SearcharxivSearch

arXiv subjects

Ziqing Li

Publications and source records attributed to Ziqing Li.

10 recordsLinked to original sources

Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network

We consider a neural network (NN) that may experience memory faults and computational errors. In this paper, we propose a novel real-number-based error correction code (ECC) capable of detecting and correcting both memory errors and computational errors. The proposed approach introduces structures in the form of real-number-based linear constraints on the NN weights to enable error detection and correction, without sacrificing classification performance or increasing the number of real-valued NN parameters.

cs.NE

A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education

The development of Automatic Question Generation (QG) models has the potential to significantly improve educational practices by reducing the teacher workload associated with creating educational content. This paper introduces a novel approach to educational question generation that controls the topical focus of questions. The proposed Topic-Controlled Question Generation (T-CQG) method enhances the relevance and effectiveness of the generated content for educational purposes. Our approach uses fine-tuning on a pre-trained T5-small model, employing specially created datasets tailored to educational needs. The research further explores the impacts of pre-training strategies, quantisation, and data augmentation on the model's performance. We specifically address the challenge of generating semantically aligned questions with paragraph-level contexts, thereby improving the topic specificity of the generated questions. In addition, we introduce and explore novel evaluation methods to assess the topical relatedness of the generated questions. Our results, validated through rigorous offline and human-backed evaluations, demonstrate that the proposed models effectively generate high-quality, topic-focused questions. These models have the potential to reduce teacher workload and support personalised tutoring systems by serving as bespoke question generators. With its relatively small number of parameters, the proposals not only advance the capabilities of question generation models for handling specific educational topics but also offer a scalable solution that reduces infrastructure costs. This scalability makes them feasible for widespread use in education without reliance on proprietary large language models like ChatGPT.

cs.CY

Bounds for DP color function and canonical labelings

The DP-coloring is a generalization of the list coloring, introduced by Dvořák and Postle. Let $\mathcal{H}=(L,H)$ be a cover of a graph $G$ and $P_{DP}(G,\mathcal{H})$ be the number of $\mathcal{H}$-colorings of $G$. The DP color function $P_{DP}(G,m)$ of $G$, introduced by Kaul and Mudrock, is the minimum value of $P_{DP}(G,\mathcal{H})$ where the minimum is taken over all possible $m$-fold covers $\mathcal{H}$ of $G$. For the family of $n$-vertex connected graphs, one can deduce that trees maximize the DP color function, from two results of Kaul and Mudrock. In this paper we obtain tight upper bounds for the DP color function of $n$-vertex $2$-connected graphs. Another concern in this paper is the canonical labeling in a cover. It is well known that if an $m$-fold cover $\mathcal{H}$ of a graph $G$ has a canonical labeling, then $P_{DP}(G,\mathcal{H})=P(G,m)$ in which $P(G,m)$ is the chromatic polynomial of $G$. However the converse statement of this conclusion is not always true. We give examples that for some $m$ and $G$, there exists an $m$-fold cover $\mathcal{H}$ of $G$ such that $P_{DP}(G,\mathcal{H})=P(G,m)$, but $\mathcal{H}$ has no canonical labelings. We also prove that when $G$ is a unicyclic graph or a theta graph, for each $m\geq 3$, if $P_{DP}(G,\mathcal{H})=P(G,m)$, then $\mathcal{H}$ has a canonical labeling.

math.CO

MLFEF: Machine Learning Fusion Model with Empirical Formula to Explore the Momentum in Competitive Sports

Tennis is so popular that coaches and players are curious about factors other than skill, such as momentum. This article will try to define and quantify momentum, providing a basis for real-time analysis of tennis matches. Based on the tennis Grand Slam men's singles match data in recent years, we built two models, one is to build a model based on data-driven, and the other is to build a model based on empirical formulas. For the data-driven model, we first found a large amount of public data including public data on tennis matches in the past five years and personal information data of players. Then the data is preprocessed, and feature engineered, and a fusion model of SVM, Random Forrest algorithm and XGBoost was established. For the mechanism analysis model, important features were selected based on the suggestions of many tennis players and enthusiasts, the sliding window algorithm was used to calculate the weight, and different methods were used to visualize the momentum. For further analysis of the momentum fluctuation, it is based on the popular CUMSUM algorithm in the industry as well as the RUN Test, and the result shows the momentum is not random and the trend might be random. At last, the robustness of the fusion model is analyzed by Monte Carlo simulation.

cs.LG

Languaging Ethics in Technology Practice

Ethics as embodied by technology practitioners resists simple definition, particularly as it relates to the interplay of identity, organizational, and professional complexity. In this paper we use the linguistic notion of languaging as an analytic lens to describe how technology and design practitioners negotiate their conception of ethics as they reflect upon their everyday work. We engaged twelve practitioners in individual co-creation workshops, encouraging them to reflect on their ethical role in their everyday work through a series of generative and evaluative activities. We analyzed these data to identify how each practitioner reasoned about ethics through language and artifacts, finding that practitioners used a range of rhetorical tropes to describe their ethical commitments and beliefs in ways that were complex and sometimes contradictory. Across three cases, we describe how ethics was negotiated through language across three key zones of ecological emergence: the practitioner's "core" beliefs about ethics, internal and external ecological elements that shaped or mediated these core beliefs, and the ultimate boundaries they reported refusing to cross. Building on these findings, we describe how the languaging of ethics reveals opportunities to definitionally and practically engage with ethics in technology ethics research, practice, and education.

