No abstract available.
Proceeding Downloads
Liver cutting algorithm based on virtual plane
At present, the algorithm for virtual liver cutting requires a lot of computation, has poor real-time performance, and is easy to produce degenerated triangle and deformed triangle, and the physical characteristics are lost during the cutting process. ...
Multi-scale ultrasound image denoising algorithm based on deep learning model for super-resolution reconstruction
Effective suppression of speckle noise in ultrasound images is of great significance for improving image quality and clinical diagnostic analysis. The traditional edge enhancement nonlinear coherent diffusion (EENCD) and multi-scale filtering based on ...
Research on Multi-Domain Sample Classification Method Based on Baidu API
This paper proposes a multi-domain sample classification method based on Baidu API's general object recognition function. we used three datasets in the experiment,including CIFAR-10, CIFAR-100, and Mini-ImageNet. For an unknown sample belonging to these ...
STAA: Spatio-Temporal Adversarial Attack Based on Attention Mechanism
Traffic prediction models play a crucial role in estimating future traffic conditions based on historical data and road network structures. However, these models are vulnerable to adversarial attacks, wherein malicious attackers can manipulate key nodes ...
ANA: An Adaptive Non-outlier-detection-based Aggregation Algorithm Against Poisoning Attack for Federated Learning
Federated learning (FL) is an emerging learning paradigm in distributed machine learning (ML) that enables multiple data owners, referred to as clients, to collaboratively train a global model without sharing their local training data. The decentralized ...
A New Dynamic Window Approach Algorithm with Informed Rapidly Exploring Random Tree* Algorithm Implementation on a Robot Operating System
To enhance the performance of the Dynamic Window Approach (DWA) algorithm in complex obstacle environments and address its inability to handle negative-weighted edge graphs, this study proposes a path-planning algorithm that combines DWA with informed ...
Concrete learning method for segmentation and denoising using CBCT Image
Cone Beam Computed Tomography (CBCT) has emerged as a valuable imaging technique in dental diagnosis, which enables comprehensive evaluation of dental pathologies, aiding in the diagnosis and treatment planning of complex cases such as impacted teeth, ...
Collaborative information and semantic information Fusion over Heterogeneous information Network for Top-N Recommendation System
In recent years, additional information in the side of both users and items are more and more common in the natural world. Traditional recommendation methods mainly utilize the the user-item rating information. These information, if properly used, can ...
RSAA: Relation-Specific Attention and Global Alignment Based Joint Entity and Relation Extraction
Joint relational triple extraction is a crucial task in knowledge graph construction. However, most of these methods either perform a large number of redundant predictions on relations, resulting in slower inference speed or ignore the semantic ...
Instruction Tuning Text-to-SQL with Large Language Models in the Power Grid Domain
This paper explores the large language models to address the Text-to-SQL task in real-world scenarios in the electricity domain. To tackle the lack of training data and corresponding databases for vertical domain real-world scenarios, the paper devised ...
Mal-lightDet: A light method to detect malicious encrypted traffic based on machine learning
Encryption not only protects the network security and privacy, but also encrypts attackers’ malicious traffic to evade detection. Thus, how to detect malicious encrypted traffic is critical for network security. From the perspective of privacy, methods ...
Analysis and identification method of dust accumulation and shadow characteristics of photovoltaic modules
Abstract—Aiming at the problem of identifying the characteristics of dust accumulation and shadow of photovoltaic modules, the difference of photovoltaic characteristic curves of dust accumulation and shadow is analyzed in detail, and the time-varying ...
Disentangled Representation Learning for Generative Adversarial Multi-task Imitation Learning
Multi-task imitation learning (MTIL) is an effective approach to training an autonomous agent that is capable of performing multiple tasks using multi-task expert demonstrations. Since different tasks often share similarities, learning them ...
Learning High-Quality Bounding Box for Rotated Object Detection via Rotated Cascade Region Proposal Network
Existing two-stage detectors usually generate oriented proposals based on heuristically defined anchors with different scales, angles, and aspect ratios. This scheme usually suffers from severe memory-consuming and redundant computation. Additionally, ...
PPL-net:Convolutional Neural Network-Based Polymorphic Points-Line verification framework
To address the problems that the line segments extracted by the existing line segment detectors have local ambiguity and insufficient fitting accuracy, we propose PPL-net, a line segment detector based on the Modified Convolutional Neural Network (CNN) ...
