Yan Liu

Three-weight codes and the quintic construction

2016 · arXiv (Cornell University)

We construct a class of three-Lee-weight and two infinite families of five-Lee-weight codes over the ring $R=\mathbb{F}_2 +v\mathbb{F}_2 +v^2\mathbb{F}_2 +v^3\mathbb{F}_2 +v^4\mathbb{F}_2,$ where $v^5=1.$ The same ring occurs in the quintic construction of binary quasi-cyclic codes. …

Benchmarking deep learning models on large healthcare datasets

2018 · Journal of Biomedical Informatics

Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications. However, few works exist which have benchmarked …

Continuous Location Statistics Sharing Algorithm with Local Differential Privacy

2018

Continuous sharing of location statistics produces valuable knowledge to understand important phenomena, such as popular places or pattern behaviors. Most importantly, data should be shared without jeopardizing users' privacy. Differential privacy becomes de-facto technique for …

Four Classes of Optimal Quinary Cyclic Codes

2020 · IEEE Communications Letters

The construction of optimal ternary cyclic codes has received a lot of attention and much progress has been made. However, little is known about optimal quinary cyclic codes. In this letter, four classes of infinite …

DeepCompete : A deep learning approach to competing risks in continuous time domain.

2020 · PubMed

, aimed at survival analysis for competing risks. Our model learns the risk of each disease in an entirely data-driven fashion without making strong assumptions about the underlying stochastic processes. Further, we demonstrate that our …

In-Class Multitasking with Smartphones and Laptops: Exploring Student Experiences and Perceptions

2021 · College Teaching

Although multitasking with laptops and mobile phones has become endemic on university campuses, we still don’t have adequate understanding of this phenomenon. There is especially a lack of qualitative studies offering detailed and rich description …

Study on Reconstruction and Feature Tracking of Silicone Heart 3D Surface

2021 · Sensors

At present, feature-based 3D reconstruction and tracking technology is widely applied in the medical field. In minimally invasive surgery, the surgeon can achieve three-dimensional reconstruction through the images obtained by the endoscope in the human …

A Trustworthy View on XAI Method Evaluation

2022

As the demand grows to develop end-user trust in AI models, practitioners start to build and configure customized XAI (Explainable Artificial Intelligence) methods. The challenge is the lack of systematic evaluation of the newly proposed …

Time-delayed Multivariate Time Series Predictions

2023 · Society for Industrial and Applied Mathematics eBooks

A major issue with real-time monitoring is to collect complete data. Hardware or software failures, network issues or, more frequently, time delays can disrupt such a collection. This results in having two versions of the …

Solar radio spectrogram segmentation algorithm based on improved fuzzy C-means clustering and adaptive cross filtering

2024 · Physica Scripta

Abstract Solar radio spectrograms contain essential information, such as the duration type; therefore, recognizing and detecting solar radio spectrograms are significant for the further study of solar radio. With the upgrading of solar radio observation, …

XAIport: A Service Framework for the Early Adoption of XAI in AI Model Development

2024

In this study, we propose the early adoption of Explainable AI (XAI) with a focus on three properties: Quality of explanation, the explanation summaries should be consistent across multiple XAI methods; Architectural Compatibility, for effective …

Multi-round Counterfactual Generation: Interpreting and Improving Models of Text Classification

2024

In recent years, natural language processing (NLP) models have demonstrated remarkable performance in text classification tasks. However, trust in the decision-making process requires a deeper understanding of the operational principles of these networks. Therefore, there …

The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models

2024 · arXiv (Cornell University)

Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem mainly focused …

Chemical Experiment Aided Design System Based on Data Mining Algorithms

2024

Experimental teaching refers to the instructional stage of combining theoretical knowledge with practical activities, abstraction with concreteness, and direct and indirect. This teaching mode is more comprehensive, practical, direct and innovative than pure theory teaching. …

Enhancing Medical Image Classification with Unified Model Agnostic Computation and Explainable AI

2024 · AI

Background: Advances in medical image classification have recently benefited from general augmentation techniques. However, these methods often fall short in performance and interpretability. Objective: This paper applies the Unified Model Agnostic Computation (UMAC) framework specifically …

Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization

2025 · arXiv (Cornell University)

Commenting code is a crucial activity in software development, as it aids in facilitating future maintenance and updates. To enhance the efficiency of writing comments and reduce developers' workload, researchers has proposed various automated code …

Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction

2017

Recently, many e-commerce websites have encouraged their users to rate shopping items and write review texts. This review information has been very useful for understanding user preferences and item properties, as well as enhancing the …