Yan-Ann Chen

Muhammad Abu Bakar, Yu-Ting Tsai, Muhammad Imran et al.

In virtual reality, it is challenging to achieve satisfactory text entry speed/accuracy, ergonomics, usability, and learnability. To address this issue, we developed ErgoGlide, a novel lightweight and compact wearable device that facilitates text entry tasks in virtual environments. The proposed ErgoGlide can be regarded as a small trackball that is wearable on a user's finger like a ring. By using ErgoGlide with a hive-like virtual keyboard, the user can rotate the ball for key selections, making text entry intuitive and accurate. We conducted three user studies to evaluate ErgoGlide and found that key confirmation techniques have significant effects on text entry speed and the hive-like keyboard design significantly reduced thumb movements. Furthermore, ErgoGlide can significantly improve typing accuracy, ergonomics, and usability over previous text entry methods. Experimental results also indicated that the typing speed of ErgoGlide can be notably improved after training.

Ming-Lun Lee, Fu-Shiang Yang, Cheng-Kuan Lin et al.

Federated learning (FL) enables clients to collaboratively train a shared model in a distributed manner, setting it apart from traditional deep learning paradigms. However, most existing FL research assumes consistent client participation, overlooking the practical scenario of dynamic participation (DPFL), where clients may intermittently join or leave during training. Moreover, no existing benchmarking framework systematically supports the study of DPFL-specific challenges. In this work, we present the first open-source framework explicitly designed for benchmarking FL models under dynamic client participation. Our framework provides configurable data distributions, participation patterns, and evaluation metrics tailored to DPFL scenarios. Using this platform, we benchmark four major categories of widely adopted FL models and uncover substantial performance degradation under dynamic participation. To address these challenges, we further propose Knowledge-Pool Federated Learning (KPFL), a generic plugin that maintains a shared knowledge pool across both active and idle clients. KPFL leverages dual-age and data-bias weighting, combined with generative knowledge distillation, to mitigate instability and prevent knowledge loss. Extensive experiments demonstrate the significant impact of dynamic participation on FL performance and the effectiveness of KPFL in improving model robustness and generalization.

Ming-Lun Lee, Han-Chang Chou, Yan-Ann Chen

Federated learning is a distributed machine learning framework to collaboratively train a global model without uploading privacy-sensitive data onto a centralized server. Usually, this framework is applied to edge devices such as smartphones, wearable devices, and Internet of Things (IoT) devices which closely collect information from users. However, these devices are mostly battery-powered. The update procedure of federated learning will constantly consume the battery power and the transmission bandwidth. In this work, we propose an update control for federated learning, FedSAUC, by considering the similarity of users' behaviors (models). At the server side, we exploit clustering algorithms to group devices with similar models. Then we select some representatives for each cluster to update information to train the model. We also implemented a testbed prototyping on edge devices for validating the performance. The experimental results show that this update control will not affect the training accuracy in the long run.

Wei-Chia Chang, Yan-Ann Chen

Vehicle make and model recognition (VMMR) is an important task in intelligent transportation systems, but existing approaches struggle to adapt to newly released models. Contrastive Language-Image Pretraining (CLIP) provides strong visual-text alignment, yet its fixed pretrained weights limit performance without costly image-specific finetuning. We propose a pipeline that integrates vision language models (VLMs) with Retrieval-Augmented Generation (RAG) to support zero-shot recognition through text-based reasoning. A VLM converts vehicle images into descriptive attributes, which are compared against a database of textual features. Relevant entries are retrieved and combined with the description to form a prompt, and a language model (LM) infers the make and model. This design avoids large-scale retraining and enables rapid updates by adding textual descriptions of new vehicles. Experiments show that the proposed method improves recognition by nearly 20% over the CLIP baseline, demonstrating the potential of RAG-enhanced LM reasoning for scalable VMMR in smart-city applications.

Yan-Ann Chen, Guan-Lin Chen

Federated learning is a novel decentralized learning architecture. During the training process, the client and server must continuously upload and receive model parameters, which consumes a lot of network transmission resources. Some methods use clustering to find more representative customers, select only a part of them for training, and at the same time ensure the accuracy of training. However, in federated learning, it is not trivial to know what the number of clusters can bring the best training result. Therefore, we propose to dynamically adjust the number of clusters to find the most ideal grouping results. It may reduce the number of users participating in the training to achieve the effect of reducing communication costs without affecting the model performance. We verify its experimental results on the non-IID handwritten digit recognition dataset and reduce the cost of communication and transmission by almost 50% compared with traditional federated learning without affecting the accuracy of the model.

Yu-Lin Kuo, Yu-Chee Tseng, Ting-Hui Chiang et al.

WiFi fingerprint-based localization has been studied intensively. Point-based solutions rely on position annotations of WiFi fingerprints. Trajectory-based solutions, however, require end-position annotations of WiFi trajectories, where a WiFi trajectory is a multivariate time series of signal features. A trajectory dataset is much larger than a pointwise dataset as the number of potential trajectories in a field may grow exponentially with respect to the size of the field. This work presents a semi-self representation learning solution, where a large dataset $C$ of crowdsourced unlabeled WiFi trajectories can be automatically labeled by a much smaller dataset $\tilde C$ of labeled WiFi trajectories. The size of $\tilde C$ only needs to be proportional to the size of the physical field, while the unlabeled $C$ could be much larger. This is made possible through a novel ``cut-and-flip'' augmentation scheme based on the meet-in-the-middle paradigm. A two-stage learning consisting of trajectory embedding followed by endpoint embedding is proposed for the unlabeled $C$. Then the learned representations are labeled by $\tilde C$ and connected to a neural-based localization network. The result, while delivering promising accuracy, significantly relieves the burden of human annotations for trajectory-based localization.

Fang-Jing Wu, Matthias R. Brust, Yan-Ann Chen et al.

Mobile location-based services (LBSs) empowered by mobile crowdsourcing provide users with context-aware intelligent services based on user locations. As smartphones are capable of collecting and disseminating massive user location-embedded sensing information, privacy preservation for mobile users has become a crucial issue. This paper proposes a metric called privacy exposure to quantify the notion of privacy, which is subjective and qualitative in nature, in order to support mobile LBSs to evaluate the effectiveness of privacy-preserving solutions. This metric incorporates activity coverage and activity uniformity to address two primary privacy threats, namely activity hotspot disclosure and activity transition disclosure. In addition, we propose an algorithm to minimize privacy exposure for mobile LBSs. We evaluate the proposed metric and the privacy-preserving sensing algorithm via extensive simulations. Moreover, we have also implemented the algorithm in an Android-based mobile system and conducted real-world experiments. Both our simulations and experimental results demonstrate that (1) the proposed metric can properly quantify the privacy exposure level of human activities in the spatial domain and (2) the proposed algorithm can effectively cloak users' activity hotspots and transitions at both high and low user-mobility levels.