检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wei, Bingcai Liu, Hui Qian, Chuang Jia, Yi Wu, Wangyu Li, Zhishan School of Computer Science Wuhan University Wuhan China GNSS Research Center Wuhan Unicersity Wuhan China Intelligent Transport Systems Research Center Wuhan University of Technology Wuhan China College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin China University of Liverpool Liverpool United Kingdom School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350368741

Stereo image sand removal is crucial to improve the perceptual quality for autonomous driving perception. Existing methods often fall short in accurately estimating the uncertainty inherent in degraded images, leading to suboptimal outcomes. To address this, we introduce a novel framework named Decoupling While Coupling(DWC). DWC pioneers the integration of inter-view uncertainty estimation, cross-view uncertainty-aware interaction and block-wise uncertainty representation for superior stereo image sand removal. For cross-view information interaction, we propose an Uncertainty-aware Cross-view Attentive Interaction module(UCAI) to cope with the lack of uncertainty estimation ability in the existing cross-view information interaction mechanism. For the uncertainty perception and information interaction within the inter-view, we propose a Distribution Modeling Coupling Block(DMCB), which transmits the representation of uncertainty between each backbone module. For block-wise uncertainty estimation, we use our proposed Uncertainty-aware Distribution Feature Modulator(UDFM) as the backbone of DWC to modulate the uncertainty inside the neural network itself. Extensive experimental validations on our proposed stereo image sand removal dataset SandST confirm the efficacy of DWC. Our method not only achieves higher PSNR and SSIM, but also exhibits enhanced robustness against various sand degrees and patterns. © 2025 IEEE.

关键词： Cross-view Inter-view Sand removal Stereo image Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

Control of Multipath Transmissions in the Nodes of Switching Segments of Reserved Paths 6

Control of Multipath Transmissions in the Nodes of Switching...

引用

6th International Scientific Conference on information, Control, and Communication Technologies, ICCT 2022

作者： Bogatyrev, Vladimir A. Bogatyrev, Stanislav V. Bogatyrev, Anatoly V. Saint-Petersburg State University of Aerospace Instrumentation Department Information Systems Security Saint Petersburg Russia Itmo University Faculty of Software Engineering and Computer Systems Saint Petersburg Russia Yadro Cloud Storage Development Center Saint Petersburg Russia

ISBN: (数字)9781665493673

ISBN: (纸本)9781665493673

The options for ensuring timely delivery of packages to the addressee in networks with duplication of communication paths with the addressee for some subscribers are analyzed. Connecting subscribers to two communication routes with the addressee allows you to load-balance routes and carry out duplicated transmissions aimed at increasing the probability of delivering at least one copy of the transmitted packet in the required time. The possibilities of using route switch nodes for traffic management and replication of transmitted packets are analyzed. At the same time, two variants of duplicated transmissions are considered. For the first option, new replicas and ways of their transmission to the addressee are formed in one of the nodes connecting the existing paths by the first accepted replica. The replica coming in second is destroyed. For the second option, changing the transmission paths of replicas generated from the source in the nodes linking the paths is not carried out. The area of effectiveness of the proposed variants of duplicated transmissions is shown. The influence of the location of route switches on the timeliness of package delivery from subscribers connected to one or two communication paths with the addressee is investigated. The existence of an optimal arrangement of route switches is shown. © 2022 IEEE.

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

Long Text Classification Using Pre-trained Language Model for a Low-Resource Language

Long Text Classification Using Pre-trained Language Model fo...

引用

International Conference on information and Computer Technologies (ICICT)

作者： Hailemariam Mehari Yohannes Toshiyuki Amagasa Systems and Information Engineering University of Tsukuba Tsukuba Japan Center of Computational Science University of Tsukuba Tsukuba Japan

Text classification is an essential task of Natural Language Processing (NLP) that intends to classify texts into predefined classes. Most recent studies show that transformer-based pre-trained language models such as BERT and RoBERTa have achieved state-of-the-art performance in several downstream NLP tasks. Despite their advantages, these models suffer from one primary drawback of the restricted input size. Because of this limitation, they cannot operate the entire input long texts. This paper presents an approach that utilizes the self-attention mechanism to address the bottleneck of most pre-trained language models of long input texts in the case of Amharic, regarded as a low-resourced language. Specifically, our method carefully investigates the significance of each word in the dataset using a self-attention mechanism. Then identify and select the most relevant words according to their attention scores. Finally, we train our model on the filtered text. Our results show that the approach achieves better performance in terms of accuracy compared to the baseline model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Degradation Detection on Voice Over Internet Protocol (VoIP) Calls Using Deep Learning Techniques

Degradation Detection on Voice Over Internet Protocol (VoIP)...

