-
Chapter and Conference Paper
LAMB: Label-Induced Mixed-Level Blending for Multimodal Multi-label Emotion Detection
To better understand complex human emotions, there is growing interest in utilizing heterogeneous sensory data to detect multiple co-occurring emotions. However, existing studies have focused on extracting sta...
-
Chapter and Conference Paper
Research on Target Detection Algorithm of Unmanned Surface Vehicle Based on Deep Learning
The typical YOLO algorithm, SSD algorithm and RCNN model all have the problem of low detection accuracy or slow detection speed in surface target detection, and cannot be applied to surface unmanned ships that...
-
Chapter and Conference Paper
Design and Evaluation of an Exergame System of Knee with the Azure Kinect
Timely and effective knee function evaluation and knee exercises promote the prevention and self-management of knee diseases. In this paper, a Kinect-based exergame system is proposed to assess and train the k...
-
Chapter and Conference Paper
Multi-dimensional Fatigue Driving Detection Method Based on SVM Improved by the Kernel Function
Driver fatigue is one of the leading causes of traffic accidents. At present, fatigue driving detection has disadvant ages such as low practical application effect and high equipment requirements. This paper p...
-
Chapter and Conference Paper
Controller Placements for Optimizing Switch-to-Controller and Inter-controller Communication Latency in Software Defined Networks
The logically centralized control plane in large-scale SDN networks consists of multiple controllers, and the controllers communicate with each other to keep a consistent view of the network status. Inconsiste...
-
Chapter and Conference Paper
Pavement Crack Detection Using Attention U-Net with Multiple Sources
The detection of road cracks is the main basis of highway maintenance, and the noise, shadows, and irregularities of road images will bring great challenges to traditional detection. Therefore, we propose a mu...
-
Chapter and Conference Paper
A Novel Node-to-Set Node-Disjoint Fault-Tolerant Routing Strategy in Hypercube
This paper proposes a node-to-set node-disjoint routing algorithm based on a path storage model for the hypercube networks with faulty nodes. Two properties of the storage model are listed in the paper on cond...
-
Chapter and Conference Paper
In-Memory Checkpointing for MPI Programs by XOR-Based Double-Erasure Codes
Today, the scale of High performance computing (HPC) systems is much larger than ever. This brings a challenge to fault tolerance of HPC systems. MPI (Message Passing Interface) is one of the most important pr...