MengChu Zhou
YOU?
Author Swipe
View article: Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment
Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignment Open
Neural speech synthesis techniques have enabled highly realistic speech deepfakes, posing major security risks. Speech deepfake detection is challenging due to distribution shifts across spoofing methods and variability in speakers, channe…
View article: Revisiting Randomized Smoothing: Nonsmooth Nonconvex Optimization Beyond Global Lipschitz Continuity
Revisiting Randomized Smoothing: Nonsmooth Nonconvex Optimization Beyond Global Lipschitz Continuity Open
Randomized smoothing is a widely adopted technique for optimizing nonsmooth objective functions. However, its efficiency analysis typically relies on global Lipschitz continuity, a condition rarely met in practical applications. To address…
View article: Petri Net Modeling and Deadlock-Free Scheduling of Attachable Heterogeneous AGV Systems
Petri Net Modeling and Deadlock-Free Scheduling of Attachable Heterogeneous AGV Systems Open
The increasing demand for automation and flexibility drives the widespread adoption of heterogeneous automated guided vehicles (AGVs). This work intends to investigate a new scheduling problem in a material transportation system consisting…
View article: Evaluation of continuous improvement effect of perioperative nursing quality in Da Vinci robot-assisted laparoscopic radical prostatectomy
Evaluation of continuous improvement effect of perioperative nursing quality in Da Vinci robot-assisted laparoscopic radical prostatectomy Open
This study explores the clinical effect of continuous improvement of perioperative nursing quality in patients with Da Vinci robot-assisted laparoscopic radical prostatectomy. A total of 222 patients who received Da Vinci robot-assisted la…
View article: MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark Open
Tables and table-based use cases play a crucial role in many important real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally require expert-level users like data engineers, data analysts…
View article: Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning
Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning Open
Discrete diffusion models represent a significant advance in generative modeling, demonstrating remarkable success in synthesizing complex, high-quality discrete data. However, to avoid exponential computational costs, they typically rely …
View article: SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples
SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples Open
Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation. Ex…
View article: Control Strategies for Pursuit-Evasion Under Occlusion Using Visibility and Safety Barrier Functions
Control Strategies for Pursuit-Evasion Under Occlusion Using Visibility and Safety Barrier Functions Open
This paper develops a control strategy for pursuit-evasion problems in environments with occlusions. We address the challenge of a mobile pursuer keeping a mobile evader within its field of view (FoV) despite line-of-sight obstructions. Th…
View article: A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism
A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism Open
Neural architecture search (NAS) enables researchers to automatically explore vast search spaces and find efficient neural networks. But NAS suffers from a key bottleneck, i.e., numerous architectures need to be evaluated during the search…
View article: Solving the Food-Energy-Water Nexus Problem via Intelligent Optimization Algorithms
Solving the Food-Energy-Water Nexus Problem via Intelligent Optimization Algorithms Open
The application of evolutionary algorithms (EAs) to multi-objective optimization problems has been widespread. However, the EA research community has not paid much attention to large-scale multi-objective optimization problems arising from…
View article: Improving Classification Performance in Dendritic Neuron Models through Practical Initialization Strategies
Improving Classification Performance in Dendritic Neuron Models through Practical Initialization Strategies Open
A dendritic neuron model (DNM) is a deep neural network model with a unique dendritic tree structure and activation function. Effective initialization of its model parameters is crucial for its learning performance. This work proposes a no…
View article: Learning From Human Educational Wisdom: A Student-Centered Knowledge Distillation Method
Learning From Human Educational Wisdom: A Student-Centered Knowledge Distillation Method Open
Existing studies on knowledge distillation typically focus on teacher-centered methods, in which the teacher network is trained according to its own standards before transferring the learned knowledge to a student one. However, due to diff…
View article: Applying additive manufacturing technologies to a supply chain: A Petri net-based decision model
Applying additive manufacturing technologies to a supply chain: A Petri net-based decision model Open
Nowadays, applying additive manufacturing (AM) technologies into a supply chain (SC) permits realization of the so-called “demand chains” and transformation of conventional production to mass customization. However, integration of AM techn…
View article: Robust and Fair Multi-Objective Power Allocation Problem Based on Efficient and Healthy Cognitive Radio
Robust and Fair Multi-Objective Power Allocation Problem Based on Efficient and Healthy Cognitive Radio Open
Cognitive radio networks (CRNs) is a technology that can alleviate the scarcity of radio resources, improve communication efficiency, and reduce electromagnetic radiation pollution. However, traditional research mostly concentrates on a si…
View article: A Sparse Cross Attention-based Graph Convolution Network with Auxiliary Information Awareness for Traffic Flow Prediction
A Sparse Cross Attention-based Graph Convolution Network with Auxiliary Information Awareness for Traffic Flow Prediction Open
Deep graph convolution networks (GCNs) have recently shown excellent performance in traffic prediction tasks. However, they face some challenges. First, few existing models consider the influence of auxiliary information, i.e., weather and…
View article: Applications and Future Research Directions of Learning Automata
Applications and Future Research Directions of Learning Automata Open
As a powerful computational intelligence algorithm, Learning Automata (LAs) have been studied and applied widely. In this chapter, their applications and future research directions are discussed. Researchers have developed many algorithm v…
View article: Incorporation of Ordinal Optimization into Learning Automata
Incorporation of Ordinal Optimization into Learning Automata Open
In practical applications, a learning automaton acts as an adaptive controller in modeling a process as well as an appropriate control signal generator. Systems built with learning automata (LAs) have been successfully employed in many dif…
View article: Application‐Oriented Learning Automata
Application‐Oriented Learning Automata Open
Learning automata (LAs) have many variants for various application fields. Sometimes, these variants abstract characters from specific applied problems and own respective different learning schemes. In this chapter, two special variants ar…
View article: An Improved Discrete Jaya Algorithm for Shortest Path Problems in Transportation-Related Processes
An Improved Discrete Jaya Algorithm for Shortest Path Problems in Transportation-Related Processes Open
Shortest path problems are encountered in many engineering applications, e.g., intelligent transportation, robot path planning, and smart logistics. The environmental changes as sensed and transmitted via the Internet of Things make the sh…
View article: Transaction Fraud Detection via an Adaptive Graph Neural Network
Transaction Fraud Detection via an Adaptive Graph Neural Network Open
Many machine learning methods have been proposed to achieve accurate transaction fraud detection, which is essential to the financial security of individuals and banks. However, most existing methods leverage original features only or requ…
View article: PePNet: A Periodicity-Perceived Workload Prediction Network Supporting Rare Occurrence of Heavy Workload
PePNet: A Periodicity-Perceived Workload Prediction Network Supporting Rare Occurrence of Heavy Workload Open
Cloud providers can greatly benefit from accurate workload prediction. However, the workload of cloud servers is highly variable, with occasional heavy workload bursts. This makes workload prediction challenging. There are mainly two categ…
View article: Damping-Assisted Evolutionary Swarm Intelligence for Industrial IoT Task Scheduling in Cloud Computing
Damping-Assisted Evolutionary Swarm Intelligence for Industrial IoT Task Scheduling in Cloud Computing Open
Advancements in the Industrial Internet of Things (IIoT) have yielded massive volumes of data, taxing the capabilities of cloud computing infrastructure. Allocating limited computing resources to numerous incoming requests is crucial for c…