引用

International Conf on Electrical and Electronic engineering (ICEEE)

作者： Hasan Kilimci H. Hakan Kilinc Zeynep Hilal Kilimci R&D Center Orion Innovation Turkey Istanbul Turkiye Department of Information Systems Engineering Kocaeli University Kocaeli Türkiye

ISBN: (数字)9798350362541

ISBN: (纸本)9798350362558

Degradation in speech on VoIP (Voice over Internet Protocol) refers to any deterioration in the quality of the audio during a VoIP call. This degradation can manifest in various forms, including distortion, delay, jitter, packet loss, echo, background noise, and so on. Detecting degradation in VoIP calls is crucial for the following several reasons such as improving user experience and satisfaction, boosting the effective communication and collaboration, impacting productivity and efficiency, allowing providers to proactively address issues and maintain service quality, helping network administrators to identify the root causes of quality issues and implementing solutions to improve performance and reliability. Overall, detecting degradation in speech on VoIP is essential for ensuring high-quality communication, maintaining customer satisfaction, and optimizing the performance of VoIP systems and networks. In this work, focus on detecting degradations on voice over VoIP using deep learning algorithms, namely, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory Networks (LSTMs). To show the effectiveness of the models, TCD- VoIP dataset is carried out during the experiments. Experiment results demonstrate that the inclusion of deep learning methodologies exhibits remarkable experiment results.

关键词： Degradation Deep learning Recurrent neural networks Packet loss User experience Convolutional neural networks Reliability Internet telephony Long short term memory Optimization

来源：评论

学校读者我要写书评

暂无评论

SuTraN: an Encoder-Decoder Transformer for Full-Context-Aware Suffix Prediction of Business Processes

SuTraN: an Encoder-Decoder Transformer for Full-Context-Awar...

引用

International Conference on Process Mining (ICPM)

作者： Brecht Wuyts Seppe Vanden Broucke Jochen De Weerdt Research Center for Information Systems Engineering (LIRIS) KU Leuven Leuven Belgium Department of Business Informatics and Operations Management Ghent University Belgium

ISBN: (数字)9798350365030

ISBN: (纸本)9798350365047

Predictive Process Monitoring (PPM) in Process Mining (PM) uses predictive analytics to forecast business process progression. A key challenge is suffix prediction, forecasting future event sequences with activity labels, timestamps, and remaining runtime. Current techniques often focus on one-step-ahead predictions, rely on iterative feedback loops for suffix generation, and underutilize payload data. Additionally, many lag behind recent advancements in model architectures, sticking to LSTM-based models. Addressing these gaps, we propose SuTraN, a novel transformer architecture for PPM suffix prediction. SuTraN avoids iterative prediction loops and utilizes all available data, including event features, to forecast entire event suffixes in a single forward pass. Our approach integrates autoregressive suffix generation, data awareness, and seq2seq learning. Experimental results on real-life event logs demonstrate SuTraN’s superior performance in suffix prediction, highlighting its contributions often overlooked in current research.

关键词： Process mining Process monitoring Feedback loop Runtime Transformers Iterative methods Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Temporal Phase Characterization of Picosecond Pulsed Squeezed Vacuum

Temporal Phase Characterization of Picosecond Pulsed Squeeze...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Zicong Xu Sho Nitanai Yasuyuki Ozeki Research Center of Advanced Science and Technology The University of Tokyo Tokyo Japan Department of Electrical Engineering and Information Systems The University of Tokyo Tokyo Japan

We propose a method to measure the temporal phase of ultrashort pulsed squeezed vacuum. We verified that the temporal chirp has limited influence on pulsed squeezing level.

ISBN: (纸本)9798350369311

We propose a method to measure the temporal phase of ultrashort pulsed squeezed vacuum. We verified that the temporal chirp has limited influence on pulsed squeezing level.

关键词： Vacuum systems Phase measurement Chirp Pulse measurements Lasers and electrooptics Optical pulse generation Laser applications Electro-optical waveguides Optical fiber dispersion Fiber lasers

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV Collaborative Reconnaissance Based on Multi Agent Deep Reinforcement Learning

Multi-UAV Collaborative Reconnaissance Based on Multi Agent ...

引用

International Conference on Big Data and information Analytics (BigDIA)

作者： Xiao Feng Ru Gao Fujie Tang Jianjun Luo National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha China Jiuquan Satellite Launch Center Jiuquan China

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

In this paper, we explore a multi-agent reinforcement learning(MARL) method for the collaborative reconnaissance of unmanned aerial vehicles (UAVs). Most UAVs still use programmed control to perform reconnaissance tasks, and fully autonomous intelligent collaborative reconnaissance based on environmental conditions has not yet been achieved. To enable each drone to autonomously plan and cooperate with each other to complete dynamic target reconnaissance based on changing environmental conditions and target positions, we designed a multi-agent deep reinforcement learning algorithm for the collaborative reconnaissance of UAVs based on the multi-agent deep deterministic policy gradient (MADDPG). It adopts a centralized training and distributed execution strategy, where each drone uses its own Actor-Critic network to select and execute actions and then makes corresponding evaluations. Due to the many shortcomings of the original MADDPG algorithm, it is difficult to directly and effectively apply it to environments with a large number of intelligent agents and dynamic changes. Therefore, we have made several improvements to the original MADDPG algorithm, including the introduction of residual networks and parameter sharing, the implementation of entropy regularization exploration strategies, and the design of clear communication mechanisms. Simulation experiments have verified that our proposed improved algorithm can effectively achieve coordinated reconnaissance of UAVs and perform reconnaissance tasks without basic collisions. Compared with the original MADDPG algorithm, the simulation results show that the learning efficiency of our improved algorithm is significantly enhanced, and the reconnaissance effectiveness of UAVs is further improved.

