behaviors andpreferences, delivering tailored content that enhances user engagement and satisfaction.The deductive approach is the selected approach to fulfill this study is objective.Particularly, the research hypothesis (H1) posits that AI-driven personalization positivelyinfluences customer experience on TikTok. To test this hypothesis, we conducted aquantitative study involving structured questionnaires distributed to a diverse sample ofTikTok users via social media platforms, resulting in 365 usable answers. The findingsconfirm a significant positive relationship between AI-driven personalization andcustomer experience, underscoring the critical role of AI in shaping user interactions andexperiences on social media platforms - TikTok. This study contributes to the literatureon digital marketing and customer experience management by highlighting theeffectiveness of AI-driven personalization in fostering engagement and satisfaction.

In actor-critic framework for fully decentralized multi-agent reinforcement learning (MARL), one of the key components is the MARL policy evaluation (PE) problem, where a set of $N$ agents work cooperatively to evaluate the value function of the global states for a given policy through communicating with their neighbors. In MARL-PE, a critical challenge is how to lower the sample and communication complexities, which are defined as the number of training samples and communication rounds needed to converge to some $\epsilon$-stationary point. To lower communication complexity in MARL-PE, a "natural'' idea is to perform multiple local TD-update steps between each consecutive rounds of communication to reduce the communication frequency. However, the validity of the local TD-update approach remains unclear due to the potential "agent-drift'' phenomenon resulting from heterogeneous rewards across agents in general. This leads to an interesting open question: Can the local TD-update approach entail low sample and communication complexities? In this paper, we make the first attempt to answer this fundamental question. We focus on the setting of MARL-PE with average reward, which is motivated by many multi-agent network optimization problems. Our theoretical and experimental results confirm that allowing multiple local TD-update steps is indeed an effective approach in lowering the sample and communication complexities of MARL-PE compared to consensus-based MARL-PE algorithms. Specifically, the local TD-update steps between two consecutive communication rounds can be as large as $\mathcal{O}(1/\epsilon^{1/2}\log{(1/\epsilon)})$ in order to converge to an $\epsilon$-stationary point of MARL-PE. Moreover, we show theoretically that in order to reach the optimal sample complexity, the communication complexity of local TD-update approach is $\mathcal{O}(1/\epsilon^{1/2}\log{(1/\epsilon)})$., Comment: Main body of the paper appeared in AAMAS24

Federated Learning (FL) offers a distributed framework to train a global control model across multiple base stations without compromising the privacy of their local network data. This makes it ideal for applications like wireless traffic prediction (WTP), which plays a crucial role in optimizing network resources, enabling proactive traffic flow management, and enhancing the reliability of downstream communication-aided applications, such as IoT devices, autonomous vehicles, and industrial automation systems. Despite its promise, the security aspects of FL-based distributed wireless systems, particularly in regression-based WTP problems, remain inadequately investigated. In this paper, we introduce a novel fake traffic injection (FTI) attack, designed to undermine the FL-based WTP system by injecting fabricated traffic distributions with minimal knowledge. We further propose a defense mechanism, termed global-local inconsistency detection (GLID), which strategically removes abnormal model parameters that deviate beyond a specific percentile range estimated through statistical methods in each dimension. Extensive experimental evaluations, performed on real-world wireless traffic datasets, demonstrate that both our attack and defense strategies significantly outperform existing baselines., Comment: Accepted by IFIP/IEEE Networking 2024

In recent years, the complexity of 5G and beyond wireless networks has escalated, prompting a need for innovative frameworks to facilitate flexible management and efficient deployment. The concept of digital twins (DTs) has emerged as a solution to enable real-time monitoring, predictive configurations, and decision-making processes. While existing works primarily focus on leveraging DTs to optimize wireless networks, a detailed mapping methodology for creating virtual representations of network infrastructure and properties is still lacking. In this context, we introduce VH-Twin, a novel time-series data-driven framework that effectively maps wireless networks into digital reality. VH-Twin distinguishes itself through complementary vertical twinning (V-twinning) and horizontal twinning (H-twinning) stages, followed by a periodic clustering mechanism used to virtualize network regions based on their distinct geological and wireless characteristics. Specifically, V-twinning exploits distributed learning techniques to initialize a global twin model collaboratively from virtualized network clusters. H-twinning, on the other hand, is implemented with an asynchronous mapping scheme that dynamically updates twin models in response to network or environmental changes. Leveraging real-world wireless traffic data within a cellular wireless network, comprehensive experiments are conducted to verify that VH-Twin can effectively construct, deploy, and maintain network DTs. Parametric analysis also offers insights into how to strike a balance between twinning efficiency and model accuracy at scale., Comment: Accepted by IFIP/IEEE Networking 2024

To fully suppress the current harmonics of torque plane and zero-sequence dimension in open-end winding (OW) permanent-magnet synchronous motor (PMSM), a novel 3-D space vector pulsewidth modulation (SVPWM) strategy is proposed in this article. First, the distribution of 3-D space vectors is analyzed. Then, a subspace-based vector selection method is developed to utilize the adjacent vectors in space to synthesize the reference vector. On this basis, a repetitive controller is equipped for zero-sequence current to guarantee precise current tracking. By using the proposed 3D-SVPWM strategy, the current controls in 3D can be well balanced. Besides, the fault-tolerant control of open-phase fault in OW PMSM drive is realized with the proposed 3D-SVPWM strategy by simply changing zero-sequence current reference. The experiments are carried out to prove the effectiveness of the proposed strategy.

Damages within asphalt have been interesting phenomena in asphalt engineering, the detection of which is significant for maintenance of road sections. This project focuses on cracks and delaminations. An attempt was made to filter radar image data with a method based on a VNA-antenna-multilayered system model as well as the data from two specific measurements, aiming at better visualizing cracks as well as other features in radar image, and the results were checked and analysed. This part of work has provided an application of the aforementioned method of radar image data filtering as well as the points worth noticing and avoiding when making this application. For delaminations, machine learning algorithms, first the EM algorithm and then the YOLO v3 algorithm, were used as an attempt to highlight and detect them. Though the results still need improving, it is still valuable that the workload for human intervention can be alleviated with the help of these algorithms and that better performance can be expected based on current work, with the increasing amount of data with high quality achieved in the future., Applied Geophysics | IDEA League

Damages within asphalt have been interesting phenomena in asphalt engineering, the detection of which is significant for maintenance of road sections. This project focuses on cracks and delaminations. An attempt was made to filter radar image data with a method based on a VNA-antenna-multilayered system model as well as the data from two specific measurements, aiming at better visualizing cracks as well as other features in radar image, and the results were checked and analysed. This part of work has provided an application of the aforementioned method of radar image data filtering as well as the points worth noticing and avoiding when making this application. For delaminations, machine learning algorithms, first the EM algorithm and then the YOLO v3 algorithm, were used as an attempt to highlight and detect them. Though the results still need improving, it is still valuable that the workload for human intervention can be alleviated with the help of these algorithms and that better performance can be expected based on current work, with the increasing amount of data with high quality achieved in the future., Applied Geophysics | IDEA League