arXiv subjects

Zhiyi Zhu

Publications and source records attributed to Zhiyi Zhu.

8 recordsLinked to original sources

arXiv2026

Denoising Rather Than Gap Filling: Missing-Data Handling in Sparse Outdoor BLE Positioning

Received signal strength indicator (RSSI) positioning outdoors has one to two orders of magnitude fewer anchors than the indoor systems its methods come from. In the ten-day cattle-tracking deployment reported here, four gateways cover $4{,}302\,\mathrm{m}^2$, or $0.93$ anchors per $1000\,\mathrm{m}^2$. An animal is heard by $0.99$ gateways per second on average, so the observation vector for a given second is almost never complete. How the gaps are filled is therefore a first-order design choice, not a preprocessing detail. Filling at all is worth $8.1\,\mathrm{m}$, $96\%$ of the improvement the hold-length setting can deliver and a $29\%$ error reduction. How long a value is then held is worth the remaining $4\%$, from four seconds to unbounded. Once a value is available, the gain comes from removing noise rather than rebuilding the lost sample: a filtered channel estimate improves on a held raw sample, whereas filling backwards from future samples makes it worse. As that mechanism predicts, smoothing strength has a real interior optimum that is costly to miss in either direction. A smoother allowed to read the future gains only $0.55\,\mathrm{m}$, one fifteenth of what filling is worth, which bounds what any offline method can add. Three method families do not apply here for structural reasons rather than poor performance: two or more of the four channels are live in only $25\%$ of seconds, so the cross-channel structure generative imputation must learn is largely unobserved.

eess.SP↗

arXiv2026

MLVTG: Mamba-Based Feature Alignment and LLM-Driven Purification for Multi-Modal Video Temporal Grounding

Video Temporal Grounding (VTG), which aims to localize video clips corresponding to natural language queries, is a fundamental yet challenging task in video understanding. Existing Transformer-based methods often suffer from redundant attention and suboptimal multi-modal alignment. To address these limitations, we propose MLVTG, a novel framework that integrates two key modules: MambaAligner and LLMRefiner. MambaAligner uses stacked Vision Mamba blocks as a backbone instead of Transformers to model temporal dependencies and extract robust video representations for multi-modal alignment. LLMRefiner leverages the specific frozen layer of a pre-trained Large Language Model (LLM) to implicitly transfer semantic priors, enhancing multi-modal alignment without fine-tuning. This dual alignment strategy, temporal modeling via structured state-space dynamics and semantic purification via textual priors, enables more precise localization. Extensive experiments on QVHighlights, Charades-STA, and TVSum demonstrate that MLVTG achieves state-of-the-art performance and significantly outperforms existing baselines.

cs.CV↗

arXiv2025

A Study on E2E Performance Improvement of Platooning Using Outdoor LiFi

Platooning within autonomous vehicles has proven effective in addressing driver shortages and reducing fuel consumption. However, as platooning lengths increase, traditional C-V2X (cellular vehicle-to-everything) architectures are susceptible to end-to-end (E2E) latency increases. This is due to the necessity of relaying information through multiple hops from the leader vehicle to the last vehicle. To address this problem, this paper proposes a hybrid communication architecture based on a simulation that integrates light fidelity (LiFi) and C-V2X. The proposed architecture introduces multiple-leader vehicles equipped with outdoor LiFi communication nodes in platoons to achieve high-speed and low-delay communication between leader vehicles, which reduces E2E delay.

cs.NI↗

arXiv2025

NR Cell Identity-based Handover Decision-making Algorithm for High-speed Scenario within Dual Connectivity

The dense deployment of 5G heterogeneous networks (HetNets) has improved network capacity. However, it also brings frequent and unnecessary handover challenges to high-speed mobile user equipment (UE), resulting in unstable communication and degraded quality of service. Traditional handovers ignore the type of target next-generation Node B (gNB), resulting in high-speed UEs being able to be handed over to any gNB. This paper proposes a NR cell identity (NCI)-based handover decision-making algorithm (HDMA) to address this issue. The proposed HDMA identifies the type of the target gNB (macro/small/mmWave gNB) using the gNB identity (ID) within the NCI to improve the handover decision-making strategy. The proposed HDMA aims to improve the communication stability of high-speed mobile UE by enabling high-speed UEs to identify the target gNB type during the HDMA using the gNB ID. Simulation results show that the proposed HDMA outperforms other HDMAs in enhanced connection stability.

cs.NI↗

arXiv2025

Enhancing Video Memorability Prediction with Text-Motion Cross-modal Contrastive Loss and Its Application in Video Summarization