CAS_NeXt: Towards Accurate and Topology-Preserving Coronary Artery Segmentation in Digital Substraction Angiography
Coronary artery segmentation in digital substraction angiography, as one of the most critical steps in percutaneous coronary intervention (PCI) procedures, has strict accuracy requirements for clinical diagnosis. However, previous studies have seldom ...
CIMNet: A Contextual Information Mining Network for Real-time Instance Segmentation
Real-time instance segmentation seeks to partition and localize instances with desired efficiency, which has been applied to autonomous driving, robot navigation, and medical image analysis, and so forth. By learning hierarchical features, convolutional ...
PointWave-MLP: Point Cloud Analysis Based on Wave-MLP Architecture
Due to the irregularity and disorder of point clouds, point cloud analysis based on deep learning remains a challenging task. Although the previous point cloud analysis networks based on multi-layer perceptions (MLPs) exhibit a simple structure, they ...
Multi-Stage Action Quality Assessment Method
In most of the existing mainstream action quality assessment methods, the score regression is performed on a complete action video to obtain the predicted score, which may prevent us from fully exploiting the multi-stage information in action video. In ...
MSTCNet: Parallel Multi-Scale Network For Medical Image Segmentation
Transformer-like architectures, which are the model of choice in the field of natural language processing, have recently been adapted to computer vision (CV) fields and demonstrated remarkable effectiveness on various CV tasks. However, current ...
Multi-scale vehicle detection method for expressway based on YOLOv7
A YOLOv7-based multi-scale vehicle detection method for expressways is proposed for the problem of low accuracy of multi-scale vehicle detection due to insufficient extraction and representation of vehicle features in multi-scale vehicle detection in ...
Structure-aware Table-to-Text Generation with Prefix-tuning
Table-to-text generation is designed to generate descriptive natural language for structured tables that conforms to objective facts and follows the source data. The current challenge in this field is to capture the structural information of the table ...
A Comprehensive Survey on Text Filling Algorithms: A Research Review
Starting from the concept, application scenarios and research significance of text filling, this paper divides text filling algorithms into two categories: traditional methods and deep learning, summarizes the development process of text filling ...
Chinese Implicit Binary complex Sentence Relation Recognition Based on RDAGCN Hybrid Model
Chinese implicit complex sentence relation recognition aims to analyze the semantic logical relationships between two sub-sentences. The main challenge lies in capturing accurate semantic interactions due to the absence of explicit conjunctions. ...
Construction of Traditional Culture Ontology Based on Representation and Role
Traditional culture refers to a culture that has evolved from civilization and can reflect the characteristics and spirit of a nation. However, at present, the traditional cultural ontology only focuses on modeling and data organization of a certain ...
A Unified Mixed-Bandwidth ASR Framework with Generative Adversarial Network
The recognition of mixed-bandwidth audio presents a challenge for both academic and industrial fields, with potentially greater implications for the latter. In this paper, we present a unified ASR architecture for mixed-bandwidth audio's recognition, ...
Multi-objective Optimization Configuration Scheme for Photovoltaic Energy Storage Charging Stations Considering Operational Efficiency
Abstract—The operational efficiency of photovoltaic energy storage charging stations affects their economic benefits and grid-side power quality. To address the problem of non-essential losses due to insufficient consideration of operational efficiency ...
Research on Commutation Failure Suppression and Coordinated Restoration Strategy Based on the Interaction Characteristics of Multiple DC Feed-Ins and Feed-Outs
Interactive characteristics exist in multi-DC (multi-infeed-multi-outlet) transmission system at both the sending and the receiving end, coupling effect between transmission lines is further strengthened on the basis of the traditional multi-infeed ...
A Vector-fitting-based Impedance Reshaping Method for Sub-synchronous Oscillation Suppression in Converter-dominated System
In this paper, a vector-fitting-based impedance reshaping method for sub-synchronous oscillation suppression in a converter-dominated system is proposed to enhance system damping. In this method, an impedance network model is first established based on ...
A microgrid power trading framework based on blockchain and deep reinforcement learning
With the development of renewable energy technologies and the emergence of distributed power generation devices, traditional centralized power trading markets no longer meet people's transactional needs. Peer-to-peer (P2P) electricity trading within ...
Index Terms
- Proceedings of the 2023 4th International Conference on Control, Robotics and Intelligent System