cs.CY

Human Health Indicator Prediction from Gait Video

Body Mass Index (BMI), age, height and weight are important indicators of human health conditions, which can provide useful information for plenty of practical purposes, such as health care, monitoring and re-identification. Most existing methods of health indicator prediction mainly use front-view body or face images. These inputs are hard to be obtained in daily life and often lead to the lack of robustness for the models, considering their strict requirements on view and pose. In this paper, we propose to employ gait videos to predict health indicators, which are more prevalent in surveillance and home monitoring scenarios. However, the study of health indicator prediction from gait videos using deep learning was hindered due to the small amount of open-sourced data. To address this issue, we analyse the similarity and relationship between pose estimation and health indicator prediction tasks, and then propose a paradigm enabling deep learning for small health indicator datasets by pre-training on the pose estimation task. Furthermore, to better suit the health indicator prediction task, we bring forward Global-Local Aware aNd Centrosymmetric Encoder (GLANCE) module. It first extracts local and global features by progressive convolutions and then fuses multi-level features by a centrosymmetric double-path hourglass structure in two different ways. Experiments demonstrate that the proposed paradigm achieves state-of-the-art results for predicting health indicators on MoVi, and that the GLANCE module is also beneficial for pose estimation on 3DPW.

cs.CV

Practitioner Trajectories of Engagement with Ethics-Focused Method Creation

Design and technology practitioners are increasingly aware of the ethical impact of their work practices, desiring tools to support their ethical awareness across a range of contexts. In this paper, we report on findings from a series of co-design workshops with technology and design practitioners that supported their creation of a bespoke ethics-focused action plan. Using a qualitative content analysis and thematic analysis approach, we identified a range of roles and process moves that practitioners employed and illustrate the interplay of these elements of practitioners' instrumental judgment through a series of three cases, which includes evolution of the action plan itself, the ethical dilemmas or areas of support the action plan was intended to support, and how the action plan represents resonance for the practitioner that created it. We conclude with implications for supporting ethics in socio-technical practice and opportunities for the further development of ethics-focused methods that are resonant with the realities of practice.

cs.HC

Scaffolding Ethics-Focused Methods for Practice Resonance

Numerous methods and tools have been proposed to motivate or support ethical awareness in design practice. However, many existing resources are not easily discoverable by practitioners. One reason being that they are framed using language that is not immediately accessible or resonant with the felt complexity of everyday practice. In this paper, we propose a set of empirically-supported "intentions" to frame practitioners' selection of relevant ethics-focused methods based on interviews with practitioners from a range of technology and design professions, and then leverage these intentions in the design and iterative evaluation of a website that allows practitioners to identify supports for ethics-focused action in their work context. Building on these findings, we propose a set of heuristics to evaluate the practice resonance of resources to support ethics-focused practice, laying the groundwork for increased ecological resonance of ethics-focused methods and method selection tools.

cs.HC

Surveying the Landscape of Ethics-Focused Design Methods

Over the past decade, HCI researchers, design researchers, and practitioners have increasingly addressed ethics-focused issues through a range of theoretical, methodological and pragmatic contributions to the field. While many forms of design knowledge have been proposed and described, we focus explicitly on knowledge that has been codified as "methods," which we define as any supports for everyday work practices of designers. In this paper, we identify, analyze, and map a collection of 63 existing ethics-focused methods intentionally designed for ethical impact. We present a content analysis, providing a descriptive record of how they operationalize ethics, their intended audience or context of use, their "core" or "script," and the means by which these methods are formulated, articulated, and languaged. Building on these results, we provide an initial definition of ethics-focused methods, identifying potential opportunities for the development of future methods to support design practice and research.

cs.HC

Let's Talk About Socio-Technical Angst: Tracing the History and Evolution of Dark Patterns on Twitter from 2010-2021

Designers' use of deceptive and manipulative design practices have become increasingly ubiquitous, impacting users' ability to make choices that respect their agency and autonomy. These practices have been popularly defined through the term "dark patterns" which has gained attention from designers, privacy scholars, and more recently, even legal scholars and regulators. The increased interest in the term and underpinnings of dark patterns across a range of sociotechnical practitioners intrigued us to study the evolution of the concept, to potentially speculate the future trajectory of conversations around dark patterns. In this paper, we examine the history and evolution of the Twitter discourse through #darkpatterns from its inception in June 2010 until April 2021, using a combination of quantitative and qualitative methods to describe how this discourse has changed over time. We frame the evolution of this discourse as an emergent transdisciplinary conversation that connects multiple disciplinary perspectives through the shared concept of dark patterns, whereby these participants engage in a conversation marked by socio-technical angst in order to identify and fight back against deceptive design practices. We discuss the potential future trajectories of this discourse and opportunities for further scholarship at the intersection of design, policy, and activism.

cs.SI