Video memorability refers to the ability of videos to be recalled after viewing, playing a crucial role in creating content that remains memorable. Existing models typically focus on extracting multimodal features to predict video memorability scores but often fail to fully utilize motion cues. The representation of motion features is compromised during the fine-tuning phase of the motion feature extractor due to a lack of labeled data. In this paper, we introduce the Text-Motion Cross-modal Contrastive Loss (TMCCL), a multimodal video memorability prediction model designed to enhance the representation of motion features. We tackle the challenge of improving motion feature representation by leveraging text description similarities across videos to establish positive and negative motion sample sets for a given target. This enhancement allows the model to learn similar feature representations for semantically related motion content, resulting in more accurate memorability predictions. Our model achieves state-of-the-art performance on two video memorability prediction datasets. Moreover, the potential applications of video memorability prediction have been underexplored. To address this gap, we present Memorability Weighted Correction for Video Summarization (MWCVS), using video memorability prediction to reduce subjectivity in video summarization labels. Experimental results on two video summarization datasets demonstrate the effectiveness of MWCVS, showcasing the promising applications of video memorability prediction.

cs.CV↗

arXiv2023

Revisiting type-2 triangular norms on normal convex fuzzy truth values

This paper studies t-norms on the space $\mathbf{L}$ of all normal and convex fuzzy truth values. We first prove that the only non-convolution form type-2 t-norm constructed by Wu et al. satisfies the distributivity law for meet-convolution and show that t-norm in the sense of Walker and Walker is strictly stronger than t$_{r}$-norm on $\mathbf{L}$, which is strictly stronger than t-norm on $\mathbf{L}$. Furthermore, we characterize some restrictive axioms of t$_{r}$-norms for convolution operations on $\mathbf{L}$ and obtain some necessary conditions for t$_{r}$-(co)norm convolution operations on $\mathbf{L}$ .

math.GM↗

arXiv2023

Strict Intuitionistic Fuzzy Distance/Similarity Measures Based on Jensen-Shannon Divergence

Being a pair of dual concepts, the normalized distance and similarity measures are very important tools for decision-making and pattern recognition under intuitionistic fuzzy sets framework. To be more effective for decision-making and pattern recognition applications, a good normalized distance measure should ensure that its dual similarity measure satisfies the axiomatic definition. In this paper, we first construct some examples to illustrate that the dual similarity measures of two nonlinear distance measures introduced in [A distance measure for intuitionistic fuzzy sets and its application to pattern classification problems, \emph{IEEE Trans. Syst., Man, Cybern., Syst.}, vol.~51, no.~6, pp. 3980--3992, 2021] and [Intuitionistic fuzzy sets: spherical representation and distances, \emph{Int. J. Intell. Syst.}, vol.~24, no.~4, pp. 399--420, 2009] do not meet the axiomatic definition of intuitionistic fuzzy similarity measure. We show that (1) they cannot effectively distinguish some intuitionistic fuzzy values (IFVs) with obvious size relationship; (2) except for the endpoints, there exist infinitely many pairs of IFVs, where the maximum distance 1 can be achieved under these two distances; leading to counter-intuitive results. To overcome these drawbacks, we introduce the concepts of strict intuitionistic fuzzy distance measure (SIFDisM) and strict intuitionistic fuzzy similarity measure (SIFSimM), and propose an improved intuitionistic fuzzy distance measure based on Jensen-Shannon divergence. We prove that (1) it is a SIFDisM; (2) its dual similarity measure is a SIFSimM; (3) its induced entropy is an intuitionistic fuzzy entropy. Comparative analysis and numerical examples demonstrate that our proposed distance measure is completely superior to the existing ones.

math.GM↗

arXiv2022

A Monotonous Intuitionistic Fuzzy TOPSIS Method under General Linear Orders via Admissible Distance Measures

All intuitionistic fuzzy TOPSIS methods contain two key elements: (1) the order structure, which can affect the choices of positive ideal-points and negative ideal-points, and construction of admissible distance/similarity measures; (2) the distance/similarity measure, which is closely related to the values of the relative closeness degrees and determines the accuracy and rationality of decision-making. For the order structure, many efforts are devoted to constructing some score functions, which can strictly distinguish different intuitionistic fuzzy values (IFVs) and preserve the natural partial order for IFVs.This paper proves that such a score function does not exist, namely the application of a single monotonous and continuous function does not distinguish all IFVs. For the distance or similarity measure, some examples are given to show that classical similarity measures based on the normalized Euclidean distance and normalized Minkowski distance do not meet the axiomatic definition of intuitionistic fuzzy similarity measures. Moreover,some illustrative examples are given to show that classical intuitionistic fuzzy TOPSIS methods do not ensure the monotonicity with the natural partial order or linear orders, which may yield some counter-intuitive results. To overcome the limitation of non-monotonicity, we propose a novel intuitionistic fuzzy TOPSIS method,using three new admissible distances with the linear orders measured by a score degree/similarity function and accuracy degree, or two aggregation functions, and prove that the proposed TOPSIS method is monotonous under these three linear orders.} This is the first result with a strict mathematical proof on the monotonicity with the linear orders for the intuitionistic fuzzy TOPSIS method.

math.GM↗