4,711 Result(s)
within
Chapter
Conference Paper
Lu**g Chen
English
Algorithm Analysis and Problem Complexity
-
Chapter and Conference Paper
SD-Attack: Targeted Spectral Attacks on Graphs
Graph learning (GL) models have been applied in various predictive tasks on graph data. But, similarly to other machine learning models, GL models are also vulnerable to adversarial attacks. As a powerful atta...
-
Chapter and Conference Paper
An Empirical Analysis of Gumbel MuZero on Stochastic and Deterministic Einstein Würfelt Nicht!
MuZero and its successors, Gumbel MuZero and Stochastic MuZero, have achieved superhuman performance in many domains. MuZero combines Monte Carlo tree search and model-based reinforcement learning, which allow...
-
Chapter and Conference Paper
GraphNILM: A Graph Neural Network for Energy Disaggregation
Non-Intrusive Load Monitoring (NILM) remains a critical issue in both commercial and residential energy management, with a key challenge being the requirement for individual appliance-specific deep learning mo...
-
Chapter and Conference Paper
Real-Time Driver Fatigue Detection Method Based on Comprehensive Facial Features
In recent years, there have been frequent cases of vehicle accidents caused by fatigued driving, leading to considerable economic losses and a high number of casualties. Accordingly, it has an important social...
-
Chapter and Conference Paper
Period Extraction for Traffic Flow Prediction
Due to the particularity of “Tourist chartered Buses, Liner Buses and Dangerous Goods Transport Vehicles” (“TLD Vehicles”), traffic accidents will bring serious losses. Therefore, traffic flow prediction for “...
-
Chapter and Conference Paper
An Egg Sorting System Combining Egg Recognition Model and Smart Egg Tray
Modern agriculture is at the forefront of technological transformation. Smart agricultural technology and mechanical automation are bringing unprecedented opportunities and challenges to the field. This study ...
-
Chapter and Conference Paper
Generative Adversarial Network Based Asymmetric Deep Cross-Modal Unsupervised Hashing
With the explosive growth of internet information, cross-modal retrieval has become an important and valuable frontier hotspot. Due to its low storage consumption and high search speed, deep hashing has achiev...
-
Chapter and Conference Paper
Spatio-Temporal Fusion Based Low-Loss Video Compression Algorithm for UAVs with Limited Processing Capability
Real-time urban crowd surveillance is essential for riot supervision, epidemic prevention, and urban emergency management. Unmanned aerial vehicles (UAVs) provide a promising way for real-time crowd surveillan...
-
Chapter and Conference Paper
BioReX: Biomarker Information Extraction Inspired by Aspect-Based Sentiment Analysis
Biomarkers are critical in cancer diagnosis, prognosis, and treatment planning. However, this information is often buried in unstructured text form. In this paper, we make an analogy between Biomarker Informat...
-
Chapter and Conference Paper
On Dark Knowledge for Distilling Generators
Knowledge distillation has been applied on generative models, such as Variational Autoencoder (VAE) and Generative Adversarial Networks (GANs). To distill the knowledge, the synthetic outputs of a teacher generat...
-
Chapter and Conference Paper
AdaPQ: Adaptive Exploration Product Quantization with Adversary-Aware Block Size Selection Toward Compression Efficiency
Product Quantization (PQ) has received an increasing research attention due to the effectiveness on bit-width compression for memory efficiency. PQ is developed to divide weight values into blocks and adopt clust...
-
Chapter and Conference Paper
Construct a Secure CNN Against Gradient Inversion Attack
Federated learning enables collaborative model training across multiple clients without sharing raw data, adhering to privacy regulations, which involves clients sending model updates (gradients) to a central ...
-
Chapter and Conference Paper
A Game Theory Based Task Offloading Scheme for Maximizing Social Welfare in Edge Computing
Edge computing, as a computing paradigm that enables the decentralization of cloud computing services to the edge of the network, effectively addresses the issue of service unavailability caused by power const...
-
Chapter and Conference Paper
Strategic Pairwise Selection for Labeling High-Risk Action from Video-Based Data
Accidental risk can occur anywhere in daily life, with typical examples including pedestrian accidents and concerns about child safety on school campuses. In response to these risks, the field of dangerous beh...
-
Chapter and Conference Paper
Deep Learning for Journalism: The Bibliometric Analysis of Deep Learning for News Production in the Artificial Intelligence Era
This research aims to evaluate the articles published from 2018 to 2023. We focused on the deep learning issues that have risen in the last decade. Deep learning is the popular approach in news research, espec...
-
Chapter and Conference Paper
A Deep Learning Approach for Single-Cell Perturbation Prediction Using Small Molecule Chemical Structures
In this study, we develop a deep learning framework aimed at predicting the impacts of chemical perturbations on individual cells, emphasizing the encoding of small molecular chemical structures . Utilizing th...
-
Chapter and Conference Paper
Structural Topology Optimization Using Genetic Algorithm and Fractals
Structural topology optimization is a recognized technique for designing structures. Genetic algorithm (GA) provides a reliable approach to finding the optimal structure; however, it has been criticized for it...
-
Chapter and Conference Paper
Analysis of Significant Cell Differences Between Cancer Patients and Healthy Individuals
At the end of 2019, a global outbreak of a new coronavirus ravaged the world, and to this day, many people’s bodies are still deeply affected by the virus. In order to find out if there is a correlation betwee...
-
Chapter and Conference Paper
Clustered Federated Learning Framework with Acceleration Based on Data Similarity
Federated Learning is a distributed machine learning framework which allows multiple participants training machine learning model without exchanging their local data. It addresses critical issues such as data ...
-
Chapter and Conference Paper
SecureBoost \(+\) : Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Tree
Gradient boosting decision tree (GBDT) is an ensemble machine learning algorithm that is widely used in industry. Due to the problem of data isolation and the requirement of privacy, many works try to use vert...
