Zhe Wang

Estimating Productivity in a Scrum team

2019

Scrum is an agile framework within which people can address complex problems, while productively and creatively delivering products of the highest possible value. There are many factors that may affect the completion of a project …

Another Dimension: Towards Multi-subnet Neural Network for Image Sentiment Analysis

2019

Image sentiment analysis has been studied for many years, and most of algorithms take the image sentiment as independent and discrete labels to predict by machine learning. Actually, as a product of multiple hormone combinations, …

Variable Population Memetic Search: A Case Study on the Critical Node Problem

2019 · arXiv (Cornell University)

Population-based memetic algorithms have been successfully applied to solve many difficult combinatorial problems. Often, a population of fixed size was used in such algorithms to record some best solutions sampled during the search. However, given …

Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs

2020 · arXiv (Cornell University)

Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neural network training, is hard to analyze, theoretically. The huge gap …

Comparisons on Scrum Team Pairing Strategies: A multi-agent Simulation

2020

Scrum is a type of agile process that incrementally, iteratively and continuously deliver software based on sprint time box. It is composed by User Stories, product backlog, sprint backlog, scrum team and sprints. Scrum team …

Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

2020 · Neural Information Processing Systems

The actor-critic (AC) algorithm is a popular method to find an optimal policy in reinforcement learning. In the infinite horizon scenario, the finite-sample convergence rate for the AC and natural actor-critic (NAC) algorithms has been …

Fractional-Order Terminal Sliding-Mode Control Using Self-Evolving Recurrent Chebyshev Fuzzy Neural Network for MEMS Gyroscope

2021 · IEEE Transactions on Fuzzy Systems

To maintain the vibrations of the gyroscope proof mass, a trajectory tracking control system using a neural network estimator is proposed. The proposed control system incorporates a fractional controller based on the terminal sliding-mode and …

A Classification Method of Social Network Members Based on Content Security

2021

With extensive and deep applications of Social Networking Services (SNS), more and more security issues are unfortunately related to it. Research shows unsuitable classification of social network members may induce misinformation and privacy leak. Thus, …

Research on energy-saving design strategies of libraries in severe cold regions: Taking a university in Xinjiang as an example

2021 · Energy Reports

Energy conservation, emission reduction, green and low-carbon, and environmental protection have become contemporary hot topics. Taking a green and sustainable development path is an important measure to realize a resource-saving and environment-friendly society. As a …

A Brief History of Recommender Systems

2022 · arXiv (Cornell University)

Soon after the invention of the Internet, the recommender system emerged and related technologies have been extensively studied and applied by both academia and industry. Currently, recommender system has become one of the most successful …

Long-Tailed Object Mining Based on CLIP Model for Autonomous Driving

2022

The long-tailed object distribution poses great challenges for autonomous driving. And the field collection of long-tailed objects is difficult and high-cost. In this paper, we propose a novel data mining approach for those long-tailed objects. …

Progression Cognition Reinforcement Learning With Prioritized Experience for Multi-Vehicle Pursuit

2024 · IEEE Transactions on Intelligent Transportation Systems

Multi-vehicle pursuit (MVP) such as autonomous police vehicles pursuing suspects is important but very challenging due to its mission and safety-critical nature. While multi-agent reinforcement learning (MARL) algorithms have been proposed for MVP in structured …

BERDD: A Behaviour Engineering-Based Approach for Requirements Defects Detection

2024 · IEEE Access

Detecting software requirements defects is crucial in reducing the risk of software project failures. Existing methods for automatic detection, especially during requirements changes, are limited in coverage and often lack robust tool support. Addressing this …

Aligning Multiple Knowledge Graphs in A Single Pass

2026

Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods mainly focus on aligning a pair of KGs, …

Exploring Nonlinear System with Machine Learning: Chua and Lorenz Circuits Analyzed

2024 · arXiv (Cornell University)

Nonlinear circuits serve as crucial carriers and physical models for investigating nonlinear dynamics and chaotic behavior, particularly in the simulation of biological neurons. In this study, Chua's circuit and Lorenz circuit are systematically explored for …

Approximating model-based a box revision in DL-lite: theory and practice

2015

Model-based approaches provide a semantically well justified way to revise ontologies. However, in general, model-based revision operators are limited due to lack of efficient algorithms and inexpressibility of the revision results. In this paper, we …

Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction

2020

Rich user behavior data has been proven to be of great value for click-through rate prediction tasks, especially in industrial applications such as recommender systems and online advertising. Both industry and academy have paid much …