关键词： Adaptation models Heuristic algorithms Collaboration Reconnaissance Deep reinforcement learning Computational efficiency Vehicle dynamics Optimization Residual neural networks Drones

来源：评论

学校读者我要写书评

暂无评论

Reliability and Timeliness of Servicing Requests in Infocommunication systems, Taking into Account the Physical and information Recovery of Redundant Storage Devices 6

Reliability and Timeliness of Servicing Requests in Infocomm...

引用

6th International Scientific Conference on information, Control, and Communication Technologies, ICCT 2022

ISBN: (数字)9781665493673

ISBN: (纸本)9781665493673

Markov models of reliability of fault-tolerant computer systems are proposed, taking into account two stages of recovery of redundant memory devices. At the first stage, the physical recovery of memory devices is implemented, and at the second, the informational one consists in entering the data necessary to perform the required functions. Memory redundancy is carried out to increase the stability of the system to the loss of unique data generated during the operation of the system. Data replication is implemented in all functional memory devices. information recovery is carried out using replicas of data stored in working memory devices. The model takes into account the criticality of the system to the timeliness of calculations in real time and to the impossibility of restoring information after multiple memory failures, leading to the loss of all stored replicas of unique data. The system readiness coefficient and the probability of its transition to a non-recoverable state are determined. The readiness of the system for the timely execution of requests is evaluated, taking into account the influence of the shares of the distribution of the performance of the computer allocated for the maintenance of requests and for the entry of information into memory after its physical recovery. © 2022 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Prior-based Objective Inference Mining Potential Uncertainty for Facial Expression Recognition

arXiv

引用

arXiv 2024年

作者： Liu, Hanwei Cai, Huiling Lin, Qingcheng Li, Xuefeng Xiao, Hui College of Electronics and Information Engineering Tongji University Shanghai201804 China Frontiers Science Center for Intelligent Autonomous Systems Tongji University China

Annotation ambiguity caused by the inherent subjectivity of visual judgment has always been a major challenge for Facial Expression Recognition (FER) tasks, particularly for large-scale datasets from in-the-wild scenarios. A potential solution is the evaluation of relatively objective emotional distributions to help mitigate the ambiguity of subjective annotations. To this end, this paper proposes a novel Prior-based Objective Inference (POI) network. This network employs prior knowledge to derive a more objective and varied emotional distribution and tackles the issue of subjective annotation ambiguity through dynamic knowledge transfer. POI comprises two key networks: Firstly, the Prior Inference Network (PIN) utilizes the prior knowledge of AUs and emotions to capture intricate motion details. To reduce over-reliance on priors and facilitate objective emotional inference, PIN aggregates inferential knowledge from various key facial subregions, encouraging mutual learning. Secondly, the Target Recognition Network (TRN) integrates subjective emotion annotations and objective inference soft labels provided by the PIN, fostering an understanding of inherent facial expression diversity, thus resolving annotation ambiguity. Moreover, we introduce an uncertainty estimation module to quantify and balance facial expression confidence. This module enables a flexible approach to dealing with the uncertainties of subjective annotations. Extensive experiments show that POI exhibits competitive performance on both synthetic noisy datasets and multiple real-world datasets. All codes and training logs will be publicly available at https://***/liuhw01/POI. © 2024, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Feedforward with Acceleration and Snap using Sampled-Data Differentiator for a Multi-Modal Motion System

引用

IFAC-PapersOnLine 2022年第37期55卷 253-258页

作者： Masahiro Mae Max van Haren Wataru Ohnishi Tom Oomen Hiroshi Fujimoto Department of Electrical Engineering and Information Systems Graduate School of Engineering The University of Tokyo Japan Department of Mechanical Engineering Eindhoven University of Technology The Netherlands Delft Center for Systems and Control Delft University of Technology The Netherlands

Sampled-data control requires both on-sample and intersample performance in high-precision mechatronic systems. The aim is to design a discrete-time linearly parameterized feedforward controller to improve both on-sample and intersample performance in a multi-modal motion system. The continuous-time performance is considered as state compatibility by a multirate zero-order-hold differentiator. The developed approach enables the linearly parameterized feedforward controller design for sampled-data systems with physically intuitive tuning parameters. The performance improvement is validated by comparing the developed approach with a conventional approach using a backward differentiator for a multi-modal motion system.

关键词： feedforward discrete-time system sampled-data control zero-order-hold multirate

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：